317 Commits

• Merge pull request #5221 from PriNova/fix/openrouter-system-role

  Fix OpenRouter reasoning instruction role

  Mario Zechner · 2026-06-01 00:09:58 +02:00
  b177333026
• fix(ai): suppress deprecated temperature param for Claude Opus 4.7+
  Michael Yu · 2026-05-31 16:20:22 +08:00
  40832d1957
• Fix OpenAI completions developer role test
  PriNova · 2026-05-30 12:24:19 +02:00
  74d81bd363
• Fix OpenRouter reasoning instruction role
  PriNova · 2026-05-30 11:15:30 +02:00
  b55fe1bbd4
• fix(ai): abort Codex SSE body reads
  Mario Zechner · 2026-05-29 23:20:18 +02:00
  a36a132c70
• Merge pull request #5196 from earendil-works/fix/opencode-thinking-requests

  fix(ai): handle OpenCode reasoning params

  Mario Zechner · 2026-05-29 22:32:13 +02:00
  01a8c2d62c
• fix(ai): handle OpenCode reasoning params
  Armin Ronacher · 2026-05-29 12:21:37 +02:00
  4faac05419
• ai: add custom-header support to Bedrock provider

  Honour StreamOptions.headers in the Bedrock provider by attaching a
  Smithy build-step middleware that merges caller headers into the
  request before SigV4 signing. Reserved headers (x-amz-*, authorization,
  host) are silently skipped to preserve signing and the bearer-token
  auth path. No-op when no headers are supplied. Updates the
  StreamOptions.headers JSDoc to drop the Bedrock caveat.

  Stephan Schneider · 2026-05-29 10:21:44 +02:00
  7619aaefa9
• fix(ai): use valid synthetic Responses message ids closes #5148
  Mario Zechner · 2026-05-28 23:13:15 +02:00
  d1fb34bc8d
• fix(ai): avoid duplicate Codex replay message ids closes #5148
  Mario Zechner · 2026-05-28 23:11:05 +02:00
  3f1ce9b6e9
• Fix Kimi and Xiaomi model metadata

  Closes #5075, closes #5078. Refs #5087.

  Mario Zechner · 2026-05-28 22:19:47 +02:00
  97ef317389
• Update Claude Opus and GPT thinking metadata
  Mario Zechner · 2026-05-28 21:51:55 +02:00
  bfa3d1fa60
• Fix Anthropic empty thinking signature replay

  closes #4464

  Mario Zechner · 2026-05-28 12:04:33 +02:00
  458a7bc27c
• feat(ai): add Codex device code login (#4911)
  Vegard Stikbakke · 2026-05-28 11:09:33 +02:00
  9d5fb70b7e
• fix(ai): timeout Codex SSE header stalls
  Armin Ronacher · 2026-05-27 21:24:51 +02:00
  7c02a55632
• fix(ai): avoid stale Cerebras test model
  Armin Ronacher · 2026-05-27 20:57:00 +02:00
  91b46c2ba9
• fix(codex): timeouts for websockets (#4979)
  Armin Ronacher · 2026-05-27 12:11:29 +02:00
  493efd422d
• fix(ai): use hyphenated Codex session header

  closes #4967

  Armin Ronacher · 2026-05-27 01:11:40 +02:00
  26f1e00f71
• fix(ai): disable hidden provider 429 retries (#4991)
  Armin Ronacher · 2026-05-26 23:41:58 +02:00
  8fb1e877cd
• fix(ai): detect Poolside context overflow

  Closes #4943

  Armin Ronacher · 2026-05-26 08:58:21 +02:00
  fa1180b6b7
• test(ai): avoid hardcoded Fireworks router id
  Armin Ronacher · 2026-05-22 22:59:10 +02:00
  d80bcc367e
• Fix Anthropic eager tool input compat test
  Mario Zechner · 2026-05-22 18:40:31 +02:00
  9b62f1f87c
• Support adaptive thinking for Anthropic-compatible aliases

  closes #4790

  Mario Zechner · 2026-05-22 18:30:51 +02:00
  d801d88a11
• feat(ai): refactor device code login for copilot
  Vegard Stikbakke · 2026-05-22 08:54:18 +02:00
  c554364c2a
• fix(ai): set bedrock claude default max tokens

  closes #4848

  Mario Zechner · 2026-05-21 23:27:40 +02:00
  11c3da4f74
• chore: pin dependencies and use native TypeScript
  Mario Zechner · 2026-05-20 12:46:17 +02:00
  2e02c74dcb
• test: speed up provider payload coverage
  Mario Zechner · 2026-05-20 12:37:58 +02:00
  f1f7cd50c3
• fix(ai): stop defaulting max token request caps

  closes #4675

  Mario Zechner · 2026-05-19 11:49:44 +02:00
  2787b601d7
• fix(ai): clamp OpenAI prompt cache keys

