da7c874808
tweak: show actual retry error message instead of generic error msg ( #11520 )
2026-01-31 13:15:42 -06:00
a19ef17bcb
fix(provider): use process.env directly for runtime env mutations ( #11482 )
2026-01-31 12:35:23 -06:00
35f64b80fa
docs: fix documentation issues ( #11435 )
...
Co-authored-by: damaozi <1811866786@qq.com>
2026-01-31 12:30:45 -06:00
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
53f118c57a
Revert "feat(app): add skill slash commands" ( #11484 )
2026-01-31 10:20:23 -05:00
786ae0a584
feat(app): add skill slash commands ( #11369 )
2026-01-31 08:59:28 -06:00
f73f88fb56
fix(pty): Add UTF-8 encoding defaults for Windows PTY ( #11459 )
2026-01-31 08:55:34 -06:00
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
d005e70f50
core: ensure models configuration is not empty before loading
2026-01-31 00:57:17 -05:00
81ac41e089
feat: make skills invokable as slash commands in the TUI ( #11390 )
2026-01-31 00:41:55 -05:00
c0e71c4261
fix: don't --follow by default for grep and other things using ripgrep ( #11415 )
2026-01-30 23:38:43 -06:00
90f39bf672
core: prevent parallel test runs from contaminating environment variables
2026-01-31 00:37:21 -05:00
95bf01a757
fix: ensure the mistral ordering fixes also apply to devstral ( #11412 )
2026-01-30 23:16:07 -06:00
644f0d4e92
chore: generate
2026-01-31 02:35:22 +00:00
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
3542f3e406
Revert "feat: make skills invokable as slash commands in the TUI"
...
This reverts commit 85126556b8
2026-01-30 20:37:41 -05:00
85126556b8
feat: make skills invokable as slash commands in the TUI
...
- Add Skill.content() method to load skill template content from SKILL.md files
- Modify Command.list() to include skills as invokable commands
- Add 'skill' boolean property to Command.Info schema
- Update autocomplete to show skills with (Skill) label in slash commands
- Regenerate SDK to include skill property in Command type
2026-01-30 20:36:48 -05:00
252b2c450d
chore: generate
2026-01-31 01:32:46 +00:00
0c32afbc35
fix(provider): use snake_case for thinking param with OpenAI-compatible APIs ( #10109 )
2026-01-31 01:32:02 +00:00
1a6461e8bc
fix: ensure ask question tool isn't included when using acp ( #11379 )
2026-01-30 17:32:51 -06:00
e7ff7143b6
fix: handle redirected_statement treesitter node in bash permissions ( #6737 )
2026-01-30 16:11:45 -06:00
2c36cbb87c
refactor(provider): remove google-vertex-anthropic special case in ge… ( #10743 )
2026-01-30 15:57:36 -06:00
4a56491e42
fix(provider): exclude chat models from textVerbosity setting ( #11363 )
2026-01-30 21:06:48 +00:00
7d0777a7ff
chore(tui): remove unused experimental keys ( #11195 )
2026-01-30 12:16:01 -06:00
11d486707c
fix: rm ai sdk middleware that was preventing <think> blocks from being sent back as assistant message content ( #11270 )
...
Co-authored-by: opencode-agent[bot] <opencode-agent[bot]@users.noreply.github.com>
2026-01-30 09:36:57 -05:00
b5ffa997da
feat(config): add managed settings support for enterprise deployments ( #6441 )
...
Co-authored-by: Dax <mail@thdxr.com>
2026-01-29 22:56:25 +00:00
75166a1961
fix: use ?? to prevent args being undefined for mcp server in some cases ( #11203 )
2026-01-29 22:00:12 +00:00
2125dc11c7
fix: show all provider models when no providers connected ( #11198 )
2026-01-29 21:19:50 +00:00
fdd484d2c1
feat: expose acp thinking variants ( #9064 )
...
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
2026-01-29 20:15:36 +00:00
45ec3105b1
feat: support config skill registration ( #9640 )
...
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
2026-01-29 11:47:06 -06:00
aa92ef37fd
tweak: add 'skill' to permissions config section so that ides will show it as autocomplete option (this is already a respected setting)
2026-01-29 10:55:39 -06:00
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
03ba49af4e
fix(telemetry): restore userId and sessionId metadata in experimental_telemetry ( #8195 )
2026-01-29 10:14:28 -06:00
92eb982863
fix: undo change that used anthropic messages endpoint for anthropic models on copilot due to ratelimiting issues, go back to completions endpoint instead
2026-01-28 23:52:23 -06:00
33c5c100ff
fix: frontmatter was adding newlines in some cases causing invalid model ids ( #11095 )
...
