cc487dd032
fix(opencode): gate reasoning summaries by provider ( #30973 )
2026-06-05 10:08:39 -05:00
9f42bd4a85
feat: bump bedrock and add proper mantle support for openai models through aws bedrock ( #30464 )
2026-06-04 00:09:12 -05:00
04b38ce830
chore: generate
2026-06-03 23:42:15 +00:00
0b796c5f3d
fix(opencode): route SAP AI Core reasoning variants through modelParams ( #30482 )
2026-06-03 18:40:39 -05:00
9991a33e3f
fix(core): expose azure openai xhigh efforts ( #30620 )
2026-06-03 15:27:23 -05:00
5940304098
fix: rm tool reorder logic from old bug ( #30483 )
2026-06-02 23:34:36 -05:00
a763a14d44
Revert "fix(opencode): preserve signed thinking during anthropic reorder" ( #30502 )
2026-06-02 23:34:05 -05:00
42173bca4b
fix(opencode): preserve signed thinking during anthropic reorder ( #30182 )
2026-06-02 23:33:48 -05:00
9c7788bbf9
chore: generate
2026-05-30 23:31:35 +00:00
f4f508e659
fix(opencode): support sap-ai-core anthropic opus 4.7+ adaptive reasoning ( #29991 )
2026-05-30 18:30:21 -05:00
3070b0f4ae
fix(opencode): default display summarized for gateway opus 4.7+ adaptive reasoning ( #30027 )
2026-05-30 18:07:06 -05:00
b956e9a06f
fix(opencode): support vertex opus adaptive reasoning ( #29911 )
2026-05-29 11:35:26 -05:00
05e3c4ecee
fix(opencode): enable adaptive reasoning for opus 4.7+ ( #29769 )
2026-05-28 12:19:34 -05:00
eb84f461b8
fix(llm): split OpenAI reasoning summary blocks ( #29000 )
2026-05-23 20:06:45 -05:00
e85119aa64
Load models.dev snapshot from build global ( #28077 )
2026-05-17 21:59:44 -04:00
2d6bedecd4
refactor(flags): migrate output token max to runtime flags ( #27680 )
2026-05-15 13:07:35 +05:30
7f7eb2e7f8
fix(provider): remove LiteLLM workarounds ported upstream, requires LiteLLM v1.85.0-rc.2+ ( #26819 )
...
Co-authored-by: Cursor <cursoragent@cursor.com >
2026-05-14 11:26:07 -05:00
c2723b5ea0
chore: generate
2026-05-14 04:25:32 +00:00
9675579796
fix: bug encountered when using azure gpt-5.5 w/ completions api ( #26222 )
2026-05-13 23:24:16 -05:00
16c457e712
refactor(core): move models.dev into core ( #27347 )
2026-05-13 20:58:24 -04:00
df3895d74f
cleanup: make smallOptions rely on variants ( #27390 )
2026-05-13 18:30:36 -05:00
9e8274d2da
Remove internal Zod schemas ( #26974 )
2026-05-11 21:40:44 -04:00
c36ab3f935
fix(provider): align Gemini thinking controls ( #26279 )
2026-05-08 10:22:45 -04:00
4e14f79511
fix: tweaks to transform logic for anthropic and bedrock ( #26276 )
2026-05-07 23:17:43 -05:00
e0396b809a
fix(provider): align Anthropic Opus 4.5 efforts ( #26275 )
2026-05-08 00:06:07 -04:00
319498e2fd
fix(provider): constrain OpenAI deep research efforts ( #26273 )
2026-05-07 23:43:42 -04:00
1cf8123bc6
fix(provider): align GPT-5 reasoning variants ( #26268 )
2026-05-07 23:32:47 -04:00
6409aceb1a
fix: sanitize surrogates ( #25934 )
2026-05-05 18:07:23 -05:00
ca77b8f8e9
fix(cf-ai-gateway): route provider options through openaiCompatible key ( #24432 ) ( #25573 )
2026-05-05 16:55:08 -05:00
576480b5dc
fix: ensure mistral medium 3.5 has variants properly setup ( #25887 )
2026-05-05 10:34:20 -05:00
3aaac0098e
chore: generate
2026-04-30 23:06:57 +00:00
a12333310f
fix(provider): split providerOptions key on dot for openai-compatible, openai, and anthropic providers ( #25145 )
2026-04-30 18:05:56 -05:00
a740d2c667
fix: adjust azure defaults to closer match openai to prevent Item .. of type 'reasoning' was provided without its required following item ( #25007 )
2026-04-29 16:49:28 -05:00
588261076a
fix: make deepseek string check a bit looser ( #25012 )
2026-04-29 16:47:45 -05:00
639e27c3ce
feat: add Mistral Medium 3.5 with reasoning support ( #24996 )
2026-04-29 16:26:24 -05:00
0acac216ae
fix(copilot): ensure available variants sync from api ( #24734 )
...
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-04-28 14:58:51 -05:00
528fb1d404
fix: sanitize tools for moonshot ( #24730 )
2026-04-27 23:44:21 -05:00
c361c2953f
fix: ensure toolStreaming is set to off by default when using non anthropic models with anthropic sdk ( #24642 )
2026-04-27 14:16:00 -05:00
f25f1485d5
refactor: remove module barrels ( #24554 )
2026-04-27 14:33:33 -04:00
f19d863689
ignore: split up reasoning transforms ( #24574 )
2026-04-26 23:57:32 -05:00
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
Aiden Cline