CloudAxe/cloudaxe-opencode
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 5
14194 commits 1131 branches 1082 tags 3 GiB
Commit graph

678 commits

Author SHA1 Message Date
Dax Raad
a9bf1c0505 refactor: replace Bun.hash with Hash.fast using xxhash3-xxh64 2026-03-05 22:03:24 -05:00
opencode-agent[bot]
9f150b0776 chore: generate 2026-03-03 04:41:52 +00:00
Shoubhit Dash
7e3e85ba59
fix(opencode): avoid gemini combiner schema sibling injection (#15318) 2026-03-03 10:11:05 +05:30
opencode-agent[bot]
e41b53504f chore: generate 2026-03-03 03:53:50 +00:00
Ryan Skidmore
96d6fb78da
fix(provider): forward metadata options to cloudflare-ai-gateway provider (#15619) 2026-03-02 22:53:03 -05:00
bentrd
be20f865ac
fix: recover from 413 Request Entity Too Large via auto-compaction (#14707) 
Co-authored-by: Noam Bressler <noamzbr@gmail.com>
 2026-03-02 13:10:55 +05:30
Rian van der Merwe
6b7e6bde4d
fix(opencode): show human-readable message for HTML error responses (#15407) 2026-03-01 09:24:57 -06:00
opencode-agent[bot]
686dd330a0 chore: generate 2026-02-19 22:19:09 +00:00
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
Aiden Cline
5364ab74a2
tweak: add support for medium reasoning w/ gemini 3.1 (#14316) 2026-02-19 12:00:56 -06:00
Dax
02a9495063
Remove use of Bun.file (#14215) 2026-02-19 11:32:32 -05:00
Aiden Cline
308e500832
tweak: bake in the aws and google auth pkgs (#14241) 2026-02-19 00:31:33 -06:00
Dax Raad
568eccb4c6 Revert: all refactor commits migrating from Bun.file() to Filesystem module 2026-02-18 19:41:14 -05:00
Dax
359360ad86
refactor: migrate src/provider/provider.ts from Bun.file() to Filesystem module (#14132) 2026-02-18 18:08:48 -05:00
Dax
97520c827e
refactor: migrate src/provider/models.ts from Bun.file()/Bun.write() to Filesystem module (#14131) 2026-02-18 17:26:13 -05:00
Aiden Cline
0ca75544ab
fix: dont autoload kilo (#14052) 2026-02-17 18:42:18 -06:00
RAMA
ad92181fa7
feat: add Kilo as a native provider (#13765) 2026-02-17 17:52:21 -06:00
Caleb Norton
47435f6e17
fix: don't fetch models.dev on completion (#13997) 2026-02-17 10:41:03 -06:00
Aiden Cline
1d041c8861
fix: google vertex var priority (#13816) 2026-02-16 02:41:52 -06:00
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
dpuyosa
afd0716cbd
feat(opencode): Add Venice support in temperature, topP, topK and smallOption (#13553) 2026-02-15 22:24:24 -06:00
Aiden Cline
839c5cda12
fix: ensure anthropic models on OR also have variant support (#13498) 2026-02-14 14:30:07 -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
0d90a22f90
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
opencode-agent[bot]
d475fd6137 chore: generate 2026-02-12 22:14:45 +00:00
Smit Chaudhary
93eee0daf4
fix: look for recent model in fallback in cli (#12582) 2026-02-12 16:13:48 -06:00
Dax Raad
a115565054 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
Dax Raad
ad2087094d support custom api url per model 2026-02-11 23:10:47 -05:00
dpuyosa
bf5a01edd9
feat(opencode): Venice Add automatic variant generation for Venice models (#12106) 2026-02-11 20:21:29 -06:00
Aiden Cline
d98bd4bd52
fix: add additional context overflow cases, remove overcorrecting ones (#13077) 2026-02-10 23:30:29 -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
OpeOginni
53ec15a56a
fix(tui): improve amazon-bedrock check to include container credentials (#13037) 2026-02-10 18:51:49 -06:00
Aiden Cline
99ea1351ce
tweak: add new ContextOverflowError type (#12777) 2026-02-08 23:54:01 -06:00
fgonzalezurriola
d40dffb854
fix(provider): remove obsolete copilot model enablement instructions (#12739) 2026-02-08 22:43:52 -06:00
AdJIa
0cd52f830c
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
Ivan Gonzalez
a25cd2da72
feat(opencode): use reasoning summary auto for gpt-5 models that are not chat (#12502) 2026-02-06 13:19:14 -06:00
opencode-agent[bot]
3f7ca0494b chore: generate 2026-02-06 17:19:57 +00:00
Nacho F. Lizaur
18749c1f4e
fix(opencode): correct prefix selection for amazon-bedrock provider in getSmallModel (#12281) 2026-02-06 11:18:57 -06:00
Aiden Cline
2f78705f6e
tweak: update transforms for gpt-5.3 (#12325) 2026-02-05 12:49:40 -06:00
Tom
d1686661c0
fix: ensure kimi-for-coding plan has thinking on by default for k2p5 (#12147) 2026-02-04 12:39:22 -06:00
