repo-manager/src/repo_manager/index_store.py
tegwick 5dc2f3cdf6 feat(cache): add rebuild and provenance safeguards
Assistant: codex
Assistant-Model: gpt-5.6-sol
Assistant-Session: 01a023c0-a0a3-7c03-b395-5a0d2757214d
2026-08-21 23:23:03 +02:00

109 lines
3.3 KiB
Python

"""Local JSON projection store for the vertical-slice proof (pre-Postgres)."""
from __future__ import annotations
import json
import os
import tempfile
from dataclasses import asdict, dataclass, field
from pathlib import Path
from typing import Any
from repo_manager.time import utc_now_text
def _now() -> str:
return utc_now_text()
@dataclass
class WorkRecordEntry:
kind: str
id: str | None
status: str | None
title: str | None
source_path: str
uuid: str | None = None
parent_id: str | None = None
extra: dict[str, Any] = field(default_factory=dict)
@dataclass
class RepoIndex:
slug: str
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.v1"
def to_dict(self) -> dict[str, Any]:
return {
"schema": self.schema,
"slug": self.slug,
"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,
}
@classmethod
def from_dict(cls, data: dict[str, Any]) -> RepoIndex:
records = [
WorkRecordEntry(**{k: v for k, v in r.items() if k in WorkRecordEntry.__dataclass_fields__})
for r in data.get("work_records", [])
]
return cls(
slug=data["slug"],
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",
)
def default_index_path(repo_root: Path) -> Path:
return repo_root / ".repo-manager" / "index.json"
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)
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
def load_index(path: Path) -> RepoIndex:
return RepoIndex.from_dict(json.loads(path.read_text(encoding="utf-8")))
def append_event(index: RepoIndex, event: dict[str, Any]) -> None:
event = {**event, "emitted_at": event.get("emitted_at") or _now()}
index.events.append(event)