Files
the-custodian/state-hub/api/routers/workstreams.py
tegwick 0eb2ef0650 perf(api): CUST-WP-0041 — DB indexes, TTL caches, noload on list endpoints
- Migration t7o8p9q0r1s2: indexes on tasks.status, tasks(workstream_id,status),
  workstreams.status, sbom_snapshots(repo_id,snapshot_at)
- workplan-index: 30 s TTL cache + ?refresh param (4171 ms → 16 ms on hit)
- /state/summary: 15 s TTL cache, bypassed on Cache-Control: no-cache
- /topics/: noload(workstreams, decisions, progress_events) (2382 ms → 115 ms)
- /domains/: noload(topics, repos, goals) (2252 ms → 39 ms)
- /repos/: noload(goals) (2222 ms → 599 ms first / fast on repeat)
- conftest: reset TTL caches between tests to prevent bleed-through

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-15 11:12:17 +02:00

190 lines
5.9 KiB
Python

import uuid
import socket
import time
from pathlib import Path
from typing import Any
from fastapi import APIRouter, Depends, HTTPException, Query, status
from sqlalchemy import select
from sqlalchemy.ext.asyncio import AsyncSession
from api.database import get_session
from api.models.managed_repo import ManagedRepo
from api.models.workstream import Workstream
from api.schemas.workstream import (
WorkstreamCreate,
WorkstreamRead,
WorkstreamStatus,
WorkstreamUpdate,
)
router = APIRouter(prefix="/workstreams", tags=["workstreams"])
_INDEX_CACHE: dict[str, Any] | None = None
_INDEX_CACHE_AT: float = 0.0
_INDEX_TTL = 30.0
def _repo_path(repo: ManagedRepo) -> Path | None:
hostname = socket.gethostname()
candidates = []
host_paths = repo.host_paths or {}
if host_paths.get(hostname):
candidates.append(host_paths[hostname])
if repo.local_path:
candidates.append(repo.local_path)
for raw in candidates:
path = Path(raw).expanduser()
if path.is_dir():
return path
return None
def _frontmatter(path: Path) -> dict[str, Any]:
try:
text = path.read_text(encoding="utf-8")
except OSError:
return {}
if not text.startswith("---\n"):
return {}
end = text.find("\n---", 4)
if end == -1:
return {}
data: dict[str, Any] = {}
for raw_line in text[4:end].splitlines():
line = raw_line.strip()
if not line or line.startswith("#") or ":" not in line:
continue
key, value = line.split(":", 1)
value = value.strip()
if len(value) >= 2 and value[0] == value[-1] and value[0] in {"'", '"'}:
value = value[1:-1]
data[key.strip()] = value
return data
@router.get("/", response_model=list[WorkstreamRead])
async def list_workstreams(
topic_id: uuid.UUID | None = None,
repo_id: uuid.UUID | None = None,
repo_goal_id: uuid.UUID | None = None,
status: WorkstreamStatus | None = None,
owner: str | None = None,
slug: str | None = None,
session: AsyncSession = Depends(get_session),
) -> list[Workstream]:
q = select(Workstream)
if topic_id:
q = q.where(Workstream.topic_id == topic_id)
if repo_id:
q = q.where(Workstream.repo_id == repo_id)
if repo_goal_id:
q = q.where(Workstream.repo_goal_id == repo_goal_id)
if status:
q = q.where(Workstream.status == status)
if owner:
q = q.where(Workstream.owner == owner)
if slug:
q = q.where(Workstream.slug == slug)
q = q.order_by(
Workstream.planning_priority.asc().nullslast(),
Workstream.planning_order.asc().nullslast(),
Workstream.updated_at.desc(),
)
result = await session.execute(q)
return list(result.scalars().all())
@router.get("/workplan-index")
async def workplan_index(
refresh: bool = Query(False, description="Force cache invalidation"),
session: AsyncSession = Depends(get_session),
) -> dict[str, Any]:
"""Map file-backed workstream ids to their local workplan filenames."""
global _INDEX_CACHE, _INDEX_CACHE_AT
if not refresh and _INDEX_CACHE is not None and (time.monotonic() - _INDEX_CACHE_AT) < _INDEX_TTL:
return _INDEX_CACHE
result = await session.execute(
select(ManagedRepo).where(ManagedRepo.status == "active").order_by(ManagedRepo.slug)
)
index: dict[str, Any] = {}
for repo in result.scalars().all():
root = _repo_path(repo)
if root is None:
continue
for directory, archived in (
(root / "workplans", False),
(root / "workplans" / "archived", True),
):
if not directory.is_dir():
continue
for path in sorted(directory.glob("*.md")):
data = _frontmatter(path)
workstream_id = data.get("state_hub_workstream_id")
if not workstream_id:
continue
index[str(workstream_id)] = {
"filename": path.name,
"relative_path": str(path.relative_to(root)),
"repo_slug": repo.slug,
"archived": archived,
}
_INDEX_CACHE = {"workstreams": index}
_INDEX_CACHE_AT = time.monotonic()
return _INDEX_CACHE
@router.post("/", response_model=WorkstreamRead, status_code=status.HTTP_201_CREATED)
async def create_workstream(
body: WorkstreamCreate,
session: AsyncSession = Depends(get_session),
) -> Workstream:
ws = Workstream(**body.model_dump())
session.add(ws)
await session.commit()
await session.refresh(ws)
return ws
@router.get("/{workstream_id}", response_model=WorkstreamRead)
async def get_workstream(
workstream_id: uuid.UUID,
session: AsyncSession = Depends(get_session),
) -> Workstream:
ws = await session.get(Workstream, workstream_id)
if ws is None:
raise HTTPException(status_code=404, detail="Workstream not found")
return ws
@router.patch("/{workstream_id}", response_model=WorkstreamRead)
async def update_workstream(
workstream_id: uuid.UUID,
body: WorkstreamUpdate,
session: AsyncSession = Depends(get_session),
) -> Workstream:
ws = await session.get(Workstream, workstream_id)
if ws is None:
raise HTTPException(status_code=404, detail="Workstream not found")
for field, value in body.model_dump(exclude_unset=True).items():
setattr(ws, field, value)
await session.commit()
await session.refresh(ws)
return ws
@router.delete("/{workstream_id}", response_model=WorkstreamRead)
async def archive_workstream(
workstream_id: uuid.UUID,
session: AsyncSession = Depends(get_session),
) -> Workstream:
ws = await session.get(Workstream, workstream_id)
if ws is None:
raise HTTPException(status_code=404, detail="Workstream not found")
ws.status = "archived"
await session.commit()
await session.refresh(ws)
return ws