  closes #4720

  Mario Zechner · 2026-05-19 10:51:11 +02:00
  7be75baded
• fix(ai): add Xiaomi reasoning replay compat

  closes #4678

  Mario Zechner · 2026-05-18 11:15:20 +02:00
  b8f51957a0
• fix(ai): skip unknown bedrock content blocks

  closes #4223

  Mario Zechner · 2026-05-18 01:42:18 +02:00
  9e2bfc7c40
• fix(ai): normalize opencode go reasoning replay

  closes #4251

  Mario Zechner · 2026-05-18 01:11:23 +02:00
  21d80deda2
• Closes #4342
  Mario Zechner · 2026-05-17 23:55:25 +02:00
  b256ac7d77
• fix(ai): update OpenAI Codex model list
  Mattia Cerutti · 2026-05-17 03:12:19 +02:00
  1af823be9d
• fix(ai): detect litellm context overflow errors

  closes #4563

  Mario Zechner · 2026-05-16 23:29:22 +02:00
  7c5c3d6fd6
• Merge pull request #4558 from earendil-works/fix/openai-completions-throw-on-missing-finish_reason

  fix(ai): openai-completions - throw error on missing finish-reason

  Mario Zechner · 2026-05-16 22:54:42 +02:00
  0412f62f9e
• fix(ai): preserve OpenRouter cached token semantics
  Armin Ronacher · 2026-05-16 11:55:16 +02:00
  87881ca686
• fix(ai): openai-completions - throw error on missing finish-reason

  - require \ before treating \ streams as successful
  - add regression coverage for truncated streams without \
  - closes #4345

  Ramiz Wachtler · 2026-05-15 15:26:57 +02:00
  98ffad0437
• fix(ai): ignore generic GitHub tokens for Copilot auth

  closes #4485

  Mario Zechner · 2026-05-15 01:26:31 +02:00
  a8af0b5e99
• fix(ai): honor retry-after for OpenAI Codex SSE retries

  - honor `retry-after-ms` and `retry-after` for OpenAI Codex SSE retries
  - add SSE retry coverage for millisecond, seconds, date, and fallback delays

  Ramiz Wachtler · 2026-05-13 19:44:07 +02:00
  0ae909316a
• refactor(ai): use HTTP proxy agents for Bedrock
  Mario Zechner · 2026-05-13 16:12:48 +02:00
  a5cca409d8
• Merge pull request #4358 from yanirz/fix/fireworks-session-affinity-cache

  fix(ai): add session affinity and compat fixes for Fireworks provider caching

  Mario Zechner · 2026-05-10 18:00:52 +02:00
  cb3c42ecf5
• fix(ai): align copilot claude adaptive test
  Mario Zechner · 2026-05-10 17:51:08 +02:00
  533d37305c
• fix(ai): update copilot claude test model
  Mario Zechner · 2026-05-10 17:47:45 +02:00
  cf7f2e3dbb
• fix(ai): add session affinity and compat fixes for Fireworks provider caching

  Fireworks prompt caching is enabled by default (automatic prefix matching),
  but on serverless infrastructure, requests hit random replicas. Without
  session affinity, the per-replica cache misses, negating cache hit rates
  and the discounted cacheRead pricing.
  
  Changes:
  
  - Add sendSessionAffinityHeaders and supportsCacheControlOnTools
    to AnthropicMessagesCompat interface
  - Send x-session-affinity header for Fireworks (and Cloudflare AI
    Gateway Anthropic) when sessionId is available and caching is enabled
  - Omit cache_control on tool definitions for Fireworks (unsupported
    per https://docs.fireworks.ai/tools-sdks/anthropic-compatibility)
  - Default supportsEagerToolInputStreaming to false for Fireworks
    (unsupported field)
  - Default supportsLongCacheRetention to false for Fireworks
    (cache_control.ttl not supported)
  - Add compat settings to Fireworks models in generate-models.ts
  - Update generated models with Fireworks compat settings
  - Add integration tests for session affinity and tool compat
  
  Refs: https://docs.fireworks.ai/guides/prompt-caching
  Refs: https://docs.fireworks.ai/tools-sdks/anthropic-compatibility

  yanirz · 2026-05-10 00:11:36 +02:00
  99dc6fcec8
• feat(ai): add Together AI provider
  Mario Zechner · 2026-05-08 16:44:18 +02:00
  7adb8e7634
• Merge pull request #3887 from cristinaponcela/feat/image-outputs

  feat: image content

  Mario Zechner · 2026-05-08 15:57:06 +02:00
  9751057be9
• fix(ai): disable OpenAI reasoning where supported
  Mario Zechner · 2026-05-07 22:52:54 +02:00
  783e96a144
• Merge remote-tracking branch 'upstream/main' into feat/image-outputs
  Cristina Poncela Cubeiro · 2026-05-07 16:46:17 +02:00
  ffdf426e33
• delete: images()
  Cristina Poncela Cubeiro · 2026-05-07 16:21:50 +02:00
  32b2cd0720