1329 commits

Author	SHA1	Message	Date
Vegard Stikbakke	1ffeb828d3	feat(ai): add Codex device code login	2026-05-20 15:31:54 +02:00
Vegard Stikbakke	bf5ac0011e	feat(ai): add device code login callback and use for copilot	2026-05-20 12:28:12 +02:00
Mario Zechner	b141e1fa24	chore: remove web-ui workspace	2026-05-20 02:26:09 +02:00
Armin Ronacher	ae9450dc51	chore(ts): use source import extensions	2026-05-20 00:04:03 +02:00
Mario Zechner	06c6c324d7	chore: enforce erasable TypeScript syntax	2026-05-19 23:15:39 +02:00
Mario Zechner	2787b601d7	fix(ai): stop defaulting max token request caps ... closes #4675	2026-05-19 11:49:44 +02:00
Mario Zechner	7be75baded	fix(ai): clamp OpenAI prompt cache keys ... closes #4720	2026-05-19 10:51:11 +02:00
Mario Zechner	4943c1d62c	Add [Unreleased] section for next cycle	2026-05-18 11:59:24 +02:00
Mario Zechner	a7d8dd3d5d	Release v0.75.3	2026-05-18 11:58:34 +02:00
Mario Zechner	0c4d704a7b	Add [Unreleased] section for next cycle	2026-05-18 11:47:16 +02:00
Mario Zechner	ea713ba174	Release v0.75.2	2026-05-18 11:46:23 +02:00
Mario Zechner	b8f51957a0	fix(ai): add Xiaomi reasoning replay compat ... closes #4678	2026-05-18 11:15:20 +02:00
Mario Zechner	93b2e7fae7	Add [Unreleased] section for next cycle	2026-05-18 02:01:57 +02:00
Mario Zechner	73a61654af	Release v0.75.1	2026-05-18 02:01:03 +02:00
Mario Zechner	f1218fa8aa	chore: audit unreleased changelogs	2026-05-18 02:00:07 +02:00
Mario Zechner	9e2bfc7c40	fix(ai): skip unknown bedrock content blocks ... closes #4223	2026-05-18 01:42:18 +02:00
Mario Zechner	52e13870a1	fix(ai): prefix HTTP status codes onto Azure OpenAI and OpenAI Responses error messages so auto-retry fires on 5xx/429 ... closes #4232	2026-05-18 01:11:23 +02:00
Mario Zechner	21d80deda2	fix(ai): normalize opencode go reasoning replay ... closes #4251	2026-05-18 01:11:23 +02:00
Mario Zechner	ed3904ddd3	fix(ai): switch xiaomi models to openai completions ... closes #4505	2026-05-18 00:14:31 +02:00
Mario Zechner	266234047a	Remove openai-codex fast model variants, they do not work	2026-05-18 00:02:52 +02:00
Mario Zechner	b256ac7d77	Closes #4342	2026-05-17 23:55:25 +02:00
Mario Zechner	7f3c340dc6	Add [Unreleased] section for next cycle	2026-05-17 21:03:41 +02:00
Mario Zechner	12f5c00cc1	Release v0.75.0	2026-05-17 21:02:49 +02:00
Mario Zechner	d5ebc973d0	chore: audit unreleased changelog entries	2026-05-17 21:01:03 +02:00
Mario Zechner	a01cf7afae	Merge pull request #4603 from mattiacerutti/fix/openai-codex-model-list ... fix(ai): update OpenAI Codex model list	2026-05-17 20:54:53 +02:00
Mario Zechner	6730c04a65	Merge pull request #4622 from mattiacerutti/fix/copilot-gpt-thinking-map-fix ... fix(ai): map copilot gpt 5 minimal thinking to low	2026-05-17 20:53:42 +02:00
Mario Zechner	c9e7049212	fix(coding-agent): remove global fetch override closes #4619	2026-05-17 20:52:06 +02:00
Mario Zechner	6d474f8c1a	fix(ai): cap context-sized default output budgets ... closes #4614	2026-05-17 20:06:59 +02:00
Mattia Cerutti	485afc9c3f	fix(ai): map copilot gpt minimal thinking to low	2026-05-17 12:18:50 +02:00
Mattia Cerutti	1af823be9d	fix(ai): update OpenAI Codex model list	2026-05-17 03:12:19 +02:00
Mario Zechner	2c708492e3	Release v0.74.1	2026-05-17 01:35:45 +02:00
Mario Zechner	72104d88f9	docs: audit unreleased changelogs	2026-05-17 01:29:35 +02:00
Mario Zechner	c5831df689	fix(ai): vendor proxy env resolution ... closes #4513	2026-05-17 00:02:37 +02:00
Mario Zechner	22a9c484e7	fix(ai): respect model output token limits ... closes #4539	2026-05-16 23:33:06 +02:00
Mario Zechner	7c5c3d6fd6	fix(ai): detect litellm context overflow errors ... closes #4563	2026-05-16 23:29:22 +02:00
Mario Zechner	0412f62f9e	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	2026-05-16 22:54:42 +02:00
Armin Ronacher	87881ca686	fix(ai): preserve OpenRouter cached token semantics	2026-05-16 11:55:16 +02:00
Ramiz Wachtler	98ffad0437	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	2026-05-15 15:26:57 +02:00
Mario Zechner	a8af0b5e99	fix(ai): ignore generic GitHub tokens for Copilot auth ... closes #4485	2026-05-15 01:26:31 +02:00
Ramiz Wachtler	0ae909316a	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	2026-05-13 19:44:07 +02:00
Mario Zechner	40c05f5539	Merge pull request #4473 from apoorvumang/fix/inception-mercury-2-reasoning-off ... fix(ai): mark inception/mercury-2 thinkingLevelMap.off as null	2026-05-13 18:48:49 +02:00
Mario Zechner	a5cca409d8	refactor(ai): use HTTP proxy agents for Bedrock	2026-05-13 16:12:48 +02:00
Apoorv Saxena	e2b69a0bb1	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.	2026-05-13 19:17:36 +05:30
Armin Ronacher	64882c6a51	chore(deps): remove unused dependencies (#4453)	2026-05-12 23:35:41 +02:00
Mario Zechner	f6b6b1f052	Merge pull request #4354 from haoqixu/fix-bun-ws-proxy ... fix(ai): respect proxy envs in bun's websocket	2026-05-10 18:03:48 +02:00
Mario Zechner	cb3c42ecf5	Merge pull request #4358 from yanirz/fix/fireworks-session-affinity-cache ... fix(ai): add session affinity and compat fixes for Fireworks provider caching	2026-05-10 18:00:52 +02:00
Mario Zechner	533d37305c	fix(ai): align copilot claude adaptive test	2026-05-10 17:51:08 +02:00
Mario Zechner	cf7f2e3dbb	fix(ai): update copilot claude test model	2026-05-10 17:47:45 +02:00
yanirz	99dc6fcec8	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	2026-05-10 00:11:36 +02:00
haoqixu	8c2e3eddec	fix(ai): respect proxy envs in bun's websocket ... fixes #4346	2026-05-10 03:43:07 +08:00