fix(§22): heal mig-029 vs registry-mirror collection-id divergence
On a deployment that already had >=2 projects when migration 029 ran, 029 seeds the default project's collection id as the project id (e.g. 'ohm'), but the registry mirror expects 'default' -> it inserted a duplicate empty 'default' collection, orphaning the entries. Adds projects.reconcile_default_collection_id() -- the collection-grain twin of restamp_default_project -- run at startup BEFORE the mirror so it merges onto the canonical 'default' collection instead of duplicating. Renames the divergent collection id and cascades collection_id across all keyed tables (FK-off atomic rename + foreign_key_check). Idempotent; no-op on fresh / single-project / already-aligned deploys. Seam tests show the duplicate forms without the fix and merges with it. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Ben Stull
@@ -102,6 +102,12 @@ async def lifespan(app: FastAPI):
|
||||
db.run_migrations(config)
|
||||
db.init(config)
|
||||
gitea = Gitea(config)
|
||||
# §22 framework heal: reconcile a divergent default-project collection id
|
||||
# (migration 029's ≥2-projects seed names it after the project, e.g. 'ohm',
|
||||
# but the mirror expects 'default') BEFORE the mirror runs, so the mirror
|
||||
# merges onto the canonical 'default' collection instead of duplicating it.
|
||||
# Idempotent no-op on fresh / single-project / already-aligned deployments.
|
||||
projects.reconcile_default_collection_id(config)
|
||||
# §22.2: mirror the registry before anything reads projects/content_repo.
|
||||
# First boot has no last-good rows, so a missing/invalid registry is fatal
|
||||
# (loud-fail per separation-of-concerns); the reconciler sweep keeps it
|
||||
|
||||
@@ -92,6 +92,95 @@ def restamp_default_project(config: Config) -> None:
|
||||
DEFAULT_PROJECT_ID, target, len(pid_tables))
|
||||
|
||||
|
||||
def reconcile_default_collection_id(config: Config) -> None:
|
||||
"""Heal the §22 migration-029 vs registry-mirror divergence for the default
|
||||
project's collection id on a multi-project deployment.
|
||||
|
||||
Migration 029 seeds each project's default collection id as the literal
|
||||
'default' only when the DB holds a single project at migration time; with
|
||||
≥2 projects it falls back to the *project id* (avoiding a PK collision —
|
||||
029 can't read DEFAULT_PROJECT_ID, there is no env in SQL). But the registry
|
||||
mirror (`registry._default_collection_id`) expects the deployment's default
|
||||
project to own the collection id 'default'. On an upgrade whose DB already
|
||||
held ≥2 projects when 029 ran, the default project's collection is therefore
|
||||
named after the project (e.g. 'ohm'), and the next mirror would INSERT a
|
||||
second, empty 'default' collection instead of merging — duplicating the
|
||||
default corpus and orphaning the entries (which point at 'ohm').
|
||||
|
||||
This is the collection-grain twin of `restamp_default_project`. Run at
|
||||
startup BEFORE the registry mirror so the canonical 'default' collection
|
||||
already exists when the mirror upserts (merge, not duplicate). Renames the
|
||||
divergent collection's id to 'default' and cascades `collection_id` across
|
||||
every collection-keyed table, with FK enforcement off for the atomic rename
|
||||
and a `foreign_key_check` backstop before commit. Idempotent; a no-op on
|
||||
fresh / single-project / already-aligned deployments.
|
||||
"""
|
||||
from .collections import DEFAULT_COLLECTION_ID
|
||||
|
||||
target = resolved_default_id(config)
|
||||
if target == DEFAULT_COLLECTION_ID: # default project already owns 'default'
|
||||
return
|
||||
conn = db.conn()
|
||||
# The 029 ≥2-projects seed names the default project's collection after the
|
||||
# project itself; the canonical id the mirror expects is 'default'.
|
||||
divergent = conn.execute(
|
||||
"SELECT 1 FROM collections WHERE id = ? AND project_id = ? LIMIT 1",
|
||||
(target, target),
|
||||
).fetchone()
|
||||
if not divergent:
|
||||
return
|
||||
if conn.execute(
|
||||
"SELECT 1 FROM collections WHERE id = ? LIMIT 1", (DEFAULT_COLLECTION_ID,)
|
||||
).fetchone():
