gbrain

mirror of https://github.com/garrytan/gbrain.git synced 2026-07-29 19:01:39 +00:00

Files

T

MasaandGitHub d9ac24744c fix(pricing): register claude-opus-5 in the Anthropic recipe allowlist and canonical pricing table (#3398 )

Anthropic released Claude Opus 5, at the same $5/$25 pricing tier as
Opus 4.8. Neither the chat recipe allowlist nor CANONICAL_PRICING knew
about it, so operators could not opt into it via models.tier.deep /
models.default without gbrain rejecting the id.

- src/core/ai/recipes/anthropic.ts: add claude-opus-5 to the models list.
- src/core/model-pricing.ts: add anthropic:claude-opus-5 { input: 5.00,
  output: 25.00 } (plus cache rates, matching Opus 4.8's ratios).
- src/core/takes-quality-eval/pricing.ts: add it to SUPPORTED_MODELS so
  eval takes-quality run --budget-usd doesn't reject it during preflight.
- Refreshed the stale pricing-verification date and the Opus list in
  docs/architecture/KEY_FILES.md.
- Tests: pinned-value regression in test/model-pricing.test.ts, recipe
  membership in test/anthropic-model-ids.test.ts, budget-pricing coverage
  in test/eval-takes-quality-pricing.test.ts.

Scope: registration only. TIER_DEFAULTS / DEFAULT_ALIASES /
DEFAULT_CHAT_MODEL are untouched — default-routing bumps are the
separate, already-open #2858; this just makes the id valid/priced for
operators who opt in explicitly.

2026-07-27 13:28:37 -07:00

brains-and-sources.md

v0.26.0 feat: GBrain — MCP Keys OAuth 2.1 + HTTP server + admin dashboard (#358 )

2026-05-02 22:01:05 -07:00

calibration-quality-gate-spec.md

v0.37.2.0: takes_resolution_consistency CHECK accepts 'unresolvable' (#1211 )

2026-05-20 09:19:18 -07:00

conversation-parser-patterns.md

feat(conversation-parser): parse normalized Slack markdown (takeover of #3289 ) (#3372 )

2026-07-24 11:35:54 -07:00

frontmatter-scan-incremental.md

v0.38.2.0 fix(doctor): bounded frontmatter scan + partial-state surfacing (supersedes #1287 ) (#1297 )