From df1cfac9bca8d58c2ff581a4654d58a9f2fb276b Mon Sep 17 00:00:00 2001 From: CJACK Date: Fri, 1 May 2026 21:15:17 +0800 Subject: [PATCH] refactor: replace history transcript format with numbered sections and rename upload file to HISTORY.txt --- docs/prompt-compatibility.md | 25 +++-- .../httpapi/openai/chat/chat_history_test.go | 4 +- .../openai/history/current_input_file.go | 2 +- internal/httpapi/openai/history_split_test.go | 81 +++++++++++----- internal/promptcompat/history_transcript.go | 93 +++++++++++++++++-- webui/src/locales/en.json | 2 +- webui/src/locales/zh.json | 2 +- 7 files changed, 164 insertions(+), 45 deletions(-) diff --git a/docs/prompt-compatibility.md b/docs/prompt-compatibility.md index d92cea3..f5e55c8 100644 --- a/docs/prompt-compatibility.md +++ b/docs/prompt-compatibility.md @@ -249,7 +249,7 @@ OpenAI 文件相关实现： 兼容层现在只保留 `current_input_file` 这一种拆分方式；旧的 `history_split` 已废弃，只保留为兼容旧配置的字段，不再参与请求处理。 -- `current_input_file` 默认开启；它用于把“完整上下文”合并进 `history.txt` 上下文文件。当最新 user turn 的纯文本长度达到 `current_input_file.min_chars`（默认 `0`）时，兼容层会上传一个文件名为 `history.txt` 的上下文文件，并在 live prompt 中只保留一个中性的 user 消息要求模型直接回答最新请求，不再暴露文件名或要求模型读取本地文件。 +- `current_input_file` 默认开启；它用于把“完整上下文”合并进 `HISTORY.txt` 上下文文件。当最新 user turn 的纯文本长度达到 `current_input_file.min_chars`（默认 `0`）时，兼容层会上传一个文件名为 `HISTORY.txt` 的上下文文件。文件内容会先做 OpenAI 消息标准化，再序列化成按轮次编号的 `HISTORY.txt` 风格 transcript，带有 `# HISTORY.txt` 标题和 `=== N. ROLE ===` 分段；live prompt 中则只保留一个中性的 user 消息要求模型直接回答最新请求，不再暴露文件名或要求模型读取本地文件。 - 如果 `current_input_file.enabled=false`，请求会直接透传，不上传任何拆分上下文文件。 - 旧的 `history_split.enabled` / `history_split.trigger_after_turns` 会被读取进配置对象以保持兼容，但不会触发拆分上传，也不会影响 `current_input_file` 的默认开启。 - 即使触发 `current_input_file` 后 live prompt 被缩短，对客户端回包里的上下文 token 统计，仍会沿用**拆分前的完整 prompt 语义**做计数，而不是按缩短后的占位 prompt 计算；否则会把真实上下文显著算小。 @@ -263,11 +263,24 @@ 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，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）： +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，再按轮次编号成 `HISTORY.txt` 风格的 transcript（不再注入文件边界标签）： ```text -[uploaded filename]: history.txt -<｜begin▁of▁sentence｜><｜System｜>...<｜User｜>...<｜Assistant｜>...<｜Tool｜>...<｜User｜>... +[uploaded filename]: HISTORY.txt +# HISTORY.txt +Prior conversation history and tool progress. + +=== 1. SYSTEM === +... + +=== 2. USER === +... + +=== 3. ASSISTANT === +... + +=== 4. TOOL === +... ``` 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`。 @@ -334,7 +347,7 @@ OpenAI 文件相关实现： - 大部分结构化语义被压进 `prompt` - 文件保持文件 -- 需要时把完整上下文拆进 `history.txt` 上下文文件 +- 需要时把完整上下文拆进 `HISTORY.txt` 上下文文件，并按轮次编号成 transcript ## 12. 修改时必须同步本文档的场景 @@ -347,7 +360,7 @@ OpenAI 文件相关实现： - tool result 注入方式变更 - tool prompt 模板或 tool_choice 约束变更 - inline 文件上传 / 文件引用收集规则变更 -- current input file 触发条件、上传格式、`history.txt` 包装格式变更 +- current input file 触发条件、上传格式、`HISTORY.txt` transcript 结构变更 - 旧 `history_split` 兼容逻辑的读取、忽略或退化行为变更 - completion payload 字段语义变更 - Claude / Gemini 对这套统一语义的复用关系变更 diff --git a/internal/httpapi/openai/chat/chat_history_test.go b/internal/httpapi/openai/chat/chat_history_test.go index 2201f0f..6b9f2a0 100644 --- a/internal/httpapi/openai/chat/chat_history_test.go +++ b/internal/httpapi/openai/chat/chat_history_test.go @@ -311,8 +311,8 @@ func TestChatCompletionsCurrentInputFilePersistsNeutralPrompt(t *testing.T) { if len(ds.uploadCalls) != 