|
||||
# A 'default' collection already exists (e.g. a prior buggy mirror left a
|
||||
# duplicate). Don't auto-merge data — that needs care; leave both for
|
||||
# operator cleanup and log loudly.
|
||||
log.warning(
|
||||
"reconcile: default project %r owns both a %r and a 'default' "
|
||||
"collection; skipping auto-rename (manual merge required)",
|
||||
target, target,
|
||||
)
|
||||
return
|
||||
|
||||
cid_tables = [
|
||||
t["name"]
|
||||
for t in conn.execute("SELECT name FROM sqlite_master WHERE type='table'")
|
||||
if any(c["name"] == "collection_id"
|
||||
for c in conn.execute(f"PRAGMA table_info({t['name']})"))
|
||||
]
|
||||
conn.execute("PRAGMA foreign_keys = OFF")
|
||||
try:
|
||||
conn.execute("BEGIN")
|
||||
conn.execute(
|
||||
"UPDATE collections SET id = ? WHERE id = ?",
|
||||
(DEFAULT_COLLECTION_ID, target),
|
||||
)
|
||||
for t in cid_tables:
|
||||
conn.execute(
|
||||
f"UPDATE {t} SET collection_id = ? WHERE collection_id = ?",
|
||||
(DEFAULT_COLLECTION_ID, target),
|
||||
)
|
||||
violations = conn.execute("PRAGMA foreign_key_check").fetchall()
|
||||
if violations:
|
||||
conn.execute("ROLLBACK")
|
||||
raise RuntimeError(
|
||||
f"reconcile left foreign-key violations: {[tuple(v) for v in violations]}"
|
||||
)
|
||||
conn.execute("COMMIT")
|
||||
except Exception:
|
||||
try:
|
||||
conn.execute("ROLLBACK")
|
||||
except Exception:
|
||||
pass
|
||||
raise
|
||||
finally:
|
||||
conn.execute("PRAGMA foreign_keys = ON")
|
||||
log.info(
|
||||
"reconcile: renamed default-project collection %r -> 'default' across %d tables",
|
||||
target, len(cid_tables),
|
||||
)
|
||||
|
||||
|
||||
def default_content_repo(config: Config) -> str | None:
|
||||
"""The content repo the single-corpus mirror reads, from the default
|
||||
project's row (filled by the registry mirror). Replaces the retired
|
||||
|
||||
@@ -0,0 +1,156 @@
|
||||
"""§22 framework bug — migration-029 vs registry-mirror collection-id
|
||||
divergence for a multi-project deployment's default project.
|
||||
|
||||
Migration 029 seeds the default project's collection id as the literal
|
||||
'default' only when one project exists at migration time; with ≥2 projects it
|
||||
falls back to the *project id*. The registry mirror expects the default
|
||||
project to own the collection id 'default'. On an upgrade whose DB already
|
||||
held ≥2 projects when 029 ran, the default project's collection is therefore
|
||||
named after the project (e.g. 'ohm'), and the next mirror would INSERT a
|
||||
second, empty 'default' collection. `reconcile_default_collection_id` heals
|
||||
the divergence at startup, before the mirror, so the mirror merges instead of
|
||||
duplicating. This is the collection-grain twin of `restamp_default_project`.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import tempfile
|
||||
from pathlib import Path
|
||||
|
||||
import app.db as db
|
||||
from app import projects, registry
|
||||
|
||||
_TWO_PROJECT_REGISTRY = """
|
||||
deployment:
|
||||
name: Open Human Model
|
||||
tagline: t
|
||||
projects:
|
||||
- id: ohm
|
||||
name: Open Human Model
|
||||
type: document
|
||||
content_repo: ohm-content
|
||||
visibility: public
|
||||
- id: ecomm
|
||||
name: Ecomm
|
||||
type: bdd
|
||||
content_repo: ecomm-content
|
||||
visibility: public
|
||||
"""
|
||||
|
||||
|
||||
def _collection_ids_for(conn, project_id):
|
||||
return {r["id"] for r in conn.execute(
|
||||
"SELECT id FROM collections WHERE project_id = ?", (project_id,))}
|
||||
|
||||
|
||||
class _Cfg:
|
||||
def __init__(self, path, default_id):
|
||||
self.database_path = path
|
||||
self.default_project_id = default_id
|
||||
|
||||
|
||||
def _divergent_multiproject(monkeypatch, default_id="ohm"):
|
||||
"""A DB in the post-029 divergent state: the default project ('ohm') owns a
|
||||
collection whose id is the project id (the 029 ≥2-projects seed), a second
|
||||
project ('ecomm') owns its own collection, and NO 'default' collection
|
||||
exists. Entry rows point at the divergent collection_id='ohm'."""
