Phase 5: MCP 薄殼（search_wiki/read_page）+ BM25 檢索 + 三個 Copilot Custom Agents

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

tools/search.py

@@ -0,0 +1,69 @@
+"""wiki BM25 全文檢索（第一版不用向量庫，AGENTS.md §0）。
+
+用法：python tools/search.py "查詢詞" [-k 10] [--root DIR]
+輸出：JSON 陣列（path、title、description、tags、score），供 agent 與 MCP 使用。
+"""
+import argparse
+import json
+import pathlib
+import re
+import sys
+
+sys.path.insert(0, str(pathlib.Path(__file__).parent))
+import kb
+from rank_bm25 import BM25Okapi
+
+
+def tokenize(text):
+    """英數字詞 + CJK bigram。
+
+    ponytail: bigram 斷詞無語意理解（同義詞不匹配），天花板是字面重疊；
+    升級路徑：Phase 6 後評估 EmbeddingGemma / snowflake-arctic-embed 向量檢索。
+    """
+    text = text.lower()
+    tokens = re.findall(r"[a-z0-9]+", text)
+    for run in re.findall(r"[一-鿿]+", text):
+        tokens += [run] if len(run) == 1 else [run[i:i + 2] for i in range(len(run) - 1)]
+    return tokens
+
+
+def build_corpus(root):
+    docs = []
+    for p in kb.iter_pages(root):
+        try:
+            meta, body = kb.parse_page(p.read_text(encoding="utf-8"))
+        except ValueError:
+            continue  # 壞頁由 lint 報，檢索直接略過
+        text = (f"{meta['title']} " * 3 + f"{meta['description']} " * 2
+                + " ".join(meta.get("tags") or []) + " " + body)
+        docs.append({"path": p.relative_to(root).as_posix(), "title": str(meta["title"]),
+                     "description": str(meta["description"]),
+                     "tags": [str(t) for t in meta.get("tags") or []],
+                     "tokens": tokenize(text)})
+    return docs
+
+
+def search(root, query, k=10):
+    docs = build_corpus(pathlib.Path(root))
+    if not docs:
+        return []
+    bm = BM25Okapi([d["tokens"] for d in docs])
+    scores = bm.get_scores(tokenize(query))
+    ranked = sorted(zip(docs, scores), key=lambda x: -x[1])[:k]
+    return [{"path": d["path"], "title": d["title"], "description": d["description"],
+             "tags": d["tags"], "score": round(float(s), 4)}
+            for d, s in ranked if s > 0]
+
+
+def main(argv=None):
+    ap = argparse.ArgumentParser(description=__doc__)
+    ap.add_argument("query")
+    ap.add_argument("-k", type=int, default=10, help="回傳筆數上限（查詢工作流上限 10）")
+    ap.add_argument("--root", default=str(kb.ROOT))
+    a = ap.parse_args(argv)
+    hits = search(a.root, a.query, max(1, min(a.k, 10)))
+    print(json.dumps(hits, ensure_ascii=False, indent=2))
+
+
+if __name__ == "__main__":
+    main()

tools/selfcheck_search.py

@@ -0,0 +1,88 @@
+"""Phase 5 自檢：BM25 檢索排序、MCP search_wiki / read_page、
+路徑跳脫防護（信任邊界）、token 上限截斷。
+
+執行：.venv/Scripts/python tools/selfcheck_search.py
+"""
+import os
+import pathlib
+import shutil
+import sys
+import tempfile
+
+sys.path.insert(0, str(pathlib.Path(__file__).parent))
+import kb
+import search
+
+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: 100, ingest_chunk_max_chars: 12000}
+"""
+
+
+def page(root, rel, title, desc, tags, body):
+    meta = {"type": {"summaries": "summary", "entities": "entity",
+                     "concepts": "concept"}[rel.split("/")[1]],
+            "title": title, "description": desc, "tags": tags,
+            "timestamp": "2026-07-14", "sources": ["raw/converted/x.md#abcd1234"],
+            "status": "draft"}
+    (root / rel).write_text(kb.dump_page(meta, body), encoding="utf-8")
+
+
+def main():
+    tmp = pathlib.Path(tempfile.mkdtemp(prefix="ppqa-search-"))
+    try:
+        root = tmp / "repo"
+        for sub in ("config", "wiki/summaries", "wiki/entities", "wiki/concepts"):
+            (root / sub).mkdir(parents=True)
+        (root / "config/models.yaml").write_text(CFG, encoding="utf-8")
+        page(root, "wiki/entities/payment-gateway.md", "支付閘道", "支付閘道模組",
+             ["gateway"], "壓力測試時出現逾時缺陷，重試機制未生效。")
+        page(root, "wiki/concepts/aml-testing.md", "AML 測試準則", "可疑交易監控測試綜合",
+             ["aml", "compliance"], "大額交易與分散交易樣態的監控測試要求。")
+        page(root, "wiki/summaries/long-doc.md", "長文件摘要", "截斷測試用",
+             ["test"], "逾時。" * 500)
+
+        hits = search.search(root, "支付閘道 逾時")
+        assert hits and hits[0]["path"] == "wiki/entities/payment-gateway.md", hits
+        assert all(h["score"] > 0 for h in hits)
+        hits2 = search.search(root, "可疑交易監控")
+        assert hits2[0]["path"] == "wiki/concepts/aml-testing.md", hits2
+        assert search.search(root, "zzz-nonexistent-term") == []
+        print("PASS: BM25 檢索排序（繁中 bigram）")
+
+        os.environ["PP_QA_ROOT"] = str(root)
+        import importlib
+        sys.path.insert(0, str(pathlib.Path(__file__).parents[1] / "mcp"))
+        server = importlib.import_module("server")
+        res = server.search_wiki("支付閘道 逾時", top_k=99)  # top_k 超限 → 收斂為 10
+        assert res[0]["path"] == "wiki/entities/payment-gateway.md"
+        pg = server.read_page("wiki/entities/payment-gateway.md")
+        assert pg["frontmatter"]["title"] == "支付閘道" and not pg["truncated"]
+        assert pg["source_refs"] == ["raw/converted/x.md#abcd1234"]
+        long = server.read_page("wiki/summaries/long-doc.md")
+        assert long["truncated"] and len(long["body"]) <= 150 and long["source_refs"]
+        print("PASS: MCP search_wiki + read_page（含 token 截斷、source_refs 保留）")
+
+        for bad in ("../AGENTS.md", "wiki/../config/models.yaml", "wiki/entities/x.txt"):
+            try:
+                server.read_page(bad)
+                raise AssertionError(f"應拒絕：{bad}")
+            except (ValueError, FileNotFoundError) as e:
+                assert isinstance(e, ValueError), f"{bad} 應為 ValueError"
+        try:
+            server.read_page("wiki/entities/no-such.md")
+            raise AssertionError("應拋 FileNotFoundError")
+        except FileNotFoundError:
+            pass
+        print("PASS: 路徑跳脫防護（信任邊界）")
+        print("ALL PASS")
+    finally:
+        os.environ.pop("PP_QA_ROOT", None)
+        shutil.rmtree(tmp, ignore_errors=True)
+
+
+if __name__ == "__main__":
+    main()