1 { t.Fatalf("expected current input upload to happen, got %d", len(ds.uploadCalls)) } - if ds.uploadCalls[0].Filename != "history.txt" { - t.Fatalf("expected history.txt upload, got %q", ds.uploadCalls[0].Filename) + if ds.uploadCalls[0].Filename != "HISTORY.txt" { + t.Fatalf("expected HISTORY.txt upload, got %q", ds.uploadCalls[0].Filename) } if full.HistoryText != string(ds.uploadCalls[0].Data) { t.Fatalf("expected uploaded current input file to be persisted in history text") diff --git a/internal/httpapi/openai/history/current_input_file.go b/internal/httpapi/openai/history/current_input_file.go index 181a5e2..7069207 100644 --- a/internal/httpapi/openai/history/current_input_file.go +++ b/internal/httpapi/openai/history/current_input_file.go @@ -62,7 +62,7 @@ func (s Service) ApplyCurrentInputFile(ctx context.Context, a *auth.RequestAuth, stdReq.RefFileIDs = prependUniqueRefFileID(stdReq.RefFileIDs, fileID) stdReq.FinalPrompt, stdReq.ToolNames = promptcompat.BuildOpenAIPrompt(messages, stdReq.ToolsRaw, "", stdReq.ToolChoice, stdReq.Thinking) // Token accounting must reflect the actual downstream context: - // the uploaded history.txt file content + the neutral live prompt. + // the uploaded HISTORY.txt file content + the neutral live prompt. stdReq.PromptTokenText = fileText + "\n" + stdReq.FinalPrompt return stdReq, nil } diff --git a/internal/httpapi/openai/history_split_test.go b/internal/httpapi/openai/history_split_test.go index d429b9b..799a1f7 100644 --- a/internal/httpapi/openai/history_split_test.go +++ b/internal/httpapi/openai/history_split_test.go @@ -61,26 +61,33 @@ func (streamStatusManagedAuthStub) DetermineCaller(_ *http.Request) (*auth.Reque func (streamStatusManagedAuthStub) Release(_ *auth.RequestAuth) {} -func TestBuildOpenAICurrentInputContextTranscriptUsesInjectedFileWrapper(t *testing.T) { +func TestBuildOpenAICurrentInputContextTranscriptUsesNumberedHistorySections(t *testing.T) { _, historyMessages := splitOpenAIHistoryMessages(historySplitTestMessages(), 1) transcript := buildOpenAICurrentInputContextTranscript(historyMessages) 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) + t.Fatalf("expected transcript without file wrapper tags, got %q", transcript) } - if !strings.Contains(transcript, "<｜begin▁of▁sentence｜>") { - t.Fatalf("expected serialized conversation markers, got %q", transcript) + if !strings.Contains(transcript, "# HISTORY.txt") { + t.Fatalf("expected history transcript header, got %q", transcript) } - if !strings.Contains(transcript, "first user turn") || !strings.Contains(transcript, "tool result") { - t.Fatalf("expected historical turns preserved, got %q", transcript) + if !strings.Contains(transcript, "Prior conversation history and tool progress.") { + t.Fatalf("expected history transcript description, got %q", transcript) } - if !strings.Contains(transcript, "[reasoning_content]") || !strings.Contains(transcript, "hidden reasoning") { - t.Fatalf("expected reasoning block preserved, got %q", transcript) + for _, want := range []string{ + "=== 1. USER ===", + "=== 2. ASSISTANT ===", + "=== 3. TOOL ===", + "first user turn", + "tool result", + "[reasoning_content]", + "hidden reasoning", + "<|DSML|tool_calls>", + } { + if !strings.Contains(transcript, want) { + t.Fatalf("expected transcript to