发现的缺口:maximized_drawing_area 原先只包住取证循环,审查阶段没被包住 → LLM 在受控子循环里 zoom + 截图拿到的是未最大化的 2110x462(正是上一轮刚解决的 低分辨率问题,在最需要放大看细节的审查阶段又出现了);且审查中的 zoom 不复位视口, 跑完把用户的 CAD 留在最后一次放大处。 改动: 1. __main__.run_review:把 maximized_drawing_area 从「只包取证」扩到「包取证 + 审查」 (两者都要截图);report/annotate 留在 with 之外。 2. phases/review.py:新增 _VIEW_TOOLS;review_frame 拆成外壳 + _review_frame, 外壳 try/finally 里仅当确实动过视口才复位到该图框整幅视图 (zoom_to_window(win, margin=0.02))。纯查结构化数据的路径不受影响。 3. checklist.build_system_prompt:把「可调用只读工具」改写成明确的放大取证协议—— 截图看不清时用 zoom_to_window(坐标由图框/实体 bbox 算)或 zoom_to_entity, 再 get_viewport_screenshot 复核;并约束不要为看图而反复放大。 次生问题(同轮修复):_MAX_OBS_IMAGES 原为硬编码 3,而模型一轮内会发 8 次截图 → 拍了 8 张只回灌 3 张。改为配置项 REVIEW_OBS_IMAGES(默认 6),并把预算耗尽的占位 文案改成明确告知模型「不要再请求截图,请给出结论」。 实测(真实图纸 1 图框,新增 verify_review_maximized.py):取证与审查两阶段窗口均为 [-4,-2,3444,1442](最大化态),结束精确还原 [68,0,2316,960],三项全 PASS; 子循环里 LLM 连发 8 组 zoom_to_window + get_viewport_screenshot,提示词生效。 pytest 304 passed。
109 lines
3.4 KiB
Python
109 lines
3.4 KiB
Python
"""验收:审查阶段是否也在「绘图区最大化」状态下进行,且结束后精确还原。
|
|
|
|
做法:在取证 `collect` 与审查 `review_frame` 入口各采一次窗口矩形,
|
|
并在 `McpClient.call_tool` 上挂计数器,统计 LLM 子循环是否真的用了放大工具。
|
|
用法:先启动已加载插件的 CAD 并打开图纸,然后 `python verify_review_maximized.py`。
|
|
"""
|
|
|
|
import ctypes
|
|
import sys
|
|
from ctypes import wintypes
|
|
|
|
from dwg_review import __main__ as cli
|
|
from dwg_review.mcp_client import McpClient
|
|
from dwg_review.phases import evidence as ev
|
|
from dwg_review.phases import review as rv
|
|
|
|
_u = ctypes.windll.user32
|
|
_u.GetWindowTextW.argtypes = [wintypes.HWND, wintypes.LPWSTR, ctypes.c_int]
|
|
_u.IsWindowVisible.argtypes = [wintypes.HWND]
|
|
_u.GetWindowRect.argtypes = [wintypes.HWND, ctypes.POINTER(wintypes.RECT)]
|
|
_WNDENUMPROC = ctypes.WINFUNCTYPE(wintypes.BOOL, wintypes.HWND, wintypes.LPARAM)
|
|
|
|
|
|
def _find_main_window():
|
|
hit = [None]
|
|
|
|
def cb(hwnd, _lparam):
|
|
if not _u.IsWindowVisible(hwnd):
|
|
return True
|
|
n = _u.GetWindowTextLengthW(hwnd)
|
|
if n == 0:
|
|
return True
|
|
buf = ctypes.create_unicode_buffer(n + 1)
|
|
_u.GetWindowTextW(hwnd, buf, n + 1)
|
|
if "AutoCAD" in buf.value and "[" in buf.value:
|
|
hit[0] = hwnd
|
|
return False
|
|
return True
|
|
|
|
_u.EnumWindows(_WNDENUMPROC(cb), 0)
|
|
return hit[0]
|
|
|
|
|
|
HWND = _find_main_window()
|
|
if not HWND:
|
|
print("[X] 未找到 AutoCAD 主窗口")
|
|
sys.exit(1)
|
|
|
|
|
|
def rect():
|
|
r = wintypes.RECT()
|
|
_u.GetWindowRect(HWND, ctypes.byref(r))
|
|
return [r.left, r.top, r.right, r.bottom]
|
|
|
|
|
|
def area(r):
|
|
return (r[2] - r[0]) * (r[3] - r[1])
|
|
|
|
|
|
# --- 采样点 ---------------------------------------------------------------
|
|
phase_rects = {"evidence": [], "review": []}
|
|
zoom_calls = []
|
|
|
|
_orig_collect = ev.collect
|
|
_orig_review = rv.review_frame
|
|
_orig_call = McpClient.call_tool
|
|
|
|
|
|
def collect(ctx, index, frame):
|
|
phase_rects["evidence"].append(rect())
|
|
return _orig_collect(ctx, index, frame)
|
|
|
|
|
|
def review(ctx, evidence, system_prompt, log=print):
|
|
phase_rects["review"].append(rect())
|
|
return _orig_review(ctx, evidence, system_prompt, log=log)
|
|
|
|
|
|
def call_tool(self, name, arguments=None, **kw):
|
|
if name in ("zoom_to_window", "zoom_to_entity", "get_viewport_screenshot"):
|
|
zoom_calls.append(name)
|
|
return _orig_call(self, name, arguments, **kw)
|
|
|
|
|
|
ev.collect = collect
|
|
rv.review_frame = review
|
|
McpClient.call_tool = call_tool
|
|
|
|
before = rect()
|
|
print(f"起始窗口矩形 = {before} 面积={area(before)}")
|
|
|
|
rc = cli.main(["--frames", "1"])
|
|
|
|
after = rect()
|
|
print()
|
|
print("=== 结果 ===")
|
|
print(f"取证阶段采样 = {phase_rects['evidence']}")
|
|
print(f"审查阶段采样 = {phase_rects['review']}")
|
|
print(f"结束窗口矩形 = {after} 面积={area(after)}")
|
|
print(f"子循环取证调用 = {zoom_calls}")
|
|
|
|
ok_ev = all(area(r) > area(before) for r in phase_rects["evidence"]) if phase_rects["evidence"] else False
|
|
ok_rv = all(area(r) > area(before) for r in phase_rects["review"]) if phase_rects["review"] else False
|
|
print()
|
|
print(f"[{'PASS' if ok_ev else 'FAIL'}] 取证阶段处于最大化(面积大于基线)")
|
|
print(f"[{'PASS' if ok_rv else 'FAIL'}] 审查阶段处于最大化(面积大于基线)")
|
|
print(f"[{'PASS' if after == before else 'FAIL'}] 结束精确还原窗口矩形")
|
|
sys.exit(0 if (ok_ev and ok_rv and after == before and rc == 0) else 1)
|