feat(cache): add rebuild and provenance safeguards

Assistant: codex
Assistant-Model: gpt-5.6-sol
Assistant-Session: 01a023c0-a0a3-7c03-b395-5a0d2757214d

src/repo_manager/index_store.py

@@ -3,6 +3,8 @@
 from __future__ import annotations
 
 import json
+import os
+import tempfile
 from dataclasses import asdict, dataclass, field
 from pathlib import Path
 from typing import Any
@@ -32,9 +34,11 @@ class RepoIndex:
     repo_root: str
     head_sha: str | None
     observed_at: str
+    source_fingerprint: str | None = None
+    source_files: list[str] = field(default_factory=list)
     work_records: list[WorkRecordEntry] = field(default_factory=list)
     events: list[dict[str, Any]] = field(default_factory=list)
-    schema: str = "repo_manager.index.v0"
+    schema: str = "repo_manager.index.v1"
 
     def to_dict(self) -> dict[str, Any]:
         return {
@@ -43,6 +47,8 @@ class RepoIndex:
             "repo_root": self.repo_root,
             "head_sha": self.head_sha,
             "observed_at": self.observed_at,
+            "source_fingerprint": self.source_fingerprint,
+            "source_files": self.source_files,
             "work_records": [asdict(r) for r in self.work_records],
             "events": self.events,
         }
@@ -58,6 +64,8 @@ class RepoIndex:
             repo_root=data["repo_root"],
             head_sha=data.get("head_sha"),
             observed_at=data.get("observed_at") or _now(),
+            source_fingerprint=data.get("source_fingerprint"),
+            source_files=list(data.get("source_files") or []),
             work_records=records,
             events=list(data.get("events") or []),
             schema=data.get("schema") or "repo_manager.index.v0",
@@ -71,7 +79,24 @@ def default_index_path(repo_root: Path) -> Path:
 def save_index(index: RepoIndex, path: Path | None = None) -> Path:
     path = path or default_index_path(Path(index.repo_root))
     path.parent.mkdir(parents=True, exist_ok=True)
-    path.write_text(json.dumps(index.to_dict(), indent=2) + "\n", encoding="utf-8")
+    temporary: Path | None = None
+    try:
+        with tempfile.NamedTemporaryFile(
+            mode="w",
+            encoding="utf-8",
+            dir=path.parent,
+            prefix=f".{path.name}.",
+            delete=False,
+        ) as handle:
+            temporary = Path(handle.name)
+            handle.write(json.dumps(index.to_dict(), indent=2) + "\n")
+            handle.flush()
+            os.fsync(handle.fileno())
+        os.replace(temporary, path)
+        temporary = None
+    finally:
+        if temporary is not None:
+            temporary.unlink(missing_ok=True)
     return path