diff --git a/docs/prompt-compatibility.md b/docs/prompt-compatibility.md index f733f58..5bf6025 100644 --- a/docs/prompt-compatibility.md +++ b/docs/prompt-compatibility.md @@ -259,16 +259,11 @@ OpenAI 文件相关实现： - 旧历史拆分兼容壳： [internal/httpapi/openai/history/history_split.go](../internal/httpapi/openai/history/history_split.go) -当前输入转文件启用并触发时，上传文件的真实文件名是 `history.txt`，文件内容是完整 `messages` 上下文；它仍会先用 OpenAI 消息标准化和 DeepSeek 角色标记序列化，再包进 `history.txt` 文件边界里： +当前输入转文件启用并触发时，上传文件的真实文件名是 `history.txt`，文件内容是完整 `messages` 上下文；它仍会先用 OpenAI 消息标准化和 DeepSeek 角色标记序列化，并直接作为 `history.txt` 的纯文本内容上传（不再注入文件边界标签）： ```text [uploaded filename]: history.txt -[file content end] - <｜begin▁of▁sentence｜><｜System｜>...<｜User｜>...<｜Assistant｜>...<｜Tool｜>...<｜User｜>... - -[file name]: history.txt -[file content begin] ``` 开启后，请求的 live prompt 不再直接内联完整上下文，而是保留一个 user role 的短提示，提示模型基于已提供上下文直接回答最新请求；上传后的 `file_id` 会进入 `ref_file_ids`。 diff --git a/internal/httpapi/openai/chat/chat_stream_runtime.go b/internal/httpapi/openai/chat/chat_stream_runtime.go index e5cbeb3..21d1f4f 100644 --- a/internal/httpapi/openai/chat/chat_stream_runtime.go +++ b/internal/httpapi/openai/chat/chat_stream_runtime.go @@ -143,7 +143,7 @@ func (s *chatStreamRuntime) finalize(finishReason string, deferEmptyOutput bool) finalText := cleanVisibleOutput(s.text.String(), s.stripReferenceMarkers) s.finalThinking = finalThinking s.finalText = finalText - detected := detectAssistantToolCalls(s.rawText.String(), s.rawThinking.String(), finalToolDetectionThinking, s.toolNames) + detected := detectAssistantToolCalls(s.rawText.String(), finalText, s.rawThinking.String(), finalToolDetectionThinking, s.toolNames) if len(detected.Calls) > 0 && !s.toolCallsDoneEmitted { finishReason = "tool_calls" delta := map[string]any{ diff --git a/internal/httpapi/openai/chat/empty_retry_runtime.go b/internal/httpapi/openai/chat/empty_retry_runtime.go index 61642b5..c3d37b9 100644 --- a/internal/httpapi/openai/chat/empty_retry_runtime.go +++ b/internal/httpapi/openai/chat/empty_retry_runtime.go @@ -46,7 +46,7 @@ func (h *Handler) handleNonStreamWithRetry(w http.ResponseWriter, ctx context.Co result.thinking = accumulatedThinking result.rawThinking = accumulatedRawThinking result.toolDetectionThinking = accumulatedToolDetectionThinking - detected := detectAssistantToolCalls(result.rawText, result.rawThinking, result.toolDetectionThinking, toolNames) + 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) result.finishReason = chatFinishReason(result.body) @@ -91,7 +91,7 @@ func (h *Handler) collectChatNonStreamAttempt(w http.ResponseWriter, resp *http. if searchEnabled { finalText = replaceCitationMarkersWithLinks(finalText, result.CitationLinks) } - detected := detectAssistantToolCalls(result.Text, result.Thinking, result.ToolDetectionThinking, toolNames) + detected := detectAssistantToolCalls(result.Text, finalText, result.Thinking, result.ToolDetectionThinking, toolNames) respBody := openaifmt.BuildChatCompletionWithToolCalls(completionID, model, usagePrompt, finalThinking, finalText, detected.Calls, toolsRaw) return chatNonStreamResult{ rawThinking: result.Thinking, diff --git a/internal/httpapi/openai/chat/handler.go b/internal/httpapi/openai/chat/handler.go index 92da0c6..4ad7aad 100644 --- a/internal/httpapi/openai/chat/handler.go +++ b/internal/httpapi/openai/chat/handler.go @@ -148,6 +148,6 @@ func formatFinalStreamToolCallsWithStableIDs(calls []toolcall.ParsedToolCall, id return shared.FormatFinalStreamToolCallsWithStableIDs(calls, ids, toolsRaw) } -func detectAssistantToolCalls(text, exposedThinking, detectionThinking string, toolNames []string) toolcall.ToolCallParseResult { - return shared.DetectAssistantToolCalls(text, exposedThinking, detectionThinking, toolNames) +func