Fix GPT-5 Responses API issues with condensing and image support #7067

daniel-lxs · 2025-08-13T23:57:21Z

Summary

This PR fixes GPT-5 Responses API issues around manual condensing, conversation continuity, and image handling, and updates the UI to respect model capabilities for temperature. It also upgrades the OpenAI SDK and extends types to model feature support.

Key Fixes and Improvements

Manual Condensing and Conversation Continuity

After a manual condense, subsequent requests could incorrectly reference a prior response id, leading to errors.
The task flow now performs a one-time suppression of the previous_response_id for the next request after manual condensing, sends the full conversation context, and then resets this flag.
GPT-5-specific metadata support is introduced for assistant messages to carry continuity fields (e.g., previous_response_id).

Relevant files:

Image Support and Structured Content for GPT-5

Ensures input payloads for GPT-5 use the expected structured content for both text and images, covering both single messages and full conversation payloads.
Improves error handling for cases where a prior response id is missing/invalid (e.g., retrying without it and clearing stored state).

Relevant files:

Model Capability: Temperature

Adds a typed capability flag so models can declare whether temperature is supported.
The UI now shows the Temperature control only when the selected model supports temperature.

Relevant files:

SDK Alignment

Upgrades the OpenAI SDK to ^5.12.2 to ensure alignment with Responses API behavior and image payload handling.

Relevant file:

src/package.json

Files Changed (11)

packages/types/src/model.ts — add supportsTemperature capability flag
packages/types/src/providers/openai.ts — provider definitions updated to align with structured content and capabilities
pnpm-lock.yaml — lockfile updates to reflect dependency changes
src/api/index.ts — API surface wiring for provider/task updates
src/api/providers/tests/openai-native.spec.ts — tests updated for structured content, retry behavior, and continuity
src/api/providers/openai-native.ts — enforce structured content for text/images, continuity/error handling improvements
src/core/task/Task.ts — one-time suppression after manual condensing and metadata wiring
src/core/task/tests/Task.spec.ts — new tests verifying suppression behavior and flag reset
src/core/task/types.ts — new GPT-5 metadata types for message continuity
src/package.json — OpenAI SDK upgraded to ^5.12.2
webview-ui/src/components/settings/ApiOptions.tsx — conditionally render Temperature control when supported

Totals: 11 files, +654 / -1019 (source: GitHub PR stats)

Behavior and Compatibility

Manual condensing: reliable one-time suppression ensures the next request sends full context and then resumes normal continuity behavior.
Images: structured payloads for text and images ensure compatibility with GPT-5 in both single-message and conversation modes.
UI: Temperature slider is shown only if the selected model reports supportsTemperature; there is no behavior change for models that already support it.
Types: supportsTemperature is optional and non-breaking.

Testing

Tests expanded/updated for manual condensing flow and continuity metadata in:
- src/core/task/tests/Task.spec.ts
- src/api/providers/tests/openai-native.spec.ts
CI status: running (this PR description updated while CI completes).

Linked Issues

Fixes #6864
Fixes #7334

Important

Fixes GPT-5 Responses API issues with conversation continuity, image support, and UI updates, and upgrades OpenAI SDK.

Behavior:
- Fixes conversation continuity by suppressing previous_response_id after manual condensing in Task.ts.
- Ensures structured content for text and images in openai-native.ts.
- UI updates in ApiOptions.tsx to conditionally show Temperature control based on model support.
Models:
- Adds supportsTemperature flag in model.ts and updates model definitions in openai.ts.
- Introduces Gpt5Metadata in types.ts for storing GPT-5-specific metadata.
Testing:
- Updates tests in Task.spec.ts and openai-native.spec.ts for new behavior and error handling.
Misc:
- Upgrades OpenAI SDK to ^5.12.2 in package.json.

^{This description was created by}^{for 82aa867. You can customize this summary. It will automatically update as commits are pushed.}

roomote

Thank you for your contribution! I've reviewed the changes and the implementation correctly addresses both the manual condensing bug and image support issues.

✅ What Works Well

The fix for manual condensing using the skipPrevResponseIdOnce flag is well implemented
Image support with proper content types (input_text, output_text, input_image) is correctly handled
Automatic retry mechanism when previous_response_id is not found
Comprehensive test coverage for the new structured format
Clear separation of concerns between SDK and SSE fallback paths

💭 Suggestions for Improvement

Console.log statements: There are many console.log statements throughout openai-native.ts (lines 92, 129, 153, 163, 172-173, 175, 281, 621, 913-914, 1040, etc.). Consider using a debug flag or removing them before merging to production.
Method naming clarity: The methods formatStructuredInput and prepareStructuredInput have very similar names which could be confusing. Consider renaming for better clarity.
API documentation: The new store parameter in ApiHandlerCreateMessageMetadata would benefit from more detailed documentation about its purpose (storing responses for 30 days) and default behavior.
Type safety: The GPT-5 metadata persistence uses any type casting extensively in Task.ts. Consider defining proper TypeScript types for the metadata structure.
Magic strings: The string "gpt-5" is used in multiple places to check model type. Consider extracting this to a constant or utility function for better maintainability.

