gjm
f7fa8f14d9
- checklist.py：系统提示加入结构化输出契约（只输出 {summary, issues[]}，
引用 handle 必须真实存在、不得编造）
- review.py：review_frame 返回 {summary, issues, raw}；仅在「不再请求工具」的回合
解析结论，中间工具回合的 content 永不解析；强制收口那次 chat 不传 tools
- report.py：删除 extract_issues 与 _EXTRACT_SYSTEM（不再需要第二次 LLM 调用）；
新增 format_finding（用 .get，顺带修复缺 frame 键 KeyError）；save_report 的
issues 省略时从 findings 拍平
- __main__.py：主流程改为 确定性检查 → review_frame → build_finding（合并+校验），
issues 由 flatten_issues 派生
顺带修复既有 gap：summarize 硬下标 KeyError、extract_issues 单行围栏解析失败。
144 lines
4.9 KiB
Python
144 lines
4.9 KiB
Python
"""`dwg_review.phases.report` 单元测试。"""
|
||
|
||
import json
|
||
|
||
from dwg_review.phases.report import format_finding, save_report, summarize
|
||
from tests.fakes import FakeLlmClient, make_ctx
|
||
|
||
|
||
def issue(**over):
|
||
base = {
|
||
"frame": 1, "category": "文字", "severity": "high", "message": "文字重叠",
|
||
"handle": "A1", "source": "llm", "verified": True,
|
||
}
|
||
base.update(over)
|
||
return base
|
||
|
||
|
||
def findings_fixture():
|
||
return [
|
||
{
|
||
"frame": 1, "sheet": "A1", "summary": "该图框存在文字重叠",
|
||
"issues": [issue()],
|
||
"counts": {"deterministic": 0, "llm": 1, "unverified": 0},
|
||
},
|
||
{
|
||
"frame": 2, "sheet": "A3", "summary": "未发现明显问题",
|
||
"issues": [],
|
||
"counts": {"deterministic": 0, "llm": 0, "unverified": 0},
|
||
},
|
||
]
|
||
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# format_finding
|
||
# ---------------------------------------------------------------------------
|
||
def test_format_finding_renders_summary_and_issues():
|
||
text = format_finding(findings_fixture()[0])
|
||
assert "图框 1" in text and "图幅 A1" in text
|
||
assert "该图框存在文字重叠" in text
|
||
assert "[high][LLM] 文字重叠" in text
|
||
assert "handle=A1" in text
|
||
|
||
|
||
def test_format_finding_marks_deterministic_source():
|
||
finding = {"frame": 1, "sheet": "A1", "summary": "s",
|
||
"issues": [issue(source="deterministic", handle="Z1")]}
|
||
assert "[确定性]" in format_finding(finding)
|
||
|
||
|
||
def test_format_finding_marks_unverified():
|
||
finding = {"frame": 1, "sheet": "A1", "summary": "s",
|
||
"issues": [issue(handle=None, verified=False)]}
|
||
text = format_finding(finding)
|
||
assert "未在证据中定位" in text
|
||
assert "handle=" not in text
|
||
|
||
|
||
def test_format_finding_tolerates_missing_keys():
|
||
text = format_finding({})
|
||
assert "图框 None" in text # 不再 KeyError（修复既有硬下标 gap）
|
||
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# summarize
|
||
# ---------------------------------------------------------------------------
|
||
def test_summarize_empty_returns_message_without_llm():
|
||
llm = FakeLlmClient(text="不应被调用")
|
||
ctx = make_ctx(llm=llm)
|
||
out = summarize(ctx, [], log=lambda *a: None)
|
||
assert "未识别到可审查的图框" in out
|
||
assert llm.calls == []
|
||
|
||
|
||
def test_summarize_uses_chat_text():
|
||
llm = FakeLlmClient(text="## 总报告")
|
||
ctx = make_ctx(llm=llm)
|
||
assert summarize(ctx, findings_fixture(), log=lambda *a: None) == "## 总报告"
|
||
assert len(llm.calls) == 1
|
||
assert "图框 1" in llm.calls[0]["user"]
|
||
assert "图框 2" in llm.calls[0]["user"]
|
||
|
||
|
||
def test_summarize_input_includes_issue_lines():
|
||
llm = FakeLlmClient(text="x")
|
||
ctx = make_ctx(llm=llm)
|
||
summarize(ctx, findings_fixture(), log=lambda *a: None)
|
||
user = llm.calls[0]["user"]
|
||
assert "[high][LLM] 文字重叠" in user
|
||
|
||
|
||
def test_summarize_falls_back_to_raw_input_on_error():
|
||
class Boom(FakeLlmClient):
|
||
def chat_text(self, system, user, **kwargs):
|
||
raise RuntimeError("汇总炸了")
|
||
|
||
logs = []
|
||
ctx = make_ctx(llm=Boom())
|
||
out = summarize(ctx, findings_fixture(), log=logs.append)
|
||
assert "图框 1" in out and "图框 2" in out
|
||
assert any("汇总失败" in line for line in logs)
|
||
|
||
|
||
def test_summarize_tolerates_finding_without_frame_key():
|
||
# 修复既有硬下标 gap：缺 frame 键不再 KeyError
|
||
llm = FakeLlmClient(text="ok")
|
||
ctx = make_ctx(llm=llm)
|
||
out = summarize(ctx, [{"summary": "无 frame 键", "issues": []}], log=lambda *a: None)
|
||
assert out == "ok"
|
||
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# save_report
|
||
# ---------------------------------------------------------------------------
|
||
def test_save_report_writes_md_and_json(tmp_reports):
|
||
findings = findings_fixture()
|
||
plan = {"frames": [{"bbox": [0, 0, 10, 10]}]}
|
||
issues = [issue()]
|
||
|
||
md_path, json_path = save_report("# 报告", findings, plan, issues, log=lambda *a: None)
|
||
|
||
assert md_path.exists() and json_path.exists()
|
||
assert md_path.read_text(encoding="utf-8") == "# 报告"
|
||
data = json.loads(json_path.read_text(encoding="utf-8"))
|
||
assert data["findings"] == findings
|
||
assert data["issues"] == issues
|
||
assert data["frames"] == plan["frames"]
|
||
assert "generated_at" in data
|
||
|
||
|
||
def test_save_report_derives_issues_from_findings(tmp_reports):
|
||
findings = findings_fixture()
|
||
_, json_path = save_report("md", findings, {"frames": []}, log=lambda *a: None)
|
||
data = json.loads(json_path.read_text(encoding="utf-8"))
|
||
assert data["issues"] == [issue()] # 拍平自 findings
|
||
|
||
|
||
def test_save_report_creates_missing_directory(tmp_path, monkeypatch):
|
||
from dwg_review import config
|
||
|
||
target = tmp_path / "deep" / "nested"
|
||
monkeypatch.setattr(config, "REPORT_DIR", target)
|
||
save_report("md", [], {"frames": []}, log=lambda *a: None)
|
||
assert target.is_dir()
|