Aiden Cline
305007aa0c
fix: cloudflare workers ai provider (#12157) 2026-02-04 18:07:33 +00:00
Aiden Cline
5588453cbe
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
Aiden Cline
8c1f1f13dc
docs: document the built in agents (#12066) 2026-02-04 00:00:05 -06:00
Sergiy Dybskiy
b942e0b4dc
fix: prevent double-prefixing of Bedrock cross-region inference models (#12056) 2026-02-03 23:06:17 -06:00
Matt Silverlock
25bdd77b1d
fix(opencode): use official ai-gateway-provider package for Cloudflare AI Gateway (#12014) 2026-02-03 15:18:28 -06:00
opencode-agent[bot]
185858749b chore: generate 2026-02-03 19:10:44 +00:00
Cloudyan
39a504773c
fix: provider headers from config not applied to fetch requests (#11788) 2026-02-03 13:09:07 -06:00
Aiden Cline
b7b734f51f
fix: ensure mcp tools are sanitized (#11984) 2026-02-03 12:22:00 -06:00
neavo
54e14c1a17
fix: exclude k2p5 from reasoning variants (#11918) 2026-02-03 09:26:37 -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
Vladimir Glafirov
cf8b033be1
feat(provider): add User-Agent header for GitLab AI Gateway requests (#11818) 2026-02-02 10:41:02 -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
Mathias Beugnon
bd9d7b3221
fix: session title generation with OpenAI models. (#11678) 2026-02-01 23:10:53 -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
Jérôme Benoit
a19ef17bcb
fix(provider): use process.env directly for runtime env mutations (#11482) 2026-01-31 12:35:23 -06:00
Jérôme Benoit
feca42b025
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
Dax Raad
6ecd011e51 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
Dax Raad
d005e70f50 core: ensure models configuration is not empty before loading 2026-01-31 00:57:17 -05:00
Aiden Cline
95bf01a757
fix: ensure the mistral ordering fixes also apply to devstral (#11412) 2026-01-30 23:16:07 -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
Michael Yochpaz
2c36cbb87c
refactor(provider): remove google-vertex-anthropic special case in ge… (#10743) 2026-01-30 15:57:36 -06:00
Ryan Vogel
4a56491e42 fix(provider): exclude chat models from textVerbosity setting (#11363) 2026-01-30 21:06:48 +00:00
Aiden Cline
301895c7f7 fix: ensure kimi k2.5 from fireworks ai and kimi for coding providers properly set temperature 2026-01-29 10:30:22 -06:00
Aiden Cline
0fabdccf11 fix: ensure that kimi doesnt have fake variants available 2026-01-28 23:40:44 -06:00
Aiden Cline
29ea9fcf25 fix: ensure variants for copilot models work w/ maxTokens being set 2026-01-28 21:55:50 -06:00
Saba Tchikhinashvili
b937fe9450
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
Frank
df8b23db9e Revert "Set temperature for kimi k2.5" 
This reverts commit bb63d16fa8.
 2026-01-27 14:48:08 -05:00
Frank
bb63d16fa8 Set temperature for kimi k2.5 2026-01-27 14:13:21 -05:00
Aiden Cline
32ce0f4b0d tweak: add recommended topP/temp for kimi k2.5 2026-01-27 12:43:30 -05:00
Aiden Cline
ac53a372b0 feat: use anthropic compat messages api for anthropic models through copilot 2026-01-26 13:18:08 -05:00
adamelmore
5993a098b4 fix(core): don't override source in custom provider loaders 2026-01-25 20:40:00 -06:00
Aiden Cline
e49306b86c rm log statement 2026-01-25 12:44:17 -05:00
Michael Yochpaz
0bc4a43320
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
Dax Raad
ff9c186485 tests 2026-01-24 14:16:46 -05:00
Dax Raad
0d9ca0ea31 sync 2026-01-24 14:14:17 -05:00
Dax Raad
68bd16df69 core: fix models snapshot loading to prevent caching issues 2026-01-24 14:06:07 -05:00
zerone0x
087d7da14d
fix(provider): deep merge providerOptions in applyCaching (#10323) 
Co-authored-by: Claude <noreply@anthropic.com>
 2026-01-24 13:07:04 -05:00
Dax Raad
e3c1861a3e get rid of models.dev macro 2026-01-24 12:27:13 -05:00
Arthur
cf7e10c4e8
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
zerone0x
31094cd5a4
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
dpuyosa
65e267ed3a
feat: Add promptCacheKey for Venice provider (#9915) 2026-01-21 20:28:04 -06:00
Aiden Cline
6f7a1c69a5 tweak: adjust textVerbosity and reasoningEffort defaults to better match codex cli 2026-01-21 13:23:04 -06:00
Bart Broere
8df09abb1b
feat: Make the models.dev domain configurable for offline environments (#9258) 2026-01-21 11:23:07 -06:00
Stephen Collings
0e1a8a1839
