Umut CANandClaude Opus 5
2be5e4180d
scripts/smoke_pid_com.py runs the whole track against the live AutoCAD in a new document. ComBackend.connect() is lazy by design, so the script reads reachability from system_status()["connected"] rather than from connect() as the plan sketched, and closes its document without saving unless --keep is passed. On this machine (AutoCAD 2026, "25.1s (LMS Tech)") it exits 0: 5 nodes, 4 edges, 0 dangling, confidence_min 1.0, 0 critique issues, 2 XDATA chunks — identical to the headless engine on the same spec. The first attempt exited 2 on a stale win32com gen_py cache (a package folder holding only __pycache__); an environment fault, no backend change needed. A/B against v1.5.1 published as ab-v1.5.1-vs-v1.6.0-dev.json: 26/29 -> 29/29, three miss -> pass, zero regressed. check_doc_numbers.py now names the report and the two row labels in one place (AB_REPORT, AB_*_LABEL), and README.md / benchmarks/README.md carry the new rows; the v1.5.0 and v1.4.0 tables stay as history. README: P&ID row, the showcase and catalogue images, the token table re-measured (161 / 44,930 by default, 152 / 41,420 with TOOL_PACKS=core, lean 50 / 14,007), every stale count reconciled (154 -> 166 registered, 149 -> 161 advertised, corpus 158/672 -> 162/731 by the same count, 19 -> 20 groups, 6 -> 8 resources, six-task matrix with pid_roundtrip), a "Known limitations of the P&ID track" subsection, and the snapshot line at this machine's 2423 collected tests (CI has not run on this tree; noted in the changelog with the pre-existing 1369 vs 1363 drift). CLAUDE.md: section 17, sections 5 and 7 counts, TOOL_PACKS, the two 1.6 contracts and the reader rules. Spec status -> implemented. The plan and spec markdown were reformatted by ruff (fenced Python only) because `ruff format --check .` was already red on them at HEAD and the gate requires the whole tree clean. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FKFStjEFzpGyLq5bMpWxTd
87 lines
3.2 KiB
Python
87 lines
3.2 KiB
Python
"""Exercise the P&ID track once against the live AutoCAD on this machine.
|
|
|
|
Creates a NEW document (never touches the operator's open drawing), then runs
|
|
the whole track through the same code the tools call:
|
|
|
|
apply_layer_set("pid") -> run_spec(EXAMPLE_SPEC)
|
|
= block_define -> pid_symbol_insert -> ACADMCP_PID xdata
|
|
-> pid_line_draw -> pid_graph -> six pid_* critique focuses
|
|
-> entity_get_xdata on the pump
|
|
|
|
and prints the graph stats as JSON. Exit codes:
|
|
|
|
0 every line landed on a port (``dangling == 0``)
|
|
1 the sheet drew but the reader found a dangling end
|
|
2 no live CAD application reachable (pywin32 missing, or the ProgID
|
|
cannot be created) -- the COM paths then remain fake-tested only
|
|
|
|
The backend's ``connect()`` is lazy on purpose (the server must start before
|
|
AutoCAD is open), so reachability is read from ``system_status()`` rather than
|
|
from ``connect()``. Note that the backend's ``Dispatch`` fallback *launches*
|
|
the ProgID when nothing is running; a cold AutoCAD start can take longer than
|
|
``COM_CALL_TIMEOUT`` (60 s), so open AutoCAD first when the first call times
|
|
out.
|
|
|
|
AUTOCAD_MCP_BACKEND=com uv run --frozen python scripts/smoke_pid_com.py
|
|
uv run --frozen python scripts/smoke_pid_com.py --keep # leave the document open
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
import json
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
ROOT = Path(__file__).resolve().parents[1]
|
|
sys.path.insert(0, str(ROOT))
|
|
|
|
XDATA_APP = "ACADMCP_PID"
|
|
|
|
|
|
async def main(keep_document: bool = False) -> int:
|
|
try:
|
|
from backends.com_backend import ComBackend
|
|
except ImportError as exc:
|
|
print(f"pywin32 not available: {exc}")
|
|
return 2
|
|
backend = ComBackend()
|
|
try:
|
|
await backend.connect()
|
|
except Exception as exc:
|
|
print(f"no live AutoCAD reachable: {exc}")
|
|
return 2
|
|
try:
|
|
status = await backend.system_status()
|
|
if not status.get("connected"):
|
|
print(f"no live AutoCAD reachable: {status.get('error', status)}")
|
|
return 2
|
|
|
|
from engineering.layers import apply_layer_set
|
|
from engineering.pid.spec import EXAMPLE_SPEC, run_spec
|
|
|
|
await backend.drawing_new()
|
|
await apply_layer_set(backend, "pid")
|
|
result = await run_spec(backend, EXAMPLE_SPEC)
|
|
got = await backend.entity_get_xdata(result["handles"]["P-101"], XDATA_APP)
|
|
report = {
|
|
"autocad": status.get("autocad_version") or status.get("cad_progid"),
|
|
"active_document": (await backend.system_status()).get("active_document"),
|
|
"handles": result["handles"],
|
|
"graph_stats": result["graph"]["stats"],
|
|
"crossings_total": result["crossings_total"],
|
|
"critique_issues": len(result["critique"]),
|
|
"critique": result["critique"],
|
|
"xdata_chunks": len(got["xdata"].get(XDATA_APP, [])),
|
|
}
|
|
print(json.dumps(report, indent=2))
|
|
if not keep_document:
|
|
await backend.drawing_close(save=False)
|
|
return 0 if result["graph"]["stats"]["dangling"] == 0 else 1
|
|
finally:
|
|
await backend.disconnect()
|
|
|
|
|
|
if __name__ == "__main__":
|
|
raise SystemExit(asyncio.run(main(keep_document="--keep" in sys.argv[1:])))
|