 dpuyosa
|
bf5a01edd9
feat(opencode): Venice Add automatic variant generation for Venice models (#12106)
|
2 weeks ago |
 Aiden Cline
|
0fd6f365be
fix(core): ensure compaction is more reliable, add reserve token buffer to ensure that input window has enough room to compact (#12924)
|
2 weeks ago |
|
Aiden Cline
|
99ea1351ce
tweak: add new ContextOverflowError type (#12777)
|
2 weeks ago |
 fgonzalezurriola
|
d40dffb854
fix(provider): remove obsolete copilot model enablement instructions (#12739)
|
2 weeks ago |
 AdJIa
|
0cd52f830c
fix: enable thinking for all reasoning models on alibaba-cn (DashScope) (#12772)
|
2 weeks ago |
 Ivan Gonzalez
|
a25cd2da72
feat(opencode): use reasoning summary auto for gpt-5 models that are not chat (#12502)
|
3 weeks ago |
|
Aiden Cline
|
2f78705f6e
tweak: update transforms for gpt-5.3 (#12325)
|
3 weeks ago |
 Tom
|
d1686661c0
fix: ensure kimi-for-coding plan has thinking on by default for k2p5 (#12147)
|
3 weeks ago |
|
Aiden Cline
|
b7b734f51f
fix: ensure mcp tools are sanitized (#11984)
|
3 weeks ago |
 neavo
|
54e14c1a17
fix: exclude k2p5 from reasoning variants (#11918)
|
3 weeks ago |
 Muhammad Mugni Hadi
|
3741516fe3
fix: handle nested array items for Gemini schema validation (#11952)
|
3 weeks ago |
 Kiyoung Chang
|
3adeed8f97
fix(provider): strip properties/required from non-object types in Gemini schema (#11888)
|
3 weeks ago |
 Mathias Beugnon
|
bd9d7b3221
fix: session title generation with OpenAI models. (#11678)
|
3 weeks ago |
|
Aiden Cline
|
f6948d0ffa
fix: variant logic for anthropic models through openai compat endpoint (#11665)
|
3 weeks ago |
 Rohan Godha
|
ca5e85d6ea
fix: prompt caching for opus on bedrock (#11664)
|
3 weeks ago |
 Jérôme Benoit
|
feca42b025
feat(opencode): add reasoning variants support for SAP AI Core (#8753)
|
3 weeks ago |
|
Aiden Cline
|
95bf01a757
fix: ensure the mistral ordering fixes also apply to devstral (#11412)
|
3 weeks ago |
 Steffen Deusch
|
d9f18e4006
feat(opencode): add copilot specific provider to properly handle copilot reasoning tokens (#8900)
|
4 weeks ago |
 opencode-agent[bot]
|
252b2c450d
chore: generate
|
4 weeks ago |
 Cesar Garcia
|
0c32afbc35
fix(provider): use snake_case for thinking param with OpenAI-compatible APIs (#10109)
|
4 weeks ago |
 Ryan Vogel
|
4a56491e42
fix(provider): exclude chat models from textVerbosity setting (#11363)
|
4 weeks ago |
 Aiden Cline
|
301895c7f7
fix: ensure kimi k2.5 from fireworks ai and kimi for coding providers properly set temperature
|
4 weeks ago |
|
Aiden Cline
|
0fabdccf11
fix: ensure that kimi doesnt have fake variants available
|
4 weeks ago |
|
Aiden Cline
|
29ea9fcf25
fix: ensure variants for copilot models work w/ maxTokens being set
|
4 weeks ago |
 Frank
|
df8b23db9e
Revert "Set temperature for kimi k2.5"
|
1 month ago |
|
Frank
|
bb63d16fa8
Set temperature for kimi k2.5
|
1 month ago |
|
Aiden Cline
|
32ce0f4b0d
tweak: add recommended topP/temp for kimi k2.5
|
1 month ago |
 Michael Yochpaz
|
0bc4a43320
fix(provider): enable thinking for google-vertex-anthropic models (#10442)
|
1 month ago |
 zerone0x
|
087d7da14d
fix(provider): deep merge providerOptions in applyCaching (#10323)
|
1 month ago |
 Arthur
|
cf7e10c4e8
fix: add xhigh reasoning effort for GitHub Copilot GPT-5 models (#10092)
|
1 month ago |
