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>
214 lines
6.9 KiB
Python
214 lines
6.9 KiB
Python
from __future__ import annotations
|
|
|
|
import pytest
|
|
|
|
from engineering.preflight import preflight_drawing
|
|
|
|
|
|
def _complete_requirements() -> dict:
|
|
return {
|
|
"units": "mm",
|
|
"part_type": "bracket",
|
|
"dimensions": {"width": 80.0, "height": 50.0, "thickness": 8.0},
|
|
"tolerance_policy": "ISO 2768-m",
|
|
}
|
|
|
|
|
|
def test_preflight_missing_production_fields_is_not_ready():
|
|
result = preflight_drawing("L bracket", requirements={})
|
|
|
|
assert result.ready is False
|
|
assert {q.code for q in result.questions} == {
|
|
"MISSING_UNITS",
|
|
"MISSING_PART_TYPE",
|
|
"MISSING_DIMENSIONS",
|
|
"MISSING_TOLERANCE_POLICY",
|
|
}
|
|
assert result.spec_hash.startswith("sha256:")
|
|
|
|
|
|
def test_preflight_normalizes_complete_spec_and_hash_is_deterministic():
|
|
first = preflight_drawing(
|
|
" L bracket ",
|
|
requirements=_complete_requirements(),
|
|
sheet_size="a3",
|
|
layer_set_id="MECH",
|
|
)
|
|
second = preflight_drawing(
|
|
"L bracket",
|
|
requirements={
|
|
"tolerance_policy": "ISO 2768-m",
|
|
"dimensions": {"thickness": 8, "height": 50, "width": 80},
|
|
"part_type": "bracket",
|
|
"units": "MM",
|
|
},
|
|
sheet_size="A3",
|
|
layer_set_id="mech",
|
|
)
|
|
|
|
assert first.ready is True
|
|
assert first.normalized_spec["requirements"]["units"] == "mm"
|
|
assert first.spec_hash == second.spec_hash
|
|
|
|
|
|
def test_preflight_question_text_is_english():
|
|
"""drawing_preflight returns this text to every user of a public English
|
|
package; it shipped in Turkish through v1.4."""
|
|
result = preflight_drawing("L bracket", requirements={})
|
|
by_code = {q.code: q.question for q in result.questions}
|
|
|
|
assert by_code["MISSING_UNITS"] == "What drawing units should be used?"
|
|
assert by_code["MISSING_PART_TYPE"] == "What kind of part or drawing is being produced?"
|
|
assert by_code["MISSING_DIMENSIONS"] == "What are the main production dimensions?"
|
|
assert by_code["MISSING_TOLERANCE_POLICY"] == "Which tolerance policy should apply?"
|
|
|
|
|
|
def test_preflight_conflict_message_is_english():
|
|
requirements = _complete_requirements()
|
|
requirements["constraints"] = [
|
|
{"field": "dimensions.width", "value": 80},
|
|
{"field": "dimensions.width", "value": 90},
|
|
]
|
|
|
|
result = preflight_drawing("L bracket", requirements=requirements)
|
|
|
|
assert result.conflicts[0].message == ("Conflicting values were supplied for dimensions.width.")
|
|
|
|
|
|
def test_preflight_user_facing_text_is_ascii():
|
|
"""Guard against any future non-English string leaking back into the tool
|
|
surface — codes and field names stay machine-readable, prose stays ASCII."""
