Commit graph

485 commits

Author SHA1 Message Date
Daniel
fda020a418
fix: filter out 429 rate limit errors from API error telemetry (#9987)
Co-authored-by: Roo Code <roomote@roocode.com>
Co-authored-by: cte <cestreich@gmail.com>
2025-12-10 11:32:00 -08:00
Daniel
24eb6ae984
feat: add API error telemetry to OpenRouter provider (#9953)
Co-authored-by: Roo Code <roomote@roocode.com>
2025-12-09 16:30:29 -08:00
Matt Rubens
ada7411cd3
Tweaks to baseten model definitions (#9866) 2025-12-09 16:17:52 -08:00
Matt Rubens
721b02e58c
Add a way to save screenshots from the browser tool (#9963)
* Add a way to save screenshots from the browser tool

* fix: use cross-platform paths in BrowserSession screenshot tests

* fix: validate screenshot paths to prevent filesystem escape

---------

Co-authored-by: Roo Code <roomote@roocode.com>
2025-12-09 16:12:36 -08:00
Hannes Rudolph
1898848d95
feat(deepseek): update DeepSeek models to V3.2 with new pricing (#9962)
Co-authored-by: roomote[bot] <219738659+roomote[bot]@users.noreply.github.com>
2025-12-09 15:46:04 -08:00
Hannes Rudolph
83787a76ef
feat(roo): add versioned settings support with minPluginVersion gating (#9934) 2025-12-09 12:54:15 -08:00
Bruno Bergher
8a98f140dc
feat: Make Architect save to /plans and gitignore it (#9944)
Co-authored-by: roomote[bot] <219738659+roomote[bot]@users.noreply.github.com>
Co-authored-by: Roo Code <roomote@roocode.com>
2025-12-09 06:51:43 -08:00
Hannes Rudolph
c103a4a639
feat: streaming tool stats + token usage throttling (#9926)
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2025-12-08 19:40:12 -08:00
roomote[bot]
54a52655ac
feat: forbid time estimates in architect mode (#9931)
Co-authored-by: Roo Code <roomote@roocode.com>
2025-12-08 19:06:07 -08:00
Hannes Rudolph
754b701cc8
feat: configure tool preferences for xAI models (#9923) 2025-12-08 11:33:55 -08:00
Hannes Rudolph
fba8508b10
feat: add search_replace native tool for single-replacement operations (#9918)
Adds a new search_replace tool that performs a single search and replace
operation on a file, requiring the old_string to uniquely identify the
target text with 3-5 lines of context.

Parameters:
- file_path: Path to file (relative or absolute)
- old_string: Text to find (must be unique in file)
- new_string: Replacement text (must differ from old_string)
2025-12-08 10:45:55 -08:00
Andrew Ginns
efbf427631
feat: add xhigh reasoning effort for gpt-5.1-codex-max (#9900)
* feat: add xhigh reasoning effort for gpt-5.1-codex-max

* fix: Address openai-native.spec.ts test failure

* chore: Localisation of 'Extra high'

* chore: revert unrelated CustomModesManager refactoring

---------

Co-authored-by: Hannes Rudolph <hrudolph@gmail.com>
2025-12-08 10:17:25 -08:00
roomote[bot]
bea7626a9d
fix: add Kimi, MiniMax, and Qwen model configurations for Bedrock (#9905)
* fix: add Kimi, MiniMax, and Qwen model configurations for Bedrock

- Add moonshot.kimi-k2-thinking with 32K max tokens and 256K context
- Add minimax.minimax-m2 with 16K max tokens and 230K context
- Add qwen.qwen3-next-80b-a3b with 8K max tokens and 262K context
- Add qwen.qwen3-coder-480b-a35b-v1:0 with 8K max tokens and 262K context

All models configured with native tool support and appropriate pricing.

Fixes #9902

* fix: add preserveReasoning flag and update Kimi K2 context window

- Added preserveReasoning: true to moonshot.kimi-k2-thinking model
- Added preserveReasoning: true to minimax.minimax-m2 model
- Updated Kimi K2 context window from 256_000 to 262_144

These changes ensure:
1. Reasoning traces are properly preserved for both models
2. Roo correctly recognizes task completion
3. Tool calls within reasoning traces are handled appropriately
4. Context window matches AWS Console specification

* fix: update MiniMax M2 context window to 196_608 for Bedrock

Based on AWS CLI testing, the actual context window limit for MiniMax M2
on Bedrock is 196,608 tokens, not 230,000 as initially configured.

