Files
pp-qa-km/tools/selfcheck_ingest.py
LittleYellow 0b4c2bbb15 修復中文路徑 preflight 與 BM25 核心詞落空,測資改照現實建
兩個 bug 同源於自檢測資「照能過建、不照現實建」:

- ingest preflight:git status --porcelain 預設會把含中文或空格的路徑加引號
  轉義,raw/ 白名單比對因此失效,中文檔名的 convert 產出被誤判為 raw/ 以外的
  未提交變更而中止攝入。舊測資用 ASCII 檔名,整條路徑從未被走過。

- search:BM25Okapi 的 idf 在 df >= N/2 時 <= 0(rank_bm25 對負 idf 的替代值
  epsilon x average_idf 在 average_idf 為負時同樣為負),與 search() 的 s > 0
  過濾相乘,會讓「每頁都提到的核心詞」查詢全數落空——知識庫愈小、詞愈核心
  愈嚴重,MCP 的 search_wiki 一併受害。改用 Lucene 式恆正 idf。
  舊測資每個查詢詞都只出現在一頁(df=1),恰好避開此配置。

變更:
- tools/ingest.py:preflight 比對前剝除 git 的轉義引號
- tools/search.py:_BM25 子類覆寫 _calc_idf 為 log(1 + (N-df+0.5)/(df+0.5))
- tools/selfcheck_ingest.py:新增 preflight 中文檔名放行 / 非 raw 擋下的檢查
- tools/selfcheck_search.py:新增與既有頁共用核心詞的測資,鎖住 idf 退化
- tools/convert/selfcheck.py、tools/selfcheck_lint.py:測資檔名改中文+空格
- AGENTS.md §13.4:新增「測資照現實建,不是照能過建」規則
- README.md §3.2:補 convert 產出應保持未提交、由 ingest 一併 commit 的流程

