feat: Add CodexLens Manager to dashboard and enhance GPU management

- Introduced a new CodexLens Manager item in the dashboard for easier access.
- Implemented GPU management commands in the CLI, including listing available GPUs, selecting a specific GPU, and resetting to automatic detection.
- Enhanced the embedding generation process to utilize GPU resources more effectively, including batch size optimization for better performance.
- Updated the embedder to support device ID options for GPU selection, ensuring compatibility with DirectML and CUDA.
- Added detailed logging and error handling for GPU detection and selection processes.
- Updated package version to 6.2.9 and added comprehensive documentation for Codex Agent Execution Protocol.
This commit is contained in:
catlog22
2025-12-23 18:35:30 +08:00
parent 5ff2a43b70
commit 39056292b7
17 changed files with 1834 additions and 78 deletions

View File

@@ -1,10 +1,5 @@
# Write Mode Protocol
## Mode Definition
**Mode**: `write` (FILE OPERATIONS) / `auto` (FULL OPERATIONS)
**Tools**: Codex (auto), Gemini/Qwen (write)
## Operation Boundaries
### MODE: write
@@ -15,12 +10,6 @@
**Restrictions**: Follow project conventions, cannot break existing functionality
### MODE: auto (Codex only)
- All `write` mode operations
- Run tests and builds
- Commit code incrementally
- Full autonomous development
**Constraint**: Must test every change
## Execution Flow
@@ -33,16 +22,6 @@
5. **Validate** changes
6. **Report** file changes
### MODE: auto
1. **Parse** all 6 fields
2. **Analyze** CONTEXT files - find 3+ similar patterns
3. **Plan** implementation following RULES
4. **Generate** code with tests
5. **Run** tests continuously
6. **Commit** working code incrementally
7. **Validate** EXPECTED deliverables
8. **Report** results
## Core Requirements
**ALWAYS**: