docs: INSTALL.ru.md — наша эксплуатация, источники версий и порядок обновления

What the first Linux CI run of the 1.6 tree found.

- fastmcp 3's enable()/disable() append a Visibility transform per call,
  and a tool lookup walks the transform stack as nested calls. The
  lifespan re-applies the tool profile on every client connection, so an
  in-process server grew two layers per session until every tool call,
  system_status included, raised RecursionError (CPython 3.11 counts C
  frames against the limit). The profile's transforms now replace the
  previous ones, as _apply_discovery_mode already did; a test switches
  the profile 600 times and then calls a tool. The local suite runs in
  half the time it took with the stack growing.
- 21 fake-ActiveX tests build a real pywin32 VARIANT; they now skip
  without pywin32, like the suite's other VARIANT-dependent COM tests,
  and the Windows lane keeps running them.
- A test spelled a path through a directory it never created, which only
  Windows normalises away; it creates the directory.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01FKFStjEFzpGyLq5bMpWxTd

.env.example

@@ -1,15 +1,45 @@
 # AutoCAD MCP Pro — Environment Variables
 
+# Rendering (view_screenshot / drawing_export_pdf) is an install-time choice,
+# not an env var — the core install cannot render at all. ezdxf's drawing
+# add-on imports Pillow unconditionally, so every render path needs it:
+#   pip install "autocad-mcp-pro[pdf]"   ezdxf backend, matplotlib renderer
+#                                        (also pulls Pillow in transitively)
+#   pip install "autocad-mcp-pro[com]"   live AutoCAD Win32 window capture
+#   pip install "autocad-mcp-pro[full]"  both
+# With only [com] the ezdxf backend still cannot render (no matplotlib).
+
 # Backend selection: auto | com | ezdxf
 AUTOCAD_MCP_BACKEND=auto
 
+# COM ProgID the live backend attaches to. Escape hatch for AutoCAD-compatible
+# applications that expose the same ActiveX object model.
+#
+# CAD_PROGID only changes which COM application the backend attaches to — every
+# tool beyond the connection itself is developed and tested against AutoCAD
+# alone, and AutoCAD-clone compatibility is unverified, so treat a non-default
+# ProgID as experimental. An unrecognised ProgID fails loudly rather than
+# falling back to AutoCAD, because the fallback would launch the very
+# application you said you were not using.
+#
+# Candidates below are UNVERIFIED — none was tested against a running seat.
+# List what is actually registered on your machine with:
+#   Get-ChildItem Registry::HKEY_CLASSES_ROOT |
+#     Where-Object { $_.PSChildName -like '*.Application*' } |
+#     Select-Object -Expand PSChildName
+# CAD_PROGID=BricscadApp.AcadApplication   # UNVERIFIED
+# CAD_PROGID=ZWCAD.Application             # UNVERIFIED
+# CAD_PROGID=GstarCAD.Application          # UNVERIFIED
+CAD_PROGID=AutoCAD.Application
+
 # Comma-separated list of allowed directories for file operations.
 # Leave empty to allow all paths (not recommended for production).
 # Example: ALLOWED_PATHS=C:\Drawings,D:\Projects\CAD
 ALLOWED_PATHS=
 
-# Maximum undo stack size (number of snapshots to keep)
-MAX_UNDO_STACK=50
+# Maximum undo stack size (number of snapshots to keep). The code's default is
+# 5; this file used to say 50, which was a documentation-only disagreement.
+MAX_UNDO_STACK=5
 
 # Logging level: DEBUG | INFO | WARNING | ERROR
 LOG_LEVEL=INFO
@@ -17,3 +47,52 @@ LOG_LEVEL=INFO
 # Enable dangerous AutoCAD commands (ERASE ALL, QUIT, etc.)
 # Set to true only if you trust all MCP clients
 DANGEROUS_COMMANDS_ENABLED=false
+
+# Exposed tool profile: full (default) | lean
+# lean is a curated ~47-tool drafting/inspection set for clients with tight
+# tool caps. The "core" profile was removed in v1.5.0 — the discovery layer
+# below solves the crowded-surface problem it existed for. TOOL_PROFILE=core
+# still boots, falling back to full with a warning.
+TOOL_PROFILE=full
+
+# Tool packs: all (default) | comma list of core,pid,settings — advertise only the
+# vertical packs this client uses. core is always on.
+TOOL_PACKS=all
+
+# Tool discovery: off (default) | search
+# "search" replaces the advertised catalog with search_tools + call_tool, so a
+# client sees two tools instead of ~126 and searches by AutoCAD command name
+# ("QSELECT") or plain English ("round off this corner").
+DISCOVERY_MODE=off
+
+# Per-call backend timeouts in seconds; 0 disables the check.
+# A hung call would otherwise hold the backend lock forever.
+COM_CALL_TIMEOUT=60
+EZDXF_CALL_TIMEOUT=120
+
+# Undo/redo history for the headless backend, in steps. 0 disables it.
+# Not free: ezdxf has no journal, so each step is a full DXF snapshot.
+# Measured 37x slower entity creation with it on (0.18 -> 6.65 ms/call),
+# and a snapshot of a 5000-entity drawing costs 130 ms / 658 KB. For a
+# single checkpoint use transaction_begin/rollback instead.
+# The live COM backend uses AutoCAD's own undo and ignores this.
+EZDXF_UNDO_DEPTH=0
+
+# Opt-in 3D solids (COM backend only; ezdxf reports them as unsupported)
+ENABLE_3D=false
+
+# --- Limits and remote access -------------------------------------------------
+# These four are read by config.py but were missing from this file, which made
+# it look like the complete list. Two of them are the remote-HTTP controls.
+
+# Reject DXF input larger than this many bytes (512 MB). 0 disables the check.
+MAX_DXF_BYTES=536870912
+
+# Upper bound on list/selection response sizes.
+MAX_LIST_LIMIT=5000
+
+# Permit a non-loopback HTTP bind. Requires MCP_AUTH_TOKEN as well.
+ALLOW_REMOTE_HTTP=false
+
+# Bearer token required for remote HTTP. No default; remote binds refuse without it.
+MCP_AUTH_TOKEN=

.gitattributes

@@ -1,2 +1,6 @@
 # Auto detect text files and perform LF normalization
 * text=auto
+templates/*.dxf text eol=crlf
+templates/*.dwt binary
+*.dwt binary
+*.dwg binary

.github/workflows/benchmark.yml

@@ -0,0 +1,53 @@
+name: Benchmark
+
+# Headless competitor benchmark (v2 fixed-task matrix). Manual or weekly:
+# clones the pinned competitor SHAs, runs the black-box MCP stdio lane and
+# uploads the machine-readable reports as artifacts. Results committed to
+# benchmarks/results/ are produced from these runs.
+
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: "17 5 * * 1"
+
+env:
+  # Keep in step with ci.yml; all three workflows read the same uv.lock.
+  LOCKED_UV_VERSION: "0.12.1"
+
+jobs:
+  headless-matrix:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        server:
+          - autocad-mcp-pro
+          - puran-water-autocad-mcp
+          - beiming183-autocad-mcp
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        id: python
+        with:
+          python-version: "3.12"
+      - run: pip install "uv==${{ env.LOCKED_UV_VERSION }}"
+      - name: Install the locked harness environment
+        # This lane publishes evidence, so the harness must not float: an ezdxf
+        # release would otherwise move our own numbers between runs and the
+        # diff would be unattributable. Competitors keep their own pinned
+        # checkouts and venvs (benchmarks/competitors_env.py) either way.
+        run: uv sync --locked --extra pdf --python "${{ steps.python.outputs.python-path }}"
+      - name: Run benchmark (ezdxf lane)
+        run: |
+          uv run --no-sync python -m benchmarks.run_competitors \
+            --server "${{ matrix.server }}" \
+            --backend ezdxf \
+            --artifact-dir "benchmarks/results/ci/${{ matrix.server }}" \
+            > "report-${{ matrix.server }}.json"
+      - name: Upload report
+        uses: actions/upload-artifact@v4
+        with:
+          name: benchmark-${{ matrix.server }}
+          path: |
+            report-${{ matrix.server }}.json
+            benchmarks/results/ci/${{ matrix.server }}

.github/workflows/ci.yml

@@ -0,0 +1,140 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+  workflow_dispatch:
+
+concurrency:
+  group: ci-${{ github.ref }}
+  cancel-in-progress: true
+
+# Two deliberately different installation paths run in this file:
+#
+#   lint / test-*  install from uv.lock with `--locked`. Every version, down to
+#                  the transitive graph, is the one the suite was last run
+#                  against; `--locked` *fails* rather than re-resolving if
+#                  uv.lock has drifted from pyproject.toml. A release upstream
+#                  can no longer turn main red on its own schedule.
+#   package        installs the built wheel with plain pip, from the dependency
+#                  ranges in pyproject.toml — on purpose. That is the path a
+#                  user gets from PyPI, and it is the only job that exercises
+#                  it, so it must not be locked.
+#
+# Locked CI is blind to upstream drift by construction; deps-floating.yml is the
+# deliberate counterweight that resolves the ranges fresh on a schedule.
+env:
+  # Pinned for the same reason ruff is: the tool that reads the lockfile is part
+  # of the reproducible environment. Bump this and re-run `uv lock` together.
+  LOCKED_UV_VERSION: "0.12.1"
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+      - run: pip install "uv==${{ env.LOCKED_UV_VERSION }}"
+      # Dev group only: ruff comes from the lock, the project is not built.
+      # The ruff version lives in [dependency-groups] dev in pyproject.toml and
+      # nowhere else — the formatter's output changes between minors, so a
+      # floating ruff fails `ruff format --check .` on unchanged code.
+      - run: uv sync --locked --only-group dev
+      - run: uv run --no-sync ruff check .
+      - run: uv run --no-sync ruff format --check .
+
+  test-linux:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.11", "3.12"]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        id: python
+        with:
+          python-version: ${{ matrix.python-version }}
+      - run: pip install "uv==${{ env.LOCKED_UV_VERSION }}"
+      - name: Install the locked environment
+        # uv.lock is a universal resolution over requires-python >=3.11, so the
+        # same file serves both matrix legs; --python keeps uv on the
+        # interpreter setup-python just provisioned instead of picking its own.
+        run: uv sync --locked --extra pdf --python "${{ steps.python.outputs.python-path }}"
+      - name: Run tests
+        run: uv run --no-sync pytest --cov=. --cov-report=xml --cov-report=term-missing -v
+      - name: Upload coverage
+        if: matrix.python-version == '3.11'
+        uses: actions/upload-artifact@v4
+        with:
+          name: coverage-report
+          path: coverage.xml
+
+  test-windows:
+    # Windows leg exercises the mocked-COM suite on the platform the COM
+    # backend actually targets (pywin32 installs; no live AutoCAD needed).
+    runs-on: windows-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        id: python
+        with:
+          python-version: "3.11"
+      - run: pip install "uv==${{ env.LOCKED_UV_VERSION }}"
+      - name: Install the locked environment
+        run: uv sync --locked --extra full --python "${{ steps.python.outputs.python-path }}"
+      - name: Run tests
+        run: uv run --no-sync pytest -v
+
+  package:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+      - name: Build sdist and wheel
+        run: |
+          pip install build twine
+          python -m build
+          twine check dist/*
+      # Unlocked on purpose: this resolves the published dependency ranges the
+      # way a user's `pip install autocad-mcp-pro` does. Locking it would mean
+      # nothing in CI ever proves those ranges are installable.
+      - name: Install wheel in a clean venv and smoke test
+        run: |
+          python -m venv /tmp/smoke
+          /tmp/smoke/bin/pip install dist/*.whl
+          /tmp/smoke/bin/autocad-mcp --help
+          /tmp/smoke/bin/python -c "import server, config, security, version, backends, engineering; print('wheel ok', version.__version__)"
+      - name: Upload distributions
+        uses: actions/upload-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+  docker:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Build image
+        run: docker build -t autocad-mcp:ci .
+      - name: Smoke test image
+        run: docker run --rm autocad-mcp:ci python -c "import server, engineering.gear, version; print('docker ok', version.__version__)"
+
+  registry-validate:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+      - name: Validate server.json against MCP registry schema
+        if: ${{ hashFiles('server.json') != '' }}
+        run: |
+          pip install check-jsonschema
+          check-jsonschema --schemafile https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json server.json

.github/workflows/deps-floating.yml

@@ -0,0 +1,47 @@
+name: Floating deps
+
+# The counterweight to a locked CI.
+#
+# ci.yml installs from uv.lock, so a PR can never be broken by an upstream
+# release. That is the point — and it is also a blind spot: a new fastmcp,
+# ezdxf or pydantic inside the ranges declared in pyproject.toml would go
+# unnoticed here until a user hit it, because the only unlocked job in CI
+# (`package`) merely imports the wheel and never runs the suite.
+#
+# This job is the deliberate opposite: resolve the declared ranges fresh and
+# run the full suite against whatever the index serves today. It runs on a
+# schedule and on demand only, so it never gates a pull request — a red run
+# here means "the ceiling needs a look", not "your change is broken".
+#
+# Lint is intentionally absent: ruff's formatter output moves between minors,
+# so a floating ruff would fail on unchanged source and say nothing about the
+# runtime dependencies this job exists to watch.
+
+on:
+  schedule:
+    # Mondays, 06:17 UTC. Off the hour so it does not queue behind the
+    # every-cron-on-the-hour crowd.
+    - cron: "17 6 * * 1"
+  workflow_dispatch:
+
+jobs:
+  floating:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.11", "3.12"]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install from the declared ranges (uv.lock deliberately ignored)
+        run: |
+          pip install -e ".[pdf]"
+          pip install pytest pytest-asyncio
+      - name: Record what actually resolved
+        # Printed unconditionally: when this job fails, the version list is the
+        # first thing needed to tell which upstream moved.
+        run: pip list
+      - run: pytest -q

.github/workflows/release.yml

@@ -0,0 +1,115 @@
+name: Release
+
+# Tag-driven release: run the test gate, build, publish to PyPI, then cut the
+# GitHub Release with the built artifacts attached.
+#
+# Auth: the PYPI_API_TOKEN repository secret (an API token from
+# https://pypi.org/manage/account/token/). Once the project exists on PyPI,
+# prefer replacing it with a project-scoped token — or switch back to trusted
+# publishing (OIDC) by restoring `environment: pypi` + `id-token: write` and
+# registering the publisher on PyPI.
+
+on:
+  push:
+    tags: ["v*"]
+
+env:
+  # Keep in step with ci.yml; both read the same uv.lock.
+  LOCKED_UV_VERSION: "0.12.1"
+
+jobs:
+  test:
+    # The same three lanes as ci.yml, not one. This job was a single
+    # ubuntu/3.11 run, so a Windows-only defect could reach PyPI without any
+    # Windows job having executed -- which is not hypothetical: v1.5.0 shipped
+    # with `except pywintypes.com_error` raising NameError wherever pywin32 is
+    # absent, and only the Linux legs of ci.yml caught it.
+    strategy:
+      fail-fast: true
+      matrix:
+        include:
+          - os: ubuntu-latest
+            python-version: "3.11"
+            extra: pdf
+          - os: ubuntu-latest
+            python-version: "3.12"
+            extra: pdf
+          - os: windows-latest
+            python-version: "3.11"
+            extra: full
+    runs-on: ${{ matrix.os }}
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        id: python
+        with:
+          python-version: ${{ matrix.python-version }}
+      - run: pip install "uv==${{ env.LOCKED_UV_VERSION }}"
+      - name: Install the locked environment
+        # `--locked` refuses to re-resolve, so the artifact that goes to PyPI is
+        # gated by the exact dependency set the suite was run against — not by
+        # whatever the index happens to serve at tag time. ruff's version comes
+        # from [dependency-groups] dev via the lock; it is not restated here.
+        run: uv sync --locked --extra ${{ matrix.extra }} --python "${{ steps.python.outputs.python-path }}"
+      - run: uv run --no-sync ruff check .
+      - run: uv run --no-sync ruff format --check .
+      - run: uv run --no-sync pytest -q
+
+  build:
+    needs: test
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+      - name: Verify tag matches package version
+        run: |
+          pip install tomli-w 2>/dev/null || true
+          PKG_VERSION=$(python -c "import tomllib; print(tomllib.load(open('pyproject.toml','rb'))['project']['version'])")
+          TAG_VERSION="${GITHUB_REF_NAME#v}"
+          if [ "$PKG_VERSION" != "$TAG_VERSION" ]; then
+            echo "Tag $GITHUB_REF_NAME does not match pyproject version $PKG_VERSION" >&2
+            exit 1
+          fi
+      - name: Build distributions
+        run: |
+          pip install build twine
+          python -m build
+          twine check dist/*
+      - uses: actions/upload-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+  publish-pypi:
+    needs: build
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist/
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          password: ${{ secrets.PYPI_API_TOKEN }}
+
+  github-release:
+    needs: publish-pypi
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist/
+      - name: Create GitHub Release
+        env:
+          GH_TOKEN: ${{ github.token }}
+        run: |
+          gh release create "$GITHUB_REF_NAME" dist/* \
+            --title "$GITHUB_REF_NAME" \
+            --generate-notes

.gitignore

@@ -43,6 +43,24 @@ desktop.ini
 out/
 benchmarks/results/*
 !benchmarks/results/.gitkeep
+!benchmarks/results/published
+!benchmarks/results/published/**
+benchmarks/.competitors/
 *.dxf
+# The bundled templates are the one committed DXF set: built by
+# scripts/build_templates.py and pinned reproducible by its --check.
+!templates/*.dxf
 *.dwg
 *.bak
+
+# Local editor/agent state
+.cursor/
+
+# NOTE: uv.lock is deliberately *not* ignored. It used to be — back when the
+# committed one was stale and unvetted — but CI now installs from it with
+# `uv sync --locked`, so ignoring it would silently disarm every locked lane.
+# Regenerate with `uv lock` whenever pyproject.toml dependencies change.
+
+# AutoCAD writes its plot-and-publish log into the cwd of the plotting process
+# (scripts/smoke_settings_com.py plots from the repo root).
+plot.log

.pre-commit-config.yaml

@@ -1,6 +1,11 @@
+# The ruff version here MUST equal the `ruff==` pin in pyproject.toml's
+# [dependency-groups] dev. It was v0.8.6 against a project pin of 0.16.1, and
+# ruff 0.16 formats Python inside Markdown while 0.8 does not -- so anyone who
+# ran `pre-commit install` produced commits that failed CI's
+# `ruff format --check .`. tests/test_release_consistency.py pins them equal.
 repos:
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.8.6
+    rev: v0.16.1
     hooks:
       - id: ruff
         args: [--fix]

CLAUDE.md

@@ -4,7 +4,7 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 
 ## Project Overview
 
-AutoCAD MCP Pro is a FastMCP 3.0 server that exposes ~110 tools, 5 resources, and 5 prompt templates for AutoCAD automation. (The exact tool count is reported dynamically by `system_status` / `system_about` — never hardcode it.) It runs with a dual-engine architecture: a live COM backend (Windows/AutoCAD required) and a headless ezdxf backend (works anywhere).
+AutoCAD MCP Pro is a FastMCP 3.0 server that exposes ~247 tools, 8 resources, and 5 prompt templates for AutoCAD automation. (The exact tool count is reported dynamically by `system_status` / `system_about` — never hardcode it.) It runs with a dual-engine architecture: a live COM backend (Windows/AutoCAD required) and a headless ezdxf backend (works anywhere).
 
 ## Running the Server
 
@@ -33,6 +33,9 @@ pip install -e ".[com]"
 # With PDF/screenshot support via matplotlib
 pip install -e ".[pdf]"
 
+# XLSX workbooks (takeoffs, data_extract) via openpyxl
+pip install -e ".[office]"
+
 # Everything
 pip install -e ".[full]"
 ```
@@ -53,7 +56,9 @@ Uses `pytest-asyncio` for async test support.
 
 The server uses a strategy pattern with an abstract base:
 
-- `backends/base.py` — `AutoCADBackend` ABC defining the full interface + shared dataclasses (`EntityInfo`, `LayerInfo`, `BlockInfo`, `DrawingInfo`)
+- `backends/contracts/` — the interface, one module per domain (`drawing.py`, `layouts.py`, `entity_creation.py`, …). Split in v1.5.0 out of a single 1854-line ABC; some slices (premium, gdt, settings) also carry shared *concrete* implementations, so they are mixins rather than pure interfaces.
+- `backends/capability.py` — the refusal vocabulary (`UnsupportedCapabilityError`) plus `@capability(key, reason=...)`, which marks a contract method optional and gives it a default that **raises** that refusal. Use it only for genuine engine boundaries, never for an unfinished method; `@abstractmethod` stays the default. Every key used must be declared in *both* capability maps — `tests/test_capability_contract.py` fails otherwise, which is what stops the decorator becoming a way to ship undeclared holes.
+- `backends/base.py` — shared dataclasses (`EntityInfo`, `LayerInfo`, `BlockInfo`, `DrawingInfo`, `CapabilityMap`) and the `AutoCADBackend` composition of every contract. Import surface is unchanged: `from backends.base import AutoCADBackend, UnsupportedCapabilityError` still works.
 - `backends/ezdxf_backend.py` — `EzdxfBackend`: file-based DXF operations using the `ezdxf` library. All sync ezdxf calls are wrapped with `asyncio.to_thread` via `_async()`. Transactions are implemented as full DXF snapshots on an `_undo_stack`.
 - `backends/com_backend.py` — `ComBackend`: live AutoCAD control via `pywin32` COM. All COM calls are routed through a `ThreadPoolExecutor` with a single thread to satisfy AutoCAD's STA (Single-Threaded Apartment) COM requirement.
 
@@ -69,29 +74,54 @@ The `mcp` FastMCP instance is configured with:
 - **Middleware stack**: `ErrorHandlingMiddleware` → `AuditMiddleware` (custom timing/audit log) → `TimingMiddleware` → `LoggingMiddleware`
 - **`_backend(ctx)`** helper: retrieves the backend from lifespan context, raises `ToolError` if not ready
 
-Tools are organized into 12 sections:
-1. Drawing Management (11 tools): `drawing_*`
-2. Entity Creation (13 tools): `entity_create_*`
+Tools are organized into sections (counts are indicative — `system_about` is authoritative):
+1. Drawing Management (12 tools): `drawing_*` (includes `drawing_redo`)
+2. Entity Creation (14 tools): `entity_create_*` (includes `entity_create_table`, `leader_create_mleader`)
 3. Dimensions (5 tools): `dimension_*`
-4. Entity Modification (12 tools): `entity_move/copy/rotate/scale/mirror/offset/delete/array_*`, plus in-place `entity_edit_text` (TEXT/MTEXT content/height/rotation) and `entity_edit_geometry` (CIRCLE/LINE/ARC — center/radius/endpoints/angles), both handle-preserving
-5. Entity Query (3 tools): `entity_get`, `entity_list`, `entity_delete_many`
-6. Layer Management (12 tools + 2 linetype_*): `layer_*`, `linetype_list`, `linetype_load`
-7. Block Operations (7 tools): `block_*`
-8. Analysis & Query (8 tools): `analysis_*`
-9. View & Screenshot (5 tools — includes `view_zoom_and_screenshot`): `view_*`
+4. Entity Modification (16 tools): `entity_move/copy/rotate/scale/mirror/offset/delete/array_*`, corner ops (`entity_trim/extend/fillet/chamfer`), plus in-place `entity_edit_text` (TEXT/MTEXT content/height/rotation) and `entity_edit_geometry` (CIRCLE/LINE/ARC — center/radius/endpoints/angles), both handle-preserving
+5. Entity Query (9 tools): `entity_get`, `entity_list`, `entity_delete_many`, `selection_get`, `selection_window/polygon/filter`, and `entity_get_xdata` / `entity_set_xdata` (typed by group code)
+6. Layer Management (14 tools incl. 2 linetype_*): `layer_*`, `linetype_list`, `linetype_load`
+7. Block Operations (8 tools): `block_*` — includes `block_define` (a block from typed primitive specs + ATTDEFs, no source entities needed)
+8. Analysis & Query (8 tools): `analysis_*` — plus Batch (2), Templates (2), Validation (1)
+9. View & Screenshot (4 tools — includes `view_zoom_and_screenshot`): `view_*`
 10. Transactions (3 tools): `transaction_begin/commit/rollback`
-11. System (7 tools): `system_status/get_variable/set_variable/run_command/run_lisp/about`, plus `drawing_settings` (friendly units/scale/precision/osnap facade over system variables)
-12. Engineering / Deterministic CAD (7 tools): `gear_draw_*`, `keyway_draw_*`, `titleblock_apply_iso_a3`, `drawing_finalize`
-13. Premium meta-tools: `drawing_plan`, `drawing_critique`, `point_from_snap/intersection/tangent`, `construction_*`, `drawing_apply_iso_layers`, `dimension_auto`, `entity_select_smart`
+11. System (8 tools): `system_status/get_variable/set_variable/run_command/run_lisp/about/capabilities`, plus `drawing_settings` (friendly units/scale/precision/osnap facade over system variables; the facade now also covers limits, grid/snap/ortho/polar, PSLTSCALE, annotation scale (`"1:50"`), linear/angular unit formats and the current dimstyle/textstyle, with unknown keys refused and every key reported on read)
+12. Engineering / Deterministic CAD (8 tools): `gear_draw_*`, `keyway_draw_*`, `titleblock_apply_iso_a3`, `drawing_finalize`
+13. Premium meta-tools (12): `drawing_preflight`, `drawing_plan`, `drawing_critique`, `drawing_refine`, `drawing_deliver`, `point_from_snap/intersection/tangent`, `construction_*`, `drawing_apply_iso_layers`, `dimension_auto`, `entity_select_smart`
 14. GD&T (ISO 1101 / ASME Y14.5): `gd_frame` (feature control frames), `datum_feature` — enforced by the `gdt` critique focus
+15. Layouts & Paper Space (12 tools): tab lifecycle `layout_list/create/set_current/delete/rename/copy`, viewports `viewport_create/list/set_scale/lock/delete`, and `entity_change_space` (CHSPACE — tagged `layout` *and* `modify`, and `layout` wins the group priority, so it files here). `drawing_export_pdf` takes an optional `layout` param and **does** project model content through viewports on both engines (`viewport_render` — v1.4 declared this COM-only and was wrong; the headless renderer only omits the viewport borders). `entity_change_space` is the mirror case — ezdxf-only (`chspace`), because ActiveX exposes no change-space member and the COM route is unverified.
+16. 3D Solids (5 tools, opt-in via `ENABLE_3D=true`, COM only): `solid_box/cylinder/extrude/revolve/boolean` — hidden from discovery and rejected while disabled; ezdxf reports `solid_3d` as unsupported (no headless ACIS).
+17. P&ID (9 tools, pack `pid`): `pid_symbol_list/insert` (ISO 10628-2 + ISA-5.1 catalogue authored in code, real blocks with TAG attributes, named ports, ACADMCP_PID XDATA), `pid_line_draw` (port-to-port orthogonal routing, ISA-5.1 line classes → layer/linetype/marker blocks, line numbers), `pid_tag_parse` (ISA-5.1 grammar), the reader `pid_graph` and its deliverables `pid_instrument_index/line_list/equipment_list`, and `pid_from_spec` (whole sheet, one transaction). Six `pid_*` critique focuses (`pid_dangling_line`, `pid_duplicate_tag`, `pid_incompatible_connection`, `pid_untagged_instrument`, `pid_illegal_tag`, `pid_unconnected_equipment`) run under `focus=None` and inside `drawing_finalize`; they return nothing on a drawing without P&ID nodes. Two resources (`autocad://pid/symbols`, `autocad://standards/isa51`) carry the catalogue and the ISA-5.1 letter tables. Both engines implement every P&ID contract; the COM paths were executed live once by `scripts/smoke_pid_com.py` (AutoCAD 2026).
+18. Styles (10 tools, pack `core`): `dimstyle_list/create/modify/set_current` (authored ISO-25 / ANSI presets from `engineering/standards/dimstyles.py`; `dimstyle_modify` accepts only `DIM_VARIABLE_WHITELIST` names (33) and refuses out-of-range values by name before writing; `changed` lists only variables that moved, and `rerender_required: true` says a headless DIMENSION keeps its rendered block until redrawn), `textstyle_list/create/set_current` (`font_resolved: false` is reported, never refused — DXF stores only the name), `mleaderstyle_list/create` (both engines: ezdxf on `doc.mleader_styles`, live through the `ACAD_MLEADERSTYLE` dictionary — ActiveX has no MLeaderStyle *collection*, which is not an engine boundary, so no `mleaderstyle` capability key exists), and `drawing_apply_standard("iso"|"ansi")` — dimstyle + text style + units + the `mech` layer set in one call, each item reporting `created` or already present.
+19. Page setup & templates (6 tools, pack `core`): `page_setup_list/apply` (ISO 216 / ANSI Y14.1 sizes from `PAPER_SIZES`; an unknown ctb is written and reported `plot_style_known: false`), `plot_style_list` (catalog + the files actually installed on a live seat), `batch_plot` (every paper layout through `drawing_export_pdf(layout=)`; `mediabox_mm` is **read back from the PDF's own `/MediaBox`**, so the sheet size is verified, not assumed), `drawing_template_list` (the five bundled templates: `iso_a3_mech`, `iso_a1_arch`, `iso_a3_pid`, `ansi_b_mech`, `ansi_d_arch` — DXF headless, `.dwt` twin on COM, `scripts/build_templates.py --check` proves the DXFs reproducible), `drawing_template_save` (a `.dwt` request headlessly is refused with capability `dwt_write` naming the DXF route). `drawing_new(template=)` resolves a catalog name to the bundled file and reports `template: {name, source}`.
+20. Environment (22 tools, pack `settings`): documents `document_list/activate/close` (both engines — the headless backend keeps a document registry; `document_close` refuses to discard unsaved work unless `discard=True`), layer states `layer_state_save/restore/list/delete` (portable: JSON chunks in an `ACADMCP_LAYERSTATES` XRECORD that travels with the file and **does not appear in AutoCAD's Layer States Manager** — `system_capabilities.layer_states` says so), named views `view_named_save/restore/list` (headless restore writes `$VIEWCTR/$VIEWSIZE` and reports `applied: "header_only"`), UCS `ucs_list/set/restore` (non-orthogonal axes refused with the measured angle; **tool coordinates stay WCS** — a UCS is stored for the operator, no tool interprets input in it), `system_variable_describe` (the 90-entry `SYSVAR_CATALOG`; an unknown name answers `known: false` plus nearest names, never an error; `system_set_variable` now refuses an out-of-range value for a catalogued name before writing), `drawing_properties_get/set` (custom properties on both engines through `$CUSTOMPROPERTYTAG`; the five summary fields are COM-only, capability `dwgprops`), and the live-only group `system_launch` (`live_application`), `system_preferences_get/set` (`preferences`; a whitelist of `Preferences.*` keys with ranges, read-only keys refused by name, writes report `old`/`new`), `user_pick_point/select`, `system_prompt_message` (`interactive_prompt`; a cancelled pick returns `{cancelled: true}`, a `COM_CALL_TIMEOUT` overrun reports `timed_out`). The COM paths were executed live once by `scripts/smoke_settings_com.py` (AutoCAD 2026), which also built the `.dwt` twins.
+21. Mechanical parts (6 tools, pack `mech`): `mech_part_draw`, `mech_view_add`, `mech_dimension_part`, `mech_hole_pattern`, `mech_part_from_spec`, `mech_part_inspect`. One part model — a profile (`RevolvedPart` segments or a `PrismaticPart` outline) plus typed features — and one view engine that turns it into front / side / top / section / detail views with hidden lines, cut faces and ISO 129 dimensions. The model is written onto the drawing as `ACADMCP_MECH` XDATA, so `mech_view_add` can add a view months later without the caller re-describing the part. A feature that cannot be projected into a view is listed in `omitted: [{feature, reason}]` — never dropped.
+22. Standard parts (3 tools, pack `mech`): `std_part_list`, `std_part_insert`, `std_feature_draw`. ISO 4014 / 4017 / 4032 / 7089 / 4762 fasteners, ISO 15 bearings with ISO 8826-1 representation, DIN 471/472 retaining-ring grooves, DIN 509 undercuts, DIN 332 centre holes and ISO 3601-2 O-ring grooves — authored tables, inserted as real blocks with attributes and `ACADMCP_MECH` XDATA, which is what makes the parts list a *read* of the drawing. A size outside a table's transcribed coverage is refused by name, never interpolated. The four feature tables (DIN 471/472, DIN 509, DIN 332, ISO 3601-2) ship with **no rows** in 1.6: their drawing code and provenance tests exist, every size is refused by name, and filling one is a data edit described in its module docstring.
+23. Mechanical annotation (5 tools, pack `mech`): `surface_texture` (ISO 21920-1, ISO 1302's older Ra form accepted), `weld_symbol` (ISO 2553), `centre_marks` (ISO 128-23), `section_line` (ISO 128-40 — it returns the plane `mech_view_add(kind="section")` consumes, so the label and the view cannot disagree), `hatch_material` (the ISO 128-50 map; an unknown material is refused with the list, never hatched as steel).
+24. Sheet and delivery (11 tools, pack `core`): `sheet_frame` (ISO 5457 A4-A0 — 20 mm filing margin, 10 mm elsewhere on A3, zone grid, centring and trimming marks), `titleblock_apply` (ISO 7200 for every size; `titleblock_apply_iso_a3` is now a thin alias), `revision_add`, `bom_extract` (never modifies the drawing), `bom_table` (ISO 7573), `balloon_add` (ISO 6433, linked by XDATA so a rerun renumbers instead of duplicating), `data_extract` (CSV always; XLSX refused with `xlsx_write` when `openpyxl` is absent), `xref_attach`, `xref_manage`, `image_attach`, `drawing_export_dwg` (COM `SaveAs` natively; headless only with the ODA File Converter, otherwise `dwg_write` refuses and names the install route). The COM paths of SECTIONS 21-24 were executed live once by `scripts/smoke_mech_com.py` (AutoCAD 2026): part, section, dimensions, an ISO 4014 block with its XDATA, the parts list read off the drawing, a linked balloon, an xref attached and detached, a real `.dwg`, and `drawing_critique(focus=None)` clean.
+25. Architecture (12 tools, pack `arch`): `arch_wall`, `arch_opening`, `arch_stair`, `arch_room`, `arch_rooms_detect`, `arch_schedule`, `arch_grid`, `arch_symbol`, `arch_catalogue_list`, `arch_catalogue_insert`, `arch_dimension_chains`, `arch_plan_from_spec`. One plan model — a wall network (axis polyline, thickness, justification, material) with hosted doors and windows — and one engine: L / T / X junctions resolved, openings cut, cut faces hatched by material (`engineering/arch/materials.py`: ISO 128-50 general hatching for brick, the JIS A 0150 RC / stone / wood symbols, AutoCAD's AR-CONC / AR-SAND, AAC as a declared convention), and anything it cannot place listed in `omitted: [{element, reason}]`, never dropped. Rooms are *computed*: a label's area is the planar face its point lies in, and `arch_rooms_detect` reads rooms from any plan (confidence 1.0 for our walls, 0.6 for plain lines) without modifying it. Schedules are a read of the `ACADMCP_ARCH` records, drawn as real TABLEs. Labels and schedules speak English, or Turkish with `lang="tr"` (decimal comma). The COM paths were executed live once by `scripts/smoke_arch_com.py` (AutoCAD 2026).
+26. Understanding & QA (4 tools, pack `core`): `drawing_understand` (one read-only report of a drawing somebody else made — declared vs inferred units with the evidence, declared vs robust extents and the outlier handles behind them, clusters (sheets, plan copies), every layer's likely discipline and service from an EN / TR / RU / NL / DE vocabulary with a confidence and the deciding keyword, equipment tags, rooms, text languages, blocks, layouts, title-block attributes), `drawing_scale_check` (a drawing against a reference: tags unique within a cluster are matched — a tag seen twice is `ambiguous`, never picked — pairs at least 2 m apart, the median ratio, IQR and the share within ±10 %: `to_scale` at 80 % or more, with its factor; `schematic` at 50 % or less; `partly` between), `drawing_diff` (two revisions matched by signature, then handle, then type + layer + nearest position; `markup=True` draws revision clouds on the newer one — its only write) and `drawing_topology_check` (dangling ends, near misses, interior crossings; the three `topo_*` critique focuses run the same engine under `focus=None` on layers no semantic focus covers). Every one reads one snapshot per drawing (`engineering/understand/snapshot.py`: `ezdxf` directly, or on a live seat `Document.Export(<tmp>/snap, "DXF", ...)`, which never renames the document and carries model space, paper space and block definitions — measured).
+27. Plant takeoffs (2 tools, pack `plant`): `pipe_takeoff` (topology from the P&ID — segments merged at their ends, split at T-junctions, continued through inline fittings, a double-drawn segment counted once; service from the layer overridden by supply / return words; sizes kept as drawn — `Ø51`, `SMS51`, `DN20` are never equated — direct, by continuity or `unassigned`; lengths from the layout: the rectilinear MST of the tags a run connects, labelled an estimate, the P&ID length kept beside it as a comparison; statuses A / B / C) and `cable_takeoff` (one row per load: power from the P&ID's electrical texts, never invented; the panel from the layout's `Wiring to CPn` callouts; the Manhattan length plus the allowance rounded up to the metre; a section only from a caller's `section_rules`). Both write a workbook (Metraj / Özet / Kontrol / Metodoloji, `lang` tr / en / ru, XLSX with the `office` extra, CSV always) and never the drawing. `scripts/field_test_takeoff.py` runs both on a user's own pair and writes next to it, never into this repository. The COM paths were executed live once by `scripts/smoke_understand_com.py` (AutoCAD 2026).
+
+**Tool profiles:** `TOOL_PROFILE=lean|full` (default `full`) controls the advertised surface — `lean` = 65 curated drafting tools (55 with `TOOL_PACKS=core`, which drops the three `pid_*`, the three `mech_*` and the four `arch_*` lean members, and keeps `drawing_understand`; the five settings essentials — `drawing_apply_standard`, `dimstyle_set_current`, `textstyle_set_current`, `page_setup_apply`, `batch_plot` — are core-pack tools and stay; including `cad_batch`, since a client with a tight tool cap is exactly the client paying most per turn). Applied in the lifespan; reported by `system_about`. The `core` profile was removed in v1.5.0 (the discovery layer replaced it); `TOOL_PROFILE=core` falls back to `full` with a warning.
+
+**Tool packs:** `TOOL_PACKS=all|core,pid,settings,mech,arch,plant` (default `all`) advertises only the vertical packs a client uses; `core` is always on and is everything no other pack claims; `settings` is the 22 SECTION 20 environment tools, `pid` the nine P&ID tools, `mech` the 14 SECTION 21-23 mechanical tools, `arch` the 12 SECTION 25 architectural tools, `plant` the two SECTION 27 takeoffs (track D's Plant 3D readers join it); SECTION 18/19/24/26 are core; unknown names are ignored with a warning; a `lean` profile intersects with the enabled packs. `system_about` reports `tool_packs`.
+
+**Tool discovery:** `DISCOVERY_MODE=off|search` (default `off`). `search` replaces the advertised catalog with `search_tools` + `call_tool`, ranking hits over an AutoCAD command / synonym corpus (`discovery/aliases.py`) layered on fastmcp's BM25 index.
 
 **ISO 129 tolerances:** `dimension_linear` / `dimension_radius` / `dimension_diameter` take `tol_upper` / `tol_lower` / `tol_mode` (`symmetric` ± / `deviation` +a/-b / `limit` / `basic`) and `text_override` (e.g. `⌀20 H7`). Prefer these over hand-drawn tolerance text.
 
+**ISO 286 fits:** the same dimension tools take `fit="H7"` (mutually exclusive with `tol_*`) — deviations are resolved from authored ISO 286 tables (`engineering/fits.py`; shafts d/e/f/g/h/js/k/m/n/p and interference r/s/t/u, holes D/E/F/G/H/JS and K/M/N/P by the ISO 286 delta rule, sizes 1–500 mm) against the measured nominal and the fit code is appended to the dimension text.
+
 **Drawing score:** `drawing_finalize` returns `payload["score"]` — a 0-100 scalar + `invalidity_ratio` + A-F `grade` over the validator + critique union. Use it as the objective quality metric.
 
+**Measuring:** never read vertices back and shoelace them — that loses 28.2% of the area on a semicircular edge, silently. `analysis_measure_entity(handle)` reads the real geometry, and its payload states its own accuracy: `exact`, `flatten_tolerance`, `assumed_closed`, `self_intersecting`. A HATCH reports the area it *fills* (outer loops minus islands) plus `hatch_style`; on a curved hatch edge `flatten_tolerance` is not the accuracy knob, because ezdxf hands boundaries over as cubic Beziers whose ~0.028% circle error is already baked in. `boundary_trace` / `boundary_from_entities` report the same number `analysis_measure_entity` gives for the polyline they just drew — if those ever diverge, one of them is approximating and neither says so.
+
+**Benchmark matrix:** `benchmarks/tasks_v7.py` is the current set (21 tasks; `--matrix v6` / `v5` / `v4` / `v3` / `v2` reproduce the earlier sets). The published competitor reports are pinned v1.4 runs against v2 and are **never** back-filled for the five v3 tasks, the v4 `pid_roundtrip` / `page_setup_truth`, the v5 `mech_assembly` (a flange-coupling sheet gated on a zero-issue `drawing_critique(focus=None)` and a finalize score of at least 90) or the v6 `arch_roundtrip` (a two-room plan drawn by `arch_plan_from_spec`, its rooms read back by `arch_rooms_detect` within 0.1 % of the label and of the hand-computed net floor, the schedules listing the drawn tags, gated like `mech_assembly`) or the v7 `takeoff_roundtrip` / `understand_foreign` (the synthetic plant pair of `tests/fixtures/plant_pair.py` read without its truth: the P&ID called schematic, every routable run's layout length equal to the rectilinear MST of its tags, the cable metres rounded up after the allowance; units, the outlier, both plan copies and the service layers found by one `describe`) — the chart shows them `not run`, not zero. `benchmarks/correctness_suite.py` (48 checks) is the release A/B gate: `python benchmarks/compare_versions.py v1.5.1` (the published report is `benchmarks/results/published/ab-v1.5.1-vs-v1.6.0.json`; `scripts/check_doc_numbers.py` names it in `AB_REPORT`).
+
 ### Adding a New Tool
 
-1. Add the abstract method to `AutoCADBackend` in `backends/base.py`
+1. Add the method to the matching module in `backends/contracts/` — `@abstractmethod` if both engines must have it, `@capability("key", reason=...)` only if it is a real engine boundary (and then declare `key` in both capability maps, or the gate fails)
 2. Implement it in `EzdxfBackend` (`backends/ezdxf_backend.py`) using the `_async(func)` wrapper
 3. Implement it in `ComBackend` (`backends/com_backend.py`) using `self._com(func)`
 4. Register the tool in `server.py` with `@mcp.tool(...)` calling `_backend(ctx).your_method(...)`
@@ -101,17 +131,43 @@ Tools are organized into 12 sections:
 
 - **Entity handles**: hex strings (e.g. `"1A2B"`). Always returned from create/copy operations; required by all modify/query operations.
 - **Coordinates**: drawing units (mm by default); angles in degrees, counter-clockwise from X axis.
+  **Every coordinate in or out of a tool is WCS on both engines.** DXF stores
+  CIRCLE/ARC/LWPOLYLINE/TEXT/INSERT geometry in a per-entity frame (`extrusion`);
+  `backends/ocs.py` translates at the backend boundary, so OCS never reaches a
+  tool. An entity in a plane tilted out of WCS XY reports `plane_normal` and omits
+  the fields xy cannot express; writing an xy into such an entity is refused with
+  `capability: "ocs_tilted_plane"` — use `entity_move` instead.
 - **ACI colors**: 1–255 for specific colors, 256=ByLayer, 0=ByBlock.
 - **COM backend only**: `system_run_command`, `system_run_lisp`, and `view_zoom_extents/window` (view ops are no-ops in ezdxf).
 - **Screenshot**: COM uses Win32 window capture (Pillow required); ezdxf renders via matplotlib.
 - **`_dc(obj)`**: converts dataclasses to dicts recursively for JSON serialization.
 - **Engineering layer scaffold**: `drawing_new` auto-bootstraps standard linetypes (CENTER, HIDDEN, PHANTOM) and engineering layers (GEOMETRY, DIM, CENTER, HIDDEN, PHANTOM, HATCH, TEXT, TITLEBLOCK). Pass `bootstrap=False` to opt out.
+- **Generic contracts added in 1.6:** `block_define(name, entities, attdefs)` (typed primitives + ATTDEFs, both engines; `overwrite` replaces contents so INSERTs keep the name) and `entity_get/set_xdata` (typed by group code; 255-char strings, 16 KB per entity, enforced before writing).
+- **P&ID reader rules:** `pid_graph` never modifies the drawing, reads geometry from the drawing (an INSERT's real rotation/scale) rather than the catalogue, and reports `source`/`confidence` per node (catalog 1.0, xdata 0.95, heuristic 0.6, inferred 0.3) — never raised by agreement between heuristics. Read `stats.confidence_min` before trusting a foreign drawing.
+- **`TOOL_PACKS=all|core,pid,settings,mech,arch,plant`** advertises only the packs a client uses; `core` is always on; `system_about` reports `tool_packs`.
+- **Layer states are ours, not AutoCAD's.** `layer_state_*` stores a portable snapshot in an `ACADMCP_LAYERSTATES` XRECORD; it survives save/reopen on both engines and travels with the file, and it is not listed in AutoCAD's Layer States Manager. Said in the tool docstring, in `system_capabilities.layer_states` (`mode: "xrecord"`, reason `portable_acadmcp_xrecord;not_listed_in_autocad_layer_states_manager`) and in the README.
+- **Page-setup evidence is the PDF.** `batch_plot` reports `mediabox_mm` parsed from the file's `/MediaBox` (`engineering/standards/pdfinfo.py`); a page setup is verified by what a printer would get, not by the setter's return value. A style or setting write reports `changed` — re-setting a value to itself is not a change.
+- **Nothing interprets coordinates in UCS.** `ucs_set` / `ucs_restore` store and activate a UCS for the operator's benefit; every tool input and output stays WCS (the repository rule above).
+- **The part model, not primitives**: a machine part is `mech_part_draw` with a segment list or an outline plus typed features — never hand-drawn lines. The same rule as gears and keyways, for the same reason.
+- **Standards tables are transcribed, never derived**: every row under `engineering/mech/standards/` carries a `SOURCE` naming standard, edition and table, and a size outside the coverage is refused by name. `engineering/mech/standards/materials.py` states which of its rows are ISO 128-50, which are ASME Y14.2M via `acadiso.pat`, and which (concrete, wood) have no mechanical standard at all.
+- **Six `mech_*` critique focuses** (`mech_missing_centreline`, `mech_unhatched_section`, `mech_view_misaligned`, `mech_duplicate_dimension`, `mech_thread_unrepresented`, `mech_bom_balloon_mismatch`) run under `focus=None` and inside `drawing_finalize`; they return nothing on a drawing with no `ACADMCP_MECH` payload. `mech_view_misaligned` checks the projection axis and not the quadrant, and `mech_duplicate_dimension` catches two dimensions in the same place rather than a semantic restatement — both narrowings are in the module docstring, because the payload carries no projection angle and no engine exposes what a dimension measured.
+- **Live ActiveX will not create a layer on assignment** (`entity.Layer = "X"` on a missing layer raises `Key not found`; ezdxf creates it silently). Every mechanical/annotation draw path ensures its target layers before the first entity — a new path must do the same, or it passes every headless test and dies live.
+- **A diameter's text stands beyond the FIRST chord point** on both engines (the ActiveX `AddDimDiametric` rule, measured); `dimension_diameter(x1, y1, x2, y2)` annotates on the `(x1, y1)` side.
+- **The plan model, not lines**: a wall is `arch_wall` (an axis, a thickness, a justification, a material) and a door or window is hosted in it by `arch_opening` — never hand-drawn lines. The engine resolves the junctions and cuts the openings; what it cannot place is in `omitted`.
+- **Areas are measured, never typed**: a room's area is the planar face its label point lies in, written into the label and the `room` record by `arch_room`; no tool accepts an area from its caller, and `arch_plan_from_spec` refuses a typed `area` by path.
+- **Plan text follows the plot scale**: `scale` is a denominator (50 = 1:50) and a paper height `h` is drawn at `h × scale` drawing units — no annotative objects. `lang="tr"` switches words and the decimal separator; any other language is refused with the list.
+- **Three `arch_*` critique focuses** (`arch_room_unlabelled`, `arch_wall_gap` — two wall ends within 50 mm that do not join, `arch_opening_clash`) run under `focus=None` and inside `drawing_finalize`; they return nothing on a drawing with no `ACADMCP_ARCH` record.
+- **Nominal, not standard**: the furniture and sanitary blocks carry nominal catalogue dimensions and say so; the stair tool reports the Blondel relation (2R + G within 600–650 mm) as a design rule, never as a building code; the `arch` layer colours are a repository convention (ISO 13567 fixes names, not colours).
+- **Read-only by default (track H)**: `drawing_understand`, `drawing_scale_check`, `drawing_topology_check` and both takeoffs never modify the drawing; `drawing_diff` writes only with `markup=True`, and a takeoff writes a workbook file, never the drawing.
+- **Lengths come from the inferred unit**: a reader measures in the unit the geometry implies (text heights, wall and door sizes, overall size) and reports metres; a disagreement with `INSUNITS` is a warning with the numbers — a layout declaring inches over millimetre geometry is measured in millimetres, never ×25.4.
+- **Scale check before a P&ID length**: a P&ID is a length source only when `drawing_scale_check` calls it `to_scale`; otherwise a run's length is the orthogonal estimate on the layout and the drawn length stays a comparison column (`length_source="pid"` on a schematic P&ID is refused unless `force=True`, quoting the statistics).
+- **Nothing is invented (track H)**: a power the P&ID does not state stays empty and becomes an open item, an unreadable size stays `unassigned`, and no cable-section table is authored — a section comes only from the caller's `section_rules`.
+- **Client drawings never enter the repository**: every track-H fixture is the synthetic plant pair (`tests/fixtures/plant_pair.py`), whose truth is computed from the positions it placed; `scripts/field_test_takeoff.py` refuses an output folder inside the repository and prints no quantity unless `--show` is given.
 - **Production drawings**: For real engineering output, use the `engineering/` package primitives via the `gear_*` / `keyway_*` / `titleblock_*` MCP tools — do NOT hand-draw teeth/keyways/sections with raw `entity_create_*` calls. Always end with `drawing_finalize` for the 8-step validator.
 
 ### Premium Drawing Rules
 
-These rules are non-negotiable for production engineering output. The full
-discipline + workflow templates live in `.claude/skills/autocad-mcp-premium/`.
+These rules are non-negotiable for production engineering output.
 
 1. **Plan before draw**: Call `drawing_plan(intent, scale, sheet)` *before* any
    `entity_create_*`. The returned PlanSpec is held by the backend and replayed

Dockerfile

@@ -4,9 +4,12 @@ WORKDIR /app
 
 RUN useradd --create-home --shell /bin/bash mcp
 
-COPY pyproject.toml ./
-COPY server.py config.py security.py ./
+COPY pyproject.toml README.md LICENSE ./
+COPY server.py config.py security.py version.py ./
 COPY backends/ ./backends/
+COPY engineering/ ./engineering/
+COPY discovery/ ./discovery/
+COPY templates/ ./templates/
 
 RUN pip install --no-cache-dir -e .
 
@@ -15,6 +18,6 @@ USER mcp
 EXPOSE 8000
 
 HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
-    CMD python -c "import server; print('ok')" || exit 1
+    CMD python -c "import server, engineering.gear; print('ok')" || exit 1
 
 CMD ["python", "server.py"]

INSTALL.ru.md

@@ -0,0 +1,121 @@
+# AutoCAD MCP Pro — как у нас развёрнут и как обновлять
+
+Этот репозиторий — **зеркало** открытого проекта `U-C4N/Autocad-MCP` (PyPI-пакет
+`autocad-mcp-pro`), которым мы пользуемся для черчения из агентов Hermes.
+
+## 1. Источники версий и обновлений (единственные авторитетные)
+
+| Что | Где смотреть |
+|---|---|
+| Исходный репозиторий | https://github.com/U-C4N/Autocad-MCP |
+| Релизы и теги (что нового) | https://github.com/U-C4N/Autocad-MCP/releases — теги `v1.3.0 … v1.6.0` |
+| Список изменений | `CHANGELOG.md` в корне репозитория (самый подробный источник) |
+| PyPI-пакет и доступные версии | https://pypi.org/pypi/autocad-mcp-pro/json (поле `info.version`, `releases`) |
+| Внутренняя версия сервера | MCP-вызов `system_about` / ответ `initialize` (`serverInfo.version`) |
+
+**Текущий пин зеркала:** ветка `main`, коммит `cdb1063` (после релиза **1.6.0 от 24.09.2026**).
+Релизы: `v1.5.1` → `v1.6.0` (247 зарегистрированных инструментов, 242 отдаётся по умолчанию).
+
+Обновления проверять так (без установки):
+
+```bash
+# последняя версия на PyPI
+curl -s https://pypi.org/pypi/autocad-mcp-pro/json | python3 -c "import json,sys;d=json.load(sys.stdin);print(d['info']['version'], list(d['releases'])[-4:])"
+# свежие релизы на GitHub
+curl -s https://api.github.com/repos/U-C4N/Autocad-MCP/releases | python3 -c "import json,sys;[print(r['tag_name'], r['published_at']) for r in json.load(sys.stdin)[:5]]"
+```
+
+## 2. Как это работает у нас (архитектура)
+
+```
+Hermes (Docker, VM108)  --HTTP MCP (Bearer)-->  контейнер autocad-mcp :30015  --ezdxf-->  DXF/PDF
+                                              контейнер autocad-mcp-160 :30016 (тестовый 1.6.0)
+                                              папка обмена: /var/lib/docker/volumes/hermes_hermes-data/_data/dxf  →  /opt/data/dxf
+```
+
+| Параметр | Значение |
+|---|---|
+| Рабочий контейнер | `autocad-mcp`, образ `autocad-mcp:latest` = **1.5.1 + наш патч**, порт **30015 → 8000** |
+| Тестовый контейнер | `autocad-mcp-160`, образ `autocad-mcp:1.6.0` (апстрим без патча), порт **30016** |
+| Бэкенд | `AUTOCAD_MCP_BACKEND=ezdxf` (headless, без AutoCAD; COM — только на Windows рядом с AutoCAD) |
+| Токен доступа | файл `/opt/data/.autocad_mcp_token` (chmod 600, **в git не попадает**), передаётся как `Authorization: Bearer …` |
+| Папка файлов | `ALLOWED_PATHS=/opt/data/dxf` — сервер принимает файлы **только** оттуда (иначе «Path rejected») |
+| Профиль инструментов | `TOOL_PROFILE=full`; для слабых моделей есть `TOOL_PACKS=core,mech...` и `DISCOVERY_MODE=search` (2 инструмента / 356 токенов вместо 83 921) |
+| Деплой-скрипты | `/opt/data/deploy_autocad_mcp.py` (рабочий, с тегом отката `autocad-mcp:prev`), `/opt/data/work/cad_mcp/deploy_160_test.py` (тестовый 1.6.0) |
+| Логи сборки | `/opt/data/autocad_mcp_build.log`, `/opt/data/autocad_mcp_160_build.log` |
+| Проверка живости | `python3 /opt/data/work/cad_mcp/tools_inventory.py 30015` (делает `initialize` → `tools/list`) |
+
+## 3. Что в нашей рабочей сборке сверх апстрима (патч 01.10.2026)
+
+Оверлей лежит в `/opt/data/autocad-mcp-build/patch/` и копируется поверх `site-packages`
+(см. `Dockerfile` в `/opt/data/autocad-mcp-build/`). Этих инструментов в апстриме нет:
+
+| Инструмент | Зачем |
+|---|---|
+| `titleblock_apply_gost_form3` | основная надпись по **ГОСТ Р 21.1101-2013 форма 3** (апстрим знает только ISO 7200) |
+| `file_put` / `file_get` | передача файлов внутрь `ALLOWED_PATHS` и обратно (без Docker-томов и HTTP-моста) |
+| `drawing_open_base64` / `drawing_save_base64` | обмен чертежами в base64 |
+| `entity_create_attdef`, `block_get_attdefs` | символы-блоки с атрибутами (тип/высота/группа) |
+| параметр `layout=` у инструментов **геометрии** (29 инструментов) | рисовать линии/полилинии прямо на ЛИСТЕ, а не только в модели |
+| параметр `inline_font=True` (5 инструментов) | инлайн-кодировка ISOCPEUR в каждом тексте |
+| `drawing_export_pdf(page_size="layout")` | страница PDF ровно по формату листа (в 1.5.1 апстрим подгонял по содержимому) |
+| `layout_set_paper` | явный размер бумаги листа (A4 книжный и др.) |
+| `template_apply_layers(spds)` | ГОСТ-набор слоёв (RAMKA, STAMPS, 00 БЛОКИ АННОТАЦИЙ, Стены) |
+| `dimstyle_ensure`, `text_apply_style` | размерный стиль СПДС, текстовые стили |
+
+⚠️ **Следствие:** апстрим 1.6.0 нельзя просто «поставить вместо» — часть наших возможностей
+пропадёт (ГОСТ-штамп, file_put/file_get, `layout` у геометрии, `inline_font`). Поэтому 1.6.0
+поднимается **рядом** (порт 30016), а перенос патча делается отдельным шагом.
+
+## 4. Установка с нуля
+
+```bash
+# 1) образ (Docker-контекст: Dockerfile + patch/)
+mkdir -p /opt/data/autocad-mcp-build && cd /opt/data/autocad-mcp-build
+# Dockerfile:
+#   FROM python:3.11-slim
+#   RUN pip install --no-cache-dir autocad-mcp-pro==1.5.1 matplotlib
+#   COPY patch/ /usr/local/lib/python3.11/site-packages/
+#   EXPOSE 8000
+#   CMD ["autocad-mcp","--transport","http","--host","0.0.0.0","--port","8000"]
+
+# 2) сборка и переустановка контейнера (Portainer API, безопасно: сначала образ, потом замена)
+python3 /opt/data/deploy_autocad_mcp.py            # рабочий (с тегом отката autocad-mcp:prev)
+python3 /opt/data/work/cad_mcp/deploy_160_test.py  # тестовый 1.6.0 на :30016
+
+# 3) подключение в Hermes (конфиг защищён, менять через config set)
+export PATH="/opt/hermes/.venv/bin:$PATH" HERMES_HOME=/opt/data HOME=/opt/data
+hermes config set mcp_servers.autocad.type http
+hermes config set mcp_servers.autocad.url http://10.26.5.108:30015/mcp
+hermes config set mcp_servers.autocad.headers.Authorization "Bearer <токен из /opt/data/.autocad_mcp_token>"
+hermes mcp test autocad          # ожидаем "Connected" + число инструментов
+
+# 4) проверка
+python3 /opt/data/work/cad_mcp/tools_inventory.py 30015
+python3 /opt/skills/devops/cad-automation/scripts/mcp_acceptance_test.py   # приёмочный прогон
+```
+
+## 5. Обновление версии
+
+1. Проверить новую версию (п. 1) и прочитать `CHANGELOG.md`.
+2. Собрать **тестовый** образ на новую версию: скопировать
+   `/opt/data/autocad-mcp-build/Dockerfile` в новый каталог, заменить пин версии,
+   запустить `deploy_160_test.py` (порт 30016).
+3. Прогнать инвентаризацию и приёмку по обоим портам, сравнить:
+   `tools_inventory.py 30015` против `tools_inventory.py 30016` — что появилось, что пропало.
+4. Перенести наш патч (см. п. 3) либо решить, что из апстрима заменяет нашу доработку.
+5. Переключить рабочий контейнер (`deploy_autocad_mcp.py`) — он сам ставит тег отката
+   `autocad-mcp:prev`; при проблеме вернуться на него.
+
+**Откат:** остановить контейнер, создать заново из образа `autocad-mcp:prev` с теми же
+параметрами (порт 30015 → 8000, `ALLOWED_PATHS=/opt/data/dxf`, тот же токен, User 10000:10000).
+
+## 6. Грабли, которые уже собирали (не повторять)
+
+- `tools/list` «сырым» POST даёт **HTTP 400** — нужен `initialize` → заголовок `Mcp-Session-Id` → `tools/list`.
+- Файлы внутрь контейнера: только путь из `ALLOWED_PATHS` (`/opt/data/dxf`), иначе «Path rejected».
+- У контейнера **свой том** — это не тот `/opt/data/dxf`, который видит агент; для передачи
+  файлов используем `file_put`/`file_get` или мост `dxf-bridge` (`http://10.26.5.108:30055/`).
+- PDF: проверять медиабокс (`pymupdf` → `page.rect.width/72*25.4` ≈ формат листа) и шрифт (`ISOCPEUR`).
+- Чертёж отдавать пользователю только после проверки движком AutoCAD (`accoreconsole /i … /s …`).
+- COM-режим (живой AutoCAD) **невозможен из Docker** — сервер обязан работать на Windows рядом с AutoCAD.

README.md

@@ -1,348 +1,469 @@
+<div align="center">
+
 # AutoCAD MCP Pro
 
-Production-grade AutoCAD automation for AI agents—live through COM on Windows,
-or headless through ezdxf on any platform.
+**Production-grade AutoCAD automation for AI agents.**
+Live through COM on Windows, or headless through ezdxf anywhere — one typed contract, two engines.
 
-[![License: MIT](https://img.shields.io/badge/license-MIT-3fb950)](LICENSE)
-[![Python 3.11+](https://img.shields.io/badge/python-3.11%2B-1f6feb?logo=python&logoColor=white)](pyproject.toml)
-[![FastMCP 3](https://img.shields.io/badge/MCP-FastMCP%203-8957e5)](https://github.com/jlowin/fastmcp)
-[![Stars](https://img.shields.io/github/stars/U-C4N/Autocad-MCP?style=flat&color=e3b341)](https://github.com/U-C4N/Autocad-MCP/stargazers)
+[![CI](https://github.com/U-C4N/Autocad-MCP/actions/workflows/ci.yml/badge.svg)](https://github.com/U-C4N/Autocad-MCP/actions/workflows/ci.yml)
+[![PyPI](https://img.shields.io/pypi/v/autocad-mcp-pro?color=1f6feb&label=PyPI&logo=pypi&logoColor=white)](https://pypi.org/project/autocad-mcp-pro/)
+[![Downloads](https://img.shields.io/pypi/dm/autocad-mcp-pro?color=8957e5&label=downloads)](https://pypi.org/project/autocad-mcp-pro/)
+[![Python 3.11+](https://img.shields.io/badge/python-3.11%2B-1f6feb?logo=python&logoColor=white)](https://github.com/U-C4N/Autocad-MCP/blob/main/pyproject.toml)
+[![License: MIT](https://img.shields.io/badge/license-MIT-3fb950)](https://github.com/U-C4N/Autocad-MCP/blob/main/LICENSE)
 
-One typed MCP contract controls two execution engines. Build and edit drawings,
-query exact geometry, apply engineering standards, refine quality issues inside
-transactions, and deliver hashed artifacts with validation evidence.
+[Install](#install) · [What's new](#whats-new-in-16) · [Tools](#what-you-get) · [Engines](#the-two-engines) · [Evidence](#evidence) · [Limits](#what-this-release-is-bad-at) · [Config](#configuration) · [Changelog](https://github.com/U-C4N/Autocad-MCP/blob/main/CHANGELOG.md)
 
-> **v1.3 release snapshot:** 122 tools · 6 resources · 5 prompt templates ·
-> 415 collected tests. Runtime discovery through `system_about` is authoritative.
+<img src="https://raw.githubusercontent.com/U-C4N/Autocad-MCP/main/docs/assets/autocad-mcp-showcase.png" alt="ISO A3 sheet: a module-6, 24-tooth spur gear with a keyed bore, its section A-A, ISO 129 dimensions with an H7 bore fit, and an ISO 7200 title block" width="800">
 
-## Start in 60 seconds
+<sub><b>Not a mockup.</b> Every line on this sheet was drawn by the tools this server exposes — ISO layers, involute gear geometry, DIN 6885 keyway, section A-A, ISO 129 dimensions, an ISO 286 <code>H7</code> bore fit, ISO 7200 title block — then rendered headlessly by <code>view_screenshot</code>. <code>drawing_critique</code> returns <b>0 issues</b> on it. Rebuild it with <code>python scripts/render_readme_showcase.py</code>.</sub>
 
-```bash
-git clone https://github.com/U-C4N/Autocad-MCP.git
-cd Autocad-MCP
-python -m venv .venv
-```
+</div>
 
-Activate the environment and start the stdio server:
+> **v1.6 release snapshot:** 247 tools · 8 resources · 5 prompt templates · 4992 collected tests.
+> 247 is the **registered** count; a default install advertises 242 over `tools/list`,
+> because `ENABLE_3D` is unset. `system_about` is the runtime authority.
 
-```powershell
-# Windows
-.venv\Scripts\Activate.ps1
-pip install -e .
-python server.py
-```
+## What's new in 1.6
 
-```bash
-# macOS / Linux
-source .venv/bin/activate
-pip install -e .
-python server.py
-```
+Five tracks of one [roadmap](https://github.com/U-C4N/Autocad-MCP/blob/main/docs/superpowers/specs/2026-09-15-v1.6-roadmap-design.md), 154 → 247 registered tools. Each track has its own design spec, correctness checks that can fail, and a live AutoCAD 2026 run of its COM paths recorded in the [changelog](https://github.com/U-C4N/Autocad-MCP/blob/main/CHANGELOG.md).
 
-That starts the headless-capable server with automatic backend selection. For
-live AutoCAD control on Windows:
-
-```powershell
-pip install -e ".[com]"
-$env:AUTOCAD_MCP_BACKEND = "com"
-python server.py
-```
-
-No AutoCAD installation is needed for the ezdxf backend:
-
-```powershell
-$env:AUTOCAD_MCP_BACKEND = "ezdxf"
-python server.py
-```
-
-## Evidence, not adjectives
-
-![Source-reviewed AutoCAD MCP capability benchmark](docs/assets/autocad-mcp-benchmark.svg)
-
-The graphic is generated with Matplotlib from
-[`benchmarks/source_review.json`](benchmarks/source_review.json). A fixed,
-public 100-point rubric covers functional CAD breadth, correctness and delivery,
-backend reach, engineering production, tests, and security.
-
-| Project | Score | Evidence |
-|---|---:|:---:|
-| **[U-C4N/Autocad-MCP](https://github.com/U-C4N/Autocad-MCP)** | **93** | A |
-| [varavista/autocad-mcp](https://github.com/varavista/autocad-mcp) | 84 | A |
-| [beiming183-cloud/AutoCAD-MCP](https://github.com/beiming183-cloud/AutoCAD-MCP) | 83 | A |
-| [AnCode666/multiCAD-mcp](https://github.com/AnCode666/multiCAD-mcp) | 73 | A |
-| [puran-water/autocad-mcp](https://github.com/puran-water/autocad-mcp) | 70 | A |
-| [NCO-1986/AutoCAD_mcp](https://github.com/NCO-1986/AutoCAD_mcp) | 68 | B |
-
-This is a dated source review—not a claim that every project completed a shared
-live AutoCAD run. Evidence grade **A** means source plus executable local
-evidence was reviewed; **B** means source and tool surface were reviewed but the
-live AutoCAD path was not fully executed.
-
-Reproduce the chart and run the ten-task reference adapter:
-
-```bash
-pip install -e ".[pdf]"
-python -m benchmarks.render_chart
-python -m benchmarks.run_competitors --server autocad-mcp-pro --backend ezdxf --json
-```
-
-The v1.3 ezdxf reference run records **10/10 tasks (100.0)**. It is a
-self-check, not a competitor ranking.
-
-Cross-project runtime scores will be published only after equivalent adapters
-execute the same task contract. The complete rubric, caveats, version A/B suite,
-and reproduction commands live in [`benchmarks/`](benchmarks/README.md).
-
-## Why this architecture holds up
-
-### One contract, two engines
-
-The COM backend controls a live AutoCAD session on Windows through a
-single-threaded STA executor. The ezdxf backend creates, edits, renders, and
-validates DXF drawings without AutoCAD. Both return the same typed entities,
-layers, blocks, drawing metadata, and capability format.
-
-### Geometry agents do not have to guess
-
-Tools such as `point_from_snap`, `point_intersection`, and `point_tangent`
-resolve exact construction coordinates from drawing entities. Handle-preserving
-edit tools and smart selection keep agents attached to real geometry instead of
-reconstructing state from prose.
-
-### Quality is a loop
-
-`drawing_preflight` checks whether an engineering request is ready to draw.
-`drawing_critique` reports standards and geometry issues. `drawing_refine`
-repairs the supported subset inside isolated transactions and rolls back rounds
-that reduce quality. `drawing_finalize` combines structural validation,
-standards critique, a scalar score, and invalidity ratio.
-
-### Delivery carries evidence
-
-`drawing_deliver` creates the requested artifacts, computes SHA-256 hashes,
-reopens the canonical DXF, compares entity/layer/type counts and bounds, and
-writes `manifest.json` plus `validation.json`. A successful tool call is not
-treated as proof that the drawing survived export.
-
-## Backend capabilities
-
-| Capability | COM backend | ezdxf backend |
-|---|:---:|:---:|
-| Live AutoCAD document control | ✓ | — |
-| Headless DXF creation and editing | — | ✓ |
-| Cross-platform execution | — | ✓ |
-| Deterministic entity/query contract | ✓ | ✓ |
-| Transactions and rollback | ✓ | ✓ |
-| TABLE and MLEADER semantics | Native | Portable composite |
-| Screenshots | AutoCAD window | Matplotlib render |
-| Raw AutoCAD commands / AutoLISP | Opt-in | — |
-
-Use `system_capabilities` at runtime instead of assuming backend support. The
-machine-readable response distinguishes `native`, `composite`, `emulated`, and
-`unsupported` behavior where the engines differ.
-
-## A production drawing workflow
-
-The server exposes low-level CAD primitives, but the intended engineering path
-uses deterministic orchestration and validation:
-
-```text
-drawing_preflight → drawing_plan → drawing_apply_iso_layers
-→ deterministic create/edit tools → dimension_auto
-→ drawing_critique → drawing_refine
-→ drawing_finalize → drawing_deliver
-```
-
-Representative capability groups include:
-
-| Area | Examples |
-|---|---|
-| Drawing lifecycle | create, open, save, export, audit, purge, undo/redo |
-| Geometry | lines, arcs, polylines, hatches, splines, trim/extend/fillet/chamfer |
-| Annotation | dimensions, ISO 129 tolerances, TABLE, MLEADER, text editing |
-| Engineering | gears, keyed bores, title blocks, ISO 1101 GD&T and datums |
-| Query | entity/layer/block inspection, selection, bounds, distance and area |
-| Quality | preflight, critique, score, transactional refinement and finalization |
-| Delivery | PDF/PNG/DXF output, hashes, manifests and reopen-parity checks |
-
-The tool surface evolves. Ask `system_about` for the live grouped inventory
-instead of building integrations around a copied list from this README.
-
-## Installation profiles
-
-| Profile | Command | Use case |
+| Track | What it adds | Pack |
 |---|---|---|
-| Core | `pip install -e .` | Headless ezdxf workflows |
-| COM | `pip install -e ".[com]"` | Live AutoCAD on Windows |
-| PDF | `pip install -e ".[pdf]"` | PDF export and headless screenshots |
-| Full | `pip install -e ".[full]"` | Both backends and all render features |
+| **P&ID — drafter and reader** | 43 ISO 10628-2 / ISA-5.1 symbols as real blocks with ports and `TAG` attributes, port-to-port lines with ISA-5.1 classes and line numbers, `pid_graph` reading any P&ID back with a confidence per node, instrument index, line list, equipment list, `pid_from_spec` for a whole sheet in one transaction | `pid` |
+| **The AutoCAD environment** | ISO-25 / ANSI dimension styles, text and leader styles, `drawing_apply_standard`, ISO 216 / ANSI page setups checked against the plotted PDF's own `/MediaBox`, five bundled templates, several open documents headlessly, portable layer states, named views, UCS, a 90-entry system-variable catalogue; on a live seat, preferences, launch and operator prompts | `core`, `settings` |
+| **Mechanical parts and the sheet** | one part model and one view engine (front, side, top, section and detail views with hidden lines, cut faces and ISO 129 dimensions), ISO fasteners and bearings as blocks with attributes, ISO 21920-1 surface texture, ISO 2553 welds, ISO 5457 frames A4–A0, ISO 7200 title blocks, an ISO 7573 parts list read off the drawing with linked ISO 6433 balloons, xrefs, images, real `.dwg` | `mech`, `core` |
+| **Architecture** | walls with hosted doors and windows: one engine resolves L / T / X junctions and cuts the openings. Room areas are measured from the faces the walls enclose, and rooms are read back from any plan. Door / window / room schedules are real tables; labels in English or Turkish | `arch` |
+| **Understanding and takeoffs** | `drawing_understand` reads a drawing somebody else made in one call. Also `drawing_scale_check`, `drawing_diff` and `drawing_topology_check`. `pipe_takeoff` / `cable_takeoff` take the topology from the P&ID and the lengths from the layout into a Turkish, English or Russian workbook | `core`, `plant` |
 
-Requirements:
+`TOOL_PACKS` keeps a client from paying for the tracks it does not use ([idle cost below](#why-this-exists)).
 
-- Python 3.11+
-- [FastMCP](https://github.com/jlowin/fastmcp) 3.0+
-- [ezdxf](https://github.com/mozman/ezdxf) 1.3+
-- AutoCAD, `pywin32`, and Pillow only for live COM control
-- Matplotlib only for PDF/headless rendering and benchmark visualization
+<div align="center">
 
-## Connect an MCP client
+<img src="https://raw.githubusercontent.com/U-C4N/Autocad-MCP/main/docs/assets/mech-showcase.png" alt="ISO A3 flange-coupling sheet: a hub with a full section and chain dimensions, a flange with its bolt-circle end view, two ISO 4014 bolts with ISO 4032 nuts, a parts list with linked balloons, an ISO 5457 frame with zones and an ISO 7200 title block" width="800">
 
-### Claude Desktop
+<sub><b>A mechanical sheet, gated.</b> The <code>mech_assembly</code> benchmark sheet: a hub drawn from its part model with a full section and chain dimensions, a flange with its bolt-circle end view, two ISO 4014 M12×60 bolts and ISO 4032 nuts inserted as blocks, the ISO 7573 parts list <i>read off the drawing</i>, balloons linked to its rows, an ISO 5457 frame and an ISO 7200 title block. <code>drawing_critique(focus=None)</code> returns <b>0 issues</b> and the finalize score is <b>100</b>. Rebuild it with <code>python scripts/render_readme_mech.py</code>.</sub>
 
-Add a server entry to `claude_desktop_config.json` and use the absolute path to
-your checkout:
+<img src="https://raw.githubusercontent.com/U-C4N/Autocad-MCP/main/docs/assets/arch-showcase.png" alt="Two-room floor plan: hatched brick walls with an aerated-concrete partition, two doors, two windows, a straight stair, room labels with measured areas, exterior dimension chains, and door, window and room schedules" width="800">
+
+<sub><b>A floor plan whose areas nobody typed.</b> <code>arch_plan_from_spec</code>'s example, drawn in one transaction: a 250 mm brick ring split by a 100 mm AAC wall, two doors, two windows, a straight stair and exterior dimension chains at 1:50. The rooms measure 27.74 and 21.99 m², read from the faces the walls enclose, and the door, window and room schedules are read off the drawing. <code>drawing_critique(focus=None)</code> returns <b>0 issues</b>. Rebuild it with <code>python scripts/render_readme_arch.py</code>.</sub>
+
+<img src="https://raw.githubusercontent.com/U-C4N/Autocad-MCP/main/docs/assets/pid-showcase.png" alt="P&ID sheet: a centrifugal pump, a diaphragm-actuated globe control valve, a vertical vessel with two nozzles, a flow controller bubble and an off-page connector, joined by numbered process lines and an electric signal line" width="800">
+
+<sub><b>The same server as a P&ID drafter.</b> <code>pid_from_spec</code> placed five catalogue symbols as real blocks with <code>TAG</code> attributes and named ports and routed four port-to-port lines with ISA-5.1 classes and line numbers, all in one transaction. Then <code>pid_graph</code> read the sheet back: 5 nodes, 4 edges, 0 dangling ends, <code>confidence_min</code> 1.0. Rebuild it with <code>python scripts/render_readme_pid.py</code>.</sub>
+
+<img src="https://raw.githubusercontent.com/U-C4N/Autocad-MCP/main/docs/assets/pid-catalog.png" alt="Contact sheet of the 43 P&ID catalogue symbols: valve bodies with actuators, pumps and compressors, heat exchangers, vessels, instrument bubbles, line markers and connectors" width="800">
+
+<sub><b>The catalogue, authored in code.</b> 43 ISO 10628-2 / ISA-5.1 symbols: 11 valve bodies × 6 actuators, 6 rotating machines, 4 heat exchangers, 6 parametric vessels, 7 inline items, the instrument bubble in 4 types × 5 locations, 5 line markers and 3 connectors. Every one was placed through <code>pid_symbol_insert</code>'s own path. Rebuild it with <code>python scripts/render_pid_catalog.py</code>.</sub>
+
+</div>
+
+## Why this exists
+
+**A big MCP server is expensive to be connected to.** The full catalog costs a client **83,921 tokens** before it has asked for anything. Discovery mode replaces it with two tools and costs **356**.
+
+**A drafter searches for `FILLET`, not `entity_fillet`.** Before the corpus, those command names appeared in no tool name or description. That was `df = 0` against a stock index: the tools were not ranked badly, they were *absent*. The fix was data: an authored corpus of **206 AutoCAD command names and 1439 synonym phrases** covering all 247 tools. A test refuses to let a tool exist without one.
+
+| Advertised surface | Tools seen | Idle cost |
+|---|---:|---:|
+| `TOOL_PROFILE=full` (default) | 242 | 83,921 tokens |
+| `TOOL_PACKS=core,settings` (full profile) | 205 | 63,890 tokens |
+| `TOOL_PACKS=core,mech` (full profile) | 197 | 64,836 tokens |
+| `TOOL_PACKS=core,arch` (full profile) | 195 | 63,549 tokens |
+| `TOOL_PACKS=core,pid` (full profile) | 192 | 60,844 tokens |
+| `TOOL_PACKS=core,plant` (full profile) | 185 | 59,290 tokens |
+| `TOOL_PACKS=core` (full profile) | 183 | 57,122 tokens |
+| `TOOL_PROFILE=lean` | 65 | 22,661 tokens |
+| `DISCOVERY_MODE=search` | 2 | **356 tokens** |
+
+> [!NOTE]
+> These are offline ratio estimates, not tokenizer counts, and they are the *uncached* cost: prompt caching amortises the idle term. `benchmarks/token_suite.py --tokenizer anthropic` counts for real.
+
+## Install
+
+```bash
+pip install autocad-mcp-pro     # or: uvx autocad-mcp-pro
+autocad-mcp                     # stdio MCP server, backend auto-selected
+```
+
+```bash
+AUTOCAD_MCP_BACKEND=ezdxf autocad-mcp    # portable DXF engine, no AutoCAD needed
+AUTOCAD_MCP_BACKEND=com   autocad-mcp    # live AutoCAD (needs the [com] extra)
+```
+
+| Extra | Pulls in | For |
+|---|---|---|
+| *(none)* | `fastmcp`, `ezdxf`, `pydantic` | Headless DXF on any OS — **no rendering** |
+| `[com]` | `pywin32`, `Pillow` | Live AutoCAD control + window capture |
+| `[pdf]` | `matplotlib` | PDF export and headless PNG, any platform |
+| `[office]` | `openpyxl` | XLSX workbooks (takeoffs, `data_extract`); CSV is always written |
+| `[full]` | everything above | Development and CI |
+
+> [!NOTE]
+> The bare install **cannot draw pixels** — `ezdxf.addons.drawing` imports Pillow unconditionally, so every render path needs it. Add `[pdf]` for images on Linux or macOS.
+
+<details>
+<summary><b>Wire it to an MCP client</b></summary>
 
