117 commits

Author	SHA1	Message	Date
Mario Zechner	cfa63c255d	Add [Unreleased] section for next cycle	2026-01-08 04:53:51 +01:00
Mario Zechner	4b084d0f9d	Release v0.38.0	2026-01-08 04:52:55 +01:00
Mario Zechner	946efe4b45	fix(ai): detect context_length_exceeded overflow	2026-01-08 03:16:59 +01:00
Melih Mucuk	d311978dfd	Merge branch 'main' into feat/custom-thinking-budgets	2026-01-08 00:39:11 +03:00
Mario Zechner	39fa25eb67	fix(ai): clean up openai-codex models and token limits ... - Remove model aliases (gpt-5, gpt-5-mini, gpt-5-nano, codex-mini-latest, gpt-5-codex, gpt-5.1-codex, gpt-5.1-chat-latest) - Fix context window from 400k to 272k tokens to match Codex CLI defaults - Keep maxTokens at 128k (original value) - Simplify reasoning effort clamping closes #536	2026-01-07 20:39:46 +01:00
Zhou Rui	d893ba7f20	fix(ai): clean up openai-codex models and token limits	2026-01-07 23:09:20 +08:00
Melih Mucuk	acec56c6b5	feat: add customizable thinking budgets for token-based providers ... Fixes #521	2026-01-07 15:17:18 +03:00
Melih Mucuk	0f27eae77e	feat: add thinkingBudgets option to customize token budgets	2026-01-07 15:13:26 +03:00
Mario Zechner	fcb3b4aa72	Add [Unreleased] section for next cycle	2026-01-07 01:33:34 +01:00
Mario Zechner	5514d4ffdb	Release v0.37.8	2026-01-07 01:32:53 +01:00
Mario Zechner	7508a51599	Add [Unreleased] section for next cycle	2026-01-07 01:02:34 +01:00
Mario Zechner	a4f2bb5c27	Release v0.37.7	2026-01-07 01:01:55 +01:00
Mario Zechner	9330f5a10a	Add [Unreleased] section for next cycle	2026-01-07 00:43:25 +01:00
Mario Zechner	befbeb30e4	Release v0.37.6	2026-01-07 00:42:45 +01:00
Mario Zechner	f054150ea3	Add changelog entries for bridge prompt export (#510)	2026-01-07 00:11:21 +01:00
Mario Zechner	a00322175f	Add [Unreleased] section for next cycle	2026-01-06 23:25:53 +01:00
Mario Zechner	fe95983dcf	Release v0.37.5	2026-01-06 23:25:12 +01:00
Mario Zechner	f87fb0a38a	Add [Unreleased] section for next cycle	2026-01-06 21:29:03 +01:00
Mario Zechner	b08a6b22ce	Release v0.37.4	2026-01-06 21:28:24 +01:00
Mario Zechner	a236e62025	Add [Unreleased] section for next cycle	2026-01-06 13:44:28 +01:00
Mario Zechner	86fea6379c	Release v0.37.3	2026-01-06 13:43:47 +01:00
Mario Zechner	edb0da9611	feat(ai,agent,coding-agent): add sessionId for provider session-based caching ... - Add sessionId to StreamOptions for providers that support session-based caching - OpenAI Codex provider uses sessionId for prompt_cache_key and routing headers - Agent class now accepts and forwards sessionId to stream functions - coding-agent passes session ID from SessionManager and updates on session changes - Update ai package README with table of contents, OpenAI Codex OAuth docs, and env vars table - Increase Codex instructions cache TTL from 15 minutes to 24 hours - Add tests for sessionId forwarding in ai and agent packages	2026-01-06 11:08:42 +01:00
Mario Zechner	9063a71fe6	Add [Unreleased] section for next cycle	2026-01-06 00:54:00 +01:00
Mario Zechner	6f4d16d76f	Release v0.37.2	2026-01-06 00:53:18 +01:00
Mario Zechner	aad93a1ec8	docs: add changelog entry for #484	2026-01-06 00:51:17 +01:00
Mario Zechner	2da853e9d6	Add [Unreleased] section for next cycle	2026-01-06 00:32:56 +01:00
Mario Zechner	a20112f45f	Release v0.37.1	2026-01-06 00:32:09 +01:00
Mario Zechner	0c712659b3	Add [Unreleased] section for next cycle	2026-01-06 00:07:57 +01:00
Mario Zechner	d3d53392e8	Release v0.37.0	2026-01-06 00:07:15 +01:00
Mario Zechner	0b9e3ada0c	fix: clean up Codex thinking level handling ... - Remove per-thinking-level model variants (gpt-5.2-codex-high, etc.) - Remove thinkingLevels from Model type - Provider clamps reasoning effort internally - Omit reasoning field when thinking is off fixes #472	2026-01-05 21:58:26 +01:00
Mario Zechner	168d114750	Add changelog entries for headless OAuth and truecolor detection	2026-01-05 20:16:59 +01:00
Mario Zechner	74d5f5523e	Add [Unreleased] section for next cycle	2026-01-05 06:17:05 +01:00
Mario Zechner	435cd5d61f	Release v0.36.0	2026-01-05 06:16:25 +01:00
Mario Zechner	bb50738f7e	fix(ai): append system prompt to codex bridge message instead of converting to input ... Previously the system prompt was converted to an input message in convertMessages, then stripped out by filterPiSystemPrompts. Now the system prompt is passed directly to transformRequestBody and appended after CODEX_PI_BRIDGE in the bridge message.	2026-01-05 06:03:07 +01:00
Mario Zechner	eede2e1644	Merge origin/main into feature/detect-vertex-ai	2026-01-05 04:35:17 +01:00
Mario Zechner	32f032b6d1	Add [Unreleased] section for next cycle	2026-01-05 03:42:07 +01:00
Mario Zechner	78d0b88f7d	Release v0.35.0	2026-01-05 03:41:24 +01:00
Anton Kuzmenko	63093bf7e4	fix(ai): cache vertex adc credentials file check	2026-01-04 17:16:40 -08:00
Anton Kuzmenko	a3f30e085a	fix(ai): add vertex ai dummy value for configured credentials	2026-01-04 12:59:19 -08:00
Mario Zechner	12805f61bd	Add [Unreleased] section for next cycle	2026-01-04 21:06:48 +01:00
Mario Zechner	71c978e2f9	Release v0.34.2	2026-01-04 21:06:08 +01:00
Mario Zechner	2a47b1114d	Add [Unreleased] section for next cycle	2026-01-04 20:57:34 +01:00
Mario Zechner	de92eeda1f	Release v0.34.1	2026-01-04 20:56:51 +01:00
Mario Zechner	61cadc226c	Add [Unreleased] section for next cycle	2026-01-04 20:30:34 +01:00
Mario Zechner	dc2f5d43cc	Release v0.34.0	2026-01-04 20:29:50 +01:00
butelo	36e774282d	fix duplicated thinking tokens in chutes (#443) ... Co-authored-by: xes garcia <xes.garcia@deus.ai>	2026-01-04 18:12:09 +01:00
Mario Zechner	7e2a99b485	Add [Unreleased] section for next cycle	2026-01-04 01:08:11 +01:00
Mario Zechner	faa10b9a7e	Release v0.33.0	2026-01-04 01:07:24 +01:00
Mario Zechner	7aba5883f2	Add [Unreleased] section for next cycle	2026-01-03 17:09:58 +01:00
Mario Zechner	db829e73f9	Release v0.32.3	2026-01-03 17:09:22 +01:00