From 83b4c7bcad4a13eed8a180ad9d189eebb9347b04 Mon Sep 17 00:00:00 2001
From: BigUncle <biguncle2017@gmail.com>
Date: Fri, 1 May 2026 20:50:12 +0800
Subject: [PATCH 1/7] fix: add missing Vercel rewrite rules for admin API
 routes

/admin/chat-history, /admin/proxies, /admin/dev/raw-samples,
and /admin/dev/captures were falling through to the SPA fallback
(/admin/index.html), causing "Unexpected token '<'" JSON parse
errors on the frontend.
---
 vercel.json | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/vercel.json b/vercel.json
index 600a53c..5cebd5d 100644
--- a/vercel.json
+++ b/vercel.json
@@ -81,6 +81,22 @@
       "source": "/admin/version",
       "destination": "/api/index"
     },
+    {
+      "source": "/admin/chat-history(.*)",
+      "destination": "/api/index"
+    },
+    {
+      "source": "/admin/proxies(.*)",
+      "destination": "/api/index"
+    },
+    {
+      "source": "/admin/dev/raw-samples/(.*)",
+      "destination": "/api/index"
+    },
+    {
+      "source": "/admin/dev/captures(.*)",
+      "destination": "/api/index"
+    },
     {
       "source": "/admin",
       "destination": "/admin/index.html"

From 706e68de233340e1cec392ba4fc5dbeb55b814a1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E7=8E=8B?= <wang@wangs-MacBook-Air-3.local>
Date: Fri, 1 May 2026 21:11:36 +0800
Subject: [PATCH 2/7] fix: increase stream timeout constants for large-context
 models; guard against context-cancelled double-recording

- Increase StreamIdleTimeout from 90s to 300s and MaxKeepaliveCount from 10 to 40
  to prevent premature stream termination with DeepSeek V4 Pro (~50K token contexts)
- Add r.Context().Err() check after ConsumeSSE in empty_retry_runtime (chat + responses)
  to prevent historySession.error() from overwriting historySession.stopped()
  when the request context is cancelled

References:
- MaxKeepaliveCount=10 creates a 50s no-content timeout that kills the stream
  before DeepSeek V4 Pro can produce its first token with large contexts
- Hermes Agent reports 'No response from provider for 180s' because the
  underlying SSE connection was already terminated by ds2api at 50s
- Context cancellation path: OnContextDone -> stopped(), then finalize()
  with empty output -> retry -> error() overwrites stopped()
---
 internal/deepseek/protocol/constants.go                  | 4 ++--
 internal/httpapi/openai/chat/empty_retry_runtime.go      | 3 +++
 internal/httpapi/openai/responses/empty_retry_runtime.go | 3 +++
 3 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/internal/deepseek/protocol/constants.go b/internal/deepseek/protocol/constants.go
index 3cb6c4d..83daa31 100644
--- a/internal/deepseek/protocol/constants.go
+++ b/internal/deepseek/protocol/constants.go
@@ -159,6 +159,6 @@ func toStringSet(in []string) map[string]struct{} {
 
 const (
 	KeepAliveTimeout  = 5
-	StreamIdleTimeout = 90
-	MaxKeepaliveCount = 10
+	StreamIdleTimeout = 300
+	MaxKeepaliveCount = 40
 )
diff --git a/internal/httpapi/openai/chat/empty_retry_runtime.go b/internal/httpapi/openai/chat/empty_retry_runtime.go
index de2ff12..147024f 100644
--- a/internal/httpapi/openai/chat/empty_retry_runtime.go
+++ b/internal/httpapi/openai/chat/empty_retry_runtime.go
@@ -252,6 +252,9 @@ func (h *Handler) consumeChatStreamAttempt(r *http.Request, resp *http.Response,
 			}
 		},
 	})
+	if r.Context().Err() != nil {
+		return true, false
+	}
 	terminalWritten := streamRuntime.finalize(finalReason, allowDeferEmpty && finalReason != "content_filter")
 	if terminalWritten {
 		recordChatStreamHistory(streamRuntime, historySession)
diff --git a/internal/httpapi/openai/responses/empty_retry_runtime.go b/internal/httpapi/openai/responses/empty_retry_runtime.go
index 627f074..45d861d 100644
--- a/internal/httpapi/openai/responses/empty_retry_runtime.go
+++ b/internal/httpapi/openai/responses/empty_retry_runtime.go
@@ -223,6 +223,9 @@ func (h *Handler) consumeResponsesStreamAttempt(r *http.Request, resp *http.Resp
 			}
 		},
 	})
+	if r.Context().Err() != nil {
+		return true, false
+	}
 	terminalWritten := streamRuntime.finalize(finalReason, allowDeferEmpty && finalReason != "content_filter")
 	if terminalWritten {
 		return true, false

From df1cfac9bca8d58c2ff581a4654d58a9f2fb276b Mon Sep 17 00:00:00 2001
From: CJACK <tetr20071102@gmail.com>
Date: Fri, 1 May 2026 21:15:17 +0800
Subject: [PATCH 3/7] 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",

From 3430322e8179bc5a3c290b535546fa1ecb269813 Mon Sep 17 00:00:00 2001
From: BigUncle <biguncle2017@gmail.com>
Date: Fri, 1 May 2026 21:17:52 +0800
Subject: [PATCH 4/7] docs: add Vercel chat history read-only filesystem
 troubleshooting