 ```json
 {
   "mcpServers": {
     "autocad": {
-      "command": "python",
-      "args": ["C:\\path\\to\\Autocad-MCP\\server.py"],
+      "command": "autocad-mcp",
       "env": {
         "AUTOCAD_MCP_BACKEND": "auto",
-        "ALLOWED_PATHS": "C:\\Users\\you\\Documents\\AutoCAD"
+        "ALLOWED_PATHS": "C:\\Users\\you\\Documents\\AutoCAD",
+        "TOOL_PROFILE": "full",
+        "TOOL_PACKS": "all",
+        "DISCOVERY_MODE": "off"
       }
     }
   }
 }
 ```
 
-Cursor, Cline, Continue, Goose, and other stdio-capable MCP hosts use the same
-`command` plus `args` shape. The model vendor is not part of the server
-contract.
+It works with Claude Desktop, Cursor, or any stdio MCP host. For HTTP, run `autocad-mcp --transport http --port 8000`. It binds loopback only, unless remote HTTP is explicitly enabled **and** a bearer token is set.
 
-### Local HTTP
+</details>
 
-```bash
-fastmcp run server.py:mcp --transport http --port 8000
-```
+## What you get
 
-Loopback is the default. A non-loopback bind is refused unless remote HTTP is
-explicitly enabled and bearer-token authentication is configured.
+| Area | What it does |
+|---|---|
+| Drawing lifecycle | create, open, save, export DXF/PDF, audit *(repairs)*, purge, undo/redo |
+| Geometry | lines, arcs, polylines, splines, hatches, trim/extend/fillet/chamfer, handle-preserving edits |
+| Annotation | ISO 129 toleranced dimensions, ISO 286 fits (`fit="H7"`, interference shafts r/s/t/u included), TABLE, MLEADER, GD&T frames and datums (ISO 1101) |
+| Engineering generators | involute gears (front + section A-A), DIN 6885 keyed bores, ISO A3 title block |
+| Mechanical parts | one part model (segments or outline + typed features) and one view engine: front / side / top / section / detail with hidden lines, ISO 128-50 cut faces and ISO 129 dimensions. ISO 4014/4017/4032/7089/4762 fasteners and ISO 15 bearings insert as real blocks with attributes. DIN 471/472, DIN 509, DIN 332 and ISO 3601-2 features have their drawing code, but *their tables ship empty in 1.6* (see [limits](#what-this-release-is-bad-at)). Also ISO 21920-1 surface texture, ISO 2553 welds and ISO 128-40 section lines |
+| Sheet & delivery | ISO 5457 frames A4-A0 with zones and trim marks, ISO 7200 title blocks for every size, revision blocks with clouds, ISO 7573 parts lists with ISO 6433 balloons linked by XDATA, CSV/XLSX extraction, xrefs and images on both engines, real `.dwg` on a live seat |
+| Architecture | one plan model (walls with hosted doors and windows) and one engine that resolves L / T / X junctions, cuts openings and draws poché by material. Room areas are measured from the faces the walls enclose, never typed, and rooms are read back from any plan with a confidence. Door / window / room schedules are real TABLEs. Also a furniture and sanitary catalogue at nominal sizes, a structural grid, north arrow, section / level / elevation marks, exterior dimension chains, and English or Turkish labels (`lang="tr"`, decimal comma) |
+| Understanding & takeoffs | `drawing_understand` reads a drawing somebody else made in one call: declared vs inferred units, robust extents and the outlier behind them, plan copies, each layer's discipline and service in five languages, tags, rooms. `drawing_scale_check` says whether a P&ID is to scale against its layout. `pipe_takeoff` / `cable_takeoff` take the topology from the P&ID and the lengths from the layout (rectilinear MST, statuses A/B/C, power never invented) into a Turkish / English / Russian workbook. `drawing_diff` compares revisions; `drawing_topology_check` finds dangling ends, near misses and crossings |
+| P&ID | catalogue blocks with ports and tags (ISO 10628-2 / ISA-5.1), port-to-port lines with ISA-5.1 classes and line numbers, `pid_graph` reads any P&ID back with confidence, instrument index / line list / equipment list, `pid_from_spec` one-call sheets |
+| Styles & standards | ISO-25 / ANSI dimension styles, ISOCP / ROMANS text styles, ISO / ANSI leader styles from authored presets; `drawing_apply_standard("iso")` sets all of it plus units and the `mech` layers in one call; `changed` reports only what moved |
+| Discovery | `search_tools` ranked over an AutoCAD command and synonym corpus — `FILLET`, `BPOLY`, `QSELECT`, `WBLOCK`, `OVERKILL`, `CHSPACE` each rank **#1** of the 242-tool advertised catalog |
+| Batching | `cad_batch` runs a step list in one round trip; `fields=` projects 11 result-heavy tools |
+| Paper space | tab lifecycle, viewports, `entity_change_space` (CHSPACE), `drawing_export_pdf(layout=…)` |
+| Page setup & templates | ISO 216 / ANSI Y14.1 sheets, ctb catalog, `page_setup_apply` on both engines, and `batch_plot` with every sheet size read back from its PDF's `/MediaBox`. Five bundled templates, built by the server's own tools and pinned reproducible: `drawing_new(template="iso_a3_mech")`, `iso_a1_arch`, `iso_a3_pid`, `ansi_b_mech`, `ansi_d_arch`. Save any drawing as a template (`.dwt` on live AutoCAD; `dwt_write` refused headlessly) |
+| Environment | several open documents headlessly, portable layer states (`ACADMCP_LAYERSTATES` XRECORDs — in the file, not in AutoCAD's Layer States Manager), named views, UCS *(tool coordinates stay WCS)*, a system-variable catalog with ranges, document properties. On a live seat: launch/attach, preferences, and an operator prompt / pick / select, where ESC is `cancelled`, not an error |
+| Selection | window vs crossing stated back to the caller; a polygon tested against its own shape, not its bounding box |
+| Boundaries | `boundary_trace` (BOUNDARY/BPOLY) chains loose edges into one closed polyline, arcs kept as bulges *(headless)* |
+| Measurement | `analysis_measure_entity` measures what is *in* the drawing, by handle |
+| Hatch depth | gradients, in-place edits, typed edge boundaries *(headless)*, island styles |
+| Annotation objects | WIPEOUT, REVCLOUD, MTEXT background masks *(headless)*, text find/replace |
+| 3D solids | `solid_box/cylinder/extrude/revolve/boolean` on live AutoCAD (`ENABLE_3D=true`) |
+| Quality loop | `drawing_preflight` → `drawing_plan` → `drawing_critique` → `drawing_refine` → `drawing_finalize` (0–100 score); 18 domain critique focuses (P&ID 6, mechanical 6, architecture 3, topology 3), each silent on a drawing outside its domain |
+| Delivery | `drawing_deliver`: DXF/PDF/PNG + SHA-256 manifest + reopen-parity checks |
+
+<sub>247 tools in 28 groups. <code>TOOL_PACKS=core</code> hides these from a client that needs none of them: the nine <code>pid_*</code> tools, the 22 environment tools, the 14 mechanical tools, the 12 architectural tools and the two plant takeoffs. <code>TOOL_PACKS=core,mech</code> keeps the mechanical ones, <code>TOOL_PACKS=core,arch</code> the architectural ones, and <code>TOOL_PACKS=core,plant</code> the takeoffs. There are also 8 resources that cost nothing in the tool budget (<code>autocad://drawing/info</code>, <code>layers</code>, <code>blocks</code>, <code>entities/stats</code>, <code>entities/{layer_name}</code>, <code>system/status</code>, <code>pid/symbols</code>, <code>standards/isa51</code>) and 5 prompt templates.</sub>
+
+**Two rules worth knowing.**
+
+- Every coordinate in and out of a tool is WCS on both engines. The one exception is TEXT `rotation`, which stays in the entity frame: a mirrored TEXT is mirror-imaged, and no scalar angle expresses that.
+- Never read vertices back and shoelace them. That silently loses **28.2%** of the area on a semicircular edge. `analysis_measure_entity(handle)` reads the real geometry and states its own accuracy.
+
+## The two engines
+
+One contract across 23 modules in `backends/contracts/`. `@capability(key, reason=…)` supplies a default that *refuses*, and a test holds both backends' capability key sets equal. There are **41 capability keys**. Read `system_capabilities` at runtime rather than trusting the table: several depend on what the machine has installed (matplotlib, openpyxl, the ODA File Converter).
+
+| Capability | COM (live AutoCAD) | ezdxf (headless) |
+|---|:---:|:---:|
+| Live document control | ✅ | — |
+| Cross-platform, no AutoCAD | — | ✅ |
+| Transactions and rollback | ✅ | ✅ |
+| Paper-space layouts + viewports | ✅ | ✅ |
+| Viewport model-content rendering | ✅ | ✅ ᵐ *(no borders)* |
+| Selection window / crossing / polygon | ✅ | ✅ |
+| Entity area by handle | ActiveX `.Area` | Analytic, bulges included |
+| HATCH filled area (islands subtracted) | AutoCAD's own number | Loops walked, `hatch_style` reported |
+| REGION / 3DSOLID area | ✅ | — *ACIS is opaque to ezdxf* |
+| 3D solids | ✅ *with `ENABLE_3D=true`* | — |
+| DWG write | ✅ `SaveAs` | via the ODA File Converter, if installed |
+| `.dwt` templates | ✅ | DXF only — `dwt_write` refuses |
+| Reading a foreign drawing (`drawing_understand`, takeoffs) | ✅ one `Document.Export` snapshot; the document is never renamed | ✅ |
+| XLSX workbooks | ✅ ᵒ | ✅ ᵒ |
+| Preferences · launch · operator prompts | ✅ | — *refused by name* |
+| WIPEOUT · MTEXT background colour | — *verified absent, AutoCAD 2026* | ✅ |
+| REVCLOUD · BPOLY · typed hatch edges | — *no ActiveX member* | ✅ |
+| CHSPACE | — *unverified on a live seat* | ✅ ᶜ |
+| Undo history | ✅ | opt-in — `EZDXF_UNDO_DEPTH` |
+| TABLE and MLEADER | Native | Portable composite |
+| Screenshots and PDF | Window capture | Matplotlib ᵐ |
+
+<sub>ᵐ Needs matplotlib (<code>[pdf]</code>/<code>[full]</code>). Without it, <code>png</code>, <code>pdf</code>, <code>viewport_render</code> and <code>handle_overlay</code> report unsupported headlessly.<br>
+ᵒ Needs openpyxl (<code>[office]</code>/<code>[full]</code>). Without it, XLSX is refused with <code>xlsx_write</code> and CSV is still written.<br>
+ᶜ Headless CHSPACE has four restrictions, named in its capability reason: top-view untwisted viewports only; dimensions refused unless frozen; ACIS, proxy and table entities refused; viewport clipping reported rather than applied.</sub>
+
+> [!IMPORTANT]
+> Every COM path added in v1.6 was executed against a **live AutoCAD 2026**, one smoke script per track (`scripts/smoke_*_com.py`), each run recorded in the changelog. Those runs found defects no headless test could. ActiveX refuses `entity.Layer` on a missing layer, where ezdxf quietly creates it, so `mech_part_draw` died after drawing every view. ActiveX calls a block reference `BLOCKREFERENCE`, not `INSERT`, so the parts list read nothing. And once pywin32's type-library cache existed, every listed entity arrived as a bare `IAcadEntity` with no line endpoints, so the room reader saw no walls and `arch_plan_from_spec` refused its first room label.
+
+## Evidence
+
+Everything below is produced by scripts in [`benchmarks/`](https://github.com/U-C4N/Autocad-MCP/blob/main/benchmarks/) and published as JSON under [`benchmarks/results/published/`](https://github.com/U-C4N/Autocad-MCP/tree/main/benchmarks/results/published).
+
+### Against the other AutoCAD MCP servers
+
+<img src="https://raw.githubusercontent.com/U-C4N/Autocad-MCP/main/docs/assets/autocad-mcp-benchmark.svg" alt="Source-reviewed capability leaderboard: U-C4N/Autocad-MCP 93, varavista 84, beiming183-cloud 83, best-cad-mcp 74, multiCAD-mcp 73, puran-water 70, NCO-1986 68, daobataotie 35, Easy-MCP-AutoCad 30" width="800">
+
+A fixed 100-point rubric applied to nine public AutoCAD MCP servers ([`source_review.json`](https://github.com/U-C4N/Autocad-MCP/blob/main/benchmarks/source_review.json)). Stars and raw tool counts score nothing. 1.6.0 is scored **per category, with the evidence for every point withheld**:
+
+| Category | Weight | 1.6.0 | Points withheld for |
+|---|---:|---:|---|
+| Functional CAD coverage | 25 | 24 | no electrical schematics, image-to-CAD tracing, Plant 3D, obstacle-avoiding routing or headless REGION / 3DSOLID |
+| Correctness and delivery | 20 | 19 | a headless DIMENSION does not re-render; a takeoff on a real P&ID still needs the engineer's scope decisions |
+| Backends and platforms | 15 | 14 | BricsCAD, ZWCAD and GstarCAD unverified |
+| Engineering production | 15 | 14 | four DIN / ISO feature tables ship empty |
+| Tests and maintenance | 15 | 14 | headless entity creation slower than v1.4.0 |
+| Security and operations | 10 | 8 | `ALLOWED_PATHS` unscoped by default; command filtering is a denylist |
+| **Total** | **100** | **93** | |
+
+> [!NOTE]
+> Read this as a documented self-assessment, not an independent review: this repository applies the rubric to itself and to the others. The competitor rows are their July 2026 snapshots and were not re-reviewed for this release, and the best of them, varavista/autocad-mcp, scored 84. 1.4.0 was given one overall 95. This review is stricter and scores each category apart.
+
+A second lane runs tasks instead of reading source. Every task in the fixed-task matrix can fail, and its artifacts are verified by re-opening the DXF, never by trusting a response. The reference adapter passes **21 / 21** of matrix v7. The two competitors with adapters, pinned at their July 2026 commits, passed 5 / 10 and 4 / 10 of the ten v2 tasks they were run on. The eleven tasks added since then were never put to them, so they show as *not run*, not as zero:
+
+<img src="https://raw.githubusercontent.com/U-C4N/Autocad-MCP/main/docs/assets/autocad-mcp-taskmatrix.svg" alt="Task matrix: autocad-mcp-pro passes all 21 tasks; beiming183 and puran-water were run on the first ten, with the later eleven not run" width="800">
+
+### Correctness — every release re-proves itself
+
+48 deterministic headless checks against the previous tag and the current tree. Each runs in its own subprocess, so a hard crash counts as a miss rather than killing the run.
+
+| Version | Checks passing | Pass rate | Fixed | Regressed |
+|---|---:|---:|---:|---:|
+| v1.5.1 *(baseline)* | 26 / 48 | 54.2 % | — | — |
+| **v1.6.0** *(this release)* | **48 / 48** | **100 %** | 22 | **0** |
+
+The 26 checks v1.5.1 was released on all still pass. The twenty-two fixed rows are new capability (`miss → pass`), and each one pins a number computed by hand, not read back from the code that drew it:
+
+<details>
+<summary><b>The twenty-two checks 1.6 added</b></summary>
+
+| Track | Check | Verified against |
+|---|---|---|
+| Understanding | `scale_check_detects_schematic` | the synthetic P&ID reads **schematic** against its layout; a uniform 2× copy of six tags reads **to scale** with factor 2 |
+| | `pipe_takeoff_rmst_exact` | all eight routable runs measure exactly the rectilinear MST of their tags |
+| | `cable_takeoff_roundup` | 9, 17, 19 and 10 m after the 20 % allowance; the heater's unstated power stays empty |
+| | `diff_detects_known_edits` | a move, a text change, an attribute change, an add and a delete, and nothing else |
+| | `topology_known_defects` | a 5 mm near miss, one interior crossing, and a clean T that is neither |
+| Architecture | `arch_junction_l_t_x` | an L corner mitres at (4100, −100) / (3900, 100), a T stem stops on the near face, an X cuts all four faces; wall areas 1 400 000, 1 490 000 and 2 360 000 mm² |
+| | `arch_room_area_net` | a 4 × 5 m room between 200 mm walls is labelled 20.00 m², not the 21.84 m² its axes enclose |
+| | `arch_opening_cuts_wall` | both faces are interrupted across a 900 door and two jambs close it |
+| | `arch_rooms_detect_foreign` | plain lines on a `WALLS` layer yield 20 and 15 m² at confidence 0.6, and nothing is written |
+| Mechanical and sheet | `mech_part_roundtrip` | a part read back out of its own `ACADMCP_MECH` XDATA equals the part drawn |
+| | `mech_section_hatch_area` | a 60 × ⌀40 sleeve with a ⌀20 bore cuts 1200 mm², measured out of the drawing by `analysis_measure_entity` |
+| | `mech_iso286_on_dimension` | 40 H7 is +0.025 / 0 and survives the layout |
+| | `mech_thread_unrepresented_is_caught` | the ISO 6410 focus fires on a thread drawn as a plain circle. A gate that never fires is not a gate |
+| | `std_part_iso4014_m12` | s = 18, k = 7.5, read by value |
+| | `sheet_frame_iso5457_a3` | the frame runs 20,10 to 410,287 inside the 420 × 297 sheet |
+| | `bom_balloon_link` | two identical bolts are one row of quantity 2, and its balloon carries the row's item number |
+| Environment | `settings_dimstyle_iso25_values` | the ISO-25 preset lands in the DIMSTYLE table with ISO 129-1's numbers |
+| | `settings_layer_state_roundtrip` | save → change → restore puts the layer table back, and the state survives save/reopen |
+| | `settings_pdf_mediabox_a3` | the plotted PDF's own `/MediaBox` reads 420 × 297 |
+| P&ID | `pid_block_define_attdef_roundtrip`, `pid_tag_parse_fic`, `pid_graph_edge_count` | a block with ATTDEFs defined and read back, an ISA-5.1 tag parsed, a drawn P&ID's edge count |
+
+</details>
+
+### The task matrix — tasks that can fail
+
+An earlier matrix scored this server 10/10, which carried no information: every task in it exercised something the server was built around. Five tasks were added in 1.5 because they *can* fail, and three of them did while being written. 1.6 adds six more:
+
+- one the P&ID reader can fail on its own;
+- one where the PDF file, not the setter, is the witness;
+- one where a whole mechanical sheet has to come out clean;
+- one where a floor plan's rooms are read back off the drawing;
+- two where a foreign plant's P&ID and layout are read: the takeoffs against lengths computed in advance, and the one-call report against the defects planted in it.
+
+| Task | Verified against |
+|---|---|
+| `tool_discovery` | six AutoCAD command names, each ranking #1 |
+| `token_budget` | 83,921 → 356 tokens, against a ceiling fixed in advance |
+| `hatch_islands` | 300 filled with the island, 400 ignoring it |
+| `selection_filter` | window 1, crossing 2, bounding box 3, polygon 1 |
+| `measure_from_handle` | 139.2699 against the 100.0 a vertex shoelace gives |
+| `pid_roundtrip` | the example sheet drawn by `pid_from_spec`, read back by `pid_graph`, which never sees the spec: 5 nodes, 4 edges, 0 dangling, `confidence_min` 1.0, `FIC-101` wired to `FCV-101` |
+| `page_setup_truth` | ANSI B, then ISO A3 landscape, applied to Layout1. Each is plotted through `batch_plot` and read back from its PDF's `/MediaBox`: 432 × 279, then 420 × 297 mm, not the setter's return value. A fresh layout is already A3, so the B sheet is what a no-op setter cannot fake |
+| `mech_assembly` | a flange-coupling A3 sheet: a hub with a full section, a flange with its bolt-circle end view, two ISO 4014 bolts with ISO 4032 nuts, an ISO 7573 parts list read off the drawing, linked balloons, an ISO 5457 frame and an ISO 7200 title block. Gated on `drawing_critique(focus=None)` returning **zero** issues and a finalize score of at least **90**; a test drops one balloon and watches the gate fail |
+| `arch_roundtrip` | a two-room plan (an entrance door, an interior door, two windows, a stair) drawn by `arch_plan_from_spec` and read back by `arch_rooms_detect`, which never sees the spec. Each room must be within 0.1 % of its label and of the net floor computed by hand (4825 × 5750 and 3825 × 5750 mm), and the schedules must list D1, D2, W1, W2. Gated like `mech_assembly`; a test removes one room label and watches the gate fail |
+| `takeoff_roundtrip` | the synthetic plant pair: a P&ID stretched 1.3× in one room and rearranged in the other, Russian supply / return words, a return drawn on the supply layer, a reducer, a segment drawn twice. The scale check must call it **schematic** (21.8 % of 55 pairs within ±10 %). `pipe_takeoff` must give every routable run's layout length equal to the rectilinear MST of its tags, sizes and services as drawn, and the run to a tag the layout lacks status C. `cable_takeoff` must give 9 / 17 / 19 / 10 m after the 20 % allowance and leave the heater's power empty. A test removes the wiring callouts and watches the cable half fail by name |
+| `understand_foreign` | the pair's layout (inches declared over millimetres, a stray line 5,000 km out, two plan copies) comes back as millimetres with an `INSUNITS` warning, the stray line's handle and two clusters. The P&ID's `P_product piping` / `P_cipsupplyline` / `P_cipreturnline` / `P_ijswater` / `E_power` classify as product / CIP supply / CIP return / ice water / electrical. A test makes the layout declare millimetres and watches the units gate fail |
+
+### Headless performance
+
+<img src="https://raw.githubusercontent.com/U-C4N/Autocad-MCP/main/docs/assets/autocad-mcp-perf.svg" alt="Performance across four headless workloads" width="800">
+
+The workloads call the same backend methods the MCP tools call, so server-side overhead is included. Numbers move with hardware; the report records the machine fingerprint. **Read the next section before quoting them.** This release is slower than v1.4.0 at creating entities.
+
+## What this release is bad at
+
+A page that only lists strengths is a page that has not been measured.
+
+**Headless entity creation is slower than v1.4.0, and 1.6 did not win it back.** These are medians of five alternating runs on one machine, with one interpreter (CPython 3.11.15) and one ezdxf, v1.4.0's code against 1.6.0's ([`perf-v1.4.0-vs-v1.6.0.json`](https://github.com/U-C4N/Autocad-MCP/blob/main/benchmarks/results/published/perf-v1.4.0-vs-v1.6.0.json)):
+
+| Workload | v1.4.0 | v1.6.0 | v1.6.0, `EZDXF_CALL_TIMEOUT=0` |
+|---|---:|---:|---:|
+| 2,000 lines, one call each | 244.5 ms | 306.1 ms (1.25×) | 284.9 ms (1.17×) |
+| 10,000 lines: build, DXF export, reopen | 1,847.9 ms | 2,553.5 ms (1.38×) | 2,216.4 ms (1.20×) |
+| Region query over 10,000 entities | 665.2 ms | 712.2 ms (1.07×) | 783.9 ms (1.18×) |
+| Premium quality pass | 150.6 ms | 65.3 ms (**2.3× faster**) | 69.9 ms |
+
+The per-call timeout stops one hung call from wedging a server whose document lock is a single `asyncio.Lock`. It explains only part of the slowdown: switched off, creation is still 1.17× and 1.20× slower. The rest is extra work per call that 1.6 has not removed. A cProfile of the event-loop thread counts 491,071 function calls for the 2,000 creates, against v1.4.0's 319,038. Earlier READMEs said that switching the timeout off returned creation to v1.4.0's numbers. Measured this way, it does not. The region-query row, which moves the wrong way, shows this machine's noise floor (about ±10 %). Roadmap criterion 7 is not met and moves to 1.7.
+
+**Four mechanical feature tables ship empty.** DIN 471/472 retaining-ring grooves, DIN 509 undercuts, DIN 332 centre holes and ISO 3601-2 O-ring grooves have their drawing code and their provenance tests, but no rows. A groove diameter written from memory is a wrong workshop drawing, while a narrow table is merely narrow. So every size is refused by name until rows verified against the standard's own table are transcribed. That is a data edit; each module's docstring says how.
+
+**Takeoffs are estimates, and they say so.**
+
+- A layout length is the rectilinear minimum spanning tree of the tags a run connects, plus a stated vertical allowance, and it is labelled an estimate.
+- A P&ID length is used only when `drawing_scale_check` calls the P&ID to scale.
+- A power the P&ID does not state stays empty and becomes an open item, and no cable-section table is authored: a section comes only from your `section_rules`.
+- Where no callout names a panel, the nearest panel is inferred and flagged.
+- Detail copies of equipment are flagged, and excluded only when you ask.
+
+The readers were tuned on the synthetic plant pair and on one real P&ID / layout pair that is not in this repository. Another drafting office's layer and text conventions may need vocabulary.
+
+**No Plant 3D.** The roadmap's track D (read-only queries of a Plant 3D project) was dropped: the maintainer does not use Plant 3D, and a reader tested against nobody's real projects would be a guess. Roadmap criterion 5 is withdrawn, not met.
+
+**No REGION or 2D booleans headlessly.** `add_region()` produces a REGION with **zero ACIS bytes**, and the `greiner_hormann` substitute loses **28.2%** of the area on a square with one semicircular edge.
+
+**`system_run_command` / `system_run_lisp` are a guardrail, not a security boundary.** The rejection message says so in those words. A 36-verb denylist refuses the obvious cases, but AutoCAD accepts hundreds of commands, and `DANGEROUS_COMMANDS_ENABLED=true` switches the list off entirely.
+
+**Path validation is per-tool, and unscoped until you scope it.** With `ALLOWED_PATHS` empty (the default), the only positive bound is a ten-entry system-directory denylist that does not include `C:/Users`, `/home`, `/root` or `/var`. **Set `ALLOWED_PATHS`.**
+
+**Non-AutoCAD ProgIDs are unverified.** `CAD_PROGID` changes which COM application the backend attaches to; nothing beyond the connection has been tested against BricsCAD, ZWCAD or GstarCAD.
+
+### Known limitations of the P&ID track
+
+**The router is orthogonal and blind.** `pid_line_draw` picks `auto` from seven orthogonal candidates, by fewest bends then length:
+
+- straight;
+- one bend;
+- two bends through the midline;
+- a stub out of each port joined by three bends.
+
+You can also take `direct`, or pass waypoints. It *counts* the lines it crosses (`crossings` comes back in every result, and `pid_from_spec` sums it), but it does not route around them. Obstacle-avoiding routing is not in 1.6; move the symbol or pass waypoints.
+
+**A foreign drawing is read at the confidence it earns, and no higher.** A block this server did not place classifies at 0.6, with inferred ports, by its `TAG`-style attribute or a keyword in its name. It classifies at 0.3 when a line merely touches it, and a 0.3 guess can neither raise nor suppress a critique finding.
+
+On the live engine, an INSERT turned off a right angle has members ActiveX cannot measure, so it reports an *approximate* box. `pid_graph` takes the tighter wall of that box and the attribute-inclusive box on every side. Even so, a line ending on such a body's true edge can still be reported `dangling`, with the nearest port as the hint. Read `stats.confidence_min` first.
+
+**Same-file only, DXF headlessly.** Off-page connectors link within one drawing; links across files are not resolved. The headless engine reads DXF; a DWG P&ID is read through the live backend. There is no DEXPI/Proteus export and there are no ISA-5.2 binary-logic symbols in this release. Both cuts are recorded in the spec so nobody re-derives them.
+
+### Known limitations of the settings track
+
+**Layer states are ours.** `layer_state_save` writes a portable snapshot into an `ACADMCP_LAYERSTATES` XRECORD. It survives save/reopen on both engines and travels with the DWG/DXF. It is **not** an AutoCAD `LAYERSTATE` and does not appear in the Layer States Manager, which is why `system_capabilities` reports `layer_states` as `mode: "xrecord"`.
+
+**Six of the 22 environment tools need a live seat.** Preferences, launching, the operator prompts and the five summary fields of document properties are refused headlessly with `preferences` / `dwgprops` / `live_application` / `interactive_prompt`. Each is a refusal, not a stub.
+
+A `.dwt` template is the same case (`dwt_write`): a `.dwt` is a DWG container, so headlessly the template is saved as DXF. `mleaderstyle_create` is *not* such a case. ActiveX has no MLeaderStyle collection, but the `ACAD_MLEADERSTYLE` dictionary holds full `IAcadMLeaderStyle` objects, so both engines create leader styles.
+
+**A headless dimension does not re-render.** On the ezdxf engine, `dimstyle_modify` reports `dimensions_using_style` and `rerender_required: true`, and the DIMENSION keeps its rendered block until it is redrawn. AutoCAD regenerates on the next regen.
+
+### Known limitations of the architecture track
+
+**Nominal, not standard.** The furniture and sanitary blocks carry nominal catalogue sizes and say so. The stair tool reports the Blondel relation (2R + G within 600–650 mm) as a design rule, never as a building code. The `arch` layer colours are a repository convention: ISO 13567 fixes the names, not the colours. Labels speak English or Turkish; any other `lang` is refused with the list.
 
 ## Configuration
 
-Set variables in your shell, process manager, or MCP client configuration.
-[`.env.example`](.env.example) is a reference; the server reads process
-environment variables directly.
+Nothing loads a `.env` file — export these, or set them in your MCP client's `env` block.
+
+<details>
+<summary><b>All 17 environment variables</b></summary>
 
 | Variable | Default | Purpose |
 |---|---|---|
-| `AUTOCAD_MCP_BACKEND` | `auto` | Select `auto`, `com`, or `ezdxf` |
+| `AUTOCAD_MCP_BACKEND` | `auto` | `auto`, `com`, or `ezdxf` |
+| `CAD_PROGID` | `AutoCAD.Application` | COM ProgID the live backend attaches to |
+| `TOOL_PROFILE` | `full` | `lean` (65 curated tools, 55 with `TOOL_PACKS=core`) or `full` |
+| `TOOL_PACKS` | `all` | Vertical packs to advertise: `core,pid,settings,mech,arch,plant` (`core` always on) |
+| `DISCOVERY_MODE` | `off` | `search` replaces the catalog with `search_tools` + `call_tool` |
+| `ENABLE_3D` | `false` | Expose the opt-in `solid_*` tools (COM) |
 | `LOG_LEVEL` | `INFO` | Python logging level |
-| `ALLOWED_PATHS` | empty | Comma-separated absolute paths the server may access |
+| `ALLOWED_PATHS` | *(empty)* | Comma-separated absolute paths the server may access |
 | `MAX_UNDO_STACK` | `5` | Maximum retained undo snapshots |
-| `MAX_DXF_BYTES` | `52428800` | Reject larger DXF input; `0` disables the check |
-| `MAX_LIST_LIMIT` | `5000` | Bound list and selection response sizes |
-| `COM_CALL_TIMEOUT` | `60` | Per-call live AutoCAD timeout in seconds |
-| `DANGEROUS_COMMANDS_ENABLED` | `false` | Allow blocked commands/LISP and report unsafe mode |
+| `EZDXF_UNDO_DEPTH` | `0` | Headless undo history depth; `0` disables it |
+| `MAX_DXF_BYTES` | `536870912` | Reject larger DXF input (512 MB); `0` disables |
+| `MAX_LIST_LIMIT` | `5000` | Bound list/selection response sizes |
+| `COM_CALL_TIMEOUT` | `60` | Per-call live AutoCAD timeout (s); `0` disables |
+| `EZDXF_CALL_TIMEOUT` | `120` | Per-call headless timeout (s); `0` disables |
+| `DANGEROUS_COMMANDS_ENABLED` | `false` | Allow blocked commands/LISP; reported as unsafe mode |
 | `ALLOW_REMOTE_HTTP` | `false` | Permit a non-loopback HTTP bind |
-| `MCP_AUTH_TOKEN` | empty | Bearer token required for remote HTTP |
+| `MCP_AUTH_TOKEN` | *(empty)* | Bearer token required for remote HTTP |
 
-Backend selection:
-
-| Value | Behavior |
-|---|---|
-| `auto` | Try COM on Windows, then fall back to ezdxf |
-| `com` | Require a reachable live AutoCAD instance |
-| `ezdxf` | Force portable, headless DXF operation |
+</details>
 
 ## Architecture
 
 ```mermaid
 flowchart LR
-    A[MCP host / AI agent] --> B[FastMCP server]
-    B --> C[Error · audit · timing · logging middleware]
-    C --> D[Typed tool contract]
-    D --> E[COM backend]
-    D --> F[ezdxf backend]
+  A[MCP host / AI agent] --> B[FastMCP 3 server]
+  B --> C[Error · audit · timing · logging · capability-refusal middleware]
+  C --> D[Typed contract · 23 modules · 41 capability keys]
+  D --> E[COM backend<br/>single-STA thread]
+  D --> F[ezdxf backend<br/>asyncio.to_thread]
   E --> G[Live AutoCAD]
   F --> H[Headless DXF]
-    E --> I[Engineering quality + delivery]
+  E --> I[Engineering · critique · scoring · delivery]
   F --> I
 ```
 
-- `server.py` owns the FastMCP surface, lifespan, middleware, resources, and
-  prompt templates.
-- `backends/base.py` defines the shared contract and capability model.
-- `backends/com_backend.py` serializes COM calls through one STA thread with
-  per-call timeouts.
-- `backends/ezdxf_backend.py` wraps synchronous DXF work with
-  `asyncio.to_thread` and snapshot-based transactions.
-- `engineering/` contains standards-aware planning, drawing, critique, scoring,
-  refinement, validation, and delivery.
-- `security.py` centralizes path validation and command/LISP sanitization.
+<details>
+<summary><b>The drawing at the top of this page, as tool calls</b></summary>
 
-## Security model
+The sequence in [`scripts/render_readme_showcase.py`](https://github.com/U-C4N/Autocad-MCP/blob/main/scripts/render_readme_showcase.py), which produced the hero sheet:
 
-The server treats tool input as untrusted:
+```text
+drawing_new()                                    ISO linetypes + layers bootstrapped
+drawing_apply_iso_layers("mech")                 ISO 128 lineweights per layer
+drawing_settings({units: "mm", linear_precision: 2})
 
-- Every file path passes through traversal and allowed-root validation.
-- Dangerous AutoCAD commands and AutoLISP channels are blocked by default.
-- Remote HTTP requires explicit opt-in and a bearer token.
-- DXF size, query-result size, undo history, and COM call duration are bounded.
-- Audit middleware records tool timing and failures.
-- `system_status` and `system_about` expose `unsafe_mode` when dangerous
-  operations are enabled.
+gear_draw_spur_front_view(                       involute flanks, not a decorated circle
+    module=6, teeth=24, center=[135, 172],
+    bore_diameter=40, keyway_width=12, keyway_depth=3.3)
+gear_draw_section_aa(x_offset=300, face_width=46)
 
-`DANGEROUS_COMMANDS_ENABLED=true` is a trust decision, not an installation
-shortcut. Keep it disabled for agents or clients you do not fully control.
+dimension_linear(...)                            ISO 129
+dimension_diameter(..., fit="H7")                deviations from authored ISO 286 tables
+titleblock_apply_iso_a3(title="SPUR GEAR m6 z24", material="C45E", ...)
 
-Please avoid filing public issues for vulnerabilities. Contact the maintainer
-through [GitHub](https://github.com/U-C4N) first.
+drawing_critique(focus=None)                     -> []  must be empty before finalize
+view_screenshot()                                -> PNG
+```
+
+The full production loop adds `drawing_preflight` and `drawing_plan` at the front, `drawing_refine` after the critique, and `layout_create` + `viewport_create` + `drawing_deliver` at the end.
+
+</details>
 
 ## Development
 
