feat: add context compaction to automatically summarize old messages (#compaction) (#276)

When input tokens exceed a configurable threshold after a conversation round,
the system asynchronously compacts older messages into a summary. Cascading
compactions reference prior summaries via <prior_context> tags to maintain
conversational continuity without duplicating content.

- Add bot_history_message_compacts table and compact_id on messages
- Add compaction_enabled, compaction_threshold, compaction_model_id to bots
- Implement compaction service (internal/compaction) with LLM summarization
- Integrate into conversation flow: replace compacted messages with summaries
  wrapped in <summary> tags during context loading
- Add REST API endpoints (GET/DELETE /bots/:bot_id/compaction/logs)
- Add frontend Compaction tab with settings and log viewer
- Wire compaction service into both dev (cmd/agent) and prod (cmd/memoh) entry points
- Update test mocks to include new GetBotByID columns
This commit is contained in:
Acbox Liu
2026-03-22 14:26:00 +08:00
committed by GitHub
parent 91e5e44509
commit de62f94315
40 changed files with 2375 additions and 197 deletions
+33
View File
@@ -0,0 +1,33 @@
package compaction
import "time"
// Log represents a compaction log entry.
type Log struct {
ID string `json:"id"`
BotID string `json:"bot_id"`
SessionID string `json:"session_id,omitempty"`
Status string `json:"status"`
Summary string `json:"summary"`
MessageCount int `json:"message_count"`
ErrorMessage string `json:"error_message"`
Usage any `json:"usage,omitempty"`
ModelID string `json:"model_id,omitempty"`
StartedAt time.Time `json:"started_at"`
CompletedAt *time.Time `json:"completed_at,omitempty"`
}
// ListLogsResponse is the API response for listing compaction logs.
type ListLogsResponse struct {
Items []Log `json:"items"`
}
// TriggerConfig holds the parameters needed to trigger a compaction.
type TriggerConfig struct {
BotID string
SessionID string
ModelID string
ClientType string
APIKey string //nolint:gosec // runtime credential, not a hardcoded secret
BaseURL string
}