Commit graph

6767 commits

Author SHA1 Message Date
Roo Code
64f704ad54 fix: resolve React Compiler i18n caching issues in ChatView
Fixes partial internationalization failures caused by React Compiler
aggressively caching translated values.

Changes:
- TranslationContext: Add i18n.language to translate callback dependency
  to force re-memoization when language changes
- ChatView: Store translation keys instead of translated button text
  in state, compute translations at render time
- ChatView: Remove redundant useState type annotations that may confuse
  React Compiler type inference
- ChatView: Simplify button tooltip rendering by using pre-computed
  tooltip values from key mappings

Closes #11100
2026-01-30 04:49:38 +00:00
Hannes Rudolph
cc86049f10
refactor(read_file): Codex-inspired read_file refactor EXT-617 (#10981) 2026-01-29 15:16:32 -07:00
Daniel
0f43cc9814
feat: migrate Cerebras provider to AI SDK (#11086) 2026-01-29 17:07:59 -05:00
Daniel
4b1d78fe0a
feat: migrate DeepSeek to @ai-sdk/deepseek + fix AI SDK tool streaming (#11079) 2026-01-29 15:56:51 -05:00
Hannes Rudolph
f848795775
refactor: replace fetch_instructions with skill tool and built-in skills (#11084)
Co-authored-by: Roo Code <roomote@roocode.com>
2026-01-29 12:47:36 -07:00
Hannes Rudolph
0c53f1937a
Revert "refactor: replace fetch_instructions with skill tool and built-in skills" (#11083) 2026-01-29 11:46:58 -07:00
Hannes Rudolph
67e568f6bb
refactor: replace fetch_instructions with skill tool and built-in skills (#10913) 2026-01-29 07:48:08 -07:00
Matt Rubens
40b2bdc4d0
Revert "feat(vscode-lm): add image support for VS Code LM API provider" (#11068) 2026-01-29 01:41:20 -05:00
roomote[bot]
49aac7ea00
feat(vscode-lm): add image support for VS Code LM API provider (#11065)
Co-authored-by: Roo Code <roomote@roocode.com>
Co-authored-by: Hannes Rudolph <hrudolph@gmail.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2026-01-29 01:34:09 -05:00
Alik Aslanyan
31bed9cebe
Add React Compiler integration to webview-ui (#9565) 2026-01-29 01:32:27 -05:00
Daniel
8d38e60187
feat: Add OpenAI-compatible base provider and migrate Moonshot to AI SDK (#11063) 2026-01-29 01:29:33 -05:00
Daniel
ed35b09aad
Enable parallel tool calls by default (#11031) 2026-01-29 01:29:15 -05:00
SannidhyaSah
010aba24b7
feat: add skills management UI to settings panel (#10513) (#10844)
Co-authored-by: Sannidhya <sann@Sannidhyas-MacBook-Pro.local>
Co-authored-by: daniel-lxs <ricciodaniel98@gmail.com>
Co-authored-by: Roo Code <roomote@roocode.com>
2026-01-29 01:25:36 -05:00
roomote[bot]
c983e26280
feat(marketing): add Linear integration page (#11028)
Co-authored-by: Roo Code <roomote@roocode.com>
Co-authored-by: Michael Preuss <michael@roocode.com>
2026-01-28 16:06:08 -08:00
Hannes Rudolph
d7fa963b13
docs: clarify read_command_output search param should be omitted when not filtering (#11056) 2026-01-28 13:30:01 -07:00
roomote[bot]
8640fd1472
fix: calculate header percentage based on available input space (#11054)
Co-authored-by: Roo Code <roomote@roocode.com>
2026-01-28 15:29:34 -05:00
Daniel
fe722dad23
feat: add AI SDK dependencies and message conversion utilities (#11047) 2026-01-28 14:05:53 -05:00
Daniel
f5004ac40a
fix: prevent time-travel bug in parallel tool calling (#11046) 2026-01-28 13:25:02 -05:00
Hannes Rudolph
e7965d9b45
feat: lossless terminal output with on-demand retrieval (#10944) 2026-01-27 22:12:19 -07:00
roomote[bot]
a44842f16f
fix: include reserved output tokens in task header percentage calculation (#11034)
Co-authored-by: Roo Code <roomote@roocode.com>
2026-01-27 23:37:48 -05:00
github-actions[bot]
c6d0306550
Changeset version bump (#11037)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2026-01-27 23:05:16 -05:00
Matt Rubens
7632807021
Release v3.45.0 (#11036) 2026-01-27 22:59:23 -05:00
Hannes Rudolph
d748de6fae
feat(condense v2.1): add smart code folding (#10942)
* feat(condense): add smart code folding with tree-sitter signatures

