5e2d74b72a
fix: ensure switching anthropic models mid convo on copilot works without errors, fix issue with reasoning opaque not being picked up for gemini models ( #11569 )
2026-02-01 01:36:44 -06:00
2e89dabee3
fix(provider): use process.env directly for runtime env mutations ( #11482 )
2026-01-31 12:35:23 -06:00
8e0808abd0
feat(opencode): add reasoning variants support for SAP AI Core ( #8753 )
...
Co-authored-by: Github Action <action@github.com >
2026-01-31 09:26:23 -06:00
e50d530613
tui: allow specifying custom models file path via OPENCODE_MODELS_PATH
...
Users can now configure their own models configuration file by setting the OPENCODE_MODELS_PATH environment variable, providing more flexibility for testing and configuration.
2026-01-31 01:53:23 -05:00
42c80d47f0
core: ensure models configuration is not empty before loading
2026-01-31 00:57:17 -05:00
a8f82e9a59
fix: ensure the mistral ordering fixes also apply to devstral ( #11412 )
2026-01-30 23:16:07 -06:00
1289be7c11
chore: generate
2026-01-31 02:35:22 +00:00
18023af20b
feat(opencode): add copilot specific provider to properly handle copilot reasoning tokens ( #8900 )
...
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com >
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com >
Co-authored-by: Aiden Cline <aidenpcline@gmail.com >
2026-01-30 19:53:22 -06:00
b1ad1961b7
chore: generate
2026-01-31 01:32:46 +00:00
3488a55a9f
fix(provider): use snake_case for thinking param with OpenAI-compatible APIs ( #10109 )
2026-01-31 01:32:02 +00:00
9b9d692b2c
refactor(provider): remove google-vertex-anthropic special case in ge… ( #10743 )
2026-01-30 15:57:36 -06:00
f3dce2b05e
fix(provider): exclude chat models from textVerbosity setting ( #11363 )
2026-01-30 21:06:48 +00:00
b3529a2a0c
fix: ensure kimi k2.5 from fireworks ai and kimi for coding providers properly set temperature
2026-01-29 10:30:22 -06:00
afdbfd0234
fix: ensure that kimi doesnt have fake variants available
2026-01-28 23:40:44 -06:00
d2d0a47886
fix: ensure variants for copilot models work w/ maxTokens being set
2026-01-28 21:55:50 -06:00
65949e13c1
fix(provider): include providerID in SDK cache key ( #11020 )
...
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com >
2026-01-28 21:26:26 -06:00
a36444882a
Revert "Set temperature for kimi k2.5"
...
This reverts commit b8be3a9543
2026-01-27 14:48:08 -05:00
b8be3a9543
Set temperature for kimi k2.5
2026-01-27 14:13:21 -05:00
a8096a5537
tweak: add recommended topP/temp for kimi k2.5
2026-01-27 12:43:30 -05:00
c29791caa2
feat: use anthropic compat messages api for anthropic models through copilot
2026-01-26 13:18:08 -05:00
fcb7685d9a
fix(core): don't override source in custom provider loaders
2026-01-25 20:40:00 -06:00
cb034dc28c
rm log statement
2026-01-25 12:44:17 -05:00
d1aeb93b40
fix(provider): enable thinking for google-vertex-anthropic models ( #10442 )
...
Co-authored-by: Aiden Cline <aidenpcline@gmail.com >
2026-01-24 23:42:29 -05:00
05cf87fd8c
tests
2026-01-24 14:16:46 -05:00
04af783c63
sync
2026-01-24 14:14:17 -05:00
9920190f6b
core: fix models snapshot loading to prevent caching issues
2026-01-24 14:06:07 -05:00
6550de3398
fix(provider): deep merge providerOptions in applyCaching ( #10323 )
...
Co-authored-by: Claude <noreply@anthropic.com >
2026-01-24 13:07:04 -05:00
e47a14fd43
get rid of models.dev macro
2026-01-24 12:27:13 -05:00
2d61d471ee
fix: add xhigh reasoning effort for GitHub Copilot GPT-5 models ( #10092 )
...
Co-authored-by: Arthur Freitas Ramos <arthur@MacBook-Air-de-Arthur.local >
2026-01-24 00:09:47 -05:00
8cd1708b56
fix(provider): add thinking presets for Google Vertex Anthropic ( #9953 )
...
Co-authored-by: Claude <noreply@anthropic.com >
2026-01-22 19:44:18 -06:00
36ece4e82f
feat: Add promptCacheKey for Venice provider ( #9915 )
2026-01-21 20:28:04 -06:00
b1a6072991
tweak: adjust textVerbosity and reasoningEffort defaults to better match codex cli
2026-01-21 13:23:04 -06:00
bddd609991
feat: Make the models.dev domain configurable for offline environments ( #9258 )
2026-01-21 11:23:07 -06:00
ccb25dd8ce
fix: Claude w/bedrock custom inference profile - caching support ( #9838 )
...
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com >
2026-01-21 10:42:13 -06:00
14f2effb0a
chore: handle fields other than reasoning_content in interleaved block
2026-01-19 12:18:17 -06:00
2574d3f676
add proper variant support to copilot
2026-01-19 00:18:42 -06:00
2cabf0e0f7
chore: generate
2026-01-19 06:14:40 +00:00
e61da6d828
chore: cleanup provider code to assign copilot sdk earlier in flow
2026-01-19 00:13:58 -06:00
5a6d365b3f
chore: generate
2026-01-19 06:12:36 +00:00
0f4408243c
fix: track reasoning by output_index for copilot compatibility ( #9124 )
...
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com >
2026-01-19 00:11:54 -06:00
d03ace53cb
fix(github-copilot): auto-route GPT-5+ models to Responses API ( #5877 )
...
Co-authored-by: Claude <noreply@anthropic.com >
2026-01-18 23:30:28 -06:00
802117a019
fix: bad variants for grok models
2026-01-18 14:21:14 -06:00
ce03719b0e
test: add azure test case
2026-01-17 00:35:49 -06:00
94cf094225
fix: gpt id stuff fr fr this time :/ ( #9006 )
2026-01-16 22:09:36 -06:00
c17c9f3bb6
chore: cleanup transform code a tad
2026-01-16 16:13:38 -06:00
f49f91e2b0
Revert "fix(app): support anthropic models on azure cognitive services" ( #8966 )
2026-01-16 15:25:23 -06:00
ceba48d96b
fix(app): support anthropic models on azure cognitive services ( #8335 )
2026-01-16 15:24:06 -06:00
e51a8fadb6
fix: fix the itemId stripping logic, this time it should fix that id issue w/ gpt models fr
2026-01-16 11:34:45 -06:00
44b8b52699
strip itemIds in more cases
2026-01-15 18:00:58 -06:00
e3221ddb69
fix(core): loading models.dev in dev
2026-01-15 13:33:48 -06:00
Aiden Cline