1329 Commits

• feat(ai): add Codex device code login
  Vegard Stikbakke · 2026-05-20 15:31:54 +02:00
  1ffeb828d3
• feat(ai): add device code login callback and use for copilot
  Vegard Stikbakke · 2026-05-20 12:28:12 +02:00
  bf5ac0011e
• chore: remove web-ui workspace
  Mario Zechner · 2026-05-20 02:26:09 +02:00
  b141e1fa24
• chore(ts): use source import extensions
  Armin Ronacher · 2026-05-20 00:04:03 +02:00
  ae9450dc51
• chore: enforce erasable TypeScript syntax
  Mario Zechner · 2026-05-19 23:15:39 +02:00
  06c6c324d7
• 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
• Add [Unreleased] section for next cycle
  Mario Zechner · 2026-05-18 11:59:24 +02:00
  4943c1d62c
• Release v0.75.3
  Mario Zechner · 2026-05-18 11:58:34 +02:00
  a7d8dd3d5d
• Add [Unreleased] section for next cycle
  Mario Zechner · 2026-05-18 11:47:16 +02:00
  0c4d704a7b
• Release v0.75.2
  Mario Zechner · 2026-05-18 11:46:23 +02:00
  ea713ba174
• fix(ai): add Xiaomi reasoning replay compat

  closes #4678

  Mario Zechner · 2026-05-18 11:15:20 +02:00
  b8f51957a0
• Add [Unreleased] section for next cycle
  Mario Zechner · 2026-05-18 02:01:57 +02:00
  93b2e7fae7
• Release v0.75.1
  Mario Zechner · 2026-05-18 02:01:03 +02:00
  73a61654af
• chore: audit unreleased changelogs
  Mario Zechner · 2026-05-18 02:00:07 +02:00
  f1218fa8aa
• fix(ai): skip unknown bedrock content blocks

  closes #4223

  Mario Zechner · 2026-05-18 01:42:18 +02:00
  9e2bfc7c40
• fix(ai): prefix HTTP status codes onto Azure OpenAI and OpenAI Responses error messages so auto-retry fires on 5xx/429

  closes #4232

  Mario Zechner · 2026-05-18 01:11:23 +02:00
  52e13870a1
• fix(ai): normalize opencode go reasoning replay

  closes #4251

  Mario Zechner · 2026-05-18 01:11:23 +02:00
  21d80deda2
• fix(ai): switch xiaomi models to openai completions

  closes #4505

  Mario Zechner · 2026-05-18 00:14:31 +02:00
  ed3904ddd3
• Remove openai-codex fast model variants, they do not work
  Mario Zechner · 2026-05-18 00:02:52 +02:00
  266234047a
• Closes #4342
  Mario Zechner · 2026-05-17 23:55:25 +02:00
  b256ac7d77
• Add [Unreleased] section for next cycle
  Mario Zechner · 2026-05-17 21:03:41 +02:00
  7f3c340dc6
• Release v0.75.0
  Mario Zechner · 2026-05-17 21:02:49 +02:00
  12f5c00cc1
• chore: audit unreleased changelog entries
  Mario Zechner · 2026-05-17 21:01:03 +02:00
  d5ebc973d0
• Merge pull request #4603 from mattiacerutti/fix/openai-codex-model-list

  fix(ai): update OpenAI Codex model list

  Mario Zechner · 2026-05-17 20:54:53 +02:00
  a01cf7afae
• Merge pull request #4622 from mattiacerutti/fix/copilot-gpt-thinking-map-fix

  fix(ai): map copilot gpt 5 minimal thinking to low

  Mario Zechner · 2026-05-17 20:53:42 +02:00
  6730c04a65
• fix(coding-agent): remove global fetch override closes #4619
  Mario Zechner · 2026-05-17 20:52:06 +02:00
  c9e7049212
• fix(ai): cap context-sized default output budgets

  closes #4614

  Mario Zechner · 2026-05-17 20:06:59 +02:00
  6d474f8c1a
• fix(ai): map copilot gpt minimal thinking to low
  Mattia Cerutti · 2026-05-17 12:18:50 +02:00
  485afc9c3f
• fix(ai): update OpenAI Codex model list
  Mattia Cerutti · 2026-05-17 03:12:19 +02:00
  1af823be9d
• Release v0.74.1
  Mario Zechner · 2026-05-17 01:35:45 +02:00
  2c708492e3
• docs: audit unreleased changelogs
  Mario Zechner · 2026-05-17 01:29:35 +02:00
  72104d88f9
• fix(ai): vendor proxy env resolution

  closes #4513

  Mario Zechner · 2026-05-17 00:02:37 +02:00
  c5831df689
• fix(ai): respect model output token limits

  closes #4539

  Mario Zechner · 2026-05-16 23:33:06 +02:00
  22a9c484e7
• 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
• Merge pull request #4473 from apoorvumang/fix/inception-mercury-2-reasoning-off

  fix(ai): mark inception/mercury-2 thinkingLevelMap.off as null

  Mario Zechner · 2026-05-13 18:48:49 +02:00
  40c05f5539
• refactor(ai): use HTTP proxy agents for Bedrock
  Mario Zechner · 2026-05-13 16:12:48 +02:00
  a5cca409d8
• fix(ai): mark inception/mercury-2 thinkingLevelMap.off as null

  Mercury 2 in instant mode (reasoning_effort: "none") disables tool calling.
  The openai-completions provider hardcodes {reasoning:{effort:"none"}} when no
  explicit reasoning level is passed and thinkingLevelMap.off isn't null
  (openai-completions.ts:575), so every caller that doesn't opt in to a level
  silently breaks Mercury 2's agentic use cases.
  
  Setting thinkingLevelMap.off = null on the Mercury 2 catalog entry causes the
  provider to omit the reasoning param entirely, letting Mercury 2's own default
  take over. Low/medium/high pass through verbatim; OpenRouter normalizes them
  to Mercury's vocabulary.
  
  Prefix-matched on "inception/mercury-2" so future Mercury 2 variants on
  OpenRouter inherit the fix.

  Apoorv Saxena · 2026-05-13 19:17:36 +05:30
  e2b69a0bb1
• chore(deps): remove unused dependencies (#4453)
  Armin Ronacher · 2026-05-12 23:35:41 +02:00
  64882c6a51
• Merge pull request #4354 from haoqixu/fix-bun-ws-proxy

  fix(ai): respect proxy envs in bun's websocket

  Mario Zechner · 2026-05-10 18:03:48 +02:00
  f6b6b1f052
• 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
• fix(ai): respect proxy envs in bun's websocket

  fixes #4346

  haoqixu · 2026-05-10 03:43:07 +08:00
  8c2e3eddec