e9be53e830
When a custom agent has `MultiTurnEnabled=false`, `applyAgentOverridesToChatManage`
sets `chatManage.MaxRounds = 0` to signal "no history". Two pipeline plugins
mistreated this zero value as "use the global default" and silently re-loaded
session history into the LLM context:
- `PluginLoadHistory` fell back to `Conversation.MaxRounds` when
`chatManage.MaxRounds == 0`.
- `PluginQueryUnderstand.loadHistory` had the same fallback, and even when
`LOAD_HISTORY` was skipped it would re-populate `chatManage.History`,
leaking previous turns into rewrite, image analysis, and the final answer.
The RAG branch in `session_knowledge_qa` also added `LOAD_HISTORY`
unconditionally, unlike the pure-chat branch which guarded it with `hasHistory`.
This change:
- Treats `chatManage.MaxRounds <= 0` as an explicit disable in both plugins;
no fallback to global config.
- Makes the RAG pipeline consistent with the pure-chat path by gating
`LOAD_HISTORY` on `hasHistory`.
- Removes the duplicated `Current Time: {{current_time}}` line from
`agent_system_prompt.yaml`. The agent already receives a fresh
`<runtime_context><current_time>` block with each turn from
`observe.buildRuntimeContextBlock`, so the static placeholder was
redundant.
The ReAct agent path (`session_agent_qa`) already checked `MultiTurnEnabled`
directly and is not affected.
Closes #1479
73 lines
2.0 KiB
Go
73 lines
2.0 KiB
Go
package chatpipeline
|
|
|
|
import (
|
|
"context"
|
|
|
|
"github.com/Tencent/WeKnora/internal/config"
|
|
"github.com/Tencent/WeKnora/internal/types"
|
|
"github.com/Tencent/WeKnora/internal/types/interfaces"
|
|
)
|
|
|
|
type PluginLoadHistory struct {
|
|
messageService interfaces.MessageService
|
|
config *config.Config
|
|
}
|
|
|
|
func NewPluginLoadHistory(eventManager *EventManager,
|
|
messageService interfaces.MessageService,
|
|
config *config.Config,
|
|
) *PluginLoadHistory {
|
|
res := &PluginLoadHistory{
|
|
messageService: messageService,
|
|
config: config,
|
|
}
|
|
eventManager.Register(res)
|
|
return res
|
|
}
|
|
|
|
func (p *PluginLoadHistory) ActivationEvents() []types.EventType {
|
|
return []types.EventType{types.LOAD_HISTORY}
|
|
}
|
|
|
|
func (p *PluginLoadHistory) OnEvent(ctx context.Context,
|
|
eventType types.EventType, chatManage *types.ChatManage, next func() *PluginError,
|
|
) *PluginError {
|
|
// chatManage.MaxRounds == 0 means multi-turn is explicitly disabled
|
|
// (e.g. by a custom agent with MultiTurnEnabled=false). Skip loading so
|
|
// history doesn't leak into the LLM context. We do NOT fall back to the
|
|
// global Conversation.MaxRounds default here, otherwise the disable flag
|
|
// would be silently overridden.
|
|
if chatManage.MaxRounds <= 0 {
|
|
pipelineInfo(ctx, "LoadHistory", "skipped", map[string]interface{}{
|
|
"session_id": chatManage.SessionID,
|
|
"reason": "multi_turn_disabled",
|
|
})
|
|
return next()
|
|
}
|
|
maxRounds := chatManage.MaxRounds
|
|
|
|
pipelineInfo(ctx, "LoadHistory", "input", map[string]interface{}{
|
|
"session_id": chatManage.SessionID,
|
|
"max_rounds": maxRounds,
|
|
})
|
|
|
|
historyList, err := loadAndProcessHistory(ctx, p.messageService, chatManage.SessionID, maxRounds, maxRounds*2+10)
|
|
if err != nil {
|
|
pipelineWarn(ctx, "LoadHistory", "history_fetch", map[string]interface{}{
|
|
"session_id": chatManage.SessionID,
|
|
"error": err.Error(),
|
|
})
|
|
return next()
|
|
}
|
|
|
|
chatManage.History = historyList
|
|
|
|
pipelineInfo(ctx, "LoadHistory", "output", map[string]interface{}{
|
|
"session_id": chatManage.SessionID,
|
|
"history_rounds": len(historyList),
|
|
"max_rounds": maxRounds,
|
|
})
|
|
|
|
return next()
|
|
}
|