|
|
requirements = _complete_requirements()
|
|
requirements["constraints"] = [
|
|
{"field": "dimensions.width", "value": 80},
|
|
{"field": "dimensions.width", "value": 90},
|
|
]
|
|
empty = preflight_drawing("L bracket", requirements={})
|
|
conflicting = preflight_drawing("L bracket", requirements=requirements)
|
|
|
|
prose = [q.question for q in empty.questions]
|
|
prose += [choice for q in empty.questions for choice in q.choices]
|
|
prose += [c.message for c in conflicting.conflicts]
|
|
|
|
assert prose, "expected some user-facing text to check"
|
|
for text in prose:
|
|
assert text.isascii(), f"non-ASCII user-facing text: {text!r}"
|
|
|
|
|
|
def test_preflight_detects_conflicting_constraints():
|
|
requirements = _complete_requirements()
|
|
requirements["constraints"] = [
|
|
{"field": "dimensions.width", "value": 80},
|
|
{"field": "dimensions.width", "value": 90},
|
|
]
|
|
|
|
result = preflight_drawing("L bracket", requirements=requirements)
|
|
|
|
assert result.ready is False
|
|
assert result.conflicts[0].code == "CONFLICTING_REQUIREMENT"
|
|
assert result.conflicts[0].field == "dimensions.width"
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
("kwargs", "code"),
|
|
[
|
|
({"sheet_size": "LETTER"}, "INVALID_SHEET_SIZE"),
|
|
({"scale": 0}, "INVALID_SCALE"),
|
|
({"view_count": 0}, "INVALID_VIEW_COUNT"),
|
|
({"dim_style": "guess"}, "INVALID_DIM_STYLE"),
|
|
({"layer_set_id": "custom"}, "INVALID_LAYER_SET"),
|
|
],
|
|
)
|
|
def test_preflight_rejects_invalid_planning_parameters(kwargs, code):
|
|
result = preflight_drawing(
|
|
"L bracket",
|
|
requirements=_complete_requirements(),
|
|
**kwargs,
|
|
)
|
|
|
|
assert result.ready is False
|
|
assert code in {conflict.code for conflict in result.conflicts}
|
|
|
|
|
|
def test_preflight_does_not_invent_values_when_assumptions_disabled():
|
|
result = preflight_drawing(
|
|
"L bracket",
|
|
requirements={"part_type": "bracket"},
|
|
allow_assumptions=False,
|
|
)
|
|
|
|
assert result.assumptions == []
|
|
assert "units" not in result.normalized_spec["requirements"]
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_backend_plan_accepts_matching_ready_preflight(backend):
|
|
preflight = await backend.drawing_preflight(
|
|
"L bracket",
|
|
requirements=_complete_requirements(),
|
|
)
|
|
|
|
plan = await backend.drawing_plan(
|
|
"L bracket",
|
|
requirements=preflight.normalized_spec["requirements"],
|
|
spec_hash=preflight.spec_hash,
|
|
)
|
|
|
|
assert plan.preflight_status == "ready"
|
|
assert plan.spec_hash == preflight.spec_hash
|
|
assert plan.requirements["units"] == "mm"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_backend_plan_rejects_not_ready_preflight_hash(backend):
|
|
preflight = await backend.drawing_preflight("L bracket", requirements={})
|
|
|
|
with pytest.raises(RuntimeError, match="not ready"):
|
|
await backend.drawing_plan("L bracket", spec_hash=preflight.spec_hash)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_backend_plan_rejects_fields_that_do_not_match_preflight_hash(backend):
|
|
preflight = await backend.drawing_preflight(
|
|
"L bracket",
|
|
requirements=_complete_requirements(),
|
|
)
|
|
|
|
with pytest.raises(RuntimeError, match="do not match"):
|
|
await backend.drawing_plan(
|
|
"Different part",
|
|
requirements=preflight.normalized_spec["requirements"],
|
|
spec_hash=preflight.spec_hash,
|
|
)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_legacy_plan_remains_compatible_and_marks_preflight_skipped(backend):
|
|
plan = await backend.drawing_plan("Legacy drawing")
|
|
|
|
assert plan.preflight_status == "skipped"
|
|
assert plan.spec_hash is None
|
|
assert plan.requirements == {}
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_document_change_clears_plan_preflight_and_gdt_state(backend):
|
|
preflight = await backend.drawing_preflight(
|
|
"First drawing",
|
|
requirements=_complete_requirements(),
|
|
)
|
|
await backend.drawing_plan(
|
|
"First drawing",
|
|
requirements=preflight.normalized_spec["requirements"],
|
|
spec_hash=preflight.spec_hash,
|
|
)
|
|
backend._gdt_datums_defined = {"A"}
|
|
backend._gdt_datums_referenced = {"A", "B"}
|
|
|
|
await backend.drawing_new()
|
|
|
|
assert backend.get_plan_spec() is None
|
|
assert backend._preflight_result is None
|
|
assert backend._gdt_datums_defined == set()
|
|
assert backend._gdt_datums_referenced == set()
|