§22 S2: corpus mirror reads each collection's <subfolder>/rfcs/

refresh_meta_repo now iterates a project's collections and keys cached_rfcs by
collection_id; the default collection (subfolder '') keeps the shipped rfcs/
root path. N=1 default path unchanged (469 green).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

backend/app/cache.py

@@ -54,15 +54,27 @@ async def refresh_meta_repo(config: Config, gitea: Gitea) -> None:
 
 
 async def _refresh_project_corpus(org: str, project_id: str, repo: str, gitea: Gitea) -> None:
-    # §22 S1: the corpus grain is the collection. The mirror is project-grained
+    # §22 S2: the corpus grain is the collection. Mirror every collection of the
-    # (reads rfcs/ at the repo root = the project's default collection); resolve
+    # project from its `<subfolder>/rfcs/` directory, keying cached_rfcs by the
-    # that collection once and key cached_rfcs by it.
+    # collection id. The default collection (subfolder '') reads `rfcs/` — the
+    # shipped path, unchanged. include_unlisted: the mirror serves every
+    # collection's content regardless of enumeration visibility.
     from . import collections as collections_mod
-    collection_id = collections_mod.default_collection_id(project_id)
+    for col in collections_mod.list_collections(project_id, include_unlisted=True):
+        await _refresh_collection_corpus(
+            org, project_id, repo, col["id"], col["subfolder"] or "", gitea
+        )
+
+
+async def _refresh_collection_corpus(
+    org: str, project_id: str, repo: str, collection_id: str, subfolder: str, gitea: Gitea
+) -> None:
+    rfcs_dir = f"{subfolder}/rfcs" if subfolder else "rfcs"
     try:
-        files = await gitea.list_dir(org, repo, "rfcs", ref="main")
+        files = await gitea.list_dir(org, repo, rfcs_dir, ref="main")
     except GiteaError as e:
-        log.warning("refresh_meta_repo: project %s: cannot list rfcs/: %s", project_id, e)
+        log.warning("refresh_meta_repo: %s/%s: cannot list %s: %s",
+                    project_id, collection_id, rfcs_dir, e)
         return
 
     seen_slugs: set[str] = set()
@@ -76,17 +88,19 @@ async def _refresh_project_corpus(org: str, project_id: str, repo: str, gitea: G
         try:
             entry = entry_mod.parse(text)
         except Exception as parse_err:
-            log.warning("refresh_meta_repo: %s: skipping %s: %s", project_id, f["path"], parse_err)
+            log.warning("refresh_meta_repo: %s/%s: skipping %s: %s",
+                        project_id, collection_id, f["path"], parse_err)
             continue
         if not entry.slug:
-            log.warning("refresh_meta_repo: %s: skipping %s: missing slug", project_id, f["path"])
+            log.warning("refresh_meta_repo: %s/%s: skipping %s: missing slug",
+                        project_id, collection_id, f["path"])
             continue
         seen_slugs.add(entry.slug)
         _upsert_cached_rfc(entry, body_sha=sha, collection_id=collection_id)
 
-    # Entries removed from a project's rfcs/ — the spec keeps withdrawn entries
+    # Entries removed from a collection's rfcs/ — the spec keeps withdrawn entries
     # as historical record (§3), so this fires only for out-of-band deletes;
-    # leave the row, scoped to this project, for reconciler attention.
+    # leave the row, scoped to this collection, for reconciler attention.
     existing = {
         row["slug"]
         for row in db.conn().execute(
@@ -94,7 +108,8 @@ async def _refresh_project_corpus(org: str, project_id: str, repo: str, gitea: G
         )
     }
     for missing in existing - seen_slugs:
-        log.info("refresh_meta_repo: %s/%s no longer in rfcs/ — leaving cache row", project_id, missing)
+        log.info("refresh_meta_repo: %s/%s/%s no longer present — leaving cache row",
+                 project_id, collection_id, missing)
 
 
 def _upsert_cached_rfc(entry: entry_mod.Entry, body_sha: str, collection_id: str = "default") -> None:

backend/tests/test_collection_scoped_serve.py

@@ -0,0 +1,77 @@
+"""§22 S2 — collection-grained corpus mirror + collection-scoped serve/propose.
+
+The mirror test drives cache.refresh_meta_repo against an in-memory content repo
+holding entries under both the default `rfcs/` and a named collection's
+`features/rfcs/`, and asserts cached_rfcs is keyed by the right collection_id."""
+from __future__ import annotations
+
+import asyncio
+import tempfile
+from pathlib import Path
+
+from app import cache, db
+from app.config import Config
+
+
+def _db() -> Config:
+    cfg = Config(
+        gitea_url="x", gitea_bot_user="x", gitea_bot_token="x", gitea_org="wiggleverse",
+        registry_repo="registry", oauth_client_id="x",
+        oauth_client_secret="x", app_url="x", secret_key="x",
+        database_path=Path(tempfile.mkdtemp(prefix="colserve-")) / "t.db",
+        owner_gitea_login="x", webhook_secret="x",
+    )
+    db.run_migrations(cfg)
+    if db._CONN is not None:
+        db._CONN.close()
+        db._CONN = None
+    db.init(cfg)
+    return cfg
+
+
+class _CorpusGitea:
+    """A content repo modelled as a flat {path: text} map, listing files under a
+    directory prefix and reading them back."""
+
+    def __init__(self, tree: dict[str, str]):
+        self._tree = tree
+
+    async def list_dir(self, org, repo, path, ref="main"):
+        out = []
+        prefix = (path.rstrip("/") + "/") if path else ""
+        for p in self._tree:
+            if p.startswith(prefix) and "/" not in p[len(prefix):]:
+                out.append({"type": "file", "name": p.split("/")[-1], "path": p})
+        return out
+
+    async def read_file(self, org, repo, path, ref="main"):
+        t = self._tree.get(path)
+        return (t, "sha-" + path) if t is not None else None
+
+
+def _entry_md(slug, title):
+    return f"---\nslug: {slug}\ntitle: {title}\nstate: active\n---\nbody\n"
+
+
+def _seed_project_with_two_collections():
+    db.conn().execute(
+        "INSERT OR REPLACE INTO projects (id, name, content_repo, visibility, updated_at) "
+        "VALUES ('ohm','Ohm','ohm-rfc','public', datetime('now'))")
+    for cid, sub in [("default", ""), ("features", "features")]:
+        db.conn().execute(
+            "INSERT OR REPLACE INTO collections (id, project_id, type, subfolder, initial_state, "
+            "visibility, created_at, updated_at) VALUES (?, 'ohm','document',?, "
+            "'super-draft','public', datetime('now'), datetime('now'))", (cid, sub))
+
+
+def test_mirror_keys_entries_by_collection():
+    cfg = _db()
+    _seed_project_with_two_collections()
+    gitea = _CorpusGitea({
+        "rfcs/a.md": _entry_md("a", "Default A"),
+        "features/rfcs/b.md": _entry_md("b", "Feature B"),
+    })
+    asyncio.run(cache.refresh_meta_repo(cfg, gitea))
+    got = {(r["collection_id"], r["slug"]) for r in
+           db.conn().execute("SELECT collection_id, slug FROM cached_rfcs")}
+    assert got == {("default", "a"), ("features", "b")}