---
 docs/DEPLOY.en.md | 17 +++++++++++++++++
 docs/DEPLOY.md    | 17 +++++++++++++++++
 2 files changed, 34 insertions(+)

diff --git a/docs/DEPLOY.en.md b/docs/DEPLOY.en.md
index a7716a3..b2ed75e 100644
--- a/docs/DEPLOY.en.md
+++ b/docs/DEPLOY.en.md
@@ -271,6 +271,7 @@ VERCEL_TEAM_ID=team_xxxxxxxxxxxx   # optional for personal accounts
 | `VERCEL_TOKEN` | Vercel sync token | — |
 | `VERCEL_PROJECT_ID` | Vercel project ID | — |
 | `VERCEL_TEAM_ID` | Vercel team ID | — |
+| `DS2API_CHAT_HISTORY_PATH` | Chat history storage path (must be set to `/tmp/chat_history.json` on Vercel, otherwise unavailable due to read-only filesystem) | `data/chat_history.json` |
 | `DS2API_VERCEL_PROTECTION_BYPASS` | Deployment protection bypass for internal Node→Go calls | — |
 
 ### 3.4 Vercel Architecture
@@ -360,6 +361,22 @@ If API responses return Vercel HTML `Authentication Required`:
 - **Option B**: Add `x-vercel-protection-bypass` header to requests
 - **Option C**: Set `VERCEL_AUTOMATION_BYPASS_SECRET` (or `DS2API_VERCEL_PROTECTION_BYPASS`) for internal Node→Go calls
 
+#### Chat History Unavailable (read-only file system)
+
+```text
+create chat history dir: mkdir /var/task/data: read-only file system
+```
+
+**Cause**: Vercel Serverless functions have a read-only filesystem (`/var/task`). Chat history fails because it cannot create directories there.
+
+**Fix**: Add the following in Vercel Project Settings → Environment Variables:
+
+```text
+DS2API_CHAT_HISTORY_PATH=/tmp/chat_history.json
+```
+
+`/tmp` is the only writable directory in Vercel Serverless. Data is ephemeral (not persisted across cold starts), but the feature works within a single instance lifetime.
+
 ### 3.6 Build Artifacts Not Committed
 
 - `static/admin` directory is not in Git
diff --git a/docs/DEPLOY.md b/docs/DEPLOY.md
index 3ff20ed..4a1b75f 100644
--- a/docs/DEPLOY.md
+++ b/docs/DEPLOY.md
@@ -271,6 +271,7 @@ VERCEL_TEAM_ID=team_xxxxxxxxxxxx   # 个人账号可留空
 | `VERCEL_TOKEN` | Vercel 同步 token | — |
 | `VERCEL_PROJECT_ID` | Vercel 项目 ID | — |
 | `VERCEL_TEAM_ID` | Vercel 团队 ID | — |
+| `DS2API_CHAT_HISTORY_PATH` | Chat history 存储路径（Vercel 上必须设为 `/tmp/chat_history.json`，否则因文件系统只读而不可用） | `data/chat_history.json` |
 | `DS2API_VERCEL_PROTECTION_BYPASS` | 部署保护绕过密钥（内部 Node→Go 调用） | — |
 
 ### 3.3 运行时行为配置（通过 Admin API 设置）
@@ -370,6 +371,22 @@ No Output Directory named "public" found after the Build completed.
 - **方案 B**：请求中添加 `x-vercel-protection-bypass` 头
 - **方案 C**：设置 `VERCEL_AUTOMATION_BYPASS_SECRET`（或 `DS2API_VERCEL_PROTECTION_BYPASS`），仅影响内部 Node→Go 调用
 
+#### Chat History 不可用（read-only file system）
+
+```text
+create chat history dir: mkdir /var/task/data: read-only file system
+```
+
+**原因**：Vercel Serverless 函数的文件系统（`/var/task`）为只读，chat history 尝试在该路径下创建目录失败。
+
+**解决**：在 Vercel Project Settings → Environment Variables 中添加：
+
+```text
+DS2API_CHAT_HISTORY_PATH=/tmp/chat_history.json
+```
+
+`/tmp` 是 Vercel Serverless 环境中唯一可写的目录。数据在函数冷启动之间不会持久化（ephemeral），但在单个实例生命周期内功能正常。
+
 ### 3.6 仓库不提交构建产物
 
 - `static/admin` 目录不在 Git 中

From 43402e7a260827a8da029860e9f0416178a90832 Mon Sep 17 00:00:00 2001
From: CJACK <tetr20071102@gmail.com>
Date: Fri, 1 May 2026 22:05:45 +0800
Subject: [PATCH 5/7] refactor: rename history file constant from HISTORY.txt
 to DS2API_HISTORY.txt across codebase and tests

---
 README.MD                                     |  2 +-
 README.en.md                                  |  2 +-
 docs/prompt-compatibility.md                  | 12 ++++----
 .../httpapi/openai/chat/chat_history_test.go  |  4 +--
 .../openai/history/current_input_file.go      |  2 +-
 internal/httpapi/openai/history_split_test.go | 30 +++++++++----------
 internal/promptcompat/history_transcript.go   |  4 +--
 .../upstream.stream.sse                       |  2 +-
 .../upstream.stream.sse                       |  2 +-
 webui/src/locales/en.json                     |  4 +--
 webui/src/locales/zh.json                     |  4 +--
 11 files changed, 34 insertions(+), 34 deletions(-)

