references/lobe-chat
1
0
Fork 0
mirror of https://github.com/lobehub/lobe-chat.git synced 2026-06-14 03:30:19 +00:00
Code Issues Packages Projects Releases Wiki Activity

🐛 fix(agent-runtime): persist assistant reasoning to DB (#15690)

Browse Source
This commit is contained in:
YuTengjing
2026-06-11 21:05:23 +08:00
committed by GitHub
parent 813d756b9c
commit f6c23e3654
2 changed files with 218 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
apps/server/src/modules/AgentRuntime/RuntimeExecutors.ts
+56 -8
View File
@@ -202,6 +202,51 @@ const isEmptyModelCompletion = (params: {
return true;
};
type ReasoningReplayNode = {
children?: ReasoningReplayNode[];
members?: ReasoningReplayNode[];
reasoning?: unknown;
};
const stripAssistantReasoningForReplay = (messages: UIChatMessage[]): UIChatMessage[] => {
const stripMessage = <T extends ReasoningReplayNode>(message: T): T => {
let changed = false;
const children = message.children?.map((child) => {
const strippedChild = stripMessage(child);
if (strippedChild !== child) changed = true;
return strippedChild;
});
const members = message.members?.map((member) => {
const strippedMember = stripMessage(member);
if (strippedMember !== member) changed = true;
return strippedMember;
});
if ('reasoning' in message) changed = true;
if (!changed) return message;
const { reasoning: _reasoning, ...messageWithoutReasoning } = message;
return {
...messageWithoutReasoning,
...(children ? { children } : {}),
...(members ? { members } : {}),
} as T;
};
let changed = false;
const strippedMessages = messages.map((message) => {
const strippedMessage = stripMessage(message);
if (strippedMessage !== message) changed = true;
return strippedMessage;
});
return changed ? strippedMessages : messages;
};
const GEN_AI_FUNCTION_TOOL_TYPE: ToolType = 'function';
type ToolFailureKind = 'replan' | 'retry' | 'stop';
@@ -704,13 +749,16 @@ export const createRuntimeExecutors = (
modelSupportsPreserveThinking && typeof preserveThinkingConfigured === 'boolean'
? preserveThinkingConfigured
: undefined;
const messagesForContext = shouldReplayAssistantReasoning
? (llmPayload.messages as UIChatMessage[])
: stripAssistantReasoningForReplay(llmPayload.messages as UIChatMessage[]);
// Extract <refer_topic> tags from messages and fetch summaries.
// Skip if messages already contain injected topic_reference_context
// (e.g., from client-side contextEngineering preprocessing) to avoid double injection.
let topicReferences;
const alreadyHasTopicRefs = (
llmPayload.messages as Array<{ content: string | unknown }>
messagesForContext as Array<{ content: string | unknown }>
).some(
(m) => typeof m.content === 'string' && m.content.includes('topic_reference_context'),
);
@@ -719,7 +767,7 @@ export const createRuntimeExecutors = (
const topicModel = new TopicModel(ctx.serverDB, ctx.userId, ctx.workspaceId);
const messageModel = new MessageModelClass(ctx.serverDB, ctx.userId, ctx.workspaceId);
topicReferences = await resolveTopicReferences(
llmPayload.messages as Array<{ content: string | unknown }>,
messagesForContext as Array<{ content: string | unknown }>,
async (topicId) => topicModel.findById(topicId),
async (topicId) => {
const topic = await topicModel.findById(topicId);
@@ -761,7 +809,7 @@ export const createRuntimeExecutors = (
agentConfig?.slug === 'web-onboarding' ||
resolved.enabledToolIds.includes('lobe-web-onboarding');
const alreadyHasOnboardingContext = (
llmPayload.messages as Array<{ content: string | unknown }>
messagesForContext as Array<{ content: string | unknown }>
).some((message) => {
if (typeof message.content !== 'string') return false;
@@ -1042,7 +1090,7 @@ export const createRuntimeExecutors = (
name: kb.name ?? '',
})),
},
messages: llmPayload.messages as UIChatMessage[],
messages: messagesForContext,
model,
provider,
systemRole: agentConfig.systemRole ?? undefined,
@@ -1070,14 +1118,14 @@ export const createRuntimeExecutors = (
CONTEXT_ENGINEERING_SPAN_NAME,
{
attributes: buildContextEngineeringAttributes({
hasImages: (llmPayload.messages as Array<{ content?: unknown }>).some(
hasImages: (messagesForContext as Array<{ content?: unknown }>).some(
(m) =>
Array.isArray(m.content) &&
(m.content as Array<{ type?: string }>).some((p) => p?.type === 'image_url'),
),
historyCompressed:
Array.isArray(llmPayload.messages) &&
llmPayload.messages.some((m: { role?: string }) => m?.role === 'compressedGroup'),
Array.isArray(messagesForContext) &&
messagesForContext.some((m: { role?: string }) => m?.role === 'compressedGroup'),
