Commit graph

3354 commits

Author SHA1 Message Date
github-actions[bot]
e1a5cef27b changeset version bump 2026-01-24 04:48:32 +00:00
Matt Rubens
4bff2ab191
chore: add changeset for v3.43.0 (#10933) 2026-01-23 23:47:44 -05:00
Hannes Rudolph
b042866ee1
fix: auto-migrate v1 condensing prompt and handle invalid providers on import (#10931) 2026-01-23 22:32:04 -05:00
Michaelzag
4e67357ab5
fix: use json-stream-stringify for pretty-printing MCP config files (#9864)
Co-authored-by: Roo Code <roomote@roocode.com>
2026-01-23 19:19:35 -08:00
rossdonald
dd561142e9
Skip thoughtSignature blocks during markdown export #10199 (#10932) 2026-01-23 19:18:58 -08:00
Hannes Rudolph
a08bd766ff
refactor: remove legacy XML tool calling code (getToolDescription) (#10929)
- Remove getToolDescription() method from MultiSearchReplaceDiffStrategy
- Remove getToolDescription() from DiffStrategy interface
- Remove unused ToolDescription type from shared/tools.ts
- Remove unused eslint-disable directive
- Update test mocks to remove getToolDescription references
- Remove getToolDescription tests from multi-search-replace.spec.ts

Native tools are now defined in src/core/prompts/tools/native-tools/ using
the OpenAI function format. The removed code was dead since XML-style tool
calling was replaced with native tool calling.
2026-01-23 19:13:55 -05:00
Daniel
339f5aad48
fix: convert orphaned tool_results to text blocks after condensing (#10927)
* fix: convert orphaned tool_results to text blocks after condensing

When condensing occurs after assistant sends tool_uses but before user responds,
the tool_use blocks get condensed away. User messages containing tool_results that
reference condensed tool_use_ids become orphaned and get filtered out by
getEffectiveApiHistory, causing user feedback to be lost.

This fix enhances the existing check in addToApiConversationHistory to detect when
the previous effective message is not an assistant and converts any tool_result
blocks to text blocks, preventing them from being filtered as orphans.

The conversion happens at the latest possible moment (message insertion) because:
- Tool results are created before we know if condensing will occur
- We need actual effective history state to make the decision
- This is the last checkpoint before orphan filtering happens

* Only include environment details in summary for automatic condensing

For automatic condensing (during attemptApiRequest), environment details
are included in the summary because the API request is already in progress
and the next user message won't have fresh environment details injected.

For manual condensing (via condenseContext button), environment details
are NOT included because fresh details will be injected on the very next
turn via getEnvironmentDetails() in recursivelyMakeClineRequests().

This uses the existing isAutomaticTrigger flag to differentiate behavior.

---------

Co-authored-by: Hannes Rudolph <hrudolph@gmail.com>
2026-01-23 19:04:36 -05:00
Hannes Rudolph
526488e5b6
chore: remove MULTI_FILE_APPLY_DIFF experiment (#10925)
* chore: remove MULTI_FILE_APPLY_DIFF experiment

Remove the 'Enable concurrent file edits' experimental feature that
allowed editing multiple files in a single apply_diff call.

- Remove multiFileApplyDiff from experiment types and config
- Delete MultiFileSearchReplaceDiffStrategy class and tests
- Delete MultiApplyDiffTool wrapper and tests
- Remove experiment-specific code paths in Task.ts, generateSystemPrompt.ts, and presentAssistantMessage.ts
- Remove special handling in ExperimentalSettings.tsx
- Remove translations from all 18 locale files

The existing MultiSearchReplaceDiffStrategy continues to handle
multiple SEARCH/REPLACE blocks within a single file.