 ```bash
-pip install -e ".[full]"
-pip install pytest pytest-asyncio pytest-cov ruff build
-python -m pytest
-python -m ruff check .
-python -m ruff format --check .
-python -m build
+uv sync --locked --all-extras
+uv run pytest
+uv run ruff check . && uv run ruff format --check .
 ```
 
-Focused benchmark checks:
+`uv.lock` pins the whole transitive graph, so this reproduces CI exactly. CI runs Linux (3.11 / 3.12) and Windows (mocked COM), plus package, Docker and MCP-registry jobs. The release gate runs the same three test lanes before anything reaches PyPI. Releases are tag-driven: `git tag vX.Y.Z && git push origin vX.Y.Z`.
 
-```bash
-python -m pytest tests/test_benchmark_chart.py tests/test_benchmark_v2.py -q
-python -m benchmarks.render_chart
-```
+## Roadmap (1.7)
 
-Repository map:
+- **Speed.** Win back the headless creation throughput that 1.6 lost against v1.4.0 (criterion 7): arm the per-call timeout only where a call can block, and remove the per-call work that came with it.
+- **IEC 60617 electrical schematics.** They reuse the P&ID track's symbol, port and graph machinery.
+- **Transcribed rows** for DIN 471/472, DIN 509, DIN 332 and ISO 3601-2, each verified against the standard's own table.
+- **HATCH boundary geometry in `entity_get`.** 1.5 and 1.6 measure a hatch's filled area but do not hand back its loops.
+- **`ezdxf.recover` as a fallback** on `drawing_open`.
+- **An allowlist of permitted AutoLISP heads**, replacing the denylist. Enumerating dangerous symbols does not terminate.
 
-```text
-server.py                 FastMCP surface and orchestration
-config.py                 Environment-driven settings
-security.py               Path, command, and AutoLISP guards
-version.py                Canonical package version
-backends/                 COM and ezdxf implementations
-engineering/              Standards, critique, refinement, delivery
-benchmarks/               Reproducible data, runners, and reports
-tests/                    Headless, mocked-COM, contract, and security tests
-```
+Features ship when their contracts and limitations are testable — not when they make a longer checklist.
 
-## Roadmap
+## Star History
 
-The next priorities are capability-aware tool discovery, paper-space/layout
-depth, ISO 286 fits, Windows CI coverage, opt-in COM 3D solids, and real
-cross-project runtime adapters. Features are published when their contracts and
-limitations are testable—not when they make a longer checklist.
-
-## Contributing
-
-Pull requests are welcome, especially for reproducible competitor adapters,
-mocked/live COM coverage, engineering standards, and backend parity. For a
-large change, open an issue first so the tool contract and evidence plan can be
-agreed before implementation.
+[![Star History Chart](https://api.star-history.com/svg?repos=U-C4N/U-Pool,U-C4N/Autocad-MCP&type=Date&legend=top-left)](https://www.star-history.com/#U-C4N/U-Pool&U-C4N/Autocad-MCP&Date&legend=top-left)
 
 ## Author
 
-**Umutcan Edizsalan** · Mechanical engineering work at **Anka-Makine** ·
-GitHub [@U-C4N](https://github.com/U-C4N)
+**Umutcan Edizsalan** · Mechanical engineering work at **Anka-Makine** · GitHub [@U-C4N](https://github.com/U-C4N)
 
 Built from production drawing work, then made model-agnostic through MCP.
 
 ## License
 
-[MIT](LICENSE)
+[MIT](https://github.com/U-C4N/Autocad-MCP/blob/main/LICENSE)
+
+<!-- MCP registry ownership marker; must equal the "name" in server.json. -->
+mcp-name: io.github.u-c4n/autocad-mcp

backends/__init__.py

@@ -1,4 +1,5 @@
 """AutoCAD MCP Pro – backend package."""
+
 from .base import AutoCADBackend, BlockInfo, DrawingInfo, EntityInfo, LayerInfo
 from .com_backend import ComBackend
 from .ezdxf_backend import EzdxfBackend

backends/block_specs.py

@@ -0,0 +1,278 @@
+# backends/block_specs.py
+"""Typed primitive specs for ``block_define``, validated before any write.
+
+Both engines consume the same normalised specs, so a malformed request is
+refused identically on COM and ezdxf and nothing is written on either. Every
+error names the offending entry (``entities[i]`` / ``attdefs[i]``) and key.
+"""
+
+from __future__ import annotations
+
+import math
+import re
+
+from security import illegal_symbol_name_chars
+
+ALLOWED_TYPES = ("line", "circle", "arc", "polyline", "text", "solid")
+TEXT_ALIGNMENTS = ("left", "center", "right", "middle_center")
+#: Checked with ``fullmatch`` — ``$`` alone would accept a trailing newline, which
+#: ezdxf then strips on write, turning two "distinct" tags into one duplicate.
+ATTDEF_TAG_RE = re.compile(r"^[A-Z][A-Z0-9_]{0,30}$")
+
+_REQUIRED = {
+    "line": ("x1", "y1", "x2", "y2"),
+    "circle": ("cx", "cy", "r"),
+    "arc": ("cx", "cy", "r", "start_deg", "end_deg"),
+    "polyline": ("points",),
+    "text": ("text", "x", "y", "height"),
+    "solid": ("points",),
+}
+_POSITIVE = {"r", "height"}
+
+
+def _scalar(value, where: str, *, positive: bool = False) -> float:
+    if isinstance(value, bool) or not isinstance(value, (int, float)):
+        raise TypeError(f"{where} must be a number, got {value!r}")
+    try:
+        number = float(value)
+    except OverflowError as exc:  # a 400-digit JSON integer is an int, not a float
+        raise TypeError(f"{where} must be finite") from exc
+    if not math.isfinite(number):
+        raise TypeError(f"{where} must be finite")
+    if positive and number <= 0:
+        raise TypeError(f"{where} must be > 0, got {number}")
+    return number
+
+
+def _number(spec: dict, key: str, where: str) -> float:
+    return _scalar(spec.get(key), f"{where}: {key!r}", positive=key in _POSITIVE)
+
+
+def _points(
+    spec: dict, where: str, *, minimum: int, maximum: int | None = None
+) -> list[tuple[float, float]]:
+    raw = spec.get("points")
+    if not isinstance(raw, (list, tuple)) or len(raw) < minimum:
+        raise TypeError(f"{where}: 'points' must be a list of at least {minimum} [x, y] pairs")
+    if maximum is not None and len(raw) > maximum:
+        raise TypeError(f"{where}: 'points' must have at most {maximum} pairs")
+    out: list[tuple[float, float]] = []
+    for i, pt in enumerate(raw):
+        if not isinstance(pt, (list, tuple)) or len(pt) != 2:
+            raise TypeError(f"{where}: points[{i}] must be an [x, y] pair")
+        out.append(
+            (
+                _scalar(pt[0], f"{where}: points[{i}].x"),
+                _scalar(pt[1], f"{where}: points[{i}].y"),
+            )
+        )
+    return out
+
+
+def _align(spec: dict, where: str) -> str:
+    align = spec.get("align", "left")
+    if align not in TEXT_ALIGNMENTS:
+        raise TypeError(f"{where}: 'align' must be one of {TEXT_ALIGNMENTS}, got {align!r}")
+    return align
+
+
+def _layer(spec: dict, where: str) -> str:
+    layer = spec.get("layer", "0")
+    if not isinstance(layer, str) or not layer.strip():
+        raise TypeError(f"{where}: 'layer' must be a non-empty string")
+    layer = layer.strip()
+    # Gate the DXF name rule here rather than letting ezdxf raise DXFValueError
+    # on `add_*(dxfattribs={"layer": ...})` mid-loop, after the block exists and
+    # earlier primitives are already written (and, with overwrite, the old
+    # definition is already gone).
+    offenders = illegal_symbol_name_chars(layer)
+    if offenders:
+        shown = ", ".join(repr(c) for c in offenders)
+        raise TypeError(f"{where}: 'layer' is not a legal DXF layer name (contains {shown})")
+    return layer
+
+
+def _one_line(value, where: str) -> str:
+    """A single-line DXF string (TEXT content, ATTDEF prompt/default).
+
+    ezdxf's DXFAttr fixer (``fix_one_line_text``) silently strips line breaks
+    and a trailing ``^`` on write, logged at DEBUG only, so the declared value
+    and the value read back would differ; COM writes the raw string, so the two
+    engines would also diverge. Refuse it here, before any write, using ezdxf's
+    own ``is_valid_one_line_text`` rule plus the other C0 controls DXF text
+    cannot carry.
+    """
+    if not isinstance(value, str):
+        raise TypeError(f"{where} must be a string")
+    controls = sorted({c for c in value if ord(c) < 32})
+    if controls:
+        shown = ", ".join(repr(c) for c in controls)
+        raise TypeError(
+            f"{where} must be a single line without control characters (contains {shown})"
+        )
+    if value.endswith("^"):
+        raise TypeError(f"{where} must not end with '^' (DXF strips a trailing caret)")
+    return value
+
+
+def validate_entity_specs(entities) -> list[dict]:
+    """Normalise ``block_define`` primitive specs; refuse the whole list on the first defect."""
+    if not isinstance(entities, (list, tuple)) or not entities:
+        raise ValueError(
+            "block_define: 'entities' is empty — a block that draws nothing is refused"
+        )
+    out: list[dict] = []
+    for i, spec in enumerate(entities):
+        where = f"entities[{i}]"
+        if not isinstance(spec, dict):
+            raise TypeError(f"{where}: must be an object")
+        kind = spec.get("type")
+        if kind not in ALLOWED_TYPES:
+            raise TypeError(f"{where}: 'type' must be one of {ALLOWED_TYPES}, got {kind!r}")
+        for key in _REQUIRED[kind]:
+            if key not in spec:
+                raise TypeError(f"{where}: {kind} requires {key!r}")
+        norm: dict = {"type": kind, "layer": _layer(spec, where)}
+        if kind == "line":
+            for key in ("x1", "y1", "x2", "y2"):
+                norm[key] = _number(spec, key, where)
+        elif kind == "circle":
+            for key in ("cx", "cy", "r"):
+                norm[key] = _number(spec, key, where)
+        elif kind == "arc":
+            for key in ("cx", "cy", "r", "start_deg", "end_deg"):
+                norm[key] = _number(spec, key, where)
+        elif kind == "polyline":
+            pts = _points(spec, where, minimum=2)
+            closed = spec.get("closed", False)
+            if not isinstance(closed, bool):
+                raise TypeError(f"{where}: 'closed' must be a boolean")
+            bulges = spec.get("bulges")
+            if bulges is not None:
+                if not isinstance(bulges, (list, tuple)) or len(bulges) != len(pts):
+                    raise TypeError(f"{where}: 'bulges' must list one value per point")
+                bulges = [_scalar(b, f"{where}: bulges[{j}]") for j, b in enumerate(bulges)]
+            norm.update(points=pts, closed=closed, bulges=list(bulges) if bulges else None)
+        elif kind == "text":
+            norm.update(
+                text=_one_line(spec.get("text"), f"{where}: 'text'"),
+                x=_number(spec, "x", where),
+                y=_number(spec, "y", where),
+                height=_number(spec, "height", where),
+                rotation_deg=_scalar(spec.get("rotation_deg", 0.0), f"{where}: 'rotation_deg'"),
+                align=_align(spec, where),
+            )
+        elif kind == "solid":
+            norm["points"] = _points(spec, where, minimum=3, maximum=4)
+        out.append(norm)
+    return out
+
+
+def validate_attdef_specs(attdefs) -> list[dict]:
+    """Normalise ATTDEF specs: tag pattern, uniqueness, numeric fields, flags."""
+    if attdefs is None:
+        return []
+    if not isinstance(attdefs, (list, tuple)):
+        raise TypeError("block_define: 'attdefs' must be a list")
+    out: list[dict] = []
+    seen: set[str] = set()
+    for i, spec in enumerate(attdefs):
+        where = f"attdefs[{i}]"
+        if not isinstance(spec, dict):
+            raise TypeError(f"{where}: must be an object")
+        tag = spec.get("tag")
+        if not isinstance(tag, str) or not ATTDEF_TAG_RE.fullmatch(tag):
+            raise TypeError(f"{where}: 'tag' must match {ATTDEF_TAG_RE.pattern}, got {tag!r}")
+        if tag in seen:
+            raise TypeError(f"{where}: duplicate tag {tag!r}")
+        seen.add(tag)
+        prompt = _one_line(spec.get("prompt", tag), f"{where}: 'prompt'")
+        default = _one_line(spec.get("default", ""), f"{where}: 'default'")
+        invisible = spec.get("invisible", False)
+        if not isinstance(invisible, bool):
+            raise TypeError(f"{where}: 'invisible' must be a boolean")
+        out.append(
+            {
+                "tag": tag,
+                "prompt": prompt,
+                "default": default,
+                "x": _number(spec, "x", where),
+                "y": _number(spec, "y", where),
+                "height": _number(spec, "height", where),
+                "rotation_deg": _scalar(spec.get("rotation_deg", 0.0), f"{where}: 'rotation_deg'"),
+                "align": _align(spec, where),
+                "invisible": invisible,
+            }
+        )
+    return out
+
+
+def validate_base_point(base_x, base_y) -> tuple[float, float]:
+    """``block_define``'s base point as finite floats; ``TypeError`` names the key.
+
+    Only ``float()`` was applied before, so ``float("nan")`` was written into
+    the BLOCK record headlessly and would reach AutoCAD as a NaN VARIANT.
+    """
+    return (
+        _scalar(base_x, "block_define: 'base_x'"),
+        _scalar(base_y, "block_define: 'base_y'"),
+    )
+
+
+def referenced_layers(entities: list[dict]) -> list[str]:
+    """The distinct layers ``block_define``'s primitives reference, other than ``0``.
+
+    DXF and ActiveX layer tables are case-insensitive, so the set is keyed on
+    the folded name and keeps the first spelling seen: a request naming
+    ``Alpha`` and ``ALPHA`` wants *one* layer. Deduping case-sensitively let
+    ezdxf write ``ALPHA`` and then raise ``DXFTableEntryError`` on ``Alpha``
+    mid-call, and let COM report two layers created for one ``Layers.Add``
+    that took effect.
+    """
+    seen: dict[str, str] = {}
+    for spec in entities:
+        layer = spec["layer"]
+        if layer != "0" and layer.lower() not in seen:
+            seen[layer.lower()] = layer
+    return sorted(seen.values())
+
+
+def validate_attribute_values(attributes, where: str = "attributes") -> dict[str, str]:
+    """``{TAG: value}`` for ``block_insert`` / ``block_set_attributes`` as the
+    strings that will be written, refused before any write.
+
+    ``str(value)`` used to be applied to whatever arrived, so a JSON ``null``
+    became the text ``None``, ``true`` became ``True`` and an object became its
+    Python repr — silently, on both engines. A string is taken as is (one line,
+    the DXF rule ``_one_line`` enforces); an int or a finite float is written
+    with ``str`` (``101`` → ``"101"``, ``2.5`` → ``"2.5"``); ``bool``, ``None``,
+    lists and objects are refused by tag. ``None`` for the whole mapping means
+    "no attributes".
+    """
+    if attributes is None:
+        return {}
+    if not isinstance(attributes, dict):
+        raise TypeError(f"{where} must be an object of {{TAG: value}} pairs")
+    out: dict[str, str] = {}
+    for tag, value in attributes.items():
+        if not isinstance(tag, str) or not tag.strip():
+            raise TypeError(f"{where}: every tag must be a non-empty string")
+        label = f"{where}[{tag!r}]"
+        if isinstance(value, str):
+            out[tag] = _one_line(value, label)
+        elif isinstance(value, bool) or value is None or not isinstance(value, (int, float)):
+            raise TypeError(f"{label} must be a string or a number, got {type(value).__name__}")
+        else:
+            if isinstance(value, float) and not math.isfinite(value):
+                raise TypeError(f"{label} must be finite")
+            out[tag] = str(value)
+    return out
+
+
+def solid_vertices(points: list[tuple[float, float]]) -> list[tuple[float, float]]:
+    """DXF SOLID draws vtx0→vtx1→vtx3→vtx2, so a quad given in polygon order
+    (a, b, c, d) is stored as (a, b, d, c). Triangles are stored as given."""
+    pts = [(float(x), float(y)) for x, y in points]
+    if len(pts) == 4:
+        return [pts[0], pts[1], pts[3], pts[2]]
+    return pts

backends/capability.py

@@ -0,0 +1,134 @@
+"""Optional contract methods: declared once, refused loudly, gated by a test.
+
+The backend contract is large (112 abstract methods before this file existed,
+and the plan adds ~39 more). Every one of them is an `@abstractmethod`, which
+means adding a single method to the contract makes **both** backends fail at
+instantiation until both are written — and two test modules construct
+`ComBackend` at import time, so the whole suite goes red on a half-finished
+edit. That is a real cost paid on every contract change.
+
+The obvious fix is to give new methods a default body. The obvious default is
+wrong: returning ``{"ok": False, "capability": ...}`` from a method nobody
+implemented produces exactly the quiet "this didn't work and nothing told you"
+that the v1.5.0 honesty pass spent a milestone deleting. A default that lies
+quietly is worse than a build break.
+
+So `@capability` gives a default that **raises**
+`UnsupportedCapabilityError` — the same typed refusal the deliberate
+boundaries raise, carrying the same `capability` key, surfaced by the same
+`CapabilityRefusalMiddleware`, and indistinguishable to a client from a
+hand-written refusal. Three properties follow:
+
+* An unimplemented method refuses instead of pretending. It cannot silently
+  succeed and it cannot silently do nothing.
+* The refusal is *declared*: `test_capability_contract.py` fails if a key used here is
+  missing from either backend's `CapabilityMap`, so `system_capabilities` can
+  never disagree with what a call actually does. This is the part that keeps
+  the escape hatch honest — without it, `@capability` would just be a way to
+  ship undeclared holes.
+* Overriding is ordinary subclassing. A backend that implements the method
+  simply defines it; nothing needs to be un-registered.
+
+`@abstractmethod` remains the default for anything both backends must have.
+Reach for `@capability` only when a method is genuinely optional — an engine
+boundary (no ACIS kernel headlessly) rather than an unfinished chore.
+"""
+
+from __future__ import annotations
+
+import functools
+from collections.abc import Callable
+from typing import Any
+
+__all__ = [
+    "UnsupportedCapabilityError",
+    "capability",
+    "capability_keys",
+    "is_capability_default",
+]
+
+
+# ---------------------------------------------------------------------------
+# The refusal vocabulary
+#
+# This lives here rather than in ``backends.base`` because the contracts import
+# the decorator and ``base`` imports the contracts — putting the exception in
+# ``base`` makes that a cycle. ``backends.base`` re-exports both names, so
+# ``from backends.base import UnsupportedCapabilityError`` is unchanged for the
+# rest of the repo.
+#
+# There is exactly one authoring rule: a backend that cannot do a thing RAISES
+# ``UnsupportedCapabilityError(capability, message)``, where ``capability`` is a
+# key of ``capabilities().features`` so a client can pre-check the same boundary
+# through ``system_capabilities`` instead of parsing English. Tools never catch
+# it and never hand-build refusal payloads — one middleware turns it into the
+# wire payload, and ``cad_batch`` turns it into a step row. One class object,
+# defined once: two look-alike types would silently break every ``isinstance``
+# classifier.
+#
+# The ``{"ok": False, "error": ...}`` returned-dict shape stays legal only for
+# soft failures that are not capability boundaries ("Layout not found", "No
+# active transaction").
+# ---------------------------------------------------------------------------
+
+
+def _unsupported(error: str, capability_key: str) -> dict:
+    """Build a backend's machine-readable "this backend can't" payload."""
+    return {"ok": False, "error": error, "capability": capability_key}
+
+
+class UnsupportedCapabilityError(RuntimeError):
+    """Raised when a call needs a capability this backend does not have.
+
+    Stays a plain ``RuntimeError``: rebasing it on ``FastMCPError`` was measured
+    and changes nothing a client can observe, because the refusal is carried by
+    ``ToolResult(structured_content=..., is_error=True)`` rather than by the
+    exception class. ``to_dict()`` keeps the ``{ok, error, capability}`` payload
+    attached to the raise so the boundary survives the ``__cause__`` chain.
+    """
+
+    def __init__(self, capability: str, error: str):
+        super().__init__(error)
+        self.capability = capability
+
+    def to_dict(self) -> dict:
+        return _unsupported(str(self), self.capability)
+
+
+#: ``{capability_key: (method_name, ...)}`` for every method declared optional.
+#: Populated at import by the decorator and read by the parity gate.
+_REGISTRY: dict[str, set[str]] = {}
+
+
+def capability(key: str, *, reason: str = "") -> Callable[[Callable], Callable]:
+    """Mark a contract method optional, defaulting to a typed refusal.
+
+    Args:
+        key: capability name; must appear in **both** backends' capability maps.
+        reason: appended to the refusal message. Say what the caller can do
+            instead, not merely that they cannot do this.
+    """
+
+    def decorate(func: Callable) -> Callable:
+        @functools.wraps(func)
+        async def default(self, *args: Any, **kwargs: Any):
+            message = f"{func.__name__}: not supported by the {self.name} backend"
+            raise UnsupportedCapabilityError(key, f"{message}. {reason}".rstrip())
+
+        default.__capability__ = key
+        default.__is_capability_default__ = True
+        _REGISTRY.setdefault(key, set()).add(func.__name__)
+        return default
+
+    return decorate
+
+
+def capability_keys() -> dict[str, set[str]]:
+    """Every optional-capability key and the methods declared under it."""
+    return {key: set(names) for key, names in _REGISTRY.items()}
+
+
+def is_capability_default(owner: type, method_name: str) -> bool:
+    """True when ``owner`` inherited the refusing default rather than implementing it."""
+    attribute = getattr(owner, method_name, None)
+    return bool(getattr(attribute, "__is_capability_default__", False))

backends/contracts/__init__.py

@@ -0,0 +1,59 @@
+"""Per-domain slices of the backend contract.
+
+One 1854-line ABC with 112 abstract methods made every contract change a
+whole-file edit, and made a half-finished change break both backends at
+instantiation at once. The seams here are the section markers that were
+already in the file, so the split moved code without re-deciding anything.
+"""
+
+from __future__ import annotations
+
+from backends.contracts.analysis import AnalysisContract
+from backends.contracts.blocks import BlockContract
+from backends.contracts.corner_ops import CornerOpsContract
+from backends.contracts.dimensions import DimensionContract
+from backends.contracts.drawing import DrawingContract
+from backends.contracts.entity_creation import EntityCreationContract
+from backends.contracts.entity_modification import EntityModificationContract
+from backends.contracts.entity_query import EntityQueryContract
+from backends.contracts.environment import EnvironmentContract
+from backends.contracts.gdt import GdtContract
+from backends.contracts.identity import IdentityContract
+from backends.contracts.layers import LayerContract
+from backends.contracts.layouts import LayoutContract
+from backends.contracts.linetypes import LinetypeContract
+from backends.contracts.pagesetup import PageSetupContract
+from backends.contracts.premium import PremiumContract
+from backends.contracts.refs import RefsContract
+from backends.contracts.settings import SettingsContract
+from backends.contracts.solids import SolidContract
+from backends.contracts.styles import StylesContract
+from backends.contracts.system import SystemContract
+from backends.contracts.transactions import TransactionContract
+from backends.contracts.view import ViewContract
+
+__all__ = [
+    "AnalysisContract",
+    "BlockContract",
+    "CornerOpsContract",
+    "DimensionContract",
+    "DrawingContract",
+    "EntityCreationContract",
+    "EntityModificationContract",
+    "EntityQueryContract",
+    "EnvironmentContract",
+    "GdtContract",
+    "IdentityContract",
+    "LayerContract",
+    "LayoutContract",
+    "LinetypeContract",
+    "PageSetupContract",
+    "PremiumContract",
+    "RefsContract",
+    "SettingsContract",
+    "SolidContract",
+    "StylesContract",
+    "SystemContract",
+    "TransactionContract",
+    "ViewContract",
+]

backends/contracts/analysis.py

@@ -0,0 +1,175 @@
+"""Measurement and analysis.
+
+Split out of the single 1854-line ``AutoCADBackend`` ABC in v1.5.0 (M7).
+``AutoCADBackend`` composes every contract in this package, so importing
+``backends.base.AutoCADBackend`` is unchanged for callers.
+"""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from typing import TYPE_CHECKING
+
+from backends.capability import capability
+
+if TYPE_CHECKING:
+    from backends.base import EntityInfo
+
+
+class AnalysisContract(ABC):
+    # ── boundary tracing (M8 / F3) ───────────────────────────────────────────
+
+    @capability(  # noqa: B027 — @capability supplies the body
+        "boundary_trace",
+        reason=(
+            "ActiveX exposes no BOUNDARY member; the live path would have to drive the "
+            "-BOUNDARY command blind, which has not been verified against a live AutoCAD. "
+            "Use the headless backend (AUTOCAD_MCP_BACKEND=ezdxf), or run BOUNDARY in "
+            "AutoCAD directly."
+        ),
+    )
+    async def boundary_trace(
+        self, x: float, y: float, layer: str | None = None, tolerance: float = 1e-9
+    ) -> dict:
+        """AutoCAD's BOUNDARY/BPOLY: trace the closed loop enclosing a seed point.
+
+        Returns ``{ok, handle, vertices, area, closed, source_handles}``.
+        ``vertices`` is a count, ``area`` is unsigned.
+
+        Implementations must not enumerate every loop in the drawing:
+        ``edgeminer.find_all_loops`` is O(n!) and was measured at 63.9 s for 40
+        edges and a timeout at 60. The seed point picks a starting edge and one
+        loop is walked from it.
+
+        A seed with no enclosing loop is refused. Returning an empty boundary
+        would be a boundary that bounds nothing, reported as success.
+        """
+        ...
+
+    @capability(  # noqa: B027 — @capability supplies the body
+        "boundary_trace",
+        reason=(
+            "Chaining arbitrary entities into a loop needs the same edge graph BOUNDARY "
+            "does, which ActiveX does not expose. Use the headless backend "
+            "(AUTOCAD_MCP_BACKEND=ezdxf)."
+        ),
+    )
+    async def boundary_from_entities(self, handles: list[str], tolerance: float = 1e-9) -> dict:
+        """Chain the given entities into one closed polyline.
+
+        Returns ``{ok, handle, vertices, area, closed}``. Refuses a chain that
+        does not close, naming the coordinates of the endpoint that dangles —
+        "these do not form a loop" is not actionable without the gap.
+        """
+        ...
+
+    @abstractmethod
+    async def analysis_list_properties(self, handle: str) -> dict:
+        """AutoCAD's LIST: the full DXF attribute set for one handle.
+
+        Returns ``{ok, handle, type, layer, properties, dxf_attributes}``.
+        ``properties`` mirrors what ``entity_get`` reports; ``dxf_attributes``
+        is the raw attribute set that ``entity_get`` deliberately does not
+        carry.
+
+        Two things the raw dump cannot be handed over as-is. It holds ``Vec3``
+        values, so it is not JSON-serialisable and would die at the wire
+        boundary; and its coordinates are stored in the entity's own frame, so
+        for anything with an extrusion they would contradict every other
+        coordinate this server reports. Both are converted here, and
+        ``extrusion`` stays in the dump so the original frame is still visible.
+        """
+        ...
+
+    @abstractmethod
+    async def analysis_stats(self) -> dict: ...
+
+    @abstractmethod
+    async def analysis_entities_in_region(
+        self,
+        x1: float,
+        y1: float,
+        x2: float,
+        y2: float,
+    ) -> list[EntityInfo]: ...
+
+    @abstractmethod
+    async def analysis_measure_distance(
+        self,
+        x1: float,
+        y1: float,
+        x2: float,
+        y2: float,
+    ) -> float: ...
+
+    @abstractmethod
+    async def analysis_measure_area(self, points: list[list[float]]) -> float: ...
+
+    @abstractmethod
+    async def entity_measure(self, handle: str, flatten_tolerance: float = 0.001) -> dict:
+        """Area and perimeter of ONE existing entity, addressed by handle.
+
+        Returns ``{"handle", "type", "area", "perimeter", "closed",
+        "assumed_closed", "method", "exact", "flatten_tolerance", "backend",
+        "self_intersecting", "perimeter_exact", "loop_count"}``.
+
+        A HATCH is measured as the area it *fills* — outer loops minus the
+        islands inside them — and the headless engine adds ``hatch_style``
+        (``normal``/``outer``/``ignore``) so the number can be read against the
+        drawing's own island setting. The live backend does not carry that key:
+        it reads ActiveX ``.Area``, which **does** apply the island style —
+        verified on a live AutoCAD 2026 (2026-08-06): a hatch of r20 with an
+        r10 island returns 942.478, which is pi*(400-100).
+
+        ``perimeter`` is ``None`` where ActiveX exposes no length member for the
+        type, and ``perimeter_exact`` is then False. The member differs per
+        type and was measured rather than assumed: LWPOLYLINE ``.Length``,
+        CIRCLE ``.Circumference``, REGION ``.Perimeter``, HATCH none. A
+        3DSOLID has no ``.Area`` at all — only ``.Volume`` — and is refused by
+        name.
+        A missing perimeter is not a reason to discard an area that was read
+        successfully — doing exactly that is what made this method raise on
+        every ACIS type it advertised.
+
+        ``exact`` and
+        ``flatten_tolerance`` are the accuracy disclosure: when one engine can
+        answer in closed form and the other has to flatten, the payload says so
+        rather than leaving two numbers to quietly disagree.
+
+        Two different refusals, and the difference matters. A type that bounds no
+        area at all (LINE, TEXT, a 3D polyline) raises a plain ``RuntimeError``:
+        no engine can measure it, so tagging a capability would falsely suggest
+        switching backends helps. A type this *engine* cannot evaluate (ACIS
+        solids headlessly) raises ``UnsupportedCapabilityError``, which names the
+        engine that can.
+        """
+        ...
+
+    @abstractmethod
+    async def analysis_bounding_box(self) -> dict: ...
+
+    @abstractmethod
+    async def analysis_select_by_layer(self, layer_name: str) -> list[EntityInfo]: ...
+
+    @abstractmethod
+    async def analysis_select_by_type(self, entity_type: str) -> list[EntityInfo]: ...
+
+    @abstractmethod
+    async def selection_get(self) -> dict:
+        """Read the live viewport's implied ("pickfirst") selection set.
+
+        COM-only / meaningful only with live AutoCAD. Returns a dict::
+
+            {
+                "ok": bool,                # True on COM even for an empty pick
+                "count": int,
+                "handles": list[str],      # entity handles to act on
+                "entities": list[EntityInfo],  # _dc()-converted by the server
+                "pickfirst": bool | None,  # state of the PICKFIRST sysvar
+                "message" / "error": str,  # optional guidance / failure reason
+            }
+
+        The ezdxf headless backend has no viewport, so it returns ``ok=False``
+        with an empty ``handles`` list (same shape, never raises).
+        """
+        ...

backends/contracts/blocks.py

@@ -0,0 +1,76 @@
+"""Blocks and block references.
+
+Split out of the single 1854-line ``AutoCADBackend`` ABC in v1.5.0 (M7).
+``AutoCADBackend`` composes every contract in this package, so importing
+``backends.base.AutoCADBackend`` is unchanged for callers.
+"""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from backends.base import BlockInfo, EntityInfo
+
+
+class BlockContract(ABC):
+    @abstractmethod
+    async def block_list(self) -> list[BlockInfo]: ...
+
+    @abstractmethod
+    async def block_insert(
+        self,
+        name: str,
+        x: float,
+        y: float,
+        scale_x: float = 1.0,
+        scale_y: float = 1.0,
+        rotation: float = 0.0,
+        attributes: dict | None = None,
+        layer: str | None = None,
+    ) -> EntityInfo: ...
+
+    @abstractmethod
+    async def block_explode(self, handle: str) -> dict: ...
+
+    @abstractmethod
+    async def block_get_attributes(self, handle: str) -> dict: ...
+
+    @abstractmethod
+    async def block_set_attributes(self, handle: str, attributes: dict) -> dict: ...
+
+    @abstractmethod
+    async def block_create_from_entities(
+        self,
+        name: str,
+        handles: list[str],
+        base_x: float = 0.0,
+        base_y: float = 0.0,
+    ) -> dict: ...
+
+    @abstractmethod
+    async def block_define(
+        self,
+        name: str,
+        entities: list[dict],
+        attdefs: list[dict] | None = None,
+        base_x: float = 0.0,
+        base_y: float = 0.0,
+        overwrite: bool = False,
+        create_layers: bool = False,
+    ) -> dict:
+        """Create (or with ``overwrite`` replace the contents of) a block
+        definition from typed primitive specs and ATTDEF specs — see
+        ``backends/block_specs.py`` for the spec vocabulary.
+
+        Refusals, all before any write: a malformed spec (``TypeError`` naming
+        ``entities[i]``/``attdefs[i]`` and the key), a non-finite or non-numeric
+        ``base_x``/``base_y`` (``TypeError`` naming it), a name clash without
+        ``overwrite`` (``ValueError``), and a primitive ``layer`` that does not
+        exist in the drawing (``ValueError`` listing the missing names) unless
+        ``create_layers`` is true, in which case the missing layers are created
+        with the engine's defaults and listed in ``layers_created``. Returns
+        ``{ok, name, entity_count, attdef_count, replaced, layers_created,
+        backend}``."""
+        ...

backends/contracts/corner_ops.py

@@ -0,0 +1,66 @@
+"""Trim, extend, fillet, chamfer.
+
+Split out of the single 1854-line ``AutoCADBackend`` ABC in v1.5.0 (M7).
+``AutoCADBackend`` composes every contract in this package, so importing
+``backends.base.AutoCADBackend`` is unchanged for callers.
+"""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from backends.base import EntityInfo
+
+
+class CornerOpsContract(ABC):
+    @abstractmethod
+    async def entity_trim(
+        self,
+        target_handle: str,
+        cutter_handle: str,
+        keep_x: float,
+        keep_y: float,
+    ) -> EntityInfo:
+        """Trim `target` against `cutter`; keep the segment containing
+        (keep_x, keep_y). Raises ToolError if no intersection."""
+        ...
+
+    @abstractmethod
+    async def entity_extend(
+        self,
+        target_handle: str,
+        boundary_handle: str,
+        end_x: float | None = None,
+        end_y: float | None = None,
+    ) -> EntityInfo:
+        """Extend `target` to meet `boundary`. If `end_x/y` is None, the
+        target endpoint nearest the boundary is auto-selected."""
+        ...
+
+    @abstractmethod
+    async def entity_fillet(
+        self,
+        handle1: str,
+        handle2: str,
+        radius: float,
+        trim: bool = True,
+    ) -> EntityInfo:
+        """Fillet two entities with the given radius. Returns the new ARC.
+        When `trim` is True (default), the source entities are shortened
+        to the tangent points (AutoCAD default behaviour)."""
+        ...
+
+    @abstractmethod
+    async def entity_chamfer(
+        self,
+        handle1: str,
+        handle2: str,
+        dist1: float,
+        dist2: float | None = None,
+        trim: bool = True,
+    ) -> EntityInfo:
+        """Chamfer two entities. When `dist2` is None it defaults to `dist1`
+        (symmetric chamfer). Returns the new chamfer LINE."""
+        ...

backends/contracts/dimensions.py

@@ -0,0 +1,89 @@
+"""ISO 129 dimensions.
+
+Split out of the single 1854-line ``AutoCADBackend`` ABC in v1.5.0 (M7).
+``AutoCADBackend`` composes every contract in this package, so importing
+``backends.base.AutoCADBackend`` is unchanged for callers.
+"""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from backends.base import EntityInfo
+
+
+class DimensionContract(ABC):
+    @abstractmethod
+    async def dimension_linear(
+        self,
+        x1: float,
+        y1: float,
+        x2: float,
+        y2: float,
+        dim_x: float,
+        dim_y: float,
+        rotation: float = 0.0,
+        layer: str | None = None,
+        tol_upper: float | None = None,
+        tol_lower: float | None = None,
+        tol_mode: str = "none",
+        text_override: str | None = None,
+    ) -> EntityInfo: ...
+
+    @abstractmethod
+    async def dimension_aligned(
+        self,
+        x1: float,
+        y1: float,
+        x2: float,
+        y2: float,
+        dim_x: float,
+        dim_y: float,
+        layer: str | None = None,
+    ) -> EntityInfo: ...
+
+    @abstractmethod
+    async def dimension_angular(
+        self,
+        vx: float,
+        vy: float,
+        x1: float,
+        y1: float,
+        x2: float,
+        y2: float,
+        tx: float,
+        ty: float,
+        layer: str | None = None,
+    ) -> EntityInfo: ...
+
+    @abstractmethod
+    async def dimension_radius(
+        self,
+        cx: float,
+        cy: float,
+        chord_x: float,
+        chord_y: float,
+        leader_length: float = 10.0,
+        layer: str | None = None,
+        tol_upper: float | None = None,
+        tol_lower: float | None = None,
+        tol_mode: str = "none",
+        text_override: str | None = None,
+    ) -> EntityInfo: ...
+
+    @abstractmethod
+    async def dimension_diameter(
+        self,
+        x1: float,
+        y1: float,
+        x2: float,
+        y2: float,
+        leader_length: float = 10.0,
+        layer: str | None = None,
+        tol_upper: float | None = None,
+        tol_lower: float | None = None,
+        tol_mode: str = "none",
+        text_override: str | None = None,
+    ) -> EntityInfo: ...

backends/contracts/drawing.py

@@ -0,0 +1,40 @@
+"""Document lifecycle.
+
+Split out of the single 1854-line ``AutoCADBackend`` ABC in v1.5.0 (M7).
+``AutoCADBackend`` composes every contract in this package, so importing
+``backends.base.AutoCADBackend`` is unchanged for callers.
+"""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from backends.base import DrawingInfo
+
+
+class DrawingContract(ABC):
+    @abstractmethod
+    async def drawing_info(self) -> DrawingInfo: ...
+
+    @abstractmethod
+    async def drawing_new(self, template: str | None = None) -> dict: ...
+
+    @abstractmethod
+    async def drawing_open(self, path: str) -> dict: ...
+
+    @abstractmethod
+    async def drawing_save(self, path: str | None = None) -> dict: ...
+
+    @abstractmethod
+    async def drawing_save_as(self, path: str, fmt: str = "dwg") -> dict: ...
+
+    @abstractmethod
+    async def drawing_export_dxf(self, path: str) -> dict: ...
+
+    @abstractmethod
+    async def drawing_export_pdf(self, path: str, layout: str | None = None) -> dict: ...
+
+    @abstractmethod
+    async def drawing_purge(self) -> dict: ...

backends/contracts/entity_creation.py

@@ -0,0 +1,255 @@
+"""Creating geometry.
+
+Split out of the single 1854-line ``AutoCADBackend`` ABC in v1.5.0 (M7).
+``AutoCADBackend`` composes every contract in this package, so importing
+``backends.base.AutoCADBackend`` is unchanged for callers.
+"""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from typing import TYPE_CHECKING
+
+from backends.capability import capability
+
+if TYPE_CHECKING:
+    from backends.base import EntityInfo
+
+
+class EntityCreationContract(ABC):
+    @abstractmethod
+    async def entity_create_line(
+        self,
+        x1: float,
+        y1: float,
+        x2: float,
+        y2: float,
+        z1: float = 0.0,
+        z2: float = 0.0,
+        layer: str | None = None,
+        color: int | None = None,
+        linetype: str | None = None,
+    ) -> EntityInfo: ...
+
+    @abstractmethod
+    async def entity_create_circle(
+        self,
+        cx: float,
+        cy: float,
+        radius: float,
+        layer: str | None = None,
+        color: int | None = None,
+    ) -> EntityInfo: ...
+
+    @abstractmethod
+    async def entity_create_arc(
+        self,
+        cx: float,
+        cy: float,
+        radius: float,
+        start_angle: float,
+        end_angle: float,
+        layer: str | None = None,
+        color: int | None = None,
+    ) -> EntityInfo: ...
+
+    @abstractmethod
+    async def entity_create_polyline(
+        self,
+        points: list[list[float]],
+        closed: bool = False,
+        layer: str | None = None,
+        color: int | None = None,
+    ) -> EntityInfo: ...
+
+    @abstractmethod
+    async def entity_create_text(
+        self,
+        text: str,
+        x: float,
+        y: float,
+        height: float = 2.5,
+        rotation: float = 0.0,
+        layer: str | None = None,
+        color: int | None = None,
+    ) -> EntityInfo: ...
+
+    @abstractmethod
+    async def entity_create_mtext(
+        self,
+        text: str,
+        x: float,
+        y: float,
+        width: float = 100.0,
+        height: float = 2.5,
+        rotation: float = 0.0,
+        layer: str | None = None,
+        color: int | None = None,
+    ) -> EntityInfo: ...
+
+    @abstractmethod
+    async def entity_create_table(
+        self,
+        x: float,
+        y: float,
+        rows: list[list[str]],
+        headers: list[str] | None = None,
+        column_widths: list[float] | None = None,
+        row_height: float = 7.0,
+        text_height: float = 2.5,
+        title: str | None = None,
+        layer: str = "TEXT",
+    ) -> EntityInfo: ...
+
+    @abstractmethod
+    async def leader_create_mleader(
+        self,
+        points: list[list[float]],
+        text: str,
+        text_height: float = 2.5,
+        landing_gap: float = 1.0,
+        arrow_size: float = 2.5,
+        layer: str = "DIM",
+    ) -> EntityInfo: ...
+
+    @abstractmethod
+    async def entity_create_hatch(
+        self,
+        pattern: str,
+        boundary_points: list[list[float]],
+        scale: float = 1.0,
+        angle: float = 0.0,
+        layer: str | None = None,
+        color: int | None = None,
+    ) -> EntityInfo: ...
+
+    @abstractmethod
+    async def entity_create_spline(
+        self,
+        fit_points: list[list[float]],
+        layer: str | None = None,
+        color: int | None = None,
+    ) -> EntityInfo: ...
+
+    @abstractmethod
+    async def entity_create_ellipse(
+        self,
+        cx: float,
+        cy: float,
+        major_x: float,
+        major_y: float,
+        ratio: float = 0.5,
+        layer: str | None = None,
+        color: int | None = None,
+    ) -> EntityInfo: ...
+
+    @abstractmethod
+    async def entity_create_point(
+        self,
+        x: float,
+        y: float,
+        layer: str | None = None,
+        color: int | None = None,
+    ) -> EntityInfo: ...
+
+    @abstractmethod
+    async def entity_create_block_ref(
+        self,
+        name: str,
+        x: float,
+        y: float,
+        scale_x: float = 1.0,
+        scale_y: float = 1.0,
+        rotation: float = 0.0,
+        layer: str | None = None,
+    ) -> EntityInfo: ...
+
+    # ── hatch depth (M8 / F4) ────────────────────────────────────────────────
+
+    @abstractmethod
+    async def hatch_set_gradient(
+        self,
+        handle: str,
+        color1: list[int],
+        color2: list[int],
+        rotation: float = 0.0,
+        centered: float = 0.0,
+        one_color: bool = False,
+        tint: float = 0.0,
+        name: str = "LINEAR",
+    ) -> dict:
+        """Replace a hatch's fill with a two-colour gradient. ``{ok, handle, gradient}``."""
+        ...
+
+    @abstractmethod
+    async def hatch_edit(
+        self,
+        handle: str,
+        pattern: str = "",
+        scale: float | None = None,
+        angle: float | None = None,
+        color: int | None = None,
+        style: str = "",
+    ) -> dict:
+        """Edit an existing hatch in place. Returns ``{ok, handle, changed}``.
+
+        ``changed`` names exactly the attributes that moved: an omitted
+        parameter must leave its attribute alone, because a partial edit that
+        quietly resets the rest is data loss. ``style`` is the island style —
+        ``normal``, ``outer`` or ``ignore``.
+        """
+        ...
+
+    @abstractmethod
+    async def hatch_add_boundary(self, handle: str, edges: list[dict]) -> dict:
+        """Add one boundary path built from typed edges.
+
+        Returns ``{ok, handle, path_count, edge_types}``. Edges are
+        ``{"type": "line"|"arc"|"ellipse", ...}``. Typed edges exist because a
+        boundary API that only accepts vertex lists silently straightens every
+        curve it is given.
+        """
+        ...
+
+    # ── annotation objects (M8 / F15) ────────────────────────────────────────
+
+    @capability(  # noqa: B027 — @capability supplies the body
+        "wipeout",
+        reason=(
+            "ActiveX has no wipeout constructor — ModelSpace.AddWipeout does not exist "
+            "(verified against AutoCAD 2026); WIPEOUT is a command only. Use the headless "
+            "backend (AUTOCAD_MCP_BACKEND=ezdxf), or run WIPEOUT in AutoCAD directly."
+        ),
+    )
+    async def entity_create_wipeout(
+        self, points: list[list[float]], layer: str | None = None
+    ) -> dict:
+        """Mask the drawing behind a closed polygon. Returns ``{ok, handle, points}``.
+
+        Refuses fewer than three points: a zero-area mask masks nothing while
+        reporting success.
+        """
+        ...
+
+    @capability(  # noqa: B027 — @capability supplies the body
+        "revcloud",
+        reason=(
+            "ActiveX exposes no revision-cloud member and driving the REVCLOUD command "
+            "blind against a live drawing is unverified. Use the headless backend "
+            "(AUTOCAD_MCP_BACKEND=ezdxf), or run REVCLOUD in AutoCAD directly."
+        ),
+    )
+    async def entity_create_revcloud(
+        self,
+        points: list[list[float]],
+        segment_length: float,
+        layer: str | None = None,
+        closed: bool = True,
+    ) -> dict:
+        """Draw a revision cloud along a path. Returns ``{ok, handle, segments}``.
+
+        A revision cloud *is* a polyline whose every segment carries an arc
+        bulge; a segment length longer than the path yields no arcs at all, so
+        that case is refused rather than returned as a rectangle.
+        """
+        ...

backends/contracts/entity_modification.py

@@ -0,0 +1,125 @@
+"""Moving, copying and editing geometry.
+
+Split out of the single 1854-line ``AutoCADBackend`` ABC in v1.5.0 (M7).
+``AutoCADBackend`` composes every contract in this package, so importing
+``backends.base.AutoCADBackend`` is unchanged for callers.
+"""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from backends.base import EntityInfo
+
+
+class EntityModificationContract(ABC):
+    @abstractmethod
+    async def entity_move(self, handle: str, dx: float, dy: float, dz: float = 0.0) -> dict: ...
+
+    @abstractmethod
+    async def entity_copy(
+        self, handle: str, dx: float, dy: float, dz: float = 0.0
+    ) -> EntityInfo: ...
+
+    @abstractmethod
+    async def entity_rotate(
+        self,
+        handle: str,
+        base_x: float,
+        base_y: float,
+        angle_deg: float,
+    ) -> dict: ...
+
+    @abstractmethod
+    async def entity_scale(
+        self,
+        handle: str,
+        base_x: float,
+        base_y: float,
+        factor: float,
+    ) -> dict: ...
+
+    @abstractmethod
+    async def entity_mirror(
+        self,
+        handle: str,
+        x1: float,
+        y1: float,
+        x2: float,
+        y2: float,
+        delete_original: bool = False,
+    ) -> EntityInfo: ...
+
+    @abstractmethod
+    async def entity_offset(
+        self,
+        handle: str,
+        distance: float,
+        side_x: float | None = None,
+        side_y: float | None = None,
+    ) -> EntityInfo: ...
+
+    @abstractmethod
+    async def entity_delete(self, handle: str) -> dict: ...
+
+    @abstractmethod
+    async def entity_array_rectangular(
+        self,
+        handle: str,
+        rows: int,
+        cols: int,
+        row_spacing: float,
+        col_spacing: float,
+    ) -> list[EntityInfo]: ...
+
+    @abstractmethod
+    async def entity_array_polar(
+        self,
+        handle: str,
+        count: int,
+        fill_angle: float,
+        center_x: float,
+        center_y: float,
+    ) -> list[EntityInfo]: ...
+
+    # ── text annotation (M8 / F15) ───────────────────────────────────────────
+
+    @abstractmethod
+    async def text_set_background(
+        self,
+        handle: str,
+        enabled: bool = True,
+        color: int | None = None,
+        scale: float = 1.5,
+    ) -> dict:
+        """Put an opaque background box behind an MTEXT. ``{ok, handle, enabled}``.
+
+        MTEXT only — TEXT has no background-fill attribute, so setting one on
+        it would report success and change nothing. ``scale`` is a multiple of
+        the text box and must be >= 1: a box smaller than its text is a stripe
+        through the text, not a mask.
+        """
+        ...
+
+    @abstractmethod
+    async def text_find_replace(
+        self,
+        find: str,
+        replace: str,
+        layer: str | None = None,
+        match_case: bool = True,
+        dry_run: bool = False,
+    ) -> dict:
+        """Replace text across the drawing.
+
+        Returns ``{ok, replaced, entities, searched_types, note, dry_run}``.
+        ``searched_types`` is reported rather than assumed: "no matches" and
+        "that type was never searched" are different answers, and an editor
+        that silently skips block attributes is the classic version of this
+        bug. DIMENSION text is deliberately out of scope — its ``text`` field
+        holds the ``<>`` override placeholder rather than the measurement, so
+        editing it would either do nothing or break the association.
+        """
+        ...

backends/contracts/entity_query.py

@@ -0,0 +1,172 @@
+"""Reading entities back.
+
+Split out of the single 1854-line ``AutoCADBackend`` ABC in v1.5.0 (M7).
+``AutoCADBackend`` composes every contract in this package, so importing
+``backends.base.AutoCADBackend`` is unchanged for callers.
+"""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from backends.base import EntityInfo
+
+
+class EntityQueryContract(ABC):
+    # ── selection filters (M8 / F1) ──────────────────────────────────────────
+
+    @abstractmethod
+    async def selection_window(
+        self,
+        x1: float,
+        y1: float,
+        x2: float,
+        y2: float,
+        mode: str = "window",
+        entity_type: str = "",
+        layer: str = "",
+    ) -> dict:
+        """AutoCAD's ssget window/crossing. ``{ok, handles, count, mode}``.
+
+        ``window`` returns only entities wholly inside the box; ``crossing``
+        also returns the ones that straddle its edge. Getting those backwards
+        is silent and wrong, so ``mode`` is reported back and defaults to the
+        narrower one. A zero-area box is refused rather than answered with an
+        empty list, which would read as "nothing there".
+
+        Selection is by *drawn* position: an entity in a mirrored frame is
+        found where ``entity_get`` reports it, not where the file stores it.
+        """
+        ...
+
+    @abstractmethod
+    async def selection_polygon(
+        self,
+        points: list[list[float]],
+        mode: str = "window",
+        entity_type: str = "",
+        layer: str = "",
+    ) -> dict:
+        """Window/crossing selection against an arbitrary polygon.
+
+        A polygon is not its bounding box — the difference is the whole point
+        of the tool, so the implementation must test against the shape itself.
+        """
+        ...
+
+    @abstractmethod
+    async def selection_filter(
+        self,
+        entity_type: str = "",
+        layer: str = "",
+        color: int | None = None,
+        linetype: str = "",
+        min_area: float | None = None,
+    ) -> dict:
+        """Property filter. Returns ``{ok, handles, count, filtered_by}``.
+
+        Named parameters rather than a query string, deliberately: ezdxf's
+        query language answers an unknown attribute with an empty result, so a
+        typo is indistinguishable from "no matches". Here a typo is a
+        ``TypeError`` at the boundary, and ``filtered_by`` tells the caller
+        which filters actually ran — "I filtered by layer and found none" and
+        "I never filtered by layer" are different answers.
+        """
+        ...
+
+    @abstractmethod
+    async def entity_get(self, handle: str) -> EntityInfo: ...
+
+    @abstractmethod
+    async def entity_set_properties(
+        self,
+        handle: str,
+        layer: str | None = None,
+        color: int | None = None,
+        linetype: str | None = None,
+        lineweight: float | None = None,
+        visible: bool | None = None,
+    ) -> dict: ...
+
+    @abstractmethod
+    async def entity_edit_text(
+        self,
+        handle: str,
+        text: str | None = None,
+        height: float | None = None,
+        rotation: float | None = None,
+    ) -> EntityInfo:
+        """Edit an existing TEXT or MTEXT entity in place. Any argument left
+        None is unchanged. Returns the updated EntityInfo. Raises if the handle
+        is not a TEXT/MTEXT entity."""
+        ...
+
+    @abstractmethod
+    async def entity_edit_geometry(
+        self,
+        handle: str,
+        cx: float | None = None,
+        cy: float | None = None,
+        radius: float | None = None,
+        x1: float | None = None,
+        y1: float | None = None,
+        x2: float | None = None,
+        y2: float | None = None,
+        start_angle: float | None = None,
+        end_angle: float | None = None,
+    ) -> EntityInfo:
+        """Edit the defining geometry of an existing entity in place.
+        - CIRCLE: cx / cy / radius
+        - LINE: x1 / y1 (start), x2 / y2 (end)
+        - ARC: cx / cy / radius / start_angle / end_angle (degrees)
+        Any argument left None is unchanged. Raises for unsupported types."""
+        ...
+
+    @abstractmethod
+    async def entity_list(
+        self,
+        type_filter: str | None = None,
+        layer_filter: str | None = None,
+        limit: int = 200,
+        offset: int = 0,
+    ) -> list[EntityInfo]: ...
+
+    @abstractmethod
+    async def entity_count(
+        self,
+        type_filter: str | None = None,
+        layer_filter: str | None = None,
+    ) -> int:
+        """How many entities ``entity_list`` would match, ignoring limit/offset.
+
+        Exists so a *paged* listing can report an honest total without paying
+        for the rows it is not going to return. ``entity_list`` stops building
+        ``EntityInfo`` objects the moment it has ``limit`` of them, so it can
+        never tell a caller whether anything followed the page — and a
+        truncated list read as complete is a correctness bug, not a token one.
+
+        Two obligations, both load-bearing:
+
+        * apply **exactly** the filter semantics of ``entity_list`` (same
+          case-insensitive type/layer comparison), or ``truncated`` would be
+          computed against a different set than the one that was paged;
+        * do not build ``EntityInfo`` rows. A count implemented by listing
+          would cost more than the listing it is meant to make cheap.
+        """
+        ...
+
+    # ── extended entity data (XDATA) ─────────────────────────────────────────
+
+    @abstractmethod
+    async def entity_get_xdata(self, handle: str, app_name: str | None = None) -> dict:
+        """Extended entity data as ``{"handle", "xdata": {app: [values]}, "backend"}``.
+        ``app_name=None`` returns every app; an absent app is ``{}``, not an error."""
+        ...
+
+    @abstractmethod
+    async def entity_set_xdata(self, handle: str, app_name: str, values: list) -> dict:
+        """Replace the app's XDATA (registering the APPID if needed). Values are typed
+        by ``backends/xdata_specs.py``; an empty list removes the app's XDATA."""
+        ...

backends/contracts/environment.py

@@ -0,0 +1,178 @@
+"""Environment: documents, layer states, named views, UCS, application,
+preferences, drawing properties and operator prompts (v1.6 track E).
+
+``AutoCADBackend`` composes every contract in this package, so importing
+``backends.base.AutoCADBackend`` is unchanged for callers.
+
+Ownership: group V owns this module. The ``# ── properties ──`` block is
+declared here and *implemented* by group C on both backends; the six
+``@capability`` members are implemented on the COM backend only and refuse on
+ezdxf with a key both capability maps declare.
+"""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+
+from backends.capability import capability
+
+
+class EnvironmentContract(ABC):
+    # ── documents ────────────────────────────────────────────────────────────
+
+    @abstractmethod
+    async def document_list(self) -> list[dict]:
+        """``[{"name", "path", "active": bool, "saved": bool, "entity_count"}]``."""
+        ...
+
+    @abstractmethod
+    async def document_activate(self, name_or_path: str) -> dict:
+        """Make one open document the target of every later call.
+        → ``{"ok", "active", "previous"}``."""
+        ...
+
+    @abstractmethod
+    async def document_close(
+        self, name_or_path: str | None = None, save: bool = False, discard: bool = False
+    ) -> dict:
+        """Close one document (default: the active one).
+
+        Unsaved and neither ``save`` nor ``discard`` → ``ValueError`` naming the
+        document; ``save`` on a document that has never been saved →
+        ``ValueError`` (no path to write, and the live engine would open a
+        modal Save dialog). → ``{"ok", "closed", "saved": bool, "active": name|None}``.
+        """
+        ...
+
+    # ── layer states (portable ACADMCP_LAYERSTATES XRECORDs, both engines) ──
+
+    @abstractmethod
+    async def layer_state_save(self, name: str, description: str | None = None) -> dict:
+        """→ ``{"ok", "name", "layer_count", "replaced"}``."""
+        ...
+
+    @abstractmethod
+    async def layer_state_restore(self, name: str, properties: list[str] | None = None) -> dict:
+        """``properties`` ⊆ {"on","frozen","locked","color","linetype","lineweight","plot","current"};
+        → ``{"ok", "name", "applied", "missing_layers", "new_layers"}``."""
+        ...
+
+    @abstractmethod
+    async def layer_state_list(self) -> list[dict]:
+        """→ ``[{"name", "description", "layer_count"}]``."""
+        ...
+
+    @abstractmethod
+    async def layer_state_delete(self, name: str) -> dict: ...
+
+    # ── named views ─────────────────────────────────────────────────────────
+
+    @abstractmethod
+    async def view_named_save(
+        self, name: str, center=None, height: float | None = None, width: float | None = None
+    ) -> dict:
+        """→ ``{"ok", "name", "center": [x, y], "height", "width", "replaced"}``."""
+        ...
+
+    @abstractmethod
+    async def view_named_restore(self, name: str) -> dict:
+        """COM: ZOOM Window on the saved rectangle (``"applied": "zoom_window"``
+        plus the read-back ``viewctr`` / ``viewsize``); ezdxf: fits the window
+        into the ``*Active`` VPORT without touching its aspect ratio,
+        ``"applied": "header_only"`` plus ``vport_height`` / ``aspect_ratio``."""
+        ...
+
+    @abstractmethod
+    async def view_named_list(self) -> list[dict]: ...
+
+    # ── UCS (stored and made current; tool coordinates stay WCS) ────────────
+
+    @abstractmethod
+    async def ucs_list(self) -> list[dict]:
+        """→ ``[{"name", "origin", "x_axis", "y_axis", "current": bool}]`` + the implicit "world".
+
+        Exactly one row is current. An *unnamed* current UCS (``UCS Origin`` /
+        ``3P`` without saving) is a trailing row with ``name: None`` carrying
+        its frame — "world" is current only when the frame is the WCS
+        (WORLDUCS live, the ``$UCS*`` header headless), never because the
+        name is empty.
+        """
+        ...
+
+    @abstractmethod
+    async def ucs_set(self, name: str, origin, x_axis, y_axis) -> dict:
+        """non-orthogonal → ``ValueError`` with the measured angle."""
+        ...
+
+    @abstractmethod
+    async def ucs_restore(self, name: str) -> dict:
+        """``"world"`` resets."""
+        ...
+
+    # ── application, preferences, operator prompts (COM only) ───────────────
+
+    @capability(  # noqa: B027 — @capability supplies the body
+        "live_application",
+        reason="only a live CAD application can be launched or attached",
+    )
+    async def system_launch(self, visible: bool = True, open_path: str | None = None) -> dict:
+        """→ ``{"launched": bool, "attached": bool, "version", "document"}``."""
+        ...
+
+    @capability(  # noqa: B027 — @capability supplies the body
+        "preferences",
+        reason="AutoCAD preferences live in the running application, not in a file",
+    )
+    async def preferences_get(self, keys: list[str] | None = None) -> dict:
+        """→ ``{"values": {key: value}, "read_only": [keys]}``."""
+        ...
+
+    @capability(  # noqa: B027 — @capability supplies the body
+        "preferences",
+        reason="AutoCAD preferences live in the running application, not in a file",
+    )
+    async def preferences_set(self, key: str, value) -> dict:
+        """→ ``{"ok", "key", "old", "new"}``."""
+        ...
+
+    @capability(  # noqa: B027 — @capability supplies the body
+        "interactive_prompt",
+        reason="prompting the operator needs a live AutoCAD session",
+    )
+    async def user_pick_point(self, prompt: str) -> dict:
+        """→ ``{"cancelled": bool, "x", "y"}`` | ``{"timed_out": True}``."""
+        ...
+
+    @capability(  # noqa: B027 — @capability supplies the body
+        "interactive_prompt",
+        reason="prompting the operator needs a live AutoCAD session",
+    )
+    async def user_select(self, prompt: str, mode: str = "single") -> dict:
+        """→ ``{"cancelled", "handles": [...]}``; ``mode="single"`` adds ``"picked": [x, y]`` in WCS."""
+        ...
+
+    @capability(  # noqa: B027 — @capability supplies the body
+        "interactive_prompt",
+        reason="prompting the operator needs a live AutoCAD session",
+    )
+    async def system_prompt_message(self, text: str) -> dict:
+        """→ ``{"ok"}``."""
+        ...
+
+    # ── properties (declared here; implemented by group C on both engines) ───
+
+    @abstractmethod
+    async def drawing_properties_get(self) -> dict:
+        """→ ``{"summary": {"title","subject","author","keywords","comments"}
+        (None each headless), "summary_available": bool, "custom": {k: v}}``."""
+        ...
+
+    @abstractmethod
+    async def drawing_properties_set(
+        self, summary: dict | None = None, custom: dict | None = None
+    ) -> dict:
+        """ezdxf: ``summary`` with any non-None field → raise
+        ``UnsupportedCapabilityError("dwgprops")``; ``custom`` → header
+        custom_vars (replace keys given; value None deletes).
+        → ``{"ok", "summary_written": [...], "custom_written": [...], "custom_deleted": [...]}``."""
+        ...

backends/contracts/gdt.py

@@ -0,0 +1,157 @@
+"""Geometric tolerancing.
+
+Split out of the single 1854-line ``AutoCADBackend`` ABC in v1.5.0 (M7).
+``AutoCADBackend`` composes every contract in this package, so importing
+``backends.base.AutoCADBackend`` is unchanged for callers.
+"""
+
+from __future__ import annotations
+
+
+class GdtContract:
+    # Composed from LINE + TEXT primitives so the exact same frame renders on
+    # both COM and ezdxf (ezdxf's native TOLERANCE entity renders blank through
+    # the matplotlib frontend). Deterministic layout math lives in engineering/
+    # gdt.py; datum letters are tracked so the `gdt` critique focus can verify
+    # every referenced datum is actually established on the part.
+
+    async def _place_boxed_text(
+        self,
+        text: str,
+        cx: float,
+        cy: float,
+        text_h: float,
+        layer: str,
+    ) -> str:
+        """Create a TEXT entity roughly centred on (cx, cy). Returns its handle.
+        entity_create_text has no alignment arg, so approximate the centring with
+        the same width heuristic the title block uses."""
+        approx_w = len(text) * text_h * 0.7
+        t = await self.entity_create_text(
+            text,
+            cx - approx_w / 2.0,
+            cy - text_h / 2.0,
+            height=text_h,
+            layer=layer,
+        )
+        return t.handle
+
+    async def draw_feature_control_frame(
+        self,
+        symbol: str,
+        tolerance: str | float,
+        x: float,
+        y: float,
+        datums: list[str] | None = None,
+        height: float = 5.0,
+        diameter: bool = False,
+        modifier: str | None = None,
+        layer: str | None = None,
+    ) -> dict:
+        """Draw an ISO 1101 feature control frame with bottom-left corner at (x, y).
+
+        symbol: one of the 14 geometric characteristics (straightness, flatness,
+        circularity, cylindricity, profile_line, profile_surface, angularity,
+        perpendicularity, parallelism, position, concentricity, symmetry,
+        circular_runout, total_runout). `datums` is the ordered datum reference
+        list (e.g. ["A", "B"]); `diameter=True` prefixes ⌀ for a cylindrical zone;
+        `modifier` ∈ {M, L, S} appends the material-condition symbol.
+
+        Orientation/location/runout characteristics require at least one datum
+        (raises otherwise). The referenced datums are recorded for the `gdt`
+        critique focus.
+        """
+        from engineering.gdt import fcf_compartments, fcf_layout
+
+        comps = fcf_compartments(
+            symbol,
+            tolerance,
+            datums,
+            diameter=diameter,
+            modifier=modifier,
+        )
+        layer = layer or self._role_layer("dim")
+        await self._ensure_layer(layer, color=2)
+        lay = fcf_layout(comps, float(x), float(y), float(height))
+        handles: list[str] = []
+
+        box = lay["box"]
+        box_poly = await self.entity_create_polyline(
+            [[bx, by] for bx, by in box],
+            closed=False,
+            layer=layer,
+        )
+        handles.append(box_poly.handle)
+        for (sx, sy), (ex, ey) in lay["dividers"]:
+            ln = await self.entity_create_line(sx, sy, ex, ey, layer=layer)
+            handles.append(ln.handle)
+        th = lay["text_height"]
+        for text, tcx, tcy in lay["labels"]:
+            handles.append(await self._place_boxed_text(text, tcx, tcy, th, layer))
+
+        refs = getattr(self, "_gdt_datums_referenced", None)
+        if refs is None:
+            refs = set()
+            self._gdt_datums_referenced = refs
+        for d in datums or []:
+            d = str(d).strip().upper()
+            if d:
+                refs.add(d)
+
+        return {
+            "ok": True,
+            "symbol": symbol,
+            "compartments": comps,
+            "handles": handles,
+            "width": lay["width"],
+            "height": lay["height"],
+            "layer": layer,
+        }
+
+    async def draw_datum_feature(
+        self,
+        letter: str,
+        x: float,
+        y: float,
+        size: float = 5.0,
+        layer: str | None = None,
+    ) -> dict:
+        """Place an ISO 1101 datum feature symbol (filled triangle + boxed letter)
+        with its apex at (x, y). Records the datum letter so a feature control
+        frame that references it passes the `gdt` critique focus."""
+        from engineering.gdt import datum_triangle, fcf_layout
+
+        letter = str(letter).strip().upper()
+        if not letter:
+            raise RuntimeError("draw_datum_feature: a datum letter is required.")
+        layer = layer or self._role_layer("dim")
+        await self._ensure_layer(layer, color=2)
+        size = float(size)
+        handles: list[str] = []
+
+        tri = datum_triangle(float(x), float(y), size, down=True)
+        tri_poly = await self.entity_create_polyline(
+            [[px, py] for px, py in tri],
+            closed=True,
+            layer=layer,
+        )
+        handles.append(tri_poly.handle)
+
+        box_h = size * 1.4
+        lay = fcf_layout([letter], float(x) - box_h / 2.0, float(y) - size - box_h, box_h)
+        box_poly = await self.entity_create_polyline(
+            [[bx, by] for bx, by in lay["box"]],
+            closed=False,
+            layer=layer,
+        )
+        handles.append(box_poly.handle)
+        for text, tcx, tcy in lay["labels"]:
+            handles.append(await self._place_boxed_text(text, tcx, tcy, lay["text_height"], layer))
+
+        defined = getattr(self, "_gdt_datums_defined", None)
+        if defined is None:
+            defined = set()
+            self._gdt_datums_defined = defined
+        defined.add(letter)
+
+        return {"ok": True, "datum": letter, "handles": handles, "layer": layer}

backends/contracts/identity.py

@@ -0,0 +1,33 @@
+"""Connecting and describing the backend.
+
+Split out of the single 1854-line ``AutoCADBackend`` ABC in v1.5.0 (M7).
+``AutoCADBackend`` composes every contract in this package, so importing
+``backends.base.AutoCADBackend`` is unchanged for callers.
+"""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from backends.base import CapabilityMap
+
+
+class IdentityContract(ABC):
+    @property
+    @abstractmethod
+    def name(self) -> str: ...
+
+    @property
+    @abstractmethod
+    def is_connected(self) -> bool: ...
+
+    @abstractmethod
+    async def connect(self) -> None: ...
+
+    @abstractmethod
+    async def disconnect(self) -> None: ...
+
+    @abstractmethod
+    def capabilities(self) -> CapabilityMap: ...

backends/contracts/layers.py

@@ -0,0 +1,61 @@
+"""Layers.
+
+Split out of the single 1854-line ``AutoCADBackend`` ABC in v1.5.0 (M7).
+``AutoCADBackend`` composes every contract in this package, so importing
+``backends.base.AutoCADBackend`` is unchanged for callers.
+"""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from backends.base import LayerInfo
+
+
+class LayerContract(ABC):
+    @abstractmethod
+    async def layer_list(self) -> list[LayerInfo]: ...
+
+    @abstractmethod
+    async def layer_create(
+        self,
+        name: str,
+        color: int = 7,
+        linetype: str = "Continuous",
+        lineweight: float = -3,
+    ) -> LayerInfo: ...
+
+    @abstractmethod
+    async def layer_delete(self, name: str) -> dict: ...
+
+    @abstractmethod
+    async def layer_set_current(self, name: str) -> dict: ...
+
+    @abstractmethod
+    async def layer_modify(
+        self,
+        name: str,
+        color: int | None = None,
+        linetype: str | None = None,
+        lineweight: float | None = None,
+    ) -> LayerInfo: ...
+
+    @abstractmethod
+    async def layer_freeze(self, name: str) -> dict: ...
+
+    @abstractmethod
+    async def layer_thaw(self, name: str) -> dict: ...
+
+    @abstractmethod
+    async def layer_lock(self, name: str) -> dict: ...
+
+    @abstractmethod
+    async def layer_unlock(self, name: str) -> dict: ...
+
+    @abstractmethod
+    async def layer_hide(self, name: str) -> dict: ...
+
+    @abstractmethod
+    async def layer_show(self, name: str) -> dict: ...

backends/contracts/layouts.py

@@ -0,0 +1,170 @@
+"""Layouts, viewports and change-space.
+
+Split out of the single 1854-line ``AutoCADBackend`` ABC in v1.5.0 (M7).
+``AutoCADBackend`` composes every contract in this package, so importing
+``backends.base.AutoCADBackend`` is unchanged for callers.
+"""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+
+from backends.capability import capability
+
+
+class LayoutContract(ABC):
+    @abstractmethod
+    async def layout_list(self) -> dict:
+        """Return {ok, layouts: [names], current: name} incl. 'Model'."""
+        ...
+
+    @abstractmethod
+    async def layout_create(self, name: str) -> dict:
+        """Create a new paper-space layout."""
+        ...
+
+    @abstractmethod
+    async def layout_set_current(self, name: str) -> dict:
+        """Activate a layout tab ('Model' or a paper-space layout name)."""
+        ...
+
+    @abstractmethod
+    async def layout_delete(self, name: str) -> dict:
+        """Delete a paper-space layout and everything drawn on it.
+
+        Returns ``{ok, deleted, entities_destroyed, current}``. ``current`` is
+        the space geometry goes into afterwards, which the implementation must
+        keep consistent with ``layout_list()`` — deleting the active tab
+        otherwise leaves the reported current layout, the DXF tile mode and the
+        space entities actually land in disagreeing with each other.
+
+        Refuses ``'Model'``, a blank name (which ezdxf resolves to the *first*
+        paper-space layout), a name that does not exist, and the last remaining
+        paper-space layout.
+        """
+        ...
+
+    @abstractmethod
+    async def layout_rename(self, old_name: str, new_name: str) -> dict:
+        """Rename a paper-space layout, keeping its entities and their handles.
+
+        Returns ``{ok, old, new, current}``. Refuses ``'Model'`` on either side,
+        a blank or otherwise invalid new name, and a name already in use.
+        """
+        ...
+
+    @abstractmethod
+    async def layout_copy(self, source: str, new_name: str) -> dict:
+        """Copy a paper-space layout, its page setup and its geometry.
+
+        Returns ``{ok, source, layout, entities_copied, skipped,
+        associativity_remapped, associativity_dropped}``. ``skipped`` names the
+        DXF types that could not be cloned — a copy missing geometry must never
+        report a bare success. Associative boundaries (hatches) are re-pointed
+        at the cloned entities where possible and cleared otherwise, because a
+        boundary still referencing the source layout dangles as soon as that
+        layout is deleted and no auditor reports it.
+        """
+        ...
+
+    @abstractmethod
+    async def viewport_create(
+        self,
+        layout: str,
+        center_x: float,
+        center_y: float,
+        width: float,
+        height: float,
+        view_center_x: float,
+        view_center_y: float,
+        scale: float = 1.0,
+    ) -> dict:
+        """Place a scaled model-space viewport on a paper-space layout.
+
+        ``scale`` is paper:model (1.0 = 1:1, 0.5 = 1:2). The viewport shows
+        the model window centered at (view_center_x, view_center_y) with
+        view height = height / scale.
+        """
+        ...
+
+    @abstractmethod
+    async def viewport_list(self, layout: str | None = None) -> dict:
+        """List the viewports on one paper-space layout, or on all of them.
+
+        Returns ``{ok, viewports: [...], count}``. Each row carries ``handle``,
+        ``layout``, ``center``, ``width``, ``height``, ``view_center``,
+        ``view_height``, ``scale``, ``locked``, ``status``, ``id`` and
+        ``is_main``.
+
+        The layout's own main viewport is reported with ``is_main: True`` rather
+        than filtered out — it is what remains after deleting every drafting
+        viewport, and a caller who cannot see it cannot explain that. ``scale``
+        and ``locked`` are ``None`` on documents that cannot store them (R12),
+        never a fabricated number. Viewports are addressed by handle; ``id`` is
+        metadata only.
+        """
+        ...
+
+    @abstractmethod
+    async def viewport_set_scale(self, handle: str, scale: float) -> dict:
+        """Set a viewport's paper:model scale. Returns ``{ok, handle, scale,
+        view_height}`` with ``scale`` read back from the entity.
+
+        Refuses the main viewport (whose view height is the tab's own pan/zoom
+        state, not a drafting scale) and documents that cannot persist it.
+        Geometric scale only: annotative text and dimensions do not resize.
+        """
+        ...
+
+    @abstractmethod
+    async def viewport_lock(self, handle: str, locked: bool = True) -> dict:
+        """Lock or unlock a viewport's display scale. Returns ``{ok, handle,
+        locked}`` with ``locked`` read back from the entity."""
+        ...
+
+    # B027 (empty method, no @abstractmethod) is exactly what this pattern
+    # looks like from the outside: the decorator replaces the `...` body with
+    # the refusing default, so the source really is empty on purpose.
+    @capability(  # noqa: B027
+        "chspace",
+        reason=(
+            "ActiveX exposes no change-space member, so a live backend would have to recreate "
+            "geometry through CopyObjects or drive the CHSPACE command blind — neither has been "
+            "verified against a live AutoCAD. Use the headless backend "
+            "(AUTOCAD_MCP_BACKEND=ezdxf), or run CHSPACE in AutoCAD directly."
+        ),
+    )
+    async def entity_change_space(
+        self,
+        handles: list[str],
+        viewport_handle: str,
+        direction: str = "to_paper",
+        freeze_dimensions: bool = False,
+    ) -> dict:
+        """Move entities between model space and a sheet, *through* a viewport.
+
+        Returns ``{ok, moved, refused, scale, viewport}``. Each ``moved`` row
+        carries ``handle``, ``from``, ``to``, ``inside_viewport`` and
+        ``on_sheet``; each ``refused`` row carries ``handle`` and ``reason``.
+
+        The geometric transform is the whole point: a move without it leaves a
+        100 mm feature as 100 mm of paper inside a 1:2 viewport, produces a file
+        that audits clean, and is indistinguishable from success. Backends that
+        cannot apply the viewport transform must refuse rather than move.
+
+        Refuses per entity for dimensions (unless ``freeze_dimensions`` bakes
+        the pre-transform measurement into the text first), ACIS bodies, tables
+        and proxies, viewports, and entities already in the target space; and
+        refuses the whole call for a twisted or non-top-view viewport.
+        """
+        ...
+
+    @abstractmethod
+    async def viewport_delete(self, handle: str, force: bool = False) -> dict:
+        """Delete a viewport. Returns ``{ok, handle, layout, was_main}``.
+
+        The layout's main viewport needs ``force=True`` and the implementation
+        must repair the layout's current-viewport pointer afterwards; a dangling
+        pointer is invisible to every headless audit and shows up only in CAD.
+        """
+        ...

backends/contracts/linetypes.py

@@ -0,0 +1,22 @@
+"""Linetypes.
+
+Split out of the single 1854-line ``AutoCADBackend`` ABC in v1.5.0 (M7).
+``AutoCADBackend`` composes every contract in this package, so importing
+``backends.base.AutoCADBackend`` is unchanged for callers.
+"""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+
+
+class LinetypeContract(ABC):
+    @abstractmethod
+    async def linetype_list(self) -> list[str]: ...
+
+    @abstractmethod
+    async def linetype_load(
+        self,
+        name: str,
+        file: str | None = None,
+    ) -> dict: ...

backends/contracts/pagesetup.py

@@ -0,0 +1,82 @@
+"""Page setup, plot styles and templates (v1.6 track E, group P).
+
+``AutoCADBackend`` composes every contract in this package, so importing
+``backends.base.AutoCADBackend`` is unchanged for callers.
+"""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+
+
+class PageSetupContract(ABC):
+    @abstractmethod
+    async def page_setup_list(self, layout: str | None = None) -> list[dict]:
+        """Page setup of one paper-space layout, or of every one.
+
+        Rows: ``{layout, paper, canonical_media_name, size_mm: [w, h],
+        orientation, plot_style, scale, plot_area, device,
+        margins_mm: [top, bottom, left, right], paper_units, center}``.
+        ``size_mm`` and ``margins_mm`` are the sheet *as plotted*: under
+        ``plot_rotation`` 1/3 (AutoCAD's landscape-on-portrait-media
+        convention) both are turned together, through the one mapping the
+        renderer plots by (``papers.turned_sheet``), so the printable area a
+        row implies is the area the same engine plots. ``paper`` is the
+        catalogue name when the size matches one within 0.5 mm, otherwise the
+        media name as stored. ``paper_units`` (``"mm"`` | ``"inches"`` |
+        ``"pixels"``) is what one paper-space unit means at the plot scale;
+        sizes and margins are millimetres whatever it says. ``center`` is a
+        bool for an extents plot and ``None`` for a layout plot, where
+        centring is not applicable (AutoCAD greys it out; ActiveX refuses
+        ``CenterPlot = True`` under ``acLayout``). Raises ``ValueError`` for
+        an unknown layout.
+        ``Model`` is never listed: model space is plotted through
+        ``drawing_export_pdf(layout=None)`` and carries no sheet.
+        """
+        ...
+
+    @abstractmethod
+    async def page_setup_apply(self, layout: str, setup: dict) -> dict:
+        """Write a page setup resolved by
+        ``engineering.standards.papers.resolve_page_setup`` to a layout.
+
+        Returns ``{ok, layout, applied: {...setup}, changed: {key: [old, new]},
+        warnings: [str], plot_style_known, viewports_kept}``. ``changed`` is
+        computed from the read-back before and after (the rows
+        ``page_setup_list`` reports), so re-applying the same setup reports
+        ``{}``. The write resets ``plot_rotation`` to 0 (orientation rides on
+        the media's width/height); headlessly, with no ``margins_mm`` asked
+        for, the turned margins are re-written un-turned so the sheet keeps
+        the margins it had, and on the live engine (margins come from the
+        .pc3) the ones that moved show in ``changed``. ``setup["paper_units"]``
+        (``"mm"`` default, ``"inches"``, or ``None`` to keep the layout's
+        units as AutoCAD's own Page Setup does) is written when given; a move
+        rescales every paper-space unit by 25.4 at the plot scale and is named
+        in ``changed`` *and* ``warnings`` (``papers.page_setup_warnings``).
+        Refuses ``Model``, an unknown layout, and a ``setup`` missing a
+        resolved key, before anything is written. A write the engine refuses
+        part-way through is unwound (every landed value put back) before the
+        ``ValueError`` names the refused property. Never deletes viewports.
+        """
+        ...
+
+    @abstractmethod
+    async def plot_style_list(self) -> list[dict]:
+        """``[{name, source: "catalog"|"installed", installed: bool|None}]`` —
+        the authored ctb catalogue plus, on a live engine, the files present
+        in the plot style search path. ``installed`` is ``None`` where no
+        installation can be scanned."""
+        ...
+
+    @abstractmethod
+    async def drawing_template_save(
+        self, path: str, name: str | None = None, description: str | None = None
+    ) -> dict:
+        """Save the current drawing as a template.
+
+        ``.dxf`` writes on both engines; ``.dwt`` writes on the live engine
+        (``SaveAs(path, ac2018_Template)``) and raises
+        ``UnsupportedCapabilityError("dwt_write")`` headlessly. Returns
+        ``{ok, path, format: "dxf"|"dwt", backend, name, description_written}``.
+        """
+        ...

backends/contracts/premium.py

@@ -0,0 +1,777 @@
+"""Planning, critique, snapping and construction geometry.
+
+Split out of the single 1854-line ``AutoCADBackend`` ABC in v1.5.0 (M7).
+``AutoCADBackend`` composes every contract in this package, so importing
+``backends.base.AutoCADBackend`` is unchanged for callers.
+"""
+
+from __future__ import annotations
+
+import math
+from abc import ABC, abstractmethod
+from typing import TYPE_CHECKING, Any
+
+from backends.quarantine import DocumentQuarantineError
+
+if TYPE_CHECKING:
+    from backends.base import EntityInfo
+    from engineering.plan_spec import (
+        CritiqueFocus,
+        DimStyle,
+        Issue,
+        LayerSetId,
+        PlanSpec,
+        SheetSize,
+        SnapType,
+    )
+
+
+class PremiumContract(ABC):
+    # These are CONCRETE and backend-agnostic: they orchestrate the abstract
+    # primitives above plus the shared EntityInfo.properties contract (start/
+    # end/center/radius/start_angle/end_angle — populated identically by both
+    # backends), so the ezdxf and COM backends inherit identical premium
+    # behaviour. The only backend-specific primitive is `_create_xline` — XLINE
+    # has no cross-backend equivalent among the standard entity_create_* tools.
+
+    _plan_spec: PlanSpec | None = None
+    _preflight_result: Any = None
+    # The standard `drawing_apply_iso_layers` last bootstrapped on *this*
+    # drawing (None until it runs) — `_active_layer_set_id` reads it ahead of
+    # the PlanSpec. Drawing-scoped like the plan: a live backend clears it
+    # when AutoCAD's active document changes, the headless registry keeps one
+    # per open document.
+    _active_layer_set: LayerSetId | None = None
+
+    def _reset_document_state(self) -> None:
+        """Clear metadata that is valid only for the current drawing."""
+        self._plan_spec = None
+        self._preflight_result = None
+        self._active_layer_set = None
+        self._gdt_datums_defined = set()
+        self._gdt_datums_referenced = set()
+
+    async def _ensure_document_state(self) -> None:
+        """Allow live backends to detect an out-of-band document switch."""
+        return None
+
+    async def drawing_preflight(
+        self,
+        intent: str,
+        requirements: dict | None = None,
+        sheet_size: SheetSize = "A3",
+        scale: float = 1.0,
+        layer_set_id: LayerSetId = "mech",
+        view_count: int = 1,
+        dim_style: DimStyle = "chain",
+        allow_assumptions: bool = False,
+    ):
+        from engineering.preflight import preflight_drawing
+
+        await self._ensure_document_state()
+
+        result = preflight_drawing(
+            intent,
+            requirements,
+            sheet_size,
+            scale,
+            layer_set_id,
+            view_count,
+            dim_style,
+            allow_assumptions=allow_assumptions,
+        )
+        self._preflight_result = result
+        return result
+
+    async def drawing_plan(
+        self,
+        intent: str,
+        sheet_size: SheetSize = "A3",
+        scale: float = 1.0,
+        layer_set_id: LayerSetId = "mech",
+        view_count: int = 1,
+        dim_style: DimStyle = "chain",
+        notes: list[str] | None = None,
+        requirements: dict | None = None,
+        spec_hash: str | None = None,
+    ) -> PlanSpec:
+        """Commit a drawing intent before any geometry is created.
+        Returns a PlanSpec and stores it on the backend; read it back with
+        `get_plan_spec()`. (N8: the previous claim that `drawing_critique`
+        replays this plan was untrue — critique runs geometric checks, not a
+        plan diff.)"""
+        from engineering.plan_spec import PlanSpec
+
+        await self._ensure_document_state()
+        preflight_status = "skipped"
+        normalized_plan: dict[str, Any] | None = None
+        if spec_hash is not None:
+            from engineering.preflight import preflight_drawing
+
+            preflight = getattr(self, "_preflight_result", None)
+            if preflight is None or preflight.spec_hash != spec_hash:
+                raise RuntimeError("drawing_plan: spec_hash does not match the latest preflight.")
+            if not preflight.ready:
+                raise RuntimeError(
+                    "drawing_plan: preflight is not ready; resolve questions/conflicts first."
+                )
+            candidate = preflight_drawing(
+                intent,
+                requirements
+                if requirements is not None
+                else preflight.normalized_spec["requirements"],
+                sheet_size,
+                scale,
+                layer_set_id,
+                view_count,
+                dim_style,
+            )
+            if candidate.spec_hash != spec_hash:
+                raise RuntimeError(
+                    "drawing_plan: supplied fields do not match the hashed preflight spec."
+                )
+            normalized_plan = preflight.normalized_spec
+            preflight_status = "ready"
+
+        if normalized_plan is not None:
+            intent = normalized_plan["intent"]
+            sheet_size = normalized_plan["sheet_size"]
+            scale = normalized_plan["scale"]
+            layer_set_id = normalized_plan["layer_set_id"]
+            view_count = normalized_plan["view_count"]
+            dim_style = normalized_plan["dim_style"]
+            requirements = normalized_plan["requirements"]
+
+        plan = PlanSpec(
+            intent=str(intent),
+            sheet_size=sheet_size,
+            scale=float(scale),
+            layer_set_id=layer_set_id,
+            view_count=int(view_count),
+            dim_style=dim_style,
+            notes=list(notes) if notes else [],
+            requirements=dict(requirements or {}),
+            spec_hash=spec_hash,
+            preflight_status=preflight_status,
+        )
+        self._plan_spec = plan
+        return plan
+
+    async def drawing_critique(
+        self,
+        focus: list[CritiqueFocus] | None = None,
+    ) -> list[Issue]:
+        """Run premium-quality geometric checks; return zero issues before
+        `drawing_finalize`. `focus=None` runs all checks. (N8: this does NOT
+        replay the committed PlanSpec — it inspects the live drawing geometry.)"""
+        from engineering.critique import run_critique
+
+        await self._ensure_document_state()
+        return await run_critique(self, focus)
+
+    def get_plan_spec(self) -> dict | None:
+        """Return the PlanSpec committed by `drawing_plan` as a dict, or None
+        if no plan has been committed. (N8: makes the stored `_plan_spec`
+        actually readable instead of being write-only dead state.)"""
+        plan = getattr(self, "_plan_spec", None)
+        return plan.to_dict() if plan is not None else None
+
+    async def point_from_snap(
+        self,
+        handle: str,
+        snap: SnapType,
+        ref_x: float | None = None,
+        ref_y: float | None = None,
+    ) -> tuple[float, float]:
+        """Return a deterministic snap point on `handle`.
+        snap ∈ {end, mid, center, quad, perp, near}. For `near/perp`,
+        `ref_x/y` is the reference point. Sources geometry from the shared
+        EntityInfo.properties contract — works on every backend."""
+        ent = await self.entity_get(handle)
+        et = ent.type
+        p = ent.properties
+        ref = (float(ref_x), float(ref_y)) if ref_x is not None and ref_y is not None else None
+
+        def _line_pts():
+            s = p.get("start")
+            e = p.get("end")
+            if s is None or e is None:
+                raise RuntimeError(f"point_from_snap: entity {handle} ({et}) has no start/end.")
+            return (float(s[0]), float(s[1])), (float(e[0]), float(e[1]))
+
+        def _circle_geom():
+            c = p.get("center")
+            r = p.get("radius")
+            if c is None or r is None:
+                raise RuntimeError(f"point_from_snap: entity {handle} ({et}) has no center/radius.")
+            return float(c[0]), float(c[1]), float(r)
+
+        def _arc_angles():
+            # N7: use .get() + descriptive RuntimeError (matching _line_pts /
+            # _circle_geom) instead of bracket indexing that raises an opaque
+            # KeyError when start_angle/end_angle are missing.
+            sa = p.get("start_angle")
+            ea = p.get("end_angle")
+            if sa is None or ea is None:
+                raise RuntimeError(
+                    f"point_from_snap: entity {handle} ({et}) has no start_angle/end_angle."
+                )
+            return math.radians(float(sa)), math.radians(float(ea))
+
+        if snap == "end":
+            if et == "LINE":
+                s, e = _line_pts()
+                if ref is None:
+                    return s
+                ds = (s[0] - ref[0]) ** 2 + (s[1] - ref[1]) ** 2
+                de = (e[0] - ref[0]) ** 2 + (e[1] - ref[1]) ** 2
+                return s if ds <= de else e
+            if et == "ARC":
+                cx, cy, r = _circle_geom()
+                sa, ea = _arc_angles()
+                sp = (cx + r * math.cos(sa), cy + r * math.sin(sa))
+                ep = (cx + r * math.cos(ea), cy + r * math.sin(ea))
+                if ref is None:
+                    return sp
+                ds = (sp[0] - ref[0]) ** 2 + (sp[1] - ref[1]) ** 2
+                de = (ep[0] - ref[0]) ** 2 + (ep[1] - ref[1]) ** 2
+                return sp if ds <= de else ep
+            raise RuntimeError(f"point_from_snap: 'end' snap not supported on {et}")
+
+        if snap == "mid":
+            if et == "LINE":
+                s, e = _line_pts()
+                return ((s[0] + e[0]) / 2.0, (s[1] + e[1]) / 2.0)
+            if et == "ARC":
+                cx, cy, r = _circle_geom()
+                sa, ea = _arc_angles()
+                if ea < sa:
+                    ea += 2 * math.pi
+                ma = (sa + ea) / 2.0
+                return (cx + r * math.cos(ma), cy + r * math.sin(ma))
+            raise RuntimeError(f"point_from_snap: 'mid' snap not supported on {et}")
+
+        if snap == "center":
+            if et in ("CIRCLE", "ARC", "ELLIPSE"):
+                c = p.get("center")
+                if c is None:
+                    raise RuntimeError(f"point_from_snap: entity {handle} ({et}) has no center.")
+                return (float(c[0]), float(c[1]))
+            raise RuntimeError(f"point_from_snap: 'center' snap not supported on {et}")
+
+        # NEW-snap-quad-arc / NEW-snap-near-arc: an ARC only covers part of the
+        # full circle, so quad/near candidates derived from the circle may fall
+        # outside the [start_angle, end_angle] sweep. Restrict (quad) / clamp
+        # (near) the projected angle to the sweep, with 2π wraparound.
+        def _arc_sweep():
+            sa, ea = _arc_angles()
+            if ea < sa:
+                ea += 2 * math.pi
+            return sa, ea
+
+        def _angle_in_sweep(theta: float, sa: float, ea: float) -> bool:
+            # Normalise theta into [sa, sa+2π) and test against [sa, ea].
+            t = sa + ((theta - sa) % (2 * math.pi))
+            return t <= ea + 1e-9
+
+        def _arc_endpoints(cx: float, cy: float, r: float, sa: float, ea: float):
+            return (
+                (cx + r * math.cos(sa), cy + r * math.sin(sa)),
+                (cx + r * math.cos(ea), cy + r * math.sin(ea)),
+            )
+
+        if snap == "quad":
+            if et == "CIRCLE":
+                cx, cy, r = _circle_geom()
+                pts = [(cx + r, cy), (cx, cy + r), (cx - r, cy), (cx, cy - r)]
+                if ref is None:
+                    return pts[0]
+                return min(pts, key=lambda q: (q[0] - ref[0]) ** 2 + (q[1] - ref[1]) ** 2)
+            if et == "ARC":
+                cx, cy, r = _circle_geom()
+                sa, ea = _arc_sweep()
+                quad_angles = (0.0, math.pi / 2.0, math.pi, 3 * math.pi / 2.0)
+                pts = [
+                    (cx + r * math.cos(a), cy + r * math.sin(a))
+                    for a in quad_angles
+                    if _angle_in_sweep(a, sa, ea)
+                ]
+                if not pts:
+                    # No quadrant lies on the sweep — fall back to arc endpoints.
+                    pts = list(_arc_endpoints(cx, cy, r, sa, ea))
+                if ref is None:
+                    return pts[0]
+                return min(pts, key=lambda q: (q[0] - ref[0]) ** 2 + (q[1] - ref[1]) ** 2)
+            raise RuntimeError(f"point_from_snap: 'quad' snap not supported on {et}")
+
+        if snap == "perp":
+            if ref is None:
+                raise RuntimeError("point_from_snap: 'perp' requires ref_x/ref_y.")
+            if et == "LINE":
+                s, e = _line_pts()
+                dx = e[0] - s[0]
+                dy = e[1] - s[1]
+                L2 = dx * dx + dy * dy
+                if L2 < 1e-18:
+                    raise RuntimeError("point_from_snap: line has zero length.")
+                t = ((ref[0] - s[0]) * dx + (ref[1] - s[1]) * dy) / L2
+                return (s[0] + t * dx, s[1] + t * dy)
+            raise RuntimeError(f"point_from_snap: 'perp' snap not supported on {et}")
+
+        if snap == "near":
+            if ref is None:
+                raise RuntimeError("point_from_snap: 'near' requires ref_x/ref_y.")
+            if et == "LINE":
+                s, e = _line_pts()
+                dx = e[0] - s[0]
+                dy = e[1] - s[1]
+                L2 = dx * dx + dy * dy
+                if L2 < 1e-18:
+                    return s
+                t = ((ref[0] - s[0]) * dx + (ref[1] - s[1]) * dy) / L2
+                t = max(0.0, min(1.0, t))
+                return (s[0] + t * dx, s[1] + t * dy)
+            if et == "CIRCLE":
+                cx, cy, r = _circle_geom()
+                vx, vy = ref[0] - cx, ref[1] - cy
+                L = math.hypot(vx, vy)
+                if L < 1e-18:
+                    return (cx + r, cy)
+                return (cx + r * vx / L, cy + r * vy / L)
+            if et == "ARC":
+                cx, cy, r = _circle_geom()
+                sa, ea = _arc_sweep()
+                vx, vy = ref[0] - cx, ref[1] - cy
+                L = math.hypot(vx, vy)
+                if L < 1e-18:
+                    # Degenerate ref at center: return the start endpoint.
+                    return (cx + r * math.cos(sa), cy + r * math.sin(sa))
+                theta = math.atan2(vy, vx)
+                if _angle_in_sweep(theta, sa, ea):
+                    return (cx + r * math.cos(theta), cy + r * math.sin(theta))
+                # Projected angle is off the sweep — fall back to the nearer endpoint.
+                sp, ep = _arc_endpoints(cx, cy, r, sa, ea)
+                ds = (sp[0] - ref[0]) ** 2 + (sp[1] - ref[1]) ** 2
+                de = (ep[0] - ref[0]) ** 2 + (ep[1] - ref[1]) ** 2
+                return sp if ds <= de else ep
+            raise RuntimeError(f"point_from_snap: 'near' snap not supported on {et}")
+
+        if snap == "int":
+            raise RuntimeError(
+                "point_from_snap: 'int' (intersection) requires a 2nd entity; "
+                "compute via two endpoints. V2 will accept a 2nd handle."
+            )
+
+        raise RuntimeError(
+            f"point_from_snap: unknown snap type '{snap}'. "
+            "Use one of: end, mid, center, quad, perp, near."
+        )
+
+    async def point_intersection(
+        self,
+        handle1: str,
+        handle2: str,
+        ref_x: float | None = None,
+        ref_y: float | None = None,
+    ) -> tuple[float, float]:
+        """Return the intersection point of two geometry entities.
+
+        Supports LINE-LINE, LINE-CIRCLE, and CIRCLE-CIRCLE cases. When
+        multiple intersections exist (e.g. two circles), ``ref_x``/``ref_y``
+        selects the candidate nearest to that reference point. If omitted the
+        first candidate is returned.
+
+        Raises RuntimeError when no real intersection exists or entity types
+        are unsupported.
+        """
+        info1 = await self.entity_get(handle1)
+        info2 = await self.entity_get(handle2)
+        t1, t2 = info1.type.upper(), info2.type.upper()
+        props1, props2 = info1.properties, info2.properties
+
+        candidates: list[tuple[float, float]] = []
+
+        if t1 == "LINE" and t2 == "LINE":
+            # Line-line intersection via parametric form
+            x1, y1 = props1["start"][0], props1["start"][1]
+            x2, y2 = props1["end"][0], props1["end"][1]
+            x3, y3 = props2["start"][0], props2["start"][1]
+            x4, y4 = props2["end"][0], props2["end"][1]
+            dx1, dy1 = x2 - x1, y2 - y1
+            dx2, dy2 = x4 - x3, y4 - y3
+            denom = dx1 * dy2 - dy1 * dx2
+            if abs(denom) < 1e-12:
+                raise RuntimeError("point_intersection: lines are parallel or coincident.")
+            t = ((x3 - x1) * dy2 - (y3 - y1) * dx2) / denom
+            candidates = [(x1 + t * dx1, y1 + t * dy1)]
+
+        elif {t1, t2} == {"LINE", "CIRCLE"}:
+            line_p = props1 if t1 == "LINE" else props2
+            circ_p = props2 if t1 == "LINE" else props1
+            lx1, ly1 = line_p["start"][0], line_p["start"][1]
+            lx2, ly2 = line_p["end"][0], line_p["end"][1]
+            cx, cy = circ_p["center"][0], circ_p["center"][1]
+            r = circ_p["radius"]
+            dx, dy = lx2 - lx1, ly2 - ly1
+            fx, fy = lx1 - cx, ly1 - cy
+            a = dx * dx + dy * dy
+            b = 2.0 * (fx * dx + fy * dy)
+            c = fx * fx + fy * fy - r * r
+            disc = b * b - 4.0 * a * c
+            if disc < 0:
+                raise RuntimeError("point_intersection: line does not intersect circle.")
+            sq = math.sqrt(disc)
+            for sign in (1, -1):
+                t = (-b + sign * sq) / (2.0 * a)
+                candidates.append((lx1 + t * dx, ly1 + t * dy))
+
+        elif t1 == "CIRCLE" and t2 == "CIRCLE":
+            cx1, cy1, r1 = props1["center"][0], props1["center"][1], props1["radius"]
+            cx2, cy2, r2 = props2["center"][0], props2["center"][1], props2["radius"]
+            dx, dy = cx2 - cx1, cy2 - cy1
+            d = math.hypot(dx, dy)
+            if d < 1e-12:
+                raise RuntimeError("point_intersection: circles are concentric.")
+            if d > r1 + r2 + 1e-9 or d < abs(r1 - r2) - 1e-9:
+                raise RuntimeError("point_intersection: circles do not intersect.")
+            a = (r1 * r1 - r2 * r2 + d * d) / (2.0 * d)
+            h_sq = r1 * r1 - a * a
+            h = math.sqrt(max(h_sq, 0.0))
+            mx = cx1 + a * dx / d
+            my = cy1 + a * dy / d
+            candidates = [
+                (mx + h * dy / d, my - h * dx / d),
+                (mx - h * dy / d, my + h * dx / d),
+            ]
+
+        else:
+            raise RuntimeError(
+                f"point_intersection: unsupported entity combination {t1}+{t2}. "
+                "Supported: LINE-LINE, LINE-CIRCLE, CIRCLE-CIRCLE."
+            )
+
+        if len(candidates) == 1:
+            return candidates[0]
+        if ref_x is not None and ref_y is not None:
+            return min(
+                candidates,
+                key=lambda p: (p[0] - float(ref_x)) ** 2 + (p[1] - float(ref_y)) ** 2,
+            )
+        return candidates[0]
+
+    async def point_tangent(
+        self,
+        circle_handle: str,
+        from_x: float,
+        from_y: float,
+        ref_x: float | None = None,
+        ref_y: float | None = None,
+    ) -> tuple[float, float]:
+        """Return the tangent point on a circle from an external point.
+
+        When two tangent points exist, ``ref_x``/``ref_y`` selects the
+        nearer one; without it, the first is returned (counter-clockwise from
+        the from-point—circle-center line).
+
+        Raises RuntimeError if the point is inside the circle.
+        """
+        info = await self.entity_get(circle_handle)
+        if info.type.upper() != "CIRCLE":
+            raise RuntimeError(
+                f"point_tangent: handle {circle_handle!r} is {info.type}, expected CIRCLE."
+            )
+        cx, cy = info.properties["center"][0], info.properties["center"][1]
+        r = info.properties["radius"]
+        fx, fy = float(from_x), float(from_y)
+        dx, dy = cx - fx, cy - fy
+        d = math.hypot(dx, dy)
+        if d < r - 1e-9:
+            raise RuntimeError(
+                f"point_tangent: from-point ({fx}, {fy}) is inside the circle "
+                f"(center ({cx}, {cy}), radius {r})."
+            )
+        if d < 1e-12:
+            raise RuntimeError("point_tangent: from-point coincides with circle center.")
+        # Tangent point T lies on the circle such that (T-F)⊥(T-C).
+        # Solving cos(θ - α) = -r/d where α = atan2(C-F) gives the two
+        # circle angles θ at which the tangent touches the perimeter.
+        alpha = math.atan2(dy, dx)  # direction from F to C
+        # NEW-base-1: clamp the acos argument to [-1, 1] so a from-point in the
+        # narrow band [r-1e-9, r) (past the internal-point guard but with
+        # |-r/d| marginally > 1 from float error) degenerates gracefully to the
+        # tangent-at-perimeter case instead of raising a raw ValueError
+        # ("math domain error"). Genuine internal points (d < r) are already
+        # rejected by the RuntimeError guard above.
+        acos_neg = math.acos(max(-1.0, min(1.0, -r / d)))  # (π/2, π] for external pt
+        candidates: list[tuple[float, float]] = [
+            (cx + r * math.cos(alpha + acos_neg), cy + r * math.sin(alpha + acos_neg)),
+            (cx + r * math.cos(alpha - acos_neg), cy + r * math.sin(alpha - acos_neg)),
+        ]
+        if ref_x is not None and ref_y is not None:
+            return min(
+                candidates,
+                key=lambda p: (p[0] - float(ref_x)) ** 2 + (p[1] - float(ref_y)) ** 2,
+            )
+        return candidates[0]
+
+    @abstractmethod
+    async def _create_xline(
+        self,
+        x: float,
+        y: float,
+        dx: float,
+        dy: float,
+        layer: str,
+    ) -> EntityInfo:
+        """Create an infinite construction line (XLINE) through (x, y) with
+        unit direction (dx, dy) on `layer`. Backend-specific: XLINE has no
+        cross-backend entity_create_* equivalent."""
+        ...
+
+    async def _ensure_layer(self, name: str, color: int = 7) -> None:
+        """Idempotently make sure `name` exists (no-op if already present)."""
+        try:
+            existing = {lyr.name for lyr in await self.layer_list()}
+        except Exception:
+            existing = set()
+        if name not in existing:
+            try:
+                await self.layer_create(name, color=color)
+            except Exception:
+                pass  # already created / racy create — harmless
+
+    def _active_layer_set_id(self) -> str:
+        """Best-effort active layer set: an explicit `drawing_apply_iso_layers`
+        wins, else the committed PlanSpec, else 'mech' (the default bootstrap)."""
+        explicit = getattr(self, "_active_layer_set", None)
+        if explicit:
+            return explicit
+        plan = getattr(self, "_plan_spec", None)
+        if plan is not None:
+            return getattr(plan, "layer_set_id", "mech")
+        return "mech"
+
+    def _role_layer(self, role: str) -> str:
+        """Resolve the layer name for a role ('dim' | 'construction') in the
+        active layer set, so dims/scaffolding land on the right layer for
+        iso13567 (M-DIMEN-T-N / M-CONST-E-N) not just mech/pid (DIM/CONSTRUCTION)."""
+        from engineering.layers import resolve_role_layer
+
+        return resolve_role_layer(self._active_layer_set_id(), role)
+
+    async def construction_xline(
+        self,
+        x: float,
+        y: float,
+        angle_deg: float,
+        layer: str | None = None,
+    ) -> EntityInfo:
+        """Create an infinite construction line (XLINE) on the active layer set's
+        construction layer (auto-created with color 250 = lightest if missing)."""
+        layer = layer or self._role_layer("construction")
+        await self._ensure_layer(layer, color=250)
+        ang = math.radians(float(angle_deg))
+        return await self._create_xline(
+            float(x),
+            float(y),
+            math.cos(ang),
+            math.sin(ang),
+            layer,
+        )
+
+    async def construction_clear(
+        self,
+        layer: str | None = None,
+    ) -> dict:
+        """Delete every entity on the active layer set's construction layer.
+        Must be called before `drawing_finalize`."""
+        layer = layer or self._role_layer("construction")
+        try:
+            ents = await self.entity_list(layer_filter=layer, limit=5000)
+        except DocumentQuarantineError:
+            # "deleted: 0" here would read as "there was nothing to clear" on a
+            # document the backend has declared untrusted -- and this is step 9
+            # of the standard workflow, immediately before finalize.
+            raise
+        except Exception:
+            ents = []
+        deleted = 0
+        for ent in ents:
+            try:
+                await self.entity_delete(ent.handle)
+                deleted += 1
+            except Exception:
+                continue
+        return {"ok": True, "layer": layer, "deleted": deleted}
+
+    async def drawing_apply_iso_layers(
+        self,
+        standard: LayerSetId = "mech",
+    ) -> dict:
+        """Bootstrap a full ISO-conformant layer set with correct colors
+        and lineweights. Idempotent."""
+        from engineering.layers import apply_layer_set
+
+        result = await apply_layer_set(self, standard)
+        self._active_layer_set = standard
+        return {"ok": True, "standard": standard, "layers": result}
+
+    async def dimension_auto(
+        self,
+        handles: list[str],
+        style: DimStyle = "chain",
+        offset: float = 10.0,
+        layer: str | None = None,
+    ) -> list[EntityInfo]:
+        """Generate ISO 129 dimensions across `handles` in the chosen style
+        (chain | baseline | ordinate). `offset` is the dimension-line
+        distance from the reference geometry (mm). `layer` defaults to the
+        active layer set's dimension layer (DIM, or M-DIMEN-T-N for iso13567)."""
+        if not handles:
+            return []
+        dim_layer = layer or self._role_layer("dim")
+        if style not in ("chain", "baseline", "ordinate"):
+            raise RuntimeError(
+                f"dimension_auto: unknown style '{style}'. Use 'chain', 'baseline', or 'ordinate'."
+            )
+        segs: list[tuple[float, float, float, float]] = []
+        for h in handles:
+            ent = await self.entity_get(h)
+            if ent.type != "LINE":
+                raise RuntimeError(
+                    f"dimension_auto V1: only LINE entities supported (handle {h} is {ent.type})."
+                )
+            s = ent.properties.get("start")
+            e = ent.properties.get("end")
+            if s is None or e is None:
+                raise RuntimeError(f"dimension_auto: line {h} missing start/end.")
+            segs.append((float(s[0]), float(s[1]), float(e[0]), float(e[1])))
+
+        off = float(offset)
+        results: list[EntityInfo] = []
+
+        if style == "chain":
+            # Each line gets its own linear (rotated) dimension, offset clear of
+            # the geometry along its own perpendicular.
+            for sx, sy, ex, ey in segs:
+                mx = (sx + ex) / 2.0
+                my = (sy + ey) / 2.0
+                dx, dy = ex - sx, ey - sy
+                L = math.hypot(dx, dy) or 1.0
+                nx, ny = -dy / L, dx / L
+                dim = await self.dimension_linear(
+                    sx,
+                    sy,
+                    ex,
+                    ey,
+                    mx + nx * off,
+                    my + ny * off,
+                    rotation=math.degrees(math.atan2(dy, dx)),
+                    layer=dim_layer,
+                )
+                results.append(dim)
+
+        elif style == "baseline":
+            sx0, sy0, ex0, ey0 = segs[0]
+            dx, dy = ex0 - sx0, ey0 - sy0
+            L0 = math.hypot(dx, dy) or 1.0
+            ux, uy = dx / L0, dy / L0
+            base_rot = math.degrees(math.atan2(dy, dx))
+            for i, (_sx, _sy, ex, ey) in enumerate(segs):
+                dim = await self.dimension_linear(
+                    sx0,
+                    sy0,
+                    ex,
+                    ey,
+                    sx0 - uy * (off + i * off),
+                    sy0 + ux * (off + i * off),
+                    # Dimension line must run parallel to the (possibly rotated)
+                    # baseline, not horizontal.
+                    rotation=base_rot,
+                    layer=dim_layer,
+                )
+                results.append(dim)
+
+        else:  # ordinate — stacked X/Y distances; each feature offset so dims don't overlap
+            for i, (sx, sy, ex, ey) in enumerate(segs):
+                rung = off + i * off  # stagger per feature to avoid coincident dims
+                if abs(ex - sx) > 1e-9:
+                    dim = await self.dimension_linear(
+                        sx,
+                        sy,
+                        ex,
+                        sy,
+                        sx + (ex - sx) / 2.0,
+                        max(sy, ey) + rung,
+                        layer=dim_layer,
+                    )
+                    results.append(dim)
+                if abs(ey - sy) > 1e-9:
+                    dim = await self.dimension_linear(
+                        ex,
+                        sy,
+                        ex,
+                        ey,
+                        max(sx, ex) + rung,
+                        (sy + ey) / 2.0,
+                        rotation=90.0,
+                        layer=dim_layer,
+                    )
+                    results.append(dim)
+
+        return results
+
+    async def entity_select_smart(
+        self,
+        predicate: dict,
+    ) -> list[EntityInfo]:
+        """Semantic entity selection. Predicate keys (all optional, AND-ed):
+        - type: "LINE" | "CIRCLE" | ...
+        - layer: layer name
+        - near: [x, y, radius] — entity reference point within circle
+        - length_range: [min, max] — applies to LINE/ARC
+        - color: ACI int
+        """
+        if not isinstance(predicate, dict):
+            raise RuntimeError("entity_select_smart: predicate must be a dict.")
+        ptype = predicate.get("type")
+        player = predicate.get("layer")
+        pnear = predicate.get("near")  # [x, y, radius]
+        plen = predicate.get("length_range")  # [min, max]
+        pcolor = predicate.get("color")
+
+        ents = await self.entity_list(
+            type_filter=ptype.upper() if isinstance(ptype, str) else None,
+            layer_filter=player if isinstance(player, str) else None,
+            limit=5000,
+        )
+
+        def _ok(e: EntityInfo) -> bool:
+            if pcolor is not None and int(e.color) != int(pcolor):
+                return False
+            if pnear is not None:
+                try:
+                    nx, ny, nr = float(pnear[0]), float(pnear[1]), float(pnear[2])
+                except Exception:
+                    return False
+                pt = (
+                    e.properties.get("start")
+                    or e.properties.get("center")
+                    or e.properties.get("insertion")
+                    or e.properties.get("insertion_point")
+                )
+                if pt is None:
+                    return False
+                if (float(pt[0]) - nx) ** 2 + (float(pt[1]) - ny) ** 2 > nr**2:
+                    return False
+            if plen is not None and e.type in ("LINE", "ARC"):
+                try:
+                    lmin, lmax = float(plen[0]), float(plen[1])
+                except Exception:
+                    return False
+                length = e.properties.get("length")
+                if length is None or not (lmin <= float(length) <= lmax):
+                    return False
+            return True
+
+        return [e for e in ents if _ok(e)]

backends/contracts/refs.py

@@ -0,0 +1,103 @@
+"""External references, raster images and DWG output (v1.6 tracks B+G, group G).
+
+These are the only four operations of the sheet track that genuinely differ per
+engine, so they are the only four that become contract members. Everything else
+in `engineering/sheet/` composes the generic members and is written once.
+
+``AutoCADBackend`` composes every contract in this package, so importing
+``backends.base.AutoCADBackend`` is unchanged for callers.
+"""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+
+#: An xref is attached (its own xrefs come with it) or overlaid (they do not).
+XREF_KINDS = ("attach", "overlay")
+
+#: `list`, `detach` and `path` are headless; `reload` and `bind` need a live
+#: seat and are refused with the `xref_live` capability on the ezdxf engine.
+XREF_ACTIONS = ("list", "reload", "bind", "detach", "path")
+
+#: DWG formats both engines name the same way. COM maps them to AcSaveAsType
+#: (measured on AutoCAD 2026: 12/24/36/48/60/64); ezdxf maps them through
+#: `ezdxf.addons.odafc.VERSION_MAP`, which covers exactly these six and more.
+DWG_VERSIONS = ("R2000", "R2004", "R2007", "R2010", "R2013", "R2018")
+
+
+class RefsContract(ABC):
+    @abstractmethod
+    async def xref_attach(
+        self,
+        path: str,
+        at,
+        scale: float,
+        rotation: float,
+        kind: str,
+    ) -> dict:
+        """Attach an external reference and insert it once.
+
+        The block name is the referenced file's stem, which is what both
+        engines do. Returns ``{ok, name, path, kind, handle, at, scale,
+        rotation, backend}``.
+
+        Refuses, before anything is written: a `kind` outside
+        :data:`XREF_KINDS`, a file that does not exist, a non-finite
+        coordinate/scale/rotation, a non-positive scale, and a block name the
+        drawing already holds (re-attaching would either silently replace the
+        definition or raise mid-write).
+        """
+        ...
+
+    @abstractmethod
+    async def xref_manage(self, name: str, action: str, new_path: str | None) -> dict:
+        """One of :data:`XREF_ACTIONS` on one external reference.
+
+        ``list`` ignores `name` and returns
+        ``{ok, xrefs: [{name, path, kind, inserts}], backend}``. ``kind`` and
+        ``inserts`` are ``None`` on a live seat -- ActiveX's ``IAcadBlock``
+        carries no overlay indicator and no per-xref insert count (measured on
+        the registered type library), and a constant would read as measured.
+        ``path`` rewrites the saved path to `new_path` and returns the new one.
+        ``detach`` removes every insert of the xref -- in *every* entity space,
+        model space and each paper-space layout, because an insert left behind
+        with no block definition is a corrupt drawing -- then the definition,
+        and reports ``inserts_removed``. ``inserts`` counts the same set.
+        ``reload`` and ``bind`` need a live seat's xref manager: the headless engine raises
+        ``UnsupportedCapabilityError("xref_live", ...)`` rather than pretending,
+        which is why the key exists; ``list``/``detach``/``path`` are *not*
+        behind it.
+
+        Refuses an action outside the vocabulary, an unknown xref name, and a
+        ``path`` action with no `new_path`.
+        """
+        ...
+
+    @abstractmethod
+    async def image_attach(self, path: str, at, scale: float, rotation: float) -> dict:
+        """Attach a raster image as an underlay.
+
+        `scale` is drawing units per pixel, so the placed size is the image's
+        pixel size times `scale` and the aspect ratio is the file's. Returns
+        ``{ok, path, handle, at, scale, rotation, pixels: [w, h],
+        size_mm: [w, h], backend}``.
+
+        Refuses a file that does not exist, a file no image reader can open
+        (naming it), a non-positive scale and a non-finite number -- all before
+        anything is written.
+        """
+        ...
+
+    @abstractmethod
+    async def drawing_export_dwg(self, path: str, version: str) -> dict:
+        """Write the current drawing as a real DWG.
+
+        Returns ``{ok, path, version, bytes, backend}``. Refuses a `version`
+        outside :data:`DWG_VERSIONS` by name. Headlessly this needs the ODA
+        File Converter and otherwise raises
+        ``UnsupportedCapabilityError("dwg_write", ...)`` naming the install
+        route; on a live seat it is ``Document.SaveAs`` with the matching
+        ``AcSaveAsType``, which -- as AutoCAD's own SaveAs does -- leaves the
+        session bound to the file it just wrote.
+        """
+        ...

backends/contracts/settings.py

@@ -0,0 +1,684 @@
+"""Friendly facade over system variables.
+
+Split out of the single 1854-line ``AutoCADBackend`` ABC in v1.5.0 (M7).
+``AutoCADBackend`` composes every contract in this package, so importing
+``backends.base.AutoCADBackend`` is unchanged for callers.
+
+v1.6 (track E) grows the facade from 15 keys to 29: drawing limits, grid and
+snap, ortho and polar tracking, PSLTSCALE, the annotation scale, linear and
+angular unit formats, and the current dimension / text style. Every key still
+goes through ``system_get_variable`` / ``system_set_variable`` so the facade
+stays backend-agnostic; the *engines* are where a variable's real home is
+known (header, VPORT, the variable dictionary, or — headlessly — nowhere).
+"""
+
+from __future__ import annotations
+
+import math
+import re
+from typing import Any
+
+
+class SettingsContract:
+    # A user-facing wrapper over system_get_variable / system_set_variable that
+    # maps memorable names ("units", "dimscale", …) to AutoCAD system variables.
+    # Concrete + backend-agnostic: both engines accept the bare sysvar name, so
+    # the same call reads/writes on live COM and headless ezdxf alike.
+
+    async def drawing_settings(self, settings: dict | None = None) -> dict:
+        """Read (no args) or apply (with args) common drawing settings.
+
+        With ``settings=None`` returns a snapshot of every known setting. With a
+        dict, applies each provided key and returns ``{applied, changed,
+        errors}`` — ``changed`` holds ``[old, new]`` only for keys whose value
+        actually moved (re-setting a value to itself is not a change).
+
+        Friendly keys: units, linear_precision, angular_precision, ltscale,
+        dimscale, dim_text_height, dim_arrow_size, dim_decimals,
+        decimal_separator, zero_suppression, text_size, point_mode, point_size,
+        osmode, fillet_radius, limits, grid, grid_spacing, snap, snap_spacing,
+        ortho, polar, polar_angle, psltscale, annotation_scale, linear_units,
+        angular_units, dimstyle, textstyle.
+
+        Refusals (per key, in ``errors``; the other keys still apply): an
+        unknown key; a value outside ``_SETTING_RANGES``; a malformed
+        ``limits`` / ``annotation_scale``; ``annotation_scale`` on an R12 file
+        headlessly (no OBJECTS section, so the value would vanish at save —
+        save as R2000 or newer first); ``osmode`` / ``polar`` / ``polar_angle``
+        on the headless engine (registry-saved — ``capability: registry_sysvar``;
+        a snapshot reports them as ``None`` there, a file holds no value);
+        ``dimstyle`` / ``textstyle`` when the backend has no styles contract.
+
+        Note that a no-argument snapshot is one ``system_get_variable`` per key
+        (two for ``limits``). Free headless; a COM round trip each on a live
+        seat, and a write costs a read before and after it for ``changed``."""
+        if not settings:
+            snapshot: dict = {}
+            for key, spec in _SETTING_MAP.items():
+                try:
+                    snapshot[key] = await self._read_setting(key, spec)
+                except Exception as exc:
+                    snapshot[key] = {"error": str(exc)}
+            return {"ok": True, "settings": snapshot}
+
+        applied: dict = {}
+        changed: dict = {}
+        errors: dict = {}
+        for key, value in settings.items():
+            spec = _SETTING_MAP.get(key)
+            if spec is None:
+                errors[key] = f"unknown setting (valid: {sorted(_SETTING_MAP)})"
+                continue
+            try:
+                before = await self._read_setting(key, spec)
+                await self._write_setting(key, spec, value)
+                after = await self._read_setting(key, spec)
+                applied[key] = value
+                if after != before:
+                    changed[key] = [before, after]
+            except Exception as exc:
+                errors[key] = str(exc)
+
+        result = {"ok": not errors, "applied": applied, "changed": changed}
+        if errors:
+            result["errors"] = errors
+        return result
+
+    async def _read_setting(self, key: str, spec: tuple[str, str]) -> Any:
+        var, kind = spec
+        if kind == "limits":
+            low = await self.system_get_variable("LIMMIN")
+            high = await self.system_get_variable("LIMMAX")
+            if low is None or high is None:
+                return None
+            return [_point2(low), _point2(high)]
+        return _decode_setting(key, kind, await self.system_get_variable(var))
+
+    async def _write_setting(self, key: str, spec: tuple[str, str], value: Any) -> None:
+        var, kind = spec
+        if kind == "limits":
+            low, high = _encode_limits(key, value)  # validated before either write
+            await self.system_set_variable("LIMMIN", low)
+            await self.system_set_variable("LIMMAX", high)
+            return
+        if kind == "name":
+            name = _encode_name(key, value)
+            setter = getattr(self, _STYLE_SETTERS[key], None)
+            if not callable(setter):
+                raise ValueError(
+                    f"{key}: this backend has no {_STYLE_SETTERS[key]} (styles contract "
+                    f"absent); the current {key} can be read but not changed here."
+                )
+            await setter(name)
+            return
+        if kind == "bit":
+            flag = _encode_bool(key, value)
+            raw = await self.system_get_variable(var)
+            current = int(raw) if raw is not None else 0
+            mask = _BIT_MASKS[key]
+            await self.system_set_variable(var, (current | mask) if flag else (current & ~mask))
+            return
+        await self.system_set_variable(var, _encode_setting(key, kind, value))
+
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+
+# Friendly setting name -> (AutoCAD system variable, value kind).
+_SETTING_MAP: dict[str, tuple[str, str]] = {
+    "units": ("INSUNITS", "units"),
+    "linear_precision": ("LUPREC", "int"),
+    "angular_precision": ("AUPREC", "int"),
+    "ltscale": ("LTSCALE", "float"),
+    "dimscale": ("DIMSCALE", "float"),
+    # The dimension variables had no friendly name until v1.5.2, so the only
+    # way to reach dimension lettering was a raw `system_set_variable` — which
+    # is precisely the path that silently did nothing on the headless engine.
+    # `text_size` is TEXTSIZE, the height of a standalone TEXT entity; it has
+    # never had anything to do with the numbers on a dimension.
+    "dim_text_height": ("DIMTXT", "float"),
+    "dim_arrow_size": ("DIMASZ", "float"),
+    "dim_decimals": ("DIMDEC", "int"),
+    "decimal_separator": ("DIMDSEP", "char"),
+    "zero_suppression": ("DIMZIN", "int"),
+    "text_size": ("TEXTSIZE", "float"),
+    "point_mode": ("PDMODE", "int"),
+    "point_size": ("PDSIZE", "float"),
+    # OSMODE is registry-saved (a DXF R2000+ file has no $OSMODE), so the
+    # headless engine refuses it like the polar pair below.
+    "osmode": ("OSMODE", "int"),
+    "fillet_radius": ("FILLETRAD", "float"),
+    # ── track E: the environment a drawing lives in ──────────────────────
+    # `limits` is one friendly key over two variables; `_read_setting` and
+    # `_write_setting` special-case the kind, the variable named here is the
+    # first of the pair.
+    "limits": ("LIMMIN", "limits"),
+    # GRIDMODE / GRIDUNIT / SNAPMODE / SNAPUNIT are not header variables in a
+    # DXF file — AutoCAD keeps them on the active VPORT — so the headless engine
+    # routes them there (see `EzdxfBackend.system_set_variable`).
+    "grid": ("GRIDMODE", "bool"),
+    "grid_spacing": ("GRIDUNIT", "spacing"),
+    "snap": ("SNAPMODE", "bool"),
+    "snap_spacing": ("SNAPUNIT", "spacing"),
+    "ortho": ("ORTHOMODE", "bool"),
+    # Polar tracking on/off is AUTOSNAP bit 8 (the F10 toggle), not POLARMODE
+    # — POLARMODE's bits choose *how* polar angles are measured. Both AUTOSNAP
+    # and POLARANG are registry-saved, so a headless file cannot hold them.
+    "polar": ("AUTOSNAP", "bit"),
+    "polar_angle": ("POLARANG", "degrees"),
+    "psltscale": ("PSLTSCALE", "bool"),
+    # CANNOSCALE is a DICTIONARYVAR in AcDbVariableDictionary, not a header
+    # variable; CANNOSCALEVALUE is derived from it and read-only.
+    "annotation_scale": ("CANNOSCALE", "scale"),
+    "linear_units": ("LUNITS", "lunits"),
+    "angular_units": ("AUNITS", "aunits"),
+    # The current style names read through the header / GetVariable; a write
+    # delegates to the styles contract (`dimstyle_set_current` /
+    # `textstyle_set_current`) because DIMSTYLE is a read-only variable.
+    "dimstyle": ("DIMSTYLE", "name"),
+    "textstyle": ("TEXTSTYLE", "name"),
+}
+
+_STYLE_SETTERS = {"dimstyle": "dimstyle_set_current", "textstyle": "textstyle_set_current"}
+
+#: AUTOSNAP bit 8 = polar tracking on. (1 marker, 2 magnet, 4 tooltip, 16
+#: object snap tracking, 32 tracking tooltips, 64 dynamic input aperture.)
+_BIT_MASKS = {"polar": 8}
+
+# INSUNITS code table (AutoCAD $INSUNITS): friendly name <-> integer code.
+_UNIT_TO_CODE: dict[str, int] = {
+    "unitless": 0,
+    "inch": 1,
+    "inches": 1,
+    "in": 1,
+    "feet": 2,
+    "ft": 2,
+    "foot": 2,
+    "mm": 4,
+    "millimeter": 4,
+    "millimeters": 4,
+    "cm": 5,
+    "centimeter": 5,
+    "centimeters": 5,
+    "m": 6,
+    "meter": 6,
+    "meters": 6,
+}
+_CODE_TO_UNIT: dict[int, str] = {0: "unitless", 1: "inch", 2: "feet", 4: "mm", 5: "cm", 6: "m"}
+
+# LUNITS (linear unit format) and AUNITS (angular unit format) code tables.
+_LUNITS_TO_CODE: dict[str, int] = {
+    "scientific": 1,
+    "decimal": 2,
+    "engineering": 3,
+    "architectural": 4,
+    "fractional": 5,
+}
+_CODE_TO_LUNITS: dict[int, str] = {code: name for name, code in _LUNITS_TO_CODE.items()}
+_AUNITS_TO_CODE: dict[str, int] = {
+    "degrees": 0,
+    "dms": 1,
+    "grads": 2,
+    "radians": 3,
+    "surveyor": 4,
+}
+_CODE_TO_AUNITS: dict[int, str] = {code: name for name, code in _AUNITS_TO_CODE.items()}
+
+#: DIMDSEP is a character *code*, not a character — ezdxf raises DXFValueError
+#: on a string in the header — so the friendly key is where the translation
+#: belongs. Only two markers are in real use: ISO 129's point and the comma most
+#: of continental Europe drafts with. Anything else lands an arbitrary glyph in
+#: the middle of every number on the sheet, so it is refused rather than stored.
+_DECIMAL_MARKERS = (".", ",")
+
+#: "1:50", "2:1", "1:2.5" — paper units : drawing units, both strictly positive.
+SCALE_RE = re.compile(r"^\s*(\d+(?:\.\d+)?)\s*:\s*(\d+(?:\.\d+)?)\s*$")
+
+
+def parse_scale(text: Any) -> tuple[str, float, float]:
+    """``"1:50"`` → ``("1:50", 1.0, 50.0)``; raises ``ValueError`` naming the input.
+
+    Returns the canonical name (whitespace stripped, integers without a
+    trailing ``.0``), the paper units and the drawing units. The annotation
+    scale value AutoCAD reports as CANNOSCALEVALUE is ``paper / drawing``.
+    """
+    match = SCALE_RE.match(str(text)) if not isinstance(text, bool) else None
+    if match is None:
+        raise ValueError(
+            f"annotation_scale: {text!r} is not a scale — use 'paper:drawing' such as "
+            "'1:1', '1:50' or '2:1'."
+        )
+    paper, drawing = float(match.group(1)), float(match.group(2))
+    if paper <= 0 or drawing <= 0:
+        raise ValueError(f"annotation_scale: both sides of {text!r} must be greater than 0.")
+    return f"{_trim(paper)}:{_trim(drawing)}", paper, drawing
+
+
+def scale_value(text: Any) -> float:
+    """CANNOSCALEVALUE for a scale name: ``"1:50"`` → ``0.02``."""
+    _, paper, drawing = parse_scale(text)
+    return paper / drawing
+
+
+def _trim(number: float) -> str:
+    return str(int(number)) if number == int(number) else f"{number:g}"
+
+
+def _point2(raw: Any) -> list[float]:
+    """A 2D point from whatever the engine returned (tuple, list, Vec2/Vec3)."""
+    try:
+        return [float(raw[0]), float(raw[1])]
+    except (TypeError, IndexError, ValueError) as exc:
+        raise ValueError(f"expected a point, got {raw!r}") from exc
+
+
+def _finite(key: str, value: Any, what: str) -> float:
+    if isinstance(value, bool) or not isinstance(value, (int, float)):
+        raise ValueError(f"{key}: {what} must be a number, got {value!r}")
+    number = float(value)
+    if not math.isfinite(number):
+        raise ValueError(f"{key}: {what} must be finite")
+    return number
+
+
+def _encode_limits(key: str, value: Any) -> tuple[tuple[float, float], tuple[float, float]]:
+    """``[[xmin, ymin], [xmax, ymax]]`` → two 2D tuples; refused before any write."""
+    if (
+        not isinstance(value, (list, tuple))
+        or len(value) != 2
+        or any(not isinstance(corner, (list, tuple)) or len(corner) != 2 for corner in value)
+    ):
+        raise ValueError(f"{key}: expected [[xmin, ymin], [xmax, ymax]], got {value!r}")
+    xmin = _finite(key, value[0][0], "xmin")
+    ymin = _finite(key, value[0][1], "ymin")
+    xmax = _finite(key, value[1][0], "xmax")
+    ymax = _finite(key, value[1][1], "ymax")
+    if xmax <= xmin or ymax <= ymin:
+        raise ValueError(
+            f"{key}: the upper-right corner must be above and right of the lower-left "
+            f"(got {[[xmin, ymin], [xmax, ymax]]})"
+        )
+    return (xmin, ymin), (xmax, ymax)
+
+
+_TRUE_WORDS = {"1", "on", "true", "yes"}
+_FALSE_WORDS = {"0", "off", "false", "no"}
+
+
+def _encode_bool(key: str, value: Any) -> bool:
+    if isinstance(value, bool):
+        return value
+    if isinstance(value, (int, float)) and value in (0, 1):
+        return bool(value)
+    if isinstance(value, str):
+        word = value.strip().lower()
+        if word in _TRUE_WORDS:
+            return True
+        if word in _FALSE_WORDS:
+            return False
+    raise ValueError(f"{key}: expected true/false (or 1/0, on/off), got {value!r}")
+
+
+def _encode_name(key: str, value: Any) -> str:
+    if not isinstance(value, str) or not value.strip():
+        raise ValueError(f"{key}: expected a non-empty style name, got {value!r}")
+    return value.strip()
+
+
+def _encode_enum(key: str, value: Any, table: dict[str, int]) -> int:
+    if isinstance(value, (int, float)) and not isinstance(value, bool):
+        code = int(value)
+        if code in table.values():
+            return code
+        raise ValueError(f"{key}: code {code} is not one of {sorted(table.values())}")
+    name = str(value).strip().lower()
+    if name in table:
+        return table[name]
+    raise ValueError(f"{key}: unknown value {value!r}. Use one of {sorted(table)}.")
+
+
+def _encode_setting(key: str, kind: str, value: Any) -> Any:
+    """Coerce a friendly value into the raw system-variable value."""
+    if kind == "units":
+        if isinstance(value, (int, float)) and not isinstance(value, bool):
+            return int(value)
+        code = _UNIT_TO_CODE.get(str(value).strip().lower())
+        if code is None:
+            raise ValueError(
+                f"units: unknown value {value!r}. Use one of "
+                f"{sorted(set(_UNIT_TO_CODE))} or an INSUNITS integer."
+            )
+        return code
+    if kind == "lunits":
+        return _encode_enum(key, value, _LUNITS_TO_CODE)
+    if kind == "aunits":
+        return _encode_enum(key, value, _AUNITS_TO_CODE)
+    if kind == "bool":
+        return 1 if _encode_bool(key, value) else 0
+    if kind == "scale":
+        name, _paper, _drawing = parse_scale(value)
+        return name
+    if kind == "spacing":
+        if isinstance(value, (list, tuple)):
+            if len(value) != 2:
+                raise ValueError(f"{key}: expected a number or [x, y], got {value!r}")
+            x = _in_range(key, _finite(key, value[0], "x"))
+            y = _in_range(key, _finite(key, value[1], "y"))
+            return (x, y)
+        step = _in_range(key, _finite(key, value, "spacing"))
+        return (step, step)
+    if kind == "degrees":
+        degrees = _in_range(key, _finite(key, value, "angle"))
+        return math.radians(degrees)
+    if kind == "char":
+        if isinstance(value, bool):
+            marker = ""
+        elif isinstance(value, (int, float)):
+            code = int(value)
+            marker = chr(code) if 0 < code < 0x110000 else ""
+        else:
+            marker = str(value).strip()
+        if marker not in _DECIMAL_MARKERS:
+            raise ValueError(
+                f"{key}: unknown value {value!r}. Use one of {list(_DECIMAL_MARKERS)}."
+            )
+        return ord(marker)
+    if kind == "int":
+        return _in_range(key, int(float(value)))
+    if kind == "float":
+        return _in_range(key, float(value))
+    return value
+
+
+#: AutoCAD's own ranges for the settings that now reach the renderer.
+#:
+#: Before the DIM* header fold, an out-of-range value died harmlessly in the
+#: header. Folding it into the per-dimension override is what gave it teeth:
+#: `dim_decimals=-1` reported `ok: True` and then killed the *next* dimension
+#: with `ValueError: Format specifier missing precision` raised from inside
+#: ezdxf's formatter, nowhere near the call responsible; `dim_decimals=40`
+#: printed forty digits of float noise onto the sheet; and a non-positive
+#: length was reported applied and silently discarded. `applied` has to mean
+#: applied.
+_SETTING_RANGES: dict[str, tuple[float, float]] = {
+    "dim_decimals": (0, 8),  # DIMDEC
+    "zero_suppression": (0, 15),  # DIMZIN is a bitmask
+    "linear_precision": (0, 8),  # LUPREC
+    "angular_precision": (0, 8),  # AUPREC
+    "dim_text_height": (1e-9, 1e6),  # DIMTXT, strictly positive
+    "dim_arrow_size": (1e-9, 1e6),  # DIMASZ, strictly positive
+    "text_size": (1e-9, 1e6),  # TEXTSIZE
+    "dimscale": (0, 1e6),  # 0 means "scale to the viewport" and is legal
+    "ltscale": (1e-9, 1e6),
+    "point_size": (-100, 1e6),  # negative is a percentage of the screen
+    "fillet_radius": (0, 1e6),
+    # track E
+    "grid_spacing": (1e-9, 1e9),  # GRIDUNIT, strictly positive per axis
+    "snap_spacing": (1e-9, 1e9),  # SNAPUNIT, strictly positive per axis
+    "polar_angle": (1e-9, 360),  # POLARANG increment, degrees at the facade
+}
+
+
+def _in_range(key: str, value: float) -> float:
+    """Refuse a value the renderer cannot use, naming the range."""
+    bounds = _SETTING_RANGES.get(key)
+    if bounds is None:
+        return value
+    low, high = bounds
+    if not low <= value <= high:
+        low_text = "greater than 0" if 0 < low < 1e-6 else f"at least {low:g}"
+        raise ValueError(
+            f"{key}: {value:g} is out of range - must be {low_text} and at most {high:g}."
+        )
+    return value
+
+
+def _decode_setting(key: str, kind: str, raw: Any) -> Any:
+    """Present a raw system-variable value in friendly form."""
+    if raw is None:
+        return None
+    if kind == "units":
+        try:
+            code = int(raw)
+        except (TypeError, ValueError):
+            return raw
+        return {"code": code, "name": _CODE_TO_UNIT.get(code, "unknown")}
+    if kind == "lunits":
+        try:
+            code = int(raw)
+        except (TypeError, ValueError):
+            return raw
+        return {"code": code, "name": _CODE_TO_LUNITS.get(code, "unknown")}
+    if kind == "aunits":
+        try:
+            code = int(raw)
+        except (TypeError, ValueError):
+            return raw
+        return {"code": code, "name": _CODE_TO_AUNITS.get(code, "unknown")}
+    if kind == "bool":
+        try:
+            return bool(int(raw))
+        except (TypeError, ValueError):
+            return raw
+    if kind == "bit":
+        try:
+            return bool(int(raw) & _BIT_MASKS[key])
+        except (TypeError, ValueError):
+            return raw
+    if kind == "degrees":
+        try:
+            return round(math.degrees(float(raw)), 6)
+        except (TypeError, ValueError):
+            return raw
+    if kind == "spacing":
+        try:
+            x, y = _point2(raw)
+        except ValueError:
+            return raw
+        return x if x == y else [x, y]
+    if kind == "scale":
+        try:
+            name, paper, drawing = parse_scale(raw)
+        except ValueError:
+            return {"name": str(raw), "value": None}
+        return {"name": name, "value": paper / drawing}
+    if kind == "name":
+        return str(raw)
+    if kind == "char":
+        try:
+            code = int(raw)
+        except (TypeError, ValueError):
+            return raw
+        # ezdxf's renderer reads DIMDSEP 0 as a comma rather than as "unset",
+        # so report the marker that would actually be drawn.
+        return "," if code == 0 else chr(code)
+    if kind == "int":
+        try:
+            return int(raw)
+        except (TypeError, ValueError):
+            return raw
+    if kind == "float":
+        try:
+            return float(raw)
+        except (TypeError, ValueError):
+            return raw
+    return raw
+
+
+# ---------------------------------------------------------------------------
+# Document properties (DWGPROPS) — validation shared by both engines
+# ---------------------------------------------------------------------------
+
+#: The SummaryInfo fields AutoCAD's DWGPROPS dialog shows on its Summary tab.
+SUMMARY_FIELDS = ("title", "subject", "author", "keywords", "comments")
+
+
+#: The printable characters AutoCAD's ``SummaryInfo.AddCustomInfo`` rejects
+#: anywhere inside a custom key with ``Invalid key``. Measured on AutoCAD 2026
+#: by sweeping every character 0x20-0x7E through ``AddCustomInfo`` on a scratch
+#: document: exactly these thirteen are refused; every other printable ASCII
+#: character, every control character (0x01-0x1F, including tab), internal
+#: spaces, a no-break space and other unicode are accepted. Leading or
+#: trailing whitespace (space, tab or no-break space) is refused separately.
+_CUSTOM_KEY_FORBIDDEN = frozenset('"*,/:;<=>?\\`|')
+
+
+def custom_key_fold(key: str) -> str:
+    """Fold a custom-property key the way AutoCAD compares them.
+
+    AutoCAD's ``AddCustomInfo`` / ``SetCustomByKey`` / ``RemoveCustomByKey``
+    match keys by a *simple* one-to-one case compare, not Unicode full case
+    folding. Measured on AutoCAD 2026 (``AddCustomInfo`` of the second
+    spelling over the first): ``Project``/``PROJECT``, ``Grün``/``GRÜN``,
+    ``é``/``É``, ``ÿ``/``Ÿ``, ``ł``/``Ł``, ``σ``/``Σ``, ``я``/``Я`` and
+    ``dž``/``DŽ`` are the same key (``Duplicate key``), while ``Straße``/
+    ``STRASSE``, ``ẞ``/``ß``, ``kelvin``/``Kelvin`` (Kelvin sign), ``µ``/``Μ``,
+    ``σς``/``ΣΣ`` and ``Dž``/``DŽ`` are distinct (both stored) — every one of
+    which Python's ``str.casefold()`` calls equal. So this folds each character
+    to its lowercase only when the mapping is a single character that
+    round-trips (``lower().upper() == upper()``, ``upper().lower() == lower()``
+    and the character is one of the two); anything else — ``ß`` (uppercases
+    to ``SS``), the final sigma ``ς``, the micro sign ``µ``, the Kelvin sign,
+    the title-case digraph ``Dž``, dotless ``ı`` and dotted ``İ`` — is kept as
+    is. The result never changes length. This is what the headless engine and
+    the validator match on; the live engine lets AutoCAD decide (see
+    ``ComBackend.drawing_properties_set``).
+    """
+    out: list[str] = []
+    for c in key:
+        lo, up = c.lower(), c.upper()
+        if (
+            len(lo) == 1
+            and len(up) == 1
+            and lo.upper() == up
+            and up.lower() == lo
+            and c in (lo, up)
+        ):
+            out.append(lo)
+        else:
+            out.append(c)
+    return "".join(out)
+
+
+def _check_custom_text(key: str, text: str, what: str) -> None:
+    """A newline in a custom key or value corrupts the DXF on save.
+
+    ezdxf writes custom properties verbatim as ``9 / $CUSTOMPROPERTYTAG / 1 /
+    {key}`` and ``9 / $CUSTOMPROPERTY / 1 / {value}`` header lines — a line
+    break inside either text starts a new (invalid) group and the reopened
+    file fails with ``DXFStructureError``. Refused here so neither engine
+    writes it.
+    """
+    if "\n" in text or "\r" in text:
+        raise ValueError(
+            f"custom[{key!r}]: the {what} contains a line break, which corrupts the "
+            "DXF on save (the whole drawing would fail to reopen, not just the "
+            "property). Custom properties are single-line."
+        )
+
+
+def _check_custom_key_for_write(key: str) -> None:
+    """Mirror AutoCAD's ``AddCustomInfo`` key syntax so the live engine cannot
+    refuse mid-write. Measured on AutoCAD 2026: ``Invalid key`` for a key with
+    leading/trailing whitespace (space, tab, no-break space) or any of
+    ``_CUSTOM_KEY_FORBIDDEN`` anywhere in it — raised after the summary fields
+    and the earlier keys were already applied, while the headless engine
+    writes the same key without complaint. Only a *write* goes through
+    ``AddCustomInfo``; ``RemoveCustomByKey`` does not validate syntax (measured:
+    ``Key not found``, never ``Invalid key``), so a delete is not held to these
+    rules — a key that reached the drawing by other means (a DXF written by
+    ezdxf, say) must stay removable."""
+    if key != key.strip():
+        raise ValueError(
+            f"custom: key {key!r} has leading or trailing whitespace — AutoCAD's "
+            "AddCustomInfo rejects it as 'Invalid key'. Strip the key."
+        )
+    bad = sorted(set(key) & _CUSTOM_KEY_FORBIDDEN)
+    if bad:
+        shown = " ".join(repr(c) for c in bad)
+        raise ValueError(
+            f"custom: key {key!r} contains {shown} — AutoCAD's AddCustomInfo rejects "
+            f"it as 'Invalid key' (refused characters: {''.join(sorted(_CUSTOM_KEY_FORBIDDEN))}). "
+            "Use another separator."
+        )
+
+
+def validate_drawing_properties(
+    summary: dict | None, custom: dict | None
+) -> tuple[dict[str, str], dict[str, str], list[str]]:
+    """→ (summary fields to write, custom keys to write, custom keys to delete).
+
+    Refuses the whole request by name before either engine writes anything:
+    an unknown summary field is a ``ValueError``; a non-string summary value,
+    a non-string or empty custom key, or a custom value that is neither a
+    string nor ``None`` (``None`` deletes) is a ``TypeError``. Values are never
+    coerced with ``str()`` — a number the caller meant as text is theirs to
+    format.
+
+    Custom keys and values are also held to the rules the *other* engine would
+    enforce or the file format would break on, so the same call cannot succeed
+    on one engine and half-apply on the other (``ValueError`` naming the key):
+
+    * a key to *write* with leading or trailing whitespace, or containing any
+      of the thirteen characters ``" * , / : ; < = > ? \\ ` |`` — AutoCAD's
+      ``AddCustomInfo`` rejects exactly these as ``Invalid key`` mid-write
+      (measured on AutoCAD 2026 over every printable ASCII character), after
+      the summary fields and the earlier keys were already applied; the
+      headless engine writes them without complaint, and AutoCAD then loads
+      them from the DXF. A *delete* (``None``) is exempt: ``RemoveCustomByKey``
+      never validates syntax, and such keys do reach drawings by other routes,
+      so they must stay removable;
+    * two keys in one request that AutoCAD would treat as the same key — its
+      key compare is a simple one-to-one case compare (``custom_key_fold``;
+      measured: ``AddCustomInfo("PROJECT")`` over an existing ``Project``
+      raises ``Duplicate key``, while ``Straße`` and ``STRASSE`` are two
+      keys), so the second would fail mid-write on the live engine and write
+      a second tag headlessly;
+    * a key or value containing a line break (LF or CR) — ezdxf emits custom
+      properties unescaped, one header line per text, so the saved DXF is
+      corrupt and the whole drawing fails to reopen (``DXFStructureError``),
+      not just the property.
+    """
+    if summary is not None and not isinstance(summary, dict):
+        raise TypeError("summary: must be an object of {field: text}")
+    written: dict[str, str] = {}
+    for field, value in (summary or {}).items():
+        if field not in SUMMARY_FIELDS:
+            raise ValueError(f"summary: unknown field {field!r} (valid: {list(SUMMARY_FIELDS)})")
+        if value is None:
+            continue
+        if not isinstance(value, str):
+            raise TypeError(f"summary.{field}: must be a string, got {type(value).__name__}")
+        written[field] = value
+    if custom is not None and not isinstance(custom, dict):
+        raise TypeError("custom: must be an object of {key: text | null}")
+    to_write: dict[str, str] = {}
+    to_delete: list[str] = []
+    seen: dict[str, str] = {}  # folded key (AutoCAD's rule) -> the spelling seen first
+    for key, value in (custom or {}).items():
+        if not isinstance(key, str) or not key.strip():
+            raise TypeError(f"custom: key {key!r} must be a non-empty string")
+        _check_custom_text(key, key, "key")
+        folded = custom_key_fold(key)
+        if folded in seen:
+            raise ValueError(
+                f"custom: keys {seen[folded]!r} and {key!r} differ only by case — "
+                "AutoCAD compares custom keys with a simple per-character case "
+                "compare and calls these the same key (AddCustomInfo raises "
+                "'Duplicate key'). Mention the key once."
+            )
+        seen[folded] = key
+        if value is None:
+            to_delete.append(key)
+        elif isinstance(value, str):
+            _check_custom_key_for_write(key)
+            _check_custom_text(key, value, "value")
+            to_write[key] = value
+        else:
+            raise TypeError(
+                f"custom[{key!r}]: must be a string or null (null deletes the key), "
+                f"got {type(value).__name__}"
+            )
+    return written, to_write, to_delete

backends/contracts/solids.py

@@ -0,0 +1,79 @@
+"""ACIS solids (live AutoCAD only).
+
+Split out of the single 1854-line ``AutoCADBackend`` ABC in v1.5.0 (M7).
+``AutoCADBackend`` composes every contract in this package, so importing
+``backends.base.AutoCADBackend`` is unchanged for callers.
+"""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+
+
+class SolidContract(ABC):
+    @abstractmethod
+    async def solid_box(
+        self, cx: float, cy: float, cz: float, length: float, width: float, height: float
+    ) -> dict:
+        """Create a 3D solid box centered at (cx, cy, cz)."""
+        ...
+
+    @abstractmethod
+    async def solid_cylinder(
+        self, cx: float, cy: float, cz: float, radius: float, height: float
+    ) -> dict:
+        """Create a 3D solid cylinder centered at (cx, cy, cz)."""
+        ...
+
+    @abstractmethod
+    async def solid_extrude(
+        self, profile_handle: str, height: float, taper_angle: float = 0.0
+    ) -> dict:
+        """Extrude a closed profile (circle/closed polyline) into a solid."""
+        ...
+
+    @abstractmethod
+    async def solid_revolve(
+        self,
+        profile_handle: str,
+        axis_x1: float,
+        axis_y1: float,
+        axis_x2: float,
+        axis_y2: float,
+        angle: float = 360.0,
+    ) -> dict:
+        """Revolve a closed profile around an axis into a solid."""
+        ...
+
+    @abstractmethod
+    async def solid_boolean(self, target_handle: str, tool_handle: str, operation: str) -> dict:
+        """Boolean two solids: operation is union | subtract | intersect."""
+        ...
+
+    @abstractmethod
+    async def drawing_audit(self) -> dict:
+        """Audit the drawing, applying every repair the backend can make.
+
+        This MUTATES the drawing. Returns ``{"ok", "repaired", "fixes",
+        "fix_count", "errors", "error_count"}``, where ``fixes`` are problems
+        already repaired and ``errors`` are problems that could not be; both are
+        lists of ``{"code": int, "name": str, "message": str, "handle": str |
+        None}``.
+
+        A backend that repairs but cannot observe its own result reports
+        ``repaired``/``fix_count``/``error_count`` as ``None`` — never ``0``,
+        which would claim nothing was wrong — plus ``"detail": "unavailable"``
+        and ``"capability": "audit_detail"`` so a client can pre-check the
+        boundary. Any implementation that repairs MUST mark the document dirty,
+        or the repair is discarded the next time the document is closed.
+        """
+        ...
+
+    @abstractmethod
+    async def drawing_close(self, save: bool = True) -> dict: ...
+
+    @abstractmethod
+    async def drawing_undo(self) -> dict: ...
+
+    @abstractmethod
+    async def drawing_redo(self) -> dict: ...

backends/contracts/styles.py

@@ -0,0 +1,136 @@
+"""Dimension, text and multileader styles (track E, group S).
+
+``AutoCADBackend`` composes every contract in this package, so importing
+``backends.base.AutoCADBackend`` is unchanged for callers.
+
+Names are matched case-insensitively — AutoCAD's rule for every symbol
+table — and reported in the table's own spelling. Every refusal is raised
+before a table is touched: ``ValueError`` naming the key (a missing style, a
+clash, a variable outside ``engineering.standards.dimstyles.DIM_VARIABLE_RANGES``),
+``TypeError`` for a wrong type.
+"""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+
+
+class StylesContract(ABC):
+    @abstractmethod
+    async def dimstyle_list(self) -> list[dict]:
+        """Every DIMSTYLE entry: ``[{name, current, values, values_available}]``.
+
+        ``values`` holds the seventeen preset variables
+        (``engineering.standards.dimstyles.PRESET_VARIABLES``) with ``DIMDSEP``
+        as the character. Headless every row carries them (the DXF's stored
+        value, else the schema default AutoCAD applies to an omitted code).
+        On the live engine ActiveX has no per-style getters — ``AcadDimStyle``
+        exposes ``Name`` and ``CopyFrom`` only — so ``values`` is read for the
+        *current* style and the other rows carry ``values: None`` with
+        ``values_available: False`` rather than cycling the active style
+        behind the operator's back.
+        """
+        ...
+
+    @abstractmethod
+    async def dimstyle_create(self, name: str, values: dict, set_current: bool = False) -> dict:
+        """Create a dimension style from a fully resolved ``values`` dict
+        (``engineering.standards.dimstyles.resolve_dimstyle(preset, overrides)``).
+
+        Returns ``{ok, name, values, written, current, textstyle_created}``.
+        ``DIMTXSTY`` must name a text style that exists or a bundled preset
+        (ISOCP / ISOCPEUR / ARIAL / ROMANS), which is created first and
+        reported in ``textstyle_created``; anything else is refused by name.
+        A name clash is refused (``dimstyle_modify`` changes an existing
+        style). With ``set_current`` the style becomes ``$DIMSTYLE`` *and* its
+        values become the current ``DIM*`` settings — what a live seat does —
+        so the next dimension carries them on both engines.
+        """
+        ...
+
+    @abstractmethod
+    async def dimstyle_modify(self, name: str, values: dict) -> dict:
+        """Change variables on an existing style.
+
+        Returns ``{ok, name, changed: {VAR: [old, new]}, dimensions_using_style,
+        rerender_required}``. ``changed`` names only the variables that moved
+        (the ``hatch_edit`` rule: re-setting a value to itself is not a
+        change). Dimensions already drawn with the style are listed by handle;
+        ``rerender_required`` is ``True`` headlessly when any exist and
+        something changed, because a headless DIMENSION carries its rendered
+        block and shows the old style until it is redrawn — AutoCAD re-renders
+        on the next regen, so the live engine reports ``False``. Modifying the
+        current style also updates the ``DIM*`` current settings.
+        """
+        ...
+
+    @abstractmethod
+    async def dimstyle_set_current(self, name: str) -> dict:
+        """Make ``name`` the current dimension style.
+
+        Returns ``{ok, current, previous, changed}``. Sets ``$DIMSTYLE`` and
+        loads the style's stored variables into the current ``DIM*`` settings
+        (AutoCAD's ``-DIMSTYLE Restore``; on the live engine unsaved overrides
+        of the previous style are discarded, which is AutoCAD's own rule).
+        The dimension tools then create dimensions with it; the per-dimension
+        override path (tolerances, fits, text override) is unchanged.
+        """
+        ...
+
+    @abstractmethod
+    async def textstyle_list(self) -> list[dict]:
+        """``[{name, font, height, width_factor, oblique_deg, current}]``."""
+        ...
+
+    @abstractmethod
+    async def textstyle_create(
+        self,
+        name: str,
+        font: str,
+        height: float = 0.0,
+        width_factor: float = 1.0,
+        oblique_deg: float = 0.0,
+        set_current: bool = False,
+    ) -> dict:
+        """Create a text style. Returns ``{ok, name, font, font_resolved, current}``.
+
+        ``font`` is a preset (``ISOCP`` / ``isocp.shx`` / ``isocp``, any case)
+        or any file name. A file that is neither a preset nor found on the
+        engine's font path is *written* and reported ``font_resolved: False``
+        — a DXF stores only the name and AutoCAD substitutes at open — never
+        refused. Refuses a clash, ``width_factor <= 0``, ``height < 0``, an
+        oblique angle outside ±85°, an empty font.
+        """
+        ...
+
+    @abstractmethod
+    async def textstyle_set_current(self, name: str) -> dict:
+        """``$TEXTSTYLE``. Returns ``{ok, current, previous, changed}``; new
+        TEXT/MTEXT then carry the style on both engines."""
+        ...
+
+    @abstractmethod
+    async def mleaderstyle_list(self) -> list[dict]:
+        """``[{name, arrow_size, landing_gap, text_style, text_height, values_available}]``.
+
+        Both engines report the four values (``values_available: True``).
+        Headless they are read from the MLEADERSTYLE object (schema defaults
+        for an unset field); live from the ``AcadMLeaderStyle`` objects the
+        ``ACAD_MLEADERSTYLE`` dictionary holds (``ArrowSize`` / ``LandingGap``
+        / ``TextHeight`` in drawing units, ``TextStyle`` a name) — ActiveX
+        exposes no *collection* property for them, but the dictionary items
+        are full ``IAcadMLeaderStyle`` objects.
+        """
+        ...
+
+    @abstractmethod
+    async def mleaderstyle_create(self, name: str, values: dict) -> dict:
+        """Create a multileader style from a resolved ``values`` dict
+        (``engineering.standards.mleaderstyles.resolve_mleaderstyle``).
+        Both engines: ezdxf on ``doc.mleader_styles``; live through
+        ``Dictionaries.Item("ACAD_MLEADERSTYLE").AddObject(name,
+        "AcDbMLeaderStyle")`` and the object's property writes. Returns
+        ``{ok, name, values, textstyle_created}``; the text style follows the
+        ``dimstyle_create`` rule (exists or preset, else refused by name); a
+        clash is refused — before anything is written."""
+        ...

backends/contracts/system.py

@@ -0,0 +1,28 @@
+"""System variables and raw commands.
+
+Split out of the single 1854-line ``AutoCADBackend`` ABC in v1.5.0 (M7).
+``AutoCADBackend`` composes every contract in this package, so importing
+``backends.base.AutoCADBackend`` is unchanged for callers.
+"""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from typing import Any
+
+
+class SystemContract(ABC):
+    @abstractmethod
+    async def system_status(self) -> dict: ...
+
+    @abstractmethod
+    async def system_get_variable(self, name: str) -> Any: ...
+
+    @abstractmethod
+    async def system_set_variable(self, name: str, value: Any) -> dict: ...
+
+    @abstractmethod
+    async def system_run_command(self, command: str) -> dict: ...
+
+    @abstractmethod
+    async def system_run_lisp(self, expression: str) -> dict: ...

backends/contracts/transactions.py

@@ -0,0 +1,21 @@
+"""Transactions.
+
+Split out of the single 1854-line ``AutoCADBackend`` ABC in v1.5.0 (M7).
+``AutoCADBackend`` composes every contract in this package, so importing
+``backends.base.AutoCADBackend`` is unchanged for callers.
+"""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+
+
+class TransactionContract(ABC):
+    @abstractmethod
+    async def transaction_begin(self) -> dict: ...
+
+    @abstractmethod
+    async def transaction_commit(self) -> dict: ...
+
+    @abstractmethod
+    async def transaction_rollback(self) -> dict: ...

backends/contracts/view.py

@@ -0,0 +1,43 @@
+"""Views and screenshots.
+
+Split out of the single 1854-line ``AutoCADBackend`` ABC in v1.5.0 (M7).
+``AutoCADBackend`` composes every contract in this package, so importing
+``backends.base.AutoCADBackend`` is unchanged for callers.
+"""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+
+
+class ViewContract(ABC):
+    @abstractmethod
+    async def view_zoom_extents(self) -> dict: ...
+
+    @abstractmethod
+    async def view_zoom_window(
+        self,
+        x1: float,
+        y1: float,
+        x2: float,
+        y2: float,
+    ) -> dict: ...
+
+    @abstractmethod
+    async def view_screenshot(self, overlay_handles: bool = False) -> bytes | None: ...
+
+    @abstractmethod
+    async def view_screenshot_grounded(
+        self,
+        overlay_handles: bool = True,
+        max_labels: int = 40,
+    ) -> dict:
+        """Screenshot plus the handle-to-position mapping it drew.
+
+        Returns ``{"png", "labels", "labelled", "total", "truncated"}``.
+        ``labels`` maps handle -> ``[x, y]`` in drawing units, so the picture and
+        the handle space a caller can act on are the same thing. ``truncated``
+        says a crowded drawing was capped rather than letting a labelled subset
+        read as the whole sheet.
+        """
+        ...

backends/ocs.py

@@ -0,0 +1,126 @@
+"""OCS (Object Coordinate System) to WCS translation, shared by both backends.
+
+DXF does not store 2D geometry in world coordinates. CIRCLE, ARC, LWPOLYLINE,
+TEXT, INSERT and a dimension's text position live in a per-entity frame derived
+from the entity's ``extrusion`` vector by the Arbitrary Axis Algorithm. Mirroring
+flips extrusion to ``(0, 0, -1)`` and leaves the stored x *unnegated*, so a raw
+``dxf.center`` read reports a point the entity is not at — by 60 mm in the
+measured case, while the same response's bounding box (which ezdxf computes
+through the renderer, in WCS) said otherwise.
+
+The rule this module exists to enforce: **everything crossing the MCP boundary is
+WCS.** OCS never leaves the backends.
+
+Both engines share this. ``ezdxf`` is a core dependency, not an extra, so the COM
+backend may import it too — and should, rather than hand-rolling the Arbitrary
+Axis Algorithm a second time. The functions take a raw extrusion/normal triple
+rather than an entity, because a COM object exposes ``.Normal`` where an ezdxf
+one exposes ``.dxf.extrusion``.
+
+Not every entity that *carries* extrusion is affected: ezdxf makes ``ocs()`` a
+pass-through for LINE, MTEXT, ELLIPSE, SPLINE and POINT, which are WCS-native.
+Keying any fix off "has an extrusion attribute" breaks those.
+"""
+
+from __future__ import annotations
+
+import math
+
+from ezdxf.math import OCS, Vec3
+
+_IDENTITY = (0.0, 0.0, 1.0)
+
+
+def is_wcs_frame(extrusion) -> bool:
+    """True when the entity's frame is the identity — nothing to translate."""
+    try:
+        return OCS(Vec3(extrusion)).uz.isclose(_IDENTITY)
+    except Exception:
+        return True  # an unreadable extrusion is not evidence of a rotated frame
+
+
+def is_flat_frame(extrusion) -> bool:
+    """True when the entity's plane is parallel to WCS XY (extrusion is +/-Z).
+
+    Only these frames admit an exact 2D write: given a tilted plane, an ``(x, y)``
+    pair does not determine a point in it, so writing one would displace the
+    entity out of its own plane by an amount nobody supplied.
+    """
+    try:
+        uz = OCS(Vec3(extrusion)).uz
+    except Exception:
+        return True
+    return abs(uz.x) < 1e-12 and abs(uz.y) < 1e-12
+
+
+def to_wcs_2d(extrusion, x, y, z=0.0) -> list[float]:
+    """OCS ``(x, y, z)`` to WCS ``[x, y]``.
+
+    ``z`` is ``dxf.elevation`` for an LWPOLYLINE (whose vertices carry no z of
+    their own) and the point's own z otherwise.
+    """
+    v = OCS(Vec3(extrusion)).to_wcs(Vec3(float(x), float(y), float(z)))
+    return [float(v.x), float(v.y)]
+
+
+def from_wcs(extrusion, x, y, z=0.0) -> tuple[float, float, float]:
+    """WCS ``(x, y, z)`` to OCS ``(x, y, z)`` — the inverse of :func:`to_wcs_2d`.
+
+    Needed on every write path. The read and write halves used to be *equally*
+    wrong, which made a read-then-write round trip an accidental no-op; fixing
+    reads alone would have converted that no-op into a real move.
+    """
+    v = OCS(Vec3(extrusion)).from_wcs(Vec3(float(x), float(y), float(z)))
+    return (float(v.x), float(v.y), float(v.z))
+
+
+def wcs_arc_angles(extrusion, center_ocs, radius, start_deg, end_deg) -> tuple[float, float]:
+    """OCS sweep angles to CCW-in-WCS angles about the WCS centre.
+
+    Computed by mapping the two endpoints through the frame rather than by
+    arithmetic on the angles, so it stays right for any frame. A left-handed
+    frame (``uz.z < 0``, which is what a mirror produces) reverses the direction
+    of the sweep, so the endpoints swap roles.
+    """
+    ocs = OCS(Vec3(extrusion))
+    c0 = Vec3(center_ocs)
+    centre = ocs.to_wcs(c0)
+    angles = []
+    for angle in (float(start_deg), float(end_deg)):
+        point = ocs.to_wcs(Vec3.from_deg_angle(angle, abs(float(radius))) + c0)
+        angles.append(math.degrees(math.atan2(point.y - centre.y, point.x - centre.x)) % 360.0)
+    if ocs.uz.z < 0:
+        angles.reverse()
+    return angles[0], angles[1]
+
+
+def plane_normal(extrusion) -> list[float]:
+    """The entity's plane normal, for reporting a frame that xy cannot express."""
+    uz = OCS(Vec3(extrusion)).uz
+    return [float(uz.x), float(uz.y), float(uz.z)]
+
+
+def wcs_bulge(extrusion, bulge) -> float:
+    """An LWPOLYLINE vertex bulge as the arc reads in WCS XY.
+
+    The bulge is ``tan(sweep/4)``, signed counter-clockwise *in the entity's
+    own frame*. A left-handed frame (``uz.z < 0`` — what a mirror produces) is
+    a reflection of WCS XY, and a reflection reverses every arc's sense: the
+    same stored ``+1`` that bowed to -y before ``entity_mirror`` bows to +y
+    after it, while ``points`` translated through :func:`to_wcs_2d` land where
+    the vertices really are. Handing the stored sign out next to translated
+    points describes the arc's mirror image, and nothing in the payload can
+    show it (``length`` is frame-invariant). Same rule as
+    :func:`wcs_arc_angles` reversing an ARC's endpoints.
+
+    The magnitude is left alone: it is exact for every flat frame, and in a
+    tilted plane the projected arc is no longer circular at all, which
+    ``plane_normal`` already reports.
+    """
+    value = float(bulge or 0.0)
+    if value == 0.0:
+        return 0.0
+    try:
+        return -value if OCS(Vec3(extrusion)).uz.z < 0 else value
+    except Exception:
+        return value  # an unreadable extrusion is not evidence of a reflected frame

backends/quarantine.py

@@ -0,0 +1,208 @@
+"""Document quarantine — the vocabulary for a call that was abandoned mid-write.
+
+``EzdxfBackend._async`` cannot cancel an ``asyncio.to_thread`` worker. When a
+call overruns ``EZDXF_CALL_TIMEOUT`` the handler swaps in a fresh
+``asyncio.Lock`` so later callers do not deadlock behind the orphaned one — and
+that swap is precisely what removes the mutual exclusion the lock existed for.
+The runaway thread keeps a live reference to the one shared ``ezdxf.Drawing``,
+which is explicitly not thread-safe, through the closure it was handed.
+
+Measured, with a runaway ``_sync`` that really appends LINEs to ``_doc``:
+``entity_create_circle`` after the abandonment returned handle ``A1``;
+``drawing_info`` reported 116 entities for a modelspace observed at 302 and
+climbing; ``drawing_save`` returned ``{"ok": True}`` and wrote a valid DXF of
+15200 of the 60000 entities the runaway would go on to write — a considered
+document of a state that never existed. Only the timed-out caller was warned.
+
+So the abandonment quarantines the DOCUMENT, not the backend. The document stays
+untrusted until it is REPLACED by an object the abandoned thread has no
+reference to (``drawing_open`` / ``drawing_new`` / ``drawing_close``), or until
+the abandoned call is seen to finish cleanly — see ``AbandonedCall``.
+
+This module deliberately has no ezdxf import: ``server.py`` needs the exception
+type to classify a refusal on a box where a backend's dependencies are missing.
+"""
+
+from __future__ import annotations
+
+import time
+from typing import Any
+
+__all__ = [
+    "AbandonedCall",
+    "DocumentQuarantineError",
+    "QuarantineRecord",
+    "quarantine_refusal",
+    "real_call_name",
+]
+
+#: Longest ``repr`` kept for a return value nobody received. A late
+#: ``entity_list`` can return thousands of entities; the diagnostic is that the
+#: value was lost, not what was in it.
+_MAX_RESULT_REPR = 200
+
+
+def real_call_name(func: Any) -> str:
+    """The backend method ``func`` belongs to, not the closure's own name.
+
+    Every real backend method hands ``_async`` a closure literally named
+    ``_sync`` — measured: ``__name__='_sync'``,
+    ``__qualname__='EzdxfBackend.drawing_save.<locals>._sync'`` — so
+    ``__name__`` made every production timeout read ``ezdxf call '_sync' timed
+    out``. The qualname carries the name the user typed and was being discarded.
+    """
+    qualname = getattr(func, "__qualname__", "") or ""
+    parts = qualname.split(".")
+    if "<locals>" in parts:
+        index = parts.index("<locals>")
+        if index:
+            return parts[index - 1]
+    return getattr(func, "__name__", None) or "call"
+
+
+class AbandonedCall:
+    """Observation post for a worker thread ``_async`` can no longer await.
+
+    The obvious hook does not work, and this was checked before being relied on:
+    ``asyncio.timeout_at`` **cancels** the Future ``_async`` awaits, so by the
+    time the abandon branch runs that Future is already done and
+    ``add_done_callback`` fires immediately with ``cancelled()`` True. It reports
+    the *await* ending, never the thread — which ``asyncio.to_thread`` cannot
+    cancel. The only place the thread's outcome is observable is inside the
+    thread, so ``_async`` wraps every timed call in one of these.
+
+    Deliberately no ``threading.Event``: this is allocated on every ``_async``
+    call and an Event carries a Condition and a Lock. ``finished`` is a plain
+    bool written once by the worker and read from the event loop; a bool store is
+    atomic under the GIL and nothing here ever waits on it.
+    """
+
+    __slots__ = ("func", "finished", "result", "error")
+
+    def __init__(self, func):
+        self.func = func
+        self.finished = False
+        self.result: Any = None
+        self.error: BaseException | None = None
+
+    def __call__(self, *args, **kwargs):
+        try:
+            self.result = self.func(*args, **kwargs)
+            return self.result
+        except BaseException as exc:
+            self.error = exc
+            raise
+        finally:
+            self.finished = True
+
+
+class QuarantineRecord:
+    """One abandoned call, and what became of it.
+
+    Holds the identity of the ``Drawing`` that was live at abandon time as well
+    as its path: rebinding ``self._doc`` isolates a ``_sync`` that captured
+    doc/msp once at entry (the shape of nearly every closure in the backend), but
+    one that re-reads ``self._msp()`` inside its own loop would follow the rebind
+    into the fresh document. ``_async`` cannot prevent that, so recovery says
+    when the runaway was still alive instead of implying it was fenced off.
+    """
+
+    def __init__(
+        self,
+        call: str,
+        timeout: float,
+        watcher: Any,
+        *,
+        document_path: str | None = None,
+        document_id: int | None = None,
+    ):
+        self.call = call
+        self.timeout = float(timeout)
+        self.watcher = watcher
+        self.document_path = document_path
+        self.document_id = document_id
+        self.stamp = time.monotonic()
+        self.outcome = "running"
+        self.detail = ""
+        self.released_by: str | None = None
+        self.result_lost = False
+        self.result_repr: str | None = None
+
+    def age(self) -> float:
+        return time.monotonic() - self.stamp
+
+    def thread_alive(self) -> bool:
+        return not self.watcher.finished
+
+    def capture_lost_result(self) -> None:
+        """Record that the return value never reached the caller.
+
+        A late-completing ``entity_create_*`` leaves an entity in the document
+        whose handle nobody holds. That is not recoverable, so it is at least
+        reported rather than dropped.
+        """
+        self.result_lost = True
+        try:
+            text = repr(self.watcher.result)
+        except Exception:  # a __repr__ that raises must not break the report
+            text = f"<unreprable {type(self.watcher.result).__name__}>"
+        if len(text) > _MAX_RESULT_REPR:
+            text = text[: _MAX_RESULT_REPR - 3] + "..."
+        self.result_repr = text
+
+    def to_dict(self) -> dict:
+        return {
+            "call": self.call,
+            "timeout": self.timeout,
+            "age_seconds": round(self.age(), 3),
+            "thread_alive": self.thread_alive(),
+            "outcome": self.outcome,
+            "detail": self.detail,
+            "released_by": self.released_by,
+            "result_lost": self.result_lost,
+            "lost_return_value": self.result_repr,
+            "document_path": self.document_path,
+        }
+
+
+def quarantine_refusal(record: QuarantineRecord) -> DocumentQuarantineError:
+    """The refusal every later call on a quarantined document gets."""
+    thread = "still running" if record.thread_alive() else "has since stopped"
+    return DocumentQuarantineError(
+        record,
+        f"ezdxf document quarantined: '{record.call}' overran "
+        f"EZDXF_CALL_TIMEOUT={record.timeout:g}s {record.age():.1f}s ago and its worker "
+        f"thread ({thread}) cannot be cancelled, so it may still be mutating this "
+        "drawing. Every call on it is refused, reads included - a read of a container "
+        "another thread is appending to does not fail loudly, it never finishes. "
+        "Recover with drawing_open(path), drawing_new() or drawing_close(): those "
+        "rebind the document to a freshly constructed object the abandoned thread "
+        "cannot reach. Undo and rollback are not a way back - their snapshots may "
+        "themselves have been serialised mid-write. system_status() stays answerable "
+        "and reports the abandoned call.",
+    )
+
+
+class DocumentQuarantineError(RuntimeError):
+    """The open document is untrusted because a call was abandoned on it.
+
+    Carries **no** ``capability`` attribute, on purpose.
+    ``server._batch_capability_of`` classifies refusals structurally — any
+    exception with a non-empty ``capability`` str plus a callable ``to_dict()``
+    is reported to the client as ``kind: "unsupported"`` and filed by
+    ``cad_batch`` as a capability step row. Borrowing one here would tell the
+    client the ezdxf engine cannot draw a circle. The engine is fine; the
+    document is not. This needs its own kind, not a borrowed one.
+    """
+
+    def __init__(self, record: QuarantineRecord, message: str):
+        super().__init__(message)
+        self.quarantine = record.to_dict()
+
+    def to_dict(self) -> dict:
+        return {
+            "ok": False,
+            "kind": "quarantined",
+            "error": str(self),
+            "quarantine": self.quarantine,
+        }

backends/xdata_specs.py

@@ -0,0 +1,196 @@
+"""XDATA value typing and limits, shared by both engines.
+
+DXF XDATA is a list of (group code, value) pairs under a registered APPID.
+This module is the one place that decides how a JSON value becomes a group
+code and enforces the two limits AutoCAD enforces silently: 255 characters
+per string and 16 KB per *entity* -- across every application on it, the ACAD
+app's own overrides (DSTYLE on a toleranced dimension) included, not just the
+app being written. ``encode_values`` refuses a single call that cannot fit;
+``check_entity_budget`` is the real gate, run by both engines against the
+entity's existing XDATA before anything is written, so the headless engine
+refuses exactly the write the live engine's ``SetXData`` would reject.
+
+It also refuses the values neither engine can store: a line separator inside a
+string, and a non-finite or non-numeric "number". DXF is a text format of
+alternating "group code" / "value" lines, and ezdxf writes a 1000 tag verbatim,
+so a LF or CR in the value splits the tag pair and the saved file -- and every
+undo/transaction snapshot, which is also a DXF save -- becomes unreadable. A
+``nan``/``inf`` real is written as the literal text ``nan``/``inf``, which is
+not a DXF double, and a string coerced into a point coordinate is a silent
+wrong number; both are refused before any write, the same way
+``backends/block_specs.py`` refuses them for block primitives.
+"""
+
+from __future__ import annotations
+
+import math
+import re
+from collections.abc import Iterable, Mapping
+
+APP_NAME_RE = re.compile(r"^[A-Za-z_][A-Za-z0-9_]{0,30}$")
+RESERVED_APPS = {"ACAD"}
+MAX_STRING = 255
+MAX_BYTES = 16 * 1024
+INT_MIN, INT_MAX = -(2**31), 2**31 - 1
+LINE_SEPARATORS = ("\n", "\r")
+
+Tag = tuple[int, object]
+
+
+def validate_app_name(app) -> str:
+    if not isinstance(app, str) or not APP_NAME_RE.match(app):
+        raise ValueError(f"xdata: app name must match {APP_NAME_RE.pattern}, got {app!r}")
+    if app.upper() in RESERVED_APPS:
+        raise ValueError(f"xdata: app name {app!r} is reserved")
+    return app
+
+
+def _real(value, where: str) -> float:
+    """A finite float from an int or float; strings, bools and nan/inf are refused."""
+    if isinstance(value, bool) or not isinstance(value, (int, float)):
+        raise TypeError(f"xdata: {where} must be a number, got {value!r}")
+    try:
+        number = float(value)
+    except OverflowError:
+        number = math.inf
+    if not math.isfinite(number):
+        raise ValueError(f"xdata: {where} must be finite, got {value!r}")
+    return number
+
+
+def tag_size(code: int, value) -> int:
+    """Bytes one XDATA tag occupies in AutoCAD's accounting (what ``xdsize`` reports).
+
+    Every tag carries a one-byte group code; strings (1000-1004) add a two-byte
+    length, reals are 8 bytes, points 3 reals, a 32-bit int 4, a 16-bit int 2,
+    a handle 8. The 1001 application marker is a string and counts like one.
+    """
+    if code in (1000, 1001, 1002, 1003, 1004, 1005):
+        if isinstance(value, str):
+            return 3 + len(value.encode("utf-8"))
+        if isinstance(value, (bytes, bytearray, list, tuple)):  # 1004 binary chunk
+            return 3 + len(value)
+        return 3 + len(str(value).encode("utf-8"))
+    if code in (1010, 1011, 1012, 1013):
+        return 1 + 3 * 8
+    if code in (1040, 1041, 1042):
+        return 1 + 8
+    if code == 1070:
+        return 1 + 2
+    if code == 1071:
+        return 1 + 4
+    raise ValueError(f"xdata: {code} is not an XDATA group code")
+
+
+def app_size(app: str, tags: Iterable[Tag]) -> int:
+    """Bytes one application's XDATA occupies: its 1001 marker plus every tag.
+
+    ``tags`` may or may not carry the 1001 marker (ezdxf stores it, its
+    ``get_xdata`` strips it); it is counted exactly once either way.
+    """
+    return tag_size(1001, app) + sum(tag_size(code, value) for code, value in tags if code != 1001)
+
+
+def encode_values(values) -> list[Tag]:
+    """JSON values → (group code, value). Raises TypeError/ValueError; writes nothing."""
+    if not isinstance(values, (list, tuple)):
+        raise TypeError("xdata: values must be a list")
+    tags: list[Tag] = []
+    for i, value in enumerate(values):
+        where = f"values[{i}]"
+        if isinstance(value, bool):
+            raise TypeError(f"xdata: {where} booleans have no XDATA group code")
+        if isinstance(value, str):
+            if len(value) > MAX_STRING:
+                raise ValueError(
+                    f"xdata: {where} is {len(value)} characters; the limit is {MAX_STRING}"
+                )
+            if any(sep in value for sep in LINE_SEPARATORS):
+                raise ValueError(
+                    f"xdata: {where} contains a newline; "
+                    "line separators are not allowed in XDATA strings"
+                )
+            tags.append((1000, value))
+        elif isinstance(value, int):
+            if not INT_MIN <= value <= INT_MAX:
+                raise ValueError(f"xdata: {where} is outside the 32-bit integer range")
+            tags.append((1071, int(value)))
+        elif isinstance(value, float):
+            tags.append((1040, _real(value, where)))
+        elif isinstance(value, (list, tuple)) and len(value) in (2, 3):
+            coords = tuple(_real(c, f"{where}[{j}]") for j, c in enumerate(value))
+            if len(coords) == 2:
+                coords = (coords[0], coords[1], 0.0)
+            tags.append((1010, coords))
+        else:
+            raise TypeError(f"xdata: {where} must be a string, int, float or [x, y(, z)] point")
+    # A single call that cannot fit on an empty entity is refused here; the
+    # per-entity budget (existing apps included) is check_entity_budget().
+    size = sum(tag_size(code, value) for code, value in tags)
+    if size > MAX_BYTES:
+        raise ValueError(f"xdata: encoded size {size} bytes exceeds the 16 KB per-entity limit")
+    return tags
+
+
+def check_entity_budget(
+    app: str, tags: Iterable[Tag], existing: Mapping[str, Iterable[Tag]]
+) -> int:
+    """Bytes the entity's XDATA occupies once ``app`` is replaced by ``tags``.
+
+    ``existing`` is every application currently on the entity (ACAD included)
+    with its tags; ``app``'s own entry is what the write replaces, so it is
+    dropped from the sum. Raises ValueError over ``MAX_BYTES``; writes nothing.
+    An empty ``tags`` removes the app and is never refused, whatever the other
+    applications already hold (a file opened with too much XDATA must still be
+    shrinkable).
+    """
+    tags = list(tags)
+    others = 0
+    for other, other_tags in existing.items():
+        if other == app:
+            continue
+        others += app_size(other, other_tags)
+    if not tags:
+        return others
+    total = app_size(app, tags) + others
+    if total > MAX_BYTES:
+        raise ValueError(
+            f"xdata: entity would carry {total} bytes of XDATA ({others} under other "
+            f"applications); the limit is 16 KB per entity across every application"
+        )
+    return total
+
+
+def decode_values(tags) -> list:
+    """(group code, value) → JSON values. Skips the 1001 app marker and 1002 braces."""
+    out: list = []
+    for code, value in tags:
+        if code in (1001, 1002):
+            continue
+        if code == 1010 or code in (1011, 1012, 1013):
+            out.append([float(c) for c in value])
+        elif code in (1040, 1041, 1042):
+            out.append(float(value))
+        elif code in (1070, 1071):
+            out.append(int(value))
+        else:
+            out.append(str(value))
+    return out
+
+
+def split_tags_by_app(codes, values) -> dict[str, list[Tag]]:
+    """A flat ActiveX GetXData stream (1001 markers inline) → {app: raw tags}."""
+    out: dict[str, list[Tag]] = {}
+    current: str | None = None
+    for code, value in zip(codes, values, strict=True):
+        if code == 1001:
+            current = str(value)
+            out.setdefault(current, [])
+        elif current is not None:
+            out[current].append((code, value))
+    return out
+
+
+def split_by_app(codes, values) -> dict[str, list]:
+    """A flat ActiveX GetXData stream (1001 markers inline) → {app: values}."""
+    return {app: decode_values(tags) for app, tags in split_tags_by_app(codes, values).items()}

benchmarks/README.md

@@ -1,15 +1,17 @@
 # Benchmarks
 
+![Public AutoCAD MCP capability leaderboard](../docs/assets/autocad-mcp-benchmark.svg)
+
 ## Two evidence layers
 
 This repository publishes two deliberately separate forms of evidence:
 
-1. **Source-reviewed capability benchmark.** Six named AutoCAD MCP projects are
+1. **Source-reviewed capability benchmark.** Nine named AutoCAD MCP projects are
    scored with a fixed 100-point rubric covering CAD breadth, correctness and
    delivery, backend reach, engineering production, tests, and security. The
    dated data lives in [`source_review.json`](source_review.json), and the README
    graphic is generated—not hand-edited—from that file.
-2. **Fixed-task runtime benchmark.** Adapters execute the same ten tasks and
+2. **Fixed-task runtime benchmark.** Adapters execute the same task matrix and
    return `pass`, `partial`, `unsupported`, `fail`, `timeout`, or `not_run`.
    AutoCAD MCP Pro currently has the reference adapter; other projects do not
    receive runtime scores until an adapter actually runs their public interface.
@@ -24,28 +26,258 @@ python -m benchmarks.render_chart
 The source-review chart is not presented as a shared live AutoCAD run. Review
 dates, evidence grades, project URLs, and the boundary are stored with the data.
 
-## Fixed-task runtime runner v2
+## Fixed-task runtime runner
 
-The v2 runner separates runtime evidence from the source-review rubric. Every
-adapter receives the same ten tasks and produces the same closed result enum:
+The runner separates runtime evidence from the source-review rubric. Every
+adapter receives the same tasks and produces the same closed result enum:
 `pass`, `partial`, `unsupported`, `fail`, `timeout`, or `not_run`. A timeout is
-reported per task. Execution is in-process, so adapters that delegate blocking
-work must provide cancellation-safe task implementations or be wrapped by an
-external process supervisor. Reports include commit SHA, Python/platform
-details, backend capability claims, durations, coverage, and hashes for returned
-artifacts. Unsupported tasks remain in the fixed-matrix denominator with score
-zero, preventing partial implementations from receiving an inflated score.
+reported per task, and a capability refusal is recorded `unsupported` rather
+than `fail` — "cannot reach this" and "got this wrong" are different findings.
+Execution is in-process, so adapters that delegate blocking work must provide
+cancellation-safe task implementations or be wrapped by an external process
+supervisor. Reports include commit SHA, Python/platform details, backend
+capability claims, durations, coverage, and hashes for returned artifacts.
+Unsupported tasks remain in the fixed-matrix denominator with score zero,
+preventing partial implementations from receiving an inflated score.
 