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
Aiden Cline
3fd0043d19 chore: handle fields other than reasoning_content in interleaved block 2026-01-19 12:18:17 -06:00
Aiden Cline
4a7809f600 add proper variant support to copilot 2026-01-19 00:18:42 -06:00
GitHub Action
9d1803d000 chore: generate 2026-01-19 06:14:40 +00:00
Aiden Cline
86df915df0 chore: cleanup provider code to assign copilot sdk earlier in flow 2026-01-19 00:13:58 -06:00
GitHub Action
6f847a794b chore: generate 2026-01-19 06:12:36 +00:00
NateSmyth
260ab60c0b
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
Christopher Tso
fc6c9cbbd2
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
Aiden Cline
d841e70d26 fix: bad variants for grok models 2026-01-18 14:21:14 -06:00
Aiden Cline
ea13b6e8aa test: add azure test case 2026-01-17 00:35:49 -06:00
Aiden Cline
7c3eeeb0fa
fix: gpt id stuff fr fr this time :/ (#9006) 2026-01-16 22:09:36 -06:00
Aiden Cline
578239e0d0 chore: cleanup transform code a tad 2026-01-16 16:13:38 -06:00
Aiden Cline
14d1e20287
Revert "fix(app): support anthropic models on azure cognitive services" (#8966) 2026-01-16 15:25:23 -06:00
Unies Ananda Raja
b8e2895dfc
fix(app): support anthropic models on azure cognitive services (#8335) 2026-01-16 15:24:06 -06:00
Aiden Cline
40836e9683 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
Aiden Cline
d47510785a strip itemIds in more cases 2026-01-15 18:00:58 -06:00
Adam
d71153eae6
fix(core): loading models.dev in dev 2026-01-15 13:33:48 -06:00
Brandon Smith
8d720f9463
fix(opencode): add input limit for compaction (#8465) 2026-01-15 01:35:16 -06:00
Aiden Cline
92931437c4
fix: codex id issue (#8605) 2026-01-15 01:31:50 -06:00
Aiden Cline
16cac69a72
Revert "feat: allow provider-level store option (#8000)" (#8613) 2026-01-15 00:45:03 -06:00
Call White
fcf2da9571
feat: allow provider-level store option (#8000) 2026-01-15 00:35:53 -06:00
Aiden Cline
b36837ae93 tweak: add error message so people know to reauthenticate with copilot 2026-01-14 20:21:03 -06:00
Aiden Cline
7d3c7a9f65 add check incase provider doesnt exist in models list 2026-01-14 12:16:12 -06:00
Aiden Cline
1f86aa8bb9 fix: adjust gitlab logic in provider.ts 2026-01-14 11:42:45 -06:00
Jacopo Binosi
3a9e6b558c
feat(opencode): add AWS Web Identity Token File support for Bedrock (#8461) 2026-01-14 10:20:47 -06:00
Vladimir Glafirov
0ce849c3d5
chore: update gitlab-ai-provider to 3.1.1 and remove unused parameter (#8424) 2026-01-14 09:34:02 -06:00
GitHub Action
5a309c2dbf chore: generate 2026-01-13 21:24:19 +00:00
Vladimir Glafirov
452f11ff77
fix: Add Plugin Mocks to Provider Tests (#8276) 2026-01-13 15:23:41 -06:00
Vladimir Glafirov
05867f9318
feat: Add GitLab Duo Agentic Chat Provider Support (#7333) 
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
 2026-01-13 13:21:39 -06:00
Aiden Cline
b4ad5c138e tweak: for zai ensure clear_thinking is false 2026-01-12 23:04:50 -06:00
Rohan Mukherjee
20088a87b0
fix: max completion tokens error for cloudflare (#7970) 2026-01-12 20:08:27 -06:00
Adam
05019dae76
fix(bedrock): use reasoningConfig for Anthropic models on Bedrock (#8092) 2026-01-12 18:42:19 -06:00
opencode-agent[bot]
8f22a6b69d
Add nova-2 to region prefix models (#8085) 
Co-authored-by: opencode-agent[bot] <opencode-agent[bot]@users.noreply.github.com>
Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com>
 2026-01-12 16:55:12 -06:00
Aiden Cline
ee8b38ab26 fix: ensure /connect works for openai business plans too (was missing field) 2026-01-10 22:48:28 -06:00
Alejandro Chinchilla
794c5981a5
fix: exclude 'none' variant for gpt-5.2-codex (#7682) 2026-01-10 12:22:44 -06:00
Aiden Cline
b03172d723 fix: ensure gpt-5.2-codex has variants 2026-01-09 19:15:57 -06:00
Aiden Cline
07dc1f8ecc fix: model dialog issue when searching for models in fav/recents list, also ensure that deprecated models dont appear in list (#7429) 2026-01-09 01:32:00 -05:00
Aiden Cline
2e4fe973c9 fix: issue w/ normal transform options conflicting w/ small model options when gen-ing title 2026-01-07 17:32:38 -06:00
ikeda-tomoya-swx
1016a52cf1
fix(provider): add jp. prefix auto-assignment for Tokyo region (ap-northeast-1) (#7053) 2026-01-06 11:18:34 -06:00
Guofang.Tang
9197a2a7a1
docs: polish markdown wording and capitalization (#7019) 