* fix: remove unused EXPERIMENT_IDS/experiments import from Task.ts

Addresses review feedback: removes the unused imports from
src/core/task/Task.ts that were left over after removing the
MULTI_FILE_APPLY_DIFF experiment routing code.
2026-01-23 18:39:24 -05:00
Hannes Rudolph
f7434dec72
chore: remove POWER_STEERING experimental feature (#10926)
- Remove powerSteering from experimentIds array and schema in packages/types
- Remove POWER_STEERING from EXPERIMENT_IDS and experimentConfigsMap
- Remove power steering conditional block from getEnvironmentDetails
- Remove POWER_STEERING entry from all 18 locale settings.json files
- Update related test files to remove power steering references
2026-01-23 18:07:58 -05:00
Daniel
2d2ed15bfb
Remove Merge button from worktrees (#10924)
Co-authored-by: Roo Code <roomote@roocode.com>
2026-01-23 16:55:46 -05:00
Hannes Rudolph
85f42dca83
chore: remove diffEnabled and fuzzyMatchThreshold settings (#10298) 2026-01-23 16:39:08 -05:00
Hannes Rudolph
0ff826d21d
feat(condense): improve condensation with environment details, accurate token counts, and lazy evaluation (#10920) 2026-01-23 13:52:47 -07:00
Hannes Rudolph
cf5d42e1e1
Intelligent Context Condensation v2 (#10873) 2026-01-23 12:33:35 -07:00
github-actions[bot]
f7bf7a4840
Changeset version bump (#10911)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2026-01-22 23:56:42 -05:00
Matt Rubens
f38bac9fe6
Release v3.42.0 (#10910) 2026-01-22 23:52:33 -05:00
Hannes Rudolph
6eb3d5dd0a
chore(prompts): clarify linked SKILL.md file handling (#10907) 2026-01-22 22:32:25 -05:00
Daniel
3ab1d08159
Fix EXT-553: Remove percentage-based progress tracking for worktree file copying (#10905)
* Fix EXT-553: Remove percentage-based progress tracking for worktree file copying

- Removed totalBytes from CopyProgress interface
- Removed Math.min() clamping that caused stuck-at-100% issue
- Changed UI from progress bar to spinner with activity indicator
- Shows 'item — X MB copied' instead of percentage
- Updated all 18 locale files
- Uses native cp with polling (no new dependencies)

* fix: translate copyingProgress text in all 17 non-English locale files

---------

Co-authored-by: Roo Code <roomote@roocode.com>
2026-01-22 21:17:16 -05:00
Hannes Rudolph
9d65772d24
fix(condense): remove custom condensing model option (#10901)
* fix(condense): remove custom condensing model option

Remove the ability to specify a different model/API configuration for
condensing conversations. Modern conversations include provider-specific
data (tool calls, reasoning blocks, thought signatures) that only the
originating model can properly understand and summarize.

Changes:
- Remove condensingApiHandler parameter from summarizeConversation()
- Remove condensingApiConfigId from context management and Task
- Remove API config dropdown for CONDENSE in settings UI
- Update telemetry to remove usedCustomApiHandler parameter
- Update related tests

Users can still customize the CONDENSE prompt text; only model selection
is removed.

* fix: remove condensingApiConfigId from types and test fixtures

---------

Co-authored-by: Roo Code <roomote@roocode.com>
2026-01-22 20:06:04 -05:00
Daniel
f98dc1389e
feat: hide worktree feature from menus (#10899) 2026-01-22 17:35:21 -05:00
Hannes Rudolph
be0e8c2665
chore: clean up XML legacy code and native-only comments (#10900) 2026-01-22 15:56:11 -05:00
roomote[bot]
f6006c998d
Fix: Enforce file restrictions for all editing tools (#10896)
Co-authored-by: Roo Code <roomote@roocode.com>
2026-01-22 14:17:42 -05:00
Chris Estreich
13e090ef81
fix: prevent task abortion when resuming via IPC/bridge (#10892) 2026-01-22 02:31:51 -08:00
Matt Rubens
94459adba1
Open the worktreeinclude file after creating it (#10891)
Co-authored-by: roomote[bot] <219738659+roomote[bot]@users.noreply.github.com>
2026-01-22 03:22:45 -05:00
Hannes Rudolph
1feefb6f43
fix(openai): prevent double emission of text/reasoning in native and codex handlers (#10888) 2026-01-22 01:22:29 -05:00
Daniel
971885d8e7
feat: add size-based progress tracking for worktree file copying (#10871) 2026-01-21 22:53:12 -05:00
MP
d87abe8efc
feat(web): redesign Slack page Featured Workflow section with YouTube… (#10880)
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
Co-authored-by: Roo Code <roomote@roocode.com>
2026-01-21 22:47:42 -05:00
Hannes Rudolph
5e0bb5af26
refactor: unify export path logic and default to Downloads (#10882) 2026-01-21 21:34:48 -05:00
Hannes Rudolph
3f332d8e2b
refactor: migrate context condensing prompt to customSupportPrompts and cleanup legacy code (#10881) 2026-01-21 21:33:46 -05:00
Daniel
7f854c0dd7
feat: remove Claude Code provider (#10883) 2026-01-21 21:32:56 -05:00
Hannes Rudolph
8de9337e63
chore: remove XML tool calling support (#10841)
Co-authored-by: daniel-lxs <ricciodaniel98@gmail.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2026-01-20 20:25:08 -05:00
Chris Estreich
04256be956
Git worktree management (#10458)
Co-authored-by: Roo Code <roomote@roocode.com>
Co-authored-by: Hannes Rudolph <hrudolph@gmail.com>
Co-authored-by: daniel-lxs <ricciodaniel98@gmail.com>
2026-01-20 13:39:24 -08:00
Hannes Rudolph
06039400cd
perf(webview): avoid resending taskHistory in state updates (#10842)
Co-authored-by: roomote[bot] <219738659+roomote[bot]@users.noreply.github.com>
2026-01-19 21:22:32 -07:00
Hannes Rudolph
1a1827d806
feat(openai-codex): add ChatGPT subscription usage limits dashboard (#10813) 2026-01-19 11:55:40 -07:00
roomote[bot]
0f08867656
refactor: unify user content tags to <user_message> (#10723)
Co-authored-by: Roo Code <roomote@roocode.com>
2026-01-18 22:04:00 -05:00
roomote[bot]
a148862a06
feat: warn users when too many MCP tools are enabled (#10772)
* feat: warn users when too many MCP tools are enabled