* Update packages/types/src/providers/bedrock.ts

Co-authored-by: roomote[bot] <219738659+roomote[bot]@users.noreply.github.com>

---------

Co-authored-by: Roo Code <roomote@roocode.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
Co-authored-by: roomote[bot] <219738659+roomote[bot]@users.noreply.github.com>
2025-12-08 10:16:43 -05:00
Matt Rubens
1f7e1ee630
Make eval runs deleteable (#9909) 2025-12-07 23:30:28 -05:00
Hannes Rudolph
8aa13467d3
Refactor: Unified context-management architecture with improved UX (#9795)
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
2025-12-07 17:43:48 -05:00
Hannes Rudolph
9d5eca92aa
Update xAI models catalog (#9872) 2025-12-05 16:21:59 -05:00
Alex Ker
642a187030
(update): Add DeepSeek V3-2 Support for Baseten Provider (#9861)
Co-authored-by: AlexKer <AlexKer@users.noreply.github.com>
2025-12-05 12:11:08 -05:00
Hannes Rudolph
e633c62e70
chore: restrict gpt-5 tool set to apply_patch (#9853) 2025-12-05 00:35:45 -05:00
Hannes Rudolph
a3de2935b3
feat: add dynamic settings support for Roo models from API (#9852) 2025-12-04 23:57:00 -05:00
Hannes Rudolph
bea7d81510
feat: add gpt-5.1-codex-max model to OpenAI provider (#9848) 2025-12-04 22:30:07 -05:00
Hannes Rudolph
8433eafb05
feat(evals-ui): Add filtering, bulk delete, tool consolidation, and run notes (#9837) 2025-12-04 14:28:37 -07:00
Seb Duerr
94c997c9d6
Fix/cerebras conservative max tokens (#9804)
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2025-12-04 00:43:22 -05:00
Daniel
ce229012a3
refactor: remove insert_content tool (#9751)
Co-authored-by: Roo Code <roomote@roocode.com>
2025-12-03 16:33:22 -05:00
Hannes Rudolph
23605bed93
fix: restore context when rewinding after condense (#8295) (#9665) 2025-12-03 11:40:39 -05:00
SannidhyaSah
873a763ea7
feat: Add provider routing selection for OpenRouter embeddings (#9144) (#9693)
Co-authored-by: Sannidhya <sann@Sannidhyas-MacBook-Pro.local>
2025-12-02 22:59:55 -05:00
roomote[bot]
9a1d7a673b
fix: remove reasoning toggles for GLM-4.5 and GLM-4.6 on z.ai provider (#9752)
Co-authored-by: Roo Code <roomote@roocode.com>
2025-12-02 14:20:48 -05:00
Matt Rubens
aa507ad990
Add vendor confidentiality section to the system prompt for stealth models (#9742)
Co-authored-by: roomote[bot] <219738659+roomote[bot]@users.noreply.github.com>
2025-12-02 10:23:54 -05:00
Matt Rubens
d2b274a9af
Allow models to contain default temperature (#9734) 2025-12-01 23:29:42 -05:00
Chris Estreich
3f4f7c0c41
Better IPC error logging (#9727) 2025-12-01 15:02:34 -08:00
Chris Estreich
9b18014b4b
chore: bump version to v1.89.0 (#9718) 2025-12-01 14:25:48 -08:00
Daniel
ad28e12818
feat: add native tool support for LiteLLM provider (#9719) 2025-12-01 16:35:08 -05:00
Matt Rubens
be7659461a
Support tool calling in native ollama provider (#9696)
Co-authored-by: Roo Code <roomote@roocode.com>
2025-12-01 15:28:01 -05:00
Matt Rubens
faa6c40ac1
Bedrock native tool calling (#9698) 2025-12-01 15:26:34 -05:00
Matt Rubens
eb120543e1
Add native tools support to Unbound (#9699)
Co-authored-by: Roo Code <roomote@roocode.com>
2025-12-01 14:50:01 -05:00
Matt Rubens
0a2d1a41e4
Add NTC support for Cerebras (#9692) 2025-12-01 14:49:53 -05:00
Matt Rubens
48d3e4d2e8
Release: v1.88.0 (#9713) 2025-12-01 10:47:24 -05:00
Matt Rubens
75903052ae
Update a couple provider labels (#9711)
Co-authored-by: Roo Code <roomote@roocode.com>
2025-12-01 10:44:12 -05:00
Bruno Bergher
49aad8576e
ux: Toolbar cleanup and settings consolidation (#9710)
Co-authored-by: Roo Code <roomote@roocode.com>
2025-12-01 09:43:15 -05:00
Matt Rubens
4591e960ed
Add native tool calling for deepinfra (#9691) 2025-11-29 20:05:21 -05:00
Matt Rubens
ae29777062
Add Grok 4 Fast and Grok 4.1 Fast, plus xAI native tool calling (#9690)
* Add Grok 4 Fast and Grok 4.1 Fast