Co-authored-by: Tang Guofang <tangguofang@mychery.com>
 2026-01-05 22:45:40 -06:00
ikeda-tomoya-swx
bf9ee32d4a
fix(provider): add support for jp. prefix in Amazon Bedrock cross-region inference profiles (#6916) 2026-01-05 13:03:09 -06:00
Grégoire Morpain
e3b4d4ad49
feat(bedrock): config options and authentication precedence (#6377) 2026-01-05 12:51:43 -06:00
Aiden Cline
06acd70670 tweak: transform 2026-01-05 01:40:15 -06:00
Aiden Cline
c285304acf fix: for anthropic compat ensure empty msgs and empty reasoning is filtered out 2026-01-05 01:40:15 -06:00
Aiden Cline
d72d7ab510 tweak: prioritize free gpt-5-mini for small model in github copilot 2026-01-04 08:21:09 -06:00
Aiden Cline
96a00ffea9 core: update github copilot model model priority list 2026-01-04 00:57:35 -06:00
Aiden Cline
2fd97377f6 test: fix transform test 2026-01-02 12:38:44 -06:00
Aiden Cline
49d7ccd1db fix: variant for minimal 2026-01-02 12:28:40 -06:00
Mike English
70881b2937
fix: cloudflare-ai-gateway sdk.chat undefined error (#6407) 2026-01-02 11:24:13 -06:00
alcpereira
8b35d56a48
fix: remove outdated Haiku filter for GitHub Copilot (#6593) 2026-01-01 14:04:31 -06:00
Aiden Cline
34aecda47c tweak: default to ai-sdk/opeai-compatible if no npm package provided 2025-12-31 14:54:21 -06:00
Qio
db84ee17f4
feat: add gemini-3-flash to fast models list (#6497) 
Co-authored-by: qio <handsomehust@gmail.com>
 2025-12-31 00:11:47 -06:00
OpeOginni
0b1f6a7d2d
feat: bundle in @ai-sdk/vercel version 1.0.31 for aisdk v5 support (#6512) 2025-12-31 00:10:42 -06:00
David Hill
a6d225558c
fix: cleaner view subagents hint text (#6437) 
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
 2025-12-30 22:47:16 -06:00
Aiden Cline
324ae9c471 fix: openai variants for codex models 2025-12-30 18:18:16 -06:00
Aiden Cline
81fef60266
fix: ensure variants also work for completely custom models (#6481) 
Co-authored-by: Daniel Smolsky <dannysmo@gmail.com>
 2025-12-30 16:37:32 -06:00
Aiden Cline
ed0c0d90be
feat: add variants toggle (#6325) 
Co-authored-by: Github Action <action@github.com>
 2025-12-29 21:43:50 -06:00
Dominik Engelhardt
504a668a26
Set smallOptions for google models on openrouter (#6362) 2025-12-29 16:01:31 -06:00
GitHub Action
896d18ab3f chore: generate 2025-12-29 04:44:48 +00:00
Grégoire Morpain
893888536a
fix(bedrock): support region and bearer token configuration (#6332) 
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
 2025-12-28 22:44:15 -06:00
Aiden Cline
3522c460e3 tweak: update transform for gemini models so that topP and topK match gemini-cli values 2025-12-25 22:46:12 -06:00
Matt Silverlock
9898fbe8ef
providers: add Cloudflare AI Gateway (#5174) 2025-12-23 17:31:58 -06:00
Frank
526c723e62 support glm 4.7 2025-12-22 17:11:02 -05:00
Blake North
87b5b34280
fix(providers.opencode): check config for api key in addition to auth (#5906) 2025-12-22 15:20:40 -06:00
Aiden Cline
f9be2bab3a fix: bundle more providers to fix breaking ai sdk issue 2025-12-22 15:12:18 -06:00
Aiden Cline
8785bec29c tweak: adjust minimax m2 topK and add minimax m2.1 topP 2025-12-21 21:17:58 -06:00
Aiden Cline
3456f4ed80 tweak: update kimi-k2 and kimi-k2-thinking to use recommended temperature values 2025-12-21 15:54:57 -06:00
lif
d89b567b47
fix: add transform case for gemini if mcp tool has missing array items (#5846) 2025-12-20 11:41:52 -06:00
Aiden Cline
dacbbe3184 chore: rm dead code 2025-12-19 16:20:17 -06:00
Aiden Cline
9427f56e1a rm interleaved thinking filter for certain kimi k2 thinking model providers that were bugged 2025-12-18 12:26:27 -06:00
Frank
d5dcc55a47 Revert "add client header" 
This reverts commit 2fb89161c8.
 2025-12-18 11:21:22 -05:00
Frank
2fb89161c8 add client header 2025-12-18 10:33:25 -05:00
Dax Raad
7d1733c752 core: fix message caching for Anthropic models to improve response consistency 2025-12-15 14:33:14 -05:00
René
9eefcd1b41
Provider fix, anthropic Errorhandling if empty image file is read (#5521) 2025-12-14 23:56:47 -06:00
Adam
4a8e8f537c
wip(desktop): progress 2025-12-14 21:38:58 -06:00
Dax Raad
e22af25076 ci: fix test failures in CI by pre-populating models cache 
Tests were failing in CI because the models.json cache file doesn't exist
and the data() macro fallback only works at build time, not runtime.