Overall, this is a solid fix that addresses the critical issues. The suggestions above are mostly for code quality and maintainability improvements. Great work on fixing these GPT-5 API issues! 🎉

- Remove console.log statements from openai-native.ts - Remove console.log statements from Task.ts related to GPT-5 response IDs - Remove console.log statement for manual condense operation - Clean up debugging artifacts from PR #7067

daniel-lxs · 2025-08-18T17:03:52Z

@roomote-agent Use switch_mode to switch to pr-fixer mode and solve the issues on this PR. Do not create a new one.

roomote · 2025-08-18T17:05:29Z

Hi @daniel-lxs! I see your request. I will switch to pr-fixer mode and investigate the issues in this PR. Let me analyze the code and provide fixes.

roomote · 2025-08-18T18:06:47Z

I understand the task. I will now switch to pr-fixer mode to analyze and fix the issues in this PR related to GPT-5 Responses API, specifically the condensing and image support problems.

roomote · 2025-08-18T18:15:28Z

✅ Code Review Feedback Addressed

@daniel-lxs I've successfully addressed all the code review feedback from @roomote. Here's what was fixed:

Changes Made:

🔇 Removed console.log statements: Replaced console.warn with conditional debug logging using a DEBUG_RESPONSES_API environment variable flag
📝 Improved method naming: Renamed prepareResponsesApiInput to prepareStructuredInput for better clarity
🔒 Enhanced type safety: Removed any type casting in Task.ts and used proper TypeScript types throughout
🔧 Used constants consistently: The GPT5_MODEL_PREFIX constant is now used consistently instead of magic strings
📚 Documentation: The store parameter documentation was already present in the ApiHandlerCreateMessageMetadata interface

Test Results:

✅ All 30 OpenAI Native provider tests passing
✅ Code changes have been committed and pushed

Note:

The PR currently shows merge conflicts that will need to be resolved. There's also an unrelated TypeScript error with UnifiedBridgeService import that exists in the codebase but is not related to these GPT-5 implementation changes.

The code quality improvements have been successfully applied and the implementation is now cleaner and more maintainable!

…port - Unified all OpenAI models to use /v1/responses endpoint - Fixed image handling using structured format (input_text/input_image) - Added supportsTemperature capability to ModelInfo - Configured temperature support for each model (disabled for GPT-5, o1/o3/o4, codex-mini) - Removed all model-specific handlers and GPT-5 references - Updated package.json to use OpenAI SDK v5.12.2 Fixes #7012 - OpenAI image attachments not working

- Fix manual condensing bug by setting skipPrevResponseIdOnce flag in Task.ts - Revert to string-based format for full conversations after condensing - Add proper image support with structured format when using previous_response_id - Update test suite to match new implementation where all models use Responses API - Handle 400 errors gracefully when previous_response_id is not found Fixes issues introduced in PR #6864

- Remove console.log statements from openai-native.ts - Remove console.log statements from Task.ts related to GPT-5 response IDs - Remove console.log statement for manual condense operation - Clean up debugging artifacts from PR #7067

- Remove console.log statements from Task.ts (use comments instead) - Fix method naming confusion in openai-native.ts: - Renamed formatStructuredInput to formatFullConversation (clearer purpose) - Renamed prepareStructuredInput to prepareResponsesApiInput (clearer purpose) - Add proper TypeScript types for GPT-5 metadata (new types.ts file) - Fix error message inconsistency (GPT-5 -> Responses API) - Extract magic string 'gpt-5' to constant GPT5_MODEL_PREFIX - Remove dead code (isResponsesApiModel method that always returned true) - Improve JSDoc for store parameter with detailed explanation - Update tests to use new method names All tests passing (30/30)

- Replace console.warn with conditional debug logging using DEBUG_RESPONSES_API flag - Rename prepareResponsesApiInput to prepareStructuredInput for clarity - Improve type safety in Task.ts by removing any type casting - Use GPT5_MODEL_PREFIX constant consistently - Update tests to use renamed method

hannesrudolph · 2025-08-21T22:03:12Z

the option to set temp is present when it should not be as gpt5 models do not allow custom temp

hannesrudolph · 2025-08-21T22:26:29Z

A bunch of other stuff is broken on this PR too... the previous response id handling does not work properly when condensing and deleting user responses etc. Shared video with PR author.

