Commit graph

7023 commits

Author SHA1 Message Date
Hannes Rudolph
1370cb04f7
fix: use foreground color for context-management icons (#9912) 2025-12-08 08:17:47 -07:00
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
roomote[bot]
946fd0390f
feat: change defaultToolProtocol default from xml to native (#9892)
* feat: change defaultToolProtocol to default to native instead of xml

* fix: add missing getMcpHub mock to Subtask Rate Limiting tests

---------

Co-authored-by: Roo Code <roomote@roocode.com>
2025-12-06 11:51:16 -05:00
Matt Rubens
2eae32104e
Default to using native tools when supported on openrouter (#9878) 2025-12-05 23:01:33 -05:00
Matt Rubens
4a5cbcba86
Stop making count_tokens requests (#9884) 2025-12-05 22:53:35 -05:00
Daniel
dd92453276
refactor: decouple tools from system prompt (#9784) 2025-12-05 16:26:47 -05:00
Hannes Rudolph
9d5eca92aa
Update xAI models catalog (#9872) 2025-12-05 16:21:59 -05:00
Hannes Rudolph
9f4dcfc0e6
fix: sanitize removed/invalid API providers to prevent infinite loop (#9869) 2025-12-05 16:03:19 -05:00
Bruno Bergher
d285d01853
web: Product pages (#9865)
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
Co-authored-by: roomote[bot] <219738659+roomote[bot]@users.noreply.github.com>
2025-12-05 14:01:41 -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
Chris Estreich
5c501600cd
Better error logs for parseToolCall exceptions (#9857) 2025-12-04 23:06:58 -08:00
github-actions[bot]
65c750d1be
Changeset version bump (#9856)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2025-12-05 01:07:34 -05:00
Matt Rubens
1b151c0c26
Release v3.36.2 (#9855) 2025-12-05 01:03:48 -05:00
Chris Estreich
6bdefb8de3
Fix chutes model fetching (#9854) 2025-12-05 00:57:06 -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
github-actions[bot]
247bf017e0
Changeset version bump (#9840)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2025-12-04 22:44:20 -05:00
Matt Rubens
39a549f056
Release v3.36.1 (#9851) 2025-12-04 22:39:24 -05:00
Matt Rubens
3e3fa327e9
Delete .changeset/symlink-commands.md 2025-12-04 22:38:58 -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
Daniel
9f111e174b
fix: handle unknown/invalid native tool calls to prevent extension freeze (#9834) 2025-12-04 22:21:09 -05:00
Matt Rubens
79458600aa
Revert "Exclude the ID from Roo reasoning details" (#9850) 2025-12-04 22:16:01 -05:00
Hannes Rudolph
c10d1d9ffc
feat(web-evals): add multi-model launch and UI improvements (#9845)
Co-authored-by: Roo Code <roomote@roocode.com>
2025-12-04 20:48:38 -05:00
Hannes Rudolph
630c8bce90
FIX + feat: add MessageManager layer for centralized history coordination (#9842) 2025-12-04 20:48:31 -05:00
Hannes Rudolph
a1d392f5cc
fix: prevent cascading truncation loop by only truncating visible messages (#9844) 2025-12-04 20:41:49 -05:00
Matt Rubens
581256dec0
Exclude the ID from Roo reasoning details (#9847) 2025-12-04 20:40:27 -05:00
Matt Rubens
b9e2fd16b7
Revert "fix: sanitize reasoning_details IDs to remove invalid characters" (#9846) 2025-12-04 20:16:58 -05:00
John Richmond
c719117fb4
Be safer about large file reads (#9843)
validateFileTokenBudget wasn't being called considering
the output budget.
2025-12-04 13:35:26 -08:00
Hannes Rudolph
8433eafb05
feat(evals-ui): Add filtering, bulk delete, tool consolidation, and run notes (#9837) 2025-12-04 14:28:37 -07:00
Daniel
ae655c5d29
fix: sanitize reasoning_details IDs to remove invalid characters (#9839) 2025-12-04 15:53:10 -05:00
Matt Rubens
63f6fecb1a
feat: add symlink support for slash commands in .roo/commands folder (#9838)
Co-authored-by: Roo Code <roomote@roocode.com>
2025-12-04 15:41:10 -05:00
Hannes Rudolph
61aabe715c
ChatView: smoother stick-to-bottom during streaming (#8999) 2025-12-04 14:38:17 -05:00
Chris Estreich
ffff38be2c
Always enabled reasoning for models that require it (#9836) 2025-12-04 10:52:47 -08:00
Bruno Bergher
29385e01d7
fix: Overly round follow-up question suggestions (#9829)
Not that rounded
2025-12-04 16:31:04 +00:00
Matt Rubens
3178113402
Ignore input to the execa terminal process (#9827) 2025-12-04 10:55:58 -05:00
Bruno Bergher
0ed5f3ccd4
web: New Pricing Page (#9821)
* Removes Pro, restructures pricing page

