perf(doi): 13x speedup for /repos/doi/summary (108s → ~6s)

Two fixes:
1. skip_consistency=True in summary mode — omits C7/C13 subprocess calls
   (consistency_check.py) which were the main bottleneck (32 spawns for 16 repos).
   Full check still available per-repo via GET /repos/{slug}/doi.
2. asyncio.gather — all repos evaluated in parallel instead of sequentially.

Also: rename Repositories page title from "Repos" to "Repositories".

Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-03-20 01:29:27 +01:00
parent 5eeeeeb6c4
commit 27e755815f
3 changed files with 42 additions and 31 deletions

View File

@@ -1,3 +1,4 @@
import asyncio
import uuid
from fastapi import APIRouter, Depends, HTTPException, status
@@ -80,8 +81,7 @@ async def doi_summary(session: AsyncSession = Depends(get_session)) -> list[DoIS
domain_result = await session.execute(select(Domain))
domain_map = {d.id: d.slug for d in domain_result.scalars().all()}
entries: list[DoISummaryEntry] = []
for repo in repos:
async def _check_one(repo: ManagedRepo) -> DoISummaryEntry:
repo_dict = {
"slug": repo.slug,
"domain_slug": domain_map.get(repo.domain_id),
@@ -90,8 +90,10 @@ async def doi_summary(session: AsyncSession = Depends(get_session)) -> list[DoIS
"host_paths": repo.host_paths or {},
"last_sbom_at": str(repo.last_sbom_at) if repo.last_sbom_at else None,
}
report = await _doi_evaluate(repo_dict)
entries.append(DoISummaryEntry(
# skip_consistency=True: omits C7/C13 subprocess calls for speed.
# The full check is available via GET /repos/{slug}/doi.
report = await _doi_evaluate(repo_dict, skip_consistency=True)
return DoISummaryEntry(
repo_slug=repo.slug,
domain_slug=domain_map.get(repo.domain_id),
tier=report.tier,
@@ -99,7 +101,9 @@ async def doi_summary(session: AsyncSession = Depends(get_session)) -> list[DoIS
standard_pass=report.standard_pass,
full_pass=report.full_pass,
checked_at=report.checked_at,
))
)
entries: list[DoISummaryEntry] = list(await asyncio.gather(*[_check_one(r) for r in repos]))
tier_order = {"none": 0, "core": 1, "standard": 2, "full": 3}
entries.sort(key=lambda e: tier_order.get(e.tier, 0))