 ```bash
-python -m benchmarks.run_competitors --list
-python -m benchmarks.run_competitors --server autocad-mcp-pro --backend ezdxf --json
-python -m benchmarks.run_competitors --task table_mleader --task auditable_delivery --json
+python -m benchmarks.run_competitors --list --matrix v7
+python -m benchmarks.run_competitors --server autocad-mcp-pro --backend ezdxf --matrix v7 --json
+python -m benchmarks.run_competitors --task table_mleader --task hatch_islands --json
 ```
 
-The release-machine v1.3 ezdxf self-check is **10/10 (100.0)**. It is not a
-competitor ranking. Cross-project scores become comparable only when another
-adapter runs this exact task matrix; repository stars and raw tool counts do not
-contribute to the score. Adapter registration lives in `competitors.yaml`.
+The release-machine ezdxf self-check is **21/21 (100.0)** on the v7 matrix
+(`--matrix v6` … `--matrix v2` reproduce the earlier sets); the published
+report is [`results/published/autocad-mcp-pro.json`](results/published/autocad-mcp-pro.json).
+Repository stars and raw tool counts do not contribute to the score. Adapter
+registration lives in `competitors.yaml`.
+
+### Matrix v3 (v1.5.0) — five tasks that can fail
+
+v2 scored this server 10/10, and that number carried no information: every task
+in it exercised something the server was designed around. `tasks_v3.py` keeps
+the v2 ten unchanged — their ids and weights key the published v1.4 reports —
+and adds five chosen because they *can* fail. Three of them did, while being
+written:
+
+| Task | Category | Verified against |
+|---|---|---|
+| `tool_discovery` | discovery | six AutoCAD command names, each found in the top 3 of the 154-tool registry the harness ranks — all six came back #1 in the published run |
+| `token_budget` | efficiency | 40,305 → 356 tokens advertised, against a 2,000 ceiling fixed in advance |
+| `hatch_islands` | hatch | 300 filled with the island, 400 ignoring it |
+| `selection_filter` | selection | window 1, crossing 2, bounding box 3, polygon 1 |
+| `measure_from_handle` | measurement | 139.2699 against the 100.0 a vertex shoelace gives |
+
+Token counts come from the offline ratio estimator and the report labels them
+`ratio/v1 (estimate)`; `token_suite.py --tokenizer anthropic` counts for real.
+
+**Two renames from the release plan, and they are the point.**
+`tool_discovery_bilingual` → `tool_discovery`: a Turkish query normalizer was
+written and then removed, because this repository is English throughout and the
+Turkish was inferred from the author's chat language rather than required by the
+product. `measurement_massprops` → `measure_from_handle`: no centroid or
+moment-of-inertia tool ships.
+
+**The competitor reports are not re-scored.** Those servers are pinned at v1.4
+commits and were run against the v2 matrix; they have never been asked these
+five questions. Their scores stand over the ten they ran, and the matrix chart
+leaves the five new rows blank (`not run`) instead of scoring them zero — a
+zero we invented would be indistinguishable from a zero we measured.
+
+`--matrix v2` stays available so a v1.4 report can be reproduced rather than
+only described, and `--publish` writes the artifact-path-free file that
+`results/published/` holds.
+
+### Matrix v4 (v1.6) — the P&ID round trip and the page-setup truth
+
+`tasks_v4.py` keeps the v3 fifteen unchanged and adds two tasks that can each
+fail on their own:
+
+| Task | Category | Verified against |
+|---|---|---|
+| `pid_roundtrip` | pid | the example spec drawn through `pid_from_spec`'s code, then read back by the graph builder, which never sees the spec: 5 nodes, 4 edges, 0 dangling ends, `confidence_min` 1.0, zero critique issues, an instrument index of exactly `FIC-101` wired to `FCV-101`, and the two authored line numbers back on the two process lines while the two unnumbered lines carry sequence-built numbers from XDATA |
+| `page_setup_truth` | pagesetup | `page_setup_apply("Layout1", ANSI_B landscape 1:1)` then `batch_plot` — the PDF's own `/MediaBox` must parse to 432 × 279 mm (±0.5), a size no fresh document has; then `page_setup_apply("Layout1", ISO_A3 landscape 1:1)` and `batch_plot` again — 420 × 297, the setter's `changed.size_mm` must read `[[432, 279], [420, 297]]`, the page-setup list must say `ISO_A3` / `landscape` / `[420, 297]`, and the ctb must be a known one. A setter that writes nothing fails at the first PDF (`tests/test_benchmark_v4.py` stubs it to prove that) |
+
+The competitor reports carry no result for either, for the same reason they
+carry none for the v3 five. `--matrix v3` reproduces the v1.5 set exactly.
+
+### Matrix v5 (v1.6) — the mechanical sheet
+
+`tasks_v5.py` keeps the v4 seventeen unchanged and adds roadmap criterion 3:
+
+| Task | Category | Verified against |
+|---|---|---|
+| `mech_assembly` | mech | a flange-coupling A3 sheet built through the code the tools call — `apply_titleblock` (ISO 5457 frame with zones and marks, ISO 7200 title block), a hub drawn by `draw_part` with a full section by `add_view` and chain dimensions by `dimension_part`, a flange with its bolt-circle end view, two ISO 4014 M12x60 bolts and two ISO 4032 M12 nuts by `insert_std_part`, the ISO 7573 parts list *read off the drawing* by `extract_records` and drawn by `draw_bom_table`, and one balloon per row linked to that row's inserts by `add_balloon`. The sheet is saved, then gated on two numbers that cannot be negotiated: `run_critique(focus=None)` returns **zero** issues and `combine(validator, critique)` scores at least **90**. The focuses that fired come back in the metrics, and `tests/test_benchmark_v5.py` drops one balloon to prove the gate fails and names `mech_bom_balloon_mismatch` |
+
+Nothing in the task tidies up after the tools: the view engine draws the ISO
+128-23 centre lines of every circle it emits, so the sheet is clean because it
+was drawn clean. Building it found four defects that every headless test had
+missed — the headless diameter text on the wrong side of the chord, the
+validator reading a fastener designation (`M12x60`) as a fake dimension, and on
+the live seat a missing `MECH` layer and a parts list that could not see a
+`BLOCKREFERENCE`; each is fixed with a test. The competitor reports carry no
+result for it.
+
+### Matrix v6 (v1.6) — the architectural plan
+
+`tasks_v6.py` keeps the v5 eighteen unchanged and adds track F's evidence:
+
+| Task | Category | Verified against |
+|---|---|---|
+| `arch_roundtrip` | arch | the plan of `engineering/arch/spec.py::EXAMPLE_SPEC` — a 9 × 6 m brick ring at 250 mm split by a 100 mm AAC wall, an entrance door, an interior door, two windows, a straight stair, two labelled rooms, the exterior chains and the door / window / room schedules — drawn in one transaction by `draw_plan_from_spec`, then read back without the spec: `rooms_detect` on the wall layer must find each labelled room within 0.1 % of the area its label carries **and** of the net floor computed by hand (4825 × 5750 = 27 743 750 and 3825 × 5750 = 21 993 750 mm²), `schedule_rows` must list exactly D1, D2 and W1, W2, and the saved plan is gated like `mech_assembly`: `run_critique(focus=None)` returns **zero** issues and `combine(validator, critique)` scores at least **90**. `tests/test_benchmark_v6.py` removes one room label to prove the gate fails and names `arch_room_unlabelled` |
+
+The competitor reports carry no result for it.
+
+### Matrix v7 (v1.6) — understanding foreign drawings
+
+`tasks_v7.py` keeps the v6 nineteen unchanged and adds track H's evidence, both on the synthetic plant pair of `tests/fixtures/plant_pair.py` (invented names; its truth is computed from the positions it placed, never typed):
+
+| Task | Category | Verified against |
+|---|---|---|
+| `takeoff_roundtrip` | plant | `scale_check(pid, layout)` must say **schematic** (room 1 is a 1.3× stretch, room 2 is rearranged: 21.8 % of the 55 tag pairs within ±10 % of the median ratio); `pipe_rows(..., length_source="auto")` must report all nine runs with the truth's status, each routable run's layout length equal to the rectilinear MST of its tags to a micron (PR1 5500, PR2 13200, CS1 20700 mm, …), its size and service as drawn — the CIP return drawn on the supply layer included — and both sizes across the reducer; `cable_rows` must give M11 / T102 / M12 / T202 their panels, 6900 / 14100 / 15800 / 8000 mm and 9 / 17 / 19 / 10 m after the 20 % allowance, the heater's power empty. `tests/test_benchmark_v7.py` deletes the wiring callouts and the gate names all four loads |
+| `understand_foreign` | understand | `describe(layout)` must infer millimetres and warn about `INSUNITS` (the file says inches), name the stray line's handle in its extents and report two clusters (the plan is drawn twice, 100 m apart); `describe(pid)` must classify `P_product piping`, `P_cipsupplyline`, `P_cipreturnline`, `P_ijswater` and `E_power` as product, CIP supply, CIP return, ice water and electrical. `tests/test_benchmark_v7.py` makes the layout declare millimetres and the units gate fails alone |
+
+The competitor reports carry no result for them.
+
+## Live competitor lane (v1.4)
+
+Two competitor adapters now execute the exact same task matrix, black-box over
+MCP stdio, against commits pinned in `competitors.yaml`:
+
+| Server | Matrix | Pinned | Score | Pass | Coverage |
+|---|---|---|---:|---:|---:|
+| autocad-mcp-pro (reference) | v7 (21) | 1.6.0 tree | 100.0 | 21/21 | 100% |
+| beiming183-cloud/AutoCAD-MCP | v2 (10) | `11f7c47e` | 50.0 | 5/10 | 50% |
+| puran-water/autocad-mcp | v2 (10) | `95476a33` | 45.0 | 4/10 | 50% |
+
+The competitor rows are the v1.4 runs, unchanged. Read the matrix column
+before the score column: the denominators differ because the eleven tasks
+added since v2 came after those runs and have not been put to them.
+
+Method and boundaries:
+
+- `benchmarks/competitors_env.py` clones the pinned SHA into
+  `benchmarks/.competitors/<id>/` (gitignored), builds an isolated venv, and
+  installs the competitor from its own `pyproject.toml`.
+- `benchmarks/adapters/mcp_stdio.py` drives the competitor exactly like an MCP
+  host (fastmcp `Client` over stdio). No competitor code is imported.
+- Task playbooks call each server's **own documented tool contract**, read from
+  the pinned source (consolidated `operation` + payload tools; beiming's
+  `doc_id`/`expected_revision` discipline is honored via
+  `transaction(operation="context")`).
+- **Verification never trusts the competitor's response**: every geometry claim
+  must survive `save`/`save_as_dxf` and re-opening the DXF with ezdxf inside
+  the harness.
+- Tasks with no documented equivalent are reported `unsupported` with the
+  reason string; they stay in the fixed-matrix denominator at score zero.
+- This lane is headless (ezdxf backends only). File-IPC / live-AutoCAD lanes
+  (including COM-only servers such as best-cad-mcp or daobataotie/CAD-MCP)
+  require a local AutoCAD session and are out of CI scope by design.
+
+Published machine-readable reports (artifact paths sanitized to filenames)
+live under [`results/published/`](results/published/); the README charts are
+regenerated from them:
+
+```bash
+python -m benchmarks.run_competitors --server puran-water-autocad-mcp --backend ezdxf --matrix v2
+python -m benchmarks.run_competitors --server beiming183-autocad-mcp --backend ezdxf --matrix v2
+python -m benchmarks.render_live_chart     # score bars
+python -m benchmarks.render_matrix_chart   # tasks x servers status heatmap
+```
+
+`--publish <path>` writes the same report with artifact paths reduced to
+filenames, which is how `results/published/` is produced; the sha256 stays,
+because that is what makes an artifact checkable.
+
+## Headless performance lane
+
+`perf_suite.py` measures wall time on fixed workloads through the same backend
+methods the MCP tools call (server-side overhead included): 2,000 individual
+line creates, a 10,000-entity build → DXF export → reopen roundtrip, a region
+query over 10,000 entities, and a full premium quality pass (ISO layers,
+geometry, dimensions, complete critique). The report records the machine
+fingerprint; numbers move with hardware, workload definitions do not.
+**Self-measurement only** — competitor servers would pay an extra stdio
+serialization cost that in-process runs do not, so no cross-server timing
+claims are made.
+
+```bash
+python -m benchmarks.perf_suite --out benchmarks/results/published/perf-ezdxf.json
+python -m benchmarks.render_perf_chart
+```
+
+### v1.4.0 against v1.6.0, and what the call-timeout guard costs
+
+The published v1.4 report was recorded on CPython 3.14 and the later ones on
+3.11.15, so comparing those files directly shows an apparent speedup that is
+almost entirely the interpreter. The comparison that means something runs one
+interpreter and one ezdxf over each tree's own code: 1.6.0's `perf_suite.py`
+(v1.4.0 had none) against a v1.4.0 worktree, against 1.6.0, and against 1.6.0
+with the guard off — five rounds, the three configurations alternating within
+a round. Medians, from
+[`results/published/perf-v1.4.0-vs-v1.6.0.json`](results/published/perf-v1.4.0-vs-v1.6.0.json),
+which keeps every run:
+
+| Workload | v1.4.0 | v1.6.0 | v1.6.0, `EZDXF_CALL_TIMEOUT=0` |
+|---|---:|---:|---:|
+| `create_lines_2k` | 244.5 ms | 306.1 ms (1.25×) | 284.9 ms (1.17×) |
+| `roundtrip_10k` | 1,847.9 ms | 2,553.5 ms (1.38×) | 2,216.4 ms (1.20×) |
+| `region_query_10k` | 665.2 ms | 712.2 ms (1.07×) | 783.9 ms (1.18×) |
+| `premium_pass` | 150.6 ms | 65.3 ms (0.43×) | 69.9 ms (0.46×) |
+
+The guard explains part of the creation cost, not all of it. v1.5.1 rebuilt
+the wrapper around one `asyncio.timeout_at` instead of two `asyncio.wait_for`s
+(`wait_for` wraps its awaitable in a Task, so the old shape created two extra
+Tasks and two timer handles per call), which recovered about a third of its
+overhead; the rest is the Task the abandon-on-timeout design needs. With the
+guard off, creation is still 1.17× and 1.20× v1.4.0's time. A cProfile of the
+event-loop thread over the 2,000 creates counts **491,071** function calls on
+1.6.0 against **319,038** on v1.4.0: per-call work added since 1.4 that 1.6
+has not removed. The region-query row, whose guard-off median is the slower
+one, is this machine's noise floor (about ±10 %).
+
+Roadmap criterion 7 — headless creation throughput back to v1.4.0's numbers —
+is therefore **not met** and moves to 1.7. Earlier versions of this page said
+that `EZDXF_CALL_TIMEOUT=0` returned creation to v1.4.0's numbers; measured
+this way, it does not. The guard stays: it is what stops one hung ezdxf call
+wedging a server whose document lock is a single `asyncio.Lock`.
+
+`perf-ezdxf.json`, the chart's input, is the median of the five
+default-configuration runs, with every run kept in `runs_ms`.
+
+Reproduce (the v1.4.0 tree needs 1.6.0's `benchmarks/perf_suite.py` copied in):
+
+```bash
+git worktree add ../v140 v1.4.0 && cp benchmarks/perf_suite.py ../v140/benchmarks/
+for i in 1 2 3 4 5; do
+  python -m benchmarks.perf_suite --json > main-$i.json
+  EZDXF_CALL_TIMEOUT=0 python -m benchmarks.perf_suite --json > off-$i.json
+  (cd ../v140 && python -m benchmarks.perf_suite --json) > v140-$i.json
+done
+```
+
+The profile, run from each tree's root:
+
+```python
+import asyncio, cProfile, pstats
+from backends.ezdxf_backend import EzdxfBackend
+
+
+async def work():
+    b = EzdxfBackend()
+    await b.connect()
+    await b.drawing_new()
+    for i in range(2000):
+        await b.entity_create_line(0, i, 100, i)
+    await b.disconnect()
+
+
+pr = cProfile.Profile()
+pr.enable()
+asyncio.run(work())
+pr.disable()
+print(pstats.Stats(pr).total_calls)
+```
 
 ## Correctness A/B suite
 
@@ -63,6 +295,103 @@ python benchmarks/compare_versions.py v1.0.0     # vs a tag/ref
 python benchmarks/compare_versions.py --json results.json
 ```
 
