scriptoriumadmin/Roo-Code
1
0
Fork 0
mirror of https://github.com/RooVetGit/Roo-Code.git synced 2026-08-28 05:27:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
6184 commits 2166 branches 585 tags 928 MiB
Commit graph

3005 commits

Author SHA1 Message Date
Roo Code
5b3b8c7384 fix: ensure commands require explicit approval when auto-approval is disabled 
- Fixed issue where commands were being auto-executed without user consent
- Added check to ensure BOTH autoApprovalEnabled AND alwaysAllowExecute must be true
- Added comprehensive tests to verify the fix
- Fixes #9606
 2025-11-26 09:47:38 +00:00
github-actions[bot]
3806b3d27d
Changeset version bump (#9604) 
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
 2025-11-26 00:51:15 -05:00
Matt Rubens
3c989d3591
Revert "Add support for Roo Code Cloud as an embeddings provider" (#9602) 2025-11-26 00:08:39 -05:00
Matt Rubens
71e761e21b
Make single file read only apply to xml tools (#9600) 2025-11-26 00:08:00 -05:00
Matt Rubens
0fe55b9403
fix: update API handler when toolProtocol changes (#9599) 2025-11-25 23:54:12 -05:00
Daniel
05f35735f0
feat: enable multiple native tool calls per turn with failure guardrails (#9273) 2025-11-25 20:21:13 -05:00
Daniel
f173c9c2dc
feat: set native tools as default for minimax-m2 and claude-haiku-4.5 (#9586) 2025-11-25 16:24:02 -05:00
github-actions[bot]
37d2f59b2e
Changeset version bump (#9591) 
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
 2025-11-25 15:27:48 -05:00
Matt Rubens
e4847ed8d9
Add support for images api (#9587) 2025-11-25 14:18:14 -05:00
Daniel
311940b085
fix: preserve tool_use blocks in summary message during condensing with native tools (#9582) 2025-11-25 13:17:26 -05:00
Daniel
774b492eff
fix: preserve dynamic MCP tool names in native mode API history (#9559) 2025-11-25 13:16:34 -05:00
github-actions[bot]
86cdbff0a5
Changeset version bump (#9579) 
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
 2025-11-25 10:24:00 -05:00
roomote[bot]
2945b30191
fix: enable caching for Opus 4.5 model (#9568) 
Added claude-opus-4-5-20251101 to the cache control switch statements
to enable prompt caching, matching the behavior of other Claude models.

Fixes #9567

Co-authored-by: Roo Code <roomote@roocode.com>
 2025-11-25 07:15:58 -05:00
Daniel
8949c2f6fe
Fix ask_followup_question streaming issue and add missing tool cases (#9561) 2025-11-25 00:11:16 -05:00
Daniel
0327f12751
feat: implement streaming for native tool calls (#9542) 2025-11-24 23:12:39 -05:00
Matt Rubens
fb4f23537a
Add support for Roo Code Cloud as an embeddings provider (#9543) 2025-11-24 17:21:30 -05:00
github-actions[bot]
1e13533633
Changeset version bump (#9546) 
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
 2025-11-24 17:16:55 -05:00
Daniel
5336246f4d
fix: gracefully skip unsupported content blocks in Gemini transformer (#9537) 
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
 2025-11-24 15:14:21 -05:00
Matt Rubens
a8b366f3dd
Add Roo Code Cloud as an imagegen provider (#9528) 2025-11-24 15:11:35 -05:00
Daniel
a20d047417
fix: flush LiteLLM cache when credentials change on refresh (#9536) 2025-11-24 12:09:50 -05:00
Daniel
3ac5bec3fc
fix: ensure XML parser state matches tool protocol on config update (#9535) 2025-11-24 10:01:29 -05:00
Seb Duerr
becdb1ac1c
feat: update Cerebras models (#9527) 
Co-authored-by: Roo Code <roomote@roocode.com>
 2025-11-24 00:57:40 -05:00
Daniel
b531075626
fix: support reasoning_details format for Gemini 3 models (#9506) 2025-11-24 00:47:25 -05:00
github-actions[bot]
d96f939dca
Changeset version bump (#9523) 
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
 2025-11-23 13:36:31 -05:00
Matt Rubens
1558df65b5
Track cloud synced messages (#9518) 2025-11-23 13:17:26 -05:00
github-actions[bot]
529c686804
Changeset version bump (#9496) 
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
 2025-11-21 23:05:41 -05:00
Matt Rubens
bc0daab6b1
chore: add changeset and announcement for v3.34.0 (#9495) 2025-11-21 23:02:15 -05:00
Daniel
513eebc9a9
Enhance native tool descriptions with examples and clarifications (#9486) 2025-11-21 21:59:54 -05:00
Daniel
f6d3fdfff6
fix: copy model-level capabilities to OpenRouter endpoint models (#9483) 2025-11-21 16:05:26 -07:00
Alex Ker
fa764ba7f1
(feat): Add Baseten Provider (#9461) 
Co-authored-by: roomote[bot] <219738659+roomote[bot]@users.noreply.github.com>
Co-authored-by: AlexKer <AlexKer@users.noreply.github.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
 2025-11-21 17:49:15 -05:00
Matt Rubens
7edc86bb52
Test a provider-oriented welcome screen (#9484) 
Co-authored-by: roomote[bot] <219738659+roomote[bot]@users.noreply.github.com>
 2025-11-21 17:37:30 -05:00
Daniel
1dd223d240
fix: Make cancel button immediately responsive during streaming (#9448) 2025-11-21 17:34:17 -05:00
Daniel
842a4af17c
fix: implement model cache refresh to prevent stale disk cache (#9478) 2025-11-21 17:32:52 -05:00
Daniel
999ea686ab
fix: resolve apply_diff performance regression from PR #9456 (#9474) 2025-11-21 17:31:47 -05:00
Hannes Rudolph
ee93530076
Browser Use 2.0 (#8941) 
Co-authored-by: roomote[bot] <219738659+roomote[bot]@users.noreply.github.com>
Co-authored-by: daniel-lxs <ricciodaniel98@gmail.com>
 2025-11-21 17:26:15 -05:00
Matt Rubens
8472bbb43b
Improvements to base openai compatible (#9462) 
Co-authored-by: Roo Code <roomote@roocode.com>
 2025-11-21 16:42:19 -05:00
Daniel
a65e7807b1
fix: add fallback to yield tool calls regardless of finish_reason (#9476) 2025-11-21 16:04:38 -05:00
github-actions[bot]
038f830bf6
Changeset version bump (#9460) 
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
 2025-11-20 23:23:10 -05:00
Daniel
a49e81f37c
fix: improve search and replace symbol parsing (#9456) 2025-11-20 23:05:14 -05:00
Daniel
905181810e
feat: implement Minimax as Anthropic-compatible provider (#9455) 2025-11-20 22:53:00 -05:00
Daniel
3da6f81fac
fix: improve markdown formatting and add reasoning support (#9458) 2025-11-20 22:52:35 -05:00
Daniel
08027ad4fa
fix: send tool_result blocks for skipped tools in native protocol (#9457) 2025-11-20 22:52:27 -05:00
Daniel
5c5a893b50
Fix preserveReasoning flag to control API reasoning inclusion (#9453) 
* feat: store reasoning in conversation history for all providers