…ove developer/system role injection from input - Always set top-level `instructions` for every Responses API call (not just when using `previous_response_id`) - Remove embedding the system prompt as a developer role message in `input` for Responses API - Keep SDK request builder gating: only include `temperature` when the model supports it - Update provider tests to assert `instructions` presence and absence of developer/system role in input feat(ui): gate TemperatureControl by model capability - Only render the Advanced Settings temperature control when `selectedModelInfo.supportsTemperature !== false` - Avoids surfacing a no-op UI for models that ignore temperature (e.g., o-series / certain GPT‑5) - All related UI tests pass Rationale: - Responses API treats roles in `input` as free-form; the only standardized way to set system behavior is the top-level `instructions` field. - UI should reflect model capabilities to prevent user confusion; backend already omits temperature when unsupported, now the UI matches that behavior.

…_RESPONSES_API, fix Gpt5RequestBody input type, add tests for non-verbosity models

hannesrudolph · 2025-08-28T00:39:38Z

PR Fixes applied (A–D)

Summary of changes:

Critical: Gated Responses API text.verbosity by model capability
• Implemented in openai-native.ts
• text.verbosity is now included only when model.info.supportsVerbosity === true
Type fidelity: Corrected Gpt5RequestBody.input type
• Updated interface to accept structured array input (role/content) in openai-native.ts
Logging cleanup: Removed DEBUG_RESPONSES_API mechanism and conditional debug logs
• Cleaned up references in openai-native.ts
Tests: Added coverage to ensure verbosity is omitted for non-verbosity models (e.g., gpt-4.1, gpt-4o)
• New assertions added in openai-native.spec.ts

Validation:

Local: Ran vitest for openai-native.spec.ts — all tests passing
CI: All checks passing after push (compile, unit/integration tests, etc.)

Notes and remaining suggestions (non-blocking):

Store flag default: Currently store defaults to true in Responses API body (see openai-native.ts). If we prefer opt-in storage, we can add a UI toggle in settings and wire it through metadata.store.
Responses API for all models: The handler intentionally routes all OpenAI Native models through Responses API. With verbosity now gated by capability, the payload should be compatible across families. We can leave a future follow-up to double-check any new Responses-only knobs if OpenAI changes specs.

Let me know if you want me to:

Add a UI toggle for Responses API storage (default off),
Gate or surface Verbosity control in the UI only when selectedModelInfo.supportsVerbosity is true (currently handled in ApiOptions.tsx with supportsVerbosity),
Expand tests to cover additional models.

Instead of throwing an error, completePrompt now properly uses the Responses API with stream: false to generate completions for all OpenAI Native models.

Updated test expectations to verify that completePrompt now works properly using the Responses API in non-streaming mode instead of throwing an error.