contain %q, got %q", want, transcript) + } } - if !strings.Contains(transcript, "<|DSML|tool_calls>") { - t.Fatalf("expected tool calls preserved, got %q", transcript) - } - } func TestSplitOpenAIHistoryMessagesUsesLatestUserTurn(t *testing.T) { @@ -243,7 +250,7 @@ func TestApplyCurrentInputFileDisabledPassThrough(t *testing.T) { } } -func TestApplyCurrentInputFileUploadsFirstTurnWithInjectedWrapper(t *testing.T) { +func TestApplyCurrentInputFileUploadsFirstTurnWithNumberedHistoryTranscript(t *testing.T) { ds := &inlineUploadDSStub{} h := &openAITestSurface{ Store: mockOpenAIConfig{ @@ -273,15 +280,21 @@ func TestApplyCurrentInputFileUploadsFirstTurnWithInjectedWrapper(t *testing.T) t.Fatalf("expected 1 current input upload, got %d", len(ds.uploadCalls)) } upload := ds.uploadCalls[0] - if upload.Filename != "history.txt" { + if upload.Filename != "HISTORY.txt" { t.Fatalf("unexpected upload filename: %q", upload.Filename) } uploadedText := string(upload.Data) 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) + for _, want := range []string{ + "# HISTORY.txt", + "=== 1. USER ===", + "first turn content that is long enough", + } { + if !strings.Contains(uploadedText, want) { + t.Fatalf("expected uploaded transcript to contain %q, got %q", want, uploadedText) + } } if !strings.Contains(uploadedText, promptcompat.ThinkingInjectionMarker) { t.Fatalf("expected thinking injection in current input file, got %q", uploadedText) @@ -290,7 +303,7 @@ func TestApplyCurrentInputFileUploadsFirstTurnWithInjectedWrapper(t *testing.T) 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) } - if strings.Contains(out.FinalPrompt, "CURRENT_USER_INPUT.txt") || strings.Contains(out.FinalPrompt, "history.txt") || strings.Contains(out.FinalPrompt, "Read that file") { + if strings.Contains(out.FinalPrompt, "CURRENT_USER_INPUT.txt") || strings.Contains(out.FinalPrompt, "history.txt") || strings.Contains(out.FinalPrompt, "HISTORY.txt") || strings.Contains(out.FinalPrompt, "Read that file") { t.Fatalf("expected live prompt not to instruct file reads, got %s", out.FinalPrompt) } if !strings.Contains(out.FinalPrompt, "Answer the latest user request directly.") { @@ -302,6 +315,9 @@ func TestApplyCurrentInputFileUploadsFirstTurnWithInjectedWrapper(t *testing.T) if !strings.Contains(out.PromptTokenText, "first turn content that is long enough") { t.Fatalf("expected prompt token text to preserve original full context, got %q", out.PromptTokenText) } + if !strings.Contains(out.PromptTokenText, "# HISTORY.txt") || !strings.Contains(out.PromptTokenText, "=== 1. USER ===") { + t.Fatalf("expected prompt token text to include numbered history transcript, got %q", out.PromptTokenText) + } } func TestApplyCurrentInputFilePreservesFullContextPromptForTokenCounting(t *testing.T) { @@ -337,7 +353,10 @@ func TestApplyCurrentInputFilePreservesFullContextPromptForTokenCounting(t *test t.Fatalf("expected prompt token text to contain file context with full conversation, got %q", out.PromptTokenText) } if strings.Contains(out.PromptTokenText, "[file content end]") || strings.Contains(out.PromptTokenText, "[file name]:") { - t.Fatalf("expected prompt token text to use raw transcript without wrapper tags, got %q", out.PromptTokenText) + t.Fatalf("expected prompt token text to omit file wrapper tags, got %q", out.PromptTokenText) + } + if !strings.Contains(out.PromptTokenText, "# HISTORY.txt") || !strings.Contains(out.PromptTokenText, "=== 1. SYSTEM ===") { + t.Fatalf("expected prompt token text to include numbered history transcript, got %q", out.PromptTokenText) } if !strings.Contains(out.PromptTokenText, "Answer the latest user request directly.") { t.Fatalf("expected prompt token text to also include neutral live prompt, got %q", out.PromptTokenText) @@ -378,16 +397,16 @@ func TestApplyCurrentInputFileUploadsFullContextFile(t *testing.T) { t.Fatalf("expected one current input upload, got %d", len(ds.uploadCalls)) } upload := ds.uploadCalls[0] - if upload.Filename != "history.txt" { - t.Fatalf("expected history.txt upload, got %q", upload.Filename) + if upload.Filename != "HISTORY.txt" { + t.Fatalf("expected HISTORY.txt upload, got %q", upload.Filename) } uploadedText := string(upload.Data) - for _, want := range []string{"system instructions", "first user turn", "hidden reasoning", "tool result", "latest user turn", promptcompat.ThinkingInjectionMarker} { + for _, want := range []string{"# HISTORY.txt", "=== 1. SYSTEM ===", "=== 2. USER ===", "=== 3. ASSISTANT ===", "=== 4. TOOL ===", "=== 5. USER ===", "system instructions", "first user turn", "hidden reasoning", "tool result", "latest user turn", promptcompat.ThinkingInjectionMarker} { if !strings.Contains(uploadedText, want) { t.Fatalf("expected full context file to contain %q, got %q", want, uploadedText) } } - if strings.Contains(out.FinalPrompt, "first user turn") || strings.Contains(out.FinalPrompt, "latest user turn") || strings.Contains(out.FinalPrompt, "CURRENT_USER_INPUT.txt") || strings.Contains(out.FinalPrompt, "history.txt") || strings.Contains(out.FinalPrompt, "Read that file") { + if strings.Contains(out.FinalPrompt, "first user turn") || strings.Contains(out.FinalPrompt, "latest user turn") || strings.Contains(out.FinalPrompt, "CURRENT_USER_INPUT.txt") || strings.Contains(out.FinalPrompt, "history.txt") || strings.Contains(out.FinalPrompt, "HISTORY.txt") || strings.Contains(out.FinalPrompt, "Read that file") { t.Fatalf("expected live prompt to use only a neutral continuation instruction, got %s", out.FinalPrompt) } if !strings.Contains(out.FinalPrompt, "Answer the latest user request directly.") { @@ -423,6 +442,9 @@ func TestApplyCurrentInputFileCarriesHistoryText(t *testing.T) { if out.HistoryText != string(ds.uploadCalls[0].Data) { t.Fatalf("expected current input file flow to preserve uploaded text in history, got %q", out.HistoryText) } + if !strings.Contains(out.HistoryText, "# HISTORY.txt") || !strings.Contains(out.HistoryText, "=== 1. SYSTEM ===") { + t.Fatalf("expected history text to use numbered transcript format, got %q", out.HistoryText) + } } func TestChatCompletionsCurrentInputFileUploadsContextAndKeepsNeutralPrompt(t *testing.T) { @@ -454,7 +476,7 @@ func TestChatCompletionsCurrentInputFileUploadsContextAndKeepsNeutralPrompt(t *t t.Fatalf("expected 1 upload call, got %d", len(ds.uploadCalls)) } upload := ds.uploadCalls[0] - if upload.Filename != "history.txt" { + if upload.Filename != "HISTORY.txt" { t.Fatalf("unexpected upload filename: %q", upload.Filename) } if upload.Purpose != "assistants" { @@ -462,7 +484,10 @@ func TestChatCompletionsCurrentInputFileUploadsContextAndKeepsNeutralPrompt(t *t } historyText := string(upload.Data) 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) + t.Fatalf("expected history transcript without file wrapper tags, got %s", historyText) + } + if !strings.Contains(historyText, "# HISTORY.txt") || !strings.Contains(historyText, "=== 1. SYSTEM ===") { + t.Fatalf("expected history transcript to use numbered sections, got %s", historyText) } if !strings.Contains(historyText, "latest user turn") { t.Fatalf("expected full context to include latest turn, got %s", historyText) @@ -523,6 +548,10 @@ func TestResponsesCurrentInputFileUploadsContextAndKeepsNeutralPrompt(t *testing if len(ds.uploadCalls) != 1 { t.Fatalf("expected 1 upload call, got %d", len(ds.uploadCalls)) } + historyText := string(ds.uploadCalls[0].Data) + if !strings.Contains(historyText, "# HISTORY.txt") || !strings.Contains(historyText, "=== 1. SYSTEM ===") { + t.Fatalf("expected uploaded history text to use numbered transcript format, got %s", historyText) + } if ds.completionReq == nil { t.Fatal("expected completion payload to be captured") } @@ -669,6 +698,10 @@ func TestCurrentInputFileWorksAcrossAutoDeleteModes(t *testing.T) { if len(ds.uploadCalls) != 1 { t.Fatalf("expected current input upload for mode=%s, got %d", mode, len(ds.uploadCalls)) } + historyText := string(ds.uploadCalls[0].Data) + if !strings.Contains(historyText, "# HISTORY.txt") || !strings.Contains(historyText, "=== 1. SYSTEM ===") { + t.Fatalf("expected uploaded history text to use numbered transcript format, got %s", historyText) + } if ds.completionReq == nil { t.Fatalf("expected completion payload for mode=%s", mode) } diff --git a/internal/promptcompat/history_transcript.go b/internal/promptcompat/history_transcript.go index a3f7905..84a62cb 100644 --- a/internal/promptcompat/history_transcript.go +++ b/internal/promptcompat/history_transcript.go @@ -1,35 +1,108 @@ package promptcompat import ( + "fmt" "strings" - - "ds2api/internal/prompt" ) -const CurrentInputContextFilename = "history.txt" +const CurrentInputContextFilename = "HISTORY.txt" + +const historyTranscriptTitle = "# HISTORY.txt" +const historyTranscriptSummary = "Prior conversation history and tool progress." func BuildOpenAIHistoryTranscript(messages []any) string { - return buildOpenAIInjectedFileTranscript(messages) + return buildOpenAIHistoryTranscript(messages) } func BuildOpenAICurrentUserInputTranscript(text string) string { if strings.TrimSpace(text) == "" { return "" } - return BuildOpenAICurrentInputContextTranscript([]any{ + return buildOpenAIHistoryTranscript([]any{ map[string]any{"role": "user", "content": text}, }) } func BuildOpenAICurrentInputContextTranscript(messages []any) string { - return buildOpenAIInjectedFileTranscript(messages) + return buildOpenAIHistoryTranscript(messages) } -func buildOpenAIInjectedFileTranscript(messages []any) string { - normalized := NormalizeOpenAIMessagesForPrompt(messages, "") - transcript := strings.TrimSpace(prompt.MessagesPrepare(normalized)) +func buildOpenAIHistoryTranscript(messages []any) string { + if len(messages) == 0 { + return "" + } + var b strings.Builder + b.WriteString(historyTranscriptTitle) + b.WriteString("\n") + b.WriteString(historyTranscriptSummary) + b.WriteString("\n\n") + + entry := 0 + for _, raw := range messages { + msg, ok := raw.