openai-native: include reasoning.encrypted_content only when reasoningEffort is set; prevent Responses API error on non-reasoning models. types: remove supportsVerbosity from gpt-5-chat-latest to avoid invalid verbosity error. Fixes#9225
* Migrate conversation continuity to plugin-side encrypted reasoning items (Responses API)
Summary
We moved continuity off OpenAI servers and now maintain conversation state locally by persisting and replaying encrypted reasoning items. Requests are stateless (store=false) while retaining the performance/caching benefits of the Responses API.
Why
This aligns with how Roo manages context and simplifies our Responses API implementation while keeping all the benefits of continuity, caching, and latency improvements.
What changed
- All OpenAI models now use the Responses API; system instructions are passed via the top-level instructions field; requests include store=false and include=["reasoning.encrypted_content"].
- We persist encrypted reasoning items (type: "reasoning", encrypted_content, optional id) into API history and replay them on subsequent turns.
- Reasoning summaries default to summary: "auto" when supported; text.verbosity only when supported.
- Atomic persistence via safeWriteJson.
Removed
- previous_response_id flows, suppressPreviousResponseId/skipPrevResponseIdOnce, persistGpt5Metadata(), and GPT‑5 response ID metadata in UI messages.
Kept
- taskId and mode metadata for cross-provider features.
Result
- ZDR-friendly, stateless continuity with equal or better performance and a simpler codepath.
* fix(webview): remove unused metadata prop from ReasoningBlock render
* Responses API: retain response id for troubleshooting (not continuity)
Continuity is stateless via encrypted reasoning items that we persist and replay. We now capture the top-level response id in OpenAiNativeHandler and persist the assistant message id into api_conversation_history.json solely for debugging/correlation with provider logs; it is not used for continuity or control flow.
Also: silence request-body debug logging to avoid leaking prompts.
* remove DEPRECATED tests
* chore: remove unused Task types file to satisfy knip CI
* fix(task): properly type cleanConversationHistory and createMessage args in Task to address Dan's review
Aligns claude-opus-4-1-20250805 max token limit with claude-opus-4-20250514,
both models now supporting 32K output tokens (overridable to 8K when
enableReasoningEffort is false).
Fixes#9045
Co-authored-by: Roo Code <roomote@roocode.com>
* feat: add OpenRouter embedding provider support
Implement comprehensive OpenRouter embedding provider support for codebase indexing with the following features:
- New OpenRouterEmbedder class with full API compatibility
- Support for OpenRouter's OpenAI-compatible embedding endpoint
- Rate limiting and retry logic with exponential backoff
- Base64 embedding handling to bypass OpenAI package limitations
- Global rate limit state management across embedder instances
- Configuration updates for API key storage and provider selection
- UI integration for OpenRouter provider settings
- Comprehensive test suite with mocking
- Model dimension support for OpenRouter's embedding models
This adds OpenRouter as the 7th supported embedding provider alongside OpenAI, Ollama, OpenAI-compatible, Gemini, Mistral, and Vercel AI Gateway.