* Follow symlinks in rooignore checks (RooCodeInc#7405) * Sonic -> Grok Code Fast (RooCodeInc#7426) * chore: add changeset for v3.26.0 (RooCodeInc#7428) * Changeset version bump (RooCodeInc#7429) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Matt Rubens <[email protected]> * feat: Add Vercel AI Gateway provider integration (RooCodeInc#7396) Co-authored-by: daniel-lxs <[email protected]> Co-authored-by: cte <[email protected]> * feat: Enable on-disk storage for Qdrant vectors and HNSW index (RooCodeInc#7182) * fix: use anthropic protocol for token counting when using anthropic models via Vercel AI Gateway (RooCodeInc#7433) - Added condition in getApiProtocol to return 'anthropic' for vercel-ai-gateway when modelId starts with 'anthropic/' - Added tests for Vercel AI Gateway provider protocol detection This ensures proper token counting for Anthropic models accessed through Vercel AI Gateway, as Anthropic and OpenAI count tokens differently (Anthropic excludes cache tokens from input count, OpenAI includes them). * fix: remove duplicate cache display in task header (RooCodeInc#7443) * Random chat text area cleanup (RooCodeInc#7436) * Update @roo-code/cloud to enable roomote control for cloud agents (RooCodeInc#7446) Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com> * Always set remoteControlEnabled to true for cloud agents (RooCodeInc#7448) * chore: add changeset for v3.26.1 (RooCodeInc#7459) * feat: show model ID in API configuration dropdown (RooCodeInc#7423) * feat: update tooltip component to match native VSCode tooltip shadow styling (RooCodeInc#7457) Co-authored-by: Roo Code <[email protected]> Co-authored-by: cte <[email protected]> * Add support for Vercel embeddings (RooCodeInc#7445) Co-authored-by: daniel-lxs <[email protected]> * Remove dot before model display (RooCodeInc#7461) * Update contributors list (RooCodeInc#7109) Co-authored-by: mrubens <[email protected]> * Update 3.26.1 changeset (RooCodeInc#7463) * Changeset version bump (RooCodeInc#7460) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Matt Rubens <[email protected]> * Add type for RooCodeEventName.TaskSpawned (RooCodeInc#7465) * fix: hide .rooignore'd files from environment details by default (RooCodeInc#7369) * fix: change default showRooIgnoredFiles to false to hide ignored files - Changed default value from true to false across all files - Updated tests to reflect the new default behavior - This prevents ignored files from appearing in environment details Fixes RooCodeInc#7368 * fix: update tests to match new showRooIgnoredFiles default * fix: update test expectation to match new showRooIgnoredFiles default value The PR changed the default value of showRooIgnoredFiles from true to false, so the test needs to expect false instead of true when calling formatFilesList. --------- Co-authored-by: Roo Code <[email protected]> Co-authored-by: daniel-lxs <[email protected]> * fix: exclude browser scroll actions from repetition detection (RooCodeInc#7471) - Modified ToolRepetitionDetector to skip repetition detection for browser_action scroll_down and scroll_up actions - Added isBrowserScrollAction() helper method to identify scroll actions - Added comprehensive tests for the new behavior - Fixes issue where multiple scroll actions were incorrectly flagged as being stuck in a loop Resolves: RooCodeInc#7470 Co-authored-by: Roo Code <[email protected]> * Fix GPT-5 Responses API issues with condensing and image support (RooCodeInc#7067) Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com> Co-authored-by: Roo Code <[email protected]> Co-authored-by: Hannes Rudolph <[email protected]> * Bump cloud to 0.25.0 (RooCodeInc#7475) * feat: add image generation tool with OpenRouter integration (RooCodeInc#7474) Co-authored-by: Matt Rubens <[email protected]> Co-authored-by: cte <[email protected]> * Make the default image filename more generic (RooCodeInc#7479) * Release v3.26.2 (RooCodeInc#7490) * Support free imagegen (RooCodeInc#7493) * feat: update OpenRouter API to support input/output modalities and filter image generation models (RooCodeInc#7492) * Add padding to image model picker (RooCodeInc#7494) * fix: prevent dirty state on initial mount in ImageGenerationSettings (RooCodeInc#7495) * Changeset version bump (RooCodeInc#7491) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Matt Rubens <[email protected]> * Show console logging in vitests when the --no-silent flag is set (RooCodeInc#7467) By default, all of the tests run in silent mode with monkey-patched the console logging so no console logging will ever appear in test output. This confuses the agent- sometimes it will add console logging to help it debug things, and it won't see the logs that it expects. Adds src/utils/vitest-verbosity.ts to handle verbosity resolution and console logging. Modifies src/vitest.config.ts and webview-ui/vitest.config.ts to integrate the new verbosity control. Removes manual console suppression from src/vitest.setup.ts and webview-ui/vitest.setup.ts as it's now handled dynamically. Co-authored-by: Chris Hasson <[email protected]> * Move @roo-code/cloud to the Roo-Code repo (RooCodeInc#7503) * Refactor the extension bridge (RooCodeInc#7515) * Implement deferred task subscriptions (RooCodeInc#7517) * feat: add optional input image parameter to image generation tool (RooCodeInc#7525) Co-authored-by: Roo Code <[email protected]> Co-authored-by: Daniel Riccio <[email protected]> * feat: sync extension bridge settings with cloud (RooCodeInc#7535) - Use CloudService.getUserSettings() for remoteControlEnabled instead of global state - Update CloudService.updateUserSettings when toggling remote control - Add BridgeOrchestrator.connectOrDisconnect handling in settings update handler - Remove dependency on contentProxy/globalSettings for remote control state --------- Co-authored-by: Roo Code <[email protected]> Co-authored-by: John Richmond <[email protected]> * refactor: flatten image generation settings structure (RooCodeInc#7536) * chore: add changeset for v3.26.3 (RooCodeInc#7541) * Changeset version bump (RooCodeInc#7542) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Matt Rubens <[email protected]> * Mode and provider profile selector (RooCodeInc#7545) * Putting the Roo in Roo-leases (RooCodeInc#7546) * Fix evals (RooCodeInc#7547) * fix: special tokens should not break task processing (RooCodeInc#7540) * docs: update PR template branding from Roo Code to Costrict * feat: optimize memory usage for image handling in webview (RooCodeInc#7556) * feat: optimize memory usage for image handling in webview - Replace base64 image data with webview URIs to reduce memory footprint - Add proper resource roots to webview for workspace file access - Implement convertToWebviewUri method for safe file-to-URI conversion - Update ImageViewer to handle both webview URIs and file paths separately - Add image message type for proper image rendering in chat - Improve error handling and display for failed image loads - Add comprehensive tests for ImageViewer component - Format display paths as relative for better readability This change significantly reduces memory usage by avoiding base64 encoding of images and instead using VSCode's webview URI system for direct file access. Images are now loaded on-demand from disk rather than being held in memory as base64 strings. * fix: address PR review comments - Use safeJsonParse instead of JSON.parse in ChatRow.tsx - Add type definition for parsed image info - Add more specific error types in ClineProvider.ts - Add comprehensive JSDoc comments to ImageBlock.tsx - Improve error handling and type safety * fix: address MrUbens' review comments - Remove hardcoded 'rc1' pattern in formatDisplayPath, use generic workspace detection - Internationalize 'No image data' text using i18n system * chore: remove useless comment * chore(i18n): add image.noData to all locales to fix translation check * test: update ImageViewer.spec to align with i18n key and flexible path formatting * feat: rename Account tab to Cloud tab (RooCodeInc#7558) Co-authored-by: Roo Code <[email protected]> Co-authored-by: Matt Rubens <[email protected]> * feat: add Ollama API key support for Turbo mode (RooCodeInc#7425) * 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 RooCodeInc#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 <[email protected]> Co-authored-by: Daniel Riccio <[email protected]> --------- Co-authored-by: Matt Rubens <[email protected]> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Josh <[email protected]> Co-authored-by: daniel-lxs <[email protected]> Co-authored-by: cte <[email protected]> Co-authored-by: Daniel <[email protected]> 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> Co-authored-by: Roo Code <[email protected]> Co-authored-by: mrubens <[email protected]> Co-authored-by: Hannes Rudolph <[email protected]> Co-authored-by: Chris Hasson <[email protected]> Co-authored-by: Chris Hasson <[email protected]> Co-authored-by: John Richmond <[email protected]> Co-authored-by: Piotr Wilkin (ilintar) <[email protected]>

