Claude/modernize frontend backend 01 cbj25e x pm8 u3zuayfp7 q4 d #1
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…ilities feat: add cross-platform automation and reporting
…emote-access Expose automation runner via FastAPI service
…or-multithreading-support Add asynchronous runner support for concurrent runs
…agement-for-api Add Redis-backed queue for asynchronous task execution
…sk-ids-by-status Add tasks aggregation endpoint
…egui-for-backend-apis Add NiceGUI frontend for AI Testing Tool API
…eplace-with-typescript Replace NiceGUI frontend with React TypeScript interface
…auth-system Add authentication, authorization, and result tabs
…-user-prompt-options Enhance frontend layout and task handling
…ame-change Add persistent task storage and report folder restructuring
…rontend-and-api Add Dockerfiles for frontend, API, and queue runner services
…e-and-rename-components Refactor project structure to backend and frontend servers
…le-and-improve-ui feat: improve task management table experience
…-one-line Improve task status layout and scroll behavior
…on-for-human-input Add human feedback scoring support
…on-for-human-input-ckay6t Add human scoring UI and API for generated code
Remove manual score input from code library
…event-overlay Adjust grid lines to avoid frame overlap
…os-and-move-dropdown Set iOS as the default test device and surface the selector
…-user-data-access Add admin portal to review user task statuses
…ith-chrome-devtools-mcp Add chrome-devtools-mcp web driver integration
…egrate-ai-agents Expand README with multi-agent email integration guidance
…p-dropdown Simplify subscription IMAP settings
…sable-entity-error Fix subscription keyword input sanitization
This commit modernizes the frontend and backend to allow users to configure LLM parameters for their automation tasks: Backend changes: - Extended RunRequest model with llm_model, temperature, and max_tokens fields - Updated generate_next_action() to use configurable LLM parameters - Modified _run_tasks(), run_tasks(), and run_tasks_async() to accept and pass through LLM config - Updated queue_runner to extract LLM parameters from task payload - Parameters fall back to environment variables when not specified Frontend changes: - Added LLM configuration section to RunTaskForm with: - Model selection field (with examples) - Temperature slider (0.0-2.0) - Max tokens input (1-16384) - Added same LLM controls to TaskEditDialog for editing stored tasks - Updated TypeScript types to include new optional fields - Payload construction includes LLM parameters when provided Features: - Users can now specify custom LLM models per task - Temperature control for adjusting response randomness - Max tokens limit for controlling response length - All parameters are optional with sensible defaults - Backward compatible with existing tasks
Author
|
merge |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.