|
||||
path = str(Path(tempfile.mkdtemp()) / "t.db")
|
||||
cfg = _Cfg(path, default_id)
|
||||
db.run_migrations(cfg) # seeds bootstrap 'default' project + 'default' collection
|
||||
monkeypatch.setattr(db, "_CONN", db.connect(path))
|
||||
conn = db.conn()
|
||||
# Drop the single-project bootstrap seed and rebuild the divergent
|
||||
# multi-project state 029 would have produced on an upgrade.
|
||||
conn.execute("DELETE FROM collections")
|
||||
conn.execute("DELETE FROM projects")
|
||||
conn.execute("INSERT INTO projects (id,name,content_repo,visibility) "
|
||||
"VALUES ('ohm','Open Human Model','ohm-content','public')")
|
||||
conn.execute("INSERT INTO projects (id,name,content_repo,visibility) "
|
||||
"VALUES ('ecomm','Ecomm','ecomm-content','public')")
|
||||
# 029 ≥2-projects seed: collection id == project id.
|
||||
conn.execute("INSERT INTO collections (id,project_id,type,subfolder,initial_state,visibility,name) "
|
||||
"VALUES ('ohm','ohm','document','','super-draft','public','Open Human Model')")
|
||||
conn.execute("INSERT INTO collections (id,project_id,type,subfolder,initial_state,visibility,name) "
|
||||
"VALUES ('ecomm','ecomm','bdd','ecomm','super-draft','public','Ecomm')")
|
||||
conn.execute("INSERT INTO users (id,gitea_login,display_name,role) VALUES (1,'a','A','contributor')")
|
||||
# Entry data for the default project lives in the divergent 'ohm' collection.
|
||||
conn.execute("INSERT INTO cached_rfcs (slug,title,state,collection_id) VALUES ('human','Human','active','ohm')")
|
||||
conn.execute("INSERT INTO rfc_collaborators (rfc_slug,user_id,role_in_rfc,collection_id) "
|
||||
"VALUES ('human',1,'contributor','ohm')")
|
||||
conn.execute("INSERT INTO stars (user_id,rfc_slug,collection_id) VALUES (1,'human','ohm')")
|
||||
# The 'ecomm' collection has its own entry.
|
||||
conn.execute("INSERT INTO cached_rfcs (slug,title,state,collection_id) VALUES ('cart','Cart','active','ecomm')")
|
||||
return cfg, conn
|
||||
|
||||
|
||||
def test_reconcile_renames_divergent_default_collection_to_default(monkeypatch):
|
||||
cfg, conn = _divergent_multiproject(monkeypatch, default_id="ohm")
|
||||
projects.reconcile_default_collection_id(cfg)
|
||||
# The default project's collection id is now the canonical 'default'.
|
||||
assert conn.execute("SELECT 1 FROM collections WHERE id='ohm'").fetchone() is None
|
||||
row = conn.execute("SELECT project_id FROM collections WHERE id='default'").fetchone()
|
||||
assert row is not None and row["project_id"] == "ohm"
|
||||
# Entry rows cascaded onto 'default'.
|
||||
assert conn.execute("SELECT collection_id FROM cached_rfcs WHERE slug='human'").fetchone()["collection_id"] == "default"
|
||||
assert conn.execute("SELECT collection_id FROM rfc_collaborators WHERE rfc_slug='human'").fetchone()["collection_id"] == "default"
|
||||
assert conn.execute("SELECT collection_id FROM stars WHERE rfc_slug='human'").fetchone()["collection_id"] == "default"
|
||||
# The non-default 'ecomm' collection is untouched (mirror + 029 agree on it).
|
||||
assert conn.execute("SELECT 1 FROM collections WHERE id='ecomm'").fetchone() is not None
|
||||
assert conn.execute("SELECT collection_id FROM cached_rfcs WHERE slug='cart'").fetchone()["collection_id"] == "ecomm"