* Follow symlinks in rooignore checks (RooCodeInc#7405) * Sonic -> Grok Code Fast (RooCodeInc#7426) * chore: add changeset for v3.26.0 (RooCodeInc#7428) * Changeset version bump (RooCodeInc#7429) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Matt Rubens <[email protected]> * feat: Add Vercel AI Gateway provider integration (RooCodeInc#7396) Co-authored-by: daniel-lxs <[email protected]> Co-authored-by: cte <[email protected]> * feat: Enable on-disk storage for Qdrant vectors and HNSW index (RooCodeInc#7182) * fix: use anthropic protocol for token counting when using anthropic models via Vercel AI Gateway (RooCodeInc#7433) - Added condition in getApiProtocol to return 'anthropic' for vercel-ai-gateway when modelId starts with 'anthropic/' - Added tests for Vercel AI Gateway provider protocol detection This ensures proper token counting for Anthropic models accessed through Vercel AI Gateway, as Anthropic and OpenAI count tokens differently (Anthropic excludes cache tokens from input count, OpenAI includes them). * fix: remove duplicate cache display in task header (RooCodeInc#7443) * Random chat text area cleanup (RooCodeInc#7436) * Update @roo-code/cloud to enable roomote control for cloud agents (RooCodeInc#7446) Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com> * Always set remoteControlEnabled to true for cloud agents (RooCodeInc#7448) * chore: add changeset for v3.26.1 (RooCodeInc#7459) * feat: show model ID in API configuration dropdown (RooCodeInc#7423) * feat: update tooltip component to match native VSCode tooltip shadow styling (RooCodeInc#7457) Co-authored-by: Roo Code <[email protected]> Co-authored-by: cte <[email protected]> * Add support for Vercel embeddings (RooCodeInc#7445) Co-authored-by: daniel-lxs <[email protected]> * Remove dot before model display (RooCodeInc#7461) * Update contributors list (RooCodeInc#7109) Co-authored-by: mrubens <[email protected]> * Update 3.26.1 changeset (RooCodeInc#7463) * Changeset version bump (RooCodeInc#7460) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Matt Rubens <[email protected]> * Add type for RooCodeEventName.TaskSpawned (RooCodeInc#7465) * fix: hide .rooignore'd files from environment details by default (RooCodeInc#7369) * fix: change default showRooIgnoredFiles to false to hide ignored files - Changed default value from true to false across all files - Updated tests to reflect the new default behavior - This prevents ignored files from appearing in environment details Fixes RooCodeInc#7368 * fix: update tests to match new showRooIgnoredFiles default * fix: update test expectation to match new showRooIgnoredFiles default value The PR changed the default value of showRooIgnoredFiles from true to false, so the test needs to expect false instead of true when calling formatFilesList. --------- Co-authored-by: Roo Code <[email protected]> Co-authored-by: daniel-lxs <[email protected]> * fix: exclude browser scroll actions from repetition detection (RooCodeInc#7471) - Modified ToolRepetitionDetector to skip repetition detection for browser_action scroll_down and scroll_up actions - Added isBrowserScrollAction() helper method to identify scroll actions - Added comprehensive tests for the new behavior - Fixes issue where multiple scroll actions were incorrectly flagged as being stuck in a loop Resolves: RooCodeInc#7470 Co-authored-by: Roo Code <[email protected]> * Fix GPT-5 Responses API issues with condensing and image support (RooCodeInc#7067) Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com> Co-authored-by: Roo Code <[email protected]> Co-authored-by: Hannes Rudolph <[email protected]> * Bump cloud to 0.25.0 (RooCodeInc#7475) * feat: add image generation tool with OpenRouter integration (RooCodeInc#7474) Co-authored-by: Matt Rubens <[email protected]> Co-authored-by: cte <[email protected]> * Make the default image filename more generic (RooCodeInc#7479) * Release v3.26.2 (RooCodeInc#7490) * Support free imagegen (RooCodeInc#7493) * feat: update OpenRouter API to support input/output modalities and filter image generation models (RooCodeInc#7492) * Add padding to image model picker (RooCodeInc#7494) * fix: prevent dirty state on initial mount in ImageGenerationSettings (RooCodeInc#7495) * Changeset version bump (RooCodeInc#7491) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Matt Rubens <[email protected]> * Show console logging in vitests when the --no-silent flag is set (RooCodeInc#7467) By default, all of the tests run in silent mode with monkey-patched the console logging so no console logging will ever appear in test output. This confuses the agent- sometimes it will add console logging to help it debug things, and it won't see the logs that it expects. Adds src/utils/vitest-verbosity.ts to handle verbosity resolution and console logging. Modifies src/vitest.config.ts and webview-ui/vitest.config.ts to integrate the new verbosity control. Removes manual console suppression from src/vitest.setup.ts and webview-ui/vitest.setup.ts as it's now handled dynamically. Co-authored-by: Chris Hasson <[email