feat(review): 取证层多源化 + 视觉多图(整体+2x2 象限)

- 新增 evidence_model.py:统一证据模型(source_type + images 列表),访问器兼容旧 image_b64/image_mime 单图字段
- phases/evidence.py:新增 collect() 多源分发 seam(仅 CAD)、capture_images() 整体+等分象限多图(结束复位视口)、sub_windows()
- phases/review.py:多图逐张下采样喂 LLM,payload 增加 source_type
- config.py:EVIDENCE_DETAIL_TILES=4 / EVIDENCE_MAX_IMAGES=5(默认开启多图)
- 新增 tests/test_evidence_model.py,更新 evidence/review 断言与 fakes 归一
This commit is contained in:
gjm committed 2026-10-15 19:48:18 +08:00
1 parent 22db93b6f5
commit 1c9fc72839
10 files changed
+396 -32

No files matched your search

+3 -2
View File
@@ -15,11 +15,12 @@ if str(_ROOT) not in sys.path:
@pytest.fixture(autouse=True)
def _no_render_wait(monkeypatch):
"""消除 collect_frame 里每个图框的 RENDER_WAIT 等待(单元测试不需要真实渲染)。"""
def _fast_defaults(monkeypatch):
"""单元测试默认:不等待渲染、取证只取整体单图(多图用例自行覆盖 tiles)。"""
from dwg_review import config
monkeypatch.setattr(config, "RENDER_WAIT", 0)
monkeypatch.setattr(config, "EVIDENCE_DETAIL_TILES", 0)
@pytest.fixture