At context condensation time, use tree-sitter to generate folded code
signatures (function definitions, class declarations) for files read
during the conversation. Each file is included as its own <system-reminder>
block in the condensed summary, preserving structural awareness without
consuming excessive tokens.

- Add getFilesReadByRoo() method to FileContextTracker
- Create generateFoldedFileContext() using tree-sitter parsing
- Update summarizeConversation() to accept array of file sections
- Each file gets its own content block in the summary message
- Add comprehensive test coverage (12 tests)

* fix: skip tree-sitter error strings in folded file context

- Add isTreeSitterErrorString helper to detect error messages
- Skip files that return error strings instead of embedding them
- Add test for error string handling

* refactor: move generateFoldedFileContext() inside summarizeConversation()

- Update summarizeConversation() to accept filesReadByRoo, cwd, rooIgnoreController instead of pre-generated sections
- Move folded file context generation inside summarizeConversation() (lines 319-339)
- Update ContextManagementOptions type and manageContext() to pass new parameters
- Remove generateFoldedFileContext from Task.ts imports - folding now handled internally
- Update all tests to use new parameter signature
- Reduces Task.ts complexity by moving folding logic to summarization module

* fix: prioritize most recently read files in folded context

Files are now sorted by roo_read_date descending before folded context
generation, so if the character budget runs out, the most relevant
(recently read) files are included and older files are skipped.

* refactor: improve code quality in condense module

- Convert summarizeConversation to use options object instead of 11 positional params
- Extract duplicated getFilesReadByRoo error handling into helper method
- Remove unnecessary re-export of generateFoldedFileContext
- Update all test files to use new options object pattern

* fix: address roomote feedback - batch error logging and early budget exit

---------

Co-authored-by: Roo Code <roomote@roocode.com>
Co-authored-by: daniel-lxs <ricciodaniel98@gmail.com>
2026-01-27 18:47:24 -05:00
github-actions[bot]
7607c684e9
Changeset version bump (#11027)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2026-01-27 15:52:37 -05:00
Matt Rubens
e9043723d3
Release v3.44.2 (#11025) 2026-01-27 15:43:20 -05:00
Daniel
17d3456e96
fix: remove duplicate tool_call emission from Responses API providers (#11008) 2026-01-27 13:33:15 -05:00
Daniel
b9cf163b87
fix: use relative paths in isPathInIgnoredDirectory to fix worktree indexing (#11009) 2026-01-27 12:43:47 -05:00
roomote[bot]
d6d00dedec
Fix local model validation error for Ollama models (#10893)
fix: prevent false validation error for local Ollama models

The validation logic was checking against an empty router models object
that was initialized but never populated for Ollama. This caused false
validation errors even when models existed locally.

Now only validates against router models if they actually contain data,
preventing the false error when using local Ollama models.