diff --git a/README.MD b/README.MD
index be7698f..ebb8a70 100644
--- a/README.MD
+++ b/README.MD
@@ -318,7 +318,7 @@ go run ./cmd/ds2api
 - `runtime`：账号并发、队列与 token 刷新策略，可通过 Admin Settings 热更新。
 - `auto_delete.mode`：请求结束后的远端会话清理策略，支持 `none` / `single` / `all`。
 - `history_split`：旧轮次拆分字段，已废弃并忽略，仅保留兼容旧配置。
-- `current_input_file`：唯一生效的独立拆分策略；默认开启且阈值为 `0`，触发时将完整上下文合并上传为 `history.txt` 上下文文件。
+- `current_input_file`：唯一生效的独立拆分策略；默认开启且阈值为 `0`，触发时将完整上下文合并上传为 `DS2API_HISTORY.txt` 上下文文件。
 - 如果关闭 `current_input_file`，请求会直接透传，不上传拆分上下文文件。
 - `thinking_injection`：默认开启；在最新 user 消息末尾追加思考增强提示词，提高高强度推理与工具调用前的思考稳定性；`prompt` 留空时使用内置默认提示词。
 
diff --git a/README.en.md b/README.en.md
index c2ebf0e..267f7b1 100644
--- a/README.en.md
+++ b/README.en.md
@@ -306,7 +306,7 @@ Common fields:
 - `runtime`: account concurrency, queueing, and token refresh behavior, hot-reloadable via Admin Settings.
 - `auto_delete.mode`: remote session cleanup after each request, supporting `none` / `single` / `all`.
 - `history_split`: legacy multi-turn history split field, now ignored and kept only for backward-compatible config loading.
-- `current_input_file`: the only active split mode; it is enabled by default and uploads the full context as a `history.txt` context file once the character threshold is reached.
+- `current_input_file`: the only active split mode; it is enabled by default and uploads the full context as a `DS2API_HISTORY.txt` context file once the character threshold is reached.
 - If you turn off `current_input_file`, requests pass through directly without uploading any split context file.
 
