co-mono/packages
Mario Zechner a2515cf43f Wire context event to preprocessor for per-LLM-call execution
- Change from contextTransform (runs once at agent start) to preprocessor
- preprocessor runs before EACH LLM call inside the agent loop
- ContextEvent now uses Message[] (pi-ai format) instead of AppMessage[]
- Deep copy handled by pi-ai preprocessor, not Agent

This enables:
- Pruning rules applied on every turn (not just agent start)
- /prune during long agent loop takes effect immediately
- Compaction can use same transforms (future work)
2025-12-30 22:42:20 +01:00
..
agent Wire context event to preprocessor for per-LLM-call execution 2025-12-30 22:42:20 +01:00
ai Remove emitLastMessage from continue(), use prompt(AppMessage) instead 2025-12-30 22:42:19 +01:00
coding-agent Wire context event to preprocessor for per-LLM-call execution 2025-12-30 22:42:20 +01:00
mom Session tree: simplify types, add branching API, comprehensive tests 2025-12-30 22:42:18 +01:00
pods Release v0.30.2 2025-12-26 03:25:55 +01:00
proxy Release v0.30.2 2025-12-26 03:25:55 +01:00
tui Release v0.30.2 2025-12-26 03:25:55 +01:00
web-ui Release v0.30.2 2025-12-26 03:25:55 +01:00