This repository has been archived on 2026-03-24. You can view files and clone it. You cannot open issues or pull requests or push a commit.

Claude 167fd0a7b4 Add outcome-based learning system for swarm agents ...

Introduce a feedback loop where task outcomes (win/loss, success/failure)
feed back into agent bidding strategy. Borrows the "learn from outcomes"
concept from Spark Intelligence but builds it natively on Timmy's existing
SQLite + swarm architecture.

New module: src/swarm/learner.py
- Records every bid outcome with task description context
- Computes per-agent metrics: win rate, success rate, keyword performance
- suggest_bid() adjusts bids based on historical performance
- learned_keywords() discovers what task types agents actually excel at

Changes:
- persona_node: _compute_bid() now consults learner for adaptive adjustments
- coordinator: complete_task/fail_task feed results into learner
- coordinator: run_auction_and_assign records all bid outcomes
- routes/swarm: add /swarm/insights and /swarm/insights/{agent_id} endpoints
- routes/swarm: add POST /swarm/tasks/{task_id}/fail endpoint

All 413 tests pass (23 new + 390 existing).

https://claude.ai/code/session_01E5jhTCwSUnJk9p9zrTMVUJ

2026-02-22 22:04:37 +00:00

9.8 KiB

Raw Blame History

View Raw