Umut CANandClaude Opus 5
b03a7615b1
Tool count 131 -> 154; 474 -> 1242 collected tests. The release exists for two measured reasons. A 149-tool catalog costs a client ~40,300 tokens before it has asked for anything, and a drafter searching the way drafters think -- FILLET, BPOLY, QSELECT, WBLOCK -- scored df=0 against the stock index, because those words were simply not in the data. Discovery and batching - DISCOVERY_MODE=search replaces the catalog with search_tools + call_tool, ranked over an AutoCAD command and synonym corpus (discovery/aliases.py) on top of fastmcp's BM25 index. Measured: 40,305 -> 356 tokens advertised. - cad_batch runs a step list in one round trip; fields= projects result-heavy responses. The `core` profile is gone -- discovery replaced it. Honesty debt (Tier 0) - OCS/ECS: `extrusion` appeared nowhere in this codebase, so mirrored and rotated geometry reported coordinates that were quietly wrong. backends/ocs.py translates at the backend boundary; every tool coordinate is WCS on both engines, and a tilted plane refuses rather than answering with a number that looks fine. - drawing_save_as(fmt="dwg") wrote DXF bytes to a .dwg path. drawing_audit never repaired. analysis_measure_area shoelaced points the caller typed in. - ezdxf calls gained a per-call timeout, so one hung call can no longer wedge a server whose document lock is a single asyncio.Lock. Architecture - The 1854-line backend ABC is 19 contract modules; @capability(key, reason=) makes optional methods declarative and a gate fails on undeclared holes. - 8 layout/viewport tools, CHSPACE, CAD_PROGID escape hatch. - Wave A: selection filters, boundary tracing, hatch depth, annotation objects, measurement -- 13 tools of a planned 39. The REGION and 2D-boolean family was cut on evidence: add_region() yields zero ACIS bytes and the greiner_hormann substitute loses 28.2% of the area on a square with one semicircular edge. Verified against a live AutoCAD 2026, which found four COM defects no amount of reading would have caught -- AcadPViewport has no ViewCenter, and the line that set it had been swallowed by a bare except since v1.4. Benchmark v3 (15 tasks) and what it caught - v2 scored this server 10/10, which carried no information: every task in it exercised something the server was built around. Five tasks were added because they can fail, and three did while being written -- a hatch could not be measured though the refusal listed HATCH as measurable, the boundary tools and the measure tool disagreed about the same shape (139.2177 vs 139.2699), and a circle stored as two bulged vertices measured 0.0. - Competitor reports are NOT re-scored. They are pinned v1.4 runs against v2 and were never asked these five questions; the chart shows those rows `not run`. - Correctness A/B: 21/24 -> 24/24, zero regressions. Performance, stated plainly The published v1.4 perf report was recorded on CPython 3.14 and the new one on 3.11.15, so the apparent 2-6x speedup is the interpreter, not this release. Re-measured on one interpreter, v1.5.0 is 28% slower creating entities and 22% slower on the 10k roundtrip. Fully attributed: EZDXF_CALL_TIMEOUT=0 restores v1.4.0's exact numbers. That is the deadlock fix being paid for, the knob is documented, and winning it back is on the 1.6 roadmap. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
54 lines
1.9 KiB
YAML
54 lines
1.9 KiB
YAML
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 }}
|