- Add WarningRow component for displaying generic warnings with icon, title, message, and optional docs link
- Add TooManyToolsWarning component that shows when users have more than 40 MCP tools enabled
- Add MAX_MCP_TOOLS_THRESHOLD constant (40)
- Add i18n translations for the warning message
- Integrate warning into ChatView to display after task header
- Add comprehensive tests for both components

Closes ROO-542

* Moves constant to the right place

* Move it to the backend

* i18n

* Add actionlink that takes you to MCP settings in this case

* Add to MCP settings too

* Bump max tools up to 60 since github itself has 50+

* DRY

* Fix test

---------

Co-authored-by: Roo Code <roomote@roocode.com>
Co-authored-by: Bruno Bergher <bruno@roocode.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2026-01-18 09:22:09 -05:00
github-actions[bot]
719e6cb35b
Changeset version bump (#10823)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2026-01-18 08:05:06 -05:00
github-actions[bot]
c1f7099698
Changeset version bump (#10790)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2026-01-16 18:03:24 -05:00
Daniel
95be704ebf
fix(litellm): detect Gemini models with space-separated names for thought signature injection (#10787) 2026-01-16 17:43:51 -05:00
roomote[bot]
c40c882561
fix: add openai-codex to providers that don't require API key (#10786)
Co-authored-by: Roo Code <roomote@roocode.com>
2026-01-16 17:13:50 -05:00
Hannes Rudolph
9533f0be3c
fix(openai-codex): reset invalid model selection (#10777) 2026-01-16 14:55:01 -07:00
Bruno Bergher
9bf7173725
feat: add button to open markdown in VSCode preview (#10773)
Co-authored-by: Roo Code <roomote@roocode.com>
2026-01-16 10:56:19 -05:00
github-actions[bot]
8b9f02aa0d
Changeset version bump (#10768)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2026-01-16 00:48:45 -05:00
Daniel
ddac338fdd
fix: Gemini thought signature validation errors (#10694)
Co-authored-by: Roo Code <roomote@roocode.com>
2026-01-15 23:25:42 -05:00
Daniel
e34d93e2cb
fix: truncate call_id to 64 chars for OpenAI Responses API (#10763) 2026-01-15 23:09:54 -05:00
Daniel
bbb6a6e4b4
fix: prevent duplicate tool_use IDs causing API 400 errors (#10760) 2026-01-15 23:08:21 -05:00
Daniel
df42655fc9
fix: flatten top-level anyOf/oneOf/allOf in MCP tool schemas (#10726) 2026-01-15 23:05:00 -05:00
Daniel
3a884ee01e
fix: filter out empty text blocks from user messages for Gemini compatibility (#10728) 2026-01-15 23:03:16 -05:00
Daniel
bbf3196837
fix: filter Ollama models without native tool support (#10735) 2026-01-15 23:01:25 -05:00
T
f48ea389df
Feat/issue 5376 aggregate subtask costs (#10757) 2026-01-15 16:44:55 -05:00
Hannes Rudolph
f2b16d400d
fix: handle missing tool identity in OpenAI Native streams (#10719) 2026-01-15 11:42:34 -07:00