knowledgeCount:
(contextEngineInput.knowledge?.knowledgeBases?.length ?? 0) +
(contextEngineInput.knowledge?.fileContents?.length ?? 0),
@@ -1085,7 +1133,7 @@ export const createRuntimeExecutors = (
(contextEngineInput.knowledge?.knowledgeBases?.length ?? 0) > 0 ||
(contextEngineInput.knowledge?.fileContents?.length ?? 0) > 0,
memoryInjected: Boolean(contextEngineInput.userMemory?.memories),
messageCount: llmPayload.messages.length,
messageCount: messagesForContext.length,
operationId,
stepIndex,
systemRoleLength: contextEngineInput.systemRole?.length,
apps/server/src/modules/AgentRuntime/__tests__/RuntimeExecutors.test.ts
+162
View File
@@ -1611,6 +1611,168 @@ describe('RuntimeExecutors', () => {
);
});
it('should strip stored assistant reasoning before context processing when replay gate is off', async () => {
const ctxWithConfig: RuntimeExecutorContext = {
...ctx,
agentConfig: {
plugins: [],
systemRole: 'test',
},
};
const executors = createRuntimeExecutors(ctxWithConfig);
const state = createMockState();
const messages = [
{
content: 'Previous answer',
reasoning: { content: 'stored reasoning should stay display-only' },
role: 'assistant',
},
{ content: 'Continue', role: 'user' },
];
await executors.call_llm!(
{
payload: {
messages,
model: 'gpt-4',
provider: 'openai',
},
type: 'call_llm' as const,
},
state,
);
const engineInput = engineSpy.mock.calls[0][0];
expect(engineInput.messages[0]).toEqual({
content: 'Previous answer',
role: 'assistant',
});
expect(messages[0]).toEqual(
expect.objectContaining({
reasoning: { content: 'stored reasoning should stay display-only' },
}),
);
});
it('should strip stored reasoning from grouped assistant messages before context processing when replay gate is off', async () => {
const ctxWithConfig: RuntimeExecutorContext = {
...ctx,
agentConfig: {
plugins: [],
systemRole: 'test',
},
};
const executors = createRuntimeExecutors(ctxWithConfig);
const state = createMockState();
const groupedChild = {
content: 'Grouped answer',
id: 'group-child-1',
reasoning: { content: 'grouped child reasoning should stay display-only' },
role: 'assistant',
};
const councilMember = {
content: 'Council member answer',
id: 'member-1',
reasoning: { content: 'member reasoning should stay display-only' },
role: 'assistant',
};
const nestedCouncilChild = {
content: 'Nested council answer',
id: 'member-child-1',
reasoning: { content: 'nested member reasoning should stay display-only' },
role: 'assistant',
};
const messages = [
{
children: [groupedChild],
content: '',
id: 'group-1',
role: 'assistantGroup',
},
{
content: '',
id: 'council-1',
members: [
councilMember,
{
children: [nestedCouncilChild],
content: '',
id: 'member-group-1',
role: 'assistantGroup',
},
],
role: 'agentCouncil',
},
{ content: 'Continue', role: 'user' },
];
await executors.call_llm!(
{
payload: {
messages,
model: 'gpt-4',
provider: 'openai',
},
type: 'call_llm' as const,
},
state,
);
const engineInput = engineSpy.mock.calls[0][0];
expect(engineInput.messages[0].children[0]).not.toHaveProperty('reasoning');
expect(engineInput.messages[1].members[0]).not.toHaveProperty('reasoning');
expect(engineInput.messages[1].members[1].children[0]).not.toHaveProperty('reasoning');
expect(groupedChild).toHaveProperty('reasoning');
expect(councilMember).toHaveProperty('reasoning');
expect(nestedCouncilChild).toHaveProperty('reasoning');
});
it('should keep stored assistant reasoning before context processing when replay gate is enabled', async () => {
const ctxWithConfig: RuntimeExecutorContext = {
...ctx,
agentConfig: {
chatConfig: { preserveThinking: true },
plugins: [],
systemRole: 'test',
},
};
const executors = createRuntimeExecutors(ctxWithConfig);
const state = createMockState({
modelRuntimeConfig: {
model: 'qwen3.6-plus',
provider: 'qwen',
},
});
await executors.call_llm!(
{
payload: {
messages: [
{
content: 'Previous answer',
reasoning: { content: 'reasoning to replay' },
role: 'assistant',
},
{ content: 'Continue', role: 'user' },
],
model: 'qwen3.6-plus',
provider: 'qwen',
},
type: 'call_llm' as const,
},
state,
);
const engineInput = engineSpy.mock.calls[0][0];
expect(engineInput.messages[0]).toEqual(
expect.objectContaining({
content: 'Previous answer',
reasoning: { content: 'reasoning to replay' },
role: 'assistant',
}),
);
});
it('should not call serverMessagesEngine when agentConfig is not set', async () => {
const executors = createRuntimeExecutors(ctx); // ctx without agentConfig
const state = createMockState();