Rodrigo Rodriguez (Pragmatismo)
4ce06daf75
- Added initial 30s delay to compact prompt scheduler - Implemented async LLM summarization for conversation history - Reduced lock contention by minimizing critical sections - Added fallback to original text if summarization fails - Updated README with guidance for failed requirements - Added new `summarize` method to LLMProvider trait - Improved session manager query with proper DSL usage The changes optimize the prompt compaction process by: 1. Reducing lock contention through better resource management 2. Adding LLM-based summarization for better conversation compression 3. Making the system more resilient with proper error handling 4. Improving documentation for development practices
18 lines
No EOL
966 B
Markdown
18 lines
No EOL
966 B
Markdown
## LLM Strategy & Workflow
|
|
|
|
### Fallback Strategy (After 3 attempts / 10 minutes):
|
|
When initial attempts fail, sequentially try these LLMs:
|
|
1. **DeepSeek-V3-0324** (good architect, adventure, reliable, let little errors just to be fixed by gpt-*)
|
|
1. **DeepSeek-V3.1** (slower)
|
|
1. **gpt-5-chat** (slower, let warnings...)
|
|
1. **gpt-oss-120b**
|
|
1. **Claude (Web)**: Copy only the problem statement and create unit tests. Create/extend UI.
|
|
1. **Llama-3.3-70B-Instruct** (alternative)
|
|
|
|
### Development Workflow:
|
|
- **One requirement at a time** with sequential commits
|
|
- **On error**: Stop and consult Claude for guidance
|
|
- **Change progression**: Start with DeepSeek, conclude with gpt-oss-120b
|
|
- If a big req. fail, specify a @code file that has similar pattern or sample from official docs.
|
|
- **Final validation**: Use prompt "cargo check" with gpt-oss-120b
|
|
- Be humble, one requirement, one commit. But sometimes, freedom of caos is welcome - when no deadlines are set. |