fix(agent): pass reasoning_content back to providers that require it
MiMo and DeepSeek V3.2/V4 reject multi-turn requests in thinking mode when the prior assistant message lacks reasoning_content with HTTP 400: "The reasoning_content in the thinking mode must be passed back to the API." Agent's ReAct loop is the worst-case scenario — every round produces tool calls, exactly the case DeepSeek's docs specify reasoning_content MUST participate in subsequent context. Plumb reasoning_content through the full assistant-message round-trip: - chat.Message / types.ChatResponse / types.AgentStep gain a reasoning_content field (AgentStep persists via the existing Message.AgentSteps jsonb column, no migration needed). - streamLLMToEventBus accumulates reasoning chunks into result.ReasoningContent and surfaces it on the round's ChatResponse. - engine.runReActIteration writes it onto AgentStep so cross-turn replay preserves it. - observe.appendToolResults attaches it to the same-turn assistant message; agent_history.buildAssistantHistoryMessages does the same on cross-turn replay. - RemoteAPIChat.ConvertMessages forwards it on assistant turns to openai.ChatCompletionMessage.ReasoningContent (already supported by go-openai); providers that don't recognize the field ignore it. Tests cover the three boundaries: ConvertMessages serializes it for upstream, appendToolResults preserves it within the same turn, and buildAssistantHistoryMessages replays it across turns. Scope is intentionally limited to Agent mode — KnowledgeQA's chat pipeline and Anthropic's signed thinking_blocks are separate fixes that require schema changes (rendered_content / thinking_blocks columns). Fixes #1302
This commit is contained in:
@@ -158,9 +158,10 @@ func buildAssistantHistoryMessages(m *types.Message) []chat.Message {
|
||||
continue
|
||||
}
|
||||
assistantMsg := chat.Message{
|
||||
Role: "assistant",
|
||||
Content: step.Thought,
|
||||
ToolCalls: make([]chat.ToolCall, 0, len(nonTerminalCalls)),
|
||||
Role: "assistant",
|
||||
Content: step.Thought,
|
||||
ReasoningContent: step.ReasoningContent,
|
||||
ToolCalls: make([]chat.ToolCall, 0, len(nonTerminalCalls)),
|
||||
}
|
||||
for _, tc := range nonTerminalCalls {
|
||||
argsJSON, _ := json.Marshal(tc.Args)
|
||||
|
||||
@@ -230,3 +230,40 @@ func TestFilterNonTerminalToolCalls(t *testing.T) {
|
||||
assert.Equal(t, agenttools.ToolWebSearch, out[1].Name)
|
||||
}
|
||||
}
|
||||
|
||||
// TestBuildAssistantHistoryMessages_ReplaysReasoningContent guards the
|
||||
// cross-turn replay path: AgentStep.ReasoningContent persisted on a prior turn
|
||||
// must be re-attached to the rebuilt assistant message, otherwise MiMo and
|
||||
// DeepSeek thinking-mode reject the next turn with HTTP 400 (issue #1302).
|
||||
func TestBuildAssistantHistoryMessages_ReplaysReasoningContent(t *testing.T) {
|
||||
msg := &types.Message{
|
||||
Role: "assistant",
|
||||
Content: "Found 3 matches in the docs.",
|
||||
AgentSteps: types.AgentSteps{
|
||||
{
|
||||
Iteration: 0,
|
||||
Thought: "Let me search.",
|
||||
ReasoningContent: "model's chain of thought",
|
||||
ToolCalls: []types.ToolCall{{
|
||||
ID: "call_1",
|
||||
Name: agenttools.ToolKnowledgeSearch,
|
||||
Args: map[string]interface{}{"query": "foo"},
|
||||
Result: &types.ToolResult{
|
||||
Success: true,
|
||||
Output: "doc A",
|
||||
},
|
||||
}},
|
||||
},
|
||||
},
|
||||
}
|
||||
got := buildAssistantHistoryMessages(msg)
|
||||
if !assert.Len(t, got, 3) {
|
||||
return
|
||||
}
|
||||
assert.Equal(t, "model's chain of thought", got[0].ReasoningContent,
|
||||
"reasoning_content from AgentStep must be replayed onto the rebuilt assistant message "+
|
||||
"so MiMo/DeepSeek thinking-mode does not 400 on multi-turn (issue #1302)")
|
||||
// Tool message and final answer message must NOT carry reasoning_content.
|
||||
assert.Empty(t, got[1].ReasoningContent)
|
||||
assert.Empty(t, got[2].ReasoningContent)
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user