* 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
* 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: 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>
* fix: add cache reporting support for OpenAI-Native provider
- Add normalizeUsage method to properly extract cache tokens from Responses API
- Support both detailed token shapes (input_tokens_details) and legacy fields
- Calculate cache read/write tokens with proper fallbacks
- Include reasoning tokens when available in output_tokens_details
- Ensure accurate cost calculation using uncached input tokens
This fixes the issue where caching information was not being reported
when using the OpenAI-Native provider with the Responses API.
* fix: improve cache token normalization and add comprehensive tests
- Add fallback to derive total input tokens from details when totals are missing
- Remove unused convertToOpenAiMessages import
- Add comment explaining cost calculation alignment with Gemini provider
- Add comprehensive test coverage for normalizeUsage method covering:
- Detailed token shapes with cached/miss tokens
- Legacy field names and SSE-only events
- Edge cases including missing totals with details-only
- Cost calculation with uncached input tokens
* fix: address PR review comments
- Remove incorrect fallback to missFromDetails for cache write tokens
- Fix cost calculation to pass total input tokens (calculateApiCostOpenAI handles subtraction)
- Improve readability by extracting cache detail checks to intermediate variables
- Remove redundant ?? undefined
- Update tests to reflect correct behavior (miss tokens are not cache writes)
- Add clarifying comments about cache miss vs cache write tokens
* feat: add Ollama API key support for Turbo mode
- Add ollamaApiKey field to ProviderSettings schema
- Add ollamaApiKey to SECRET_STATE_KEYS for secure storage
- Update Ollama and NativeOllama providers to use API key for authentication
- Add UI field for Ollama API key (shown when custom base URL is provided)
- Add test coverage for API key functionality
This enables users to use Ollama Turbo with datacenter-grade hardware by providing an API key for authenticated Ollama instances or cloud services.
* fix: use VSCodeTextField for Ollama API key field
Remove non-existent ApiKeyField import and use standard VSCodeTextField with password type, matching other provider implementations
* Add missing translation keys for Ollama API key support
- Add providers.ollama.apiKey and providers.ollama.apiKeyHelp to all 18 language files
- Support for authenticated Ollama instances and cloud services
- Relates to PR #7425
* refactor: improve type safety for Ollama client configuration
- Replace 'any' type with proper OllamaOptions (Config) type
- Import Config type from ollama package for better type checking
---------
Co-authored-by: Roo Code <roomote@roocode.com>
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
* fix: handle Mistral thinking content as reasoning chunks
- Add TypeScript interfaces for Mistral content types (text and thinking)
- Update createMessage to yield reasoning chunks for thinking content
- Update completePrompt to filter out thinking content in non-streaming mode
- Add comprehensive tests for reasoning content handling
- Follow the pattern used by other providers (Anthropic, OpenAI, Gemini, etc.)
Fixes#6842
* fix: resolve TypeScript type issue in completePrompt method
* fix: handle Mistral thinking content chunks in streaming responses
- Added ContentChunkWithThinking type helper to handle thinking chunks
- Properly converts thinking content to reasoning chunks in streaming
- Filters out thinking content in non-streaming completePrompt responses
- Confirmed that Mistral API does send thinking chunks with type 'thinking'
- Works with Mistral SDK v1.9.18
---------
Co-authored-by: Roo Code <roomote@roocode.com>
Co-authored-by: daniel-lxs <ricciodaniel98@gmail.com>