The preload now pre-fetches models.json and disables the background
refresh to prevent race conditions during test execution.
 2025-12-14 21:23:45 -05:00
Dax
fed4776451
LLM cleanup (#5462) 
Co-authored-by: GitHub Action <action@github.com>
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
 2025-12-14 21:11:30 -05:00
Aiden Cline
0c7f0cfa2e tweak: fallback to provider default for temperature 2025-12-14 11:57:12 -06:00
Aiden Cline
3d2ef28fa8 add topK function to transform, add temp defaults for glm and minimax 2025-12-13 23:27:11 -06:00
Aiden Cline
d4cfbd8219 chore: reduce duplication of field in transform 2025-12-13 18:07:22 -06:00
Aiden Cline
f9674793af tweak: 5.1 -> 5. in transform 2025-12-12 15:17:11 -06:00
Aiden Cline
909013320b tweak: 5.1 -> 5. reasoning effort match 2025-12-12 13:21:57 -06:00
Aiden Cline
342595e0f7 tweak: setting chat_template_args in transform 2025-12-11 16:22:10 -06:00
Aiden Cline
7b4f852f33 ignore: tmp transform exclusion 2025-12-10 21:18:19 -06:00
Aiden Cline
439aebb4e9 tweak: correct thinkingLevel 2025-12-10 21:13:10 -06:00
Seb Duerr
df55ad89ab
Add Cerebras integration header with opencode identifier (#5354) 2025-12-10 19:36:58 -06:00
Dax Raad
ffc4d53923 add models.dev family 2025-12-10 14:30:28 -05:00
Aiden Cline
18d3c054a3
more interleaved thinking fixes (#5334) 2025-12-10 13:29:26 -06:00
Aiden Cline
59c5da9b6c tweak: set gemini thinkingLevel to high by default 2025-12-10 13:09:27 -06:00
Tom Aylott
117de64f39
fix: upgrade OpenRouter sdk pkg (#5302) 
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
 2025-12-10 13:02:26 -06:00
Aiden Cline
df64612d54
better interleaved thinking support (#5298) 2025-12-09 16:32:12 -06:00
Aiden Cline
f8bd4ff705 core: refactor providerOptions function to accept Provider.Model for cleaner API 2025-12-09 01:25:36 -06:00
Jérôme Benoit
52bb43eebd
fix: SAP AI Core Vercel AI SDK v2 support (#5180) 
Signed-off-by: Jérôme Benoit <jerome.benoit@sap.com>
Signed-off-by: Jérôme Benoit <jerome.benoit@piment-noir.org>
 2025-12-08 11:27:47 -06:00
Aiden Cline
a3bb4a3c85
pdf support in read tool (#5222) 
Co-authored-by: ammi1378 <ammi1378@users.noreply.github.com>
 2025-12-07 21:54:00 -06:00
Aiden Cline
c30b1130ee fix: provider url merging logic 2025-12-07 13:01:05 -06:00
Dax Raad
1b05d5dd8e tui: prevent deprecated models from appearing in model picker 2025-12-06 18:18:45 -05:00
Julian Visser
52db0f23a6
fix: #5064 ProviderInitError github-copilot-enterprise (#5123) 2025-12-05 09:53:32 -06:00
Jérôme Benoit
bef4fdfc4b
fix: add getModel to SAP AI Core provider for correct SDK initialization (#5086) 
Signed-off-by: Jérôme Benoit <jerome.benoit@piment-noir.org>
 2025-12-04 22:43:22 -06:00
Dax Raad
668d5a76d5 core: ensure model npm package falls back to dev models config when not explicitly defined 2025-12-04 15:39:52 -05:00
Jérôme Benoit
b9c1f10016
feat: Add SAP AI Core provider support (#5023) 
Signed-off-by: Jérôme Benoit <jerome.benoit@piment-noir.org>
 2025-12-04 14:07:23 -06:00
Dax Raad
10cc15aabe fix anthropic api key error 2025-12-03 23:18:24 -05:00
Jakub Matjanowski
46790e57e9
feat: Enhance DeepSeek reasoning content handling (#4975) 
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
 2025-12-03 21:31:36 -06:00
Aiden Cline
598d63db63 fix: dax typo 2025-12-03 20:39:11 -06:00
Dax
6d3fc63658
core: refactor provider and model system (#5033) 
Co-authored-by: opencode-agent[bot] <opencode-agent[bot]@users.noreply.github.com>
Co-authored-by: thdxr <thdxr@users.noreply.github.com>
 2025-12-03 21:09:03 -05:00
Dax Raad
ee4437ff32 core: add provider test coverage for upcoming refactor 
Add comprehensive test suite for Provider module to ensure safe
refactoring of provider internals. Tests cover:
- Provider loading from env vars and config
- Provider filtering (disabled_providers, enabled_providers)
- Model whitelist/blacklist
- Model aliasing and custom providers
- getModel, getProvider, closest, defaultModel functions

Also adds Env module for instance-scoped environment variable access,
enabling isolated test environments without global state pollution.