Co-authored-by: aptdnfapt <aptdnfapt@users.noreply.github.com>
2026-01-28 23:40:59 -06:00
0fabdccf11
fix: ensure that kimi doesnt have fake variants available
2026-01-28 23:40:44 -06:00
41ea4694db
more timeout race guards
2026-01-29 00:17:39 -05:00
e84d92da28
feat: Sequential numbering for forked session titles (Issue #10105 ) ( #10321 )
2026-01-28 23:08:35 -06:00
58ba486375
guard destroyed input field in timeout
2026-01-28 23:53:37 -05:00
f40bdd1ac3
feat(cli): include cache tokens in stats ( #10582 )
2026-01-28 22:03:44 -06:00
29ea9fcf25
fix: ensure variants for copilot models work w/ maxTokens being set
2026-01-28 21:55:50 -06:00
870c38a6aa
fix: maxOutputTokens was accidentally hardcoded to undefined ( #10995 )
2026-01-28 21:28:15 -06:00
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
427ef95f7d
fix(opencode): allow media-src data: URL for small audio files ( #11082 )
2026-01-28 21:21:49 -06:00
8cdb82038a
docs: update experimental environment variables in CLI docs ( #11030 )
2026-01-28 20:20:13 -06:00
4d2696e027
tweak: add ctx.abort to grep tool
2026-01-28 20:06:36 -06:00
e5b33f8a5e
fix(opencode): add `AbortSignal` support to `Ripgrep.files()` and `GlobTool` ( #10833 )
2026-01-28 18:47:09 -06:00
8c05eb22b1
fix(markdown): Add streaming prop to markdown element ( #11025 )
2026-01-28 12:55:57 -05:00
26e14ce628
fix: add SubtaskPart with metadata reference ( #10990 )
...
Co-authored-by: yangtianzhe <yangtianzhe@corp.netease.com>
2026-01-28 11:11:43 -05:00
acb92fcd34
chore: cleanup
2026-01-28 07:28:03 -06:00
c9bbea4266
chore: cleanup
2026-01-28 07:28:03 -06:00
65e1186efe
wip(app): global config
2026-01-28 07:28:03 -06:00
2f35c40bb5
chore(app): global config changes
2026-01-28 07:28:02 -06:00
8798a77a72
bump: plugins
2026-01-28 07:19:18 +00:00
5a0b3ee673
fix: ensure copilot plugin properly sets headers for new messages api
2026-01-28 02:04:30 -05:00
558590712d
fix: ensure parallel tool calls dont double load AGENTS.md
2026-01-28 01:38:10 -05:00
026b3cc88d
bump plugin version
2026-01-28 01:31:01 -05:00
28e5557bf4
ignore: adjust flag
2026-01-28 01:09:31 -05:00
9a8da20a97
chore: generate
2026-01-28 06:05:21 +00:00
63f5669eb5
fix(opencode): ensure unsub(PartUpdated) is always called in TaskTool ( #9992 )
2026-01-28 01:04:43 -05:00
aedd760141
fix(cli): restore brand integrity of CLI wordmark ( #10912 )
2026-01-27 22:24:02 -05:00
5f2a7c630b
chore: generate
2026-01-28 03:06:58 +00:00
7988f52231
feat(app): use opentui markdown component behind experimental flag ( #10900 )
2026-01-27 22:06:09 -05:00
898118bafb
feat: support headless authentication for chatgpt/codex ( #10890 )
...
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
2026-01-27 19:05:52 -05:00
b8e726521d
fix(tui): handle 4-5 codes too in c to copy logic
2026-01-27 16:29:01 -05:00
df8b23db9e
Revert "Set temperature for kimi k2.5"
...
This reverts commit bb63d16fa8
2026-01-27 14:48:08 -05:00
bb63d16fa8
Set temperature for kimi k2.5
2026-01-27 14:13:21 -05:00
32ce0f4b0d
tweak: add recommended topP/temp for kimi k2.5
2026-01-27 12:43:30 -05:00
f12f7e7718
tweak: adjust retry check to be more defensive
2026-01-27 11:31:02 -05:00
dbc8d7edca
chore: generate
2026-01-27 15:59:54 +00:00
d8e7e915e2
feat(opencode): Handle Venice cache creation tokens ( #10735 )
...