Fixes ROO-581

Co-authored-by: Roo Code <roomote@roocode.com>
2026-01-27 16:50:05 +00:00
Matt Rubens
dc5e765e9c
Revert "Revert "Enable parallel tool calling with new_task isolation safeguards"" (#11006) 2026-01-27 10:31:03 -05:00
github-actions[bot]
2078537201
Changeset version bump (#11005)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2026-01-27 10:28:20 -05:00
Matt Rubens
7b54a733e7
Release v3.44.1 (#11003) 2026-01-27 10:22:03 -05:00
Matt Rubens
5b3626f1a6
Revert "Enable parallel tool calling with new_task isolation safeguards" (#11004) 2026-01-27 10:20:12 -05:00
Seb Duerr
6e08ae4bfd
Add temperature=0.9 and top_p=0.95 to zai-glm-4.7 model (#10945)
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2026-01-27 09:57:21 -05:00
MP
5100d15830
Add quality checks to marketing site deployment workflows (#10959)
Co-authored-by: cte <cestreich@gmail.com>
2026-01-27 00:56:30 -08:00
Daniel
2584504b9b
Enable parallel tool calling with new_task isolation safeguards (#10979)
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
Co-authored-by: Hannes Rudolph <hrudolph@gmail.com>
2026-01-27 00:26:49 -05:00
Daniel
f5d32e771a
Fix LiteLLM tool ID validation errors for Bedrock proxy (#10990) 2026-01-26 23:54:48 -05:00
github-actions[bot]
3edf71e29a
Changeset version bump (#10989)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2026-01-26 23:26:46 -05:00
Matt Rubens
826e6da416
chore: add changeset for v3.44.0 (#10987) 2026-01-26 23:19:13 -05:00
roomote[bot]
2391a0f065
fix: use --force by default when deleting worktrees (#10986)
Co-authored-by: Roo Code <roomote@roocode.com>
2026-01-26 23:10:23 -05:00
Hannes Rudolph
2f92cb7a8d
fix: prevent nested condensing from including previously-condensed content (#10985) 2026-01-26 22:34:04 -05:00
Daniel
dd245cc40c
fix: VS Code LM token counting returns 0 outside requests, breaking context condensing (EXT-620) (#10983)
- Modified VsCodeLmHandler.internalCountTokens() to create temporary cancellation tokens when needed
- Token counting now works both during and outside of active requests
- Added 4 new tests to verify the fix and prevent regression
- Resolves issue where VS Code LM API users experienced context overflow errors
2026-01-26 19:43:10 -05:00
Daniel
27708f3038
feat: new_task tool creates checkpoint the same way write_to_file does (#10982) 2026-01-26 17:21:49 -07:00
Hannes Rudolph
bd29766406
fix: record truncation event when condensation fails but truncation succeeds (#10984) 2026-01-26 17:19:27 -07:00
Hannes Rudolph
7534e19c60
chore: remove POWER_STEERING experiment remnants (#10980) 2026-01-26 15:26:47 -07:00
Peter Dave Hello
953c7773c0
Update and improve zh-TW Traditional Chinese locale and docs (#10953) 2026-01-25 07:07:23 -05:00
roomote[bot]
b472c15220
fix: restore opaque background to settings section headers (#10951)
Co-authored-by: Roo Code <roomote@roocode.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2026-01-25 01:49:27 -05:00
roomote[bot]
c28478eda7
feat: add wildcard support for MCP alwaysAllow configuration (#10948)
Co-authored-by: Roo Code <roomote@roocode.com>
2026-01-24 22:42:47 -05:00
Bruno Bergher
c56f0f43c7
ux: improve worktree selector and creation UX (#10940)
* Delete modal

* Restructured

* Much more prominent

* UI

* i18n

* Fixes i18n

* Remove mergeresultmodel

* i18n

* tests

* knip

* code review
2026-01-24 22:06:37 +00:00
roomote[bot]
c7910a99c7
fix(types): remove unsupported Fireworks model tool fields (#10937)
fix(types): remove unsupported tool capability fields from Fireworks model metadata

Co-authored-by: Roo Code <roomote@roocode.com>
2026-01-24 07:39:09 -05:00
Bruno Bergher
5848db66be
ux: Improve subtask visibility and navigation in history and chat views (#10864)
* Taskheader

* Subtask messages

* View subtask

* subtasks in history items

* i18n

* Table

* Lighter visuals

* bug

* fix: Align tests with implementation behavior

* refactor: extract CircularProgress component from TaskHeader

- Created reusable CircularProgress component for displaying percentage as a ring
- Moved inline SVG calculation from TaskHeader.tsx to dedicated component
- Added comprehensive tests for CircularProgress component (14 tests)
- Component supports customizable size, strokeWidth, and className
- Includes proper accessibility attributes (progressbar role, aria-valuenow)

* chore: update StandardTooltip default delay to 600ms

As mentioned in the PR description, increased the tooltip delay to 600ms
for less intrusive tooltips. The delay is still configurable via the
delay prop for components that need a different value.

---------

Co-authored-by: Roo Code <roomote@roocode.com>
2026-01-24 07:21:25 -05:00