* Add native tool calling support
2025-11-29 19:41:42 -05:00
Hannes Rudolph
d2017c80cf
Add web-evals updates and kill run functionality (#9681)
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
Co-authored-by: Roo Code <roomote@roocode.com>
2025-11-29 13:08:56 -07:00
Hannes Rudolph
933534896a
feat: add apply_patch native tool (#9663)
Co-authored-by: daniel-lxs <ricciodaniel98@gmail.com>
2025-11-28 23:07:03 -05:00
Daniel
127ecf6ddd
feat: enable native tool calls for Vertex Gemini models (#9678)
Add supportsNativeTools: true to all Gemini-based models in the Vertex
provider. The VertexHandler extends GeminiHandler which already has full
native tool handling logic implemented.

Models updated:
- gemini-3-pro-preview
- gemini-2.5-flash-preview-05-20:thinking
- gemini-2.5-flash-preview-05-20
- gemini-2.5-flash
- gemini-2.5-flash-preview-04-17:thinking
- gemini-2.5-flash-preview-04-17
- gemini-2.5-pro-preview-03-25
- gemini-2.5-pro-preview-05-06
- gemini-2.5-pro-preview-06-05
- gemini-2.5-pro
- gemini-2.5-pro-exp-03-25
- gemini-2.0-pro-exp-02-05
- gemini-2.0-flash-001
- gemini-2.0-flash-lite-001
- gemini-2.0-flash-thinking-exp-01-21
- gemini-1.5-flash-002
- gemini-1.5-pro-002
- gemini-2.5-flash-lite-preview-06-17
2025-11-28 13:48:55 -05:00
Daniel
59ee1c9d04
feat: add native tools support for OpenAI-compatible providers (#9676)
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2025-11-28 11:59:32 -05:00
Daniel
5d020991bd
feat(groq): enable native tool support for models that support function calling (#9673)
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2025-11-28 11:02:34 -05:00
Daniel
b111d125c0
feat: enable native tool support for DeepSeek and Doubao models (#9671)
Add supportsNativeTools: true to DeepSeek and Doubao model definitions,
enabling native OpenAI-compatible tool calling for these providers.

Both providers already extend OpenAiHandler which has built-in support
for native tools, so this change is all that's needed to enable the feature.
2025-11-28 10:38:03 -05:00
Hannes Rudolph
e682c039de
feat: add search_and_replace tool for batch text replacements (#9549)
Co-authored-by: daniel-lxs <ricciodaniel98@gmail.com>
2025-11-27 21:19:10 -07:00
Hannes Rudolph
9b5f6392df
Metadata‑driven subtasks (no UI changes): automatic parent resume and single‑open safety (#9090) 2025-11-27 21:18:42 -07:00
Hannes Rudolph
3f0a6971ca
feat(web-evals): add task log viewing, export failed logs, and new run options (#9637)
Co-authored-by: roomote[bot] <219738659+roomote[bot]@users.noreply.github.com>
2025-11-27 21:15:31 -07:00
Daniel
5a6dd58fcb
feat: add model-specific tool customization via excludedTools and includedTools (#9641)
* feat: add model-specific tool customization via excludedTools and includedTools

- Add excludedTools and includedTools to ModelInfo schema
- Implement applyModelToolCustomization helper to filter tools based on model config
- Integrate model tool filtering into filterNativeToolsForMode for native protocol
- Add comprehensive tests for tool customization functionality
- Wire up modelInfo through buildNativeToolsArray and Task.ts

This allows providers to override which native tools are available on a per-model basis via MODEL_DEFAULTS, enabling better control over tool selection for models with specific needs.

* feat: add customTools for opt-in only tools

- Add customTools array to ToolGroupConfig for defining opt-in only tools
- Update getToolsForMode() to exclude customTools from default tool set
- Modify applyModelToolCustomization() to include customTools only via includedTools
- Add tests for customTools functionality
- Add comprehensive documentation with usage examples

customTools allows defining tools that are NOT available by default,
even when a mode includes their group. These tools are only available
when explicitly included via a model's includedTools configuration.

This enables:
- Gradual rollout of experimental tools
- Model-specific specialized capabilities
- Safe experimentation without affecting default tool sets

* Add assertions for customTools tests per review feedback

* test: add tests for including customTools via includedTools

* Update src/core/prompts/tools/__tests__/filter-tools-for-mode.spec.ts

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>

---------

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
2025-11-27 13:45:32 -05:00