 For the full environment variable list, see [docs/DEPLOY.en.md](docs/DEPLOY.en.md). For auth behavior, see [API.en.md](API.en.md#authentication).
diff --git a/docs/prompt-compatibility.md b/docs/prompt-compatibility.md
index f5e55c8..f3538ff 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。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。
+- `current_input_file` 默认开启；它用于把“完整上下文”合并进 `DS2API_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 `DS2API_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 `DS2API_HISTORY.txt` 风格 transcript，带有 `# DS2API_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 +263,11 @@ 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，再按轮次编号成 `HISTORY.txt` 风格的 transcript（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 `DS2API_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 `DS2API_HISTORY.txt` 风格的 transcript（不再注入文件边界标签）：
 
 ```text
-[uploaded filename]: HISTORY.txt
-# HISTORY.txt
+[uploaded filename]: DS2API_HISTORY.txt
+# DS2API_HISTORY.txt
 Prior conversation history and tool progress.
 
 === 1. SYSTEM ===
@@ -347,7 +347,7 @@ Prior conversation history and tool progress.
 
 - 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，并按轮次编号成 transcript
+- 需要时把完整上下文拆进 `DS2API_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
 
@@ -360,7 +360,7 @@ Prior conversation history and tool progress.
 - 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` transcript 结构变更
+- current input file 触发条件、上传格式、`DS2API_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 6b9f2a0..89bc02d 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 != "DS2API_HISTORY.txt" {
+		t.Fatalf("expected DS2API_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 7069207..10d5297 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 DS2API_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 799a1f7..27a3bf7 100644
--- a/internal/httpapi/openai/history_split_test.go
+++ b/internal/httpapi/openai/history_split_test.go
@@ -68,7 +68,7 @@ func TestBuildOpenAICurrentInputContextTranscriptUsesNumberedHistorySections(t *
 	if strings.Contains(transcript, "[file content end]") || strings.Contains(transcript, "[file content begin]") || strings.Contains(transcript, "[file name]:") {
 		t.Fatalf("expected transcript without file wrapper tags, got %q", transcript)
 	}
-	if !strings.Contains(transcript, "# HISTORY.txt") {
+	if !strings.Contains(transcript, "# DS2API_HISTORY.txt") {
 		t.Fatalf("expected history transcript header, got %q", transcript)
 	}
 	if !strings.Contains(transcript, "Prior conversation history and tool progress.") {
@@ -280,7 +280,7 @@ func TestApplyCurrentInputFileUploadsFirstTurnWithNumberedHistoryTranscript(t *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 != "DS2API_HISTORY.txt" {
 		t.Fatalf("unexpected upload filename: %q", upload.Filename)
 	}
 	uploadedText := string(upload.Data)
@@ -288,7 +288,7 @@ func TestApplyCurrentInputFileUploadsFirstTurnWithNumberedHistoryTranscript(t *t
 		t.Fatalf("expected uploaded transcript without file wrapper tags, got %q", uploadedText)
 	}
 	for _, want := range []string{
-		"# HISTORY.txt",
+		"# DS2API_HISTORY.txt",
 		"=== 1. USER ===",
 		"first turn content that is long enough",
 	} {
@@ -303,7 +303,7 @@ func TestApplyCurrentInputFileUploadsFirstTurnWithNumberedHistoryTranscript(t *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, "HISTORY.txt") || strings.Contains(out.FinalPrompt, "Read that file") {
+	if strings.Contains(out.FinalPrompt, "CURRENT_USER_INPUT.txt") || strings.Contains(out.FinalPrompt, "DS2API_HISTORY.txt") || strings.Contains(out.FinalPrompt, "DS2API_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.") {
@@ -315,7 +315,7 @@ func TestApplyCurrentInputFileUploadsFirstTurnWithNumberedHistoryTranscript(t *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 ===") {
+	if !strings.Contains(out.PromptTokenText, "# DS2API_HISTORY.txt") || !strings.Contains(out.PromptTokenText, "=== 1. USER ===") {
 		t.Fatalf("expected prompt token text to include numbered history transcript, got %q", out.PromptTokenText)
 	}
 }
@@ -355,7 +355,7 @@ func TestApplyCurrentInputFilePreservesFullContextPromptForTokenCounting(t *test
 	if strings.Contains(out.PromptTokenText, "[file content end]") || strings.Contains(out.PromptTokenText, "[file name]:") {
 		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 ===") {
+	if !strings.Contains(out.PromptTokenText, "# DS2API_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.") {
@@ -397,16 +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 != "DS2API_HISTORY.txt" {
+		t.Fatalf("expected DS2API_HISTORY.txt upload, got %q", upload.Filename)
 	}
 	uploadedText := string(upload.Data)
-	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} {
+	for _, want := range []string{"# DS2API_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, "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, "DS2API_HISTORY.txt") || strings.Contains(out.FinalPrompt, "DS2API_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.") {
@@ -442,7 +442,7 @@ 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 ===") {
+	if !strings.Contains(out.HistoryText, "# DS2API_HISTORY.txt") || !strings.Contains(out.HistoryText, "=== 1. SYSTEM ===") {
 		t.Fatalf("expected history text to use numbered transcript format, got %q", out.HistoryText)
 	}
 }
@@ -476,7 +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 != "DS2API_HISTORY.txt" {
 		t.Fatalf("unexpected upload filename: %q", upload.Filename)
 	}
 	if upload.Purpose != "assistants" {
@@ -486,7 +486,7 @@ func TestChatCompletionsCurrentInputFileUploadsContextAndKeepsNeutralPrompt(t *t
 	if strings.Contains(historyText, "[file content end]") || strings.Contains(historyText, "[file content begin]") || strings.Contains(historyText, "[file name]:") {
 		t.Fatalf("expected history transcript without file wrapper tags, got %s", historyText)
 	}
-	if !strings.Contains(historyText, "# HISTORY.txt") || !strings.Contains(historyText, "=== 1. SYSTEM ===") {
+	if !strings.Contains(historyText, "# DS2API_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") {
@@ -549,7 +549,7 @@ func TestResponsesCurrentInputFileUploadsContextAndKeepsNeutralPrompt(t *testing
 		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 ===") {
+	if !strings.Contains(historyText, "# DS2API_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 {
@@ -699,7 +699,7 @@ func TestCurrentInputFileWorksAcrossAutoDeleteModes(t *testing.T) {
 				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 ===") {
+			if !strings.Contains(historyText, "# DS2API_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 {
diff --git a/internal/promptcompat/history_transcript.go b/internal/promptcompat/history_transcript.go
index 84a62cb..fbbfc4b 100644
--- a/internal/promptcompat/history_transcript.go
+++ b/internal/promptcompat/history_transcript.go
@@ -5,9 +5,9 @@ import (
 	"strings"
 )
 
-const CurrentInputContextFilename = "HISTORY.txt"
+const CurrentInputContextFilename = "DS2API_HISTORY.txt"
 
-const historyTranscriptTitle = "# HISTORY.txt"
+const historyTranscriptTitle = "# DS2API_HISTORY.txt"
 const historyTranscriptSummary = "Prior conversation history and tool progress."
 
 func BuildOpenAIHistoryTranscript(messages []any) string {
diff --git a/tests/raw_stream_samples/longtext-deepseek-v4-flash-20260429/upstream.stream.sse b/tests/raw_stream_samples/longtext-deepseek-v4-flash-20260429/upstream.stream.sse
index 4048f8e..bc412db 100644
--- a/tests/raw_stream_samples/longtext-deepseek-v4-flash-20260429/upstream.stream.sse
+++ b/tests/raw_stream_samples/longtext-deepseek-v4-flash-20260429/upstream.stream.sse
@@ -1,4 +1,4 @@
-{"code":0,"msg":"","data":{"biz_code":0,"biz_msg":"","biz_data":{"id":"file-b10a2aca-39e9-4a38-be9d-9f22e398cb62","status":"PENDING","file_name":"history.txt","from_share":false,"file_size":732,"model_kind":"NORMAL","token_usage":null,"error_code":null,"inserted_at":1777485015.255,"updated_at":1777485015.255,"is_image":false,"audit_result":null}}}
+{"code":0,"msg":"","data":{"biz_code":0,"biz_msg":"","biz_data":{"id":"file-b10a2aca-39e9-4a38-be9d-9f22e398cb62","status":"PENDING","file_name":"DS2API_HISTORY.txt","from_share":false,"file_size":732,"model_kind":"NORMAL","token_usage":null,"error_code":null,"inserted_at":1777485015.255,"updated_at":1777485015.255,"is_image":false,"audit_result":null}}}
 event: ready
 data: {"request_message_id":1,"response_message_id":2,"model_type":"default"}
 
diff --git a/tests/raw_stream_samples/longtext-deepseek-v4-pro-20260429/upstream.stream.sse b/tests/raw_stream_samples/longtext-deepseek-v4-pro-20260429/upstream.stream.sse
index 8b14272..72a3d07 100644
--- a/tests/raw_stream_samples/longtext-deepseek-v4-pro-20260429/upstream.stream.sse
+++ b/tests/raw_stream_samples/longtext-deepseek-v4-pro-20260429/upstream.stream.sse
@@ -1,4 +1,4 @@
-{"code":0,"msg":"","data":{"biz_code":0,"biz_msg":"","biz_data":{"id":"file-9c8ae986-75f7-4611-9956-5e1b502f3ec2","status":"SUCCESS","file_name":"history.txt","from_share":false,"file_size":732,"model_kind":"NORMAL","token_usage":145,"error_code":null,"inserted_at":1777485076.42,"updated_at":1777485076.42,"signed_path":"/file?file_id=9c8ae986-75f7-4611-9956-5e1b502f3ec2&state=a1REa2AdO8JmDuxMFiUTPJfpiyY4ie2weyUpYxfvEOrk5lxUCZifpRw9toZAEzn3DAjkgbR6blgZf41KLkHBKwwrcYTIjfxTRKijDqjEfguis03yddpuVrii6keG4%2BXIlcLAsyZG3qcGhfTGVZhsr%2BRl17J%2BcnT9roslhxBcEy4rthFJVMWUI%2BSHjuo2gLEUDfvMfULQ1gSLVGtr%2Fpq%2FcNPCPSxZapIQv04ZVmJLcdbzRkz%2Bb%2BxM5RWUIPujp%2B3ke1WDa3%2B6S4pP0Pv%2BAJ0MFUjQsloUwO4AsJ8YhGBFWg8Ehe1b2yt1N%2Fi%2BIjLRPt5xiNmALcJJXIY%3D","is_image":false,"audit_result":null}}}
+{"code":0,"msg":"","data":{"biz_code":0,"biz_msg":"","biz_data":{"id":"file-9c8ae986-75f7-4611-9956-5e1b502f3ec2","status":"SUCCESS","file_name":"DS2API_HISTORY.txt","from_share":false,"file_size":732,"model_kind":"NORMAL","token_usage":145,"error_code":null,"inserted_at":1777485076.42,"updated_at":1777485076.42,"signed_path":"/file?file_id=9c8ae986-75f7-4611-9956-5e1b502f3ec2&state=a1REa2AdO8JmDuxMFiUTPJfpiyY4ie2weyUpYxfvEOrk5lxUCZifpRw9toZAEzn3DAjkgbR6blgZf41KLkHBKwwrcYTIjfxTRKijDqjEfguis03yddpuVrii6keG4%2BXIlcLAsyZG3qcGhfTGVZhsr%2BRl17J%2BcnT9roslhxBcEy4rthFJVMWUI%2BSHjuo2gLEUDfvMfULQ1gSLVGtr%2Fpq%2FcNPCPSxZapIQv04ZVmJLcdbzRkz%2Bb%2BxM5RWUIPujp%2B3ke1WDa3%2B6S4pP0Pv%2BAJ0MFUjQsloUwO4AsJ8YhGBFWg8Ehe1b2yt1N%2Fi%2BIjLRPt5xiNmALcJJXIY%3D","is_image":false,"audit_result":null}}}
 event: ready
 data: {"request_message_id":1,"response_message_id":2,"model_type":"expert"}
 
diff --git a/webui/src/locales/en.json b/webui/src/locales/en.json
index 072e514..0808398 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 DS2API_HISTORY.txt context file.",
         "currentInputFileMinChars": "Current input threshold (characters)",
         "currentInputFileHelp": "Default is 0, which uses independent split for any non-empty input.",
         "compatibilityTitle": "Compatibility",
@@ -485,4 +485,4 @@
             "four": "Trigger a redeploy to apply the updated environment variables."
         }
     }
-}
+}
\ No newline at end of file
diff --git a/webui/src/locales/zh.json b/webui/src/locales/zh.json
index 409f48d..b3b2460 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 DS2API_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",
@@ -485,4 +485,4 @@
             "four": "触发重新部署以应用新的环境变量。"
         }
     }
-}
+}
\ No newline at end of file

From dd5a0c52136a0fdfc2e76c8873cc2603ffc53f48 Mon Sep 17 00:00:00 2001
From: CJACK <tetr20071102@gmail.com>
Date: Fri, 1 May 2026 22:27:59 +0800
Subject: [PATCH 6/7] refactor: update and standardize current input file
 continuation prompt instructions

---
 docs/prompt-compatibility.md                  |  4 +--
 .../httpapi/openai/chat/chat_history_test.go  |  6 ++--
 .../openai/chat/vercel_prepare_test.go        |  4 +--
 .../openai/history/current_input_file.go      |  4 +--
 internal/httpapi/openai/history_split_test.go | 28 +++++++++----------
 .../chatHistory/ChatHistoryContainer.jsx      | 12 ++++++--
 6 files changed, 33 insertions(+), 25 deletions(-)

diff --git a/docs/prompt-compatibility.md b/docs/prompt-compatibility.md
index f3538ff..58c2c6c 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 `DS2API_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 `DS2API_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 `DS2API_HISTORY.txt` 风格 transcript，带有 `# DS2API_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。
+- `current_input_file` 默认开启；它用于把“完整上下文”合并进 `DS2API_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 `DS2API_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 `DS2API_HISTORY.txt` 风格 transcript，带有 `# DS2API_HISTORY.txt` 标题和 `=== N. ROLE ===` 分段；live prompt 中则会给出一个 continuation 语气的 user 消息，引导模型从 `DS2API_HISTORY.txt` 的最新状态继续推进，并直接回答最新请求，避免把任务拉回起点。
 - 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。
@@ -332,7 +332,7 @@ Prior conversation history and tool progress.
 
