Commit Graph
5 Commits
Author SHA1 Message Date
Ilker ManapandClaude Opus 5.5 f0477f140d Quality suites, and new weights held to one: ctl eval, model update/promote --eval, model gate
A suite is a set of cases in YAML or JSON lines, each scored by exact,
contains, regex, a number within a tolerance, a JSON Schema subset, or a
judge model with a rubric; weighed into one score against a threshold.
internal/bench/eval runs one on the control plane through Router.Replay, as
the gateway's own requests, and keeps every run and its cases in the store
(migration 0028: eval_runs, eval_cases).

- llmgw ctl eval MODEL --suite FILE|NAME, --history, --run, --suites; exits
  non-zero below the score. Suites by name from control.eval_dir, or the
  two built in from deploy/eval (arithmetic, json-format).
- model update and promote take --eval SUITE --min-score N, or a model's
  standing gate (ctl model gate, eval: in the catalog): a promote asks the
  canary first and leaves it below the score; an update tries the new
  weights as a canary given no share, then promotes or removes it.
- The console's model menu: ask a suite with its progress, its runs, its
  gate.
- The audit middleware no longer hands a handler a body cut off at 64 KiB.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-05 00:04:43 +02:00
Ilker ManapandClaude Opus 5.5 a1dfd4df1d Canary of a model's newer weights: ctl model canary, promote and canaries, rolled back by itself when it serves worse
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 20:31:26 +02:00
Ilker ManapandClaude Opus 5.5 1b71c38f89 Notifications: webhooks for a parked model, a lost node, a spent budget and new weights; Alertmanager receiver templates
notify.webhooks sends signed JSON or Slack-compatible messages, queued,
retried, de-duplicated hourly; ctl notify test checks each webhook.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 16:58:11 +02:00
Ilker ManapandClaude Opus 5.5 f36c46a881 Trace weights fetched before origins were kept, and let an origin be given by hand
The mirror keeps where it fetched a file beside it, and reports that and the
checksum after it restarts. A model whose files the mirror cannot trace is
found on the registry: a repository holding a file of that name that has the
commit the mirror's directory is named after, with every file at the same
size, the most downloaded first. ctl model origin and the console set one by
hand, checked the same way. Commits compare shortened.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 00:24:41 +02:00
Ilker ManapandClaude Opus 5.5 44425193bd Track the registry's new weights for served models, and move a model to them or back
A model served from the registry records its origin: repository, commit and
each file's checksum; one served before is worked out from the mirror's
record of where it fetched the file. Every mirror.update_check (6h) the
control plane asks whether those files changed there. ctl model updates
lists it, ctl model update fetches beside the old files, checks, swaps and
replaces replicas one at a time, ctl model rollback goes back. The console
shows it on Models and offers the same.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-04 00:12:20 +02:00