+### Result — v1.6.0 vs v1.5.1 (release gate)
+
+48 checks, ezdxf backend, one subprocess per check. Machine-readable report:
+[`results/published/ab-v1.5.1-vs-v1.6.0.json`](results/published/ab-v1.5.1-vs-v1.6.0.json).
+
+| Version | Checks passing | Pass rate | Fixed | Regressed |
+|---------|----------------|-----------|-------|-----------|
+| **v1.5.1** (baseline)     | 26 / 48 | 54.2 % | — | — |
+| **v1.6.0** (this release) | 48 / 48 | 100 % | 22 | **0** |
+
+The twenty-two are all `miss → pass` — v1.5.1 has none of the methods. Five are track H: `scale_check_detects_schematic` (the synthetic P&ID is schematic against its layout; a uniform 2× copy is to scale with factor 2), `pipe_takeoff_rmst_exact` (eight routable runs, each exactly the rectilinear MST of its tags), `cable_takeoff_roundup` (9 / 17 / 19 / 10 m, the unstated power left empty), `diff_detects_known_edits` (five known edits and nothing else) and `topology_known_defects` (one near miss, one crossing, a clean T). Four are track F: `arch_junction_l_t_x` (L, T and X junction outlines against hand-computed corners and wall areas), `arch_room_area_net` (a 4 × 5 m room between 200 mm walls is labelled 20.00 m², not its 21.84 m² axis area), `arch_opening_cuts_wall` (both faces interrupted across a door, two jambs) and `arch_rooms_detect_foreign` (plain lines on a WALLS layer read as 20 and 15 m² at confidence 0.6, nothing written). Seven
+are tracks B and G: `mech_part_roundtrip` (a part read back from its own
+`ACADMCP_MECH` XDATA equals the part drawn), `mech_section_hatch_area` (a
+sleeve 60 long, ⌀40 outside, ⌀20 bore: a full section cuts two 60 × 10 faces,
+1200 mm² exactly, measured out of the drawing by `entity_measure` — never from
+the code that drew it), `mech_iso286_on_dimension` (ISO 286-1: 40 H7 is
++0.025 / 0, and the fit survives `layout_dimensions`),
+`mech_thread_unrepresented_is_caught` (the ISO 6410 focus fires on a thread
+drawn as a plain circle and stops firing once the thin ¾ arc is there — the
+mechanical twin of `dim_overlap_critique_fires`), `std_part_iso4014_m12` (ISO
+4014:2011 table 1, M12: s = 18, k = 7.5, matched by value; the inserted block
+carries its designation back), `sheet_frame_iso5457_a3` (the frame runs 20,10
+to 410,287 inside the 420 × 297 trimmed sheet) and `bom_balloon_link` (two
+identical bolts collapse into one row of quantity 2 with a stable item number,
+and that row's balloon carries it). The other six are the three
+P&ID checks track A added (`pid_block_define_attdef_roundtrip`,
+`pid_tag_parse_fic`, `pid_graph_edge_count`) and the three settings checks of
+track E (`settings_dimstyle_iso25_values`: the ISO-25 preset reaches the
+DIMSTYLE table with ISO 129-1's numbers, read back through ezdxf and not
+through the lister; `settings_layer_state_roundtrip`: save → change → restore
+puts the layer table back and the state survives save/reopen as an XRECORD in
+the file; `settings_pdf_mediabox_a3`: the plotted PDF's own `/MediaBox` reads
+420 × 297 mm). Every one of the 26 checks it was released on still passes, so
+the five tracks added capability without moving a number it had already earned.
+
+### Result — v1.5.1 vs v1.5.0
+
+26 checks at the time, ezdxf backend, one subprocess per check. Machine-readable report:
+[`results/published/ab-v1.5.0-vs-v1.5.1.json`](results/published/ab-v1.5.0-vs-v1.5.1.json).
+
+| Version | Checks passing | Pass rate | Fixed | Regressed |
+|---------|----------------|-----------|-------|-----------|
+| v1.5.0 (baseline)     | 24 / 26 | 92.3 % | — | — |
+| v1.5.1 (that release) | 26 / 26 | 100 % | 2 | **0** |
+
+v1.5.0 fails `diameter_dim_measures_the_diameter` and
+`radius_dim_ignores_the_leader_length`: it has both methods and gets both
+wrong. That is the defect 1.5.1 exists to fix and the reason 1.5.0 is yanked.
+
+### Result — v1.5.1 vs v1.4.0
+
+Same 26-check suite, older baseline:
+[`results/published/ab-v1.4.0-vs-v1.5.1.json`](results/published/ab-v1.4.0-vs-v1.5.1.json).
+
+| Version | Checks passing | Pass rate | Fixed | Regressed |
+|---------|----------------|-----------|-------|-----------|
+| v1.4.0 (baseline)     | 21 / 26 | 80.8 % | — | — |
+| v1.5.1 (that release) | 26 / 26 | 100 % | 5 | **0** |
+
+> This row used to read `v1.5.0 | 24 / 26 | 92.3 % | 5`, which was impossible on
+> its face — 21 passing plus 5 fixed is 26, not 24 — and it contradicted the
+> report it linked. The cause is worth recording: the file named
+> `ab-v1.4.0-vs-v1.5.0.json` was regenerated from a tree that already carried
+> the dimension fixes, so it never measured the v1.5.0 *tag*. The v1.5.0 tag
+> really does score 24/26, which is what the v1.5.0-baseline table above
+> reports. This table now names the tree it actually measured.
+
+The pass rate is against the 26-check current suite; v1.4.0 passed 21/21 of the
+checks that existed when it shipped. The five splits into two kinds, and the
+difference is the whole reason this lane distinguishes `miss` from `fail`:
+
+* **Three are new capability.** v1.4.0 has no `entity_measure` and no boundary
+  tracing, so it misses `hatch_area_subtracts_its_island`,
+  `boundary_area_agrees_with_measure` and `two_vertex_circle_has_area` by not
+  having the method (`miss → pass`). They are in the suite because all three
+  broke during v1.5.0 development and nothing outside their own unit tests
+  would have caught it.
+* **Two are repaired defects.** v1.4.0 *and v1.5.0* both have
+  `dimension_diameter` and `dimension_radius` and both get them wrong
+  (`fail → pass`): `leader_length`, a text placement, was being measured as
+  geometry, so at default settings every diameter callout came out
+  2 × `leader_length` too large. Only 1.5.1 passes them.
+
+The 21 pre-existing checks are unchanged and all still pass: the discovery
+layer, `cad_batch`, the 19-module contract split, the layout/viewport family
+and Wave A landed with **zero correctness regressions**.
+
+### Result — v1.4.0 vs v1.3.0
+
+21 checks. Report:
+[`results/published/ab-v1.3.0-vs-v1.4.0.json`](results/published/ab-v1.3.0-vs-v1.4.0.json).
+
+| Version | Checks passing | Pass rate | Fixed | Regressed |
+|---------|----------------|-----------|-------|-----------|
+| **v1.3.0** (baseline) | 21 / 21 | 100 % | — | — |
+| **v1.4.0**            | 21 / 21 | 100 % | 0 | **0** |
+
 ### Result — v1.1.0 vs v1.0.0 (`origin/main`, commit 15fa2bc)
 
 21 checks, ezdxf backend, CPython 3.14, one subprocess per check.
@@ -109,8 +438,5 @@ not a cherry-picked list of failures; the baseline genuinely does basic CAD work
 - COM-backend behaviour is not covered here (no live AutoCAD); see the mocked-COM
   suites in `tests/`.
 
-## Performance (throughput) — coming
-
-Scale / throughput numbers (1k–100k entities, render timings, model-by-model
-tool-call success rate) are tracked in the main README and will be published here
-with a hardware footprint.
+Model-by-model tool-call success rates remain future work; scale/throughput
+numbers live in the headless performance lane above.

benchmarks/adapters/autocad_mcp_pro.py

@@ -1,15 +1,54 @@
-"""Reference v2 adapter for this repository."""
+"""Reference adapter for this repository, covering the v7 task matrix.
+
+Every task verifies against a value worked out independently of the code under
+test — a closed-form area, a count of entities placed on purpose, a token
+ceiling fixed before the measurement. A task that only checks the server agrees
+with itself is a task that cannot fail.
+"""
 
 from __future__ import annotations
 
+import math
 from pathlib import Path
 
 from benchmarks.adapters.base import BenchmarkAdapter, TaskResult
-from benchmarks.tasks_v2 import TaskSpec
+from benchmarks.tasks_v7 import TaskSpec
 from engineering.delivery import deliver_drawing
 from engineering.layers import ensure_engineering_layers, ensure_standard_linetypes
 from engineering.refiner import refine_drawing
 
+#: AutoCAD command names a drafter types, none of which appeared in any tool
+#: name or description before v1.5.0 — measured `df = 0` against the stock BM25
+#: index, so no amount of tuning could have surfaced them.
+#: Each command is answered by a *set*, because more than one tool can be a
+#: correct answer -- QSELECT is both "filter by properties" and "select
+#: similar", and picking a winner between them would test the tie-break rather
+#: than the discovery.
+DISCOVERY_QUERIES: tuple[tuple[str, frozenset[str]], ...] = (
+    ("FILLET", frozenset({"entity_fillet"})),
+    ("BPOLY", frozenset({"boundary_trace"})),
+    ("QSELECT", frozenset({"selection_filter", "entity_select_smart"})),
+    ("WBLOCK", frozenset({"block_create_from_entities"})),
+    ("OVERKILL", frozenset({"drawing_refine"})),
+    ("CHSPACE", frozenset({"entity_change_space"})),
+)
+
+#: How far down the ranking still counts as found. A drafter reads the top few.
+DISCOVERY_TOP_N = 3
+
+#: The advertised catalog must stay under this in discovery mode. Fixed here
+#: rather than derived from the measurement, so the measurement can miss it.
+TOKEN_CEILING = 2_000
+
+#: The net floor of the two rooms of ``engineering/arch/spec.py::EXAMPLE_SPEC``,
+#: computed by hand: the 250 mm ring on axis (0,0)-(9000,6000) has its inner
+#: faces at x = 125 / 8875 and y = 125 / 5875, the 100 mm wall on x = 5000 its
+#: faces at 4950 / 5050. Room 01: 4825 x 5750; room 02: 3825 x 5750.
+ROUNDTRIP_AREAS_MM2: dict[str, float] = {
+    "01": 4825.0 * 5750.0,
+    "02": 3825.0 * 5750.0,
+}
+
 
 class AutoCADMCPProAdapter(BenchmarkAdapter):
     name = "autocad-mcp-pro"
@@ -90,10 +129,11 @@ class AutoCADMCPProAdapter(BenchmarkAdapter):
         table = await self.backend.entity_create_table(
             0, 20, [["A", "1"]], headers=["ITEM", "QTY"], layer="TEXT"
         )
-        leader = await self.backend.leader_create_mleader(
-            [[0, 0], [10, 10]], "NOTE", layer="DIM"
-        )
-        representations = [table.properties.get("representation"), leader.properties.get("representation")]
+        leader = await self.backend.leader_create_mleader([[0, 0], [10, 10]], "NOTE", layer="DIM")
+        representations = [
+            table.properties.get("representation"),
+            leader.properties.get("representation"),
+        ]
         return all(representations), {"representations": representations}, []
 
     async def _task_transactions(self):
@@ -137,6 +177,751 @@ class AutoCADMCPProAdapter(BenchmarkAdapter):
             await reopened.disconnect()
         return count == 1, {"entity_count": count}, [str(path)]
 
+    # ── v3 (v1.5.0) ─────────────────────────────────────────────────────────
+
+    async def _task_tool_discovery(self):
+        """Can a drafter find the tool by typing the command they know?
+
+        Ranked through the real transform, not a stub: the corpus is what makes
+        these commands findable at all, and testing anything else would test
+        the fixture.
+        """
+        import server
+        from discovery.transform import CadSearchTransform
+
+        tools = list(await server.mcp._list_tools())
+        transform = CadSearchTransform()
+
+        ranks: dict[str, int | None] = {}
+        for command, accepted in DISCOVERY_QUERIES:
+            hits = [
+                tool.name for tool in transform.rank(tools, command, limit=DISCOVERY_TOP_N).hits
+            ]
+            found = next((index for index, name in enumerate(hits) if name in accepted), None)
+            ranks[command] = None if found is None else found + 1
+
+        passed = all(rank is not None for rank in ranks.values())
+        return passed, {"ranks": ranks, "top_n": DISCOVERY_TOP_N}, []
+
+    async def _task_token_budget(self):
+        """What the client pays before it has asked for anything.
+
+        The ceiling is a constant, so a regression that doubles the catalog
+        fails this rather than quietly reporting a bigger number.
+        """
+        import server
+        from benchmarks.token_suite import (
+            FORMAT_JSON_SCHEMA,
+            _client,
+            _wire_payload,
+            build_counter,
+        )
+
+        async def _advertised(mode: str) -> tuple[int, int]:
+            """Tokens on the wire for `tools/list`, and how many tools that is.
+
+            Measured through a real client rather than the registry: the
+            registry is what the transform hides, so counting it would make
+            discovery mode look free.
+            """
+            server._apply_discovery_mode(mode)
+            async with _client() as client:
+                tools = await client.list_tools()
+            return counter.count(_wire_payload(tools), FORMAT_JSON_SCHEMA), len(tools)
+
+        counter = build_counter("ratio")
+        try:
+            full, catalog_count = await _advertised("off")
+            discovery, advertised_count = await _advertised("search")
+        finally:
+            server._apply_discovery_mode("off")
+
+        passed = discovery < TOKEN_CEILING and discovery < full
+        return (
+            passed,
+            {
+                "catalog_tokens": full,
+                "discovery_tokens": discovery,
+                "ceiling": TOKEN_CEILING,
+                "reduction_x": round(full / discovery, 1) if discovery else None,
+                "catalog_tools": catalog_count,
+                "advertised_tools": advertised_count,
+                # Named, because "40,305 tokens" reads like a count and is not
+                # one. `benchmarks/token_suite.py --tokenizer anthropic` counts
+                # for real; this lane has to stay offline and deterministic.
+                "tokenizer": f"{counter.name} (estimate)" if counter.estimated else counter.name,
+            },
+            [],
+        )
+
+    async def _task_hatch_islands(self):
+        """A section view is mostly holes, so the island is the measurement.
+
+        20x20 outer square with a 10x10 island: the filled area is 300, and a
+        server that records the island without subtracting it reports 400 while
+        looking entirely correct on screen.
+        """
+        await ensure_engineering_layers(self.backend)
+        hatch = await self.backend.entity_create_hatch(
+            "ANSI31", [[0, 0], [20, 0], [20, 20], [0, 20]], layer="HATCH"
+        )
+        island = [
+            {"type": "line", "start": [5, 5], "end": [15, 5]},
+            {"type": "line", "start": [15, 5], "end": [15, 15]},
+            {"type": "line", "start": [15, 15], "end": [5, 15]},
+            {"type": "line", "start": [5, 15], "end": [5, 5]},
+        ]
+        added = await self.backend.hatch_add_boundary(hatch.handle, island)
+        measured = await self.backend.entity_measure(hatch.handle)
+        ignored = await self.backend.hatch_edit(hatch.handle, style="ignore")
+        over_island = await self.backend.entity_measure(hatch.handle)
+
+        passed = (
+            added["path_count"] == 2
+            and abs(measured["area"] - 300.0) < 1e-6
+            and measured["hatch_style"] == "outer"  # what entity_create_hatch writes
+            and ignored["changed"] == ["style"]
+            and abs(over_island["area"] - 400.0) < 1e-6
+        )
+        return (
+            passed,
+            {
+                "path_count": added["path_count"],
+                "filled_area": measured["area"],
+                "area_ignoring_islands": over_island["area"],
+                "expected_filled": 300.0,
+                "hatch_style": measured["hatch_style"],
+            },
+            [],
+        )
+
+    async def _task_selection_filter(self):
+        """Window is not crossing, and a polygon is not its bounding box.
+
+        Three circles placed so each distinction has exactly one right answer:
+        one wholly inside, one straddling the edge, one out in the corner that
+        the bounding box catches and the triangle does not.
+        """
+        await ensure_engineering_layers(self.backend)
+        await self.backend.entity_create_circle(5, 5, 1, layer="GEOMETRY")
+        await self.backend.entity_create_circle(10, 5, 3, layer="GEOMETRY")
+        await self.backend.entity_create_circle(18, 18, 0.5, layer="GEOMETRY")
+        await self.backend.entity_create_circle(40, 40, 1, layer="TEXT")
+
+        window = await self.backend.selection_window(0, 0, 10, 10, mode="window")
+        crossing = await self.backend.selection_window(0, 0, 10, 10, mode="crossing")
+        bbox = await self.backend.selection_window(0, 0, 20, 20, mode="window")
+        triangle = await self.backend.selection_polygon([[0, 0], [20, 0], [0, 20]], mode="window")
+        by_layer = await self.backend.selection_filter(entity_type="CIRCLE", layer="TEXT")
+
+        passed = (
+            window["count"] == 1
+            and crossing["count"] == 2
+            and bbox["count"] == 3
+            and triangle["count"] == 1
+            and by_layer["count"] == 1
+            and by_layer["filtered_by"] == ["entity_type", "layer"]
+        )
+        return (
+            passed,
+            {
+                "window": window["count"],
+                "crossing": crossing["count"],
+                "bounding_box": bbox["count"],
+                "polygon": triangle["count"],
+                "by_layer": by_layer["count"],
+            },
+            [],
+        )
+
+    async def _task_measure_from_handle(self):
+        """The 28.2% that reading coordinates back loses.
+
+        A 10x10 square whose top edge is a semicircle encloses 139.2699. Chain
+        the loose edges into a boundary, then measure that boundary by handle;
+        shoelacing the four corners the model would have remembered gives 100.
+        """
+        await ensure_engineering_layers(self.backend)
+        await self.backend.entity_create_line(0, 0, 10, 0, layer="GEOMETRY")
+        await self.backend.entity_create_line(10, 0, 10, 10, layer="GEOMETRY")
+        await self.backend.entity_create_line(0, 10, 0, 0, layer="GEOMETRY")
+        await self.backend.entity_create_arc(5, 10, 5, 0, 180, layer="GEOMETRY")
+
+        loop = await self.backend.boundary_trace(5.0, 5.0)
+        measured = await self.backend.entity_measure(loop["handle"])
+        naive = await self.backend.analysis_measure_area([[0, 0], [10, 0], [10, 10], [0, 10]])
+
+        true_area = 100.0 + math.pi * 25.0 / 2.0
+        lost = (true_area - naive) / true_area
+        passed = (
+            loop["ok"] is True
+            and abs(measured["area"] - true_area) < 1e-5
+            and abs(loop["area"] - measured["area"]) < 1e-9
+            and measured["method"] == "analytic_bulge"
+            and measured["exact"] is True
+            and 0.28 < lost < 0.29
+        )
+        return (
+            passed,
+            {
+                "measured_area": measured["area"],
+                "true_area": round(true_area, 6),
+                "vertex_shoelace_area": naive,
+                "fraction_lost_by_reading_points_back": round(lost, 4),
+                "boundary_agrees": abs(loop["area"] - measured["area"]) < 1e-9,
+            },
+            [],
+        )
+
+    async def _task_pid_roundtrip(self):
+        """Five symbols, four lines, read back with nothing dangling.
+
+        The spec is drawn through the same code ``pid_from_spec`` calls; the
+        graph, the instrument index and the line list are then read back from
+        the drawing by the reader, which never sees the spec. Every expected
+        number below is counted from the spec by hand.
+        """
+        from engineering.layers import apply_layer_set
+        from engineering.pid.deliverables import instrument_index, line_list
+        from engineering.pid.spec import EXAMPLE_SPEC, run_spec
+
+        await apply_layer_set(self.backend, "pid")
+        result = await run_spec(self.backend, EXAMPLE_SPEC)
+        graph = result["graph"]
+        index = instrument_index(graph)
+        lines = line_list(graph)
+        # The spec numbers its two process lines; the connector line is left
+        # to the default ``number_format``, which with no size/service/spec/
+        # insulation collapses to the bare sequence number, and it must come
+        # back through XDATA, not a label search. The electric signal line is
+        # unnumbered by rule (ISA-5.1 signal lines carry no pipe line number)
+        # and must not have consumed a sequence number: the connector is "3".
+        authored = "100-P-1001-CS1"
+        numbers = {(r["from_tag"], r["to_tag"]): r["line_number"] for r in lines}
+        authored_ok = (
+            numbers.get(("P-101", "FCV-101")) == authored
+            and numbers.get(("FCV-101", "V-201")) == authored
+        )
+        others = [r for r in lines if r["line_number"] != authored]
+        signal = [r for r in others if r["line_class"] == "electric"]
+        sequenced = [r for r in others if r["line_class"] != "electric"]
+        sequenced_ok = (
+            len(signal) == 1
+            and signal[0]["line_number"] is None
+            and len(sequenced) == 1
+            and sequenced[0]["line_number"] == "3"
+            and sequenced[0]["number_source"] == "xdata"
+        )
+        passed = (
+            len(graph["nodes"]) == 5
+            and len(graph["edges"]) == 4
+            and graph["stats"]["dangling"] == 0
+            and graph["stats"]["confidence_min"] == 1.0
+            and result["critique"] == []
+            and [r["tag"] for r in index] == ["FIC-101"]
+            and index[0]["connected_to"] == "FCV-101"
+            and len(lines) == 4
+            and authored_ok
+            and sequenced_ok
+        )
+        return (
+            passed,
+            {
+                "nodes": len(graph["nodes"]),
+                "edges": len(graph["edges"]),
+                "dangling": graph["stats"]["dangling"],
+                "confidence_min": graph["stats"]["confidence_min"],
+                "critique_issues": len(result["critique"]),
+                "instrument_index_rows": len(index),
+                "line_list_rows": len(lines),
+                "authored_line_numbers_kept": authored_ok,
+                "unnumbered_lines_sequenced": sequenced_ok,
+            },
+            [],
+        )
+
+    async def _task_page_setup_truth(self):
+        """ISO A3 landscape on Layout1, plotted, and the sheet read back from the PDF.
+
+        The number that matters is parsed from the file's ``/MediaBox`` — the
+        setter's ``applied`` block is what we asked for, the page-setup list is
+        what the LAYOUT now says, and the PDF is what a printer would get. All
+        three have to agree with ISO 216's 420 × 297.
+
+        A fresh document's Layout1 is already A3 landscape, so that read-back
+        alone would pass with the setter stubbed out. The task first moves the
+        sheet to ANSI B — 432 × 279, a size no fresh document has — and reads
+        that PDF, then applies A3 and requires the setter to report the layout
+        moved from B to A3. The stub fails at the first PDF.
+        """
+        from engineering.standards.papers import resolve_page_setup
+        from engineering.standards.plot import batch_plot
+
+        out_dir = self.artifact_dir / "page_setup_truth"
+        out_dir.mkdir(parents=True, exist_ok=True)
+        # Stage 1: a non-default sheet, proven by its PDF.
+        await self.backend.page_setup_apply(
+            "Layout1",
+            resolve_page_setup("ANSI_B", orientation="landscape", scale="1:1"),
+        )
+        before = await batch_plot(
+            self.backend, ["Layout1"], str(out_dir), "{drawing}-{layout}-ansi_b.pdf"
+        )
+        row_before = before["sheets"][0]
+        width_before, height_before = (float(v) for v in row_before["mediabox_mm"])
+        # Stage 2: the sheet under test.
+        setup = resolve_page_setup(
+            "ISO_A3",
+            orientation="landscape",
+            plot_style="monochrome.ctb",
+            scale="1:1",
+        )
+        applied = await self.backend.page_setup_apply("Layout1", setup)
+        listed = (await self.backend.page_setup_list("Layout1"))[0]
+        report = await batch_plot(
+            self.backend, ["Layout1"], str(out_dir), "{drawing}-{layout}-iso_a3.pdf"
+        )
+        row = report["sheets"][0]
+        width_mm, height_mm = (float(v) for v in row["mediabox_mm"])
+        size_listed = tuple(float(v) for v in listed["size_mm"])
+        size_changed = applied["changed"].get("size_mm")
+        # ±0.5 mm, the spec's own tolerance: the live engine measures ANSI B
+        # as 431.8 × 279.4 (11 × 17 in), the headless one as 432 × 279.
+        moved = size_changed or [[0.0, 0.0], [0.0, 0.0]]
+        moved_from_b = (
+            abs(float(moved[0][0]) - 432.0) < 0.5 and abs(float(moved[0][1]) - 279.0) < 0.5
+        )
+        moved_to_a3 = (
+            abs(float(moved[1][0]) - 420.0) < 0.5 and abs(float(moved[1][1]) - 297.0) < 0.5
+        )
+        passed = (
+            abs(width_before - 432.0) < 0.5
+            and abs(height_before - 279.0) < 0.5
+            and applied["ok"] is True
+            and applied["plot_style_known"] is True
+            and moved_from_b
+            and moved_to_a3
+            and listed["paper"] == "ISO_A3"
+            and listed["orientation"] == "landscape"
+            and size_listed == (420.0, 297.0)
+            and abs(width_mm - 420.0) < 0.5
+            and abs(height_mm - 297.0) < 0.5
+            and row["bytes"] > 0
+        )
+        return (
+            passed,
+            {
+                "paper": listed["paper"],
+                "orientation": listed["orientation"],
+                "size_mm_listed": list(size_listed),
+                "mediabox_mm": [width_mm, height_mm],
+                "mediabox_mm_before": [width_before, height_before],
+                "size_mm_changed": size_changed,
+                "pdf_bytes": row["bytes"],
+                "plot_style_known": applied["plot_style_known"],
+            },
+            [str(row_before["path"]), str(row["path"])],
+        )
+
+    async def _task_mech_assembly(self):
+        """A flange-coupling sheet built from the part model and the sheet standard.
+
+        Roadmap criterion 3. Two parts (a hub with a bore and a flange), a full
+        section through the hub, four standard fasteners with their parts-list
+        rows and balloons, an ISO 5457 A3 frame and an ISO 7200 title block.
+        Every step goes through the code the tools call: the frame and title
+        block through ``apply_titleblock``, the parts list is *read* off the
+        drawing by ``extract_records`` and drawn by ``draw_bom_table``, and each
+        balloon is linked to its row's inserts by ``add_balloon``.
+
+        The gate is two numbers, and both are asserted rather than reported:
+        ``run_critique(focus=None)`` must return zero issues, and the score the
+        finalize gate computes - ``combine(validator.summary, critique)`` over
+        the saved sheet - must be at least 90. A regression in either fails the
+        task; the focuses that fired come back in the metrics so the failure
+        names itself.
+
+        No step here repairs what the critique would flag: the view engine
+        draws the ISO 128-23 centre lines of every circle it emits (the end
+        view's bore and bolt holes included), so the sheet is clean because
+        the tools drew it clean, not because the benchmark tidied up after them.
+        """
+        from engineering import DrawingValidator
+        from engineering.critique import run_critique
+        from engineering.layers import apply_layer_set
+        from engineering.mech.draw import add_view, dimension_part, draw_part
+        from engineering.mech.part import build_part
+        from engineering.mech.stdparts import insert_std_part
+        from engineering.scoring import combine
+        from engineering.sheet.bom import (
+            add_balloon,
+            draw_bom_table,
+            extract_records,
+            rows_from_records,
+        )
+        from engineering.sheet.titleblock import (
+            TB_HEIGHT,
+            TitleBlockMetadata,
+            apply_titleblock,
+            titleblock_origin,
+        )
+
+        await apply_layer_set(self.backend, "mech")
+        await apply_titleblock(
+            self.backend,
+            size="A3",
+            metadata=TitleBlockMetadata(
+                title="FLANGE COUPLING",
+                drawing_no="MA-001",
+                drawn_by="autocad-mcp-pro",
+                scale="1:1",
+                material="S235JR",
+            ),
+            projection="first",
+            frame=True,
+            zones=True,
+            marks=True,
+        )
+
+        hub = build_part(
+            {
+                "kind": "revolved",
+                "name": "HUB",
+                "material": "steel",
+                "segments": [
+                    {"length": 40.0, "d_outer": 40.0, "d_inner": 20.0},
+                    {"length": 15.0, "d_outer": 90.0, "d_inner": 20.0},
+                ],
+            }
+        )
+        flange = build_part(
+            {
+                "kind": "revolved",
+                "name": "FLANGE",
+                "material": "cast_iron",
+                "segments": [{"length": 15.0, "d_outer": 90.0, "d_inner": 40.0}],
+                # Four M12 clearance holes (ISO 273 medium, 13.5) on a 65 PCD.
+                "features": [
+                    {
+                        "kind": "hole_circle",
+                        "id": "bolts",
+                        "x": 7.5,
+                        "pcd": 65.0,
+                        "count": 4,
+                        "diameter": 13.5,
+                        "start_angle": 45.0,
+                    }
+                ],
+            }
+        )
+        # A3 landscape: the frame runs (20, 10)-(410, 287) and the title block
+        # fills its lower-right corner, 180 x 60. First angle throughout: the
+        # hub's front view sits at x = 125 so its section lands left of it
+        # inside the frame; the flange's front view stands at x = 345 so its
+        # end view (the bolt circle) lands between the two parts; the
+        # fasteners take the free band below, left of the title block.
+        drawn_hub = await draw_part(
+            self.backend, hub, at=(125.0, 160.0), views=("front",), dimension=False
+        )
+        # A full longitudinal section along the hub's axis (part-local frame).
+        await add_view(
+            self.backend,
+            drawn_hub["part_id"],
+            "section",
+            plane={"p1": [0.0, 0.0], "p2": [55.0, 0.0], "label": "A"},
+            style="full",
+        )
+        await dimension_part(self.backend, drawn_hub["part_id"], style="chain")
+        await draw_part(
+            self.backend, flange, at=(345.0, 160.0), views=("front", "side"), dimension=True
+        )
+
+        # Two bolt-and-nut pairs: each nut sits on the thread of its bolt.
+        stations = (60.0, 110.0, 160.0, 210.0)
+        fasteners = []
+        for index, x in enumerate(stations):
+            designation = "ISO 4014 - M12x60" if index % 2 == 0 else "ISO 4032 - M12"
+            fasteners.append(
+                await insert_std_part(self.backend, designation, at=(x, 90.0), view="side")
+            )
+
+        # The parts list is a read of the drawing, not a list typed beside it.
+        records = await extract_records(self.backend)
+        rows = rows_from_records(records)
+        tb_x, tb_y = titleblock_origin("A3")
+        await draw_bom_table(self.backend, rows, at=(tb_x, tb_y + TB_HEIGHT))
+        station_of = {
+            str(result.get("handle")): x for result, x in zip(fasteners, stations, strict=True)
+        }
+        for row in rows:
+            targets = [str(handle) for handle in row.get("handles") or ()]
+            x = station_of.get(targets[0], stations[0]) if targets else stations[0]
+            await add_balloon(
+                self.backend,
+                item=int(row["item"]),
+                at=(x, 135.0),
+                leader_to=(x, 95.0),
+                targets=targets,
+            )
+
+        # drawing_finalize saves before it validates; so does the benchmark,
+        # or the validator's not_saved/no_path findings would grade the
+        # harness instead of the sheet.
+        sheet = self.artifact_dir / "mech_assembly.dxf"
+        await self.backend.drawing_save_as(str(sheet))
+        issues = await run_critique(self.backend, None)
+        validation = await DrawingValidator().run(self.backend)
+        summary = {"error": 0, "warning": 0, "info": 0}
+        for issue in issues:
+            summary[issue.severity] = summary.get(issue.severity, 0) + 1
+        score = combine(validation.summary, summary)
+        passed = len(issues) == 0 and float(score["score"]) >= 90.0
+        return (
+            passed,
+            {
+                "critique_issues": len(issues),
+                "critique_focuses": sorted({issue.focus for issue in issues}),
+                "score": float(score["score"]),
+                "grade": score["grade"],
+                "invalidity_ratio": score["invalidity_ratio"],
+                "parts_list_rows": len(rows),
+                "fasteners": len(fasteners),
+                "validator_findings": sorted(f.code for f in validation.findings),
+            },
+            [str(sheet)],
+        )
+
+    async def _task_arch_roundtrip(self):
+        """A two-room plan drawn from one spec and read back off the drawing.
+
+        Track F's evidence (spec §10). ``arch_plan_from_spec`` draws the plan of
+        ``engineering/arch/spec.py::EXAMPLE_SPEC`` - a 9 x 6 m brick ring at 250
+        mm split by a 100 mm AAC wall, an entrance door, an interior door, two
+        windows, a straight stair, two labelled rooms, the exterior chains and
+        the three schedules. Then the drawing is read, never the spec:
+
+        * ``rooms_detect`` on the wall layer must find each labelled room, and
+          its area must agree with the area the label's record carries within
+          0.1 %, and with the net floor computed by hand in
+          ``ROUNDTRIP_AREAS_MM2`` - so a label that typed the axis area fails;
+        * the door and window schedules read off the records must list exactly
+          the drawn tags;
+        * ``run_critique(focus=None)`` returns zero issues and the finalize
+          score - ``combine(validator.summary, critique)`` over the saved plan -
+          is at least 90.
+
+        Any one slipping fails the task, and the metrics name what slipped.
+        """
+        from engineering import DrawingValidator
+        from engineering.arch.critique import point_in_loop
+        from engineering.arch.draw import read_plan
+        from engineering.arch.layers import ARCH_ROLE_LAYER
+        from engineering.arch.rooms import rooms_detect
+        from engineering.arch.schedule import schedule_rows
+        from engineering.arch.spec import EXAMPLE_SPEC, draw_plan_from_spec
+        from engineering.critique import run_critique
+        from engineering.scoring import combine
+
+        drawn = await draw_plan_from_spec(self.backend, EXAMPLE_SPEC)
+        plan = await read_plan(self.backend)
+        detected = await rooms_detect(self.backend, layers=[ARCH_ROLE_LAYER["wall"]])
+        faces = list(detected.get("rooms") or [])
+
+        areas: dict[str, dict] = {}
+        for room in plan["rooms"]:
+            face = next((f for f in faces if point_in_loop(room.at, f["loop"])), None)
+            detected_area = float(face["area"]) if face is not None else 0.0
+            hand = ROUNDTRIP_AREAS_MM2.get(str(room.number))
+            areas[str(room.number)] = {
+                "label_mm2": float(room.area),
+                "detected_mm2": detected_area,
+                "hand_mm2": hand,
+                "agrees": face is not None
+                and hand is not None
+                and abs(detected_area - float(room.area)) <= 1e-3 * float(room.area)
+                and abs(detected_area - hand) <= 1e-3 * hand,
+            }
+        rooms_ok = (
+            set(areas) == set(ROUNDTRIP_AREAS_MM2)
+            and len(faces) == len(ROUNDTRIP_AREAS_MM2)
+            and all(row["agrees"] for row in areas.values())
+        )
+
+        door_tags = sorted(str(row["tag"]) for row in schedule_rows("doors", plan, lang="en"))
+        window_tags = sorted(str(row["tag"]) for row in schedule_rows("windows", plan, lang="en"))
+        tags_ok = door_tags == ["D1", "D2"] and window_tags == ["W1", "W2"]
+
+        sheet = self.artifact_dir / "arch_roundtrip.dxf"
+        await self.backend.drawing_save_as(str(sheet))
+        issues = await run_critique(self.backend, None)
+        validation = await DrawingValidator().run(self.backend)
+        summary = {"error": 0, "warning": 0, "info": 0}
+        for issue in issues:
+            summary[issue.severity] = summary.get(issue.severity, 0) + 1
+        score = combine(validation.summary, summary)
+        passed = rooms_ok and tags_ok and len(issues) == 0 and float(score["score"]) >= 90.0
+        return (
+            passed,
+            {
+                "rooms": areas,
+                "faces_detected": len(faces),
+                "confidence_min": detected.get("confidence_min"),
+                "door_tags": door_tags,
+                "window_tags": window_tags,
+                "omitted": drawn.get("omitted"),
+                "critique_issues": len(issues),
+                "critique_focuses": sorted({issue.focus for issue in issues}),
+                "score": float(score["score"]),
+                "grade": score["grade"],
+                "invalidity_ratio": score["invalidity_ratio"],
+                "validator_findings": sorted(f.code for f in validation.findings),
+            },
+            [str(sheet)],
+        )
+
+    async def _task_takeoff_roundtrip(self):
+        """Pipe and cable quantities off the synthetic plant pair, against its truth.
+
+        Track H's evidence (spec §15). The pair is written fresh into the
+        artifact folder by ``tests/fixtures/plant_pair.py``, whose truth is
+        computed from the positions it placed. Then only the two DXFs are read:
+
+        * ``scale_check(pid, layout)`` must say ``schematic`` - room 1 is the
+          layout stretched 1.3x, room 2 is rearranged, and 21.8 % of the 55 tag
+          pairs lie within ±10 % of the median ratio;
+        * ``pipe_rows(..., length_source="auto")`` must report every run of the
+          P&ID (the ice-water utility included, because ``services`` names it)
+          with the truth's status; a routable run's layout length must equal the
+          rectilinear MST of its tags exactly, its sizes (both across the
+          reducer) and its service must be the drawn ones (the CIP return drawn
+          on the supply layer included); the run ending on T105, which the
+          layout lacks, is status C with no layout length;
+        * ``cable_rows(pid, layout)`` must give every load its panel from the
+          layout's wiring callouts, its stated power (the heater's stays empty),
+          the Manhattan length to the panel and the metres rounded up after the
+          20 % allowance.
+
+        Any one slipping fails the task, and the metrics name what slipped.
+        """
+        from engineering.understand.network import build_network
+        from engineering.understand.scale import scale_check
+        from engineering.understand.snapshot import read_snapshot
+        from engineering.understand.takeoff import cable_rows, pipe_rows
+        from tests.fixtures.plant_pair import build_plant_pair
+
+        truth = build_plant_pair(self.artifact_dir / "plant_pair")
+        pid = read_snapshot(truth["pid"])
+        layout = read_snapshot(truth["layout"])
+        scale = scale_check(pid, layout)
+        services = tuple(sorted({run["service"] for run in truth["pipe_runs"]}))
+        pipe = pipe_rows(
+            build_network(pid), pid, layout, scale=scale, services=services, length_source="auto"
+        )
+        found = {(run["service"], tuple(sorted(run["tags"]))): run for run in pipe["runs"]}
+        pipe_mismatch = []
+        for run in truth["pipe_runs"]:
+            got = found.get((run["service"], tuple(run["tags"])))
+            if got is None:
+                pipe_mismatch.append({"run": run["id"], "reason": "no run with these tags"})
+                continue
+            reasons = []
+            if got["status"] != run["status"]:
+                reasons.append(f"status {got['status']} != {run['status']}")
+            want, have = run["layout_length_mm"], got.get("layout_m")
+            if want is None and have is not None:
+                reasons.append(f"a layout length ({have} m) for an unroutable run")
+            elif want is not None and (have is None or abs(float(have) * 1000.0 - want) > 1e-6):
+                reasons.append(f"layout length {have} m != {want} mm")
+            if set(got["diameters"]) != set(run["diameters"]):
+                reasons.append(f"sizes {sorted(got['diameters'])} != {sorted(run['diameters'])}")
+            if reasons:
+                pipe_mismatch.append({"run": run["id"], "reason": "; ".join(reasons)})
+
+        # panel_rule="stated": the gate reads what the drawing says; a nearest-panel
+        # guess is no evidence
+        cable = {row["tag"]: row for row in cable_rows(pid, layout, panel_rule="stated")["rows"]}
+        cable_mismatch = []
+        for want in truth["cable_rows"]:
+            got = cable.get(want["tag"])
+            if got is None:
+                cable_mismatch.append({"tag": want["tag"], "wrong": ["missing"]})
+                continue
+            wrong = [key for key in ("panel", "kw") if got.get(key) != want[key]]
+            if got.get("cable_m") != want["roundup_m"]:
+                wrong.append("cable_m")
+            length = got.get("length_m")
+            if length is None or abs(float(length) * 1000.0 - want["length_mm"]) > 1e-6:
+                wrong.append("length_m")
+            if wrong:
+                cable_mismatch.append({"tag": want["tag"], "wrong": wrong})
+
+        passed = scale["verdict"] == truth["scale_verdict"] and not pipe_mismatch
+        passed = passed and not cable_mismatch
+        return (
+            passed,
+            {
+                "scale_verdict": scale["verdict"],
+                "within_10pct": scale.get("within_10pct"),
+                "length_source": pipe.get("length_source"),
+                "runs_checked": len(truth["pipe_runs"]),
+                "pipe_mismatch": pipe_mismatch,
+                "loads_checked": len(truth["cable_rows"]),
+                "cable_mismatch": cable_mismatch,
+            },
+            [truth["pid"], truth["layout"]],
+        )
+
+    async def _task_understand_foreign(self):
+        """One call on a foreign layout reports what is wrong with it, by evidence.
+
+        Track H's evidence (spec §5, §15), on the synthetic plant pair: the
+        layout declares inches (``$INSUNITS = 1``) over millimetre geometry, a
+        stray LINE 5,000 km away stretches its declared extents, and the plan is
+        drawn twice, 100 m apart. ``describe`` of the layout must infer
+        millimetres, report that they disagree with the declared unit and warn
+        about ``INSUNITS``, name the stray entity's handle in its extents, and
+        report exactly two clusters; ``describe`` of the P&ID must classify its
+        four service layers and the electrical layer as the generator names them
+        (English and Dutch names). A warning or an extents report is searched as
+        JSON, so the gate holds whatever shape the evidence takes.
+        """
+        import json
+
+        from engineering.understand.describe import describe
+        from engineering.understand.snapshot import read_snapshot
+        from tests.fixtures.plant_pair import build_plant_pair
+
+        truth = build_plant_pair(self.artifact_dir / "plant_pair")
+        layout = describe(read_snapshot(truth["layout"]))
+        pid = describe(read_snapshot(truth["pid"]))
+        units = layout["units"]
+        units_flagged = (
+            str(units.get("inferred")) == truth["layout_true_unit"]
+            and units.get("agree") is False
+            and "INSUNITS" in json.dumps(layout["warnings"], ensure_ascii=False)
+        )
+        outlier_found = f'"{truth["outlier_handle"]}"' in json.dumps(layout["extents"])
+        copies_separated = len(layout["clusters"]) == truth["cluster_count"]
+        read = {row["name"]: row["service"] for row in pid["layers"]}
+        misread = {
+            name: read.get(name)
+            for name, service in truth["layer_services"].items()
+            if read.get(name) != service
+        }
+        passed = units_flagged and outlier_found and copies_separated and not misread
+        return (
+            passed,
+            {
+                "units": units,
+                "units_flagged": units_flagged,
+                "outlier_found": outlier_found,
+                "clusters": len(layout["clusters"]),
+                "copies_separated": copies_separated,
+                "misread_layers": misread,
+            },
+            [truth["layout"], truth["pid"]],
+        )
+
     async def _task_auditable_delivery(self):
         await ensure_engineering_layers(self.backend)
         await self.backend.entity_create_line(0, 0, 10, 0, layer="GEOMETRY")