 ```json
 {
-  "prompt": "<｜begin▁of▁sentence｜><｜System｜>原 system / developer\n\nYou have access to these tools: ...<｜end▁of▁instructions｜><｜User｜>The current request and prior conversation context have already been provided. Answer the latest user request directly.<｜Assistant｜>",
+  "prompt": "<｜begin▁of▁sentence｜><｜System｜>原 system / developer\n\nYou have access to these tools: ...<｜end▁of▁instructions｜><｜User｜>Continue from the latest state in the attached DS2API_HISTORY.txt context. Treat it as the current working state and answer the latest user request directly.<｜Assistant｜>",
   "ref_file_ids": [
     "file-current-input-ignore",
     "file-systemprompt",
diff --git a/internal/httpapi/openai/chat/chat_history_test.go b/internal/httpapi/openai/chat/chat_history_test.go
index 89bc02d..e0c47fc 100644
--- a/internal/httpapi/openai/chat/chat_history_test.go
+++ b/internal/httpapi/openai/chat/chat_history_test.go
@@ -318,9 +318,9 @@ func TestChatCompletionsCurrentInputFilePersistsNeutralPrompt(t *testing.T) {
 		t.Fatalf("expected uploaded current input file to be persisted in history text")
 	}
 	if len(full.Messages) != 1 {
-		t.Fatalf("expected neutral prompt to be the only persisted message, got %#v", full.Messages)
+		t.Fatalf("expected continuation prompt to be the only persisted message, got %#v", full.Messages)
 	}
-	if !strings.Contains(full.Messages[0].Content, "Answer the latest user request directly.") {
-		t.Fatalf("expected neutral prompt to be persisted, got %#v", full.Messages[0])
+	if !strings.Contains(full.Messages[0].Content, "Continue from the latest state in the attached DS2API_HISTORY.txt context.") {
+		t.Fatalf("expected continuation prompt to be persisted, got %#v", full.Messages[0])
 	}
 }
diff --git a/internal/httpapi/openai/chat/vercel_prepare_test.go b/internal/httpapi/openai/chat/vercel_prepare_test.go
index 59e62d9..b27be18 100644
--- a/internal/httpapi/openai/chat/vercel_prepare_test.go
+++ b/internal/httpapi/openai/chat/vercel_prepare_test.go
@@ -130,8 +130,8 @@ func TestHandleVercelStreamPrepareAppliesCurrentInputFile(t *testing.T) {
 		t.Fatalf("expected payload object, got %#v", body["payload"])
 	}
 	promptText, _ := payload["prompt"].(string)
-	if !strings.Contains(promptText, "Answer the latest user request directly.") {
-		t.Fatalf("expected neutral prompt, got %s", promptText)
+	if !strings.Contains(promptText, "Continue from the latest state in the attached DS2API_HISTORY.txt context.") {
+		t.Fatalf("expected continuation prompt, got %s", promptText)
 	}
 	if strings.Contains(promptText, "first user turn") || strings.Contains(promptText, "latest user turn") {
 		t.Fatalf("expected original turns hidden from prompt, got %s", promptText)
diff --git a/internal/httpapi/openai/history/current_input_file.go b/internal/httpapi/openai/history/current_input_file.go
index 10d5297..648331c 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 DS2API_HISTORY.txt file content + the neutral live prompt.
+	// the uploaded DS2API_HISTORY.txt file content + the continuation live prompt.
 	stdReq.PromptTokenText = fileText + "\n" + stdReq.FinalPrompt
 	return stdReq, nil
 }
@@ -87,5 +87,5 @@ func latestUserInputForFile(messages []any) (int, string) {
 }
 
