Tracked: morrowind agent (py/cfg), skills/, training-data/, research/, notes/, specs/, test-results/, metrics/, heartbeat/, briefings/, memories/, skins/, hooks/, decisions.md, OPERATIONS.md, SOUL.md Excluded: screenshots, PNGs, binaries, sessions, databases, secrets, audio cache, timmy-config/ and timmy-telemetry/ (separate repos)
7 lines
789 B
JSON
7 lines
789 B
JSON
[
|
|
{
|
|
"prompt": "Review the Timmy-Time-dashboard codebase for performance optimization opportunities specifically related to local LLM inference on Apple M3 Max with 36GB RAM. Check: 1) How many redundant LLM calls are made per user interaction, 2) Whether context windows are being used efficiently or wasted, 3) Model loading/unloading patterns, 4) Memory usage patterns that could cause swapping, 5) Async patterns that could be blocking, 6) Prompt engineering issues (overly long system prompts eating into context), 7) Caching opportunities for repeated queries. Look at src/timmy/agent.py, src/timmy/agents/, src/timmy/agentic_loop.py, src/timmy/session.py, config/providers.yaml, config/agents.yaml.",
|
|
"chosen": "",
|
|
"session": "session_20260314_092659_764164.json"
|
|
}
|
|
] |