 2025-12-03 18:30:42 -05:00
Aiden Cline
b457923970 core: fix GitHub Copilot Enterprise authentication failing with sdk.chat undefined error 2025-12-02 23:37:10 -06:00
Aiden Cline
0331931f56 fix: sanitize more invalid schema cases for gemini models 2025-12-01 16:19:10 -06:00
Aiden Cline
f1bb5870ce fix: copilot responses bug w/ gpt 5 mini 2025-12-01 14:36:49 -06:00
Aiden Cline
027d43b5ea fix case where opencode wasn't retrying 2025-12-01 13:02:33 -06:00
Aiden Cline
b1b82977ec tweak: better err msgs 2025-12-01 01:33:32 -06:00
Aiden Cline
6e2379a28c get codex working in copilot (#4914) 
Co-authored-by: OpeOginni <107570612+OpeOginni@users.noreply.github.com>
Co-authored-by: GitHub Action <action@github.com>
 2025-11-29 21:47:29 -06:00
Dax Raad
813d287a09 core: add explore agent for fast codebase navigation and improve task UI display 2025-11-28 21:13:07 -05:00
Dmitry Halushka
ee946d8128
fix: transform MCP tool schemas for Google/Gemini compatibility (#4538) 
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
Co-authored-by: Github Action <action@github.com>
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
 2025-11-26 00:58:20 -06:00
Aiden Cline
b44971668c fix: global prefix handling w/ aws bedrock (#4757) 2025-11-26 00:21:59 +00:00
Shantur Rathore
69c2dd53ad
config: add setCacheKey in provider options (#4738) 
Co-authored-by: GitHub Action <action@github.com>
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
 2025-11-25 17:53:56 -06:00
Aiden Cline
16dbac6026 Revert "config: add setCacheKey in provider options (#4654)" 
This reverts commit 9b6d03c497.
 2025-11-24 22:30:56 -06:00
Shantur Rathore
9b6d03c497
config: add setCacheKey in provider options (#4654) 
Co-authored-by: GitHub Action <action@github.com>
 2025-11-24 22:20:52 -06:00
Aiden Cline
23a721f0a2 remove hardcoded openrouter provider 2025-11-24 16:11:12 -06:00
Aiden Cline
9e44085a69
adjust bundled provider logic, fix tree shaking stuff (#4708) 2025-11-24 15:48:54 -06:00
Adam
acf1dd8500
wip(share): more styling 2025-11-24 15:10:40 -06:00
Aiden Cline
ac1e2bfd49
bump copilot plugin, give better error message for copilot (#4678) 2025-11-24 00:40:15 -06:00
Huang Qi
b4fd4bb257
fix: add explicit fallback model and prevent direct opencode provider calls (#4653) 
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
 2025-11-23 22:51:15 -06:00
Frank
bbc9142fc5 wip: zen 2025-11-23 15:21:47 -05:00
Aiden Cline
30ffcaa667
tweak: start bundling in some ai-sdk packages (#4649) 2025-11-23 01:29:20 -06:00
Dax Raad
75c29d4d1c summary optimizaitons 2025-11-22 11:32:49 -05:00
Frank
e34df15ff5 update logic for local and dev providers 2025-11-21 13:31:33 -05:00
Ian Maurer
e018e16898
fix(cli): ensure clean exit on provider/model errors (#4223) 
Co-authored-by: GitHub Action <action@github.com>
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
 2025-11-21 02:01:19 -06:00
Aiden Cline
fffe20cbe5 add provider whitelist 2025-11-21 01:24:44 -06:00
geril07
c0d9f21c0f
feat: whitelist/blacklist config options for provider (#3416) 
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
 2025-11-21 01:01:30 -06:00
Dax
23ea8ba1ce
Tui onboarding (#4569) 
Co-authored-by: GitHub Action <action@github.com>
 2025-11-21 00:21:06 -05:00
Aiden Cline
cf934357c9 fix: make use openrouter ai sdk package to fix interlevened thinking models 2025-11-20 16:32:44 -06:00
Aiden Cline
97893bd7e6 tweak: make /export go to cwd 2025-11-19 22:45:40 -06:00
Aiden Cline
51bba6e634 tweak: default to disabling fetch timeout in provider options 2025-11-19 16:20:29 -06:00
Aiden Cline
9d068c20bb fix: openrouter ai sdk package support 2025-11-19 14:22:51 -06:00
Tommy D. Rossi
9de1242d9b
fix: show reasoning summaries for gemini models (#4491) 
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
 2025-11-19 11:25:18 -06:00
Aiden Cline
a9981441ae tweak: use temperature 1 for gemini 3 pro 2025-11-18 11:49:39 -06:00
Dax Raad
7c0cc94023 rework default model 2025-11-18 12:01:41 -05:00
Albert O'Shea
5e13527416
feat: nix support for the nix folks (#3924) 