(map[string]any) + if !ok { + continue + } + role := normalizeOpenAIRoleForPrompt(strings.ToLower(strings.TrimSpace(asString(msg["role"])))) + content := strings.TrimSpace(buildOpenAIHistoryEntry(role, msg)) + if content == "" { + continue + } + entry++ + fmt.Fprintf(&b, "=== %d. %s ===\n%s\n\n", entry, strings.ToUpper(roleLabelForHistory(role)), content) + } + + transcript := strings.TrimSpace(b.String()) if transcript == "" { return "" } - return transcript + return transcript + "\n" +} + +func buildOpenAIHistoryEntry(role string, msg map[string]any) string { + switch role { + case "assistant": + return strings.TrimSpace(buildAssistantContentForPrompt(msg)) + case "tool", "function": + return strings.TrimSpace(buildToolHistoryContent(msg)) + case "system", "user": + return strings.TrimSpace(NormalizeOpenAIContentForPrompt(msg["content"])) + default: + return strings.TrimSpace(NormalizeOpenAIContentForPrompt(msg["content"])) + } +} + +func buildToolHistoryContent(msg map[string]any) string { + content := strings.TrimSpace(NormalizeOpenAIContentForPrompt(msg["content"])) + parts := make([]string, 0, 2) + if name := strings.TrimSpace(asString(msg["name"])); name != "" { + parts = append(parts, "name="+name) + } + if callID := strings.TrimSpace(asString(msg["tool_call_id"])); callID != "" { + parts = append(parts, "tool_call_id="+callID) + } + header := "" + if len(parts) > 0 { + header = "[" + strings.Join(parts, " ") + "]" + } + switch { + case header != "" && content != "": + return header + "\n" + content + case header != "": + return header + default: + return content + } +} + +func roleLabelForHistory(role string) string { + role = strings.ToLower(strings.TrimSpace(role)) + switch role { + case "function": + return "tool" + case "": + return "unknown" + default: + return role + } } diff --git a/webui/src/locales/en.json b/webui/src/locales/en.json index 0b3de63..072e514 100644 --- a/webui/src/locales/en.json +++ b/webui/src/locales/en.json @@ -394,7 +394,7 @@ "thinkingInjectionPromptHelp": "Leave empty to use the built-in default prompt shown as the input placeholder.", "currentInputFileTitle": "Independent Split", "currentInputFileEnabled": "Independent split (by size)", - "currentInputFileDesc": "Enabled by default. Once the character threshold is reached, upload the full context as a history.txt context file.", + "currentInputFileDesc": "Enabled by default. Once the character threshold is reached, upload the full context as a HISTORY.txt context file.", "currentInputFileMinChars": "Current input threshold (characters)", "currentInputFileHelp": "Default is 0, which uses independent split for any non-empty input.", "compatibilityTitle": "Compatibility", diff --git a/webui/src/locales/zh.json b/webui/src/locales/zh.json index 9aa127b..409f48d 100644 --- a/webui/src/locales/zh.json +++ b/webui/src/locales/zh.json @@ -394,7 +394,7 @@ "thinkingInjectionPromptHelp": "留空时使用内置默认提示词；默认内容会显示在输入框占位文本中。", "currentInputFileTitle": "独立拆分", "currentInputFileEnabled": "独立拆分（按量）", - "currentInputFileDesc": "默认开启。达到字符阈值后，将完整上下文上传为 history.txt 上下文文件。", + "currentInputFileDesc": "默认开启。达到字符阈值后，将完整上下文上传为 HISTORY.txt 上下文文件。", "currentInputFileMinChars": "当前输入阈值（字符数）", "currentInputFileHelp": "默认 0，表示只要有输入就会使用独立拆分。", "compatibilityTitle": "兼容性设置",