mirror of
https://github.com/memohai/Memoh.git
synced 2026-04-27 07:16:19 +09:00
Acbox Liu
de62f94315
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
51 lines
2.3 KiB
Go
51 lines
2.3 KiB
Go
package settings
|
|
|
|
const (
|
|
DefaultMaxContextLoadTime = 24 * 60
|
|
DefaultLanguage = "auto"
|
|
DefaultReasoningEffort = "medium"
|
|
DefaultHeartbeatInterval = 30
|
|
)
|
|
|
|
type Settings struct {
|
|
ChatModelID string `json:"chat_model_id"`
|
|
SearchProviderID string `json:"search_provider_id"`
|
|
MemoryProviderID string `json:"memory_provider_id"`
|
|
TtsModelID string `json:"tts_model_id"`
|
|
BrowserContextID string `json:"browser_context_id"`
|
|
MaxContextLoadTime int `json:"max_context_load_time"`
|
|
MaxContextTokens int `json:"max_context_tokens"`
|
|
Language string `json:"language"`
|
|
AllowGuest bool `json:"allow_guest"`
|
|
ReasoningEnabled bool `json:"reasoning_enabled"`
|
|
ReasoningEffort string `json:"reasoning_effort"`
|
|
HeartbeatEnabled bool `json:"heartbeat_enabled"`
|
|
HeartbeatInterval int `json:"heartbeat_interval"`
|
|
HeartbeatModelID string `json:"heartbeat_model_id"`
|
|
TitleModelID string `json:"title_model_id"`
|
|
CompactionEnabled bool `json:"compaction_enabled"`
|
|
CompactionThreshold int `json:"compaction_threshold"`
|
|
CompactionModelID string `json:"compaction_model_id,omitempty"`
|
|
}
|
|
|
|
type UpsertRequest struct {
|
|
ChatModelID string `json:"chat_model_id,omitempty"`
|
|
SearchProviderID string `json:"search_provider_id,omitempty"`
|
|
MemoryProviderID string `json:"memory_provider_id,omitempty"`
|
|
TtsModelID string `json:"tts_model_id,omitempty"`
|
|
BrowserContextID string `json:"browser_context_id,omitempty"`
|
|
MaxContextLoadTime *int `json:"max_context_load_time,omitempty"`
|
|
MaxContextTokens *int `json:"max_context_tokens,omitempty"`
|
|
Language string `json:"language,omitempty"`
|
|
AllowGuest *bool `json:"allow_guest,omitempty"`
|
|
ReasoningEnabled *bool `json:"reasoning_enabled,omitempty"`
|
|
ReasoningEffort *string `json:"reasoning_effort,omitempty"`
|
|
HeartbeatEnabled *bool `json:"heartbeat_enabled,omitempty"`
|
|
HeartbeatInterval *int `json:"heartbeat_interval,omitempty"`
|
|
HeartbeatModelID string `json:"heartbeat_model_id,omitempty"`
|
|
TitleModelID string `json:"title_model_id,omitempty"`
|
|
CompactionEnabled *bool `json:"compaction_enabled,omitempty"`
|
|
CompactionThreshold *int `json:"compaction_threshold,omitempty"`
|
|
CompactionModelID *string `json:"compaction_model_id,omitempty"`
|
|
}
|