Rodrigo Rodriguez (Pragmatismo)
856e2f0252
Add logic to save user messages to session history for better traceability and context continuity. Simplify session creation error handling and remove redundant warning on closed response channel. Update README with guidance on maintaining production-ready source code. |
||
|---|---|---|
| .. | ||
| add-keyword.md | ||
| add-model.md | ||
| add-service.md | ||
| botserver.md | ||
| cli.md | ||
| doc-guide-topic.md | ||
| fix-errors.md | ||
| ide.md | ||
| README.md | ||
| shared.md | ||
LLM Strategy & Workflow
Fallback Strategy (After 3 attempts / 10 minutes):
When initial attempts fail, sequentially try these LLMs:
- DeepSeek-V3-0324 (good architect, adventure, reliable, let little errors just to be fixed by gpt-*)
- DeepSeek-V3.1 (slower)
- gpt-5-chat (slower, let warnings...)
- gpt-oss-120b
- Claude (Web): Copy only the problem statement and create unit tests. Create/extend UI.
- 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.
- Keep in the source codebase only deployed and tested source, no lab source code in main project. At least, use optional features to introduce new behaviour gradually in PRODUCTION.