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>
2026-03-20 01:29:27 +01:00
parent 5eeeeeb6c4
commit 27e755815f
3 changed files with 42 additions and 31 deletions
--- a/api/doi_engine.py
+++ b/api/doi_engine.py
@@ -110,7 +110,11 @@ async def _run_consistency(repo_slug: str, api_base: str) -> tuple[int, int, int
    return fail, warn, info


-async def evaluate(repo: dict, api_base: str = "http://127.0.0.1:8000") -> DoIReport:
+async def evaluate(
+    repo: dict,
+    api_base: str = "http://127.0.0.1:8000",
+    skip_consistency: bool = False,
+) -> DoIReport:
    slug = repo.get("slug", "unknown")
    results: list[CriterionResult] = []

@@ -171,14 +175,17 @@ async def evaluate(repo: dict, api_base: str = "http://127.0.0.1:8000") -> DoIRe
        _r("C6", "CLAUDE.md present", "standard", "fail", "CLAUDE.md not found at repo root")

    # C7: workplan convention — consistency check 0 FAIL
-    try:
-        fail, warn, _ = await _run_consistency(slug, api_base)
-        if fail == 0:
-            _r("C7", "Workplan convention (0 FAIL)", "standard", "pass", f"consistency: {fail} fail / {warn} warn")
-        else:
-            _r("C7", "Workplan convention (0 FAIL)", "standard", "fail", f"consistency: {fail} fail / {warn} warn")
-    except Exception as e:
-        _r("C7", "Workplan convention (0 FAIL)", "standard", "skip", f"Could not run consistency check: {e}")
+    if skip_consistency:
+        _r("C7", "Workplan convention (0 FAIL)", "standard", "skip", "Not checked in summary mode — use /repos/{slug}/doi for full check")
+    else:
+        try:
+            fail, warn, _ = await _run_consistency(slug, api_base)
+            if fail == 0:
+                _r("C7", "Workplan convention (0 FAIL)", "standard", "pass", f"consistency: {fail} fail / {warn} warn")
+            else:
+                _r("C7", "Workplan convention (0 FAIL)", "standard", "fail", f"consistency: {fail} fail / {warn} warn")
+        except Exception as e:
+            _r("C7", "Workplan convention (0 FAIL)", "standard", "skip", f"Could not run consistency check: {e}")

    # C8: SBOM ingested
    last_sbom = repo.get("last_sbom_at")
@@ -251,21 +258,21 @@ async def evaluate(repo: dict, api_base: str = "http://127.0.0.1:8000") -> DoIRe
                   "CLAUDE.md has no kaizen agent reference")

    # C13: consistency check clean (0 FAIL, 0 WARN — C-12 exempt)
-    try:
-        fail, warn, _ = await _run_consistency(slug, api_base)
-        # C-12 warns are legacy DB-only tasks — deduct them from warn count
-        c12_count = await _get(api_base, "/tasks/", {"workstream_id": None}) or []
-        # Use raw counts from the script output
-        if fail == 0 and warn == 0:
-            _r("C13", "Consistency check clean (0 FAIL/WARN)", "full", "pass")
-        elif fail == 0 and warn > 0:
-            _r("C13", "Consistency check clean (0 FAIL/WARN)", "full", "warn",
-               f"{warn} warn(s) — C-12 legacy tasks may be exempt")
-        else:
-            _r("C13", "Consistency check clean (0 FAIL/WARN)", "full", "fail",
-               f"{fail} fail(s), {warn} warn(s)")
-    except Exception as e:
-        _r("C13", "Consistency check clean (0 FAIL/WARN)", "full", "skip", f"Could not run: {e}")
+    if skip_consistency:
+        _r("C13", "Consistency check clean (0 FAIL/WARN)", "full", "skip", "Not checked in summary mode — use /repos/{slug}/doi for full check")
+    else:
+        try:
+            fail, warn, _ = await _run_consistency(slug, api_base)
+            if fail == 0 and warn == 0:
+                _r("C13", "Consistency check clean (0 FAIL/WARN)", "full", "pass")
+            elif fail == 0 and warn > 0:
+                _r("C13", "Consistency check clean (0 FAIL/WARN)", "full", "warn",
+                   f"{warn} warn(s) — C-12 legacy tasks may be exempt")
+            else:
+                _r("C13", "Consistency check clean (0 FAIL/WARN)", "full", "fail",
+                   f"{fail} fail(s), {warn} warn(s)")
+        except Exception as e:
+            _r("C13", "Consistency check clean (0 FAIL/WARN)", "full", "skip", f"Could not run: {e}")

    # C14: host paths registered
    host_paths = repo.get("host_paths") or {}
--- a/api/routers/repos.py
+++ b/api/routers/repos.py
@@ -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))
--- a/dashboard/src/repos.md
+++ b/dashboard/src/repos.md
@@ -1,5 +1,5 @@
 ---
-title: Repos
+title: Repositories
 ---

 ```js
@@ -115,7 +115,7 @@ const doiFullCount     = repoRows.filter(r => r._doiTier === "full").length;
 const doiNoneCount     = repoRows.filter(r => r._doiTier === "none").length;
 ```

-# Repos
+# Repositories

 ```js
 import {withDocHelp} from "./components/doc-overlay.js";