§22 S1: thread collection_id through backend + update tests (N=1 unchanged, 454 green)
- collections.py resolution helpers (default_collection_id, type, initial_state) - registry mirror writes project grouping fields + default-collection corpus fields - auth.project_of_rfc joins collections; project_member_role reads memberships - cache/api_*/funder writers+readers re-keyed to collection_id (cached_prs + denormalised project_id tags unchanged); api_deployment reads type/initial_state from the default collection - projects.py restamp detects bootstrap via collections; initial_state via collection - tests updated to the three-tier schema; test_migration_028 retired (superseded by 029) - add @S1 acceptance test (collection grain + N=1 serving) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Ben Stull
+51
-20
@@ -114,44 +114,74 @@ def parse_registry(text: str) -> RegistryDoc:
|
||||
)
|
||||
|
||||
|
||||
def apply_registry(doc: RegistryDoc, registry_sha: str) -> None:
|
||||
"""Upsert the parsed registry into projects + deployment. Idempotent.
|
||||
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
|
||||
literal `'default'` — matching migration 029's seed so the upsert *merges*
|
||||
onto the migration-seeded row rather than duplicating it (critical on a
|
||||
fresh deploy where the bootstrap `default` project is later restamped to the
|
||||
configured id). Any additional project keys its default collection by its own
|
||||
id, keeping the collection PK globally unique (pre-S5 multi-project)."""
|
||||
return "default" if project_id == default_id else project_id
|
||||
|
||||
§22.4a: `type` is immutable — a change against an existing row is rejected
|
||||
(skip + log), never applied. Projects absent from the registry are left in
|
||||
place (archival is out of scope for M3; they simply stop refreshing).
|
||||
|
||||
def apply_registry(doc: RegistryDoc, registry_sha: str, default_id: str) -> None:
|
||||
"""Upsert the parsed registry into projects + their default collections +
|
||||
the deployment singleton. Idempotent.
|
||||
|
||||
§22 three-tier (S1): a project carries the grouping-tier fields (name,
|
||||
content_repo, visibility, config); the per-corpus fields (`type`,
|
||||
`initial_state`) live on the project's default collection. §22.4a: `type` is
|
||||
immutable — a change against an existing collection is rejected (skip the
|
||||
type change + log), never applied. Projects absent from the registry are
|
||||
left in place (archival is out of scope for M3; they stop refreshing).
|
||||
"""
|
||||
with db.tx() as conn:
|
||||
for e in doc.projects:
|
||||
cid = _default_collection_id(e.id, default_id)
|
||||
existing = conn.execute(
|
||||
"SELECT type FROM projects WHERE id = ?", (e.id,)
|
||||
"SELECT type FROM collections WHERE id = ?", (cid,)
|
||||
).fetchone()
|
||||
if existing is not None and existing["type"] != e.type:
|
||||
type_locked = existing is not None and existing["type"] != e.type
|
||||
if type_locked:
|
||||
log.error(
|
||||
"registry: refusing immutable type change on project %s (%s -> %s)",
|
||||
e.id, existing["type"], e.type,
|
||||
"registry: refusing immutable type change on collection %s (%s -> %s)",
|
||||
cid, existing["type"], e.type,
|
||||
)
|
||||
continue
|
||||
# The project (grouping tier) always refreshes.
|
||||
conn.execute(
|
||||
"""
|
||||
INSERT INTO projects
|
||||
(id, name, type, content_repo, visibility, initial_state,
|
||||
config_json, registry_sha, updated_at)
|
||||
VALUES (?, ?, ?, ?, ?, ?, ?, ?, datetime('now'))
|
||||
(id, name, content_repo, visibility, config_json, registry_sha, updated_at)
|
||||
VALUES (?, ?, ?, ?, ?, ?, datetime('now'))
|
||||
ON CONFLICT(id) DO UPDATE SET
|
||||
name = excluded.name,
|
||||
type = excluded.type,
|
||||
content_repo = excluded.content_repo,
|
||||
visibility = excluded.visibility,
|
||||
initial_state = excluded.initial_state,
|
||||
config_json = excluded.config_json,
|
||||
registry_sha = excluded.registry_sha,
|
||||
updated_at = datetime('now')
|
||||
""",
|
||||
(
|
||||
e.id, e.name, e.type, e.content_repo, e.visibility,
|
||||
e.initial_state, json.dumps(e.config), registry_sha,
|
||||
),
|
||||
(e.id, e.name, e.content_repo, e.visibility, json.dumps(e.config), registry_sha),
|
||||
)
|
||||
# The default collection (corpus tier). On an immutable-type
|
||||
# conflict, keep the stored type but still refresh the rest.
|
||||
effective_type = existing["type"] if type_locked else e.type
|
||||
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,
|
||||
type = excluded.type,
|
||||
initial_state = excluded.initial_state,
|
||||
visibility = excluded.visibility,
|
||||
name = excluded.name,
|
||||
registry_sha = excluded.registry_sha,
|
||||
updated_at = datetime('now')
|
||||
""",
|
||||
(cid, e.id, effective_type, e.initial_state, e.visibility, e.name, registry_sha),
|
||||
)
|
||||
conn.execute(
|
||||
"""
|
||||
@@ -181,5 +211,6 @@ async def refresh_registry(config: Config, gitea: Gitea) -> None:
|
||||
# includes it on the contents response); fall back to the blob sha.
|
||||
sha = item.get("last_commit_sha") or item.get("sha") or ""
|
||||
doc = parse_registry(text)
|
||||
apply_registry(doc, sha)
|
||||
from . import projects as projects_mod
|
||||
apply_registry(doc, sha, projects_mod.resolved_default_id(config))
|
||||
log.info("registry: mirrored %d project(s) at %s", len(doc.projects), sha)
|
||||
|
||||
Reference in New Issue
Block a user