benchmarks/adapters/beiming_autocad.py

@@ -0,0 +1,301 @@
+"""Black-box adapter for beiming183-cloud/AutoCAD-MCP (headless ezdxf lane).
+
+Contract verified against the pinned checkout's ``server.py`` (v3.10 line):
+
+- document identity comes from ``transaction(operation="context")`` and every
+  mutation must carry ``doc_id`` + ``expected_revision`` — top-level for the
+  ``entity``/``annotation`` tools, inside ``data`` for ``drawing`` operations;
+- ``entity create_line`` takes top-level ``x1..y2``; circle/dimension payloads
+  sit under ``data`` (same field spellings as the upstream puran-water base);
+- ``transaction begin/commit/rollback`` are compatibility operations that the
+  headless backend may reject with ``E_UNSUPPORTED*`` — that outcome is
+  reported as ``unsupported`` rather than ``fail``.
+
+Verification is artifact-based: geometry claims are checked by exporting a DXF
+(``drawing save_as_dxf``) and re-reading it with ezdxf in the harness.
+"""
+
+from __future__ import annotations
+
+import math
+from typing import Any
+
+from benchmarks.adapters.base import TaskResult
+from benchmarks.adapters.mcp_stdio import (
+    McpStdioAdapter,
+    ToolCallFailed,
+    extract_handle,
+)
+from benchmarks.competitors_env import CompetitorSpec
+
+PINNED_SHA = "11f7c47e5038796a20451b38b23032e625b5aa26"
+
+
+def _find_key(payload: Any, *keys: str) -> Any:
+    if isinstance(payload, dict):
+        for key in keys:
+            if key in payload and payload[key] not in (None, ""):
+                return payload[key]
+        for value in payload.values():
+            found = _find_key(value, *keys)
+            if found is not None:
+                return found
+    elif isinstance(payload, (list, tuple)):
+        for item in payload:
+            found = _find_key(item, *keys)
+            if found is not None:
+                return found
+    return None
+
+
+class BeimingAutocadAdapter(McpStdioAdapter):
+    name = "beiming183-autocad-mcp"
+    spec = CompetitorSpec(
+        competitor_id="beiming183-autocad-mcp",
+        repo_url="https://github.com/beiming183-cloud/AutoCAD-MCP.git",
+        pinned_sha=PINNED_SHA,
+        entry_candidates=(
+            ("-m", "autocad_mcp"),
+            ("server.py",),
+            ("src/server.py",),
+        ),
+        pip_installs=(("-e", "."),),
+        launch_env={"AUTOCAD_MCP_BACKEND": "ezdxf"},
+        pythonpath="src",
+    )
+
+    def extra_launch_env(self) -> dict[str, str]:
+        # The server redirects writes outside its managed output root; point
+        # the root at the benchmark artifact directory so exports land where
+        # the harness verifies them.
+        return {
+            "AUTOCAD_MCP_OUTPUT_ROOT": str(self.artifact_dir),
+            "AUTOCAD_MCP_ALLOW_EXTERNAL_OUTPUTS": "true",
+        }
+
+    def warmup_calls(self):
+        # Absorb lazy backend initialization once during setup.
+        return (
+            ("system", {"operation": "status"}),
+            ("drawing", {"operation": "create", "data": {}}),
+        )
+
+    async def _ctx(self) -> dict[str, Any]:
+        """Read doc_id + revision from ``transaction(operation="context")``."""
+        try:
+            payload = await self.call("transaction", {"operation": "context"})
+        except ToolCallFailed:
+            return {}
+        doc_id = _find_key(payload, "doc_id", "document_id")
+        revision = _find_key(payload, "revision", "expected_revision", "document_revision")
+        context: dict[str, Any] = {}
+        if doc_id is not None:
+            context["doc_id"] = doc_id
+        if revision is not None:
+            context["expected_revision"] = revision
+        return context
+
+    async def _new_drawing(self) -> None:
+        await self.call("drawing", {"operation": "create", "data": {}})
+
+    async def _save_dxf(self, filename: str) -> str:
+        target = self.save_target(filename)
+        payload: dict[str, Any] = {"path": str(target)}
+        try:
+            await self.call("drawing", {"operation": "save_as_dxf", "data": payload})
+        except ToolCallFailed:
+            context = await self._ctx()
+            await self.call("drawing", {"operation": "save_as_dxf", "data": {**payload, **context}})
+        return str(target)
+
+    async def _entity(self, operation: str, **fields: Any) -> Any:
+        context = await self._ctx()
+        return await self.call("entity", {"operation": operation, **context, **fields})
+
+    async def _create_line(self, x1: float, y1: float, x2: float, y2: float):
+        return await self._entity("create_line", x1=x1, y1=y1, x2=x2, y2=y2)
+
+    # -- tasks ----------------------------------------------------------------
+
+    async def _task_core_geometry(self) -> TaskResult:
+        await self._new_drawing()
+        await self._create_line(0, 0, 3, 4)
+        await self._entity("create_circle", data={"cx": 10, "cy": 10, "radius": 2})
+        artifact = await self._save_dxf("beiming_core_geometry.dxf")
+        _, doc = self.verify_dxf(self.save_target("beiming_core_geometry.dxf"))
+        lines = doc.modelspace().query("LINE")
+        circles = doc.modelspace().query("CIRCLE")
+        length = None
+        if lines:
+            start, end = lines[0].dxf.start, lines[0].dxf.end
+            length = math.dist((start.x, start.y), (end.x, end.y))
+        passed = (
+            len(lines) == 1
+            and len(circles) == 1
+            and length is not None
+            and abs(length - 5.0) < 1e-6
+            and abs(circles[0].dxf.radius - 2.0) < 1e-6
+        )
+        return TaskResult(
+            "core_geometry",
+            "pass" if passed else "fail",
+            100.0 if passed else 0.0,
+            metrics={"line_length": length, "lines": len(lines), "circles": len(circles)},
+            artifacts=[artifact],
+        )
+
+    async def _task_modify_query(self) -> TaskResult:
+        await self._new_drawing()
+        created = await self._create_line(0, 0, 10, 0)
+        handle = extract_handle(created)
+        if not handle:
+            return TaskResult(
+                "modify_query",
+                "fail",
+                0.0,
+                "could not extract created-entity handle from the create_line response",
+            )
+        await self._entity("move", entity_id=handle, data={"dx": 5, "dy": 2})
+        artifact = await self._save_dxf("beiming_modify_query.dxf")
+        _, doc = self.verify_dxf(self.save_target("beiming_modify_query.dxf"))
+        lines = doc.modelspace().query("LINE")
+        moved = (
+            bool(lines)
+            and abs(lines[0].dxf.start.x - 5.0) < 1e-6
+            and (abs(lines[0].dxf.start.y - 2.0) < 1e-6)
+        )
+        return TaskResult(
+            "modify_query",
+            "pass" if moved else "fail",
+            100.0 if moved else 0.0,
+            artifacts=[artifact],
+        )
+
+    async def _task_layers_linetypes(self) -> TaskResult:
+        await self._new_drawing()
+        context = await self._ctx()
+        await self.call("drawing", {"operation": "setup_mechanical", "data": {**context}})
+        artifact = await self._save_dxf("beiming_layers.dxf")
+        _, doc = self.verify_dxf(self.save_target("beiming_layers.dxf"))
+        layers = {layer.dxf.name.upper() for layer in doc.layers}
+        linetypes = {lt.dxf.name.upper() for lt in doc.linetypes}
+        expected_layers = {"OUTLINE", "CENTER", "DIM"}
+        got_layers = expected_layers.issubset(layers)
+        got_linetype = "CENTER" in linetypes
+        if got_layers and got_linetype:
+            return TaskResult("layers_linetypes", "pass", 100.0, artifacts=[artifact])
+        if got_layers:
+            return TaskResult(
+                "layers_linetypes",
+                "partial",
+                50.0,
+                "GB/T layers created but CENTER linetype missing from the table",
+                artifacts=[artifact],
+            )
+        return TaskResult(
+            "layers_linetypes",
+            "fail",
+            0.0,
+            f"layers={sorted(layers)}",
+            artifacts=[artifact],
+        )
+
+    async def _task_dimensions(self) -> TaskResult:
+        await self._new_drawing()
+        context = await self._ctx()
+        await self.call(
+            "annotation",
+            {
+                "operation": "create_dimension_linear",
+                **context,
+                "data": {"x1": 0, "y1": 0, "x2": 50, "y2": 0, "dim_x": 25, "dim_y": 10},
+            },
+        )
+        artifact = await self._save_dxf("beiming_dimensions.dxf")
+        _, doc = self.verify_dxf(self.save_target("beiming_dimensions.dxf"))
+        dims = [e for e in doc.modelspace() if e.dxftype() == "DIMENSION"]
+        return TaskResult(
+            "dimensions",
+            "pass" if dims else "fail",
+            100.0 if dims else 0.0,
+            metrics={"dimension_count": len(dims)},
+            artifacts=[artifact],
+        )
+
+    async def _task_transactions(self) -> TaskResult:
+        await self._new_drawing()
+        context = await self._ctx()
+        try:
+            begin = await self.call("transaction", {"operation": "begin", **context})
+        except ToolCallFailed as exc:
+            if "E_UNSUPPORTED" in str(exc):
+                return TaskResult(
+                    "transactions",
+                    "unsupported",
+                    0.0,
+                    "transaction begin is rejected as unsupported on the headless backend",
+                )
+            raise
+        transaction_id = _find_key(begin, "transaction_id", "txn_id")
+        await self._entity("create_circle", data={"cx": 0, "cy": 0, "radius": 1})
+        context = await self._ctx()
+        rollback_args: dict[str, Any] = {"operation": "rollback", **context}
+        if transaction_id is not None:
+            rollback_args["transaction_id"] = transaction_id
+        await self.call("transaction", rollback_args)
+        artifact = await self._save_dxf("beiming_transactions.dxf")
+        _, doc = self.verify_dxf(self.save_target("beiming_transactions.dxf"))
+        count = len(list(doc.modelspace()))
+        return TaskResult(
+            "transactions",
+            "pass" if count == 0 else "fail",
+            100.0 if count == 0 else 0.0,
+            metrics={"entity_count_after_rollback": count},
+            artifacts=[artifact],
+        )
+
+    async def _task_dxf_roundtrip(self) -> TaskResult:
+        await self._new_drawing()
+        await self._create_line(0, 0, 10, 10)
+        artifact = await self._save_dxf("beiming_roundtrip.dxf")
+        _, doc = self.verify_dxf(self.save_target("beiming_roundtrip.dxf"))
+        count = len(list(doc.modelspace()))
+        return TaskResult(
+            "dxf_roundtrip",
+            "pass" if count == 1 else "fail",
+            100.0 if count == 1 else 0.0,
+            metrics={"entity_count": count},
+            artifacts=[artifact],
+        )
+
+    # -- documented coverage gaps ----------------------------------------------
+
+    async def _task_table_mleader(self) -> TaskResult:
+        return TaskResult(
+            "table_mleader",
+            "unsupported",
+            0.0,
+            "no TABLE or MLEADER operation in the annotation tool (v3.10)",
+        )
+
+    async def _task_preflight(self) -> TaskResult:
+        return TaskResult("preflight", "unsupported", 0.0, "no requirements-preflight equivalent")
+
+    async def _task_quality_refiner(self) -> TaskResult:
+        return TaskResult(
+            "quality_refiner",
+            "unsupported",
+            0.0,
+            "audits detect issues but there is no automated repair loop",
+        )
+
+    async def _task_auditable_delivery(self) -> TaskResult:
+        return TaskResult(
+            "auditable_delivery",
+            "unsupported",
+            0.0,
+            "drawing.deliver is documented as File-IPC only (not headless)",
+        )
+
+
+__all__ = ["BeimingAutocadAdapter"]

benchmarks/adapters/mcp_stdio.py

@@ -0,0 +1,304 @@
+"""Generic MCP-stdio benchmark adapter.
+
+Drives a *competitor* MCP server as a black box over the standard stdio
+transport (fastmcp ``Client``), exactly the way an agent host would. No
+competitor code is imported; verification never trusts the competitor's
+response payload — every task that claims to have produced geometry must
+save a DXF which the harness re-opens with ezdxf and inspects itself.
+
+Subclasses provide the launch runtime (via ``benchmarks.competitors_env``)
+and per-task playbooks named ``_task_<task_id>``; anything unmapped is
+reported as ``unsupported`` (coverage-aware scoring already accounts for it).
+"""
+
+from __future__ import annotations
+
+import dataclasses
+import json
+import re
+from pathlib import Path
+from typing import Any
+
+import ezdxf
+from fastmcp import Client
+from fastmcp.client.transports import StdioTransport
+
+from benchmarks.adapters.base import BenchmarkAdapter, TaskResult
+from benchmarks.competitors_env import CompetitorRuntime, CompetitorSpec, ensure_competitor
+from benchmarks.tasks_v2 import TaskSpec
+
+CALL_TIMEOUT_SECONDS = 15.0
+WARMUP_TIMEOUT_SECONDS = 90.0
+
+
+class ToolCallFailed(RuntimeError):
+    """A competitor tool call returned an error result."""
+
+
+def read_dxf(path: Path):
+    return ezdxf.readfile(str(path))
+
+
+def modelspace_types(doc) -> list[str]:
+    return [entity.dxftype() for entity in doc.modelspace()]
+
+
+def find_dxf(artifact_dir: Path, preferred: Path | None = None) -> Path | None:
+    """Locate the DXF a competitor produced.
+
+    Servers with managed output roots may relocate writes, so fall back to
+    the newest ``*.dxf`` anywhere under the artifact directory.
+    """
+    if preferred is not None and preferred.is_file():
+        return preferred
+    candidates = sorted(
+        artifact_dir.rglob("*.dxf"), key=lambda item: item.stat().st_mtime, reverse=True
+    )
+    return candidates[0] if candidates else None
+
+
+class McpStdioAdapter(BenchmarkAdapter):
+    """Black-box adapter base for competitor MCP servers."""
+
+    name = "mcp-stdio"
+    spec: CompetitorSpec  # set by subclasses
+
+    def __init__(self, *, backend: str = "ezdxf"):
+        if backend != "ezdxf":
+            raise ValueError(
+                f"{type(self).__name__} only benchmarks the headless ezdxf lane; "
+                f"got backend={backend!r}. COM lanes run locally, not in CI."
+            )
+        self.backend_name = backend
+        self.artifact_dir = Path()
+        self.runtime: CompetitorRuntime | None = None
+        self._client: Client | None = None
+        self.tool_names: set[str] = set()
+
+    # -- lifecycle ----------------------------------------------------------
+
+    def extra_launch_env(self) -> dict[str, str]:
+        """Environment computed at setup time (``self.artifact_dir`` is set)."""
+        return {}
+
+    async def setup(self, artifact_dir: Path) -> None:
+        self.artifact_dir = Path(artifact_dir)
+        self.runtime = ensure_competitor(self.spec)
+        env = {**self.runtime.env, **self.extra_launch_env()}
+        env.setdefault("PYTHONIOENCODING", "utf-8")
+        transport = StdioTransport(
+            command=str(self.runtime.python_exe),
+            args=list(self.runtime.entry_args),
+            env=env,
+            cwd=str(self.runtime.repo_dir),
+        )
+        self._client = Client(transport)
+        await self._client.__aenter__()
+        self.tool_names = {tool.name for tool in await self._client.list_tools()}
+        await self._warmup()
+
+    def warmup_calls(self) -> tuple[tuple[str, dict[str, Any]], ...]:
+        """Calls issued once after connect to absorb the competitor's lazy
+        backend initialization (which can exceed the per-call timeout)."""
+        return ()
+
+    async def _warmup(self) -> None:
+        for tool, arguments in self.warmup_calls():
+            if tool not in self.tool_names:
+                continue
+            try:
+                await self._client.call_tool(
+                    tool, arguments, timeout=WARMUP_TIMEOUT_SECONDS, raise_on_error=False
+                )
+            except Exception:  # cold-start absorption is best effort
+                continue
+
+    async def cleanup(self) -> None:
+        if self._client is not None:
+            await self._client.__aexit__(None, None, None)
+            self._client = None
+
+    def metadata(self) -> dict:
+        return {
+            "backend": self.backend_name,
+            "kind": "mcp-stdio-blackbox",
+            "repo": self.spec.repo_url,
+            "pinned_sha": self.spec.pinned_sha,
+            "tools_discovered": sorted(self.tool_names),
+        }
+
+    # -- call helpers ---------------------------------------------------------
+
+    async def call(self, tool: str, arguments: dict[str, Any]) -> Any:
+        """Call one tool; raise ``ToolCallFailed`` on an error result.
+
+        Competitor servers in this family report failures *inside* the payload
+        (``CommandResult(ok=False, error=...)`` serialized as text) rather than
+        via the MCP ``isError`` flag, so the payload is inspected as well.
+        """
+        if tool not in self.tool_names:
+            raise ToolCallFailed(f"tool {tool!r} is not exposed by {self.name}")
+        result = await self._client.call_tool(
+            tool, arguments, timeout=CALL_TIMEOUT_SECONDS, raise_on_error=False
+        )
+        if getattr(result, "is_error", False):
+            raise ToolCallFailed(f"{tool}({arguments}) -> {_result_text(result)}")
+        data = getattr(result, "data", None)
+        payload = data if data is not None else _result_text(result)
+        payload = _normalize_payload(payload)
+        error = _payload_error(payload)
+        if error:
+            raise ToolCallFailed(f"{tool}({arguments}) -> {error}")
+        return payload
+
+    async def call_op(
+        self,
+        tool: str,
+        operation: str,
+        data: dict[str, Any] | None = None,
+        *,
+        shapes: tuple[dict[str, Any], ...] | None = None,
+    ) -> Any:
+        """Call a consolidated ``{tool}(operation=..., ...)`` style tool.
+
+        Competitors disagree on whether payload fields live under ``data`` or
+        at the top level, and on field spellings. ``shapes`` supplies explicit
+        argument dicts to try in order; otherwise both common layouts of
+        ``data`` are attempted. The first non-error result wins.
+        """
+        attempts: list[dict[str, Any]] = []
+        if shapes:
+            attempts.extend({"operation": operation, **shape} for shape in shapes)
+        else:
+            payload = data or {}
+            attempts.append({"operation": operation, "data": payload})
+            if payload:
+                attempts.append({"operation": operation, **payload})
+        last_error: Exception | None = None
+        for arguments in attempts:
+            try:
+                return await self.call(tool, arguments)
+            except ToolCallFailed as exc:  # try the next argument shape
+                last_error = exc
+        raise ToolCallFailed(str(last_error))
+
+    # -- task dispatch --------------------------------------------------------
+
+    async def run_task(self, task: TaskSpec) -> TaskResult:
+        handler = getattr(self, f"_task_{task.task_id}", None)
+        if handler is None:
+            return TaskResult(
+                task.task_id,
+                "unsupported",
+                0.0,
+                f"{self.name} has no documented equivalent for this task",
+            )
+        try:
+            return await handler()
+        except ToolCallFailed as exc:
+            return TaskResult(task.task_id, "fail", 0.0, str(exc)[:500])
+
+    # -- verification ---------------------------------------------------------
+
+    def save_target(self, filename: str) -> Path:
+        return self.artifact_dir / filename
+
+    def verify_dxf(self, preferred: Path | None = None):
+        located = find_dxf(self.artifact_dir, preferred)
+        if located is None:
+            raise ToolCallFailed("no DXF artifact was produced")
+        return located, read_dxf(located)
+
+
+def _result_text(result: Any) -> str:
+    parts: list[str] = []
+    for item in getattr(result, "content", None) or []:
+        text = getattr(item, "text", None)
+        if text:
+            parts.append(str(text))
+    return " | ".join(parts)[:1000] if parts else "<no text content>"
+
+
+def _normalize_payload(payload: Any) -> Any:
+    """Unwrap fastmcp's dynamic output wrappers and JSON-in-text payloads.
+
+    Legacy servers return plain text; the fastmcp client may deserialize it
+    into a generated *dataclass* (e.g. ``entityOutput(result='<json>')``) or a
+    pydantic model. Normalize down to dict / list / str so verification and
+    handle extraction see real data.
+    """
+    if dataclasses.is_dataclass(payload) and not isinstance(payload, type):
+        payload = dataclasses.asdict(payload)
+    elif hasattr(payload, "model_dump"):
+        payload = payload.model_dump()
+    elif not isinstance(payload, (dict, list, str)) and hasattr(payload, "result"):
+        payload = payload.result
+    if isinstance(payload, dict) and set(payload) == {"result"}:
+        payload = payload["result"]
+    if isinstance(payload, str):
+        try:
+            parsed = json.loads(payload)
+        except ValueError:
+            parsed = None
+        if isinstance(parsed, (dict, list)):
+            payload = parsed
+    return payload
+
+
+_TEXT_ERROR_MARKERS = ('"ok": false', "'ok': false", '"ok":false', "ok=false")
+
+
+def _payload_error(payload: Any) -> str | None:
+    """Detect failure reported inside a tool payload instead of MCP isError."""
+    if isinstance(payload, dict):
+        if payload.get("ok") is False or payload.get("success") is False:
+            return str(payload.get("error") or payload.get("message") or "ok=false")[:300]
+        error = payload.get("error")
+        if isinstance(error, str) and error.strip():
+            return error[:300]
+        return None
+    if isinstance(payload, str):
+        lowered = payload.lower()
+        if lowered.startswith("error") or any(m in lowered for m in _TEXT_ERROR_MARKERS):
+            return payload[:300]
+    return None
+
+
+def wrapped_shapes(payload: dict[str, Any], **top_level: Any) -> tuple[dict[str, Any], ...]:
+    """Produce the two common consolidated-tool argument layouts for a payload:
+    nested under ``data`` and flattened at the top level."""
+    return (
+        {**top_level, "data": payload},
+        {**top_level, **payload},
+    )
+
+
+_HANDLE_KEYS = ("handle", "entity_id", "entity_handle", "id", "object_id")
+_HANDLE_RE = re.compile(
+    r'"(?:handle|entity_id|entity_handle|object_id)"\s*:\s*"?([0-9A-Fa-f*][\w*-]*)"?'
+)
+
+
+def extract_handle(payload: Any) -> str | None:
+    """Best-effort extraction of a created-entity handle from a black-box
+    tool response (structured dict, list, or raw text)."""
+    if isinstance(payload, dict):
+        for key in _HANDLE_KEYS:
+            value = payload.get(key)
+            if isinstance(value, (str, int)) and str(value):
+                return str(value)
+        for value in payload.values():
+            found = extract_handle(value)
+            if found:
+                return found
+        return None
+    if isinstance(payload, (list, tuple)):
+        for item in payload:
+            found = extract_handle(item)
+            if found:
+                return found
+        return None
+    if isinstance(payload, str):
+        match = _HANDLE_RE.search(payload)
+        return match.group(1) if match else None
+    return None

benchmarks/adapters/puran_water.py

@@ -0,0 +1,224 @@
+"""Black-box adapter for puran-water/autocad-mcp (headless ezdxf lane).
+
+The competitor exposes 8 consolidated tools (``drawing``, ``entity``,
+``layer``, ``block``, ``annotation``, ``pid``, ``view``, ``system``) whose
+operations take an ``operation`` selector plus a payload. Argument spellings
+are probed through ``wrapped_shapes`` fallbacks; every geometry claim is
+verified by saving a DXF and re-reading it with ezdxf in the harness.
+
+Tasks with no documented equivalent on this server are reported as
+``unsupported`` with an explicit reason so the published JSON explains the
+coverage gap instead of hiding it.
+"""
+
+from __future__ import annotations
+
+import math
+
+from benchmarks.adapters.base import TaskResult
+from benchmarks.adapters.mcp_stdio import (
+    McpStdioAdapter,
+    ToolCallFailed,
+    extract_handle,
+)
+from benchmarks.competitors_env import CompetitorSpec
+
+PINNED_SHA = "95476a33a1c246308326eb4709d6379ef2efdbc1"
+
+
+class PuranWaterAdapter(McpStdioAdapter):
+    name = "puran-water-autocad-mcp"
+    spec = CompetitorSpec(
+        competitor_id="puran-water-autocad-mcp",
+        repo_url="https://github.com/puran-water/autocad-mcp.git",
+        pinned_sha=PINNED_SHA,
+        entry_candidates=(
+            ("-m", "autocad_mcp"),
+            ("server.py",),
+            ("src/server.py",),
+            ("main.py",),
+        ),
+        pip_installs=(("-e", "."),),
+        launch_env={"AUTOCAD_MCP_BACKEND": "ezdxf"},
+        pythonpath="src",
+    )
+
+    # Exact v3.1 contract (verified against the pinned checkout's server.py):
+    # entity create_line takes top-level x1..y2; circle/dimension payloads sit
+    # under ``data``; modify ops take top-level ``entity_id`` + ``data``.
+
+    def warmup_calls(self):
+        # The first backend touch lazily initializes and can exceed the
+        # per-call timeout; absorb it once during setup.
+        return (
+            ("system", {"operation": "status"}),
+            ("drawing", {"operation": "create", "data": {}}),
+        )
+
+    async def _new_drawing(self) -> None:
+        await self.call_op("drawing", "create", {})
+
+    async def _save(self, filename: str) -> str:
+        target = self.save_target(filename)
+        await self.call_op("drawing", "save", {"path": str(target)})
+        return str(target)
+
+    async def _create_line(self, x1: float, y1: float, x2: float, y2: float):
+        return await self.call(
+            "entity",
+            {"operation": "create_line", "x1": x1, "y1": y1, "x2": x2, "y2": y2},
+        )
+
+    # -- tasks ----------------------------------------------------------------
+
+    async def _task_core_geometry(self) -> TaskResult:
+        await self._new_drawing()
+        await self._create_line(0, 0, 3, 4)
+        await self.call_op("entity", "create_circle", {"cx": 10, "cy": 10, "radius": 2})
+        preferred = await self._save("puran_core_geometry.dxf")
+        _, doc = self.verify_dxf(self.save_target("puran_core_geometry.dxf"))
+        lines = doc.modelspace().query("LINE")
+        circles = doc.modelspace().query("CIRCLE")
+        length = None
+        if lines:
+            start, end = lines[0].dxf.start, lines[0].dxf.end
+            length = math.dist((start.x, start.y), (end.x, end.y))
+        passed = (
+            len(lines) == 1
+            and len(circles) == 1
+            and length is not None
+            and abs(length - 5.0) < 1e-6
+            and abs(circles[0].dxf.radius - 2.0) < 1e-6
+        )
+        return TaskResult(
+            "core_geometry",
+            "pass" if passed else "fail",
+            100.0 if passed else 0.0,
+            metrics={"line_length": length, "lines": len(lines), "circles": len(circles)},
+            artifacts=[preferred],
+        )
+
+    async def _task_modify_query(self) -> TaskResult:
+        await self._new_drawing()
+        created = await self._create_line(0, 0, 10, 0)
+        handle = extract_handle(created)
+        if not handle:
+            return TaskResult(
+                "modify_query",
+                "fail",
+                0.0,
+                "could not extract created-entity handle from the create_line response",
+            )
+        await self.call(
+            "entity",
+            {"operation": "move", "entity_id": handle, "data": {"dx": 5, "dy": 2}},
+        )
+        artifact = await self._save("puran_modify_query.dxf")
+        _, doc = self.verify_dxf(self.save_target("puran_modify_query.dxf"))
+        lines = doc.modelspace().query("LINE")
+        moved = (
+            bool(lines)
+            and abs(lines[0].dxf.start.x - 5.0) < 1e-6
+            and (abs(lines[0].dxf.start.y - 2.0) < 1e-6)
+        )
+        return TaskResult(
+            "modify_query",
+            "pass" if moved else "fail",
+            100.0 if moved else 0.0,
+            artifacts=[artifact],
+        )
+
+    async def _task_layers_linetypes(self) -> TaskResult:
+        await self._new_drawing()
+        try:
+            await self.call_op(
+                "layer",
+                "create",
+                {"name": "GEOMETRY", "color": 3, "linetype": "CENTER"},
+            )
+        except ToolCallFailed:
+            await self.call_op("layer", "create", {"name": "GEOMETRY", "color": 3})
+        artifact = await self._save("puran_layers.dxf")
+        _, doc = self.verify_dxf(self.save_target("puran_layers.dxf"))
+        has_layer = "GEOMETRY" in {layer.dxf.name.upper() for layer in doc.layers}
+        has_center = "CENTER" in {lt.dxf.name.upper() for lt in doc.linetypes}
+        if has_layer and has_center:
+            return TaskResult("layers_linetypes", "pass", 100.0, artifacts=[artifact])
+        if has_layer:
+            return TaskResult(
+                "layers_linetypes",
+                "partial",
+                50.0,
+                "layer created; no linetype-loading operation is exposed",
+                artifacts=[artifact],
+            )
+        return TaskResult("layers_linetypes", "fail", 0.0, artifacts=[artifact])
+
+    async def _task_dimensions(self) -> TaskResult:
+        await self._new_drawing()
+        await self.call_op(
+            "annotation",
+            "create_dimension_linear",
+            {"x1": 0, "y1": 0, "x2": 50, "y2": 0, "dim_x": 25, "dim_y": 10},
+        )
+        artifact = await self._save("puran_dimensions.dxf")
+        _, doc = self.verify_dxf(self.save_target("puran_dimensions.dxf"))
+        dims = [e for e in doc.modelspace() if e.dxftype() == "DIMENSION"]
+        return TaskResult(
+            "dimensions",
+            "pass" if dims else "fail",
+            100.0 if dims else 0.0,
+            metrics={"dimension_count": len(dims)},
+            artifacts=[artifact],
+        )
+
+    async def _task_dxf_roundtrip(self) -> TaskResult:
+        await self._new_drawing()
+        await self._create_line(0, 0, 10, 10)
+        artifact = await self._save("puran_roundtrip.dxf")
+        _, doc = self.verify_dxf(self.save_target("puran_roundtrip.dxf"))
+        count = len(list(doc.modelspace()))
+        return TaskResult(
+            "dxf_roundtrip",
+            "pass" if count == 1 else "fail",
+            100.0 if count == 1 else 0.0,
+            metrics={"entity_count": count},
+            artifacts=[artifact],
+        )
+
+    # -- documented coverage gaps ----------------------------------------------
+
+    async def _task_table_mleader(self) -> TaskResult:
+        return TaskResult(
+            "table_mleader",
+            "unsupported",
+            0.0,
+            "no TABLE or MLEADER operation in the 8-tool surface (v3.1)",
+        )
+
+    async def _task_transactions(self) -> TaskResult:
+        return TaskResult(
+            "transactions",
+            "unsupported",
+            0.0,
+            "no transaction begin/commit/rollback tool (undo/redo are File-IPC only)",
+        )
+
+    async def _task_preflight(self) -> TaskResult:
+        return TaskResult("preflight", "unsupported", 0.0, "no requirements-preflight equivalent")
+
+    async def _task_quality_refiner(self) -> TaskResult:
+        return TaskResult(
+            "quality_refiner", "unsupported", 0.0, "no critique/repair loop equivalent"
+        )
+
+    async def _task_auditable_delivery(self) -> TaskResult:
+        return TaskResult(
+            "auditable_delivery",
+            "unsupported",
+            0.0,
+            "no hashed delivery-manifest equivalent (plot_pdf is File-IPC only)",
+        )
+
+
+__all__ = ["PuranWaterAdapter", "ToolCallFailed"]

benchmarks/compare_versions.py

@@ -11,6 +11,7 @@ recorded as a miss instead of taking down the whole run.
 The older ref is checked out into a throwaway git worktree, benchmarked, and
 removed. The "new" side is always the current repository checkout.
 """
+
 from __future__ import annotations
 
 import json
@@ -27,8 +28,7 @@ PY = sys.executable
 
 def _run(cmd, cwd, repo_on_path):
     env = {**os.environ, "PYTHONPATH": repo_on_path}
-    return subprocess.run(cmd, cwd=cwd, env=env, capture_output=True,
-                          text=True, timeout=120)
+    return subprocess.run(cmd, cwd=cwd, env=env, capture_output=True, text=True, timeout=120)
 
 
 def list_checks():
@@ -43,9 +43,14 @@ def list_checks():
 
 def run_one(repo, suite, name):
     try:
-        r = subprocess.run([PY, suite, name], cwd=repo,
+        r = subprocess.run(
+            [PY, suite, name],
+            cwd=repo,
             env={**os.environ, "PYTHONPATH": repo},
-                           capture_output=True, text=True, timeout=120)
+            capture_output=True,
+            text=True,
+            timeout=120,
+        )
     except subprocess.TimeoutExpired:
         return "timeout"
     last = (r.stdout.strip().splitlines() or [""])[-1].strip()
@@ -82,22 +87,30 @@ def main():
     op = sum(r["old"] == "pass" for r in rows)
     npass = sum(r["new"] == "pass" for r in rows)
     summary = {
-        "baseline_ref": ref, "total": total,
-        "old_pass": op, "new_pass": npass,
-        "old_pct": round(100 * op / total, 1), "new_pct": round(100 * npass / total, 1),
+        "baseline_ref": ref,
+        "total": total,
+        "old_pass": op,
+        "new_pass": npass,
+        "old_pct": round(100 * op / total, 1),
+        "new_pct": round(100 * npass / total, 1),
         "fixed": sum(r["old"] != "pass" and r["new"] == "pass" for r in rows),
         "regressed": sum(r["old"] == "pass" and r["new"] != "pass" for r in rows),
     }
     print(f"{'CHECK':<32} {'CATEGORY':<13} {'baseline':<8} {'current':<8}")
     print("-" * 66)
     for r in rows:
-        mark = " ->FIXED" if (r["old"] != "pass" and r["new"] == "pass") else (
-            " !!REGRESS" if (r["old"] == "pass" and r["new"] != "pass") else "")
+        mark = (
+            " ->FIXED"
+            if (r["old"] != "pass" and r["new"] == "pass")
+            else (" !!REGRESS" if (r["old"] == "pass" and r["new"] != "pass") else "")
+        )
         print(f"{r['check']:<32} {r['category']:<13} {r['old']:<8} {r['new']:<8}{mark}")
     print("-" * 66)
-    print(f"baseline {ref}: {op}/{total} ({summary['old_pct']}%)   "
+    print(
+        f"baseline {ref}: {op}/{total} ({summary['old_pct']}%)   "
         f"current: {npass}/{total} ({summary['new_pct']}%)   "
-          f"fixed: {summary['fixed']}  regressed: {summary['regressed']}")
+        f"fixed: {summary['fixed']}  regressed: {summary['regressed']}"
+    )
     if json_out:
         with open(json_out, "w") as fh:
             json.dump({"summary": summary, "rows": rows}, fh, indent=2)

benchmarks/competitors.yaml

@@ -5,6 +5,22 @@
       "id": "autocad-mcp-pro",
       "adapter": "benchmarks.adapters.autocad_mcp_pro:AutoCADMCPProAdapter",
       "backends": ["ezdxf", "com"]
+    },
+    {
+      "id": "puran-water-autocad-mcp",
+      "adapter": "benchmarks.adapters.puran_water:PuranWaterAdapter",
+      "backends": ["ezdxf"],
+      "repo": "https://github.com/puran-water/autocad-mcp",
+      "pinned_sha": "95476a33a1c246308326eb4709d6379ef2efdbc1",
+      "notes": "Black-box MCP stdio lane; File-IPC (live AutoCAD) features run in the local COM lane only."
+    },
+    {
+      "id": "beiming183-autocad-mcp",
+      "adapter": "benchmarks.adapters.beiming_autocad:BeimingAutocadAdapter",
+      "backends": ["ezdxf"],
+      "repo": "https://github.com/beiming183-cloud/AutoCAD-MCP",
+      "pinned_sha": "11f7c47e5038796a20451b38b23032e625b5aa26",
+      "notes": "Black-box MCP stdio lane; deliver/undo/redo are documented File-IPC only and reported unsupported."
     }
   ]
 }

benchmarks/competitors_env.py

@@ -0,0 +1,121 @@
+"""Reproducible checkout + venv management for competitor MCP servers.
+
+Every competitor is pinned to an exact commit so a benchmark run is
+reproducible: same tasks, same tree, same interpreter isolation. The cache
+lives under ``benchmarks/.competitors/<id>/`` (gitignored) as::
+
+    repo/    the pinned git checkout
+    venv/    an isolated interpreter with the competitor installed
+
+Nothing here talks MCP — it only prepares a runnable ``python`` + entry args
+for :class:`benchmarks.adapters.mcp_stdio.McpStdioAdapter`.
+"""
+
+from __future__ import annotations
+
+import subprocess
+import sys
+from dataclasses import dataclass, field
+from pathlib import Path
+
+CACHE_ROOT = Path(__file__).resolve().parent / ".competitors"
+
+
+@dataclass(frozen=True)
+class CompetitorSpec:
+    """Everything needed to fetch and launch one competitor server."""
+
+    competitor_id: str
+    repo_url: str
+    pinned_sha: str
+    # Candidate stdio entrypoints, resolved in order against the checkout.
+    # ("-m", "pkg") entries are accepted when repo/pkg or repo/src/pkg exists.
+    entry_candidates: tuple[tuple[str, ...], ...]
+    # pip arguments executed inside the venv, relative to the checkout.
+    pip_installs: tuple[tuple[str, ...], ...] = (("-e", "."),)
+    # Extra environment applied when launching the server.
+    launch_env: dict[str, str] = field(default_factory=dict)
+    # Set PYTHONPATH to this repo-relative directory (e.g. "src") if not None.
+    pythonpath: str | None = None
+
+
+@dataclass(frozen=True)
+class CompetitorRuntime:
+    """A resolved, launchable competitor installation."""
+
+    python_exe: Path
+    repo_dir: Path
+    entry_args: tuple[str, ...]
+    env: dict[str, str]
+
+
+def _run(cmd: list[str], cwd: Path | None = None, timeout: float = 600.0) -> None:
+    completed = subprocess.run(cmd, cwd=cwd, capture_output=True, text=True, timeout=timeout)
+    if completed.returncode != 0:
+        raise RuntimeError(
+            f"command failed ({' '.join(cmd)}):\n{completed.stdout}\n{completed.stderr}"
+        )
+
+
+def _venv_python(venv_dir: Path) -> Path:
+    if sys.platform == "win32":
+        return venv_dir / "Scripts" / "python.exe"
+    return venv_dir / "bin" / "python"
+
+
+def _ensure_checkout(spec: CompetitorSpec, repo_dir: Path) -> None:
+    if not (repo_dir / ".git").exists():
+        repo_dir.parent.mkdir(parents=True, exist_ok=True)
+        _run(["git", "clone", "--quiet", spec.repo_url, str(repo_dir)])
+    head = subprocess.run(
+        ["git", "rev-parse", "HEAD"], cwd=repo_dir, capture_output=True, text=True
+    ).stdout.strip()
+    if head != spec.pinned_sha:
+        _run(["git", "fetch", "--quiet", "origin"], cwd=repo_dir)
+        _run(["git", "checkout", "--quiet", spec.pinned_sha], cwd=repo_dir)
+
+
+def _ensure_venv(spec: CompetitorSpec, venv_dir: Path, repo_dir: Path) -> Path:
+    python_exe = _venv_python(venv_dir)
+    marker = venv_dir / ".installed-sha"
+    if python_exe.exists() and marker.exists() and marker.read_text().strip() == spec.pinned_sha:
+        return python_exe
+    _run([sys.executable, "-m", "venv", str(venv_dir)])
+    _run([str(python_exe), "-m", "pip", "install", "--quiet", "--upgrade", "pip"])
+    for install in spec.pip_installs:
+        _run([str(python_exe), "-m", "pip", "install", "--quiet", *install], cwd=repo_dir)
+    marker.write_text(spec.pinned_sha)
+    return python_exe
+
+
+def _resolve_entry(spec: CompetitorSpec, repo_dir: Path) -> tuple[str, ...]:
+    for candidate in spec.entry_candidates:
+        if candidate[0] == "-m":
+            package = candidate[1].replace(".", "/")
+            roots = [repo_dir, repo_dir / "src"]
+            if any(
+                (root / package).is_dir() or (root / f"{package}.py").is_file() for root in roots
+            ):
+                return candidate
+        elif (repo_dir / candidate[0]).is_file():
+            return tuple([str(repo_dir / candidate[0]), *candidate[1:]])
+    raise RuntimeError(
+        f"{spec.competitor_id}: no stdio entrypoint found "
+        f"(tried {[c[0] for c in spec.entry_candidates]})"
+    )
+
+
+def ensure_competitor(spec: CompetitorSpec, cache_root: Path | None = None) -> CompetitorRuntime:
+    """Clone, pin, install and resolve one competitor. Idempotent."""
+    root = (cache_root or CACHE_ROOT) / spec.competitor_id
+    repo_dir = root / "repo"
+    _ensure_checkout(spec, repo_dir)
+    python_exe = _ensure_venv(spec, root / "venv", repo_dir)
+    entry_args = _resolve_entry(spec, repo_dir)
+
+    env = dict(spec.launch_env)
+    if spec.pythonpath is not None:
+        env["PYTHONPATH"] = str(repo_dir / spec.pythonpath)
+    return CompetitorRuntime(
+        python_exe=python_exe, repo_dir=repo_dir, entry_args=entry_args, env=env
+    )

benchmarks/perf_suite.py

@@ -0,0 +1,210 @@
+"""Headless performance suite (v3 lane): wall-time on real drawing workloads.
+
+Complements the correctness/coverage lanes with *scale* evidence: how long the
+ezdxf engine takes to create, roundtrip, query and quality-check real geometry.
+Workloads drive the backend exactly like the MCP tools do (same async methods),
+so the numbers include the server-side call overhead, not just raw ezdxf.
+
+Honesty boundaries:
+
+- Self-measurement only — no competitor timing claims (their servers would pay
+  an extra stdio serialization cost ours does not pay in-process).
+- Wall-clock on the machine recorded in the report; absolute numbers move with
+  hardware, the workload definitions do not.
+
+Run:
+
+    python -m benchmarks.perf_suite            # human summary
+    python -m benchmarks.perf_suite --json     # machine-readable report
+    python -m benchmarks.perf_suite --out benchmarks/results/published/perf-ezdxf.json
+"""
+
+from __future__ import annotations
+
+import argparse
+import asyncio
+import json
+import platform
+import sys
+import time
+from dataclasses import asdict, dataclass
+from pathlib import Path
+
+from backends.ezdxf_backend import EzdxfBackend
+
+
+@dataclass
+class WorkloadResult:
+    workload_id: str
+    description: str
+    wall_ms: float
+    metric: str
+    metric_value: float
+    detail: dict
+
+
+async def _timed(coro) -> tuple[float, object]:
+    started = time.perf_counter()
+    result = await coro
+    return (time.perf_counter() - started) * 1000.0, result
+
+
+async def workload_create_lines_2k(backend: EzdxfBackend) -> WorkloadResult:
+    """2,000 individual entity_create_line calls (per-call tool overhead included)."""
+    await backend.drawing_new()
+    started = time.perf_counter()
+    for index in range(2_000):
+        y = float(index % 100)
+        await backend.entity_create_line(0.0, y, 100.0, y + 1.0)
+    wall_ms = (time.perf_counter() - started) * 1000.0
+    count = (await backend.drawing_info()).entity_count
+    return WorkloadResult(
+        "create_lines_2k",
+        "Create 2,000 lines through individual backend calls",
+        round(wall_ms, 1),
+        "entities_per_second",
+        round(2_000 / (wall_ms / 1000.0), 1),
+        {"entity_count": count},
+    )
+
+
+async def workload_roundtrip_10k(backend: EzdxfBackend, scratch: Path) -> WorkloadResult:
+    """Build a 10,000-entity drawing, export DXF, reopen, read info."""
+    await backend.drawing_new()
+    build_started = time.perf_counter()
+    for index in range(10_000):
+        x = float(index % 500)
+        y = float(index // 500)
+        await backend.entity_create_line(x, y, x + 0.8, y + 0.8)
+    build_ms = (time.perf_counter() - build_started) * 1000.0
+
+    target = scratch / "perf_roundtrip_10k.dxf"
+    export_ms, _ = await _timed(backend.drawing_export_dxf(str(target)))
+
+    reopened = EzdxfBackend()
+    await reopened.connect()
+    try:
+        reopen_ms, _ = await _timed(reopened.drawing_open(str(target)))
+        count = (await reopened.drawing_info()).entity_count
+    finally:
+        await reopened.disconnect()
+
+    total = build_ms + export_ms + reopen_ms
+    return WorkloadResult(
+        "roundtrip_10k",
+        "Create 10,000 lines, export DXF, reopen and verify",
+        round(total, 1),
+        "entities_per_second",
+        round(10_000 / (total / 1000.0), 1),
+        {
+            "build_ms": round(build_ms, 1),
+            "export_ms": round(export_ms, 1),
+            "reopen_ms": round(reopen_ms, 1),
+            "file_bytes": target.stat().st_size,
+            "entity_count": count,
+        },
+    )
+
+
+async def workload_region_query_10k(backend: EzdxfBackend) -> WorkloadResult:
+    """Rectangular region query against the 10,000-entity drawing."""
+    # backend still holds the 10k drawing from the roundtrip workload builder;
+    # rebuild deterministically to stay order-independent.
+    await backend.drawing_new()
+    for index in range(10_000):
+        x = float(index % 500)
+        y = float(index // 500)
+        await backend.entity_create_line(x, y, x + 0.8, y + 0.8)
+    wall_ms, found = await _timed(backend.analysis_entities_in_region(0.0, 0.0, 250.0, 10.0))
+    return WorkloadResult(
+        "region_query_10k",
+        "Crossing-selection region query over 10,000 entities",
+        round(wall_ms, 1),
+        "entities_matched",
+        float(len(found)),
+        {"entity_count": 10_000},
+    )
+
+
+async def workload_premium_pass(backend: EzdxfBackend) -> WorkloadResult:
+    """Small end-to-end quality loop: layers, geometry, dimensions, critique."""
+    started = time.perf_counter()
+    await backend.drawing_new()
+    await backend.drawing_apply_iso_layers("mech")
+    plate = [
+        (0.0, 0.0, 120.0, 0.0),
+        (120.0, 0.0, 120.0, 80.0),
+        (120.0, 80.0, 0.0, 80.0),
+        (0.0, 80.0, 0.0, 0.0),
+    ]
+    for x1, y1, x2, y2 in plate:
+        await backend.entity_create_line(x1, y1, x2, y2, layer="GEOMETRY")
+    await backend.entity_create_circle(60.0, 40.0, 12.0, layer="GEOMETRY")
+    await backend.dimension_linear(0, 0, 120, 0, 60, -15, layer="DIM")
+    await backend.dimension_linear(0, 0, 0, 80, -15, 40, 90, layer="DIM")
+    issues = await backend.drawing_critique(None)
+    wall_ms = (time.perf_counter() - started) * 1000.0
+    return WorkloadResult(
+        "premium_pass",
+        "Plate with hole: ISO layers, geometry, dimensions and full critique",
+        round(wall_ms, 1),
+        "critique_issues",
+        float(len(issues)),
+        {"entities": (await backend.drawing_info()).entity_count},
+    )
+
+
+async def run_suite(scratch: Path) -> dict:
+    backend = EzdxfBackend()
+    await backend.connect()
+    try:
+        results = [
+            await workload_create_lines_2k(backend),
+            await workload_roundtrip_10k(backend, scratch),
+            await workload_region_query_10k(backend),
+            await workload_premium_pass(backend),
+        ]
+    finally:
+        await backend.disconnect()
+    return {
+        "schema_version": "perf/1.0",
+        "backend": "ezdxf",
+        "environment": {
+            "python": sys.version.split()[0],
+            "implementation": platform.python_implementation(),
+            "platform": platform.platform(),
+            "machine": platform.machine(),
+        },
+        "workloads": [asdict(item) for item in results],
+    }
+
+
+def build_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("--json", action="store_true", help="Print machine-readable JSON")
+    parser.add_argument("--out", type=Path, default=None, help="Also write the report to a file")
+    parser.add_argument("--scratch", type=Path, default=Path("benchmarks/results/perf-scratch"))
+    return parser
+
+
+def main() -> int:
+    args = build_parser().parse_args()
+    args.scratch.mkdir(parents=True, exist_ok=True)
+    report = asyncio.run(run_suite(args.scratch))
+    rendered = json.dumps(report, ensure_ascii=False, indent=2, sort_keys=True)
+    if args.out is not None:
+        args.out.parent.mkdir(parents=True, exist_ok=True)
+        args.out.write_text(rendered + "\n", encoding="utf-8")
+    if args.json:
+        print(rendered)
+    else:
+        for item in report["workloads"]:
+            print(
+                f"{item['workload_id']:>18}  {item['wall_ms']:>10.1f} ms   "
+                f"{item['metric']}={item['metric_value']}"
+            )
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

benchmarks/render_chart.py

@@ -66,24 +66,38 @@ def render_chart(data: dict[str, Any], output: Path) -> None:
 
     matplotlib.rcParams["svg.hashsalt"] = "autocad-mcp-source-review-v1"
     projects = sorted(data["projects"], key=lambda item: item["score"])
-    labels = [item["repository"] for item in projects]
+    total = len(projects)
+    # rank 1 = highest score (drawn topmost by barh with ascending sort)
+    labels = [f"{total - index}. {item['repository']}" for index, item in enumerate(projects)]
     scores = [item["score"] for item in projects]
     grades = [item["evidence_grade"] for item in projects]
-    colors = ["#0969da" if label == "U-C4N/Autocad-MCP" else "#6e7781" for label in labels]
+    # leaderboard palette by rank (rank 1 first), canvas/LLM-benchmark style
+    rank_palette = [
+        "#3fb950",  # 1 green
+        "#58a6ff",  # 2 sky
+        "#6e7ce0",  # 3 indigo
+        "#d29922",  # 4 amber
+        "#c4622d",  # 5 rust
+        "#e3b341",  # 6 yellow
+        "#bf4b8a",  # 7 magenta
+        "#f0876e",  # 8 salmon
+        "#8957e5",  # 9 purple
+    ]
+    colors = [rank_palette[(total - 1 - index) % len(rank_palette)] for index in range(total)]
 
-    fig, ax = plt.subplots(figsize=(12, 6.4), constrained_layout=True)
-    fig.patch.set_facecolor("#f6f8fa")
-    ax.set_facecolor("#f6f8fa")
+    fig, ax = plt.subplots(figsize=(12, 0.62 * total + 2.4), constrained_layout=True)
+    fig.patch.set_facecolor("#0d1117")
+    ax.set_facecolor("#0d1117")
     bars = ax.barh(labels, scores, color=colors, height=0.62)
 
     ax.set_xlim(0, 100)
-    ax.set_xlabel("Weighted capability score / 100", color="#24292f", labelpad=10)
+    ax.set_xlabel("Weighted capability score / 100", color="#e6edf3", labelpad=10)
     ax.set_title(
-        "Source-reviewed capability benchmark",
+        "Public AutoCAD MCP leaderboard — Source-reviewed capability benchmark",
         loc="left",
-        fontsize=18,
+        fontsize=15,
         fontweight="bold",
-        color="#24292f",
+        color="#e6edf3",
         pad=28,
     )
     ax.text(
@@ -91,17 +105,17 @@ def render_chart(data: dict[str, Any], output: Path) -> None:
         1.02,
         f"Fixed rubric · reviewed {data['reviewed_at']} · evidence grade shown per project",
         transform=ax.transAxes,
-        color="#57606a",
+        color="#8b949e",
         fontsize=10,
     )
 
     for bar, score, grade in zip(bars, scores, grades, strict=True):
         ax.text(
-            min(score + 1.2, 96),
+            min(score + 1.2, 88),
             bar.get_y() + bar.get_height() / 2,
-            f"{score}  ·  {grade}",
+            f"{score} / 100  ·  {grade}",
             va="center",
-            color="#24292f",
+            color="#e6edf3",
             fontweight="bold",
         )
 
@@ -110,13 +124,13 @@ def render_chart(data: dict[str, Any], output: Path) -> None:
         -0.17,
         "Shared live-run results are not implied. Scores reflect public-source and recorded test evidence.",
         transform=ax.transAxes,
-        color="#57606a",
+        color="#8b949e",
         fontsize=9,
     )
-    ax.grid(axis="x", color="#d0d7de", linewidth=0.8, alpha=0.8)
+    ax.grid(axis="x", color="#30363d", linewidth=0.8, alpha=0.9)
     ax.set_axisbelow(True)
-    ax.tick_params(axis="x", colors="#57606a")
-    ax.tick_params(axis="y", colors="#24292f", length=0, pad=8)
+    ax.tick_params(axis="x", colors="#8b949e")
+    ax.tick_params(axis="y", colors="#e6edf3", length=0, pad=8)
     for spine in ax.spines.values():
         spine.set_visible(False)
 

benchmarks/render_live_chart.py

@@ -0,0 +1,149 @@
+"""Render the live-run benchmark lane (v2 fixed-task matrix) as a deterministic SVG.
+
+Input: the published per-server reports under ``benchmarks/results/published/``
+(produced by ``benchmarks.run_competitors``, artifact paths sanitized to
+filenames). Output: a GitHub-readable horizontal bar chart showing the
+weighted score and task coverage per server.
+"""
+
+from __future__ import annotations
+
+import argparse
+import json
+from pathlib import Path
+from typing import Any
+
+ROOT = Path(__file__).resolve().parents[1]
+DEFAULT_INPUT_DIR = ROOT / "benchmarks" / "results" / "published"
+DEFAULT_OUTPUT = ROOT / "docs" / "assets" / "autocad-mcp-livebench.svg"
+
+
+def load_reports(input_dir: Path) -> list[dict[str, Any]]:
+    reports: list[dict[str, Any]] = []
+    for path in sorted(input_dir.glob("*.json")):
+        data = json.loads(path.read_text(encoding="utf-8"))
+        if data.get("schema_version") != "2.0":
+            continue  # other lanes (e.g. perf/1.0) share the published folder
+        summary = data.get("summary") or {}
+        if "score" not in summary or "coverage_percent" not in summary:
+            raise ValueError(f"{path.name}: summary is missing score/coverage")
+        reports.append(data)
+    if not reports:
+        raise SystemExit(f"no published reports found in {input_dir}")
+    return reports
+
+
+def render_chart(reports: list[dict[str, Any]], output: Path) -> None:
+    try:
+        import matplotlib
+
+        matplotlib.use("Agg")
+        import matplotlib.pyplot as plt
+    except ImportError as exc:
+        raise SystemExit(
+            'Matplotlib is required. Install it with: pip install -e ".[pdf]"'
+        ) from exc
+
+    matplotlib.rcParams["svg.hashsalt"] = "autocad-mcp-livebench-v2"
+    reports = sorted(reports, key=lambda item: item["summary"]["score"])
+    labels = [item["adapter"] for item in reports]
+    scores = [item["summary"]["score"] for item in reports]
+    coverage = [item["summary"]["coverage_percent"] for item in reports]
+    passed = [item["summary"]["passed"] for item in reports]
+    attempted = [item["summary"]["attempted"] for item in reports]
+    # Which task set each server actually ran. Not decoration: since v1.5.0
+    # the reference adapter runs the 15-task v3 matrix while the pinned
+    # competitor reports are v2 runs from v1.4, so the bars do not share a
+    # denominator and a chart that implies they do is the lie this lane
+    # exists to avoid.
+    matrices = [item.get("matrix", "v2") for item in reports]
+    colors = ["#58a6ff" if label == "autocad-mcp-pro" else "#484f58" for label in labels]
+
+    fig, ax = plt.subplots(figsize=(12, 4.8), constrained_layout=True)
+    fig.patch.set_facecolor("#0d1117")
+    ax.set_facecolor("#0d1117")
+    bars = ax.barh(labels, scores, color=colors, height=0.58)
+
+    ax.set_xlim(0, 100)
+    ax.set_xlabel(
+        "Weighted live-run score / 100, within each server's own task matrix",
+        color="#e6edf3",
+        labelpad=10,
+    )
+    ax.set_title(
+        "Live-run benchmark - headless ezdxf lane",
+        loc="left",
+        fontsize=18,
+        fontweight="bold",
+        color="#e6edf3",
+        pad=28,
+    )
+    ax.text(
+        0,
+        1.02,
+        "Same harness, pinned competitor commits; artifacts verified by re-opening the DXF. "
+        "Matrices differ - read the per-bar label.",
+        transform=ax.transAxes,
+        color="#8b949e",
+        fontsize=10,
+    )
+
+    for bar, score, cov, ok, total, matrix in zip(
+        bars, scores, coverage, passed, attempted, matrices, strict=True
+    ):
+        ax.text(
+            min(score + 1.2, 76),
+            bar.get_y() + bar.get_height() / 2,
+            f"{score:g}  ({ok}/{total} pass, {cov:g}% coverage, matrix {matrix})",
+            va="center",
+            color="#e6edf3",
+            fontweight="bold",
+        )
+
+    ax.text(
+        0,
+        -0.22,
+        "Unsupported tasks score 0 within a server's own matrix. The tasks added after v2 "
+        "were never put to the pinned competitor runs; per-task statuses are "
+        "in benchmarks/results/published/.",
+        transform=ax.transAxes,
+        color="#8b949e",
+        fontsize=9,
+    )
+    ax.grid(axis="x", color="#30363d", linewidth=0.8, alpha=0.8)
+    ax.set_axisbelow(True)
+    ax.tick_params(axis="x", colors="#8b949e")
+    ax.tick_params(axis="y", colors="#e6edf3", length=0, pad=8)
+    for spine in ax.spines.values():
+        spine.set_visible(False)
+
+    output.parent.mkdir(parents=True, exist_ok=True)
+    fig.savefig(
+        output,
+        format="svg",
+        facecolor=fig.get_facecolor(),
+        metadata={"Creator": "AutoCAD MCP Pro live benchmark renderer", "Date": None},
+    )
+    plt.close(fig)
+
+    svg = output.read_text(encoding="utf-8")
+    normalized = "\n".join(line.rstrip() for line in svg.splitlines()) + "\n"
+    output.write_text(normalized, encoding="utf-8", newline="\n")
+
+
+def build_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("--input-dir", type=Path, default=DEFAULT_INPUT_DIR)
+    parser.add_argument("--output", type=Path, default=DEFAULT_OUTPUT)
+    return parser
+
+
+def main() -> int:
+    args = build_parser().parse_args()
+    render_chart(load_reports(args.input_dir), args.output)
+    print(f"Rendered live benchmark chart: {args.output}")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

benchmarks/render_matrix_chart.py

@@ -0,0 +1,180 @@
+"""Render the live-run task matrix (tasks x servers) as a deterministic SVG.
+
+Input: the published per-server reports under ``benchmarks/results/published/``
+(the same files the score chart uses). Output: a status heatmap — every task
+against every server — so coverage gaps are visible per capability instead of
+being folded into one number.
+"""
+
+from __future__ import annotations
+
+import argparse
+import json
+from pathlib import Path
+from typing import Any
+
+from benchmarks.tasks_v7 import TASKS_V7
+
+ROOT = Path(__file__).resolve().parents[1]
+DEFAULT_INPUT_DIR = ROOT / "benchmarks" / "results" / "published"
+DEFAULT_OUTPUT = ROOT / "docs" / "assets" / "autocad-mcp-taskmatrix.svg"
+
+STATUS_COLORS = {
+    "pass": "#238636",
+    "partial": "#d29922",
+    "fail": "#da3633",
+    "timeout": "#a40e26",
+    "unsupported": "#30363d",
+    "not_run": "#161b22",
+}
+
+STATUS_GLYPHS = {
+    "pass": "P",
+    "partial": "~",
+    "fail": "F",
+    "timeout": "T",
+    "unsupported": "-",
+    "not_run": "?",
+}
+
+
+def load_reports(input_dir: Path) -> list[dict[str, Any]]:
+    reports: list[dict[str, Any]] = []
+    for path in sorted(input_dir.glob("*.json")):
+        data = json.loads(path.read_text(encoding="utf-8"))
+        if data.get("schema_version") != "2.0":
+            continue  # perf reports and other lanes live in the same folder
+        reports.append(data)
+    if not reports:
+        raise SystemExit(f"no task-matrix reports found in {input_dir}")
+    # our server first, then alphabetical
+    reports.sort(key=lambda item: (item["adapter"] != "autocad-mcp-pro", item["adapter"]))
+    return reports
+
+
+def render_chart(reports: list[dict[str, Any]], output: Path) -> None:
+    try:
+        import matplotlib
+
+        matplotlib.use("Agg")
+        import matplotlib.pyplot as plt
+        from matplotlib.patches import Patch, Rectangle
+    except ImportError as exc:
+        raise SystemExit(
+            'Matplotlib is required. Install it with: pip install -e ".[pdf]"'
+        ) from exc
+
+    matplotlib.rcParams["svg.hashsalt"] = "autocad-mcp-taskmatrix-v1"
+
+    task_ids = [task.task_id for task in TASKS_V7]
+    task_labels = [f"{task.task_id}  ({task.category})" for task in TASKS_V7]
+    servers = [report["adapter"] for report in reports]
+    status_by_server = {
+        report["adapter"]: {item["task_id"]: item["status"] for item in report["results"]}
+        for report in reports
+    }
+
+    fig, ax = plt.subplots(
+        figsize=(3.4 + 2.4 * len(servers), 1.8 + 0.52 * len(task_ids)),
+        constrained_layout=True,
+    )
+    fig.patch.set_facecolor("#0d1117")
+    ax.set_facecolor("#0d1117")
+
+    for row, task_id in enumerate(task_ids):
+        for col, server in enumerate(servers):
+            status = status_by_server[server].get(task_id, "not_run")
+            color = STATUS_COLORS.get(status, "#f6f8fa")
+            ax.add_patch(
+                Rectangle(
+                    (col + 0.06, row + 0.08),
+                    0.88,
+                    0.84,
+                    facecolor=color,
+                    edgecolor="#30363d",
+                    linewidth=0.8,
+                )
+            )
+            glyph_color = "#ffffff" if status in ("pass", "fail", "timeout") else "#e6edf3"
+            ax.text(
+                col + 0.5,
+                row + 0.5,
+                STATUS_GLYPHS.get(status, "?"),
+                ha="center",
+                va="center",
+                fontsize=11,
+                fontweight="bold",
+                color=glyph_color,
+            )
+
+    ax.set_xlim(0, len(servers))
+    ax.set_ylim(len(task_ids), 0)
+    ax.set_xticks([index + 0.5 for index in range(len(servers))])
+    ax.set_xticklabels(servers, color="#e6edf3", fontsize=10, fontweight="bold")
+    ax.xaxis.set_ticks_position("top")
+    ax.set_yticks([index + 0.5 for index in range(len(task_ids))])
+    ax.set_yticklabels(task_labels, color="#e6edf3", fontsize=9)
+    ax.tick_params(length=0)
+    for spine in ax.spines.values():
+        spine.set_visible(False)
+
+    ax.set_title(
+        "Task matrix — live headless lane",
+        loc="left",
+        fontsize=17,
+        fontweight="bold",
+        color="#e6edf3",
+        pad=34,
+    )
+
+    legend_handles = [
+        Patch(facecolor=STATUS_COLORS["pass"], label="pass"),
+        Patch(facecolor=STATUS_COLORS["partial"], label="partial"),
+        Patch(facecolor=STATUS_COLORS["fail"], label="fail"),
+        Patch(facecolor=STATUS_COLORS["unsupported"], label="unsupported (no equivalent)"),
+        # Real rows now, not a theoretical state: the competitor reports were
+        # pinned and run against the v2 matrix, so every task added since v2
+        # was never put to them. An invented zero would look identical to a
+        # measured one, so they stay blank and say why.
+        Patch(facecolor=STATUS_COLORS["not_run"], edgecolor="#30363d", label="not run"),
+    ]
+    ax.legend(
+        handles=legend_handles,
+        loc="upper left",
+        bbox_to_anchor=(0, -0.02),
+        ncol=5,
+        frameon=False,
+        fontsize=9,
+        labelcolor="#e6edf3",
+    )
+
+    output.parent.mkdir(parents=True, exist_ok=True)
+    fig.savefig(
+        output,
+        format="svg",
+        facecolor=fig.get_facecolor(),
+        metadata={"Creator": "AutoCAD MCP Pro task-matrix renderer", "Date": None},
+    )
+    plt.close(fig)
+
+    svg = output.read_text(encoding="utf-8")
+    normalized = "\n".join(line.rstrip() for line in svg.splitlines()) + "\n"
+    output.write_text(normalized, encoding="utf-8", newline="\n")
+
+
+def build_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("--input-dir", type=Path, default=DEFAULT_INPUT_DIR)
+    parser.add_argument("--output", type=Path, default=DEFAULT_OUTPUT)
+    return parser
+
+
+def main() -> int:
+    args = build_parser().parse_args()
+    render_chart(load_reports(args.input_dir), args.output)
+    print(f"Rendered task-matrix chart: {args.output}")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

