Iflow-cli support #54
Open
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
…t-path fix: Correct system prompt path resolution for Cursor Agent
…ename The filename contained an invisible backspace character (\b) that was causing issues when cloning the repository. This has been fixed by renaming the file to remove the special character.
- Add Codex CLI type and model mappings (gpt-5) - Implement Codex CLI class with session persistence and rollout file handling - Add tool mappings for Codex operations (exec_command, apply_patch, mcp_tool_call) - Implement apply_patch tool summary processing with filename extraction - Add image reference injection for Codex CLI ([Image opactorai#1], [Image opactorai#2]) - Fix duplicate agent_message handler to prevent message duplication - Add comprehensive logging for Codex CLI debugging - Support experimental_resume parameter for session restoration - Change AGENT.md to AGENTS.md across all CLI implementations
- Add comprehensive project cleanup with running process detection - Implement safe file deletion with retry mechanisms - Handle transient filesystem locks and read-only files gracefully - Improve error handling and logging for project initialization/cleanup
- Add GET endpoint for serving uploaded images (/api/assets/{project_id}/{filename})
- Update ImageAttachment schema to support both base64_data and file paths
- Add comprehensive image processing with attachment metadata generation
- Add extensive logging for debugging image processing pipeline
- Update CLI preferences API with better status responses
- Implement automatic image upload before sending chat messages - Add data URL to blob conversion for image processing - Include FormData multipart upload with proper file handling - Add prepared images to API requests with absolute paths - Improve error handling and user feedback for image operations
- Remove image path text injection from ChatInput component - Update ChatInterface to handle images as separate parameters - Enhance MessageList with better image display handling - Clean up image processing flow between components
- Replace text image paths with actual 160x160px image thumbnails - Use attachment metadata from backend for proper image URLs - Add hover effects with image numbers and filename tooltips - Implement fallback icons for failed image loads - Add comprehensive debugging logs for image URL generation - Support both new attachment metadata and legacy path parsing
- Execute ACT API directly from main page with image data - Track uploaded image absolute paths during asset upload - Send original prompt without image path text injection - Navigate to chat page after successful ACT execution - Improve error handling for image upload failures
- Update runAct to process both new path-based and legacy base64 images - Add comprehensive image format conversion for API compatibility - Clean up image data processing with proper type checking - Improve error handling for different image input formats
- Add Codex CLI option to CLI selector components - Update CLI type definitions to include Codex - Improve CLI setup wizard with better option handling - Enhance CLI selector with consistent styling and options
- Integrate CodexCLI into the CLI manager for availability checks - Enhance debug logging for CLI status verification - Update GlobalSettings component to include Codex CLI options and assets
- Integrate new CLI base abstractions and adapters for improved modularity - Implement SQLite migration execution during application startup - Update CLI type handling and session management for better consistency - Enhance error handling and logging across CLI components
- Integrate Qwen Coder and Gemini CLI options into the application - Update GlobalSettings and HomePage components to reflect new CLI options - Enhance image handling in ChatInput for Qwen Coder and Gemini - Improve assistant selection logic to accommodate new models
- Rename Qwen Coder to Qwen3 Coder Plus across various components - Update model selection logic in HomePage and ChatPage - Improve GlobalSettings and ProjectSettings to reflect new model details - Enhance error handling and logging in QwenCLI adapter
- Introduce Plus Jakarta Sans font for improved text styling - Define assistant brand colors for consistent theming across components - Update HomePage and ChatPage to utilize new colors and styles - Improve scrollbar styles for light and dark themes - Add Symbol_white.png asset for visual enhancements
…nality - Add ThinkingSection component for improved display of thinking messages - Refactor ChatLog to utilize the new ThinkingSection for rendering thinking content - Enhance content formatting and expand/collapse functionality in ThinkingSection
…ChatPage - Introduce sessionStorage to persist selected assistant and model across page loads - Implement logic to differentiate between fresh page loads and navigation - Update HomePage to handle model and assistant selections more effectively - Enhance ChatPage to store selected parameters from URL for better user experience - Improve UI with gradient backgrounds for a more engaging interface
- Add critical file path rules for Next.js projects to system prompt documentation - Improve HomePage UI with updated class names for better accessibility and visual consistency - Revise example prompts for various applications to reflect modern design standards and user experience
…ling and error logging - Normalize default branch handling in GitHub repository pushes to ensure consistency, even for empty repos. - Update Vercel deployment logic to prefer the last pushed branch or default branch for better deployment accuracy. - Improve error logging during GitHub push and Vercel deployment processes for better debugging. - Refactor project dependency installation to ensure npm is used consistently, cleaning up non-npm artifacts if detected. - Enhance UI components for better user experience and responsiveness across various project settings.
- Replace main image with promotional and agents images for better representation. - Update demo GIF to the latest version for improved demonstration. - Add detailed sections for supported AI coding agents, including installation instructions and features. - Remove outdated design comparison section to streamline content.
- Eliminate deprecated API key and model configuration lines to streamline installation instructions. - Focus on providing clear and concise setup guidance for users.
- Replace multiple images with a single, updated Claudable image for a cleaner presentation. - Streamline the README layout to enhance clarity and focus on key features.
PR: windows bug fix (issue 14,15, 27)
model is now changable mid prompt
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 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.
https://github.com/iflow-ai/iflow-cli