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
2026-01-27 10:59:12 -05:00
1f9313847f
feat(core): add worktree to plugin tool context
2026-01-27 06:29:19 -06:00
a8c18dba82
fix(core): expose Instance.directory to custom tools
2026-01-26 20:07:47 -06:00
6cf2c3e3db
fix: use Instance.directory instead of process.cwd() in read tool
2026-01-26 20:57:50 -05:00
021d9d105e
fix(app): reactive file tree
2026-01-26 16:46:09 -06:00
45b09c1465
tweak: when using messages api for copilot, attach anthropic beta headers
2026-01-26 17:17:54 -05:00
8b5dde5536
tweak: retry logic to catch certain provider problems
2026-01-26 16:12:41 -05:00
837037cd04
fix: ensure openai 404 errors are retried ( #10590 )
2026-01-26 13:50:04 -05:00
ac53a372b0
feat: use anthropic compat messages api for anthropic models through copilot
2026-01-26 13:18:08 -05:00
39a73d4894
feat: dynamically resolve AGENTS.md files from subdirectories as agent explores them ( #10678 )
2026-01-26 10:49:41 -05:00
b1fbfa7e94
feat(opencode): add agent description ( #10680 )
2026-01-26 10:43:10 -05:00
7c34319b19
fix(app): query selector with non-latin chars
2026-01-26 09:33:42 -06:00
0edd304f42
fix: Make diff wrapping toggle always available in command_list and correct a type error ( resolves #10682 ) ( #10683 )
2026-01-26 09:01:23 -05:00
6b83b172ae
fix: await SessionRevert.cleanup for shell ( #10669 )
2026-01-26 07:36:17 -05:00
444934a4c1
fix(tui): add visual feedback for diff wrap and conceal toggles ( #10655 )
2026-01-26 07:34:09 -05:00
5993a098b4
fix(core): don't override source in custom provider loaders
2026-01-25 20:40:00 -06:00
03d884797c
wip(app): provider settings
2026-01-25 20:40:00 -06:00
eaad75b176
tweak: adjust tui syncing logic to help prevent case where agents would be undefined / missing
2026-01-25 21:26:47 -05:00
578361de64
fix: remove broken app.tsx command option
2026-01-25 20:27:41 -05:00
3071720ce7
fix(tui): Move animations toggle to global System category ( resolves #10495 ) ( #10497 )
2026-01-25 17:57:47 -05:00
94dd0a8dbe
ignore: rm spoof and bump plugin version
2026-01-25 17:27:24 -05:00
407f34fed5
chore: cleanup
2026-01-25 13:20:18 -06:00
94ce289dd9
fix(app): run start command after reset
2026-01-25 13:20:18 -06:00
e49306b86c
rm log statement
2026-01-25 12:44:17 -05:00
ebe86e40a0
fix(tui): prevent crash when theme search returns no results ( #10565 )
2026-01-25 12:11:49 -05:00
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
397ee419d1
tweak: make question valdiation more lax to avoid tool call failures
2026-01-24 23:11:21 -05:00
8f99e9a606
fix(opentui): question selection click when terminal unfocused ( #9731 )
2026-01-24 15:12:16 -05:00
ff9c186485
tests
2026-01-24 14:16:46 -05:00
0d9ca0ea31
sync
2026-01-24 14:14:17 -05:00
68bd16df69
core: fix models snapshot loading to prevent caching issues
2026-01-24 14:06:07 -05:00
32e6bcae3b
core: fix unicode filename handling in snapshot diff by disabling quote escaping
...
This ensures unicode and special characters in filenames are displayed correctly when generating diff patches, allowing proper file detection and revert operations
2026-01-24 13:07:07 -05:00
087d7da14d
fix(provider): deep merge providerOptions in applyCaching ( #10323 )
...
Co-authored-by: Claude <noreply@anthropic.com>
2026-01-24 13:07:04 -05:00
f4cf3f4976
fix(web): construct apply_patch metadata before requesting permission ( #10422 )
2026-01-24 12:00:21 -06:00
e3c1861a3e
get rid of models.dev macro
2026-01-24 12:27:13 -05:00
ad27427b48
use min/maxHeight for question textarea
2026-01-24 12:14:12 -05:00
88bcd04659
tweak: tell the model what model it is in environment section of prompt
2026-01-24 12:10:15 -05:00
077d17d433
fix: permission prompt should ignore keyboard events while dialog stack len > 0 ( #10338 )
2026-01-24 12:01:46 -05:00
ae77ef3370
chore: generate
2026-01-24 14:47:36 +00:00
68e504bdc2
fix(tui): Use selectedForeground for question prompt tab text visibility ( resolves #10334 ) ( #10337 )
2026-01-24 09:46:59 -05:00
b978ca11da
fix: retry webfetch with simple UA on 403 ( #10328 )
2026-01-24 00:14:32 -05:00
e2d8310b76
chore: generate
2026-01-24 05:12:45 +00:00
1d09343f17
fix: allow gpt-5.1-codex model in codex auth pluginFixes ( #10181 )
2026-01-24 00:11:54 -05:00
4173adf5e2
feat(tasks): Add model info as part of metadata ( #10307 )
2026-01-24 00:10:40 -05:00
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
8a216a6ad5
fix(app): normalize path separators for session diff filtering on Windows ( #10291 )
2026-01-23 16:17:47 -06:00
225b72ca36
feat: always center selected item in selection dialogs ( resolves #10209 ) ( #10207 )
2026-01-23 11:59:39 -06:00
c4d223eb99
perf(app): faster workspace creation
2026-01-23 05:18:42 -06:00
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
510f595e25
fix(tui): add weight to fuzzy search to maintain title priority ( #10106 )
2026-01-22 16:15:11 -06:00
3eaf6f3baf
fix(ui): show file path in apply_patch request permission screen ( #10079 )
2026-01-22 13:43:11 -06:00
8ebb766470
fix(attach): allow remote --dir ( #8969 )
2026-01-22 13:19:08 -06:00
a96f3d153b
Revert "fix: handle special characters in paths and git snapshot reading logic( #9804 ) ( #9807 )"
...