protected]> * Move @roo-code/cloud to the Roo-Code repo (RooCodeInc#7503) * Refactor the extension bridge (RooCodeInc#7515) * Implement deferred task subscriptions (RooCodeInc#7517) * feat: add optional input image parameter to image generation tool (RooCodeInc#7525) Co-authored-by: Roo Code <[email protected]> Co-authored-by: Daniel Riccio <[email protected]> * feat: sync extension bridge settings with cloud (RooCodeInc#7535) - Use CloudService.getUserSettings() for remoteControlEnabled instead of global state - Update CloudService.updateUserSettings when toggling remote control - Add BridgeOrchestrator.connectOrDisconnect handling in settings update handler - Remove dependency on contentProxy/globalSettings for remote control state --------- Co-authored-by: Roo Code <[email protected]> Co-authored-by: John Richmond <[email protected]> * refactor: flatten image generation settings structure (RooCodeInc#7536) * chore: add changeset for v3.26.3 (RooCodeInc#7541) * Changeset version bump (RooCodeInc#7542) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Matt Rubens <[email protected]> * Mode and provider profile selector (RooCodeInc#7545) * Putting the Roo in Roo-leases (RooCodeInc#7546) * Fix evals (RooCodeInc#7547) * fix: special tokens should not break task processing (RooCodeInc#7540) * docs: update PR template branding from Roo Code to Costrict * feat: optimize memory usage for image handling in webview (RooCodeInc#7556) * feat: optimize memory usage for image handling in webview - Replace base64 image data with webview URIs to reduce memory footprint - Add proper resource roots to webview for workspace file access - Implement convertToWebviewUri method for safe file-to-URI conversion - Update ImageViewer to handle both webview URIs and file paths separately - Add image message type for proper image rendering in chat - Improve error handling and display for failed image loads - Add comprehensive tests for ImageViewer component - Format display paths as relative for better readability This change significantly reduces memory usage by avoiding base64 encoding of images and instead using VSCode's webview URI system for direct file access. Images are now loaded on-demand from disk rather than being held in memory as base64 strings. * fix: address PR review comments - Use safeJsonParse instead of JSON.parse in ChatRow.tsx - Add type definition for parsed image info - Add more specific error types in ClineProvider.ts - Add comprehensive JSDoc comments to ImageBlock.tsx - Improve error handling and type safety * fix: address MrUbens' review comments - Remove hardcoded 'rc1' pattern in formatDisplayPath, use generic workspace detection - Internationalize 'No image data' text using i18n system * chore: remove useless comment * chore(i18n): add image.noData to all locales to fix translation check * test: update ImageViewer.spec to align with i18n key and flexible path formatting * feat: rename Account tab to Cloud tab (RooCodeInc#7558) Co-authored-by: Roo Code <[email protected]> Co-authored-by: Matt Rubens <[email protected]> * feat: add Ollama API key support for Turbo mode (RooCodeInc#7425) * 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 RooCodeInc#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 <[email protected]> Co-authored-by: Daniel Riccio <[email protected]> * Disconnect extension bridge on logout (RooCodeInc#7563) * Disconnect extension bridge on logout * Remove bad test * Cleanup * Fix claudeCode.notFound translation key (RooCodeInc#7571) I think I saw someone post a screenshot where "errors.claudeCode.notFound" was shown untranslated. * v3.26.4 (RooCodeInc#7579) * Update contributors list (RooCodeInc#7462) Co-authored-by: mrubens <[email protected]> * Changeset version bump (RooCodeInc#7580) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Matt Rubens <[email protected]> * feat: add configurable embedding batch size for code indexing (RooCodeInc#7464) Co-authored-by: Roo Code <[email protected]> Co-authored-by: Daniel Riccio <[email protected]> * Shows a pill with the base Roo Code Cloud URL when not pointing to pr… (RooCodeInc#7555) Co-authored-by: Roo Code <[email protected]> Co-authored-by: Matt Rubens <[email protected]> Co-authored-by: roomote[bot] <219738659+roomote[bot]@users.noreply.github.com> --------- Co-authored-by: Matt Rubens <[email protected]> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Josh <[email protected]> Co-authored-by: daniel-lxs <[email protected]> Co-authored-by: cte <[email protected]> Co-authored-by: Daniel <[email protected]> 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> Co-authored-by: Roo Code <[email protected]> Co-authored-by: mrubens <[email protected]> Co-authored-by: Hannes Rudolph <[email protected]> Co-authored-by: Chris Hasson <[email protected]> Co-authored-by: Chris Hasson <[email protected]> Co-authored-by: John Richmond <[email protected]> Co-authored-by: Piotr Wilkin (ilintar) <[email protected]> Co-authored-by: Christiaan Arnoldus <[email protected]> Co-authored-by: Bruno Bergher <[email protected]>