* Add translation key
* Fix mutex double release bug
* Add translations
* Add more translations
* Fix failing tests
* code-index(openrouter): fix HTTP-Referer header to RooCodeInc/Roo-Code; i18n: add and wire OpenRouter Code Index strings; test: assert default headers in embedder
---------
Co-authored-by: daniel-lxs <ricciodaniel98@gmail.com>
* feat: convert Chutes to dynamic/router provider
- Add chutes to dynamicProviders array in provider-settings
- Add chutes entry to dynamicProviderExtras in api.ts
- Create fetcher function for Chutes models API
- Convert ChutesHandler to extend RouterProvider
- Update tests to work with dynamic provider setup
- Export chutesDefaultModelInfo for RouterProvider constructor
* fix: address security and code quality issues from review
- Fix potential API key leakage in error logging
- Add temperature support check before setting temperature
- Improve code consistency with RouterProvider patterns
* fix: add chutes to routerModels initialization
- Fix TypeScript error in webviewMessageHandler
- Ensure chutes is included in RouterName Record type
* Fixes
* Support reasoning
* Fix tests
* Remove reasoning checkbox
---------
Co-authored-by: Roo Code <roomote@roocode.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
* feat: add zai-glm-4.6 model and update gpt-oss-120b for Cerebras
- Add zai-glm-4.6 with 128K context window and 40K max tokens
- Set zai-glm-4.6 as default Cerebras model
- Update gpt-oss-120b to 128K context and 40K max tokens
* feat: add zai-glm-4.6 model to Cerebras provider
- Add zai-glm-4.6 with 128K context window and 40K max tokens
- Set zai-glm-4.6 as default Cerebras model
- Model provides ~2000 tokens/s for general-purpose tasks
* add [SOON TO BE DEPRECATED] warning for Q3C
* chore: set gpt-oss-120b as default Cerebras model
* Fix cerebras test: update expected default model to gpt-oss-120b
* Apply suggestion from @mrubens
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
---------
Co-authored-by: kevint-cerebras <kevin.taylor@cerebras.net>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
* feat: update Gemini models with latest 09-2025 versions
- Add gemini-flash-latest and gemini-flash-lite-latest models
- Add gemini-2.5-flash-preview-09-2025 and gemini-2.5-flash-lite-preview-09-2025
- Reorganize models list with most recent versions at the top
- Maintain all existing models for backward compatibility
Fixes#8485
* fix: restore missing maxThinkingTokens and supportsReasoningBudget for gemini-2.5-pro-preview-03-25
Backward compatibility regression fix - these properties were accidentally
removed during reorganization and are required to preserve existing
reasoning-budget controls for users pinned to this model version.
---------
Co-authored-by: Roo Code <roomote@roocode.com>
Co-authored-by: daniel-lxs <ricciodaniel98@gmail.com>
* feat: Add supportsReasoning property for Z.ai GLM binary thinking mode
- Add supportsReasoning to ModelInfo schema for binary reasoning models
- Update GLM-4.5 and GLM-4.6 models to use supportsReasoning: true
- Implement thinking parameter support in ZAiHandler for Deep Thinking API
- Update ThinkingBudget component to show simple toggle for supportsReasoning models
- Add comprehensive tests for binary reasoning functionality
Closes#8465
* refactor: rename supportsReasoning to supportsReasoningBinary for clarity
- Rename supportsReasoning -> supportsReasoningBinary in model schema
- Update Z.AI GLM model configurations to use supportsReasoningBinary
- Update Z.AI provider logic in createStream and completePrompt methods
- Update ThinkingBudget UI component and tests
- Update all test comments and expectations
This change improves naming clarity by distinguishing between:
- supportsReasoningBinary: Simple on/off reasoning toggle
- supportsReasoningBudget: Advanced reasoning with token budget controls
- supportsReasoningEffort: Advanced reasoning with effort levels
* feat(zai): add GLM-4.5-X, AirX, Flash; sync with Z.ai docs; keep canonical api line keys
* feat(zai): add GLM-4.5V vision model (supportsImages, pricing, 16K max output); add tests
* feat(types,zai): sync Z.AI international model map and tests
- Update pricing, context window, and capabilities for:
glm-4.5-x, glm-4.5-airx, glm-4.5-flash, glm-4.5v, glm-4.6
- Add glm-4-32b-0414-128k
- Align tests with new model specs
* fix(zai): align handler generics with expanded model ids to satisfy CI compile step
* chore(zai): remove tier pricing blocks for Z.ai models
* fix(zai): simplify names in zaiApiLineConfigs for clarity
* chore(zai): set default temperature to 0.6
---------
Co-authored-by: Roo Code <roomote@roocode.com>
chore(gpt5): stop persisting instructions/reasoning_summary in UI message metadata
Problem: ui_messages.json was getting bloated with unused or duplicated content (system 'instructions' and 'reasoning_summary') that we do not read back. Root cause: earlier OpenAI Responses API implementation persisted these fields to per-message metadata; however, 'instructions' are already sent as top-level request instructions and 'reasoning_summary' is surfaced live via streaming events. Neither field is consumed from storage. Changes: (1) Task.persistGpt5Metadata now stores only previous_response_id; (2) removed instructions and reasoning_summary from types; (3) updated Zod schema; (4) persistence layer writes messages as-is (no sanitizer); (5) tests green. Impact: smaller ui_messages.json, no runtime behavior change for requests. Migration: old metadata fields will be ignored by schema.