benchmarks/render_perf_chart.py

@@ -0,0 +1,146 @@
+"""Render the headless performance suite as a deterministic SVG.
+
+Input: the report produced by ``benchmarks.perf_suite --out ...``
+(default: ``benchmarks/results/published/perf-ezdxf.json``).
+Output: a GitHub-readable log-scale wall-time chart per workload.
+"""
+
+from __future__ import annotations
+
+import argparse
+import json
+from pathlib import Path
+from typing import Any
+
+ROOT = Path(__file__).resolve().parents[1]
+DEFAULT_INPUT = ROOT / "benchmarks" / "results" / "published" / "perf-ezdxf.json"
+DEFAULT_OUTPUT = ROOT / "docs" / "assets" / "autocad-mcp-perf.svg"
+
+_LABELS = {
+    "create_lines_2k": "Create 2,000 lines (individual calls)",
+    "roundtrip_10k": "10,000 lines: build + DXF export + reopen",
+    "region_query_10k": "Region query over 10,000 entities",
+    "premium_pass": "Premium pass: layers + part + dims + full critique",
+}
+
+
+def load_report(path: Path) -> dict[str, Any]:
+    data = json.loads(path.read_text(encoding="utf-8"))
+    if data.get("schema_version") != "perf/1.0":
+        raise ValueError("unsupported perf report schema_version")
+    if not data.get("workloads"):
+        raise ValueError("perf report contains no workloads")
+    return data
+
+
+def _annotation(item: dict[str, Any]) -> str:
+    wall_s = item["wall_ms"] / 1000.0
+    if item["metric"] == "entities_per_second":
+        return f"{wall_s:.2f} s  ·  {item['metric_value']:,.0f} entities/s"
+    if item["metric"] == "entities_matched":
+        return f"{wall_s:.2f} s  ·  {item['metric_value']:,.0f} matched"
+    if item["metric"] == "critique_issues":
+        return f"{wall_s:.2f} s  ·  {item['metric_value']:.0f} issues"
+    return f"{wall_s:.2f} s"
+
+
+def render_chart(data: dict[str, Any], output: Path) -> None:
+    try:
+        import matplotlib
+
+        matplotlib.use("Agg")
+        import matplotlib.pyplot as plt
+    except ImportError as exc:
+        raise SystemExit(
+            'Matplotlib is required. Install it with: pip install -e ".[pdf]"'
+        ) from exc
+
+    matplotlib.rcParams["svg.hashsalt"] = "autocad-mcp-perf-v1"
+    workloads = sorted(data["workloads"], key=lambda item: item["wall_ms"])
+    labels = [_LABELS.get(item["workload_id"], item["workload_id"]) for item in workloads]
+    values = [item["wall_ms"] for item in workloads]
+
+    fig, ax = plt.subplots(figsize=(12, 4.6), constrained_layout=True)
+    fig.patch.set_facecolor("#0d1117")
+    ax.set_facecolor("#0d1117")
+    bars = ax.barh(labels, values, color="#58a6ff", height=0.58)
+
+    ax.set_xscale("log")
+    ax.set_xlabel("Wall time in ms (log scale) — lower is better", color="#e6edf3", labelpad=10)
+    ax.set_title(
+        "Headless performance — ezdxf engine",
+        loc="left",
+        fontsize=18,
+        fontweight="bold",
+        color="#e6edf3",
+        pad=28,
+    )
+    env = data.get("environment", {})
+    ax.text(
+        0,
+        1.02,
+        f"Fixed workloads via the same backend methods the MCP tools call · "
+        f"Python {env.get('python', '?')} · {env.get('platform', '?')}",
+        transform=ax.transAxes,
+        color="#8b949e",
+        fontsize=9,
+    )
+
+    for bar, item in zip(bars, workloads, strict=True):
+        ax.text(
+            bar.get_width() * 1.12,
+            bar.get_y() + bar.get_height() / 2,
+            _annotation(item),
+            va="center",
+            color="#e6edf3",
+            fontweight="bold",
+            fontsize=9,
+        )
+
+    ax.set_xlim(right=max(values) * 8)
+    ax.text(
+        0,
+        -0.24,
+        "Self-measurement only: competitor servers would pay extra stdio serialization cost in-process runs do not. "
+        "Reproduce: python -m benchmarks.perf_suite",
+        transform=ax.transAxes,
+        color="#8b949e",
+        fontsize=9,
+    )
+    ax.grid(axis="x", color="#30363d", linewidth=0.8, alpha=0.8)
+    ax.set_axisbelow(True)
+    ax.tick_params(axis="x", colors="#8b949e")
+    ax.tick_params(axis="y", colors="#e6edf3", length=0, pad=8)
+    for spine in ax.spines.values():
+        spine.set_visible(False)
+
+    output.parent.mkdir(parents=True, exist_ok=True)
+    fig.savefig(
+        output,
+        format="svg",
+        facecolor=fig.get_facecolor(),
+        metadata={"Creator": "AutoCAD MCP Pro perf renderer", "Date": None},
+    )
+    plt.close(fig)
+
+    svg = output.read_text(encoding="utf-8")
+    normalized = "\n".join(line.rstrip() for line in svg.splitlines()) + "\n"
+    output.write_text(normalized, encoding="utf-8", newline="\n")
+
+
+def build_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("--input", type=Path, default=DEFAULT_INPUT)
+    parser.add_argument("--output", type=Path, default=DEFAULT_OUTPUT)
+    return parser
+
+
+def main() -> int:
+    args = build_parser().parse_args()
+    render_chart(load_report(args.input), args.output)
+    print(f"Rendered perf chart: {args.output}")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

benchmarks/results/published/ab-v1.3.0-vs-v1.4.0.json

@@ -0,0 +1,140 @@
+{
+  "summary": {
+    "baseline_ref": "v1.3.0",
+    "total": 21,
+    "old_pass": 21,
+    "new_pass": 21,
+    "old_pct": 100.0,
+    "new_pct": 100.0,
+    "fixed": 0,
+    "regressed": 0
+  },
+  "rows": [
+    {
+      "check": "core_line_length",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "core_circle_radius",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "core_layer_create",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "core_polyline_closed",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "core_linear_dim",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "core_save_dxf_roundtrip",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "dim_aligned_no_error",
+      "category": "Dimensions",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "dim_angular_no_error",
+      "category": "Dimensions",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "array_polar_360_distinct",
+      "category": "Modify",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "point_intersection_line_line",
+      "category": "Geometry",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "point_tangent_external",
+      "category": "Geometry",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "arc_has_length",
+      "category": "Query",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "arc_select_by_length",
+      "category": "Query",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "ezdxf_bounding_box",
+      "category": "Query",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "mtext_rotation_roundtrip",
+      "category": "Entities",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "screenshot_png",
+      "category": "Render",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "dim_overlap_critique_fires",
+      "category": "Quality gate",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "iso13567_dim_layer",
+      "category": "Quality gate",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "construction_left_iso_caught",
+      "category": "Quality gate",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "gear_no_self_overlap",
+      "category": "Engineering",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "center_linetype_applied",
+      "category": "Entities",
+      "old": "pass",
+      "new": "pass"
+    }
+  ]
+}

benchmarks/results/published/ab-v1.4.0-vs-v1.5.0.json

@@ -0,0 +1,170 @@
+{
+  "summary": {
+    "baseline_ref": "v1.4.0",
+    "total": 26,
+    "old_pass": 21,
+    "new_pass": 26,
+    "old_pct": 80.8,
+    "new_pct": 100.0,
+    "fixed": 5,
+    "regressed": 0
+  },
+  "rows": [
+    {
+      "check": "core_line_length",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "core_circle_radius",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "core_layer_create",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "core_polyline_closed",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "core_linear_dim",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "core_save_dxf_roundtrip",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "dim_aligned_no_error",
+      "category": "Dimensions",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "dim_angular_no_error",
+      "category": "Dimensions",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "array_polar_360_distinct",
+      "category": "Modify",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "point_intersection_line_line",
+      "category": "Geometry",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "point_tangent_external",
+      "category": "Geometry",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "arc_has_length",
+      "category": "Query",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "arc_select_by_length",
+      "category": "Query",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "ezdxf_bounding_box",
+      "category": "Query",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "mtext_rotation_roundtrip",
+      "category": "Entities",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "screenshot_png",
+      "category": "Render",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "dim_overlap_critique_fires",
+      "category": "Quality gate",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "iso13567_dim_layer",
+      "category": "Quality gate",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "construction_left_iso_caught",
+      "category": "Quality gate",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "gear_no_self_overlap",
+      "category": "Engineering",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "center_linetype_applied",
+      "category": "Entities",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "hatch_area_subtracts_its_island",
+      "category": "Measurement",
+      "old": "miss",
+      "new": "pass"
+    },
+    {
+      "check": "boundary_area_agrees_with_measure",
+      "category": "Measurement",
+      "old": "miss",
+      "new": "pass"
+    },
+    {
+      "check": "two_vertex_circle_has_area",
+      "category": "Measurement",
+      "old": "miss",
+      "new": "pass"
+    },
+    {
+      "check": "diameter_dim_measures_the_diameter",
+      "category": "Dimensions",
+      "old": "fail",
+      "new": "pass"
+    },
+    {
+      "check": "radius_dim_ignores_the_leader_length",
+      "category": "Dimensions",
+      "old": "fail",
+      "new": "pass"
+    }
+  ]
+}

benchmarks/results/published/ab-v1.4.0-vs-v1.5.1.json

@@ -0,0 +1,170 @@
+{
+  "summary": {
+    "baseline_ref": "v1.4.0",
+    "total": 26,
+    "old_pass": 21,
+    "new_pass": 26,
+    "old_pct": 80.8,
+    "new_pct": 100.0,
+    "fixed": 5,
+    "regressed": 0
+  },
+  "rows": [
+    {
+      "check": "core_line_length",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "core_circle_radius",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "core_layer_create",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "core_polyline_closed",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "core_linear_dim",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "core_save_dxf_roundtrip",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "dim_aligned_no_error",
+      "category": "Dimensions",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "dim_angular_no_error",
+      "category": "Dimensions",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "array_polar_360_distinct",
+      "category": "Modify",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "point_intersection_line_line",
+      "category": "Geometry",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "point_tangent_external",
+      "category": "Geometry",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "arc_has_length",
+      "category": "Query",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "arc_select_by_length",
+      "category": "Query",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "ezdxf_bounding_box",
+      "category": "Query",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "mtext_rotation_roundtrip",
+      "category": "Entities",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "screenshot_png",
+      "category": "Render",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "dim_overlap_critique_fires",
+      "category": "Quality gate",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "iso13567_dim_layer",
+      "category": "Quality gate",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "construction_left_iso_caught",
+      "category": "Quality gate",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "gear_no_self_overlap",
+      "category": "Engineering",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "center_linetype_applied",
+      "category": "Entities",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "hatch_area_subtracts_its_island",
+      "category": "Measurement",
+      "old": "miss",
+      "new": "pass"
+    },
+    {
+      "check": "boundary_area_agrees_with_measure",
+      "category": "Measurement",
+      "old": "miss",
+      "new": "pass"
+    },
+    {
+      "check": "two_vertex_circle_has_area",
+      "category": "Measurement",
+      "old": "miss",
+      "new": "pass"
+    },
+    {
+      "check": "diameter_dim_measures_the_diameter",
+      "category": "Dimensions",
+      "old": "fail",
+      "new": "pass"
+    },
+    {
+      "check": "radius_dim_ignores_the_leader_length",
+      "category": "Dimensions",
+      "old": "fail",
+      "new": "pass"
+    }
+  ]
+}

benchmarks/results/published/ab-v1.5.0-vs-v1.5.1.json

@@ -0,0 +1,170 @@
+{
+  "summary": {
+    "baseline_ref": "v1.5.0",
+    "total": 26,
+    "old_pass": 24,
+    "new_pass": 26,
+    "old_pct": 92.3,
+    "new_pct": 100.0,
+    "fixed": 2,
+    "regressed": 0
+  },
+  "rows": [
+    {
+      "check": "core_line_length",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "core_circle_radius",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "core_layer_create",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "core_polyline_closed",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "core_linear_dim",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "core_save_dxf_roundtrip",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "dim_aligned_no_error",
+      "category": "Dimensions",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "dim_angular_no_error",
+      "category": "Dimensions",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "array_polar_360_distinct",
+      "category": "Modify",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "point_intersection_line_line",
+      "category": "Geometry",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "point_tangent_external",
+      "category": "Geometry",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "arc_has_length",
+      "category": "Query",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "arc_select_by_length",
+      "category": "Query",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "ezdxf_bounding_box",
+      "category": "Query",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "mtext_rotation_roundtrip",
+      "category": "Entities",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "screenshot_png",
+      "category": "Render",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "dim_overlap_critique_fires",
+      "category": "Quality gate",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "iso13567_dim_layer",
+      "category": "Quality gate",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "construction_left_iso_caught",
+      "category": "Quality gate",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "gear_no_self_overlap",
+      "category": "Engineering",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "center_linetype_applied",
+      "category": "Entities",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "hatch_area_subtracts_its_island",
+      "category": "Measurement",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "boundary_area_agrees_with_measure",
+      "category": "Measurement",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "two_vertex_circle_has_area",
+      "category": "Measurement",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "diameter_dim_measures_the_diameter",
+      "category": "Dimensions",
+      "old": "fail",
+      "new": "pass"
+    },
+    {
+      "check": "radius_dim_ignores_the_leader_length",
+      "category": "Dimensions",
+      "old": "fail",
+      "new": "pass"
+    }
+  ]
+}

benchmarks/results/published/ab-v1.5.1-vs-v1.6.0.json

@@ -0,0 +1,302 @@
+{
+  "summary": {
+    "baseline_ref": "v1.5.1",
+    "total": 48,
+    "old_pass": 26,
+    "new_pass": 48,
+    "old_pct": 54.2,
+    "new_pct": 100.0,
+    "fixed": 22,
+    "regressed": 0
+  },
+  "rows": [
+    {
+      "check": "core_line_length",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "core_circle_radius",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "core_layer_create",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "core_polyline_closed",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "core_linear_dim",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "core_save_dxf_roundtrip",
+      "category": "Core",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "dim_aligned_no_error",
+      "category": "Dimensions",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "dim_angular_no_error",
+      "category": "Dimensions",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "array_polar_360_distinct",
+      "category": "Modify",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "point_intersection_line_line",
+      "category": "Geometry",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "point_tangent_external",
+      "category": "Geometry",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "arc_has_length",
+      "category": "Query",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "arc_select_by_length",
+      "category": "Query",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "ezdxf_bounding_box",
+      "category": "Query",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "mtext_rotation_roundtrip",
+      "category": "Entities",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "screenshot_png",
+      "category": "Render",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "dim_overlap_critique_fires",
+      "category": "Quality gate",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "iso13567_dim_layer",
+      "category": "Quality gate",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "construction_left_iso_caught",
+      "category": "Quality gate",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "gear_no_self_overlap",
+      "category": "Engineering",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "center_linetype_applied",
+      "category": "Entities",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "hatch_area_subtracts_its_island",
+      "category": "Measurement",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "boundary_area_agrees_with_measure",
+      "category": "Measurement",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "two_vertex_circle_has_area",
+      "category": "Measurement",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "diameter_dim_measures_the_diameter",
+      "category": "Dimensions",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "radius_dim_ignores_the_leader_length",
+      "category": "Dimensions",
+      "old": "pass",
+      "new": "pass"
+    },
+    {
+      "check": "pid_block_define_attdef_roundtrip",
+      "category": "P&ID",
+      "old": "miss",
+      "new": "pass"
+    },
+    {
+      "check": "pid_tag_parse_fic",
+      "category": "P&ID",
+      "old": "miss",
+      "new": "pass"
+    },
+    {
+      "check": "pid_graph_edge_count",
+      "category": "P&ID",
+      "old": "miss",
+      "new": "pass"
+    },
+    {
+      "check": "settings_dimstyle_iso25_values",
+      "category": "Settings",
+      "old": "miss",
+      "new": "pass"
+    },
+    {
+      "check": "settings_layer_state_roundtrip",
+      "category": "Settings",
+      "old": "miss",
+      "new": "pass"
+    },
+    {
+      "check": "settings_pdf_mediabox_a3",
+      "category": "Settings",
+      "old": "miss",
+      "new": "pass"
+    },
+    {
+      "check": "mech_part_roundtrip",
+      "category": "Mechanical",
+      "old": "miss",
+      "new": "pass"
+    },
+    {
+      "check": "mech_section_hatch_area",
+      "category": "Mechanical",
+      "old": "miss",
+      "new": "pass"
+    },
+    {
+      "check": "mech_iso286_on_dimension",
+      "category": "Mechanical",
+      "old": "miss",
+      "new": "pass"
+    },
+    {
+      "check": "mech_thread_unrepresented_is_caught",
+      "category": "Mechanical",
+      "old": "miss",
+      "new": "pass"
+    },
+    {
+      "check": "std_part_iso4014_m12",
+      "category": "Mechanical",
+      "old": "miss",
+      "new": "pass"
+    },
+    {
+      "check": "sheet_frame_iso5457_a3",
+      "category": "Sheet",
+      "old": "miss",
+      "new": "pass"
+    },
+    {
+      "check": "bom_balloon_link",
+      "category": "Sheet",
+      "old": "miss",
+      "new": "pass"
+    },
+    {
+      "check": "arch_junction_l_t_x",
+      "category": "Architecture",
+      "old": "miss",
+      "new": "pass"
+    },
+    {
+      "check": "arch_room_area_net",
+      "category": "Architecture",
+      "old": "miss",
+      "new": "pass"
+    },
+    {
+      "check": "arch_opening_cuts_wall",
+      "category": "Architecture",
+      "old": "miss",
+      "new": "pass"
+    },
+    {
+      "check": "arch_rooms_detect_foreign",
+      "category": "Architecture",
+      "old": "miss",
+      "new": "pass"
+    },
+    {
+      "check": "scale_check_detects_schematic",
+      "category": "Understanding",
+      "old": "miss",
+      "new": "pass"
+    },
+    {
+      "check": "pipe_takeoff_rmst_exact",
+      "category": "Understanding",
+      "old": "miss",
+      "new": "pass"
+    },
+    {
+      "check": "cable_takeoff_roundup",
+      "category": "Understanding",
+      "old": "miss",
+      "new": "pass"
+    },
+    {
+      "check": "diff_detects_known_edits",
+      "category": "Understanding",
+      "old": "miss",
+      "new": "pass"
+    },
+    {
+      "check": "topology_known_defects",
+      "category": "Understanding",
+      "old": "miss",
+      "new": "pass"
+    }
+  ]
+}

benchmarks/results/published/autocad-mcp-pro.json

@@ -0,0 +1,816 @@
+{
+  "adapter": "autocad-mcp-pro",
+  "adapter_metadata": {
+    "backend": "ezdxf",
+    "capabilities": {
+      "backend": "ezdxf",
+      "features": {
+        "audit_detail": {
+          "mode": "native",
+          "reason": null,
+          "supported": true
+        },
+        "boundary_trace": {
+          "mode": "computed",
+          "reason": "straight_edges_split_at_intersections;curved_edges_not_split",
+          "supported": true
+        },
+        "chspace": {
+          "mode": "computed",
+          "reason": "top_view_untwisted_viewports_only;dimensions_refused_unless_frozen;acis_proxy_table_refused;viewport_clipping_reported_not_applied",
+          "supported": true
+        },
+        "delivery": {
+          "mode": "shared",
+          "reason": null,
+          "supported": true
+        },
+        "documents": {
+          "mode": "registry",
+          "reason": null,
+          "supported": true
+        },
+        "drawing_2d": {
+          "mode": "native",
+          "reason": null,
+          "supported": true
+        },
+        "dwg": {
+          "mode": null,
+          "reason": "no_dwg_writer_requires_live_autocad",
+          "supported": false
+        },
+        "dwg_write": {
+          "mode": null,
+          "reason": "requires_oda_file_converter:https://www.opendesign.com/guestfiles/oda_file_converter",
+          "supported": false
+        },
+        "dwgprops": {
+          "mode": null,
+          "reason": "summary_fields_need_live_autocad;custom_properties_need_r2004_or_newer",
+          "supported": false
+        },
+        "dwt_write": {
+          "mode": null,
+          "reason": "dwt_is_a_dwg_container_requires_live_autocad",
+          "supported": false
+        },
+        "dxf": {
+          "mode": "native",
+          "reason": null,
+          "supported": true
+        },
+        "explode_opaque_members": {
+          "mode": null,
+          "reason": "ezdxf_cannot_transform:OLE2FRAME,VIEWPORT,ACAD_PROXY_ENTITY_without_proxy_graphic;refused_before_writing",
+          "supported": false
+        },
+        "handle_overlay": {
+          "mode": "rendered",
+          "reason": null,
+          "supported": true
+        },
+        "hatch_edge_paths": {
+          "mode": "native",
+          "reason": null,
+          "supported": true
+        },
+        "interactive_prompt": {
+          "mode": null,
+          "reason": "no_operator_to_prompt_headlessly",
+          "supported": false
+        },
+        "layer_states": {
+          "mode": "xrecord",
+          "reason": "portable_acadmcp_xrecord;not_listed_in_autocad_layer_states_manager",
+          "supported": true
+        },
+        "lisp": {
+          "mode": null,
+          "reason": "live_com_only",
+          "supported": false
+        },
+        "live_application": {
+          "mode": null,
+          "reason": "headless_engine_has_no_application_to_launch_or_attach",
+          "supported": false
+        },
+        "measure_area_acis": {
+          "mode": null,
+          "reason": "acis_evaluation_requires_live_autocad",
+          "supported": false
+        },
+        "mleader": {
+          "mode": "composite",
+          "reason": null,
+          "supported": true
+        },
+        "mtext_background_color": {
+          "mode": "native",
+          "reason": null,
+          "supported": true
+        },
+        "named_views": {
+          "mode": "vport_active",
+          "reason": "restore_sets_the_view_the_file_opens_on;no_live_display",
+          "supported": true
+        },
+        "ocs_normalized": {
+          "mode": "wcs",
+          "reason": "reported_xy_is_wcs;z_component_not_reported;text_rotation_stays_in_entity_frame;hatch_boundaries_not_reported",
+          "supported": true
+        },
+        "ocs_tilted_plane": {
+          "mode": null,
+          "reason": "2d_xy_cannot_address_a_tilted_plane",
+          "supported": false
+        },
+        "paper_space": {
+          "mode": "native",
+          "reason": null,
+          "supported": true
+        },
+        "pdf": {
+          "mode": "rendered",
+          "reason": null,
+          "supported": true
+        },
+        "png": {
+          "mode": "rendered",
+          "reason": null,
+          "supported": true
+        },
+        "preferences": {
+          "mode": null,
+          "reason": "preferences_live_in_the_running_application_not_in_a_file",
+          "supported": false
+        },
+        "preflight": {
+          "mode": "shared",
+          "reason": null,
+          "supported": true
+        },
+        "refiner": {
+          "mode": "shared",
+          "reason": null,
+          "supported": true
+        },
+        "registry_sysvar": {
+          "mode": null,
+          "reason": "registry_saved_variables_have_no_home_in_a_file",
+          "supported": false
+        },
+        "revcloud": {
+          "mode": "native",
+          "reason": "ezdxf_revcloud_helper",
+          "supported": true
+        },
+        "solid_3d": {
+          "mode": null,
+          "reason": "acis_generation_requires_live_autocad",
+          "supported": false
+        },
+        "table": {
+          "mode": "composite",
+          "reason": null,
+          "supported": true
+        },
+        "transactions": {
+          "mode": "snapshot",
+          "reason": null,
+          "supported": true
+        },
+        "ucs": {
+          "mode": "stored_not_interpreted",
+          "reason": "tool_coordinates_stay_wcs",
+          "supported": true
+        },
+        "undo_history": {
+          "mode": null,
+          "reason": "set_EZDXF_UNDO_DEPTH_to_enable",
+          "supported": false
+        },
+        "viewport_render": {
+          "mode": "rendered",
+          "reason": "viewport_borders_not_drawn",
+          "supported": true
+        },
+        "wipeout": {
+          "mode": "native",
+          "reason": null,
+          "supported": true
+        },
+        "xlsx_write": {
+          "mode": "openpyxl",
+          "reason": null,
+          "supported": true
+        },
+        "xref_live": {
+          "mode": null,
+          "reason": "reload_and_bind_need_a_live_seat;list_detach_path_are_headless",
+          "supported": false
+        }
+      }
+    }
+  },
+  "environment": {
+    "implementation": "CPython",
+    "machine": "AMD64",
+    "platform": "Windows-10-10.0.26200-SP0",
+    "python": "3.11.15"
+  },
+  "generated_at": "2026-09-24T20:58:06.608758+00:00",
+  "git_sha": "554daff8d08c7d891974e55db046e7c70c15e185",
+  "matrix": "v7",
+  "results": [
+    {
+      "artifacts": [],
+      "duration_ms": 2.71,
+      "message": "",
+      "metrics": {
+        "line_length": 5.0
+      },
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "core_geometry"
+    },
+    {
+      "artifacts": [],
+      "duration_ms": 1.92,
+      "message": "",
+      "metrics": {},
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "modify_query"
+    },
+    {
+      "artifacts": [],
+      "duration_ms": 3.38,
+      "message": "",
+      "metrics": {},
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "layers_linetypes"
+    },
+    {
+      "artifacts": [],
+      "duration_ms": 24.95,
+      "message": "",
+      "metrics": {
+        "entity_type": "DIMENSION"
+      },
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "dimensions"
+    },
+    {
+      "artifacts": [],
+      "duration_ms": 3.64,
+      "message": "",
+      "metrics": {
+        "representations": [
+          "composite",
+          "composite"
+        ]
+      },
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "table_mleader"
+    },
+    {
+      "artifacts": [],
+      "duration_ms": 8.37,
+      "message": "",
+      "metrics": {
+        "entity_count": 0
+      },
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "transactions"
+    },
+    {
+      "artifacts": [],
+      "duration_ms": 0.85,
+      "message": "",
+      "metrics": {},
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "preflight"
+    },
+    {
+      "artifacts": [],
+      "duration_ms": 17.45,
+      "message": "",
+      "metrics": {
+        "final_score": 100.0,
+        "initial_score": 92.0,
+        "remaining_issues": [],
+        "rounds": [
+          {
+            "actions": [
+              {
+                "detail": {
+                  "deleted_handle": "3E",
+                  "kept_handle": "3D"
+                },
+                "fingerprint": "c1b87eac3cfdf11312c9b18ccf4c062e672791f7a9a6dfa3c45b6db7f9e5835e",
+                "focus": "duplicate_entities",
+                "handles": [
+                  "3D",
+                  "3E"
+                ],
+                "status": "applied"
+              }
+            ],
+            "error_count_after": 0,
+            "error_count_before": 0,
+            "number": 1,
+            "score_after": 100.0,
+            "score_before": 92.0,
+            "transaction": "committed"
+          }
+        ],
+        "status": "threshold_met"
+      },
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "quality_refiner"
+    },
+    {
+      "artifacts": [
+        {
+          "filename": "roundtrip.dxf",
+          "sha256": "28a18050aea00646f9ff7a5fdf8fe3b8783cd4cb77d71108b3834c746e7259c5",
+          "size_bytes": 18446
+        }
+      ],
+      "duration_ms": 7.21,
+      "message": "",
+      "metrics": {
+        "entity_count": 1
+      },
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "dxf_roundtrip"
+    },
+    {
+      "artifacts": [
+        {
+          "filename": "manifest.json",
+          "sha256": "7178055a030b533e83c4a914466c7474350e7728657cd624c9ebc01c753d9e13",
+          "size_bytes": 7929
+        }
+      ],
+      "duration_ms": 274.87,
+      "message": "",
+      "metrics": {
+        "score": {
+          "errors": 0,
+          "grade": "A",
+          "info": 0,
+          "invalidity_ratio": 0.0,
+          "score": 100.0,
+          "warnings": 0
+        }
+      },
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "auditable_delivery"
+    },
+    {
+      "artifacts": [],
+      "duration_ms": 699.92,
+      "message": "",
+      "metrics": {
+        "ranks": {
+          "BPOLY": 1,
+          "CHSPACE": 1,
+          "FILLET": 1,
+          "OVERKILL": 1,
+          "QSELECT": 1,
+          "WBLOCK": 1
+        },
+        "top_n": 3
+      },
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "tool_discovery"
+    },
+    {
+      "artifacts": [],
+      "duration_ms": 86.79,
+      "message": "",
+      "metrics": {
+        "advertised_tools": 2,
+        "catalog_tokens": 83921,
+        "catalog_tools": 242,
+        "ceiling": 2000,
+        "discovery_tokens": 356,
+        "reduction_x": 235.7,
+        "tokenizer": "ratio/v1 (estimate)"
+      },
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "token_budget"
+    },
+    {
+      "artifacts": [],
+      "duration_ms": 7.47,
+      "message": "",
+      "metrics": {
+        "area_ignoring_islands": 400.0,
+        "expected_filled": 300.0,
+        "filled_area": 300.0,
+        "hatch_style": "outer",
+        "path_count": 2
+      },
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "hatch_islands"
+    },
+    {
+      "artifacts": [],
+      "duration_ms": 26.1,
+      "message": "",
+      "metrics": {
+        "bounding_box": 3,
+        "by_layer": 1,
+        "crossing": 2,
+        "polygon": 1,
+        "window": 1
+      },
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "selection_filter"
+    },
+    {
+      "artifacts": [],
+      "duration_ms": 5.83,
+      "message": "",
+      "metrics": {
+        "boundary_agrees": true,
+        "fraction_lost_by_reading_points_back": 0.282,
+        "measured_area": 139.269908,
+        "true_area": 139.269908,
+        "vertex_shoelace_area": 100.0
+      },
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "measure_from_handle"
+    },
+    {
+      "artifacts": [],
+      "duration_ms": 58.19,
+      "message": "",
+      "metrics": {
+        "authored_line_numbers_kept": true,
+        "confidence_min": 1.0,
+        "critique_issues": 0,
+        "dangling": 0,
+        "edges": 4,
+        "instrument_index_rows": 1,
+        "line_list_rows": 4,
+        "nodes": 5,
+        "unnumbered_lines_sequenced": true
+      },
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "pid_roundtrip"
+    },
+    {
+      "artifacts": [
+        {
+          "filename": "untitled-Layout1-ansi_b.pdf",
+          "sha256": "af3c19d4d8b14fbc116ab807bb6feee9fc900fc114e57cd6feb658a6c0dabffb",
+          "size_bytes": 1287
+        },
+        {
+          "filename": "untitled-Layout1-iso_a3.pdf",
+          "sha256": "8d1d1ed505903b6f692ed6e91e9f52577c2c78db3bc2942b949ea4a3d73c9b01",
+          "size_bytes": 1287
+        }
+      ],
+      "duration_ms": 65.46,
+      "message": "",
+      "metrics": {
+        "mediabox_mm": [
+          420.0,
+          297.0
+        ],
+        "mediabox_mm_before": [
+          432.0,
+          279.0
+        ],
+        "orientation": "landscape",
+        "paper": "ISO_A3",
+        "pdf_bytes": 1287,
+        "plot_style_known": true,
+        "size_mm_changed": [
+          [
+            432.0,
+            279.0
+          ],
+          [
+            420.0,
+            297.0
+          ]
+        ],
+        "size_mm_listed": [
+          420.0,
+          297.0
+        ]
+      },
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "page_setup_truth"
+    },
+    {
+      "artifacts": [
+        {
+          "filename": "mech_assembly.dxf",
+          "sha256": "407dcbed3eb17be7f9d72dda2c1951e8f97fa3fb6090713440404a3f1497d1b2",
+          "size_bytes": 101158
+        }
+      ],
+      "duration_ms": 487.19,
+      "message": "",
+      "metrics": {
+        "critique_focuses": [],
+        "critique_issues": 0,
+        "fasteners": 4,
+        "grade": "A",
+        "invalidity_ratio": 0.0,
+        "parts_list_rows": 2,
+        "score": 100.0,
+        "validator_findings": []
+      },
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "mech_assembly"
+    },
+    {
+      "artifacts": [
+        {
+          "filename": "arch_roundtrip.dxf",
+          "sha256": "ebec378ef28670e091e651b4130a6eac5a0d2fb480d60f9335b37de28ea713c7",
+          "size_bytes": 82829
+        }
+      ],
+      "duration_ms": 982.07,
+      "message": "",
+      "metrics": {
+        "confidence_min": 1.0,
+        "critique_focuses": [],
+        "critique_issues": 0,
+        "door_tags": [
+          "D1",
+          "D2"
+        ],
+        "faces_detected": 2,
+        "grade": "A",
+        "invalidity_ratio": 0.0,
+        "omitted": [],
+        "rooms": {
+          "01": {
+            "agrees": true,
+            "detected_mm2": 27743750.0,
+            "hand_mm2": 27743750.0,
+            "label_mm2": 27743750.0
+          },
+          "02": {
+            "agrees": true,
+            "detected_mm2": 21993750.0,
+            "hand_mm2": 21993750.0,
+            "label_mm2": 21993750.0
+          }
+        },
+        "score": 100.0,
+        "validator_findings": [],
+        "window_tags": [
+          "W1",
+          "W2"
+        ]
+      },
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "arch_roundtrip"
+    },
+    {
+      "artifacts": [
+        {
+          "filename": "pid.dxf",
+          "sha256": "94dbdc026878927560a6c81e2283a7d2a26fbe6a398475d415c6383728c46672",
+          "size_bytes": 33795
+        },
+        {
+          "filename": "layout.dxf",
+          "sha256": "37963e237f27f9f495b30d7c0b3bf7f4eff54ff4fec9665f34ab50ddc3f3c7a7",
+          "size_bytes": 40503
+        }
+      ],
+      "duration_ms": 614.2,
+      "message": "",
+      "metrics": {
+        "cable_mismatch": [],
+        "length_source": "layout",
+        "loads_checked": 4,
+        "pipe_mismatch": [],
+        "runs_checked": 9,
+        "scale_verdict": "schematic",
+        "within_10pct": 0.21818181818181817
+      },
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "takeoff_roundtrip"
+    },
+    {
+      "artifacts": [
+        {
+          "filename": "layout.dxf",
+          "sha256": "ff728965a5698cf9ddf9d9a01cfa244102d183065a149488d4d29dbcee404e85",
+          "size_bytes": 40503
+        },
+        {
+          "filename": "pid.dxf",
+          "sha256": "de4f1ab4102d220efa7167b192b8fdaf9d57cbf300241e945c16967770401cd8",
+          "size_bytes": 33795
+        }
+      ],
+      "duration_ms": 311.97,
+      "message": "",
+      "metrics": {
+        "clusters": 2,
+        "copies_separated": true,
+        "misread_layers": {},
+        "outlier_found": true,
+        "units": {
+          "agree": false,
+          "confidence": 0.76,
+          "declared": {
+            "code": 1,
+            "label": "Inches",
+            "name": "in"
+          },
+          "evidence": [
+            {
+              "as": {
+                "cm": 2.5,
+                "ft": 76.2,
+                "in": 6.35,
+                "m": 250.0,
+                "mm": 0.25
+              },
+              "band": [
+                0.0018,
+                4.0
+              ],
+              "band_unit": "m",
+              "count": 26,
+              "informative": true,
+              "kind": "text_height",
+              "plausible": [
+                "mm",
+                "cm"
+              ],
+              "value": 250.0,
+              "weight": 0.5
+            },
+            {
+              "as": {
+                "cm": 2.0,
+                "ft": 60.96,
+                "in": 5.08,
+                "m": 200.0,
+                "mm": 0.2
+              },
+              "band": [
+                0.05,
+                1.0
+              ],
+              "band_unit": "m",
+              "count": 24,
+              "informative": true,
+              "kind": "wall_thickness",
+              "plausible": [
+                "mm"
+              ],
+              "value": 200.0,
+              "weight": 1.0
+            },
+            {
+              "as": {
+                "cm": 21480.0,
+                "ft": 19955572.992000002,
+                "in": 138580.368,
+                "m": 214800000.0,
+                "mm": 214.79999999999998
+              },
+              "band": [
+                1.0,
+                5000.0
+              ],
+              "band_unit": "m2",
+              "count": 4,
+              "informative": true,
+              "kind": "room_area",
+              "plausible": [
+                "mm"
+              ],
+              "value": 214800000.0,
+              "weight": 1.0
+            },
+            {
+              "as": {
+                "cm": 1364.0,
+                "ft": 41574.72,
+                "in": 3464.56,
+                "m": 136400.0,
+                "mm": 136.4
+              },
+              "band": [
+                0.01,
+                2000.0
+              ],
+              "band_unit": "m",
+              "count": 80,
+              "informative": true,
+              "kind": "overall_size",
+              "plausible": [
+                "mm",
+                "cm"
+              ],
+              "value": 136400.0,
+              "weight": 0.25
+            }
+          ],
+          "inferred": "mm",
+          "mm_per_unit": 1.0,
+          "scores": {
+            "cm": 0.75,
+            "ft": 0,
+            "in": 0.5,
+            "m": 0,
+            "mm": 2.75
+          },
+          "warning": "INSUNITS declares Inches (1) but the geometry reads as mm: text_height 250 = 0.25 m as mm, 6.35 m as in; wall_thickness 200 = 0.2 m as mm, 5.08 m as in; room_area 2.148e+08 = 214.8 m2 as mm, 1.386e+05 m2 as in; overall_size 136400 = 136.4 m as mm, 3465 m as in. Lengths are measured in mm; the header is not changed."
+        },
+        "units_flagged": true
+      },
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "understand_foreign"
+    }
+  ],
+  "schema_version": "2.0",
+  "summary": {
+    "attempted": 21,
+    "coverage_percent": 100.0,
+    "passed": 21,
+    "score": 100.0,
+    "supported": 21,
+    "unsupported": 0
+  },
+  "timeout_seconds": 30.0
+}

benchmarks/results/published/beiming183-autocad-mcp.json

@@ -0,0 +1,191 @@
+{
+  "adapter": "beiming183-autocad-mcp",
+  "adapter_metadata": {
+    "backend": "ezdxf",
+    "kind": "mcp-stdio-blackbox",
+    "pinned_sha": "11f7c47e5038796a20451b38b23032e625b5aa26",
+    "repo": "https://github.com/beiming183-cloud/AutoCAD-MCP.git",
+    "tools_discovered": [
+      "annotation",
+      "block",
+      "drawing",
+      "entity",
+      "job",
+      "layer",
+      "pid",
+      "product",
+      "solid",
+      "system",
+      "transaction",
+      "view"
+    ]
+  },
+  "environment": {
+    "implementation": "CPython",
+    "machine": "AMD64",
+    "platform": "Windows-11-10.0.26200-SP0",
+    "python": "3.14.0"
+  },
+  "generated_at": "2026-07-23T11:38:36.969519+00:00",
+  "git_sha": "4a2e9d658f051cb756f92cb8fae945c64b8cc7d4",
+  "results": [
+    {
+      "artifacts": [
+        {
+          "filename": "beiming_core_geometry.dxf",
+          "sha256": "d972b29da994b1ea8f3887eef84f2ed892a486409385b56cd444b1fe9794e337",
+          "size_bytes": 18587
+        }
+      ],
+      "duration_ms": 96.24,
+      "message": "",
+      "metrics": {
+        "circles": 1,
+        "line_length": 5.0,
+        "lines": 1
+      },
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "core_geometry"
+    },
+    {
+      "artifacts": [
+        {
+          "filename": "beiming_modify_query.dxf",
+          "sha256": "298534d8512ce62833551ab6e54c0c2a0baf18bdf7a96bd956cdf06280fb4fb8",
+          "size_bytes": 18473
+        }
+      ],
+      "duration_ms": 108.09,
+      "message": "",
+      "metrics": {},
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "modify_query"
+    },
+    {
+      "artifacts": [
+        {
+          "filename": "beiming_layers.dxf",
+          "sha256": "b401e145e97aca7011d03097190b3d0ece0a89b47d38022a81c6c4c7e250ed3d",
+          "size_bytes": 19887
+        }
+      ],
+      "duration_ms": 69.86,
+      "message": "",
+      "metrics": {},
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "layers_linetypes"
+    },
+    {
+      "artifacts": [
+        {
+          "filename": "beiming_dimensions.dxf",
+          "sha256": "8996d2ba42da66f46e79d1655405a4bf2ba72301861eeea58509cba44c408fb4",
+          "size_bytes": 20972
+        }
+      ],
+      "duration_ms": 75.55,
+      "message": "",
+      "metrics": {
+        "dimension_count": 1
+      },
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "dimensions"
+    },
+    {
+      "artifacts": [],
+      "duration_ms": 0.12,
+      "message": "no TABLE or MLEADER operation in the annotation tool (v3.10)",
+      "metrics": {},
+      "score": 0.0,
+      "status": "unsupported",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "table_mleader"
+    },
+    {
+      "artifacts": [],
+      "duration_ms": 18.99,
+      "message": "transaction begin is rejected as unsupported on the headless backend",
+      "metrics": {},
+      "score": 0.0,
+      "status": "unsupported",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "transactions"
+    },
+    {
+      "artifacts": [],
+      "duration_ms": 0.04,
+      "message": "no requirements-preflight equivalent",
+      "metrics": {},
+      "score": 0.0,
+      "status": "unsupported",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "preflight"
+    },
+    {
+      "artifacts": [],
+      "duration_ms": 0.02,
+      "message": "audits detect issues but there is no automated repair loop",
+      "metrics": {},
+      "score": 0.0,
+      "status": "unsupported",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "quality_refiner"
+    },
+    {
+      "artifacts": [
+        {
+          "filename": "beiming_roundtrip.dxf",
+          "sha256": "79d7bdc1e66e506dd2ecf66fbf030839242c77870021ccbfe3c819ad394695ce",
+          "size_bytes": 18474
+        }
+      ],
+      "duration_ms": 69.95,
+      "message": "",
+      "metrics": {
+        "entity_count": 1
+      },
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "dxf_roundtrip"
+    },
+    {
+      "artifacts": [],
+      "duration_ms": 0.06,
+      "message": "drawing.deliver is documented as File-IPC only (not headless)",
+      "metrics": {},
+      "score": 0.0,
+      "status": "unsupported",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "auditable_delivery"
+    }
+  ],
+  "schema_version": "2.0",
+  "summary": {
+    "attempted": 10,
+    "coverage_percent": 50.0,
+    "passed": 5,
+    "score": 50.0,
+    "supported": 5,
+    "unsupported": 5
+  },
+  "timeout_seconds": 30.0
+}

benchmarks/results/published/perf-ezdxf.json

@@ -0,0 +1,85 @@
+{
+  "backend": "ezdxf",
+  "environment": {
+    "implementation": "CPython",
+    "machine": "AMD64",
+    "platform": "Windows-10-10.0.26200-SP0",
+    "python": "3.11.15"
+  },
+  "schema_version": "perf/1.0",
+  "workloads": [
+    {
+      "description": "Create 2,000 lines through individual backend calls",
+      "detail": {
+        "entity_count": 2000
+      },
+      "metric": "entities_per_second",
+      "wall_ms": 306.1,
+      "workload_id": "create_lines_2k",
+      "runs_ms": [
+        287.6,
+        373.6,
+        298.2,
+        425.1,
+        306.1
+      ],
+      "metric_value": 6533.8
+    },
+    {
+      "description": "Create 10,000 lines, export DXF, reopen and verify",
+      "detail": {
+        "build_ms": 2149.4,
+        "entity_count": 10000,
+        "export_ms": 516.6,
+        "file_bytes": 1369662,
+        "reopen_ms": 535.2
+      },
+      "metric": "entities_per_second",
+      "wall_ms": 2553.5,
+      "workload_id": "roundtrip_10k",
+      "runs_ms": [
+        3201.3,
+        2550.0,
+        3118.3,
+        2553.5,
+        2289.4
+      ],
+      "metric_value": 3916.2
+    },
+    {
+      "description": "Crossing-selection region query over 10,000 entities",
+      "detail": {
+        "entity_count": 10000
+      },
+      "metric": "entities_matched",
+      "metric_value": 2500.0,
+      "wall_ms": 712.2,
+      "workload_id": "region_query_10k",
+      "runs_ms": [
+        712.2,
+        806.7,
+        295.1,
+        836.4,
+        300.6
+      ]
+    },
+    {
+      "description": "Plate with hole: ISO layers, geometry, dimensions and full critique",
+      "detail": {
+        "entities": 7
+      },
+      "metric": "critique_issues",
+      "metric_value": 0.0,
+      "wall_ms": 65.3,
+      "workload_id": "premium_pass",
+      "runs_ms": [
+        76.3,
+        65.3,
+        36.9,
+        83.8,
+        41.3
+      ]
+    }
+  ],
+  "aggregation": "median of 5 default-configuration runs, one machine, one interpreter"
+}

benchmarks/results/published/perf-v1.4.0-vs-v1.6.0.json

@@ -0,0 +1,142 @@
+{
+  "schema_version": "perf-ab/1.0",
+  "method": "benchmarks/perf_suite.py of 1.6.0 run against each tree's own code with one CPython 3.11.15 and one ezdxf, five rounds, the three configurations alternating within a round; medians of wall_ms. v1.4.0 had no perf suite; the 1.6.0 script drives the same backend methods.",
+  "environment": {
+    "implementation": "CPython",
+    "machine": "AMD64",
+    "platform": "Windows-10-10.0.26200-SP0",
+    "python": "3.11.15"
+  },
+  "medians_ms": {
+    "v1.4.0": {
+      "create_lines_2k": 244.5,
+      "roundtrip_10k": 1847.9,
+      "region_query_10k": 665.2,
+      "premium_pass": 150.6
+    },
+    "v1.6.0": {
+      "create_lines_2k": 306.1,
+      "roundtrip_10k": 2553.5,
+      "region_query_10k": 712.2,
+      "premium_pass": 65.3
+    },
+    "v1.6.0 EZDXF_CALL_TIMEOUT=0": {
+      "create_lines_2k": 284.9,
+      "roundtrip_10k": 2216.4,
+      "region_query_10k": 783.9,
+      "premium_pass": 69.9
+    }
+  },
+  "ratios_to_v1_4_0": {
+    "v1.6.0": {
+      "create_lines_2k": 1.25,
+      "roundtrip_10k": 1.38,
+      "region_query_10k": 1.07,
+      "premium_pass": 0.43
+    },
+    "v1.6.0 EZDXF_CALL_TIMEOUT=0": {
+      "create_lines_2k": 1.17,
+      "roundtrip_10k": 1.2,
+      "region_query_10k": 1.18,
+      "premium_pass": 0.46
+    }
+  },
+  "runs": {
+    "v1.4.0": [
+      {
+        "create_lines_2k": 244.5,
+        "roundtrip_10k": 1936.8,
+        "region_query_10k": 670.3,
+        "premium_pass": 160.3
+      },
+      {
+        "create_lines_2k": 221.9,
+        "roundtrip_10k": 1592.5,
+        "region_query_10k": 638.2,
+        "premium_pass": 150.6
+      },
+      {
+        "create_lines_2k": 236.7,
+        "roundtrip_10k": 1706.6,
+        "region_query_10k": 927.2,
+        "premium_pass": 140.2
+      },
+      {
+        "create_lines_2k": 261.0,
+        "roundtrip_10k": 1979.2,
+        "region_query_10k": 665.2,
+        "premium_pass": 191.4
+      },
+      {
+        "create_lines_2k": 308.4,
+        "roundtrip_10k": 1847.9,
+        "region_query_10k": 296.5,
+        "premium_pass": 70.3
+      }
+    ],
+    "v1.6.0": [
+      {
+        "create_lines_2k": 287.6,
+        "roundtrip_10k": 3201.3,
+        "region_query_10k": 712.2,
+        "premium_pass": 76.3
+      },
+      {
+        "create_lines_2k": 373.6,
+        "roundtrip_10k": 2550.0,
+        "region_query_10k": 806.7,
+        "premium_pass": 65.3
+      },
+      {
+        "create_lines_2k": 298.2,
+        "roundtrip_10k": 3118.3,
+        "region_query_10k": 295.1,
+        "premium_pass": 36.9
+      },
+      {
+        "create_lines_2k": 425.1,
+        "roundtrip_10k": 2553.5,
+        "region_query_10k": 836.4,
+        "premium_pass": 83.8
+      },
+      {
+        "create_lines_2k": 306.1,
+        "roundtrip_10k": 2289.4,
+        "region_query_10k": 300.6,
+        "premium_pass": 41.3
+      }
+    ],
+    "v1.6.0 EZDXF_CALL_TIMEOUT=0": [
+      {
+        "create_lines_2k": 285.3,
+        "roundtrip_10k": 1817.2,
+        "region_query_10k": 926.5,
+        "premium_pass": 61.4
+      },
+      {
+        "create_lines_2k": 256.1,
+        "roundtrip_10k": 2520.9,
+        "region_query_10k": 750.3,
+        "premium_pass": 80.2
+      },
+      {
+        "create_lines_2k": 260.2,
+        "roundtrip_10k": 1714.1,
+        "region_query_10k": 783.9,
+        "premium_pass": 76.7
+      },
+      {
+        "create_lines_2k": 351.7,
+        "roundtrip_10k": 3057.1,
+        "region_query_10k": 940.8,
+        "premium_pass": 69.9
+      },
+      {
+        "create_lines_2k": 284.9,
+        "roundtrip_10k": 2216.4,
+        "region_query_10k": 311.2,
+        "premium_pass": 41.7
+      }
+    ]
+  }
+}

benchmarks/results/published/puran-water-autocad-mcp.json

@@ -0,0 +1,187 @@
+{
+  "adapter": "puran-water-autocad-mcp",
+  "adapter_metadata": {
+    "backend": "ezdxf",
+    "kind": "mcp-stdio-blackbox",
+    "pinned_sha": "95476a33a1c246308326eb4709d6379ef2efdbc1",
+    "repo": "https://github.com/puran-water/autocad-mcp.git",
+    "tools_discovered": [
+      "annotation",
+      "block",
+      "drawing",
+      "entity",
+      "layer",
+      "pid",
+      "system",
+      "view"
+    ]
+  },
+  "environment": {
+    "implementation": "CPython",
+    "machine": "AMD64",
+    "platform": "Windows-11-10.0.26200-SP0",
+    "python": "3.14.0"
+  },
+  "generated_at": "2026-07-23T11:32:07.977232+00:00",
+  "git_sha": "4a2e9d658f051cb756f92cb8fae945c64b8cc7d4",
+  "results": [
+    {
+      "artifacts": [
+        {
+          "filename": "puran_core_geometry.dxf",
+          "sha256": "bc8185404c8344134859293a0e28ebf821cd5968553cdd96b7029e46e1ca0c99",
+          "size_bytes": 18587
+        }
+      ],
+      "duration_ms": 205.92,
+      "message": "",
+      "metrics": {
+        "circles": 1,
+        "line_length": 5.0,
+        "lines": 1
+      },
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "core_geometry"
+    },
+    {
+      "artifacts": [
+        {
+          "filename": "puran_modify_query.dxf",
+          "sha256": "2113a59d0a9f624b6134e89f992d153bc8e085495e956f4887b8ba7b54f3c005",
+          "size_bytes": 18473
+        }
+      ],
+      "duration_ms": 156.79,
+      "message": "",
+      "metrics": {},
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "modify_query"
+    },
+    {
+      "artifacts": [
+        {
+          "filename": "puran_layers.dxf",
+          "sha256": "7144467e22e2e8c8d18f1fc4f177f078f9ce450bb73f4e9ca8f74c16d67e1b53",
+          "size_bytes": 18498
+        }
+      ],
+      "duration_ms": 189.98,
+      "message": "layer created; no linetype-loading operation is exposed",
+      "metrics": {},
+      "score": 50.0,
+      "status": "partial",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "layers_linetypes"
+    },
+    {
+      "artifacts": [
+        {
+          "filename": "puran_dimensions.dxf",
+          "sha256": "dde808c5e504c5e6b7837f5f5c14ef096711812a6239dd284906efed5c9e3614",
+          "size_bytes": 20972
+        }
+      ],
+      "duration_ms": 215.28,
+      "message": "",
+      "metrics": {
+        "dimension_count": 1
+      },
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "dimensions"
+    },
+    {
+      "artifacts": [],
+      "duration_ms": 0.12,
+      "message": "no TABLE or MLEADER operation in the 8-tool surface (v3.1)",
+      "metrics": {},
+      "score": 0.0,
+      "status": "unsupported",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "table_mleader"
+    },
+    {
+      "artifacts": [],
+      "duration_ms": 0.02,
+      "message": "no transaction begin/commit/rollback tool (undo/redo are File-IPC only)",
+      "metrics": {},
+      "score": 0.0,
+      "status": "unsupported",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "transactions"
+    },
+    {
+      "artifacts": [],
+      "duration_ms": 0.01,
+      "message": "no requirements-preflight equivalent",
+      "metrics": {},
+      "score": 0.0,
+      "status": "unsupported",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "preflight"
+    },
+    {
+      "artifacts": [],
+      "duration_ms": 0.03,
+      "message": "no critique/repair loop equivalent",
+      "metrics": {},
+      "score": 0.0,
+      "status": "unsupported",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "quality_refiner"
+    },
+    {
+      "artifacts": [
+        {
+          "filename": "puran_roundtrip.dxf",
+          "sha256": "11335953641be32f3f47c23fbc13f79876111c6f84f8874af8f5e04d5e398cf6",
+          "size_bytes": 18474
+        }
+      ],
+      "duration_ms": 143.4,
+      "message": "",
+      "metrics": {
+        "entity_count": 1
+      },
+      "score": 100.0,
+      "status": "pass",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "dxf_roundtrip"
+    },
+    {
+      "artifacts": [],
+      "duration_ms": 0.06,
+      "message": "no hashed delivery-manifest equivalent (plot_pdf is File-IPC only)",
+      "metrics": {},
+      "score": 0.0,
+      "status": "unsupported",
+      "stderr_summary": "",
+      "stdout_summary": "",
+      "task_id": "auditable_delivery"
+    }
+  ],
+  "schema_version": "2.0",
+  "summary": {
+    "attempted": 10,
+    "coverage_percent": 50.0,
+    "passed": 4,
+    "score": 45.0,
+    "supported": 5,
+    "unsupported": 5
+  },
+  "timeout_seconds": 30.0
+}

benchmarks/run_competitors.py

@@ -5,6 +5,7 @@ from __future__ import annotations
 import argparse
 import asyncio
 import hashlib
+import importlib
 import json
 import platform
 import subprocess
@@ -13,8 +14,22 @@ import time
 from datetime import UTC, datetime
 from pathlib import Path
 
+from backends.capability import UnsupportedCapabilityError
 from benchmarks.adapters.base import BenchmarkAdapter, TaskResult
-from benchmarks.tasks_v2 import TASKS_V2, TaskSpec, task_by_id
+from benchmarks.tasks_v7 import DEFAULT_MATRIX, MATRICES, TaskSpec, task_by_id
+
+
+def _load_registry() -> dict[str, dict]:
+    """Read competitors.yaml (JSON content) into an id -> entry registry."""
+    path = Path(__file__).with_name("competitors.yaml")
+    data = json.loads(path.read_text(encoding="utf-8"))
+    return {entry["id"]: entry for entry in data.get("competitors", [])}
+
+
+def _make_adapter(entry: dict, backend: str) -> BenchmarkAdapter:
+    module_name, _, attr = entry["adapter"].partition(":")
+    adapter_cls = getattr(importlib.import_module(module_name), attr)
+    return adapter_cls(backend=backend)
 
 
 def _git_sha() -> str | None:
@@ -64,6 +79,7 @@ async def run_tasks(
     artifact_dir: str | Path,
     *,
     timeout: float = 30.0,
+    matrix: str = DEFAULT_MATRIX,
 ) -> dict:
     destination = Path(artifact_dir).resolve()
     destination.mkdir(parents=True, exist_ok=True)
@@ -76,6 +92,12 @@ async def run_tasks(
                 result = await asyncio.wait_for(adapter.run_task(task), timeout=timeout)
             except TimeoutError:
                 result = TaskResult(task.task_id, "timeout", 0.0, f"Exceeded {timeout}s")
+            except UnsupportedCapabilityError as exc:
+                # "Your server got this wrong" and "your engine cannot reach
+                # this" are different findings about a competitor. The enum has
+                # carried `unsupported` since v2 for exactly this, but a
+                # refusal is still an exception and used to land as `fail`.
+                result = TaskResult(task.task_id, "unsupported", 0.0, f"[{exc.capability}] {exc}")
             except Exception as exc:
                 result = TaskResult(task.task_id, "fail", 0.0, str(exc), stderr_summary=str(exc))
             result.duration_ms = round((time.perf_counter() - started) * 1000, 2)
@@ -91,12 +113,14 @@ async def run_tasks(
     total_weight = sum(weight_by_id.values())
     supported_weight = sum(weight_by_id[item.task_id] for item in supported)
     weighted_score = sum(
-        weight_by_id[item.task_id] * item.score
-        for item in results
-        if item.status != "unsupported"
+        weight_by_id[item.task_id] * item.score for item in results if item.status != "unsupported"
     )
     return {
+        # The *report* schema is unchanged — same keys, same enum — so the
+        # chart renderers still read v1.4's published files. `matrix` says
+        # which task set ran, which is the thing that actually moved.
         "schema_version": "2.0",
+        "matrix": matrix,
         "adapter": adapter.name,
         "adapter_metadata": adapter.metadata(),
         "git_sha": _git_sha(),
@@ -122,33 +146,85 @@ async def run_tasks(
     }
 
 
-def _parser() -> argparse.ArgumentParser:
+def _parser(registry: dict[str, dict]) -> argparse.ArgumentParser:
     parser = argparse.ArgumentParser(description=__doc__)
     parser.add_argument("--list", action="store_true", help="List the fixed benchmark tasks")
-    parser.add_argument("--server", default="autocad-mcp-pro", choices=["autocad-mcp-pro"])
+    parser.add_argument(
+        "--matrix",
+        default=DEFAULT_MATRIX,
+        choices=sorted(MATRICES),
+        help="Task set to run. v2 stays addressable so a v1.4 report can be reproduced.",
+    )
+    parser.add_argument(
+        "--server",
+        default="autocad-mcp-pro",
+        choices=sorted(registry),
+        help="Adapter id from benchmarks/competitors.yaml",
+    )
     parser.add_argument("--backend", default="ezdxf", choices=["ezdxf", "com"])
     parser.add_argument("--task", action="append", help="Run only this task id (repeatable)")
     parser.add_argument("--artifact-dir", default="benchmarks/results/latest")
     parser.add_argument("--timeout", type=float, default=30.0)
     parser.add_argument("--json", action="store_true", help="Print machine-readable JSON")
+    parser.add_argument(
+        "--publish",
+        type=Path,
+        help=(
+            "Also write the report here with artifact paths reduced to filenames. "
+            "How results/published/*.json are produced — it was a manual edit before."
+        ),
+    )
     return parser
 
 
+def _sanitize_for_publication(report: dict) -> dict:
+    """Drop absolute paths from artifacts, keep the hash that identifies them.
+
+    A published report should not carry the run machine's directory layout;
+    the sha256 is what makes the artifact checkable, and that stays.
+    """
+    published = json.loads(json.dumps(report))
+    for result in published["results"]:
+        for artifact in result["artifacts"]:
+            artifact.pop("path", None)
+    return published
+
+
 def main() -> None:
-    args = _parser().parse_args()
+    registry = _load_registry()
+    args = _parser(registry).parse_args()
     if args.list:
-        for task in TASKS_V2:
+        for task in MATRICES[args.matrix]:
             print(f"{task.task_id}\t{task.category}\t{task.description}")
         return
 
-    from benchmarks.adapters.autocad_mcp_pro import AutoCADMCPProAdapter
-
-    tasks = [task_by_id(task_id) for task_id in args.task] if args.task else list(TASKS_V2)
-    adapter = AutoCADMCPProAdapter(backend=args.backend)
+    entry = registry[args.server]
+    supported_backends = entry.get("backends", ["ezdxf"])
+    if args.backend not in supported_backends:
+        raise SystemExit(
+            f"{args.server} supports backends {supported_backends}, not {args.backend!r}"
+        )
+    tasks = (
+        [task_by_id(task_id, args.matrix) for task_id in args.task]
+        if args.task
+        else list(MATRICES[args.matrix])
+    )
+    adapter = _make_adapter(entry, args.backend)
     report = asyncio.run(
-        run_tasks(adapter, tasks, args.artifact_dir, timeout=args.timeout)
+        run_tasks(adapter, tasks, args.artifact_dir, timeout=args.timeout, matrix=args.matrix)
     )
     rendered = json.dumps(report, ensure_ascii=False, indent=2, sort_keys=True)
+    if args.publish:
+        args.publish.parent.mkdir(parents=True, exist_ok=True)
+        args.publish.write_text(
+            json.dumps(
+                _sanitize_for_publication(report), ensure_ascii=False, indent=2, sort_keys=True
+            )
+            + "\n",
+            encoding="utf-8",
+            newline="\n",
+        )
+        print(f"Published: {args.publish}", file=sys.stderr)
     print(rendered)
 
 

benchmarks/source_review.json

@@ -1,25 +1,88 @@
 {
   "schema_version": "1.0",
-  "reviewed_at": "2026-07-17",
+  "reviewed_at": "2026-09-24",
   "title": "AutoCAD MCP source-reviewed capability benchmark",
   "evidence_boundary": "source_review_not_shared_live_run",
-  "methodology": "Public source, documented behavior, and locally recorded test evidence scored with a fixed 100-point rubric. Repository stars and raw tool counts do not score points.",
+  "methodology": "Public source, documented behavior, and locally recorded test evidence scored with a fixed 100-point rubric. Repository stars and raw tool counts do not score points. The U-C4N row was re-scored for 1.6.0 on 2026-09-24 with per-category evidence; competitor rows are their July snapshots and were not re-reviewed.",
   "rubric": [
-    {"category": "Functional CAD coverage", "weight": 25},
-    {"category": "Correctness and delivery", "weight": 20},
-    {"category": "Backends and platforms", "weight": 15},
-    {"category": "Engineering production", "weight": 15},
-    {"category": "Tests and maintenance", "weight": 15},
-    {"category": "Security and operations", "weight": 10}
+    {
+      "category": "Functional CAD coverage",
+      "weight": 25
+    },
+    {
+      "category": "Correctness and delivery",
+      "weight": 20
+    },
+    {
+      "category": "Backends and platforms",
+      "weight": 15
+    },
+    {
+      "category": "Engineering production",
+      "weight": 15
+    },
+    {
+      "category": "Tests and maintenance",
+      "weight": 15
+    },
+    {
+      "category": "Security and operations",
+      "weight": 10
+    }
   ],
   "projects": [
     {
       "repository": "U-C4N/Autocad-MCP",
       "url": "https://github.com/U-C4N/Autocad-MCP",
-      "reviewed_version": "1.3.0 working tree",
+      "reviewed_version": "1.6.0 (release)",
       "score": 93,
       "evidence_grade": "A",
-      "note": "Dual COM/ezdxf backends, standards-aware quality gates, deterministic geometry, closed-loop refinement, and auditable delivery."
+      "note": "Scored per category, each with its evidence (roadmap criterion 8). 1.4.0 received a single overall 95; this review is stricter, and every point withheld is named. New in 1.5-1.6: P&ID, environment, mechanical, sheet, architecture, understanding and takeoffs; A/B 48/48 with 0 regressions; live COM smokes on every track.",
+      "category_scores": [
+        {
+          "category": "Functional CAD coverage",
+          "weight": 25,
+          "score": 24,
+          "evidence": "247 tools: drafting, ISO 129/286/1101 annotation, paper space, styles and page setup, environment, P&ID (ISO 10628-2 / ISA-5.1, read back with confidence), a mechanical part model with standard parts, ISO 5457/7200/7573/6433 sheets, an architectural plan engine, drawing understanding, diff, topology and plant takeoffs. Not covered: electrical schematics, image-to-CAD tracing, Plant 3D, obstacle-avoiding routing, headless REGION/3DSOLID."
+        },
+        {
+          "category": "Correctness and delivery",
+          "weight": 20,
+          "score": 19,
+          "evidence": "A/B gate against v1.5.1: 48/48 checks, 0 regressions (ab-v1.5.1-vs-v1.6.0.json). Matrix v7: 21 tasks whose gates can fail (zero critique issues and a finalize score of at least 90, PDF /MediaBox, rooms within 0.1 %, takeoff lengths exact). drawing_deliver writes a manifest and checks reopen parity. A field test on a real P&ID pair drove nine fixes. Minus: a headless DIMENSION does not re-render, and a takeoff on a real P&ID still needs the engineer's scope decisions."
+        },
+        {
+          "category": "Backends and platforms",
+          "weight": 15,
+          "score": 14,
+          "evidence": "COM and ezdxf behind one typed contract, with capability-map parity enforced by a test. Every 1.6 track's COM path ran live on AutoCAD 2026. CI runs Linux 3.11/3.12 and Windows. Minus: BricsCAD, ZWCAD and GstarCAD are unverified."
+        },
+        {
+          "category": "Engineering production",
+          "weight": 15,
+          "score": 14,
+          "evidence": "Transcribed standards tables (ISO 4014/4017/4032/7089/4762, ISO 15, ISO 286, ISO 5457, ISO 7200, ISO 7573) and one part model and view engine. 18 domain critique focuses (P&ID 6, mechanical 6, architecture 3, topology 3) feed drawing_finalize's 0-100 score. Minus: four DIN/ISO feature tables ship empty until verified rows exist."
+        },
+        {
+          "category": "Tests and maintenance",
+          "weight": 15,
+          "score": 14,
+          "evidence": "About 4,990 tests on a locked dependency graph. The release gate re-runs three OS/Python lanes; a document-number gate and the per-release A/B suite also run. The perf lane is published (perf-v1.4.0-vs-v1.6.0.json). Minus: entity creation is 1.25x (2,000 lines) and 1.38x (10,000-line roundtrip) slower than v1.4.0, so roadmap criterion 7 is not met."
+        },
+        {
+          "category": "Security and operations",
+          "weight": 10,
+          "score": 8,
+          "evidence": "Per-tool path validation, a loopback-only HTTP bind unless a bearer token is set, the audit middleware, and a field-test script that refuses to write inside the repository. Minus: ALLOWED_PATHS is empty, and so unscoped, by default; command and LISP filtering is a denylist, which is a guardrail rather than a security boundary."
+        }
+      ],
+      "history": [
+        {
+          "version": "1.4.0",
+          "score": 95,
+          "reviewed_at": "2026-07-23"
+        }
+      ]
     },
     {
       "repository": "varavista/autocad-mcp",
@@ -60,6 +123,31 @@
       "score": 68,
       "evidence_grade": "B",
       "note": ".NET main-thread integration with a broad live AutoCAD operation surface."
+    },
+    {
+      "repository": "LokmenoWer/best-cad-mcp",
+      "url": "https://github.com/LokmenoWer/best-cad-mcp",
+      "reviewed_version": "v1.5.0 (2026-07-23 snapshot)",
+      "score": 74,
+      "evidence_grade": "B",
+      "note": "Very broad live-AutoCAD operation surface with CAD-IR understanding, visual grounding, and guarded CADPlan dry-run/rollback; COM-only (no headless lane), no standards-based generators or toleranced annotation."
+    },
+    {
+      "repository": "daobataotie/CAD-MCP",
+      "url": "https://github.com/daobataotie/CAD-MCP",
+      "reviewed_version": "2026-07-23 snapshot",
+      "score": 35,
+      "evidence_grade": "B",
+      "note": "Multi-CAD reach (AutoCAD/GstarCAD/ZWCAD) over Windows COM with a small basic drawing surface; no verification, transactions, tests, or delivery evidence documented."
+    },
+    {
+      "repository": "zh19980811/Easy-MCP-AutoCad",
+      "url": "https://github.com/zh19980811/Easy-MCP-AutoCad",
+      "reviewed_version": "2026-07-23 snapshot",
+      "score": 30,
+      "evidence_grade": "C",
+      "note": "Basic COM drawing tool set with SQLite persistence; reviewed from the documented tool surface only, execution path not exercised locally."
     }
-  ]
+  ],
+  "competitors_reviewed_at": "2026-07-23"
 }

benchmarks/tasks_v3.py

@@ -0,0 +1,84 @@
+"""The v3 task matrix: the v2 ten, plus five the v2 ten could not see.
+
+v2 scored this server 10/10, and that number was structurally uninformative:
+every task in it exercised something the server was already built around. A
+matrix that cannot fail is a matrix that measures nothing, so the five added
+here were picked to cover capability the v2 set never touches — discovery,
+idle token cost, hatch islands, selection semantics, and measuring an entity
+that is already in the drawing.
+
+Two of the five are renamed from the release plan, and the renames are the
+point rather than bookkeeping:
+
+``tool_discovery_bilingual`` -> ``tool_discovery``
+    The plan assumed a Turkish query normalizer. One was written and then
+    removed: this repository is English throughout, and the Turkish was an
+    inference from the author's chat language, not a product requirement. A
+    task named "bilingual" would advertise a capability that does not exist,
+    which is the class of claim this release spent four milestones deleting.
+
+``measurement_massprops`` -> ``measure_from_handle``
+    No mass properties ship. The plan's eight-tool measurement family (F2) was
+    cut to one after measurement showed the repo already carried eight
+    ``analysis_*`` tools; centroids and moments of inertia were not among the
+    survivors. What did ship is measuring a *handle* instead of a caller's
+    remembered coordinates, so that is what the task is called.
+
+The v2 ids and weights are untouched. The published competitor reports were
+run against the v2 matrix at v1.4 and are not re-scored here — those servers
+have never been asked these five questions, and inventing a result for them
+would be worse than the gap. The task-matrix chart renders them ``not_run``.
+"""
+
+from __future__ import annotations
+
+from benchmarks.tasks_v2 import TASKS_V2, TaskSpec
+
+#: Added in v1.5.0. Every one of these can fail on this server.
+NEW_TASKS_V3: tuple[TaskSpec, ...] = (
+    TaskSpec(
+        "tool_discovery",
+        "discovery",
+        "Resolve AutoCAD command names to tools through the search layer",
+        1.0,
+    ),
+    TaskSpec(
+        "token_budget",
+        "efficiency",
+        "Keep the idle catalog under a fixed token ceiling",
+        1.0,
+    ),
+    TaskSpec(
+        "hatch_islands",
+        "hatch",
+        "Hatch an area with an island and measure what it fills",
+        1.0,
+    ),
+    TaskSpec(
+        "selection_filter",
+        "selection",
+        "Separate window from crossing, and a polygon from its bounding box",
+        1.0,
+    ),
+    TaskSpec(
+        "measure_from_handle",
+        "measurement",
+        "Measure a curved boundary from its handle, bulges included",
+        1.0,
+    ),
+)
+
+TASKS_V3: tuple[TaskSpec, ...] = TASKS_V2 + NEW_TASKS_V3
+
+#: Runner-selectable task sets. v2 stays addressable so a v2 report can be
+#: reproduced exactly rather than only described.
+MATRICES: dict[str, tuple[TaskSpec, ...]] = {"v2": TASKS_V2, "v3": TASKS_V3}
+
+DEFAULT_MATRIX = "v3"
+
+
+def task_by_id(task_id: str, matrix: str = DEFAULT_MATRIX) -> TaskSpec:
+    for task in MATRICES[matrix]:
+        if task.task_id == task_id:
+            return task
+    raise KeyError(f"Unknown benchmark task: {task_id}")

benchmarks/tasks_v4.py

@@ -0,0 +1,52 @@
+"""The v4 task matrix: v3 plus what 1.6 added.
+
+``pid_roundtrip`` (track A) draws a five-item P&ID through the same code the
+tools call and reads it back: the edge count, the absence of dangling ends
+and the instrument index are each derived independently of the drawing code.
+
+``page_setup_truth`` (track E) applies an ISO A3 landscape page setup to a
+layout, plots it through ``batch_plot`` and reads the sheet size back from
+the PDF's own ``/MediaBox`` — the setup is verified by the file, not by the
+setter's return value. A fresh Layout1 is already A3 landscape, so the task
+moves the sheet to ANSI B (432 × 279) and reads that PDF first; a setter that
+writes nothing fails there, not at the A3 read-back.
+
+The published competitor reports were never asked either question; the chart
+shows ``not_run`` for them, not zero.
+"""
+
+from __future__ import annotations
+
+from benchmarks.tasks_v2 import TASKS_V2, TaskSpec
+from benchmarks.tasks_v3 import TASKS_V3
+
+#: Added in v1.6.0. Each can fail on its own.
+NEW_TASKS_V4: tuple[TaskSpec, ...] = (
+    TaskSpec(
+        "pid_roundtrip",
+        "pid",
+        "Draw a P&ID from a spec and read back a matching graph, index and line list",
+        1.0,
+    ),
+    TaskSpec(
+        "page_setup_truth",
+        "pagesetup",
+        "Apply an ISO A3 page setup, plot it, and read the sheet size back from the PDF",
+        1.0,
+    ),
+)
+
+TASKS_V4: tuple[TaskSpec, ...] = TASKS_V3 + NEW_TASKS_V4
+
+#: Runner-selectable task sets. v2 and v3 stay addressable so an earlier
+#: report can be reproduced exactly rather than only described.
+MATRICES: dict[str, tuple[TaskSpec, ...]] = {"v2": TASKS_V2, "v3": TASKS_V3, "v4": TASKS_V4}
+
+DEFAULT_MATRIX = "v4"
+
+
+def task_by_id(task_id: str, matrix: str = DEFAULT_MATRIX) -> TaskSpec:
+    for task in MATRICES[matrix]:
+        if task.task_id == task_id:
+            return task
+    raise KeyError(f"{task_id} is not in matrix {matrix}")

benchmarks/tasks_v5.py

@@ -0,0 +1,50 @@
+"""The v5 task matrix: v4 plus what tracks B and G added.
+
+``mech_assembly`` (tracks B + G) is roadmap criterion 3: a flange-coupling
+sheet built from the tools — two parts with a section, a bolt circle of ISO
+4014 bolts and ISO 4032 nuts, ISO 129 dimensions, an ISO 5457 A3 frame, an
+ISO 7200 title block and an ISO 7573 parts list with balloons. The gate is two
+numbers, not an impression: ``drawing_critique(focus=None)`` returns zero
+issues and the finalize score is at least 90. Either one slipping fails the
+task outright.
+
+The published competitor reports were never asked this question; the chart
+shows ``not_run`` for them, not zero.
+"""
+
+from __future__ import annotations
+
+from benchmarks.tasks_v2 import TASKS_V2
+from benchmarks.tasks_v3 import TASKS_V3
+from benchmarks.tasks_v4 import TASKS_V4, TaskSpec
+
+#: Added in v1.6.0 by tracks B + G.
+NEW_TASKS_V5: tuple[TaskSpec, ...] = (
+    TaskSpec(
+        "mech_assembly",
+        "mech",
+        "Draw a flange-coupling sheet from the part model and the sheet standard, "
+        "with a clean critique and a finalize score of at least 90",
+        1.0,
+    ),
+)
+
+TASKS_V5: tuple[TaskSpec, ...] = TASKS_V4 + NEW_TASKS_V5
+
+#: Runner-selectable task sets. v2, v3 and v4 stay addressable so an earlier
+#: report can be reproduced exactly rather than only described.
+MATRICES: dict[str, tuple[TaskSpec, ...]] = {
+    "v2": TASKS_V2,
+    "v3": TASKS_V3,
+    "v4": TASKS_V4,
+    "v5": TASKS_V5,
+}
+
+DEFAULT_MATRIX = "v5"
+
+
+def task_by_id(task_id: str, matrix: str = DEFAULT_MATRIX) -> TaskSpec:
+    for task in MATRICES[matrix]:
+        if task.task_id == task_id:
+            return task
+    raise KeyError(f"{task_id} is not in matrix {matrix}")

benchmarks/tasks_v6.py

@@ -0,0 +1,54 @@
+"""The v6 task matrix: v5 plus what track F added.
+
+``arch_roundtrip`` (track F) is the roadmap evidence for the plan model: a
+two-room plan - an entrance door, an interior door, two windows and a stair -
+drawn by ``arch_plan_from_spec``, then read back by ``arch_rooms_detect``,
+which never sees the spec. Each room's detected area has to agree with the area
+its label carries within 0.1 %, and both with the net floor computed by hand;
+the door and window schedules have to list the drawn tags; and the sheet is
+gated on the same two numbers as ``mech_assembly``: ``drawing_critique
+(focus=None)`` returns zero issues and the finalize score is at least 90.
+
+The published competitor reports were never asked this question; the chart
+shows ``not_run`` for them, not zero.
+"""
+
+from __future__ import annotations
+
+from benchmarks.tasks_v2 import TASKS_V2
+from benchmarks.tasks_v3 import TASKS_V3
+from benchmarks.tasks_v4 import TASKS_V4
+from benchmarks.tasks_v5 import TASKS_V5, TaskSpec
+
+#: Added in v1.6.0 by track F.
+NEW_TASKS_V6: tuple[TaskSpec, ...] = (
+    TaskSpec(
+        "arch_roundtrip",
+        "arch",
+        "Draw a two-room plan from one spec, read its rooms back from the drawing "
+        "within 0.1 %, schedule its tags, with a clean critique and a finalize score "
+        "of at least 90",
+        1.0,
+    ),
+)
+
+TASKS_V6: tuple[TaskSpec, ...] = TASKS_V5 + NEW_TASKS_V6
+
+#: Runner-selectable task sets. v2 to v5 stay addressable so an earlier report
+#: can be reproduced exactly rather than only described.
+MATRICES: dict[str, tuple[TaskSpec, ...]] = {
+    "v2": TASKS_V2,
+    "v3": TASKS_V3,
+    "v4": TASKS_V4,
+    "v5": TASKS_V5,
+    "v6": TASKS_V6,
+}
+
+DEFAULT_MATRIX = "v6"
+
+
+def task_by_id(task_id: str, matrix: str = DEFAULT_MATRIX) -> TaskSpec:
+    for task in MATRICES[matrix]:
+        if task.task_id == task_id:
+            return task
+    raise KeyError(f"{task_id} is not in matrix {matrix}")

benchmarks/tasks_v7.py

@@ -0,0 +1,71 @@
+"""The v7 task matrix: v6 plus what track H added.
+
+Track H teaches the server to read drawings somebody else made, so its two
+tasks are gated on a drawing pair whose answers are known in advance - the
+synthetic plant pair of ``tests/fixtures/plant_pair.py``, which reproduces
+every field finding of the design spec with invented names:
+
+* ``takeoff_roundtrip`` - the scale check calls the P&ID ``schematic``; every
+  routable pipe run's layout length equals the rectilinear minimum spanning
+  tree of its tags exactly; its size, service and status match the generator's
+  truth; the cable rows equal the Manhattan lengths from each load to its panel
+  with the allowance rounded up to the metre.
+* ``understand_foreign`` - one ``describe`` of the layout flags inches declared
+  over millimetre geometry, finds the stray entity by handle and separates the
+  two plan copies; one ``describe`` of the P&ID classifies its English and
+  Dutch service layers.
+
+The published competitor reports were never asked these questions; the chart
+shows ``not_run`` for them, not zero.
+"""
+
+from __future__ import annotations
+
+from benchmarks.tasks_v2 import TASKS_V2
+from benchmarks.tasks_v3 import TASKS_V3
+from benchmarks.tasks_v4 import TASKS_V4
+from benchmarks.tasks_v5 import TASKS_V5
+from benchmarks.tasks_v6 import TASKS_V6, TaskSpec
+
+#: Added in v1.6.0 by track H.
+NEW_TASKS_V7: tuple[TaskSpec, ...] = (
+    TaskSpec(
+        "takeoff_roundtrip",
+        "plant",
+        "Take pipe and cable quantities off a schematic P&ID and its layout: the P&ID "
+        "called schematic, every run's layout length equal to the rectilinear MST of "
+        "its tags, sizes and services as drawn, cable metres rounded up after the "
+        "allowance",
+        1.0,
+    ),
+    TaskSpec(
+        "understand_foreign",
+        "understand",
+        "Read a foreign layout in one call: inches declared over millimetres flagged, "
+        "the stray entity found, both plan copies separated, the service layers of its "
+        "P&ID classified",
+        1.0,
+    ),
+)
+
+TASKS_V7: tuple[TaskSpec, ...] = TASKS_V6 + NEW_TASKS_V7
+
+#: Runner-selectable task sets. v2 to v6 stay addressable so an earlier report
+#: can be reproduced exactly rather than only described.
+MATRICES: dict[str, tuple[TaskSpec, ...]] = {
+    "v2": TASKS_V2,
+    "v3": TASKS_V3,
+    "v4": TASKS_V4,
+    "v5": TASKS_V5,
+    "v6": TASKS_V6,
+    "v7": TASKS_V7,
+}
+
+DEFAULT_MATRIX = "v7"
+
+
+def task_by_id(task_id: str, matrix: str = DEFAULT_MATRIX) -> TaskSpec:
+    for task in MATRICES[matrix]:
+        if task.task_id == task_id:
+            return task
+    raise KeyError(f"{task_id} is not in matrix {matrix}")

config.py

@@ -5,12 +5,51 @@ from __future__ import annotations
 import os
 from pathlib import Path
 
+#: ProgID the live backend attaches to when ``CAD_PROGID`` is unset. The only
+#: CAD this project is developed and tested against.
+DEFAULT_CAD_PROGID = "AutoCAD.Application"
+
+#: Default ``MAX_DXF_BYTES``: 512 MB.
+DEFAULT_MAX_DXF_BYTES = 512 * 1024 * 1024
+
 
 class Settings:
     """Server configuration loaded from environment variables."""
 