 func currentInputFilePrompt() string {
-	return "The current request and prior conversation context have already been provided. Answer the latest user request directly."
+	return "Continue from the latest state in the attached DS2API_HISTORY.txt context. Treat it as the current working state and answer the latest user request directly."
 }
diff --git a/internal/httpapi/openai/history_split_test.go b/internal/httpapi/openai/history_split_test.go
index 27a3bf7..d223689 100644
--- a/internal/httpapi/openai/history_split_test.go
+++ b/internal/httpapi/openai/history_split_test.go
@@ -303,11 +303,11 @@ func TestApplyCurrentInputFileUploadsFirstTurnWithNumberedHistoryTranscript(t *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, "DS2API_HISTORY.txt") || strings.Contains(out.FinalPrompt, "DS2API_HISTORY.txt") || strings.Contains(out.FinalPrompt, "Read that file") {
+	if strings.Contains(out.FinalPrompt, "CURRENT_USER_INPUT.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.") {
-		t.Fatalf("expected neutral continuation instruction in live prompt, got %s", out.FinalPrompt)
+	if !strings.Contains(out.FinalPrompt, "Continue from the latest state in the attached DS2API_HISTORY.txt context.") {
+		t.Fatalf("expected continuation-oriented prompt in live prompt, got %s", out.FinalPrompt)
 	}
 	if len(out.RefFileIDs) != 1 || out.RefFileIDs[0] != "file-inline-1" {
 		t.Fatalf("expected current input file id in ref_file_ids, got %#v", out.RefFileIDs)
@@ -358,8 +358,8 @@ func TestApplyCurrentInputFilePreservesFullContextPromptForTokenCounting(t *test
 	if !strings.Contains(out.PromptTokenText, "# DS2API_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)
+	if !strings.Contains(out.PromptTokenText, "Continue from the latest state in the attached DS2API_HISTORY.txt context.") {
+		t.Fatalf("expected prompt token text to also include continuation prompt, got %q", out.PromptTokenText)
 	}
 	if strings.Contains(out.FinalPrompt, "first user turn") || strings.Contains(out.FinalPrompt, "latest user turn") {
 		t.Fatalf("expected live prompt to hide original turns, got %q", out.FinalPrompt)
@@ -406,11 +406,11 @@ func TestApplyCurrentInputFileUploadsFullContextFile(t *testing.T) {
 			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, "DS2API_HISTORY.txt") || strings.Contains(out.FinalPrompt, "DS2API_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, "first user turn") || strings.Contains(out.FinalPrompt, "latest user turn") || strings.Contains(out.FinalPrompt, "CURRENT_USER_INPUT.txt") || strings.Contains(out.FinalPrompt, "Read that file") {
+		t.Fatalf("expected live prompt to use only a continuation instruction, got %s", out.FinalPrompt)
 	}
-	if !strings.Contains(out.FinalPrompt, "Answer the latest user request directly.") {
-		t.Fatalf("expected neutral continuation instruction in live prompt, got %s", out.FinalPrompt)
+	if !strings.Contains(out.FinalPrompt, "Continue from the latest state in the attached DS2API_HISTORY.txt context.") {
+		t.Fatalf("expected continuation-oriented prompt in live prompt, got %s", out.FinalPrompt)
 	}
 }
 