驗證:四個自檢全數通過;分別移除兩個修法後對應檢查會失敗。

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-22 07:21:45 +08:00

158 lines
7.4 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""Phase 3 自檢:以假 LLM + 沙盒 git repo 驗證攝入管線的完整 plumbing——
分支建立、頁面產出、frontmatter 合規、index/log 更新、冪等跳過、就地編輯合併,
以及 kb.llm_json 的重試與 fallback 切換。不需要 Ollama 在線。
執行:.venv/Scripts/python tools/selfcheck_ingest.py
"""
import hashlib
import pathlib
import shutil
import subprocess
import sys
import tempfile
sys.path.insert(0, str(pathlib.Path(__file__).parent))
import kb
import ingest
CFG = """ollama: {base_url: "http://localhost:11434", timeout_seconds: 5}
tasks:
ingest: {model: "fake:test", temperature: 0.2, max_retries: 2}
lint: {model: "fake:test", temperature: 0.1, max_retries: 2}
fallback: {model: "fake:fb"}
limits: {mcp_response_max_tokens: 2000, ingest_chunk_max_chars: 200}
"""
def fake_llm(cfg, task, prompt, validate):
if prompt.startswith("以下是一份長文件的第"):
obj = {"summary_markdown": "- 分段重點"}
elif '"updated_markdown"' in prompt:
obj = {"updated_markdown": "- 壓測逾時\n- 新來源事實",
"updated_description": "支付閘道模組(已更新)"}
else:
obj = {"title": "支付閘道壓測報告", "description": "壓測發現逾時缺陷",
"slug": "gateway-load-test", "tags": ["load-test", "gateway"],
"summary_markdown": "- 逾時缺陷於壓測重現",
"knowledge_items": [{"type": "entity", "slug": "payment-gateway",
"title": "支付閘道", "description": "支付閘道模組",
"tags": ["gateway"], "facts_markdown": "- 壓測逾時"}]}
err = validate(obj) # 假輸出也要通過真 validator確保契約一致
assert err is None, err
return obj, "fake:test"
def git(root, *args):
return subprocess.run(["git", *args], cwd=root, check=True, text=True,
encoding="utf-8", capture_output=True).stdout.strip()
def add_doc(root, name, text):
p = root / "raw" / "converted" / name
p.write_text(text, encoding="utf-8")
sha = hashlib.sha256(text.encode("utf-8")).hexdigest()
import json
mp = root / "raw" / "manifest.json"
m = json.loads(mp.read_text(encoding="utf-8"))
m["files"][f"raw/converted/{name}"] = {
"kind": "converted", "sha256": sha, "original_path": f"raw/originals/{name}",
"original_sha256": sha, "converter": "from_docx", "converted_at": "2026-07-14T00:00:00"}
mp.write_text(json.dumps(m, ensure_ascii=False, indent=2), encoding="utf-8")
return sha
def main():
tmp = pathlib.Path(tempfile.mkdtemp(prefix="ppqa-ingest-"))
real_llm, real_chat = kb.llm_json, kb.ollama_chat
try:
root = tmp / "repo"
for sub in ("config", "raw/originals", "raw/converted",
"wiki/summaries", "wiki/entities", "wiki/concepts"):
(root / sub).mkdir(parents=True)
(root / "config" / "models.yaml").write_text(CFG, encoding="utf-8")
(root / "raw" / "manifest.json").write_text('{"version": 1, "files": {}}',
encoding="utf-8")
(root / "index.md").write_text("# 知識庫索引\n", encoding="utf-8")
(root / "log.md").write_text("# 操作日誌\n", encoding="utf-8")
git(root, "init", "-q", "-b", "main")
git(root, "config", "user.name", "selfcheck")
git(root, "config", "user.email", "selfcheck@local")
text = "支付閘道於壓力測試下出現逾時缺陷,交易峰值時重試機制未生效。\n\n" * 12
add_doc(root, "doc1.md", text) # > 200 chars → 走分段路徑
git(root, "add", "-A")
git(root, "commit", "-q", "-m", "init")
# 1) 攝入建分支、產頁、commit、回到 main
kb.llm_json = fake_llm
ingest.main(["raw/converted/doc1.md", "--root", str(root)])
assert git(root, "branch", "--show-current") == "main"
branch = git(root, "branch", "--list", "ingest/*").strip("* ").strip()
assert branch, "未建立 ingest 分支"
assert not git(root, "status", "--porcelain"), "工作區不乾淨"
git(root, "checkout", "-q", branch)
summary = list((root / "wiki/summaries").glob("*.md"))
entity = root / "wiki/entities/payment-gateway.md"
assert len(summary) == 1 and entity.is_file()
meta, _ = kb.parse_page(entity.read_text(encoding="utf-8"))
assert kb.validate_meta(meta) == [], kb.validate_meta(meta)
assert "payment-gateway" in (root / "index.md").read_text(encoding="utf-8")
assert "] ingest |" in (root / "log.md").read_text(encoding="utf-8")
print("PASS: 攝入 → 分支 + summary/entity 頁 + index/log")
# 2) 模擬 PR 合併後:冪等跳過;新來源觸發既有頁就地編輯
git(root, "checkout", "-q", "main")
git(root, "merge", "-q", branch)
ingest.main(["raw/converted/doc1.md", "--root", str(root)]) # 應 skip
assert git(root, "branch", "--show-current") == "main"
add_doc(root, "doc2.md", "第二份文件:支付閘道逾時已修復並通過回歸測試。")
git(root, "add", "-A")
git(root, "commit", "-q", "-m", "doc2")
ingest.main(["raw/converted/doc2.md", "--root", str(root)])
b2 = [b.strip("* ").strip() for b in
git(root, "branch", "--list", "ingest/*").splitlines() if branch not in b]
git(root, "checkout", "-q", b2[0])
meta, body = kb.parse_page(entity.read_text(encoding="utf-8"))
assert len(meta["sources"]) == 2 and "已更新" in meta["description"], meta
assert "新來源事實" in body
git(root, "checkout", "-q", "main")
print("PASS: 冪等跳過 + 既有 entity 頁就地編輯sources 追加)")
# 3) preflightraw/ 下未提交的 convert 產出(含中文檔名)不得被誤判為髒污
(root / "raw" / "converted" / "測試報告.md").write_text("中文", encoding="utf-8")
ingest.git_preflight(root) # 不應拋錯
stray = root / "wiki" / "concepts" / "stray.md"
stray.write_text("x", encoding="utf-8")
try:
ingest.git_preflight(root)
raise AssertionError("raw/ 以外的未提交變更應中止")
except SystemExit:
pass
stray.unlink()
print("PASS: preflight 放行 raw/(含中文檔名)、擋下 raw/ 以外的未提交變更")
# 4) kb.llm_json重試後切 fallback全失敗拋錯
kb.llm_json = real_llm
cfg = kb.load_config(root)
calls = {"n": 0}
def flaky(cfg_, model, prompt, temperature, json_format=False):
calls["n"] += 1
return "not-json" if calls["n"] < 3 else '{"summary_markdown": "ok"}'
kb.ollama_chat = flaky
obj, model = kb.llm_json(cfg, "ingest", "p", ingest.validate_chunk)
assert obj["summary_markdown"] == "ok" and model == "fake:fb" and calls["n"] == 3
kb.ollama_chat = lambda *a, **k: "junk"
try:
kb.llm_json(cfg, "ingest", "p", ingest.validate_chunk)
raise AssertionError("應拋 RuntimeError")
except RuntimeError as e:
assert "fallback" in str(e)
print("PASS: 重試 + fallback 切換 + 全失敗報錯")
print("ALL PASS")
finally:
kb.llm_json, kb.ollama_chat = real_llm, real_chat
shutil.rmtree(tmp, ignore_errors=True)
if __name__ == "__main__":
main()