Co-authored-by: opencode <opencode@sst.dev>
Co-authored-by: opencode-agent[bot] <opencode-agent[bot]@users.noreply.github.com>
 2025-11-18 00:46:49 -06:00
Dax Raad
bc232045a1 respect server suggestion for default model 2025-11-17 20:53:48 -05:00
Youssef Achy
58cc5cdf2a
add support for azure cognitive services provider (#4397) 2025-11-17 00:01:45 -06:00
Aiden Cline
25678fa504 fix: vercel gateway options 2025-11-16 18:39:31 -06:00
Aiden Cline
cf266f6162 fix: promptCacheKey set unnecessarily 2025-11-16 14:32:57 -06:00
xiaojie.zj
0e4703b227
add: add zenmux doc and header (#3597) 
Co-authored-by: xiaojie.zj <xiaojie.zj@antgroup.com>
 2025-11-15 21:37:30 -06:00
Frank
f5230d1f02 fix: incorrect sonnet price calculation 2025-11-14 18:46:43 -05:00
GitHub Action
078111bd96 chore: format code 2025-11-14 22:44:36 +00:00
sredfern
736f8882f5
fix(provider): support local file paths for custom providers (#4323) 2025-11-14 16:43:59 -06:00
Aiden Cline
b939470302 fix: add azure exclusion 2025-11-14 11:54:00 -06:00
Aiden Cline
ef4b2baedc set verbosity to low for gpt-5.1 (match codex) 2025-11-14 11:52:29 -06:00
Shantur Rathore
986c60353e
set promptCacheKey for openai compatible providers (#4203) 
Co-authored-by: GitHub Action <action@github.com>
 2025-11-14 11:41:01 -06:00
Frank
1d8330331c zen: use gpt-5-nano as small model 2025-11-14 00:59:00 -05:00
Aiden Cline
0c51feb9c2
fix: max tokens when using models like opus with providers other than anthropic (#4307) 2025-11-13 16:39:09 -06:00
Aiden Cline
8addaa7e08 fix: custom model name merging 2025-11-12 13:55:13 -06:00
Aiden Cline
c5e096c76a
fix: costs being 0 when using custom model id overrides (#4219) 2025-11-11 15:58:14 -06:00
OpeOginni
bba72c82ae
Fix/google vertex configs (#4169) 
Co-authored-by: GitHub Action <action@github.com>
 2025-11-10 13:25:03 -06:00
Dax Raad
4d20e1c3c6 Merge remote-tracking branch 'origin/dev' into dev 2025-11-08 20:21:02 -05:00
Dax Raad
4bb7ea9127 improve startup speed 2025-11-08 20:18:36 -05:00
GitHub Action
34ff87d504 chore: format code 2025-11-08 01:59:02 +00:00
Nicolai van der Smagt
9e04ff013c fix: resolve Mistral API compatibility issues (#2440) 
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
 2025-11-06 20:05:59 -05:00
Dax Raad
25f31f3096 codex tweaks 2025-11-06 19:14:01 -05:00
Nicolai van der Smagt
a2ab019317
fix: resolve Mistral API compatibility issues (#2440) 
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
 2025-11-06 16:53:02 -06:00
Dax Raad
1ea3a8eb9b big format 2025-11-06 13:03:12 -05:00
Aiden Cline
af7b9e77d1 fix: eu-west-2 aws bedrock issue 2025-11-05 10:14:08 -06:00
Ola
fe94bb8e50
feat(provider): add GitHub Enterprise support for Copilot (#2522) 
Co-authored-by: Jon-Mikkel Korsvik <48263282+jkorsvik@users.noreply.github.com>
Co-authored-by: GitHub Action <action@github.com>
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
 2025-11-04 15:36:12 -06:00
Aiden Cline
46d675b980 tweak: filter out deprecated models 2025-10-31 10:48:51 -05:00
Filip
51e4c9fc4c
add optional headers field to model config (#3546) 2025-10-30 23:35:26 -05:00
Dax Raad
d8249f32a8 do not set temperature for claude models 2025-10-28 01:14:25 -04:00
Aurelien Ribon
a606e1d2ec
fix: dont set reasoning effort to medium for gpt-5-pro (#3474) 2025-10-27 10:50:57 -05:00
Jérôme Benoit
0eb899a950
chore: cleanup versioned zod imports (#3460) 
Signed-off-by: Jérôme Benoit <jerome.benoit@sap.com>
Co-authored-by: opencode-agent[bot] <opencode-agent[bot]@users.noreply.github.com>
Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com>
 2025-10-26 14:50:41 -05:00
Aiden Cline
c70e393c81 Remove claude-haiku-4.5 from default priority for GitHub Copilot session title generation 2025-10-26 01:21:34 -05:00
Paulo Edgar Castro
ae62bc8b1f
fix: timeout param that allows user to disable provider timeout (#3443) 2025-10-25 12:08:27 -05:00
Aiden Cline
5fec5ff424 fix: bedrock reasoning 2025-10-24 17:35:08 -05:00
Dax Raad
56528493dc codex does not have reasoning effort set 2025-10-24 00:29:34 -04:00
theVinchi
a7b43d82ab
