mirror of
https://github.com/multica-ai/multica.git
synced 2026-08-04 17:18:35 +02:00
3dce7bc925
The "meet your new agent" chat used to insert a fake user message
("👋 Hi! Please introduce yourself …") and have the agent reply to it, so
the thread looked like the creator prompting the agent.
Drop the persisted user message. Flag the auto-created session
is_agent_intro (migration 147) and drive the intro run server-side: the
daemon builds a proactive self-introduction prompt for such sessions
(buildChatPrompt) instead of a "reply to their message" prompt. The intro
stays LLM-generated; the thread now opens with the agent's own message, as
if it reached out first.
- migration 147: chat_session.is_agent_intro
- CreateChatSession carries the flag; sendAgentWelcomeChat no longer
persists/publishes a user message
- daemon: ChatIntro threaded from session flag → intro prompt
Co-authored-by: multica-agent <github@multica.ai>
7 lines
468 B
SQL
7 lines
468 B
SQL
-- Flags a chat_session auto-created when its agent was created, so its first
|
|
-- turn is a proactive self-introduction from the agent. Such a session carries
|
|
-- NO visible user message: the intro run is driven server-side (see the chat
|
|
-- prompt in server/internal/daemon/prompt.go) so the thread reads as the agent
|
|
-- messaging its creator first, not the creator prompting the agent.
|
|
ALTER TABLE chat_session ADD COLUMN is_agent_intro BOOLEAN NOT NULL DEFAULT FALSE;
|