修复吞字问题

internal/httpapi/openai/chat/chat_stream_runtime.go

@@ -107,6 +107,23 @@ func (s *chatStreamRuntime) sendChunk(v any) {
 	}
 }
 
+func (s *chatStreamRuntime) sendDelta(delta map[string]any) {
+	if len(delta) == 0 {
+		return
+	}
+	if !s.firstChunkSent {
+		delta["role"] = "assistant"
+		s.firstChunkSent = true
+	}
+	s.sendChunk(openaifmt.BuildChatStreamChunk(
+		s.completionID,
+		s.created,
+		s.model,
+		[]map[string]any{openaifmt.BuildChatStreamDeltaChoice(0, delta)},
+		nil,
+	))
+}
+
 func (s *chatStreamRuntime) sendDone() {
 	_, _ = s.w.Write([]byte("data: [DONE]\n\n"))
 	if s.canFlush {
@@ -257,7 +274,6 @@ func (s *chatStreamRuntime) onParsed(parsed sse.LineResult) streamengine.ParsedD
 		return streamengine.ParsedDecision{Stop: true, StopReason: streamengine.StopReasonHandlerRequested}
 	}
 
-	newChoices := make([]map[string]any, 0, len(parsed.Parts))
 	contentSeen := false
 	for _, p := range parsed.ToolDetectionThinkingParts {
 		trimmed := sse.TrimContinuationOverlap(s.toolDetectionThinking.String(), p.Text)
@@ -266,11 +282,6 @@ func (s *chatStreamRuntime) onParsed(parsed sse.LineResult) streamengine.ParsedD
 		}
 	}
 	for _, p := range parsed.Parts {
-		delta := map[string]any{}
-		if !s.firstChunkSent {
-			delta["role"] = "assistant"
-			s.firstChunkSent = true
-		}
 		if p.Type == "thinking" {
 			rawTrimmed := sse.TrimContinuationOverlap(s.rawThinking.String(), p.Text)
 			if rawTrimmed != "" {
@@ -287,7 +298,7 @@ func (s *chatStreamRuntime) onParsed(parsed sse.LineResult) streamengine.ParsedD
 					continue
 				}
 				s.thinking.WriteString(trimmed)
-				delta["reasoning_content"] = trimmed
+				s.sendDelta(map[string]any{"reasoning_content": trimmed})
 			}
 		} else {
 			rawTrimmed := sse.TrimContinuationOverlap(s.rawText.String(), p.Text)
@@ -308,7 +319,7 @@ func (s *chatStreamRuntime) onParsed(parsed sse.LineResult) streamengine.ParsedD
 				if trimmed == "" {
 					continue
 				}
-				delta["content"] = trimmed
+				s.sendDelta(map[string]any{"content": trimmed})
 			} else {
 				events := toolstream.ProcessChunk(&s.toolSieve, rawTrimmed, s.toolNames)
 				for _, evt := range events {
@@ -328,11 +339,7 @@ func (s *chatStreamRuntime) onParsed(parsed sse.LineResult) streamengine.ParsedD
 							"tool_calls": formatted,
 						}
 						s.toolCallsEmitted = true
-						if !s.firstChunkSent {
-							tcDelta["role"] = "assistant"
-							s.firstChunkSent = true
-						}
-						newChoices = append(newChoices, openaifmt.BuildChatStreamDeltaChoice(0, tcDelta))
+						s.sendDelta(tcDelta)
 						continue
 					}
 					if len(evt.ToolCalls) > 0 {
@@ -341,11 +348,7 @@ func (s *chatStreamRuntime) onParsed(parsed sse.LineResult) streamengine.ParsedD
 						tcDelta := map[string]any{
 							"tool_calls": formatFinalStreamToolCallsWithStableIDs(evt.ToolCalls, s.streamToolCallIDs, s.toolsRaw),
 						}
-						if !s.firstChunkSent {
-							tcDelta["role"] = "assistant"
-							s.firstChunkSent = true
-						}
-						newChoices = append(newChoices, openaifmt.BuildChatStreamDeltaChoice(0, tcDelta))
+						s.sendDelta(tcDelta)
 						s.resetStreamToolCallState()
 						continue
 					}
@@ -357,22 +360,11 @@ func (s *chatStreamRuntime) onParsed(parsed sse.LineResult) streamengine.ParsedD
 						contentDelta := map[string]any{
 							"content": cleaned,
 						}
-						if !s.firstChunkSent {
-							contentDelta["role"] = "assistant"
-							s.firstChunkSent = true
-						}
-						newChoices = append(newChoices, openaifmt.BuildChatStreamDeltaChoice(0, contentDelta))
+						s.sendDelta(contentDelta)
 					}
 				}
 			}
 		}
-		if len(delta) > 0 {
-			newChoices = append(newChoices, openaifmt.BuildChatStreamDeltaChoice(0, delta))
-		}
-	}
-
-	if len(newChoices) > 0 {
-		s.sendChunk(openaifmt.BuildChatStreamChunk(s.completionID, s.created, s.model, newChoices, nil))
 	}
 	return streamengine.ParsedDecision{ContentSeen: contentSeen}
 }

