AgentsMeeting

hmo/AgentsMeeting

Fork 0

Commit Graph

Author	SHA1	Message	Date
mohe	ae16cd4e0f	simplify: remove __REPLY__ marker, only __SILENT__ needed Default LLM behavior is to reply - no prefix needed. Only the exceptional case (silence) needs a marker. Updated xmpp_bot.py, MEMORY.md, and protocol doc.	2026-06-14 02:00:33 +08:00
mohe	34e4477642	docs: clarify markers must be bare text, no backticks Also updated xmpp_bot.py regex to handle backtick-wrapped markers defensively. Updated MEMORY.md prompt to require bare markers.	2026-06-14 01:58:00 +08:00
mohe	90b729c292	docs: add observer mode protocol (__SILENT__/__REPLY__) Define code+LLM collaboration protocol for group chat participation: - Code layer: no @mention gate, forward all msgs to LLM - LLM layer: output __SILENT__ (discard) or __REPLY__ (send) - Documented in MEMORY.md (LLM prompt) and AgentsMeeting (shared ref) - Update xmpp_bot.py to remove @mention gate	2026-06-14 00:42:05 +08:00

Author

SHA1

Message

Date

mohe

ae16cd4e0f

simplify: remove __REPLY__ marker, only __SILENT__ needed

Default LLM behavior is to reply - no prefix needed.
Only the exceptional case (silence) needs a marker.
Updated xmpp_bot.py, MEMORY.md, and protocol doc.

2026-06-14 02:00:33 +08:00

mohe

34e4477642

docs: clarify markers must be bare text, no backticks

Also updated xmpp_bot.py regex to handle backtick-wrapped markers defensively.
Updated MEMORY.md prompt to require bare markers.

2026-06-14 01:58:00 +08:00

mohe

90b729c292

docs: add observer mode protocol (__SILENT__/__REPLY__)

Define code+LLM collaboration protocol for group chat participation:
- Code layer: no @mention gate, forward all msgs to LLM
- LLM layer: output __SILENT__ (discard) or __REPLY__ (send)
- Documented in MEMORY.md (LLM prompt) and AgentsMeeting (shared ref)
- Update xmpp_bot.py to remove @mention gate

2026-06-14 00:42:05 +08:00

3 Commits