@@ -496,8 +496,8 @@ func TestChatCompletionsCurrentInputFileUploadsContextAndKeepsNeutralPrompt(t *t
 		t.Fatal("expected completion payload to be captured")
 	}
 	promptText, _ := ds.completionReq["prompt"].(string)
-	if !strings.Contains(promptText, "Answer the latest user request directly.") {
-		t.Fatalf("expected neutral completion prompt, got %s", promptText)
+	if !strings.Contains(promptText, "Continue from the latest state in the attached DS2API_HISTORY.txt context.") {
+		t.Fatalf("expected continuation-oriented prompt, got %s", promptText)
 	}
 	if strings.Contains(promptText, "first user turn") || strings.Contains(promptText, "latest user turn") {
 		t.Fatalf("expected prompt to hide original turns, got %s", promptText)
@@ -556,8 +556,8 @@ func TestResponsesCurrentInputFileUploadsContextAndKeepsNeutralPrompt(t *testing
 		t.Fatal("expected completion payload to be captured")
 	}
 	promptText, _ := ds.completionReq["prompt"].(string)
-	if !strings.Contains(promptText, "Answer the latest user request directly.") {
-		t.Fatalf("expected neutral completion prompt, got %s", promptText)
+	if !strings.Contains(promptText, "Continue from the latest state in the attached DS2API_HISTORY.txt context.") {
+		t.Fatalf("expected continuation-oriented prompt, got %s", promptText)
 	}
 	if strings.Contains(promptText, "first user turn") || strings.Contains(promptText, "latest user turn") {
 		t.Fatalf("expected prompt to hide original turns, got %s", promptText)
@@ -706,7 +706,7 @@ func TestCurrentInputFileWorksAcrossAutoDeleteModes(t *testing.T) {
 				t.Fatalf("expected completion payload for mode=%s", mode)
 			}
 			promptText, _ := ds.completionReq["prompt"].(string)
-			if !strings.Contains(promptText, "Answer the latest user request directly.") || strings.Contains(promptText, "first user turn") || strings.Contains(promptText, "latest user turn") {
+			if !strings.Contains(promptText, "Continue from the latest state in the attached DS2API_HISTORY.txt context.") || strings.Contains(promptText, "first user turn") || strings.Contains(promptText, "latest user turn") {
 				t.Fatalf("unexpected prompt for mode=%s: %s", mode, promptText)
 			}
 		})
diff --git a/webui/src/features/chatHistory/ChatHistoryContainer.jsx b/webui/src/features/chatHistory/ChatHistoryContainer.jsx
index e0b574f..c0dc98c 100644
--- a/webui/src/features/chatHistory/ChatHistoryContainer.jsx
+++ b/webui/src/features/chatHistory/ChatHistoryContainer.jsx
@@ -16,7 +16,15 @@ const TOOL_MARKER = '<｜Tool｜>'
 const END_INSTRUCTIONS_MARKER = '<｜end▁of▁instructions｜>'
 const END_SENTENCE_MARKER = '<｜end▁of▁sentence｜>'
 const END_TOOL_RESULTS_MARKER = '<｜end▁of▁toolresults｜>'
-const CURRENT_INPUT_FILE_PROMPT = 'The current request and prior conversation context have already been provided. Answer the latest user request directly.'
+const CURRENT_INPUT_FILE_PROMPT = 'Continue from the latest state in the attached DS2API_HISTORY.txt context. Treat it as the current working state and answer the latest user request directly.'
+const LEGACY_CURRENT_INPUT_FILE_PROMPTS = new Set([
+    'The current request and prior conversation context have already been provided. Answer the latest user request directly.',
+])
+
+function isCurrentInputFilePrompt(value) {
+    const text = String(value || '').trim()
+    return text === CURRENT_INPUT_FILE_PROMPT || LEGACY_CURRENT_INPUT_FILE_PROMPTS.has(text)
+}
 
 function formatDateTime(value, lang) {
     if (!value) return '-'
@@ -312,7 +320,7 @@ function buildListModeMessages(item, t) {
 
     const placeholderOnly = liveMessages.length === 1
         && String(liveMessages[0]?.role || '').trim().toLowerCase() === 'user'
-        && String(liveMessages[0]?.content || '').trim() === CURRENT_INPUT_FILE_PROMPT
+        && isCurrentInputFilePrompt(liveMessages[0]?.content)
 
     if (placeholderOnly) {
         return { messages: historyMessages, historyMerged: true }