|
||||
# FK integrity intact after the rename.
|
||||
assert conn.execute("PRAGMA foreign_key_check").fetchall() == []
|
||||
|
||||
|
||||
def test_reconcile_is_idempotent(monkeypatch):
|
||||
cfg, conn = _divergent_multiproject(monkeypatch, default_id="ohm")
|
||||
projects.reconcile_default_collection_id(cfg)
|
||||
projects.reconcile_default_collection_id(cfg) # second call: already aligned → no-op
|
||||
assert conn.execute("SELECT project_id FROM collections WHERE id='default'").fetchone()["project_id"] == "ohm"
|
||||
assert conn.execute("SELECT COUNT(*) c FROM cached_rfcs WHERE collection_id='default'").fetchone()["c"] == 1
|
||||
|
||||
|
||||
def test_reconcile_noop_when_default_id_is_literal_default(monkeypatch):
|
||||
# Single-project deployment, no DEFAULT_PROJECT_ID: 029 already seeded
|
||||
# 'default' and the mirror agrees — nothing to reconcile.
|
||||
path = str(Path(tempfile.mkdtemp()) / "t.db")
|
||||
cfg = _Cfg(path, "") # resolves to 'default'
|
||||
db.run_migrations(cfg)
|
||||
monkeypatch.setattr(db, "_CONN", db.connect(path))
|
||||
conn = db.conn()
|
||||
projects.reconcile_default_collection_id(cfg)
|
||||
assert conn.execute("SELECT 1 FROM collections WHERE id='default'").fetchone() is not None
|
||||
|
||||
|
||||
def test_mirror_duplicates_without_reconcile(monkeypatch):
|
||||
# Demonstrates the bug: the mirror on the divergent state inserts a SECOND
|
||||
# 'default' collection for the default project (alongside the 029 'ohm').
|
||||
cfg, conn = _divergent_multiproject(monkeypatch, default_id="ohm")
|
||||
doc = registry.parse_registry(_TWO_PROJECT_REGISTRY)
|
||||
registry.apply_registry(doc, registry_sha="s1", default_id="ohm")
|
||||
assert _collection_ids_for(conn, "ohm") == {"ohm", "default"} # duplicate!
|
||||
|
||||
|
||||
def test_reconcile_then_mirror_merges_no_duplicate(monkeypatch):
|
||||
# With the fix: reconcile before the mirror → the mirror merges onto the
|
||||
# canonical 'default' collection; the default project owns exactly one.
|
||||
cfg, conn = _divergent_multiproject(monkeypatch, default_id="ohm")
|
||||
projects.reconcile_default_collection_id(cfg)
|
||||
doc = registry.parse_registry(_TWO_PROJECT_REGISTRY)
|
||||
registry.apply_registry(doc, registry_sha="s1", default_id="ohm")
|
||||
assert _collection_ids_for(conn, "ohm") == {"default"}
|
||||
assert _collection_ids_for(conn, "ecomm") == {"ecomm"}
|
||||
# The default project's corpus entry is intact under 'default'.
|
||||
assert conn.execute("SELECT collection_id FROM cached_rfcs WHERE slug='human'").fetchone()["collection_id"] == "default"
|
||||
# The mirror refreshed the merged collection's metadata (type from registry).
|
||||
assert conn.execute("SELECT type FROM collections WHERE id='default'").fetchone()["type"] == "document"
|
||||
|
||||
|
||||
def test_reconcile_skips_when_default_collection_already_exists(monkeypatch):
|
||||
# A prior buggy mirror already created a 'default' collection alongside the
|
||||
# divergent 'ohm' one: don't auto-merge data — leave both for operator cleanup.
|
||||
cfg, conn = _divergent_multiproject(monkeypatch, default_id="ohm")
|
||||
conn.execute("INSERT INTO collections (id,project_id,type,subfolder,initial_state,visibility,name) "
|
||||
"VALUES ('default','ohm','document','','super-draft','public','dup')")
|
||||
projects.reconcile_default_collection_id(cfg)
|
||||
# Both still present (no destructive auto-merge).
|
||||
assert conn.execute("SELECT 1 FROM collections WHERE id='ohm'").fetchone() is not None
|
||||
assert conn.execute("SELECT 1 FROM collections WHERE id='default'").fetchone() is not None
|
||||
Reference in New Issue
Block a user