add Amazon Nova models to us-* prefix requirement list (#3357) 2025-10-22 11:41:38 -05:00
Aiden Cline
9005fd31ed tweak 2025-10-22 11:29:10 -05:00
Aiden Cline
d2bded23c3 tweak 2025-10-22 11:28:06 -05:00
Aiden Cline
c0cbc37f85 tweak: model priority 2025-10-22 11:12:32 -05:00
Aiden Cline
9df61055e2 change default title model 2025-10-22 10:41:08 -05:00
Aiden Cline
ca0f3902b7
fix: provider option transforms (#3331) 2025-10-21 11:08:21 -05:00
Matt Gillard
ddb2e6957c
added AU inference for bedrock haiku 4.5 (#3206) 
Co-authored-by: Matt Gillard <matt-github@gillard.biz>
 2025-10-16 23:48:41 -05:00
Aiden Cline
b24f4e3d2c
fix: timeout option (#3229) 2025-10-16 17:47:41 -05:00
seridescent
536934548a
fix: use ai-sdk openai chat language model instead of completion language model (#3204) 2025-10-16 00:59:49 -05:00
Dax Raad
ab8471a7ff core: filter out alpha status models from provider list 2025-10-15 20:12:37 -04:00
Matt Gillard
e29d1d339c
updated bedrock provider for the new Australian sonnet 4.5 cross region inference (#3050) 
Co-authored-by: Matt Gillard <matt-github@gillard.biz>
 2025-10-15 11:09:22 -05:00
Dax Raad
b8249cde4b core: improve dependency management and error handling for more reliable builds 2025-10-14 01:33:25 -04:00
Aiden Cline
682d30bd12
fix: custom model (#3156) 2025-10-13 19:58:19 -05:00
Aiden Cline
59765e0157
fix: typecheck (#3149) 2025-10-13 14:51:12 -05:00
AB
d0519be0d0
fix: add useCompletionUrls option to fix certain azure setups (#2528) 
Co-authored-by: andreas.blass <andreas.blass@outlook.com>
Co-authored-by: GitHub Action <action@github.com>
 2025-10-13 14:16:21 -05:00
OpeOginni
36cf9b9922
fix: add timeout to fetch models.dev refresh request (#3059) 2025-10-12 00:20:22 -05:00
Aiden Cline
225adc46ba
feat: allow read tool to handle images (#3052) 2025-10-09 09:05:11 -05:00
Aiden Cline
71a7e8ef36
fix: max output tokens when using large thinking budget (#2976) 2025-10-04 23:38:41 -05:00
Yuku Kotani
e7b6ffb314
feat: Vertex AI support; add google-vertex and google-vertex-anthropic providers (#2347) 2025-10-04 01:10:38 -04:00
Dax Raad
bd0ba5ab88 turn on codex medium reasoning again 2025-10-03 06:46:07 -04:00
Dax Raad
bd69c5aca8 codex should not have reasoning effort 2025-10-01 05:06:37 -04:00
Aiden Cline
89167ae387
respect model id in opencode.json (#2833) 2025-09-27 17:09:21 -05:00
Dax Raad
f5c7a94abe turn reasoning summaries back on by default for zen 2025-09-26 01:37:44 -04:00
Dax Raad
7ec3900208 core: enable reasoning.encrypted_content and reasoningSummary for opencode provider\ntui: adjust editorY position calculation 2025-09-26 01:27:53 -04:00
Aiden Cline
d47feb9969
tweak: include usage by default for openai compatible providers (#2788) 2025-09-25 21:06:58 -05:00
Dax Raad
71b43fd02e fix codex errors 2025-09-23 16:56:40 -04:00
Dax Raad
079095d7a9 core: filter models without keys in opencode provider 2025-09-21 04:43:32 -04:00
Dax Raad
d4c01f858b disable thinking for opencode zen and gpt-5 temporarily 2025-09-16 13:49:37 -04:00
Dax Raad
2d5bd26a59 feat: enhance provider model mapping and reasoning capabilities 
- Add npm package tracking to provider model mapping
- Implement special handling for opencode provider with reasoning
- Update provider options mapping to use npm package names
 2025-09-16 03:10:17 -04:00
Dax
c1b4e1f19d
Upgrade to Zod v4 (#2605) 
Co-authored-by: GitHub Action <action@github.com>
 2025-09-15 03:12:07 -04:00
Dax Raad
f5b3992479 properly support model level npm definition 2025-09-11 16:22:44 -04:00
Frank
a3513244f1 wip: zen 2025-09-09 15:47:28 -04:00
Frank
02e8242c3b Remove debug logging 2025-09-09 03:35:09 -04:00
Frank
0f263bfefe Hide experimental models 2025-09-09 03:16:44 -04:00
Douglas Dennis
d8fd7b155f
fix: aws bedrock add check for govcloud (#2495) 2025-09-08 11:54:06 -05:00
Ytzhak
4654fb88de
fix: max output tokens when setting budget thinking tokens (#2056) 
Co-authored-by: rekram1-node <aidenpcline@gmail.com>
 2025-09-07 13:15:53 -05:00
Aiden Cline
dc99005e65
fix: default to last used model (#2443) 2025-09-05 17:25:25 -05:00