internal/httpapi/openai/chat/empty_retry_runtime.go

@@ -49,6 +49,7 @@ func (h *Handler) handleNonStreamWithRetry(w http.ResponseWriter, ctx context.Co
 		detected := detectAssistantToolCalls(result.rawText, result.text, result.rawThinking, result.toolDetectionThinking, toolNames)
 		result.detectedCalls = len(detected.Calls)
 		result.body = openaifmt.BuildChatCompletionWithToolCalls(completionID, model, usagePrompt, result.thinking, result.text, detected.Calls, toolsRaw)
+		addRefFileTokensToUsage(result.body, refFileTokens)
 		result.finishReason = chatFinishReason(result.body)
 		if !shouldRetryChatNonStream(result, attempts) {
 			h.finishChatNonStreamResult(w, result, attempts, usagePrompt, refFileTokens, historySession)

internal/httpapi/openai/chat/handler_toolcall_test.go

@@ -1,6 +1,7 @@
 package chat
 
 import (
+	"context"
 	"encoding/json"
 	"io"
 	"net/http"
@@ -239,6 +240,75 @@ func TestHandleStreamToolsPlainTextStreamsBeforeFinish(t *testing.T) {
 	}
 }
 
+func TestHandleStreamThinkingDisabledDoesNotLeakHiddenFragmentContinuations(t *testing.T) {
+	h := &Handler{}
+	resp := makeSSEHTTPResponse(
+		`data: {"p":"response/fragments","o":"APPEND","v":[{"type":"THINK","content":"我们"}]}`,
+		`data: {"p":"response/fragments/-1/content","v":"被"}`,
+		`data: {"v":"要求"}`,
+		`data: {"p":"response/fragments","o":"APPEND","v":[{"type":"RESPONSE","content":"答"}]}`,
+		`data: {"p":"response/fragments/-1/content","v":"案"}`,
+		`data: [DONE]`,
+	)
+	rec := httptest.NewRecorder()
+	req := httptest.NewRequest(http.MethodPost, "/v1/chat/completions", nil)
+
+	h.handleStream(rec, req, resp, "cid-hidden-fragment", "deepseek-v4-flash", "prompt", 0, false, false, nil, nil, nil)
+
+	frames, done := parseSSEDataFrames(t, rec.Body.String())
+	if !done {
+		t.Fatalf("expected [DONE], body=%s", rec.Body.String())
+	}
+	content := strings.Builder{}
+	for _, frame := range frames {
+		choices, _ := frame["choices"].([]any)
+		for _, item := range choices {
+			choice, _ := item.(map[string]any)
+			delta, _ := choice["delta"].(map[string]any)
+			if c, ok := delta["content"].(string); ok {
+				content.WriteString(c)
+			}
+		}
+	}
+	if got := content.String(); got != "答案" {
+		t.Fatalf("expected only visible response text, got %q body=%s", got, rec.Body.String())
+	}
+}
+
+func TestHandleStreamEmitsSingleChoiceFramesForMultipleParsedParts(t *testing.T) {
+	h := &Handler{}
+	resp := makeSSEHTTPResponse(
+		`data: {"p":"response/fragments","o":"APPEND","v":[{"type":"THINK","content":"我们"},{"type":"THINK","content":"被"},{"type":"THINK","content":"要求"},{"type":"RESPONSE","content":"答"},{"type":"RESPONSE","content":"案"}]}`,
+		`data: [DONE]`,
+	)
+	rec := httptest.NewRecorder()
+	req := httptest.NewRequest(http.MethodPost, "/v1/chat/completions", nil)
+