detectAssistantToolCalls(rawText, visibleText, exposedThinking, detectionThinking string, toolNames []string) toolcall.ToolCallParseResult { + return shared.DetectAssistantToolCalls(rawText, visibleText, exposedThinking, detectionThinking, toolNames) } diff --git a/internal/httpapi/openai/chat/handler_chat.go b/internal/httpapi/openai/chat/handler_chat.go index 3b56f12..a2e421a 100644 --- a/internal/httpapi/openai/chat/handler_chat.go +++ b/internal/httpapi/openai/chat/handler_chat.go @@ -166,7 +166,7 @@ func (h *Handler) handleNonStream(w http.ResponseWriter, resp *http.Response, co if searchEnabled { finalText = replaceCitationMarkersWithLinks(finalText, result.CitationLinks) } - detected := detectAssistantToolCalls(result.Text, result.Thinking, result.ToolDetectionThinking, toolNames) + detected := detectAssistantToolCalls(result.Text, finalText, result.Thinking, result.ToolDetectionThinking, toolNames) if shouldWriteUpstreamEmptyOutputError(finalText) && len(detected.Calls) == 0 { status, message, code := upstreamEmptyOutputDetail(result.ContentFilter, finalText, finalThinking) if historySession != nil { diff --git a/internal/httpapi/openai/history_split_test.go b/internal/httpapi/openai/history_split_test.go index 6e6c0ce..593735a 100644 --- a/internal/httpapi/openai/history_split_test.go +++ b/internal/httpapi/openai/history_split_test.go @@ -64,8 +64,8 @@ func TestBuildOpenAICurrentInputContextTranscriptUsesInjectedFileWrapper(t *test _, historyMessages := splitOpenAIHistoryMessages(historySplitTestMessages(), 1) transcript := buildOpenAICurrentInputContextTranscript(historyMessages) - if !strings.HasPrefix(transcript, "[file content end]\n\n") { - t.Fatalf("expected injected file wrapper prefix, got %q", transcript) + if strings.Contains(transcript, "[file content end]") || strings.Contains(transcript, "[file content begin]") || strings.Contains(transcript, "[file name]:") { + t.Fatalf("expected plain transcript without file wrapper tags, got %q", transcript) } if !strings.Contains(transcript, "<｜begin▁of▁sentence｜>") { t.Fatalf("expected serialized conversation markers, got %q", transcript) @@ -79,9 +79,7 @@ func TestBuildOpenAICurrentInputContextTranscriptUsesInjectedFileWrapper(t *test if !strings.Contains(transcript, "<|DSML|tool_calls>") { t.Fatalf("expected tool calls preserved, got %q", transcript) } - if !strings.HasSuffix(transcript, "\n[file name]: history.txt\n[file content begin]\n") { - t.Fatalf("expected injected file wrapper suffix, got %q", transcript) - } + } func TestSplitOpenAIHistoryMessagesUsesLatestUserTurn(t *testing.T) { @@ -278,8 +276,8 @@ func TestApplyCurrentInputFileUploadsFirstTurnWithInjectedWrapper(t *testing.T) t.Fatalf("unexpected upload filename: %q", upload.Filename) } uploadedText := string(upload.Data) - if !strings.HasPrefix(uploadedText, "[file content end]\n\n") { - t.Fatalf("expected injected file wrapper prefix, got %q", uploadedText) + if strings.Contains(uploadedText, "[file content end]") || strings.Contains(uploadedText, "[file content begin]") || strings.Contains(uploadedText, "[file name]:") { + t.Fatalf("expected uploaded transcript without file wrapper tags, got %q", uploadedText) } if !strings.Contains(uploadedText, "<｜begin▁of▁sentence｜><｜User｜>first turn content that is long enough") { t.Fatalf("expected serialized current user turn markers, got %q", uploadedText) @@ -287,9 +285,7 @@ func TestApplyCurrentInputFileUploadsFirstTurnWithInjectedWrapper(t *testing.T) if !strings.Contains(uploadedText, promptcompat.ThinkingInjectionMarker) { t.Fatalf("expected thinking injection in current input file, got %q", uploadedText) } - if !strings.HasSuffix(uploadedText, "\n[file name]: history.txt\n[file content begin]\n") { - t.Fatalf("expected injected file wrapper suffix, got %q", uploadedText) - } + if strings.Contains(out.FinalPrompt, "first turn content that is long enough") { t.Fatalf("expected current input text to be replaced in live prompt, got %s", out.FinalPrompt) } @@ -418,8 +414,8 @@ func TestChatCompletionsCurrentInputFileUploadsContextAndKeepsNeutralPrompt(t *t t.Fatalf("unexpected purpose: %q", upload.Purpose) } historyText := string(upload.Data) - if !strings.Contains(historyText, "[file content end]") || !strings.Contains(historyText, "[file name]: history.txt") { - t.Fatalf("expected injected history.txt wrapper, got %s", historyText) + if strings.Contains(historyText, "[file content end]") || strings.Contains(historyText, "[file content begin]") || strings.Contains(historyText, "[file name]:") { + t.Fatalf("expected plain history transcript without wrapper tags, got %s", historyText) } if !strings.Contains(historyText, "latest user turn") { t.Fatalf("expected full context to include latest turn, got %s", historyText) diff --git a/internal/httpapi/openai/responses/empty_retry_runtime.go b/internal/httpapi/openai/responses/empty_retry_runtime.go index c3f8fd9..a451c92 100644 --- a/internal/httpapi/openai/responses/empty_retry_runtime.go +++ b/internal/httpapi/openai/responses/empty_retry_runtime.go @@ -47,7 +47,7 @@ func (h *Handler) handleResponsesNonStreamWithRetry(w http.ResponseWriter, ctx c result.thinking = accumulatedThinking result.rawThinking = accumulatedRawThinking result.toolDetectionThinking = accumulatedToolDetectionThinking - result.parsed = detectAssistantToolCalls(result.rawText, result.rawThinking, result.toolDetectionThinking, toolNames) + result.parsed = detectAssistantToolCalls(result.rawText, result.text, result.rawThinking, result.toolDetectionThinking, toolNames) result.body = openaifmt.BuildResponseObjectWithToolCalls(responseID, model, usagePrompt, result.thinking, result.text, result.parsed.Calls, toolsRaw) if !shouldRetryResponsesNonStream(result, attempts) { @@ -87,7 +87,7 @@ func (h *Handler) collectResponsesNonStreamAttempt(w http.ResponseWriter, resp * if searchEnabled { sanitizedText = replaceCitationMarkersWithLinks(sanitizedText, result.CitationLinks) } - textParsed := detectAssistantToolCalls(result.Text, result.Thinking, result.ToolDetectionThinking, toolNames) + textParsed := detectAssistantToolCalls(result.Text, sanitizedText, result.Thinking, result.ToolDetectionThinking, toolNames) responseObj := openaifmt.BuildResponseObjectWithToolCalls(responseID, model, usagePrompt, sanitizedThinking, sanitizedText, textParsed.Calls, toolsRaw) return responsesNonStreamResult{ rawThinking: result.Thinking, diff --git a/internal/httpapi/openai/responses/handler.go b/internal/httpapi/openai/responses/handler.go index a5f243f..ac8cd04 100644 --- a/internal/httpapi/openai/responses/handler.go +++ b/internal/httpapi/openai/responses/handler.go @@ -130,6 +130,6 @@ func filterIncrementalToolCallDeltasByAllowed(deltas []toolstream.ToolCallDelta, return shared.FilterIncrementalToolCallDeltasByAllowed(deltas, seenNames) } -func detectAssistantToolCalls(text, exposedThinking, detectionThinking string, toolNames []string) toolcall.ToolCallParseResult { - return shared.DetectAssistantToolCalls(text, exposedThinking, detectionThinking, toolNames) +func detectAssistantToolCalls(rawText, visibleText, exposedThinking, detectionThinking string, toolNames []string) toolcall.ToolCallParseResult { + return shared.DetectAssistantToolCalls(rawText, visibleText, exposedThinking, detectionThinking, toolNames) } diff --git a/internal/httpapi/openai/responses/responses_handler.go b/internal/httpapi/openai/responses/responses_handler.go index c26e4be..a04e7b1 100644 --- a/internal/httpapi/openai/responses/responses_handler.go +++ b/internal/httpapi/openai/responses/responses_handler.go @@ -135,7 +135,7 @@ func (h *Handler) handleResponsesNonStream(w http.ResponseWriter, resp *http.Res if searchEnabled { sanitizedText = replaceCitationMarkersWithLinks(sanitizedText, result.CitationLinks) } - textParsed := detectAssistantToolCalls(result.Text, result.Thinking, result.ToolDetectionThinking, toolNames) + textParsed := detectAssistantToolCalls(result.Text, sanitizedText, result.Thinking, result.ToolDetectionThinking, toolNames) if len(textParsed.Calls) == 0 && writeUpstreamEmptyOutputError(w, sanitizedText, sanitizedThinking, result.ContentFilter) { return } diff --git a/internal/httpapi/openai/responses/responses_stream_runtime_core.go b/internal/httpapi/openai/responses/responses_stream_runtime_core.go index b6a2088..2047dfe 100644 --- a/internal/httpapi/openai/responses/responses_stream_runtime_core.go +++ b/internal/httpapi/openai/responses/responses_stream_runtime_core.go @@ -150,7 +150,7 @@ func (s *responsesStreamRuntime) finalize(finishReason string, deferEmptyOutput finalThinking := s.thinking.String() finalToolDetectionThinking := s.toolDetectionThinking.String() finalText := cleanVisibleOutput(s.text.String(), s.stripReferenceMarkers) - textParsed := detectAssistantToolCalls(s.rawText.String(), s.rawThinking.String(), finalToolDetectionThinking, s.toolNames) + textParsed := detectAssistantToolCalls(s.rawText.String(), finalText, s.rawThinking.String(), finalToolDetectionThinking, s.toolNames) detected := textParsed.Calls s.logToolPolicyRejections(textParsed) diff --git a/internal/httpapi/openai/responses/responses_stream_runtime_events.go b/internal/httpapi/openai/responses/responses_stream_runtime_events.go index 550673f..20b9108 100644 --- a/internal/httpapi/openai/responses/responses_stream_runtime_events.go +++ b/internal/httpapi/openai/responses/responses_stream_runtime_events.go @@ -45,7 +45,7 @@ func (s *responsesStreamRuntime) processToolStreamEvents(events []toolstream.Eve for _, evt := range events { if emitContent && evt.Content != "" { cleaned := cleanVisibleOutput(evt.Content, s.stripReferenceMarkers) - if cleaned != "" && !(s.searchEnabled && sse.IsCitation(cleaned)) { + if cleaned != "" && (!s.searchEnabled || !sse.IsCitation(cleaned)) { s.emitTextDelta(cleaned) } } diff --git a/internal/httpapi/openai/shared/assistant_toolcalls.go b/internal/httpapi/openai/shared/assistant_toolcalls.go index 25f930b..f90860f 100644 --- a/internal/httpapi/openai/shared/assistant_toolcalls.go +++ b/internal/httpapi/openai/shared/assistant_toolcalls.go @@ -6,12 +6,12 @@ import ( "ds2api/internal/toolcall" ) -func DetectAssistantToolCalls(text, exposedThinking, detectionThinking string, toolNames []string) toolcall.ToolCallParseResult { - textParsed := toolcall.ParseStandaloneToolCallsDetailed(text, toolNames) +func DetectAssistantToolCalls(rawText, visibleText, exposedThinking, detectionThinking string, toolNames []string) toolcall.ToolCallParseResult { + textParsed := toolcall.ParseStandaloneToolCallsDetailed(rawText, toolNames) if len(textParsed.Calls) > 0 { return textParsed } - if strings.TrimSpace(text) != "" { + if strings.TrimSpace(visibleText) != "" { return textParsed } thinking := detectionThinking diff --git a/internal/promptcompat/history_transcript.go b/internal/promptcompat/history_transcript.go index befcd1d..a3f7905 100644 --- a/internal/promptcompat/history_transcript.go +++ b/internal/promptcompat/history_transcript.go @@ -1,7 +1,6 @@ package promptcompat import ( - "fmt" "strings" "ds2api/internal/prompt" @@ -32,5 +31,5 @@ func buildOpenAIInjectedFileTranscript(messages []any) string { if transcript == "" { return "" } - return fmt.Sprintf("[file content end]\n\n%s\n\n[file name]: %s\n[file content begin]\n", transcript, CurrentInputContextFilename) + return transcript }