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>
142 lines
4.6 KiB
Python
142 lines
4.6 KiB
Python
from __future__ import annotations
|
|
|
|
import pytest
|
|
|
|
import config
|
|
from engineering.refiner import RepairRegistry, refine_drawing
|
|
|
|
pytestmark = pytest.mark.asyncio
|
|
|
|
|
|
async def test_transaction_stack_is_separate_from_drawing_undo(backend, monkeypatch):
|
|
"""An undo must not consume a transaction checkpoint, or vice versa."""
|
|
monkeypatch.setattr(config.settings, "ezdxf_undo_depth", 4)
|
|
await backend.drawing_new()
|
|
await backend.entity_create_line(0, 0, 10, 0)
|
|
await backend.transaction_begin()
|
|
|
|
undo = await backend.drawing_undo()
|
|
status = await backend.system_status()
|
|
|
|
assert undo["ok"] is True, "undo walks its own history"
|
|
assert status["transaction_depth"] == 1, "and leaves the checkpoint standing"
|
|
await backend.transaction_rollback()
|
|
|
|
|
|
async def test_transaction_rollback_restores_document(backend):
|
|
await backend.entity_create_line(0, 0, 10, 0)
|
|
await backend.transaction_begin()
|
|
await backend.entity_create_circle(5, 5, 2)
|
|
|
|
await backend.transaction_rollback()
|
|
|
|
entities = await backend.entity_list(limit=100)
|
|
assert [entity.type for entity in entities] == ["LINE"]
|
|
|
|
|
|
async def test_refiner_does_not_mutate_when_transaction_cannot_start(backend, monkeypatch):
|
|
await backend.entity_create_line(0, 0, 20, 0)
|
|
await backend.entity_create_line(0, 0, 20, 0)
|
|
|
|
async def transaction_rejected():
|
|
return {"ok": False, "error": "A transaction is already active"}
|
|
|
|
async def unexpected_transaction_end():
|
|
raise AssertionError("refiner must not end a transaction it did not start")
|
|
|
|
monkeypatch.setattr(backend, "transaction_begin", transaction_rejected)
|
|
monkeypatch.setattr(backend, "transaction_commit", unexpected_transaction_end)
|
|
monkeypatch.setattr(backend, "transaction_rollback", unexpected_transaction_end)
|
|
|
|
result = await refine_drawing(backend, focus=["duplicate_entities"])
|
|
|
|
assert result.status == "transaction_unavailable"
|
|
assert result.rounds[0].transaction == "not_started"
|
|
assert len(await backend.entity_list(type_filter="LINE")) == 2
|
|
|
|
|
|
async def test_refiner_repairs_construction_and_duplicates(backend):
|
|
await backend.entity_create_line(0, 0, 20, 0)
|
|
await backend.entity_create_line(0, 0, 20, 0)
|
|
await backend.construction_xline(0, 0, 0)
|
|
|
|
result = await refine_drawing(
|
|
backend,
|
|
max_rounds=3,
|
|
min_score=95,
|
|
focus=["duplicate_entities", "construction_left"],
|
|
)
|
|
|
|
assert result.status == "threshold_met"
|
|
assert result.final_score == 100.0
|
|
assert result.rounds[0].score_after > result.rounds[0].score_before
|
|
assert await backend.drawing_critique(["duplicate_entities", "construction_left"]) == []
|
|
|
|
|
|
async def test_refiner_dry_run_does_not_mutate_drawing(backend):
|
|
await backend.entity_create_line(0, 0, 20, 0)
|
|
await backend.entity_create_line(0, 0, 20, 0)
|
|
|
|
result = await refine_drawing(
|
|
backend,
|
|
focus=["duplicate_entities"],
|
|
dry_run=True,
|
|
)
|
|
|
|
assert result.status == "dry_run"
|
|
assert len(await backend.entity_list(type_filter="LINE")) == 2
|
|
assert result.rounds[0].actions[0].status == "planned"
|
|
|
|
|
|
async def test_refiner_rolls_back_when_custom_repair_lowers_score(backend):
|
|
await backend.entity_create_line(0, 0, 20, 0)
|
|
await backend.entity_create_line(0, 0, 20, 0)
|
|
|
|
registry = RepairRegistry()
|
|
|
|
async def harmful_repair(active_backend, issue):
|
|
await active_backend.construction_xline(0, 0, 0)
|
|
return {"created": "construction"}
|
|
|
|
registry.register("duplicate_entities", harmful_repair)
|
|
before = len(await backend.entity_list(limit=100))
|
|
|
|
result = await refine_drawing(
|
|
backend,
|
|
focus=["duplicate_entities", "construction_left"],
|
|
registry=registry,
|
|
)
|
|
|
|
assert result.status == "rolled_back"
|
|
assert result.rounds[0].transaction == "rolled_back"
|
|
assert len(await backend.entity_list(limit=100)) == before
|
|
|
|
|
|
async def test_refiner_leaves_missing_gdt_datum_for_manual_resolution(backend):
|
|
backend._gdt_datums_referenced = {"A"}
|
|
|
|
result = await refine_drawing(backend, focus=["gdt"])
|
|
|
|
assert result.status == "manual_required"
|
|
assert result.remaining_issues[0]["focus"] == "gdt"
|
|
|
|
|
|
async def test_server_drawing_refine_returns_structured_payload(backend):
|
|
import server
|
|
|
|
class Ctx:
|
|
lifespan_context = {"backend": backend}
|
|
|
|
await backend.entity_create_line(0, 0, 20, 0)
|
|
await backend.entity_create_line(0, 0, 20, 0)
|
|
|
|
result = await server.drawing_refine(
|
|
max_rounds=3,
|
|
min_score=95,
|
|
focus=["duplicate_entities"],
|
|
ctx=Ctx(),
|
|
)
|
|
|
|
assert result["status"] == "threshold_met"
|
|
assert result["final_score"] == 100.0
|