025a6392ce
fix: default tool call streaming to false for google vertex ( #24573 )
2026-04-26 23:42:23 -05:00
e7053c41f4
fix: bump openrouter sdk version to resolve deepseek reasoning issue (bug was in sdk pkg) ( #24435 )
2026-04-26 00:05:16 -05:00
1a734adb4d
core: consolidate shared infrastructure into core package
...
Moves effect logging, observability, runtime utilities, flags, installation
version info, and process utilities from opencode to core package. This
enables better code sharing across packages and establishes core as the
single source of truth for foundational utilities.
All internal imports updated to use @opencode-ai/core paths for consistency.
2026-04-25 13:30:37 -04:00
86715fecc4
fix: ensure assistant messages always have reasoning on them for deepseek ( #24180 )
2026-04-24 11:10:47 -04:00
f8e939d96f
fix: support max for deepseek ( #24163 )
2026-04-24 08:48:52 -04:00
923af96d26
fix: preserve empty reasoning_content for DeepSeek V4 thinking mode ( #24146 )
...
Co-authored-by: Simon Klee <hello@simonklee.dk >
2026-04-24 08:42:57 -04:00
a882e958b3
fix: deepseek variants ( #24157 )
2026-04-24 08:34:48 -04:00
1a20703469
feat: add Mistral Small reasoning variant support (issue #19479 ) ( #23735 )
2026-04-21 16:45:06 -04:00
58232d896e
fix: dont show variants for kimi models that dont support them ( #23696 )
2026-04-21 15:33:35 -04:00
e2e7a8d722
fix: ensure display: summarized is sent by default for bedrock ( #23343 )
2026-04-18 16:04:00 -05:00
3fe602cda3
feat: add LLM Gateway provider ( #7847 )
...
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 >
2026-04-17 10:29:31 -05:00
8fbbca5f4b
fix(opencode): rescrict github copilot opus 4.7 variants to "medium" ( #23097 )
2026-04-17 10:25:12 -05:00
cb18f2ef40
fix: ensure azure sets prompt cache key by default ( #22957 )
2026-04-16 17:45:35 -05:00
610c036ef1
fix(opencode): use low reasoning effort for GitHub Copilot gpt-5 models ( #22824 )
...
Co-authored-by: opencode-agent[bot] <opencode-agent[bot]@users.noreply.github.com>
Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com >
2026-04-16 15:44:58 -05:00
2fe9d94470
fix: remove 8 more unnecessary as any casts in opencode core ( #22877 )
2026-04-16 19:27:53 +00:00
47e0e2342c
tweak: set display 'summarized' by default for opus 4.7 thorugh messages api ( #22873 )
2026-04-16 14:12:43 -05:00
c5deeee8c7
fix: ensure azure has store = true by default ( #22764 )
2026-04-16 12:19:01 -05:00
378c05f202
feat: Add support for claude opus 4.7 xhigh adaptive reasoning effort ( #22833 )
...
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com >
2026-04-16 10:57:36 -05:00
150ab07a83
chore: generate
2026-04-16 05:03:50 +00:00
6b20838981
feat: unwrap provider namespaces to flat exports + barrel ( #22760 )
2026-04-16 05:02:50 +00:00
8aa0f9fe95
feat: enable type-aware no-base-to-string rule, fix 56 violations ( #22750 )
2026-04-16 03:50:47 +00:00
0e20382396
fix: resolve circular sibling imports causing runtime ReferenceError ( #22752 )
2026-04-15 23:41:34 -04:00
d6b14e2467
fix: prefix 32 unused parameters with underscore ( #22694 )
2026-04-15 21:56:23 -04:00
1d81335ab5
feat: unwrap Provider namespace + improved automation script ( #22690 )
2026-04-15 21:44:46 -04:00
348a84969d
fix: ensure tool_use is always followed by tool_result ( #22646 )
...
Co-authored-by: opencode-agent[bot] <opencode-agent[bot]@users.noreply.github.com>
2026-04-15 14:56:45 -05:00
c2403d0f15
fix(provider): guard reasoningSummary injection for @ai-sdk/openai-compatible providers ( #22352 )
...
Co-authored-by: Nazar Hnatyshen <nazar.hnatyshen@atolls.com >
2026-04-13 20:20:06 -05:00
0b4fe14b0a
fix: forgot to put alibaba case in last commit ( #22249 )
2026-04-13 00:39:12 -05:00
7230cd2683
feat: add alibaba pkg and cache support ( #22248 )
2026-04-13 00:08:07 -05:00
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
00cb8839ae
fix: dont show invalid variants for BP ( #21555 )
2026-04-08 14:52:34 -05:00
5a6d10cd53
tweak: ensure copilot anthropic models have same reasoning effort model as copilot cli, also fix qwen incorrectly having variants ( #21212 )
2026-04-06 18:12:43 +00:00
9965d385de
fix: pass both 'openai' and 'azure' providerOptions keys for @ai-sdk/azure ( #20272 )
...
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com >
2026-04-06 02:34:53 +00:00
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
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
c33d9996f0
feat: AI SDK v6 support ( #18433 )
2026-03-27 15:24:30 -05:00
e837dcc1c5
chore: generate
2026-03-24 18:43:20 +00:00
024979f3fd
feat(bedrock): Add token caching for any amazon-bedrock provider ( #18959 )
2026-03-24 13:42:20 -05:00
cc818f8032
fix(provider): only set thinkingConfig for models with reasoning capability ( #18283 )
2026-03-21 11:57:52 -05:00
4a2a046d79
fix: filter empty content blocks for Bedrock provider ( #14586 )
2026-03-12 22:13:09 -05:00
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
5838b58913
add copilot gpt-5.4 xhigh support ( #16294 )
2026-03-09 22:07:12 +08:00
9f150b0776
chore: generate
2026-03-03 04:41:52 +00:00
7e3e85ba59
fix(opencode): avoid gemini combiner schema sibling injection ( #15318 )
2026-03-03 10:11:05 +05:30
686dd330a0
chore: generate
2026-02-19 22:19:09 +00:00
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
7e35d0c610
core: bump ai sdk packages for google, google vertex, anthropic, bedrock, and provider utils ( #14318 )
2026-02-19 12:35:51 -06:00
5364ab74a2
tweak: add support for medium reasoning w/ gemini 3.1 ( #14316 )
2026-02-19 12:00:56 -06:00
afd0716cbd
feat(opencode): Add Venice support in temperature, topP, topK and smallOption ( #13553 )
2026-02-15 22:24:24 -06:00
839c5cda12
fix: ensure anthropic models on OR also have variant support ( #13498 )
2026-02-14 14:30:07 -06:00
933a491ade
fix: ensure vercel variants pass amazon models under bedrock key ( #13631 )
2026-02-14 13:18:52 -06:00
Aiden Cline