refactor(agent): rebuild multi-turn history from DB, drop llmcontext layer
The Agent ran a parallel context cache (Redis/in-memory) on top of the messages table to feed multi-turn history into the LLM. That dual-write caused subtle drift (e.g. compression diverging from DB, system-prompt swaps lost on restart) and required a separate ClearContext path on session/IM clear. Make the messages table the single source of truth: - Add service.LoadAgentHistory: rebuilds chat.Message history per turn from the persisted messages, expanding AgentSteps into proper OpenAI assistant_with_tool_calls + tool messages and replaying the canonical final answer (with <think> blocks stripped). final_answer tool calls are filtered to avoid duplicating the trailing answer. - Make AgentEngine stateless across turns: drop ContextManager / sessionID cache plumbing from the engine, agent service, and CreateAgentEngine signature. The engine only uses sessionID for logging/event emission. - Wire AgentQA to load history from DB on demand using HistoryTurns (default 5) when MultiTurnEnabled, otherwise run with empty history. - Delete the llmcontext package (ContextManager interface, Redis/memory storage, factory) and the SessionService.ClearContext API path; IM /clear and session message clear no longer need to invalidate cache. Behavior preserved: KnowledgeQA-mode replay is unchanged (turns with empty AgentSteps just produce the single canonical assistant message), and Agent-mode turns now consistently see prior tool calls and results.
This commit is contained in:
@@ -374,10 +374,6 @@ func (h *Handler) ClearSessionMessages(c *gin.Context) {
|
||||
return
|
||||
}
|
||||
|
||||
if err := h.sessionService.ClearContext(ctx, id); err != nil {
|
||||
logger.Warnf(ctx, "Failed to clear LLM context for session %s: %v", id, err)
|
||||
}
|
||||
|
||||
logger.Infof(ctx, "Session messages cleared successfully, ID: %s", id)
|
||||
c.JSON(http.StatusOK, gin.H{
|
||||
"success": true,
|
||||
|
||||
Reference in New Issue
Block a user