+    @property
+    def backend(self) -> str:
+        """Which engine to run: ``ezdxf``, ``com`` or ``auto``.
+
+        Read live rather than captured in ``__init__``, and deliberately
+        read-only. ``_make_backend`` used to read ``os.environ`` itself while
+        this attribute had no production reader at all, so
+        ``monkeypatch.setattr(settings, "backend", "ezdxf")`` looked like a
+        guard and was a no-op — on a machine with AutoCAD open that meant a test
+        attaching to the operator's live drawing. Late binding is what keeps
+        ``monkeypatch.setenv`` working for the call sites that pin the headless
+        backend correctly; the missing setter is what makes the broken spelling
+        fail loudly instead of silently.
+        """
+        return os.environ.get("AUTOCAD_MCP_BACKEND", "auto").lower().strip()
+
+    @property
+    def cad_progid(self) -> str:
+        """COM ProgID the live backend attaches to.
+
+        Read live and deliberately read-only for the same reasons as
+        ``backend``: late binding keeps ``monkeypatch.setenv`` working, and the
+        missing setter makes a wrong spelling fail loudly rather than look like
+        a guard that does nothing.
+
+        Stripped but **not** lowercased — the value is echoed back in error
+        messages and ``system_status``, where ``gstarcad.application`` reads
+        like a typo we introduced. Never validated against what is actually
+        registered on the machine: an unrecognised ProgID is not "invalid", it
+        is unverifiable by us, and only AutoCAD is tested.
+        """
+        return os.environ.get("CAD_PROGID", "").strip() or DEFAULT_CAD_PROGID
+
     def __init__(self):
-        self.backend: str = os.environ.get("AUTOCAD_MCP_BACKEND", "auto").lower().strip()
         self.log_level: str = os.environ.get("LOG_LEVEL", "INFO").upper().strip()
 
         raw_paths = os.environ.get("ALLOWED_PATHS", "").strip()
@@ -26,9 +65,12 @@ class Settings:
             os.environ.get("DANGEROUS_COMMANDS_ENABLED", "false").lower().strip() == "true"
         )
 
-        # Reject opening DXF files larger than this many bytes (default 50 MB).
-        # Set to 0 to disable the check.
-        self.max_dxf_bytes: int = int(os.environ.get("MAX_DXF_BYTES", str(50 * 1024 * 1024)))
+        # Reject opening DXF files larger than this many bytes (default 512 MB).
+        # Set to 0 to disable the check. It was 50 MB until v1.6's track H: a
+        # real plant layout read on 2026-09-24 was a 188 MB DXF, and the
+        # understanding tools exist for exactly such drawings. The refusal
+        # names the file's size and this variable.
+        self.max_dxf_bytes: int = int(os.environ.get("MAX_DXF_BYTES", str(DEFAULT_MAX_DXF_BYTES)))
 
         # Hard cap on list/select limit params to keep tool responses bounded.
         self.max_list_limit: int = int(os.environ.get("MAX_LIST_LIMIT", "5000"))
@@ -37,11 +79,54 @@ class Settings:
         # otherwise block the single-thread STA executor forever.
         self.com_call_timeout: float = float(os.environ.get("COM_CALL_TIMEOUT", "60"))
 
+        # Per-call timeout for the headless ezdxf backend. Every ezdxf method
+        # runs under one document lock, so a single hung call (pathological DXF,
+        # a render that never returns) would otherwise hold that lock forever
+        # and deadlock every later tool call. Higher than com_call_timeout
+        # because matplotlib PDF/PNG rendering of a large drawing is legitimately
+        # slow. Set to 0 to disable the check.
+        self.ezdxf_call_timeout: float = float(os.environ.get("EZDXF_CALL_TIMEOUT", "120"))
+
+        # How many undo steps the headless backend keeps. 0 = off, which is the
+        # default because it is not free: ezdxf has no journal, so a step is a
+        # full DXF snapshot. Measured — 10 entities 3.1 ms / 19 KB, 1000
+        # entities 28 ms / 146 KB, 5000 entities 130 ms / 658 KB — and the cost
+        # is paid on every mutating call, so switching it on for a large drawing
+        # is a real trade the user should make deliberately rather than inherit.
+        self.ezdxf_undo_depth: int = max(0, int(os.environ.get("EZDXF_UNDO_DEPTH", "0")))
+
         # HTTP transport: refuse non-loopback bind unless explicitly opted in.
         self.allow_remote_http: bool = (
             os.environ.get("ALLOW_REMOTE_HTTP", "false").lower().strip() == "true"
         )
         self.mcp_auth_token: str = os.environ.get("MCP_AUTH_TOKEN", "").strip()
 
+        # Exposed tool profile: "full" (default, everything) or "lean" (a
+        # curated ~47-tool drafting/inspection core for clients with tight tool
+        # caps). Invalid values fall back to "full" with a warning at startup;
+        # so does the "core" profile removed in v1.5.0 (see
+        # server.REMOVED_TOOL_PROFILES).
+        self.tool_profile: str = os.environ.get("TOOL_PROFILE", "full").lower().strip()
+
+        # Tool packs: "all" (default) advertises every vertical pack; a comma
+        # list ("core,pid,settings") advertises only those. core cannot be disabled.
+        self.tool_packs: str = os.environ.get("TOOL_PACKS", "all").lower().strip()
+
+        # Tool discovery: "off" (default) advertises the full catalog; "search"
+        # replaces it with a search tool plus a call_tool proxy (see
+        # discovery/transform.py and server._apply_discovery_mode).
+        #
+        # Default "off" deliberately. "search" is the intended v1.x default,
+        # but flipping it changes what every connected client sees on
+        # list_tools — a breaking wire-level change that needs its own
+        # migration note and README pass, neither of which ships in v1.5.0.
+        # Invalid values fall back to "off" with a warning at startup.
+        self.discovery_mode: str = os.environ.get("DISCOVERY_MODE", "off").lower().strip()
+
+        # Opt-in 3D solids (COM backend only). Disabled by default because the
+        # headless backend cannot produce ACIS solids and live 3D modifies real
+        # documents; enable deliberately.
+        self.enable_3d: bool = os.environ.get("ENABLE_3D", "false").lower().strip() == "true"
+
 
 settings = Settings()

discovery/__init__.py

@@ -0,0 +1,7 @@
+"""Tool-discovery layer: searchable tool metadata and the search transform.
+
+Kept deliberately free of ``fastmcp`` and ``ezdxf`` imports at module scope so
+the discovery data stays cheap to import and testable in isolation.
+"""
+
+__all__: list[str] = []

discovery/serialize.py

@@ -0,0 +1,114 @@
+"""Compact one-line cards for tool-search results.
+
+Passed to a search transform as ``search_result_serializer``. FastMCP's default
+(``serialize_tools_for_output_json``) re-emits each hit's full ``list_tools``
+entry, JSON Schema and all — for this server that is roughly 1.5 kB per hit,
+and a five-hit answer costs more than the crowded catalog the search was meant
+to replace.
+
+One line per hit::
+
+    entity_fillet (write) | Round a corner between two entities. | req: handle_a, handle_b, radius | acad: FILLET, F
+
+``req:`` lists *required* parameters only. Optional parameters and types are
+deliberately absent — the honest cost of this format is that a caller must
+either already know the optional arguments or read the error from a failed
+call. That trade is worth it at five hits per search; it would not be at one.
+
+Scope note: the compact payload is a real saving but it is **not** what makes
+this discovery layer better than stock. Stock BM25 with this same serializer
+gets the same size win. The differentiators are the alias corpus (which lets a
+query find anything at all) and the risk filter — not bytes.
+"""
+
+from __future__ import annotations
+
+from collections.abc import Sequence
+
+from fastmcp.tools.base import Tool
+
+from discovery.aliases import aliases_for
+
+__all__ = ["MAX_SUMMARY_CHARS", "serialize_search_results"]
+
+# Long enough for every first docstring line in the live catalog (measured max
+# 96 characters), short enough that a rambling one cannot dominate the payload.
+MAX_SUMMARY_CHARS = 110
+
+# Beyond three, AutoCAD command names stop disambiguating and start padding.
+MAX_ACAD_COMMANDS = 3
+
+EMPTY_RESULT = "No tools matched the query."
+
+
+def _risk(tool: Tool) -> str:
+    """Same derivation as ``discovery.transform.tool_risk``, inlined.
+
+    Imported the other way round would make ``discovery.serialize`` depend on
+    the transform, and the transform already depends on this module for its
+    default serializer.
+    """
+    annotations = tool.annotations
+    if annotations is not None:
+        if annotations.destructiveHint:
+            return "destructive"
+        if annotations.readOnlyHint:
+            return "read"
+    return "write"
+
+
+def _truncate(text: str) -> str:
+    if len(text) <= MAX_SUMMARY_CHARS:
+        return text
+    clipped = text[:MAX_SUMMARY_CHARS].rsplit(" ", 1)[0].rstrip(" ,;:.")
+    return f"{clipped}..."
+
+
+def _summary(tool: Tool) -> str:
+    """One line describing the tool.
+
+    Prefers the hand-written ``@cad_tool`` summary in the MCP ``meta`` channel;
+    falls back to the first line of the docstring, which for this server is
+    already written as a standalone sentence.
+    """
+    cad = (tool.meta or {}).get("cad")
+    if isinstance(cad, dict) and cad.get("summary"):
+        return _truncate(str(cad["summary"]).strip())
+    for line in (tool.description or "").strip().splitlines():
+        if line.strip():
+            return _truncate(line.strip())
+    return "(no description)"
+
+
+def _required(tool: Tool) -> str:
+    schema = tool.parameters or {}
+    required = schema.get("required")
+    if not isinstance(required, list) or not required:
+        return "(none)"
+    return ", ".join(str(name) for name in required)
+
+
+def _acad(tool: Tool) -> str:
+    record = aliases_for(tool.name)
+    if record is None or not record.acad:
+        return ""
+    return ", ".join(record.acad[:MAX_ACAD_COMMANDS])
+
+
+def _card(tool: Tool) -> str:
+    parts = [
+        f"{tool.name} ({_risk(tool)})",
+        _summary(tool),
+        f"req: {_required(tool)}",
+    ]
+    acad = _acad(tool)
+    if acad:
+        parts.append(f"acad: {acad}")
+    return " | ".join(parts)
+
+
+def serialize_search_results(tools: Sequence[Tool]) -> str:
+    """Render search hits as one compact card per line."""
+    if not tools:
+        return EMPTY_RESULT
+    return "\n".join(_card(tool) for tool in tools)

discovery/transform.py

@@ -0,0 +1,402 @@
+"""Tool-search transform that speaks AutoCAD.
+
+Subclasses FastMCP's :class:`BM25SearchTransform` rather than replacing it, so
+the ``call_tool`` proxy, the auth-filtered catalog accessor
+(``_get_visible_tools``) and the re-entrancy bypass all come for free. Two
+things are added on top, and only two:
+
+**1. Vocabulary.** Stock BM25 indexes tool name + description + parameter names
++ parameter descriptions. Measured against this server's live catalog, that
+leaves ``BPOLY``, ``PEDIT``, ``WBLOCK``, ``OVERKILL``, ``LAYTRANS``,
+``MATCHPROP`` and ``QSELECT`` at df=0 — a search for any of them returns
+nothing at all. :func:`discovery.aliases.alias_text` supplies the missing
+AutoCAD command names and shop-floor synonyms; this module folds them into the
+indexed document. (``FILLET`` is *not* in that list: it is already indexed,
+because the tool is literally named ``entity_fillet``.)
+
+**2. Two additive boosts**, so an exact alias match outranks an incidental
+description word. See :data:`ACAD_MATCH_BOOST` / :data:`SYNONYM_MATCH_BOOST`.
+
+BM25 itself is not reimplemented: the index object the base class already
+built is reused, only with different documents.
+"""
+
+from __future__ import annotations
+
+import hashlib
+import re
+from collections.abc import Sequence
+from dataclasses import dataclass
+from typing import Annotated, Any, Literal
+
+from fastmcp.server.context import Context
+from fastmcp.server.transforms.search import BM25SearchTransform
+from fastmcp.server.transforms.search.base import SearchResultSerializer
+from fastmcp.server.transforms.search.base import (
+    _extract_searchable_text as _stock_searchable_text,
+)
+from fastmcp.tools.base import Tool
+from pydantic import Field
+
+from discovery.aliases import alias_text, aliases_for
+from discovery.serialize import serialize_search_results
+
+__all__ = [
+    "ACAD_MATCH_BOOST",
+    "MAX_SEARCH_LIMIT",
+    "RISK_CEILINGS",
+    "SYNONYM_MATCH_BOOST",
+    "CadSearchTransform",
+    "SearchOutcome",
+    "tool_risk",
+]
+
+
+# ---------------------------------------------------------------------------
+# Scoring
+# ---------------------------------------------------------------------------
+#
+# ``_BM25Index.query()`` hands back a *ranking*, not scores, so the two signals
+# are fused on a rank scale instead of a raw-score scale: BM25's nth hit is
+# worth ``1 / (1 + n)``. That makes the boosts below trivially explainable in
+# the only units that matter here — positions.
+#
+#   ACAD_MATCH_BOOST     the query names an AutoCAD command this tool owns,
+#                        *written as a command* — see _names_a_command below.
+#                        Worth exactly as much as being BM25's top hit, so a
+#                        command match pulls a tool past any number of tools
+#                        that merely share a description word.
+#   SYNONYM_MATCH_BOOST  the query contains one of the tool's synonym phrases
+#                        verbatim ("bill of materials", "round the corner").
+#                        Worth BM25's second position: strong, but it loses to
+#                        an outright command match.
+#
+# That is the whole scorer. Both boosts are flat and apply at most once, so a
+# tool with a long synonym list cannot out-shout a tool with a short one.
+ACAD_MATCH_BOOST = 1.0
+SYNONYM_MATCH_BOOST = 0.5
+
+_WORD_RE = re.compile(r"[a-z0-9]+")
+_RAW_WORD_RE = re.compile(r"[A-Za-z0-9]+")
+
+# Dropped from both sides before phrase matching, so the synonym "delete a
+# layer" still matches "delete the layer called GEOMETRY". Articles only —
+# a general stop-word list would start matching phrases that mean other things.
+_ARTICLES = frozenset({"a", "an", "the"})
+
+
+def _words(text: str) -> list[str]:
+    """Lowercase word list. Unlike BM25's tokenizer, single characters survive.
+
+    ``_tokenize`` drops ``len <= 1`` tokens, which is right for an inverted
+    index and wrong for phrase matching: dropping the "a" out of "round the
+    corner" would silently change which phrases can match.
+    """
+    return _WORD_RE.findall(text.lower())
+
+
+def _phrase_words(text: str) -> list[str]:
+    return [word for word in _words(text) if word not in _ARTICLES]
+
+
+def _names_a_command(query: str, command: str) -> bool:
+    """True when ``query`` uses ``command`` as a command, not as English.
+
+    Several AutoCAD command names are also ordinary nouns — LAYER, TABLE, LINE,
+    POINT, TEXT, BOX, ARRAY. Boosting on a bare lowercase "layer" put
+    ``layer_create`` / ``layer_modify`` above ``layer_delete`` for "delete the
+    layer called GEOMETRY", which is exactly backwards. A drafter reaching for
+    the command types it in capitals, or types nothing else:
+
+      "BPOLY", "trace it with BPOLY"  -> command
+      "bpoly"                         -> command (nothing else in the query)
+      "delete the layer ..."          -> English; BM25 handles it
+    """
+    words = _words(query)
+    if len(words) == 1 and words[0] == command.lower():
+        return True
+    return command in _RAW_WORD_RE.findall(query)
+
+
+def _contains_phrase(haystack: Sequence[str], needle: Sequence[str]) -> bool:
+    """True when ``needle`` appears as a contiguous run of words in ``haystack``.
+
+    Word-level rather than substring, so the synonym "line" does not match
+    "polyline" or "linear".
+    """
+    n = len(needle)
+    if not n or n > len(haystack):
+        return False
+    first = needle[0]
+    for i, word in enumerate(haystack):
+        if word == first and list(haystack[i : i + n]) == list(needle):
+            return True
+    return False
+
+
+# ---------------------------------------------------------------------------
+# Risk
+# ---------------------------------------------------------------------------
+#
+# Derived from the MCP annotations each tool already carries, so there is no
+# second risk table to drift out of step with the registrations. The ceiling a
+# caller may ask for, most permissive first:
+#
+#   any    everything (default — a search must not quietly narrow itself)
+#   write  hide tools that delete or overwrite (entity_delete_many, layer_delete,
+#          transaction_rollback, drawing_finalize, ...)
+#   read   only read-only query tools — the right ceiling for "how many ...?"
+RISK_CEILINGS = ("any", "write", "read")
+
+MAX_SEARCH_LIMIT = 25
+
+
+def tool_risk(tool: Tool) -> str:
+    """``"read"`` | ``"write"`` | ``"destructive"`` for one tool.
+
+    ``destructiveHint`` wins over ``readOnlyHint``: no tool in this catalog
+    sets both, and if one ever did, the safe reading is the destructive one.
+    Tools that annotate neither are treated as ``"write"`` — the honest default
+    for an unannotated tool on a server whose job is mutating drawings.
+    """
+    annotations = tool.annotations
+    if annotations is not None:
+        if annotations.destructiveHint:
+            return "destructive"
+        if annotations.readOnlyHint:
+            return "read"
+    return "write"
+
+
+def _risk_allowed(ceiling: str, level: str) -> bool:
+    if ceiling == "any":
+        return True
+    if ceiling == "write":
+        return level != "destructive"
+    return level == "read"
+
+
+@dataclass(frozen=True, slots=True)
+class SearchOutcome:
+    """One search: the tools shown, plus what the risk ceiling took away.
+
+    ``hidden`` holds only the tools the caller would otherwise have *seen* —
+    blocked hits inside the unfiltered top-``limit`` — not every blocked tool
+    in the catalog. That keeps the notice a fact about this answer.
+    """
+
+    hits: tuple[Tool, ...] = ()
+    hidden: tuple[Tool, ...] = ()
+    risk: str = "any"
+
+    def notice(self) -> str:
+        """One line naming what the risk ceiling removed, or ``""``.
+
+        A filter that silently halves a mixed intent ("list the layers then
+        delete GEOMETRY") is worse than no filter: the caller cannot tell the
+        difference between "no such tool" and "not shown to you".
+        """
+        if not self.hidden:
+            return ""
+        names = ", ".join(tool.name for tool in self.hidden)
+        return (
+            f"Risk filter: {len(self.hidden)} higher-risk match(es) hidden by "
+            f'risk="{self.risk}" ({names}). Re-run with risk="any" to include them.'
+        )
+
+
+class CadSearchTransform(BM25SearchTransform):
+    """BM25 tool search with the AutoCAD alias corpus folded into the index.
+
+    Args:
+        max_results: Default number of tools returned per search.
+        bm25_b: BM25 length-normalisation, left at the 0.75 textbook default —
+            the value every measured number in this module was obtained with.
+            Lowering it is defensible in principle (these "documents" are
+            metadata records of deliberately unequal verbosity, and a tool with
+            six synonyms is not a broader tool than one with two), but it was
+            not what shipped, so re-measure the golden set before changing it.
+    """
+
+    def __init__(
+        self,
+        *,
+        max_results: int = 5,
+        bm25_b: float = 0.75,
+        always_visible: list[str] | None = None,
+        search_tool_name: str = "search_tools",
+        call_tool_name: str = "call_tool",
+        search_result_serializer: SearchResultSerializer | None = None,
+    ) -> None:
+        super().__init__(
+            max_results=max_results,
+            always_visible=always_visible,
+            search_tool_name=search_tool_name,
+            call_tool_name=call_tool_name,
+            search_result_serializer=search_result_serializer or serialize_search_results,
+        )
+        self._bm25_k1 = self._index.k1
+        self._bm25_b = bm25_b
+
+    # ------------------------------------------------------------------
+    # Indexed document
+    # ------------------------------------------------------------------
+
+    def _extract_searchable_text(self, tool: Tool) -> str:
+        """Stock searchable text plus this tool's alias vocabulary.
+
+        The narrowest available hook: upstream's ``_extract_searchable_text``
+        is a module-level function, not a method, so it cannot be overridden in
+        place — it is called and extended instead. Tools with no alias record
+        (anything registered outside this server) keep the stock text
+        unchanged.
+        """
+        extra = alias_text(tool.name)
+        stock = _stock_searchable_text(tool)
+        return f"{stock} {extra}" if extra else stock
+
+    # ------------------------------------------------------------------
+    # Index lifecycle
+    # ------------------------------------------------------------------
+
+    def _ensure_index(self, tools: Sequence[Tool]) -> None:
+        """Rebuild the index when the catalog's indexed text changes.
+
+        The hash is order-sensitive on purpose: results are mapped back to
+        tools positionally, so a reordered catalog with identical text is still
+        a different index.
+
+        No lock: this and its only caller (:meth:`rank`) are synchronous and
+        await nothing, so two concurrent searches on one event loop cannot
+        interleave a rebuild with a query.
+        """
+        documents = [self._extract_searchable_text(t) for t in tools]
+        digest = hashlib.sha256("\x00".join(documents).encode()).hexdigest()
+        if digest == self._last_hash:
+            return
+        # Built via type() rather than importing the private _BM25Index name:
+        # the base class already owns an instance, and reusing its class keeps
+        # this from depending on a private module path.
+        index = type(self._index)(self._bm25_k1, self._bm25_b)
+        index.build(documents)
+        self._index = index
+        self._indexed_tools = tuple(tools)
+        self._last_hash = digest
+
+    # ------------------------------------------------------------------
+    # Ranking
+    # ------------------------------------------------------------------
+
+    def _alias_boost(self, tool: Tool, query: str, phrase_words: Sequence[str]) -> float:
+        record = aliases_for(tool.name)
+        if record is None:
+            return 0.0
+        boost = 0.0
+        if any(_names_a_command(query, command) for command in record.acad):
+            boost += ACAD_MATCH_BOOST
+        if any(_contains_phrase(phrase_words, _phrase_words(phrase)) for phrase in record.synonyms):
+            boost += SYNONYM_MATCH_BOOST
+        return boost
+
+    def rank(
+        self,
+        tools: Sequence[Tool],
+        query: str,
+        *,
+        limit: int | None = None,
+        risk: str = "any",
+    ) -> SearchOutcome:
+        """Rank ``tools`` against ``query``. Pure — no Context, no I/O."""
+        if risk not in RISK_CEILINGS:
+            raise ValueError(f"risk must be one of {RISK_CEILINGS}, got {risk!r}")
+        cutoff = self._max_results if limit is None else max(1, min(limit, MAX_SEARCH_LIMIT))
+        tools = list(tools)
+        if not tools:
+            return SearchOutcome(risk=risk)
+        self._ensure_index(tools)
+
+        ranked = self._index.query(query, len(tools))
+        bm25_points = {position: 1.0 / (1.0 + rank) for rank, position in enumerate(ranked)}
+        phrase_words = _phrase_words(query)
+
+        scored: list[tuple[float, str, Tool]] = []
+        for position, tool in enumerate(tools):
+            score = bm25_points.get(position, 0.0) + self._alias_boost(tool, query, phrase_words)
+            if score > 0.0:
+                scored.append((score, tool.name, tool))
+        scored.sort(key=lambda row: (-row[0], row[1]))
+        matches = [tool for _, _, tool in scored]
+
+        # Filter before truncating, so a blocked hit frees its slot for the
+        # next safe tool instead of just shortening the answer.
+        allowed = [tool for tool in matches if _risk_allowed(risk, tool_risk(tool))]
+        hidden = tuple(
+            tool for tool in matches[:cutoff] if not _risk_allowed(risk, tool_risk(tool))
+        )
+        return SearchOutcome(hits=tuple(allowed[:cutoff]), hidden=hidden, risk=risk)
+
+    async def _search(self, tools: Sequence[Tool], query: str) -> Sequence[Tool]:
+        return list(self.rank(tools, query).hits)
+
+    # ------------------------------------------------------------------
+    # The synthetic search tool
+    # ------------------------------------------------------------------
+
+    async def render(self, outcome: SearchOutcome) -> Any:
+        """Serialize an outcome, keeping the risk notice on its own line.
+
+        With the default (string) serializer the notice is appended as a
+        trailing line. A serializer that returns structured data instead gets
+        the notice as a sibling key, because there is no line to append to.
+        """
+        rendered = await self._render_results(outcome.hits)
+        notice = outcome.notice()
+        if not notice:
+            return rendered
+        if isinstance(rendered, str):
+            return f"{rendered}\n\n{notice}"
+        return {"results": rendered, "notice": notice}
+
+    def _make_search_tool(self) -> Tool:
+        transform = self
+        default_limit = self._max_results
+
+        async def search_tools(
+            query: Annotated[
+                str,
+                Field(
+                    description=(
+                        "What you want to do, in plain English or as an AutoCAD "
+                        "command name (FILLET, BPOLY, QSELECT, DLI)."
+                    )
+                ),
+            ],
+            limit: Annotated[
+                int,
+                Field(description=(f"How many tools to return. Clamped to 1..{MAX_SEARCH_LIMIT}.")),
+            ] = default_limit,
+            risk: Annotated[
+                Literal["any", "write", "read"],
+                Field(
+                    description=(
+                        "Highest risk level to return. 'any' (default) is everything; "
+                        "'write' hides tools that delete or overwrite; 'read' returns "
+                        "only read-only query tools — use it for questions like 'how "
+                        "many ...?'. Anything filtered out is reported in the result."
+                    )
+                ),
+            ] = "any",
+            ctx: Context = None,  # type: ignore[assignment]
+        ) -> Any:
+            """Find the AutoCAD tools that do a job.
+
+            Accepts AutoCAD command names as well as English. Returns one
+            compact line per tool: name, risk level, what it does, its required
+            arguments and the AutoCAD command it corresponds to. Call a result
+            with call_tool.
+            """
+            visible = await transform._get_visible_tools(ctx)
+            outcome = transform.rank(visible, query, limit=limit, risk=risk)
+            return await transform.render(outcome)
+
+        return Tool.from_function(fn=search_tools, name=self._search_tool_name)

docs/RELEASE-DISTRIBUTION.md

@@ -0,0 +1,51 @@
+# Release & Distribution Runbook (v1.4.0+)
+
+The code side of a release is fully automated; three account-bound steps need
+a human once, plus the directory submissions. Track them here.
+
+## One-time setup (owner action)
+
+- [ ] **PyPI trusted publisher** — on <https://pypi.org/manage/account/publishing/>
+  add a *pending publisher* for project `autocad-mcp-pro`:
+  repository `U-C4N/Autocad-MCP`, workflow `release.yml`, environment `pypi`.
+  (No API token is stored anywhere; `release.yml` uses OIDC.)
+- [ ] **GitHub environment** — create the `pypi` environment in the repo
+  settings (Settings → Environments) so the publish job can bind to it.
+- [ ] **MCP registry login** — install `mcp-publisher`, then
+  `mcp-publisher login github` (authenticates the `io.github.u-c4n` namespace).
+
+## Every release
+
+1. Bump `pyproject.toml` + `server.json` versions, add the CHANGELOG section,
+   update the README snapshot line — `tests/test_release_consistency.py`
+   enforces all of it.
+2. Push `main`, wait for CI to go green (lint, linux, windows, package,
+   docker, registry-validate).
+3. Tag and push: `git tag v1.4.0 && git push origin v1.4.0`.
+   `release.yml` runs the test gate, verifies tag == package version, builds,
+   publishes to PyPI via trusted publishing and cuts the GitHub Release.
+4. Verify: `pip install autocad-mcp-pro==<version>` in a clean venv;
+   `uvx autocad-mcp-pro --help`.
+5. Publish the registry manifest: `mcp-publisher publish` (validates
+   `server.json`, checks the `mcp-name` marker in the PyPI README).
+
+## Directory listings (submit once, then keep fresh)
+
+- [ ] Glama — <https://glama.ai/mcp/servers> (auto-indexes GitHub; claim the
+  server page and verify metadata).
+- [ ] mcpservers.org — submit via their GitHub repo PR flow.
+- [ ] awesome-mcp-servers — PR adding the server under CAD/engineering.
+- [ ] Smithery — optional; requires a `smithery.yaml` (evaluate demand first).
+
+## Benchmark refresh (per release)
+
+```bash
+python -m benchmarks.run_competitors --server autocad-mcp-pro --backend ezdxf
+python -m benchmarks.run_competitors --server puran-water-autocad-mcp --backend ezdxf
+python -m benchmarks.run_competitors --server beiming183-autocad-mcp --backend ezdxf
+# sanitize + copy reports into benchmarks/results/published/, then:
+python -m benchmarks.render_live_chart
+```
+
+Bump the competitor pins in `benchmarks/competitors.yaml` deliberately (new
+SHA = re-read their tool contracts before trusting the mappings).

docs/analysis/track-a-review-backlog.md

@@ -0,0 +1,292 @@
+# Track A (v1.6 P&ID) — review backlog
+
+**Source:** the plan-compliance and adversarial review rounds of Track A (2026-09-15/16),
+waves 1–4. Blocking findings were fixed inside Track A (`fix(task-N)` commits) and are
+not listed. Every *minor* finding is here, de-duplicated, with one disposition:
+
+- **fixed-in-task-N** — Track E group H (`docs/superpowers/plans/2026-09-16-v1.6-settings-implementation.md`, Tasks 1–7)
+- **fixed-in-track-A** — resolved on main by a later Track A commit (evidence cited)
+- **accepted-limitation** — kept as is, with the reason
+- **deferred-1.7** — a real item for the 1.7 roadmap
+
+Reading key: `W1-T1-03` = wave 1, Track A Task 1, finding 3. Files are repository-relative.
+
+## Wave 1
+
+#### Track A Task 1 — `block_insert(attributes=…)` (ezdxf)
+
+| ID | File | Finding | Disposition |
+|---|---|---|---|
+| W1-T1-01 | backends/ezdxf_backend.py | The undefined-block gate (`6f4bda5`) was added without being listed as a deviation. | accepted-limitation (reporting gap; the gate is kept and shared by Task 1) |
+| W1-T1-02 | plan | Branch forked before the docs commits; no code diverged. | accepted-limitation (process; merged clean) |
+| W1-T1-03 | backends/ezdxf_backend.py | `attributes` was coerced after `add_blockref`, so a non-mapping failed after the write and skipped `_mark_dirty`. | fixed-in-task-3 |
+| W1-T1-04 | backends/ezdxf_backend.py | `str(v)` wrote Python reprs (`None`, `True`, a dict) into ATTRIBs on both engines. | fixed-in-task-3 |
+| W1-T1-05 | backends/ezdxf_backend.py | Tag matching is exact-case; `{"tag": …}` silently drops against ATTDEF `TAG`. | deferred-1.7 (normalise keys to upper case; the server's own ATTDEF tags are upper-case by `ATTDEF_TAG_RE`) |
+| W1-T1-06 | backends/ezdxf_backend.py | `*Model_Space` / `*Paper_Space` pass the existence check and insert a reference cycle. | fixed-in-task-1 |
+| W1-T1-07 | backends/ezdxf_backend.py | `entity_create_block_ref` still accepts an undefined block; `doc.audit()` deletes the INSERT later. | fixed-in-task-1 |
+| W1-T1-08 | tests/test_block_insert_attributes.py | `attributes=None` yields no ATTRIBs headlessly while COM's `InsertBlock` instantiates ATTDEF defaults; refusal types diverged (ValueError vs RuntimeError). | refusal type: fixed-in-task-1 (COM raises the same ValueError); default ATTRIBs: deferred-1.7 (engine divergence on ATTDEF defaults) |
+| W1-T1-09 | backends/ezdxf_backend.py | `block_explode` drops the ATTRIB text. | fixed-in-task-2 |
+
+#### Track A Task 2 — `backends/block_specs.py`
+
+| ID | File | Finding | Disposition |
+|---|---|---|---|
+| W1-T2-01 | security.py | `illegal_symbol_name_chars` added outside the task's file list, unreported. | accepted-limitation (reporting gap; harmless, tested) |
+| W1-T2-02 | backends/block_specs.py | `fullmatch`, layer-character gate and `_one_line` are stricter than the plan stated. | accepted-limitation (all serve the validate-before-write rule; pinned by tests) |
+| W1-T2-03 | plan / spec | Spec §4.7 per-entity `color`/`linetype`/`lineweight` overrides were dropped by the plan; unknown keys are silently ignored. | deferred-1.7 (carry the three keys through or refuse unknown keys by index) |
+| W1-T2-04 | backends/block_specs.py | `_scalar` let `10**400` escape as `OverflowError` instead of the named `TypeError`. | fixed-in-task-4 |
+| W1-T2-05 | backends/block_specs.py | A non-list `entities` (dict, str, generator) is refused as "empty". | deferred-1.7 |
+| W1-T2-06 | backends/block_specs.py | `_layer` gates characters but not the 255-char length rule. | deferred-1.7 |
+| W1-T2-07 | backends/block_specs.py | Refusal messages echo the caller's value unbounded (`got {value!r}`; measured 2 MB messages). | deferred-1.7 (truncate with reprlib) |
+| W1-T2-08 | backends/block_specs.py | Same as W1-T2-03 (unknown keys such as `rotation` silently dropped). | deferred-1.7 (with W1-T2-03) |
+
+#### Track A Task 6 — ISA-5.1 tag grammar
+
+| ID | File | Finding | Disposition |
+|---|---|---|---|
+| W1-T6-01 | engineering/pid/tags.py | Three grammar changes (X user-defined, no output after V, O/C only after ZS) unreported. | accepted-limitation (the fixture is the contract; documented in `describe_tables()['rules']`) |
+| W1-T6-02 | engineering/pid/tags.py | Two of those go past the spec §8 wording. | accepted-limitation (spec text to be reconciled by the 1.7 docs pass) |
+| W1-T6-03 | spec | Spec example meanings (`Flow rate`/`Indicate`/`Control`) differ from the tables (`Flow`/`Indicator`/`Controller`). | accepted-limitation (keys match; consumers pin the tables) |
+| W1-T6-04 | engineering/pid/tags.py | The "unexpected letter" error names the first trailing letter, not the offender (`LAHX-1` → reports H). | deferred-1.7 |
+| W1-T6-05 | engineering/pid/tags.py | `equipment_prefixes={}` falls back to the default map (`or` instead of `is None`); non-string values pass through. | deferred-1.7 (also W4-T19-05) |
+| W1-T6-06 | tests/data/isa51_tags.json | No fixture row for K (rate of change / control station), M trailing, O readout, B/N/X user-defined readouts. | deferred-1.7 (≈5 rows) |
+| W1-T6-07 | engineering/pid/tags.py | O/C trailing narrowed to Z-first tags beyond the spec text. | accepted-limitation (documented resolution of a spec/fixture conflict) |
+
+#### Track A Task 12 — `engineering/pid/lines.py`
+
+| ID | File | Finding | Disposition |
+|---|---|---|---|
+| W1-T12-01 | engineering/pid/lines.py | `axis_direction`, the `string.Formatter` parser and finiteness checks were added unreported. | accepted-limitation (reporting gap; pinned by tests) |
+| W1-T12-02 | engineering/pid/__init__.py | Created outside the task's file list (branch predated Task 5). | accepted-limitation (byte-identical to Task 5's) |
+| W1-T12-03 | engineering/pid/lines.py | `direct` and waypoint modes accept a negative / NaN `stub`. | deferred-1.7 (hoist the stub check above the mode branch) |
+| W1-T12-04 | engineering/pid/lines.py | A malformed waypoint (`{"x":…}`, a flat list) escapes as `KeyError` / `TypeError` instead of `ValueError` naming `waypoints[i]`. | deferred-1.7 (also W3-T13-11) |
+| W1-T12-05 | engineering/pid/lines.py | `count_crossings` undercounts a crossing that lands exactly on the other polyline's vertex. | deferred-1.7 (reported metric; orthogonal auto routes cannot produce it) |
+| W1-T12-06 | engineering/pid/lines.py | A format spec containing `-` (`{seq:-05d}`) is refused with a misleading message. | accepted-limitation (a refusal, not a wrong number; hyphen inside a field spec is unsupported) |
+| W1-T12-07 | engineering/pid/lines.py | `label_placement([(0,0)])` raises an unnamed error; a closed-loop waypoint route is accepted; `{{seq}}` is copied through. | accepted-limitation (unreachable through the tools; cosmetic) |
+
+## Wave 2
+
+#### Track A Task 3 — `block_define`
+
+| ID | File | Finding | Disposition |
+|---|---|---|---|
+| W2-T3-01 | README.md | Snapshot bumped while lines 23/30/106 still said 154. | fixed-in-track-A (Task 21 README rewrite: "166 tools in 20 groups") |
+| W2-T3-02 | tests/test_tool_registry.py | Frozen snapshot edited outside the file list. | accepted-limitation (required by the gate; the precedent every later task follows) |
+| W2-T3-03 | backends/ezdxf_backend.py | `base_x`/`base_y` only `float()`-cast; NaN written into the BLOCK record. | fixed-in-task-4 |
+| W2-T3-04 | backends/ezdxf_backend.py | A primitive layer is written without a layer-table entry; COM would fail mid-loop. | fixed-in-task-4 |
+| W2-T3-05 | README.md | Same as W2-T3-01. | fixed-in-track-A |
+| W2-T3-06 | backends/ezdxf_backend.py | ATTDEF linetype stays BYLAYER on ezdxf vs ByBlock on COM; neither sets lineweight ByBlock. | deferred-1.7 (cosmetic; layer-0 members resolve to the INSERT's layer) |
+| W2-T3-07 | backends/ezdxf_backend.py | `attdefs or []` turns `{}`/`''` into "no ATTDEFs"; a non-str `name` raises AttributeError. | deferred-1.7 |
+| W2-T3-08 | backends/ezdxf_backend.py | `block_insert` without `attributes` carries none of the ATTDEF defaults (COM does). | deferred-1.7 (with W1-T1-08) |
+
+#### Track A Task 4 — XDATA
+
+| ID | File | Finding | Disposition |
+|---|---|---|---|
+| W2-T4-01 | discovery/aliases.py | `entity_get_xdata` ships `XDLIST` only (XDATA would break the single-route gate). | accepted-limitation (still discoverable; reporting gap) |
+| W2-T4-02 | tests/test_tool_registry.py | Snapshot edited outside the file list. | accepted-limitation (gate precedent) |
+| W2-T4-03 | backends/ezdxf_backend.py | APPID names are case-sensitive headlessly; `APP_A` and `app_a` become two groups and double-count the budget. | deferred-1.7 |
+| W2-T4-04 | backends/com_backend.py | A no-op removal registers the APPID on COM but not on ezdxf. | deferred-1.7 |
+| W2-T4-05 | backends/xdata_specs.py | 1004 binary chunks decode to the repr of a bytes object. | deferred-1.7 (hex string) |
+| W2-T4-06 | backends/xdata_specs.py | The reserved-app rule blocks reading `ACAD` by name while the unfiltered read returns it; other AutoCAD-owned apps are writable. | deferred-1.7 |
+| W2-T4-07 | README.md | Snapshot paragraph contradicted itself; collected-tests drift. | fixed-in-track-A (Task 21) |
+
+#### Track A Task 5 — `engineering/pid/xdata.py`
+
+| ID | File | Finding | Disposition |
+|---|---|---|---|
+| W2-T5-01 | engineering/pid/__init__.py | Listed as "create" but already existed. | accepted-limitation (nothing missing) |
+| W2-T5-02 | tests/test_pid_xdata.py | Sync tests under a module-level `pytest.mark.asyncio` emit PytestWarnings. | deferred-1.7 (hygiene sweep across the pid test modules) |
+| W2-T5-03 | spec | Spec payload (`actuator`, 3-element ports, no `seq`) vs plan (`variant`, 5-element ports, `seq`). | accepted-limitation (plan governs; spec text to reconcile) |
+| W2-T5-04 | engineering/pid/xdata.py | `encode_payload` uses `allow_nan=True`; a NaN would be serialised as a non-RFC literal. | deferred-1.7 (`allow_nan=False`; no current caller can deliver one after Task 5) |
+| W2-T5-05 | engineering/pid/xdata.py | `symbol_payload(params={})` is replaced by the spec's params (truthiness). | deferred-1.7 |
+| W2-T5-06 | engineering/pid/xdata.py | Duplicate port names collapse silently (last wins). | deferred-1.7 (refuse in `make_spec`) |
+| W2-T5-07 | engineering/pid/xdata.py | A non-dict payload is written and can never be read back. | deferred-1.7 |
+| W2-T5-08 | tests/test_pid_xdata.py | No multi-chunk payload round trip through a backend. | deferred-1.7 (test gap; the path was verified by hand) |
+
+#### Track A Task 7 — symbol framework
+
+| ID | File | Finding | Disposition |
+|---|---|---|---|
+| W2-T7-01 | engineering/pid/symbols.py | Per-type outlines (no circle for computer/plc) deviate from the plan snippet, unreported. | accepted-limitation (the spec's ISA table governs; tests added) |
+| W2-T7-02 | tests/test_pid_symbols.py | Unused import dropped, `math` added. | accepted-limitation (no functional effect) |
+| W2-T7-03 | engineering/pid/symbols.py | Rear-location dashed lines stop up to 1 mm short on the right. | accepted-limitation (cosmetic; no port, bbox or gate depends on it) |
+| W2-T7-04 | engineering/pid/symbols.py | A single radial `signal` port cannot describe the hexagon/square outlines (0.67 mm gap on vertical lines into `computer`). | accepted-limitation (spec §4.4 model; a per-axis reach is a 1.7 item) |
+| W2-T7-05 | engineering/pid/symbols.py | `all_specs()` swallows builder ValueErrors and nothing pins the catalogue size. | deferred-1.7 (assert `len(all_specs())`) |
+| W2-T7-06 | engineering/pid/symbols.py | `register()` overwrites silently; `list_symbols()` returns variants by reference. | deferred-1.7 |
+| W2-T7-07 | engineering/pid/geometry.py | `bbox_of` samples arcs at 1° and can under-report by 3.8e-5·r. | accepted-limitation (sub-lineweight) |
+
+#### Track A Task 8 — valves
+
+| ID | File | Finding | Disposition |
+|---|---|---|---|
+| W2-T8-01 | plan | The plan file was edited to match the shipped geometry, unreported. | accepted-limitation (the original geometry floated the dome; evidence in the commit) |
+| W2-T8-02 | engineering/pid/symbols_valves.py | `check`/`relief` advertise actuator variants they refuse. | deferred-1.7 (variants `["none"]` for those bodies) |
+| W2-T8-03 | engineering/pid/symbols_valves.py | The diaphragm *body* dome floats 1 mm above the bow-tie. | deferred-1.7 (cosmetic) |
+| W2-T8-04 | engineering/pid/symbols_valves.py | The `signal` port and the TAG/DESC text share x = 0 above the actuator; a signal line crosses the tag. | accepted-limitation (spec §4.7 placement; a tag/line overlap critique is a 1.7 item, with W2-T9-05) |
+
+#### Track A Task 9 — equipment
+
+| ID | File | Finding | Disposition |
+|---|---|---|---|
+| W2-T9-01 | engineering/pid/symbols_equipment.py | `pd_pump` ports are `in`/`out`, spec says `suction`/`discharge`. | accepted-limitation (plan governs; spec text to reconcile; `pid_from_spec` names ports explicitly) |
+| W2-T9-02 | engineering/pid/symbols_equipment.py | `spectacle_blind` cites ISO 10628-2 instead of PIP PIC001; no spec names its figure/table. | deferred-1.7 (provenance strings) |
+| W2-T9-03 | engineering/pid/symbols_equipment.py | Same as W2-T9-01. | accepted-limitation |
+| W2-T9-04 | engineering/pid/symbols_equipment.py | `build_equipment` ignores `shape` for non-reducers and its signature is narrower than `**options`. | accepted-limitation (`resolve()` validates options; builders are internal) |
+| W2-T9-05 | engineering/pid/symbols_equipment.py | TAG/DESC sit on the outward ray of every +Y port. | accepted-limitation (with W2-T8-04) |
+| W2-T9-06 | engineering/pid/symbols_equipment.py | `air_cooler` fan cross pokes 0.046 mm outside its circle. | deferred-1.7 (cosmetic, ±1.75) |
+| W2-T9-07 | engineering/pid/symbols_equipment.py | Seven origins are not the bbox centre (spec §4.2). | accepted-limitation (deliberate mounting points; spec text to reconcile) |
+
+#### Track A Task 10 — vessels
+
+| ID | File | Finding | Disposition |
+|---|---|---|---|
+| W2-T10-01 | engineering/pid/geometry.py | `scan_hits` added outside the file list, unreported. | accepted-limitation (additive, tested) |
+| W2-T10-02 | engineering/pid/symbols_vessels.py | Stricter size rules and outline-based stubs, unreported. | accepted-limitation (evidence in the commit; plan tests unchanged) |
+| W2-T10-03 | spec | `PID_VESSEL_VERTICAL_` vs `PID_VESSEL_VERTICAL_VESSEL_`. | accepted-limitation (plan's general rule governs) |
+| W2-T10-04 | engineering/pid/symbols_vessels.py | Non-finite sizes/fractions pass `validate_vessel_params` (NaN spec, `RuntimeError` for inf). | deferred-1.7 (`math.isfinite` next to `> 0`) |
+| W2-T10-05 | engineering/pid/symbols_vessels.py | Column tray lines poke through dished heads (up to 1.8 mm). | deferred-1.7 (clip to the outline with `scan_hits`) |
+| W2-T10-06 | engineering/pid/symbols_vessels.py | Nozzle fractions near 0/1 on curved/sloped sides give degenerate long stubs from a corner. | deferred-1.7 |
+| W2-T10-07 | engineering/pid/symbols_vessels.py | `trays` is unbounded (1 000 000 trays build in 6.3 s / 272 MB). | deferred-1.7 (cap by spacing ≥ 1 mm) |
+| W2-T10-08 | engineering/pid/symbols_vessels.py | Two nozzles at the same side+fraction duplicate the stub; `-0.0` hashes to a different block name. | deferred-1.7 |
+
+## Waves 3–4
+
+#### Track A Task 11 — `pid_symbol_list` / `pid_symbol_insert`
+
+| ID | File | Finding | Disposition |
+|---|---|---|---|
+| W3-T11-01 | engineering/layers.py | `PROCESS-LINE-TEXT` inserted at position 9; spec said "16th entry". | accepted-limitation (count matches; ordinal wording only) |
+
+#### Track A Task 13 — `pid_line_draw`
+
+| ID | File | Finding | Disposition |
+|---|---|---|---|
+| W3-T13-01 | tests/test_tool_registry.py | Snapshot edited outside the file list. | accepted-limitation (gate precedent) |
+| W3-T13-02 | discovery/aliases.py | `PLINE` added to `SHARED_ACAD_COMMANDS`. | accepted-limitation (required by the single-route gate; documented in the allowlist comment) |
+| W3-T13-03 | backends/com_backend.py | `e924b5d` touched three files outside the list, unreported (COM `AcDbPolyline` naming, mirrored ports). | accepted-limitation (both were defects; tests added) |
+| W3-T13-04 | server.py | `>=` for `≥` in a docstring. | accepted-limitation (cosmetic) |
+| W3-T13-05 | engineering/pid/drawlines.py | Line sequence is per current space, not per document (spec §6.3). | deferred-1.7 (document-wide scan of existing lines) |
+| W3-T13-06 | engineering/pid/drawlines.py | Every signal line got a fabricated number and label and consumed the process sequence. | fixed-in-task-6 |
+| W3-T13-07 | engineering/pid/drawlines.py | A bubble's exit aimed at the far end even with waypoints, so the first segment cut through the bubble. | fixed-in-task-6 |
+| W3-T13-08 | engineering/pid/drawlines.py | A foreign/hand-edited payload with a non-dict `from`/`to` raised `TypeError` out of `draw_line`. | fixed-in-task-7 |
+| W3-T13-09 | engineering/pid/drawlines.py | (a) crossings tested against chords, not arcs; (b) COM heavy 2DPOLYLINE `Coordinates` read with stride 2. | (a) fixed-in-task-7; (b) deferred-1.7 (heavy polylines the tool never creates) |
+| W3-T13-10 | README.md | Snapshot line edited without the collected-tests figure. | fixed-in-track-A (Task 21) |
+| W3-T13-11 | server.py | An unknown endpoint handle and a flat waypoint list surface as "Internal error" rather than a named refusal. | deferred-1.7 (with W1-T12-04) |
+
+#### Track A Task 14 — `pid_graph`
+
+| ID | File | Finding | Disposition |
+|---|---|---|---|
+| W3-T14-01 | engineering/pid/graph.py | Block-name keywords match whole tokens, not substrings (spec §9.2); `GATEVALVE` no longer classifies. | accepted-limitation (the plan's own test demands it; documented in code) |
+| W3-T14-02 | backends/ezdxf_backend.py | A public `bulges` key was added to every LWPOLYLINE `entity_get`, unreported. | accepted-limitation (additive; spec §9.4 "geometry from the drawing"; now consumed by Task 7) |
+| W3-T14-03 | tests/test_tool_registry.py | Snapshot edited outside the file list. | accepted-limitation (gate precedent) |
+| W3-T14-04 | engineering/pid/graph.py | Edge dict carries `length_approximate` and (with geometry) `bulges` beyond the spec. | accepted-limitation (additive) |
+| W3-T14-05 | tests/test_pid_graph.py | Three sync tests under the asyncio mark warn. | deferred-1.7 (hygiene, with W2-T5-02) |
+| W3-T14-06 | engineering/pid/graph.py | `_Edge.segments` omits a closed polyline's closing edge while `length` includes it. | deferred-1.7 |
+| W3-T14-07 | engineering/pid/graph.py | The dangling `nearest` hint never names a radial (bubble) port. | deferred-1.7 |
+| W3-T14-08 | engineering/pid/graph.py | Text-tag fallback searched a circle, not "above the box". | fixed-in-track-A (`d17a261`, `6ad3734`: tags above the box, `LINE_NUMBER_RE` excluded) |
+| W3-T14-09 | engineering/pid/graph.py | `scope="all"` restores `current` but not the paper-space layout binding. | deferred-1.7 |
+| W3-T14-10 | engineering/pid/graph.py | A −Z-extruded catalogue INSERT reported mirror-image ports at confidence 1.0. | fixed-in-track-A (`6ad3734`: both engines report `mirrored`; `transform_port(mirrored=)`) |
+| W3-T14-11 | engineering/pid/graph.py | A `PID_*` INSERT whose XDATA was stripped falls to the 0.6 heuristic with no ports (spec says catalogue 1.0). | deferred-1.7 |
+| W3-T14-12 | README.md | Release-consistency gate red on the collected-tests figure. | fixed-in-track-A (Task 21) |
+| W3-T14-13 | engineering/pid/symbols.py | `6ad3734` touched five files outside the list; `transform_port` grew `mirrored`/`strict`. | accepted-limitation (justified; interface kept by keyword defaults) |
+| W3-T14-14 | engineering/pid/graph.py | `_text_near` accepts a baseline half a height inside the box and excludes line-number texts — beyond the spec wording. | accepted-limitation (documented, tested) |
+| W3-T14-15 | engineering/pid/graph.py | Node dicts gained `y_scale`, `mirrored`, `notes`, `space`, `description`; junctions `space`. | accepted-limitation (additive) |
+| W3-T14-16 | docs (plan/spec) | `ruff format --check` was red on the plan and spec Markdown. | fixed-in-track-A (Task 21 formatted them) |
+| W3-T14-17 | spec | §9.1 model not extended for the added node/junction keys. | deferred-1.7 (docs) |
+| W3-T14-18 | engineering/pid/symbols.py | `strict=False` keeps a diagonal port's local angle under non-uniform scale. | accepted-limitation (unreachable: all 243 catalogue ports are axis-aligned) |
+| W3-T14-19 | backends/ezdxf_backend.py | `mirrored` is `True` for a tilted INSERT with a negative-z normal (COM twin too). | deferred-1.7 (`flat and z < 0`) |
+
+#### Track A Task 15 — deliverables
+
+| ID | File | Finding | Disposition |
+|---|---|---|---|
+| W3-T15-01 | tests/test_pid_deliverables.py | Four plan deviations (line-list rows, `_far_ends`, CSV refusal, `deliverable()` ValueError) unreported. | accepted-limitation (each stronger than the plan; the plan's own numbers were wrong) |
+| W3-T15-02 | tests/test_tool_registry.py | Snapshot edited outside the file list. | accepted-limitation (gate precedent) |
+| W3-T15-03 | tests/_probe_task15.py | A stray probe file appeared during review. | fixed-in-track-A (not in the tree) |
+| W3-T15-04 | engineering/pid/deliverables.py | `natural_key` crashes on `str.isdigit()` runs that are not `\d` (①, ²). | deferred-1.7 (`isdecimal`) |
+| W3-T15-05 | engineering/pid/deliverables.py | `_far_ends` resolves junctions at the ends of the instrument's line only, not on it. | deferred-1.7 |
+| W3-T15-06 | engineering/pid/deliverables.py | `_tag_of` writes the internal junction id into a tag column; untagged node ends are `None` vs handle in the index. | deferred-1.7 |
+| W3-T15-07 | engineering/pid/deliverables.py | `write_csv` edge cases: 0-byte file for zero rows, `csv_path=''` treated as None, directory path escapes as PermissionError, dead `mkdir`, late validation. | deferred-1.7 |
+| W3-T15-08 | engineering/pid/deliverables.py | CSV formula injection: cells starting with `=+-@` are written verbatim. | deferred-1.7 (first item of the 1.7 deliverables pass) |
+| W3-T15-09 | server.py | The three deliverable tools expose only `tolerance`/`scope`, not `label_search`/`include_foreign`. | deferred-1.7 |
+| W3-T15-10 | engineering/pid/deliverables.py | `signal_lines` counts every edge on a bubble regardless of class. | deferred-1.7 |
+
+#### Track A Task 16 — critique focuses
+
+| ID | File | Finding | Disposition |
+|---|---|---|---|
+| W3-T16-01 | tests/test_pid_critique.py | The refine test calls `refine_drawing` (no backend `drawing_refine` exists), unreported. | accepted-limitation (the plan's call could not run; stricter test) |
+| W3-T16-02 | engineering/pid/critique.py | `has_pid_content` guard instead of `not graph['nodes']`, unreported. | accepted-limitation (spec intent; pinned by tests) |
+| W3-T16-03 | engineering/pid/critique.py | `_incompatible` skips inferred ports; `_dangling` reports unknown_block ends — beyond the plan. | accepted-limitation (spec §9.4 / §11.1; tested) |
+| W3-T16-04 | tests/test_pid_critique.py | Two sync tests warn under the asyncio mark. | deferred-1.7 (hygiene) |
+| W3-T16-05 | engineering/pid/critique.py | `_untagged` tests the composed tag, not FUNC/LOOP; an empty LOOP files as `pid_illegal_tag`. | deferred-1.7 |
+| W3-T16-06 | engineering/pid/critique.py | A mechanical block whose name holds a keyword token (`OIL_FILTER`) counts as P&ID content and can fail finalize. | accepted-limitation (spec §9.2 mandates the heuristic; README "Known limitations" states it) |
+| W3-T16-07 | engineering/pid/critique.py | `_duplicate_tags` scores a text-derived (guessed) tag as a gate-failing error. | deferred-1.7 (warning for `tag_source: text`) |
+
+#### Track A Task 17 — `pid_from_spec`
+
+| ID | File | Finding | Disposition |
+|---|---|---|---|
+| W4-T17-01 | tests/test_pid_from_spec.py | Four reported deviations verified legitimate (save_path, score dict, async test, snapshot). | accepted-limitation |
+| W4-T17-02 | engineering/pid/spec.py | The module is a refactor of the plan's listing; interfaces preserved. | accepted-limitation |
+| W4-T17-03 | README.md | `pid-showcase.png` rendered but not referenced. | fixed-in-track-A (README line 20 embeds it) |
+| W4-T17-04 | tests/test_release_consistency.py | Collected-tests drift. | fixed-in-track-A (Task 21) |
+| W4-T17-05 | engineering/pid/spec.py | `_num` accepts NaN/inf; an INSERT lands at `[nan, 0]` and `build_graph` crashes. | fixed-in-task-5 |
+| W4-T17-06 | engineering/pid/spec.py | `run_spec` catches `Exception` only; a cancellation leaves an open transaction. | fixed-in-task-5 |
+| W4-T17-07 | engineering/pid/spec.py | `dry_run` skips `place_symbol`'s option checks (`scale=-1` approved; wrong item blamed). | deferred-1.7 (`validate_spec` owns scale/fail/actuator rules) |
+| W4-T17-08 | engineering/pid/spec.py | `dry_run` crossings count the spec's own lines only, unlabelled. | deferred-1.7 (`crossings_scope` field) |
+| W4-T17-09 | engineering/pid/spec.py | Nested transactions: ezdxf nests, COM refuses; `drawing_plan` is set before the refusal. | deferred-1.7 |
+| W4-T17-10 | engineering/pid/spec.py | The `sheet` block is not validated (unknown layer set / sheet size / keys accepted). | deferred-1.7 |
+| W4-T17-11 | engineering/pid/spec.py | String-typed optional keys unvalidated (`arrow: "no"` truthy; `number: 123` bare TypeError; `id` with a dot). | deferred-1.7 |
+| W4-T17-12 | README.md | README showcase half incomplete; gate red. | fixed-in-track-A (Task 21) |
+
+#### Track A Task 19 — tag parse, resources, prompt
+
+| ID | File | Finding | Disposition |
+|---|---|---|---|
+| W4-T19-01 | tests/test_tool_registry.py | Snapshot edited outside the file list. | accepted-limitation (gate precedent) |
+| W4-T19-02 | scripts/render_pid_catalog.py | Renders through its own matplotlib path instead of `view_screenshot`, unreported. | accepted-limitation (byte-reproducible output; interface kept) |
+| W4-T19-03 | README.md | Lines 23/106 still said 154 / 6 resources. | fixed-in-track-A (Task 21) |
+| W4-T19-04 | server.py | The prompt's OFF-PAGE example emits a tag warning every time it is followed (`TO P&ID-002` parsed as ISA-5.1). | deferred-1.7 (skip `parse_tag` for connectors at insert) |
+| W4-T19-05 | engineering/pid/tags.py | `equipment_prefixes={}` discarded; non-string values pass. | deferred-1.7 (with W1-T6-05) |
+| W4-T19-06 | README.md | Release gate red on the collected-tests figure. | fixed-in-track-A (Task 21) |
+
+#### Track A Task 18 — `TOOL_PACKS`
+
+| ID | File | Finding | Disposition |
+|---|---|---|---|
+| W4-T18-01 | tests/test_tool_packs.py | A sync test warns under the asyncio mark. | deferred-1.7 (hygiene) |
+| W4-T18-02 | README.md / config.py / .env.example | Token table and prose said 47 while lean has 50. | README: fixed-in-track-A (Task 21); `config.py:99` / `.env.example:52` "~47": deferred-1.7 (docs) |
+| W4-T18-03 | server.py | `TOOL_PACKS=all,mech3000` drops the unknown entry without a warning or `ignored`. | deferred-1.7 |
+| W4-T18-04 | server.py | `_enabled_packs()` runs twice per apply; unknown entries warn twice and duplicate in `ignored`. | deferred-1.7 |
+| W4-T18-05 | tests/test_tool_packs.py | The pack test compares against a hand-copied set, never the registry. | deferred-1.7 (assert against `_registered_tools()` tags) |
+| W4-T18-06 | server.py | Under `TOOL_PACKS=core` the P&ID prompt and resources are still advertised. | accepted-limitation (spec §12 scopes packs to tools) |
+
+#### Track A Task 20 — benchmark v4
+
+| ID | File | Finding | Disposition |
+|---|---|---|---|
+| W4-T20-01 | scripts/check_doc_numbers.py | The gate short-circuited on the 29-vs-26 A/B drift. | fixed-in-track-A (Task 21 regenerated the A/B report) |
+| W4-T20-02 | CLAUDE.md | An extra clause beyond the dictated sentence. | accepted-limitation (accurate) |
+| W4-T20-03 | benchmarks/README.md | "16/16 on the v4 matrix" has no published artifact behind it. | deferred-1.7 (publish a v4 reference report at the 1.6 release) |
+| W4-T20-04 | tests/test_benchmark_v4.py | No test executes `_task_pid_roundtrip`. | deferred-1.7 (Task 6 of the hardening plan runs it by hand) |
+| W4-T20-05 | benchmarks/README.md | A/B rows said 29 checks over a 26-check report. | fixed-in-track-A (Task 21) |
+
+#### Track A Task 21 — docs and smoke
+
+| ID | File | Finding | Disposition |
+|---|---|---|---|
+| W4-T21-01 | scripts/smoke_pid_com.py | Not re-run live during review (no AutoCAD running). | accepted-limitation (the implementer's live run is recorded in the CHANGELOG) |
+| W4-T21-02 | README.md | "Known limitations of the P&ID track" was not a plan item. | accepted-limitation (claims verified against the code) |
+| W4-T21-03 | docs (plan) | The plan file was ruff-formatted outside the file list. | accepted-limitation (mechanical) |
+| W4-T21-04 | benchmarks/README.md | Tables moved for the new gate labels. | accepted-limitation (required by `check_doc_numbers.py`) |
+| W4-T21-05 | CHANGELOG.md | "12.5 % short on a semicircular jump" is the v1.5 square figure; the tested geometry is 10.25 %. | deferred to the final docs task of Track E (CHANGELOG `Unreleased` edit) |
+| W4-T21-06 | README.md | The snapshot is labelled v1.5 while quoting the 1.6-dev surface. | accepted-limitation (pinned to pyproject's minor until the 1.6 bump) |
+| W4-T21-07 | scripts/smoke_pid_com.py | Exit code checks `dangling` only; critique/confidence/xdata are printed, not asserted. | deferred-1.7 |
+| W4-T21-08 | CHANGELOG.md | `LAYER_SET_INTENT_MISMATCH` is claimed for `drawing_plan`, which only appends a warning string. | deferred to the final docs task of Track E |
+
+## Totals
+
+165 rows. Fixed in this track (Tasks 1–7): 15 · fixed inside Track A: 17 · accepted with a reason: 62 · deferred (1.7 or the Track E docs task): 71.

docs/superpowers/plans/2026-07-17-repository-cleanup-readme-benchmark.md

@@ -448,10 +448,7 @@ def render_chart(data: dict[str, Any], output: Path) -> None:
     labels = [item["repository"] for item in projects]
     scores = [item["score"] for item in projects]
     grades = [item["evidence_grade"] for item in projects]
-    colors = [
-        "#0969da" if label == "U-C4N/Autocad-MCP" else "#6e7781"
-        for label in labels
-    ]
+    colors = ["#0969da" if label == "U-C4N/Autocad-MCP" else "#6e7781" for label in labels]
 
     fig, ax = plt.subplots(figsize=(12, 6.4), constrained_layout=True)
     fig.patch.set_facecolor("#f6f8fa")