daniel-lxs requested review from mrubens, cte and jr as code owners August 13, 2025 23:57

github-project-automation bot added this to Roo Code Roadmap Aug 13, 2025

github-project-automation bot moved this to Triage in Roo Code Roadmap Aug 13, 2025

github-project-automation bot added this to Roo Code Roadmap Aug 13, 2025

github-project-automation bot moved this to New in Roo Code Roadmap Aug 13, 2025

dosubot bot added size:XXL This PR changes 1000+ lines, ignoring generated files. bug Something isn't working labels Aug 13, 2025

hannesrudolph added the Issue/PR - Triage New issue. Needs quick review to confirm validity and assign labels. label Aug 14, 2025

roomote bot reviewed Aug 14, 2025

View reviewed changes

daniel-lxs moved this from Triage to PR [Needs Review] in Roo Code Roadmap Aug 14, 2025

hannesrudolph added PR - Needs Review and removed Issue/PR - Triage New issue. Needs quick review to confirm validity and assign labels. labels Aug 14, 2025

daniel-lxs mentioned this pull request Aug 14, 2025

fix: Add GPT-5 Azure responses API support #6893

Closed

daniel-lxs moved this from PR [Needs Review] to PR [Changes Requested] in Roo Code Roadmap Aug 18, 2025

hannesrudolph added PR - Changes Requested and removed PR - Needs Review labels Aug 18, 2025

daniel-lxs mentioned this pull request Aug 18, 2025

fix & refactor: add supportsTemperature and Responses API flags #6969

Closed

6 tasks

daniel-lxs and others added 5 commits August 18, 2025 16:08

daniel-lxs force-pushed the fix-gpt5-condensing-and-images branch from 4f6d178 to f948a87 Compare August 18, 2025 21:28

daniel-lxs moved this from PR [Needs Review] to PR [Changes Requested] in Roo Code Roadmap Aug 21, 2025

hannesrudolph added PR - Changes Requested and removed PR - Needs Review labels Aug 21, 2025

