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
61ca69317a
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
25e9b34b1a
fix: prevent double-prefixing of Bedrock cross-region inference models ( #12056 )
2026-02-03 23:06:17 -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
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
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
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
f3dce2b05e
fix(provider): exclude chat models from textVerbosity setting ( #11363 )
2026-01-30 21:06:48 +00:00
ad25b9d283
test: fix test
2026-01-28 22:02:14 -06:00
fcb7685d9a
fix(core): don't override source in custom provider loaders
2026-01-25 20:40:00 -06:00
2d61d471ee
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
ccb25dd8ce
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
e77d2a4a4c
test: fix transfomr test
2026-01-18 14:44:39 -06:00
ce03719b0e
test: add azure test case
2026-01-17 00:35:49 -06:00
94cf094225
fix: gpt id stuff fr fr this time :/ ( #9006 )
2026-01-16 22:09:36 -06:00
e51a8fadb6
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
60b1a7f646
test: fix transform test
2026-01-15 19:27:04 -06:00
8f12616408
fix: codex id issue ( #8605 )
2026-01-15 01:31:50 -06:00
4dbe69d271
feat(opencode): add AWS Web Identity Token File support for Bedrock ( #8461 )
2026-01-14 10:20:47 -06:00
831fff0de6
fix: Add Plugin Mocks to Provider Tests ( #8276 )
2026-01-13 15:23:41 -06:00
dbc91cc328
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
a3b25cf6f0
feat(bedrock): config options and authentication precedence ( #6377 )
2026-01-05 12:51:43 -06:00
650843eb1d
fix: for anthropic compat ensure empty msgs and empty reasoning is filtered out
2026-01-05 01:40:15 -06:00
2c5703aa19
test: fix transform test
2026-01-02 12:38:44 -06:00
f5e84c3225
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
4178c882ac
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
08a3d97002
fix: add transform case for gemini if mcp tool has missing array items ( #5846 )
2025-12-20 11:41:52 -06:00
bd51fb48e2
test: fix test case
2025-12-19 16:37:36 -06:00
960362edcd
test: add regression test for setCacheKey option
2025-12-17 10:24:53 -06:00
e9e1f3302e
Provider fix, anthropic Errorhandling if empty image file is read ( #5521 )
2025-12-14 23:56:47 -06:00
0aef1b8080
fix: test
2025-12-14 21:42:17 -06:00
46cae6260a
ignore: fix test
2025-12-10 13:31:45 -06:00
b9ad1b09cb
better interleaved thinking support ( #5298 )
2025-12-09 16:32:12 -06:00
0eadf18120
ignore: add test for provider url case
2025-12-07 13:06:12 -06:00
267cf11962
core: add test for custom model npm package inheritance
2025-12-04 16:30:54 -05:00
73c6b95c7d
feat: Enhance DeepSeek reasoning content handling ( #4975 )
...
Co-authored-by: Aiden Cline <aidenpcline@gmail.com >
2025-12-03 21:31:36 -06:00
85d8825cb1
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
5c0dccdc6c
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
840f332700
fix: max tokens when using models like opus with providers other than anthropic ( #4307 )
2025-11-13 16:39:09 -06:00
Aiden Cline