This reverts commit cf6ad4c407
2026-01-22 10:37:13 -06:00
31f3a508dc
Revert "fix(core): snapshot regression"
...
This reverts commit bb710e9ea1
2026-01-22 10:35:31 -06:00
3b7c347b2e
tweak: bash tool, ensure cat will trigger external_directory perm
2026-01-22 10:26:06 -06:00
29cebd73e5
feat(mcp log): print mcp stderr to opencode log file ( #9982 )
...
Co-authored-by: chuxuan.liang <chuxuan.liang@bytedance.com>
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
2026-01-22 10:02:26 -06:00
e4286ae7a3
fix(codex): write refresh tokens to openai auth ( #10010 ) ( #10011 )
2026-01-22 09:53:09 -06:00
16fad51b5e
feat(app): add workspace startup script to projects
2026-01-22 07:42:56 -06:00
c2844697f3
fix: ensure images are properly returned as tool results
2026-01-21 23:54:44 -06:00
fc0210c2fd
fix(acp): rename setSessionModel to unstable_setSessionModel ( #9940 )
2026-01-21 22:11:09 -06:00
c3415b79fe
fix: correct spelling 'supercedes' to 'supersedes' ( #9935 )
...
Signed-off-by: luojiyin <luojiyin@hotmail.com>
2026-01-21 22:10:40 -06:00
65e267ed3a
feat: Add promptCacheKey for Venice provider ( #9915 )
2026-01-21 20:28:04 -06:00
6d574549bc
fix: include _noop tool in activeTools for LiteLLM proxy compatibility ( #9912 )
2026-01-21 18:46:41 -06:00
19fe3e265a
mark subagent sessions as agent initiated to ensure they dont count against quota (got the ok from copilot team)
2026-01-21 16:33:43 -06:00
936f3ebe95
feat(ui): add gruvbox theme (Web/App) ( #9855 )
2026-01-21 15:34:27 -06:00
c89f6e7ac6
add chat.headers hook, adjust codex and copilot plugins to use it
2026-01-21 15:10:08 -06:00
416aaff488
feat(acp): add session/list and session/fork support ( #7976 )
2026-01-21 14:14:56 -06:00
aa599b4a7d
fix: when dropping unsupported metadata match on providerID/model.id instead of providerID/model.api.id to prevent regression when using legacy model ids (pre-variant)
2026-01-21 13:39:55 -06:00
6f7a1c69a5
tweak: adjust textVerbosity and reasoningEffort defaults to better match codex cli
2026-01-21 13:23:04 -06:00
2a370f8038
feat: implement home directory expansion for permission patterns using `~` and `$HOME` prefixes. ( #9813 )
2026-01-21 12:52:21 -06:00
d9f0287d74
tweak: add back todo list tools for openai models
2026-01-21 12:14:09 -06:00
301e74d953
fix: Persist loaded model and mode on ACP session load ( #9829 )
2026-01-21 12:10:54 -06:00
1820569818
chore(deps): update GitLab packages for better self-hosted instance support ( #9856 )
2026-01-21 11:23:33 -06:00
8df09abb1b
feat: Make the models.dev domain configurable for offline environments ( #9258 )
2026-01-21 11:23:07 -06:00
ab3d412a81
tweak: adjust skill tool description to make it more clear which skills are available
2026-01-21 11:08:28 -06:00
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
bfbcbc8863
feat(formatters): add laravel pint as a `.php` formatter ( #7312 )
2026-01-21 10:31:39 -06:00
fd77d31b49
tweak(session title): change prompt to have the response with user language ( #9847 )
2026-01-21 10:05:09 -06:00
87d91c29e2
fix(app): terminal improvements - focus, rename, error state, CSP ( #9700 )
2026-01-21 06:49:46 -06:00
bb710e9ea1
fix(core): snapshot regression
2026-01-21 06:10:01 -06:00
Aiden Cline