* Solves provider/credits

* Update apps/web-roo-code/src/app/pricing/page.tsx

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

* Updates agent landing pages to not mention a trial that doesn't exist

* Updates agent-specific landing pages to reflect new home and trial

* Indicate the agent landing page the user came from

* Clean up the carousel

---------

Co-authored-by: roomote[bot] <219738659+roomote[bot]@users.noreply.github.com>
2025-12-04 15:40:07 +00:00
Bruno Bergher
0eddc97d13
ux: improved error messages and documentation links (#9777)
* Minor ui tweaks

* Basic setup for richer API request errors

* Better errors messages and contact link

* i18n

* Update webview-ui/src/i18n/locales/en/chat.json

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

* Update webview-ui/src/i18n/locales/en/chat.json

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

* Empty better than null

* Update webview-ui/src/i18n/locales/nl/chat.json

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

* i18n

* Start retryAttempt at 1

* Reverse retryAttempt number, just ommit it from the message

---------

Co-authored-by: roomote[bot] <219738659+roomote[bot]@users.noreply.github.com>
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
2025-12-04 15:25:23 +00:00
github-actions[bot]
7df268ce48
Changeset version bump (#9828)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2025-12-04 09:22:15 -05:00
Matt Rubens
a698875315
Release v3.36.0 (#9814) 2025-12-04 09:17:33 -05:00
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
Matt Rubens
573cfc31fd
Default to native tools for all models in the Roo provider (#9811)
Co-authored-by: Roo Code <roomote@roocode.com>
2025-12-04 00:40:53 -05:00
Matt Rubens
d065b881e3
Fix the download count on the homepage (#9807) 2025-12-03 23:46:00 -05:00
John Richmond
72a6805b4b
Update next.js (#9799) 2025-12-03 20:17:28 -08:00
Hannes Rudolph
837ce3f334
chore: hide parallel tool calls experiment and disable feature (#9798) 2025-12-03 17:07:13 -07:00
roomote[bot]
ec551b1ae0
feat: add reasoning_details support to Roo provider (#9796)
- Add currentReasoningDetails accumulator to track reasoning details
- Add getReasoningDetails() method to expose accumulated details
- Handle reasoning_details array format in streaming responses
- Accumulate reasoning details by type-index key
- Support reasoning.text, reasoning.summary, and reasoning.encrypted types
- Maintain backward compatibility with legacy reasoning format
- Follows same pattern as OpenRouter provider

Co-authored-by: Roo Code <roomote@roocode.com>
2025-12-03 18:47:21 -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
Chris Estreich
1879200964
Fix Vercel AI Gateway model fetching (#9791)
Co-authored-by: Roo Code <roomote@roocode.com>
2025-12-03 11:46:15 -08:00
roomote[bot]
86edc01cb1
fix: remove omission detection logic to fix false positives (#9787)
Co-authored-by: Roo Code <roomote@roocode.com>
2025-12-03 13:20:22 -05:00