§22 S2: registry mirror reads .collection.yaml manifests

Discover named collections by walking each project's content-repo root for <subdir>/.collection.yaml; parse + upsert with immutable-type enforcement (§22.4a) and project-visibility inheritance. The default collection still flows from projects.yaml. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-05 12:59:25 -07:00
parent 599e7018f6
commit 74476423ba
2 changed files with 251 additions and 0 deletions
@@ -55,6 +55,17 @@ class ProjectEntry:
    config: dict = field(default_factory=dict)  # theme, enabled_models


+@dataclass
+class CollectionEntry:
+    """A named collection declared by a `.collection.yaml` manifest inside a
+    project's content repo (S2). `visibility=None` means "inherit the project's
+    visibility"."""
+    type: str
+    visibility: str | None
+    initial_state: str
+    name: str | None
+
+
@dataclass
 class RegistryDoc:
    deployment_name: str
@@ -114,6 +125,33 @@ def parse_registry(text: str) -> RegistryDoc:
    )


+def parse_collection_manifest(text: str) -> CollectionEntry:
+    """Parse + validate a `.collection.yaml`. Pure (no I/O). Raises RegistryError.
+
+    `type` is required and immutable (§22.4a, enforced at upsert). `visibility`
+    is optional — omitted means inherit the project's. `initial_state` defaults
+    per type (§22.4b)."""
+    raw = yaml.safe_load(text) or {}
+    if not isinstance(raw, dict):
+        raise RegistryError("collection manifest must be a mapping")
+    ctype = str(raw.get("type") or "").strip()
+    if ctype not in VALID_TYPES:
+        raise RegistryError(f"collection has invalid type {ctype!r}")
+    vis = raw.get("visibility")
+    if vis is not None:
+        vis = str(vis).strip()
+        if vis not in VALID_VISIBILITY:
+            raise RegistryError(f"collection has invalid visibility {vis!r}")
+    initial_state = str(
+        raw.get("initial_state") or _TYPE_DEFAULT_INITIAL_STATE[ctype]
+    ).strip()
+    if initial_state not in VALID_INITIAL_STATE:
+        raise RegistryError(f"collection has invalid initial_state {initial_state!r}")
+    name = raw.get("name")
+    name = str(name).strip() if name else None
+    return CollectionEntry(ctype, vis, initial_state, name)
+
+
 def _default_collection_id(project_id: str, default_id: str) -> str:
    """The id of a project's default collection. The deployment's primary
    project (== `default_id`, the §22.13 resolved default) gets the stable
@@ -193,6 +231,71 @@ def apply_registry(doc: RegistryDoc, registry_sha: str, default_id: str) -> None
        )


+def _upsert_named_collection(
+    proj: ProjectEntry, subdir: str, ce: CollectionEntry, sha: str
+) -> None:
+    """Upsert one named collection (S2). Type is immutable (§22.4a): a type
+    change against an existing row is refused (logged, not applied). A None
+    manifest visibility inherits the project's visibility."""
+    visibility = ce.visibility or proj.visibility
+    with db.tx() as conn:
+        existing = conn.execute(
+            "SELECT type FROM collections WHERE id = ?", (subdir,)
+        ).fetchone()
+        if existing is not None and existing["type"] != ce.type:
+            log.error(
+                "registry: refusing immutable type change on collection %s (%s -> %s)",
+                subdir, existing["type"], ce.type,
+            )
+            return
+        conn.execute(
+            """
+            INSERT INTO collections
+                (id, project_id, type, subfolder, initial_state, visibility, name, registry_sha, updated_at)
+            VALUES (?, ?, ?, ?, ?, ?, ?, ?, datetime('now'))
+            ON CONFLICT(id) DO UPDATE SET
+                project_id = excluded.project_id,
+                initial_state = excluded.initial_state,
+                visibility = excluded.visibility,
+                name = excluded.name,
+                registry_sha = excluded.registry_sha,
+                updated_at = datetime('now')
+            """,
+            (subdir, proj.id, ce.type, subdir, ce.initial_state, visibility, ce.name, sha),
+        )
+
+
+async def _mirror_named_collections(config: Config, gitea: Gitea, doc: RegistryDoc, sha: str) -> None:
+    """§22 S2: named collections are declared by `.collection.yaml` manifests
+    inside each project's content repo (the default collection comes from
+    projects.yaml). Walk each content repo root; a subdir carrying a manifest
+    becomes a collection keyed by the subdir name. Tolerant: a transport or
+    parse failure on one project/collection logs and is skipped, never aborts
+    the wider mirror (keep last-good)."""
+    for proj in doc.projects:
+        try:
+            items = await gitea.list_dir(config.gitea_org, proj.content_repo, "", ref="main")
+        except Exception as e:  # noqa: BLE001 — GiteaError/transport: tolerate
+            log.warning("registry: cannot list %s root: %s", proj.content_repo, e)
+            continue
+        for it in items:
+            if it.get("type") != "dir":
+                continue
+            subdir = it["name"]
+            manifest = await gitea.get_contents(
+                config.gitea_org, proj.content_repo, f"{subdir}/.collection.yaml", ref="main"
+            )
+            if not manifest or manifest.get("type") != "file":
+                continue
+            mtext = base64.b64decode(manifest["content"]).decode("utf-8")
+            try:
+                ce = parse_collection_manifest(mtext)
+            except RegistryError as e:
+                log.error("registry: bad manifest %s/%s: %s", proj.content_repo, subdir, e)
+                continue
+            _upsert_named_collection(proj, subdir, ce, sha)
+
+
 async def refresh_registry(config: Config, gitea: Gitea) -> None:
    """Mirror REGISTRY_REPO/projects.yaml into projects + deployment.

@@ -213,4 +316,6 @@ async def refresh_registry(config: Config, gitea: Gitea) -> None:
    doc = parse_registry(text)
    from . import projects as projects_mod
    apply_registry(doc, sha, projects_mod.resolved_default_id(config))
+    # §22 S2: discover + upsert named collections from each content repo.
+    await _mirror_named_collections(config, gitea, doc, sha)
    log.info("registry: mirrored %d project(s) at %s", len(doc.projects), sha)