71ca9b2b92
fix(ai): expose OpenCode Go GLM-5.2 xhigh effort
...
closes #5967
2026-06-22 13:45:44 +02:00
500b568b04
fix(ai): use OpenAI endpoint for Fireworks GLM-5.2
...
closes #5923
2026-06-20 21:32:02 +02:00
8597ebafd9
fix(ai): expose OpenRouter GLM-5.2 xhigh effort
...
closes #5770
2026-06-20 18:47:42 +02:00
651d10d90b
feat(ai): enable Mistral prompt caching
2026-06-18 23:47:25 +02:00
b09fbde00e
feat(ai): add OpenRouter Fusion alias ( #5866 )
2026-06-18 22:39:02 +02:00
bd9f8773ad
fix(ai): restore OpenCode Go DeepSeek thinking controls
2026-06-16 23:14:56 +02:00
2431491c92
fix(ai): avoid duplicate OpenCode DeepSeek reasoning controls
...
closes #5818
2026-06-16 19:05:44 +02:00
75b0d723c0
fix(ai): support Z.AI GLM-5.2 effort levels
...
closes #5770
2026-06-16 14:29:27 +02:00
b0c8f65ffa
fix(ai): update Google Vertex Gemini models
...
closes #5761
2026-06-16 01:03:12 +02:00
0369bdb8f4
fix(ai): add Moonshot CN Kimi K2.7 metadata
...
closes #5760
2026-06-15 17:08:59 +02:00
408ac103ec
fix(ai): update Copilot Claude thinking metadata
...
closes #4637
2026-06-15 09:50:25 +02:00
21a904f4b7
fix(ai): disable OpenCode long cache retention for rejecting routes
...
closes #5702
2026-06-13 23:59:45 +02:00
aa3a5233ad
fix(ai): restore Codex context limits
2026-06-13 11:02:38 +02:00
7a3cb6312e
fix(ai): normalize generated model costs ( #5634 )
2026-06-13 00:01:04 +02:00
a7cdc679e7
fix(ai): correct GPT-5 context window metadata
...
closes #5644
2026-06-12 23:03:10 +02:00
9ccfcd7cfc
fix(ai): omit disabled thinking for Claude Fable 5
2026-06-10 00:27:11 +02:00
6b5923f107
fix(ai): correct Azure gpt-5.4/5.5 context window and gpt-5-pro maxTokens
...
Azure Foundry deploys gpt-5.4 and gpt-5.5 with a 1,050,000 context
window, but the Azure provider cloned OpenAI-direct's 272k API limit.
Override the context window in the Azure derivation.
Also fix gpt-5-pro maxTokens, which upstream metadata set to 272000 (a
duplicate of the input sub-limit) instead of the actual 128000 max
output; corrected at the source so OpenAI-direct and Azure both match.
closes #5559
2026-06-09 22:57:20 +02:00
5a9d72ea02
feat(ai): add Claude Fable 5 metadata
2026-06-09 22:42:48 +02:00
3d02d1da11
fix(ai): map OpenCode max tokens
...
closes #5331
2026-06-09 13:41:08 +02:00
2326d5cb4a
fix(ai): disable Moonshot thinking when requested
...
closes #5531
2026-06-09 12:23:41 +02:00
2527441b40
Update generate-models.ts
...
Removed together.ai MiniMaxAI/MiniMax-M2.5 due to it not being supported for serverless inference.
Error: 400 Unable to access non-serverless model MiniMaxAI/MiniMax-M2.5. Please visit
https://api.together.ai/models/MiniMaxAI/MiniMax-M2.5 to create and start a new dedicated endpoint for the model.
2026-06-08 08:32:16 -05:00
564ad70fb8
Merge pull request #5333 from vastxie/zai-coding-cn-provider
...
feat(ai): add ZAI Coding Plan China provider
2026-06-03 01:07:01 +02:00
83afcdc24f
fix(ai): remove stale codex models
2026-06-03 00:09:30 +02:00
51df39b9b9
feat(ai): add ZAI Coding Plan China provider
2026-06-02 23:39:56 +08:00
25a4a8ed1e
Add Ant Ling provider
2026-06-02 16:37:44 +02:00
7e72ca47c8
Add MiniMax-M3 to direct minimax providers
...
closes #5313
2026-06-02 16:00:29 +02:00
2125221bfc
Fix OpenRouter Kimi reasoning compat
...
closes #5309
2026-06-02 15:36:52 +02:00
6e269edfd0
Restore NVIDIA Qwen 3.5 122B model
2026-06-02 15:10:36 +02:00
6014801229
Add NVIDIA NIM provider
2026-06-02 15:09:36 +02:00
f429ddbffd
Fix OpenAI GPT-5.5 thinking metadata
...
closes #5243
2026-06-01 00:39:48 +02:00
40832d1957
fix(ai): suppress deprecated temperature param for Claude Opus 4.7+
2026-05-31 16:20:22 +08:00
a213abb97e
Fix OpenRouter Kimi K2.6 developer role
...
closes #5159
2026-05-29 23:41:14 +02:00
ba2d313858
fix(ai): handle OpenCode Kimi reasoning params
2026-05-29 23:27:48 +02:00
4faac05419
fix(ai): handle OpenCode reasoning params
2026-05-29 12:21:37 +02:00
0127caea7b
Fix OpenRouter DeepSeek V4 xhigh reasoning
...
closes #4801
2026-05-28 23:56:59 +02:00
97ef317389
Fix Kimi and Xiaomi model metadata
...
Closes #5075 , closes #5078 . Refs #5087 .
2026-05-28 22:19:47 +02:00
bfa3d1fa60
Update Claude Opus and GPT thinking metadata
2026-05-28 21:51:55 +02:00
458a7bc27c
Fix Anthropic empty thinking signature replay
...
closes #4464
2026-05-28 12:04:33 +02:00
71446c6c2b
fix(ai): correct Codex Spark context window
...
closes #4969
2026-05-26 09:08:40 +02:00
d801d88a11
Support adaptive thinking for Anthropic-compatible aliases
...
closes #4790
2026-05-22 18:30:51 +02:00
2e02c74dcb
chore: pin dependencies and use native TypeScript
2026-05-20 12:46:17 +02:00
ae9450dc51
chore(ts): use source import extensions
2026-05-20 00:04:03 +02:00
b8f51957a0
fix(ai): add Xiaomi reasoning replay compat
...
closes #4678
2026-05-18 11:15:20 +02:00
ed3904ddd3
fix(ai): switch xiaomi models to openai completions
...
closes #4505
2026-05-18 00:14:31 +02:00
266234047a
Remove openai-codex fast model variants, they do not work
2026-05-18 00:02:52 +02:00
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
485afc9c3f
fix(ai): map copilot gpt minimal thinking to low
2026-05-17 12:18:50 +02:00
1af823be9d
fix(ai): update OpenAI Codex model list
2026-05-17 03:12:19 +02:00
2c708492e3
Release v0.74.1
2026-05-17 01:35:45 +02:00
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