Commit Graph

79 Commits

Author SHA1 Message Date
ryan.h.park
63035f977f fix: enable thinking for zhipuai-coding-plan & prevent Korean IME truncation (#22041)
Co-authored-by: claudianus <claudianus@users.noreply.github.com>
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-11 15:51:49 -05:00
Aiden Cline
b0600664ab feat: add support for fast modes for claude and gpt models (that support it) (#21706) 2026-04-09 12:06:26 -05:00
Kit Langton
59ca4543d8 refactor(provider): stop custom loaders using facades (#20776)
Co-authored-by: luanweslley77 <213105503+luanweslley77@users.noreply.github.com>
2026-04-04 00:24:24 +00:00
Major Hayden
26cc924ea2 feat: enable prompt caching and cache token tracking for google-vertex-anthropic (#20266)
Signed-off-by: Major Hayden <major@mhtx.net>
2026-03-31 15:16:14 -05:00
Aiden Cline
4dd866d5c4 fix: rm exclusion of ai-sdk/azure in transform.ts, when we migrated to v6 the ai sdk changed the key for ai-sdk/azure so the exclusion is no longer needed (#20326) 2026-03-31 14:57:15 -05:00
Aiden Cline
c33d9996f0 feat: AI SDK v6 support (#18433) 2026-03-27 15:24:30 -05:00
opencode-agent[bot]
e837dcc1c5 chore: generate 2026-03-24 18:43:20 +00:00
Nicholas Hansen
024979f3fd feat(bedrock): Add token caching for any amazon-bedrock provider (#18959) 2026-03-24 13:42:20 -05:00
Protocol Zero
cc818f8032 fix(provider): only set thinkingConfig for models with reasoning capability (#18283) 2026-03-21 11:57:52 -05:00
Vladimir Glafirov
05d3e65f76 feat: enable GitLab Agent Platform with workflow model discovery (#18014) 2026-03-20 12:55:22 -05:00
opencode-agent[bot]
773c1192dc chore: generate 2026-03-18 23:45:03 +00:00
Kit Langton
5ddfe4ada5 chore: type Provider.list() as Record<ProviderID, Info>, delete dead code (#18123) 2026-03-18 19:43:12 -04:00
Kit Langton
469c3a4204 refactor(instance): move scoped services to LayerMap (#17544) 2026-03-16 12:55:14 -04:00
Tom Ryder
4a2a046d79 fix: filter empty content blocks for Bedrock provider (#14586) 2026-03-12 22:13:09 -05:00
Kit Langton
dd68b85f58 refactor(provider): effectify ProviderAuthService (#17227) 2026-03-13 02:08:37 +00:00
Kit Langton
1cb7df7159 refactor(provider): flow branded ProviderID/ModelID through internal signatures (#17182) 2026-03-12 14:48:17 +00:00
Kit Langton
c45467964c feat(id): brand ProviderID and ModelID (#17110) 2026-03-12 09:27:52 -04:00
James Long
69ddc91c35 fix(core): a chunk timeout when processing llm stream (#16366) 2026-03-10 11:12:14 -04:00
opencode-agent[bot]
5a40158abf chore: generate 2026-03-10 15:07:35 +00:00
Jérôme Benoit
4dce485854 fix(opencode): add thinking variants support for SAP AI provider (#14958)
Co-authored-by: Test <test@test.com>
Co-authored-by: Stephen Collings <stevoland@gmail.com>
2026-03-10 10:05:45 -05:00
Armin Pašalić
ef9bc4ec9e feat(gitlab): send context-1m-2025-08-07 beta header to enable 1M context window (#16153)
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
2026-03-09 09:22:00 -05:00
Jack
5838b58913 add copilot gpt-5.4 xhigh support (#16294) 2026-03-09 22:07:12 +08:00
Shoubhit Dash
7e3e85ba59 fix(opencode): avoid gemini combiner schema sibling injection (#15318) 2026-03-03 10:11:05 +05:30
Ryan Skidmore
96d6fb78da fix(provider): forward metadata options to cloudflare-ai-gateway provider (#15619) 2026-03-02 22:53:03 -05:00
tctev
193013a44d feat(opencode): support adaptive thinking for claude sonnet 4.6 (#14283)
Co-authored-by: tctev <224793535+tctev@users.noreply.github.com>
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
2026-02-19 16:17:57 -06:00
Aiden Cline
7e35d0c610 core: bump ai sdk packages for google, google vertex, anthropic, bedrock, and provider utils (#14318) 2026-02-19 12:35:51 -06:00
Dax
02a9495063 Remove use of Bun.file (#14215) 2026-02-19 11:32:32 -05:00
Aiden Cline
0ca75544ab fix: dont autoload kilo (#14052) 2026-02-17 18:42:18 -06:00
opencode-agent[bot]
572a037e5d chore: generate 2026-02-17 23:53:22 +00:00
RAMA
ad92181fa7 feat: add Kilo as a native provider (#13765) 2026-02-17 17:52:21 -06:00
opencode-agent[bot]
089ab9defa chore: generate 2026-02-16 08:32:34 +00:00
Jhin Lee
f7708efa5b 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
Aiden Cline
933a491ade fix: ensure vercel variants pass amazon models under bedrock key (#13631) 2026-02-14 13:18:52 -06:00
Aiden Cline
759ec104b6 fix vercel gateway variants (#13541)
Co-authored-by: Benjamin Woodruff <github@benjam.info>"
2026-02-14 12:32:29 -06:00
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)
Co-authored-by: James Lal <james@littlebearlabs.io>
2026-02-10 19:55:22 -06:00
Dax Raad
9adcf524e2 core: bundle GitLab auth plugin directly instead of dynamic install
Remove dynamic installation of built-in plugins. GitLab auth is now imported

directly as an internal plugin, eliminating network requests during startup

and simplifying the plugin loading logic.

Removes the need for test mocks since plugins are no longer

dynamically installed at runtime.
2026-02-05 11:29:00 -05:00
Sergiy Dybskiy
b942e0b4dc fix: prevent double-prefixing of Bedrock cross-region inference models (#12056) 2026-02-03 23:06:17 -06:00
Muhammad Mugni Hadi
3741516fe3 fix: handle nested array items for Gemini schema validation (#11952) 2026-02-03 09:24:52 -06:00
Kiyoung Chang
3adeed8f97 fix(provider): strip properties/required from non-object types in Gemini schema (#11888) 2026-02-02 23:13:24 -06:00
Jigar
43354eeabd 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
Aiden Cline
f6948d0ffa fix: variant logic for anthropic models through openai compat endpoint (#11665) 2026-02-01 14:50:49 -06:00
Rohan Godha
ca5e85d6ea fix: prompt caching for opus on bedrock (#11664) 2026-02-01 14:42:42 -06:00
Aiden Cline
d1d7447493 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
opencode-agent[bot]
644f0d4e92 chore: generate 2026-01-31 02:35:22 +00:00
Steffen Deusch
d9f18e4006 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
opencode-agent[bot]
252b2c450d chore: generate 2026-01-31 01:32:46 +00:00
Cesar Garcia
0c32afbc35 fix(provider): use snake_case for thinking param with OpenAI-compatible APIs (#10109) 2026-01-31 01:32:02 +00:00
Ryan Vogel
4a56491e42 fix(provider): exclude chat models from textVerbosity setting (#11363) 2026-01-30 21:06:48 +00:00
Aiden Cline
b938e1ea99 test: fix test 2026-01-28 22:02:14 -06:00
adamelmore
5993a098b4 fix(core): don't override source in custom provider loaders 2026-01-25 20:40:00 -06:00