bvandeusenandClaude Opus 5
51e78a329b
CI / lint (push) Failing after 3s
CI / extension-version (push) Successful in 3s
Build images / sign-extension (push) Successful in 4s
Build images / build-agent (push) Successful in 8s
CI / frontend-build (push) Successful in 23s
CI / backend-lint-and-test (push) Successful in 31s
Build images / build-ml (push) Successful in 2m23s
Build images / build-web (push) Successful in 1m25s
Build images / smoke-web (push) Skipped
Build images / promote (push) Skipped
CI / integration (push) Failing after 2m31s
**The verification the step asked for came back "not the schema".**
`Source.artist_id` is a plain FK so many sources per artist already works;
`POST /api/sources` already takes an `artist_id`; the add-source dialog already
has an artist autocomplete that attaches to an EXISTING artist; and
`SourceService.reassign` already moves a source between artists WITH post and
image re-attribution. A sweep for one-source-per-artist assumptions found only
`func.count()` calls — the opposite of assuming one.
So no parallel association table was built for a relationship the schema
already expresses (rule 28). What was missing is FC OFFERING the link, and that
is all this adds.
**Accepting adds a SOURCE. It never merges two artists.** That asymmetry sets
the whole posture: adding a source is trivially undone, while a wrong merge
silently mixes two creators' work and corrupts tagging, series and provenance
downstream with nothing left to tell them apart by. A test asserts the artist
count is unchanged by accepting.
The weights encode the judgement rather than a code path doing it — name 0.65,
declared 0.35, cut at 0.60 — so that:
* an EXACT name match alone proposes (same slug on both sides is strong, and
demanding corroboration would propose almost nothing);
* a CONTAINMENT match alone does not ("art" sits inside "artgirl"), and short
slugs are excluded from containment entirely because a 3-character slug is
inside a great many longer ones;
* the declaration ALONE never proposes, because a creator may link another
creator's Patreon and a link is not a claim of identity.
A guard test pins all three against WEIGHTS directly and says not to fix a
failure by moving the numbers.
Two corrections carried forward from earlier steps rather than rediscovered:
* The declaration is NOT read from `ExternalLink`. `SUPPORTED_HOSTS` is file
hosts only and `host_for()` returns None for patreon.com, so no row is ever
written for one — the same trap that caught E5 for Discord invites. It reads
the raw body, because these links live in an `href` and `html_to_plain`
discards attributes.
* `vanity` is not a column: C1 modelled the roster before any platform was
characterised, which is exactly what `details` exists for. `vanity_or_none()`
reads it from there and falls back to the URL's last segment, so a row
written before the field was understood still resolves.
Two fixes during the writing. `accept()` first created a bare `Source()`,
skipping the platform/URL validation, duplicate check and #693 backfill-arming
that a hand-added source gets — a second, quieter way to create a source is how
two paths drift until one is subtly broken; it now goes through
`SourceService.create`. And the candidate query used a bare `exists().where()`,
which has no FROM to correlate against; now `select(...).exists()`.
Chained onto the roster sweep rather than given its own beat entry: a
suggestion can only be as good as the roster behind it, so any other cadence
would just propose from staler data.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LNXXULQDjVZmbuNa2G9mD9