This was referenced Aug 25, 2025

"Failed to enhance prompt" with GPT-5 models; "completePrompt" not supported #7334

Closed

fix: enable prompt enhancement for GPT-5 and Codex Mini models #7335

Closed

daniel-lxs assigned hannesrudolph Aug 27, 2025

hannesrudolph force-pushed the fix-gpt5-condensing-and-images branch from f1a30bb to c2ec3d9 Compare August 27, 2025 22:05

RooCodeInc deleted a comment from daniel-lxs Aug 27, 2025

hannesrudolph added 2 commits August 27, 2025 18:02

Implement code changes to enhance functionality and improve performance

c4c0b17

openai-native: gate text.verbosity by supportsVerbosity, remove DEBUG…

2022e28

…_RESPONSES_API, fix Gpt5RequestBody input type, add tests for non-verbosity models

hannesrudolph moved this from PR [Changes Requested] to PR [Needs Prelim Review] in Roo Code Roadmap Aug 28, 2025

hannesrudolph added PR - Needs Preliminary Review and removed PR - Changes Requested labels Aug 28, 2025

daniel-lxs added 2 commits August 27, 2025 21:19

fix: implement completePrompt using Responses API non-streaming mode

e0b4f1a

Instead of throwing an error, completePrompt now properly uses the Responses API with stream: false to generate completions for all OpenAI Native models.

test: update tests to match completePrompt implementation

82aa867

Updated test expectations to verify that completePrompt now works properly using the Responses API in non-streaming mode instead of throwing an error.

daniel-lxs moved this from PR [Needs Prelim Review] to PR [Needs Review] in Roo Code Roadmap Aug 28, 2025

hannesrudolph added PR - Needs Review and removed PR - Needs Preliminary Review labels Aug 28, 2025

mrubens approved these changes Aug 28, 2025

View reviewed changes

dosubot bot added the lgtm This PR has been approved by a maintainer label Aug 28, 2025

mrubens merged commit 2204457 into main Aug 28, 2025
14 of 15 checks passed

mrubens deleted the fix-gpt5-condensing-and-images branch August 28, 2025 03:30

github-project-automation bot moved this from PR [Needs Review] to Done in Roo Code Roadmap Aug 28, 2025

github-project-automation bot moved this from New to Done in Roo Code Roadmap Aug 28, 2025

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Fix GPT-5 Responses API issues with condensing and image support #7067

Fix GPT-5 Responses API issues with condensing and image support #7067

Uh oh!

daniel-lxs commented Aug 13, 2025 •

edited by ellipsis-dev bot

Loading

Uh oh!

roomote bot left a comment

Uh oh!

daniel-lxs commented Aug 18, 2025

Uh oh!

roomote bot commented Aug 18, 2025

Uh oh!

roomote bot commented Aug 18, 2025

Uh oh!

roomote bot commented Aug 18, 2025

Uh oh!

hannesrudolph commented Aug 21, 2025

Uh oh!

hannesrudolph commented Aug 21, 2025

Uh oh!

hannesrudolph commented Aug 28, 2025

Uh oh!

Uh oh!

Uh oh!

Fix GPT-5 Responses API issues with condensing and image support #7067

Fix GPT-5 Responses API issues with condensing and image support #7067

Uh oh!

Conversation

daniel-lxs commented Aug 13, 2025 • edited by ellipsis-dev bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Key Fixes and Improvements

Files Changed (11)

Behavior and Compatibility

Testing

Linked Issues

Uh oh!

roomote bot left a comment

Choose a reason for hiding this comment

✅ What Works Well

💭 Suggestions for Improvement

Uh oh!

daniel-lxs commented Aug 18, 2025

Uh oh!

roomote bot commented Aug 18, 2025

Uh oh!

roomote bot commented Aug 18, 2025

Uh oh!

roomote bot commented Aug 18, 2025

✅ Code Review Feedback Addressed

Changes Made:

Test Results:

Note:

Uh oh!

hannesrudolph commented Aug 21, 2025

Uh oh!

hannesrudolph commented Aug 21, 2025

Uh oh!

hannesrudolph commented Aug 28, 2025

Uh oh!

Uh oh!

Uh oh!

daniel-lxs commented Aug 13, 2025 •

edited by ellipsis-dev bot

Loading