+	h.handleStream(rec, req, resp, "cid-multi-parts", "deepseek-v4-pro", "prompt", 0, true, false, nil, nil, nil)
+
+	frames, done := parseSSEDataFrames(t, rec.Body.String())
+	if !done {
+		t.Fatalf("expected [DONE], body=%s", rec.Body.String())
+	}
+	var reasoning, content strings.Builder
+	for _, frame := range frames {
+		choices, _ := frame["choices"].([]any)
+		if len(choices) != 1 {
+			t.Fatalf("expected exactly one choice per stream frame, got %d frame=%#v body=%s", len(choices), frame, rec.Body.String())
+		}
+		choice, _ := choices[0].(map[string]any)
+		delta, _ := choice["delta"].(map[string]any)
+		reasoning.WriteString(asString(delta["reasoning_content"]))
+		content.WriteString(asString(delta["content"]))
+	}
+	if got := reasoning.String(); got != "我们被要求" {
+		t.Fatalf("first-choice-only client would miss reasoning tokens: got %q body=%s", got, rec.Body.String())
+	}
+	if got := content.String(); got != "答案" {
+		t.Fatalf("first-choice-only client would miss content tokens: got %q body=%s", got, rec.Body.String())
+	}
+}
+
 func TestHandleStreamIncompleteCapturedToolJSONFlushesAsTextOnFinalize(t *testing.T) {
 	h := &Handler{}
 	resp := makeSSEHTTPResponse(
@@ -447,3 +517,45 @@ func TestHandleStreamCoercesSchemaDeclaredStringArgumentsOnFinalize(t *testing.T
 	}
 	t.Fatalf("expected at least one streamed tool call delta, body=%s", rec.Body.String())
 }
+
+func TestHandleNonStreamWithRetryIncludesRefFileTokensInUsage(t *testing.T) {
+	h := &Handler{}
+
+	run := func(refFileTokens int) map[string]any {
+		resp := makeSSEHTTPResponse(
+			`data: {"p":"response/content","v":"hello world"}`,
+			`data: [DONE]`,
+		)
+		rec := httptest.NewRecorder()
+		h.handleNonStreamWithRetry(rec, context.Background(), nil, resp, nil, "", "cid-ref", "deepseek-v4-flash", "prompt", refFileTokens, false, false, nil, nil, nil)
+		if rec.Code != http.StatusOK {
+			t.Fatalf("expected 200, got %d body=%s", rec.Code, rec.Body.String())
+		}
+		return decodeJSONBody(t, rec.Body.String())
+	}
+
+	base := run(0)
+	withRef := run(7)
+
+	baseUsage, _ := base["usage"].(map[string]any)
+	refUsage, _ := withRef["usage"].(map[string]any)
+	if baseUsage == nil || refUsage == nil {
+		t.Fatalf("expected usage objects, base=%#v ref=%#v", base["usage"], withRef["usage"])
+	}
+
+	getInt := func(m map[string]any, key string) int {
+		t.Helper()
+		v, ok := m[key].(float64)
+		if !ok {
+			t.Fatalf("expected numeric %s, got %#v", key, m[key])
+		}
+		return int(v)
+	}
+
+	if got := getInt(refUsage, "prompt_tokens") - getInt(baseUsage, "prompt_tokens"); got != 7 {
+		t.Fatalf("expected prompt_tokens delta 7, got %d", got)
+	}
+	if got := getInt(refUsage, "total_tokens") - getInt(baseUsage, "total_tokens"); got != 7 {
+		t.Fatalf("expected total_tokens delta 7, got %d", got)
+	}
+}