fe3cf3fb4e
fix: don't fetch models.dev on completion ( #13997 )
2026-02-17 10:41:03 -06:00
31a30bea6b
fix: google vertex var priority ( #13816 )
2026-02-16 02:41:52 -06:00
b299880f49
feat: add openai-compatible endpoint support for google-vertex provider ( #10303 )
...
Co-authored-by: BlueT - Matthew Lien - 練喆明 <BlueT@BlueT.org >
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com >
Co-authored-by: Aiden Cline <aidenpcline@gmail.com >
2026-02-16 02:31:48 -06:00
94e2af3c60
feat(opencode): Add Venice support in temperature, topP, topK and smallOption ( #13553 )
2026-02-15 22:24:24 -06:00
b4bd78ce79
fix: ensure anthropic models on OR also have variant support ( #13498 )
2026-02-14 14:30:07 -06:00
eb3e9c74c6
fix: ensure vercel variants pass amazon models under bedrock key ( #13631 )
2026-02-14 13:18:52 -06:00
442fc7c1c7
fix vercel gateway variants ( #13541 )
...
Co-authored-by: Benjamin Woodruff <github@benjam.info >"
2026-02-14 12:32:29 -06:00
b4fe75a169
feat: update some ai sdk packages and uuse adaptive reasoning for opus 4.6 on vertex/bedrock/anthropic ( #13439 )
2026-02-13 00:56:11 -06:00
51f3a5e7a3
chore: generate
2026-02-12 22:14:45 +00:00
939c63627e
fix: look for recent model in fallback in cli ( #12582 )
2026-02-12 16:13:48 -06:00
3c66ef216f
core: allow model configurations without npm/api provider details
...
Makes npm and api fields optional in the provider schema so model definitions
can be more flexible when provider package details aren't needed.
2026-02-12 09:26:28 -05:00
10f9176a93
support custom api url per model
2026-02-11 23:10:47 -05:00
442d41191c
feat(opencode): Venice Add automatic variant generation for Venice models ( #12106 )
2026-02-11 20:21:29 -06:00
525cf17315
fix: add additional context overflow cases, remove overcorrecting ones ( #13077 )
2026-02-10 23:30:29 -06:00
61c5e8ab80
fix(core): ensure compaction is more reliable, add reserve token buffer to ensure that input window has enough room to compact ( #12924 )
...
Co-authored-by: James Lal <james@littlebearlabs.io >
2026-02-10 19:55:22 -06:00
3cfcc21e5a
fix(tui): improve amazon-bedrock check to include container credentials ( #13037 )
2026-02-10 18:51:49 -06:00
671f90a945
tweak: add new ContextOverflowError type ( #12777 )
2026-02-08 23:54:01 -06:00
5f70c465ea
fix(provider): remove obsolete copilot model enablement instructions ( #12739 )
2026-02-08 22:43:52 -06:00
e8c3d0c705
fix: enable thinking for all reasoning models on alibaba-cn (DashScope) ( #12772 )
...
Co-authored-by: lujia <lujiax@zmn.cn >
2026-02-08 22:42:23 -06:00
2d2ca2c251
feat(opencode): use reasoning summary auto for gpt-5 models that are not chat ( #12502 )
2026-02-06 13:19:14 -06:00
fcabcac26e
chore: generate
2026-02-06 17:19:57 +00:00
d9ee4b4432
fix(opencode): correct prefix selection for amazon-bedrock provider in getSmallModel ( #12281 )
2026-02-06 11:18:57 -06:00
5ad5a59f8e
tweak: update transforms for gpt-5.3 ( #12325 )
2026-02-05 12:49:40 -06:00
eead871f38
fix: ensure kimi-for-coding plan has thinking on by default for k2p5 ( #12147 )
2026-02-04 12:39:22 -06:00
5c64166f30
fix: cloudflare workers ai provider ( #12157 )
2026-02-04 18:07:33 +00:00
5d5f0b95f9
fix: revert change that caused headers to be double merged if provider was authed in multiple places ( #12072 )
2026-02-04 06:30:32 +00:00
28b0462384
docs: document the built in agents ( #12066 )
2026-02-04 00:00:05 -06:00
25e9b34b1a
fix: prevent double-prefixing of Bedrock cross-region inference models ( #12056 )
2026-02-03 23:06:17 -06:00
d7918636ea
fix(opencode): use official ai-gateway-provider package for Cloudflare AI Gateway ( #12014 )
2026-02-03 15:18:28 -06:00
7db8fd95ca
chore: generate
2026-02-03 19:10:44 +00:00
1bf27c231a
fix: provider headers from config not applied to fetch requests ( #11788 )
2026-02-03 13:09:07 -06:00
aad6f257fa
fix: ensure mcp tools are sanitized ( #11984 )
2026-02-03 12:22:00 -06:00
5ee962dcd5
fix: exclude k2p5 from reasoning variants ( #11918 )
2026-02-03 09:26:37 -06:00
70efbca7e7
fix: handle nested array items for Gemini schema validation ( #11952 )
2026-02-03 09:24:52 -06:00
2707d10956
fix(provider): strip properties/required from non-object types in Gemini schema ( #11888 )
2026-02-02 23:13:24 -06:00
bda07aeec9
feat(provider): add User-Agent header for GitLab AI Gateway requests ( #11818 )
2026-02-02 10:41:02 -06:00
4e4ce894ea
fix: convert system message content to string for Copilot provider ( #11600 )
...
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com >
2026-02-01 23:28:28 -06:00
304022ad23
fix: session title generation with OpenAI models. ( #11678 )
2026-02-01 23:10:53 -06:00
7b93ac8110
fix: variant logic for anthropic models through openai compat endpoint ( #11665 )
2026-02-01 14:50:49 -06:00
f9f29f63ba
fix: prompt caching for opus on bedrock ( #11664 )
2026-02-01 14:42:42 -06:00
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
Caleb Norton