* refactor: address review feedback

- Move comments inside else block
- Combine reasoning checks into single if block
- Make comments more concise

* refactor: make comments more concise

* Fix preserveReasoning flag to control API reasoning inclusion

Changes:
1. Removed hardcoded <think> tag logic in streaming
   - Previously hardcoded reasoning into assistant message text
   - Now passes reasoning to addToApiConversationHistory as parameter

2. Updated buildCleanConversationHistory to respect preserveReasoning flag
   - When preserveReasoning: true → reasoning block included in API requests
   - When preserveReasoning: false/undefined → reasoning stripped from API
   - Reasoning stored in history for all cases

3. Added temporary debug logs to base-openai-compatible-provider.ts
   - Shows preserveReasoning flag value
   - Logs reasoning blocks in incoming messages
   - Logs <think> tags in converted messages sent to API

* Fix: Use api.getModel() directly instead of cachedStreamingModel

Addresses review comment: cachedStreamingModel is set during streaming but
buildCleanConversationHistory is called before streaming starts. Using the
cached value could cause stale model info when switching models between requests.

Now directly uses this.api.getModel().info.preserveReasoning to ensure we
always check the current model's flag, not a potentially stale cached value.

* Clean up comments in Task.ts

Removed outdated comment regarding model's preserveReasoning flag.

* fix: remove unnecessary reasoningBlock variable in task reasoning logic
 2025-11-20 20:31:49 -05:00
Daniel
7715158d51
Store reasoning in conversation history for all providers (#9451) 2025-11-20 19:59:53 -05:00
John Richmond
341863f8cd
Update glob to ^11.1.0 (#9449) 2025-11-20 14:45:02 -08:00
Daniel
97cdc41937
fix: prevent duplicate environment_details when resuming cancelled tasks (#9442) 
- Filter out complete environment_details blocks before appending fresh ones
- Check for both opening and closing tags to ensure we're matching complete blocks
- Prevents stale environment data from being kept during task resume
- Add tests to verify deduplication logic and edge cases
 2025-11-20 17:03:02 -05:00
roomote[bot]
1589cc1849
feat: add Google Gemini 3 Pro Image Preview to image generation models (#9440) 
Co-authored-by: Roo Code <roomote@roocode.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
 2025-11-20 14:19:37 -05:00
Hannes Rudolph
f7d6daedff
Fix OpenAI Native parallel tool calls for native protocol (#9433) 
Fixes an issue where using the OpenAI Native provider together with Native Tool Calling could cause OpenAI’s Responses API to fail with errors like:
 2025-11-20 09:38:33 -07:00
Matt Rubens
1201b0fd8d
Revert "Fix Marketplace crash by removing wildcard activation event" (#9432) 2025-11-20 10:49:41 -05:00
Hannes Rudolph
6a98ffb817
Fix Marketplace crash by removing wildcard activation event (#9423) 2025-11-20 10:29:07 -05:00