619 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: 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
• 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
• 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
• 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
• 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
• fix(ai): update copilot claude test model
  Mario Zechner · 2026-05-10 17:47:45 +02:00
  cf7f2e3dbb
• feat(ai): add Together AI provider
  Mario Zechner · 2026-05-08 16:44:18 +02:00
  7adb8e7634
• fix(ai): disable OpenAI reasoning where supported
  Mario Zechner · 2026-05-07 22:52:54 +02:00
  783e96a144
• Add [Unreleased] section for next cycle
  Mario Zechner · 2026-05-07 18:02:17 +02:00
  b38bd49be1
• Release v0.74.0
  Mario Zechner · 2026-05-07 17:15:00 +02:00
  1eee081e29
• Add [Unreleased] section for next cycle
  Mario Zechner · 2026-05-07 16:45:27 +02:00
  147f815802
• Release v0.73.1
  Mario Zechner · 2026-05-07 16:44:28 +02:00
  781152fc24
• docs: audit unreleased changelog entries
  Mario Zechner · 2026-05-07 16:43:26 +02:00
  7fa924b77b
• fix(ai): handle OpenAI Responses reasoning text deltas
  Mario Zechner · 2026-05-06 00:08:26 +02:00
  31f5c23271
• Add [Unreleased] section for next cycle
  Armin Ronacher · 2026-05-04 20:33:08 +02:00
  3c9c54d51b
• Release v0.73.0
  Armin Ronacher · 2026-05-04 20:32:03 +02:00
  dbcb473d6f
• docs(changelog): audit unreleased entries
  Armin Ronacher · 2026-05-04 20:27:27 +02:00
  299dc70abe
• feat(ai): switch xiaomi default to api billing, add per-region token plan providers (#4112)

  Built-in `xiaomi` provider now targets the API billing endpoint (https://api.xiaomimimo.com/anthropic) — a single stable URL for keys issued at platform.xiaomimimo.com. The Token Plan endpoints are exposed as three sibling providers, each with its own env var:
  
  - xiaomi-token-plan-cn: XIAOMI_TOKEN_PLAN_CN_API_KEY
  - xiaomi-token-plan-ams: XIAOMI_TOKEN_PLAN_AMS_API_KEY
  - xiaomi-token-plan-sgp: XIAOMI_TOKEN_PLAN_SGP_API_KEY
  
  BREAKING CHANGE: users who previously set XIAOMI_API_KEY against the Token Plan AMS endpoint must move to xiaomi-token-plan-ams and set XIAOMI_TOKEN_PLAN_AMS_API_KEY. This also resolves the 401 reported by on #4005, where a platform.xiaomimimo.com key fails against the Token Plan endpoint.
  
  closes #4082

  Jake Jia · 2026-05-03 12:57:11 +02:00
  693888ac47
• Add [Unreleased] section for next cycle
  Mario Zechner · 2026-05-02 14:58:41 +02:00
  7268e9a9fd
• Release v0.72.1
  Mario Zechner · 2026-05-02 14:57:51 +02:00
  036bde0a5d
• fix(ai): honor codex transport option

  closes #4083

  Mario Zechner · 2026-05-02 14:14:22 +02:00
  b8bb2411ff