From 0bca6e2cee713b16896c587a07ae7dae62cf681b Mon Sep 17 00:00:00 2001
From: CJACK <tetr20071102@gmail.com>
Date: Fri, 1 May 2026 23:17:58 +0800
Subject: [PATCH 7/7] feat: implement context cancellation handling for chat
 and response stream runtimes to ensure clean termination without retries

---
 .../openai/chat/chat_stream_runtime.go        |  9 ++
 .../openai/chat/empty_retry_runtime.go        |  7 +-
 .../openai/chat/empty_retry_runtime_test.go   | 85 +++++++++++++++++++
 .../openai/responses/empty_retry_runtime.go   |  9 +-
 .../responses/empty_retry_runtime_test.go     | 70 +++++++++++++++
 .../responses_stream_runtime_core.go          |  7 ++
 6 files changed, 185 insertions(+), 2 deletions(-)
 create mode 100644 internal/httpapi/openai/chat/empty_retry_runtime_test.go
 create mode 100644 internal/httpapi/openai/responses/empty_retry_runtime_test.go

diff --git a/internal/httpapi/openai/chat/chat_stream_runtime.go b/internal/httpapi/openai/chat/chat_stream_runtime.go
index 17ff0d5..a9270a1 100644
--- a/internal/httpapi/openai/chat/chat_stream_runtime.go
+++ b/internal/httpapi/openai/chat/chat_stream_runtime.go
@@ -173,6 +173,15 @@ func (s *chatStreamRuntime) sendFailedChunk(status int, message, code string) {
 	s.sendDone()
 }
 
+func (s *chatStreamRuntime) markContextCancelled() {
+	s.finalErrorStatus = 499
+	s.finalErrorMessage = "request context cancelled"
+	s.finalErrorCode = string(streamengine.StopReasonContextCancelled)
+	s.finalThinking = s.thinking.String()
+	s.finalText = cleanVisibleOutput(s.text.String(), s.stripReferenceMarkers)
+	s.finalFinishReason = string(streamengine.StopReasonContextCancelled)
+}
+
 func (s *chatStreamRuntime) resetStreamToolCallState() {
 	s.streamToolCallIDs = map[int]string{}
 	s.streamToolNames = map[int]string{}
diff --git a/internal/httpapi/openai/chat/empty_retry_runtime.go b/internal/httpapi/openai/chat/empty_retry_runtime.go
index 147024f..464dd2c 100644
--- a/internal/httpapi/openai/chat/empty_retry_runtime.go
+++ b/internal/httpapi/openai/chat/empty_retry_runtime.go
@@ -247,12 +247,13 @@ func (h *Handler) consumeChatStreamAttempt(r *http.Request, resp *http.Response,
 			}
 		},
 		OnContextDone: func() {
+			streamRuntime.markContextCancelled()
 			if historySession != nil {
 				historySession.stopped(streamRuntime.thinking.String(), streamRuntime.text.String(), string(streamengine.StopReasonContextCancelled))
 			}
 		},
 	})
-	if r.Context().Err() != nil {
+	if streamRuntime.finalErrorCode == string(streamengine.StopReasonContextCancelled) {
 		return true, false
 	}
 	terminalWritten := streamRuntime.finalize(finalReason, allowDeferEmpty && finalReason != "content_filter")
@@ -286,6 +287,10 @@ func logChatStreamTerminal(streamRuntime *chatStreamRuntime, attempts int) {
 	if attempts > 0 {
 		source = "synthetic_retry"
 	}
+	if streamRuntime.finalErrorCode == string(streamengine.StopReasonContextCancelled) {
+		config.Logger.Info("[openai_empty_retry] terminal cancelled", "surface", "chat.completions", "stream", true, "retry_attempts", attempts, "error_code", streamRuntime.finalErrorCode)
+		return
+	}
 	if streamRuntime.finalErrorMessage != "" {
 		config.Logger.Info("[openai_empty_retry] terminal empty output", "surface", "chat.completions", "stream", true, "retry_attempts", attempts, "success_source", "none", "error_code", streamRuntime.finalErrorCode)
 		return
diff --git a/internal/httpapi/openai/chat/empty_retry_runtime_test.go b/internal/httpapi/openai/chat/empty_retry_runtime_test.go
new file mode 100644
index 0000000..ff8155f
--- /dev/null
+++ b/internal/httpapi/openai/chat/empty_retry_runtime_test.go
@@ -0,0 +1,85 @@
+package chat
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"ds2api/internal/chathistory"
+	"ds2api/internal/stream"
+)
+
+func TestConsumeChatStreamAttemptMarksContextCancelledState(t *testing.T) {
+	historyStore := newTestChatHistoryStore(t)
+	entry, err := historyStore.Start(chathistory.StartParams{
+		CallerID:  "caller:test",
+		Model:     "deepseek-v4-flash",
+		Stream:    true,
+		UserInput: "hello",
+	})
+	if err != nil {
+		t.Fatalf("start history failed: %v", err)
+	}
+	session := &chatHistorySession{
+		store:       historyStore,
+		entryID:     entry.ID,
+		startedAt:   time.Now(),
+		lastPersist: time.Now(),
+		finalPrompt: "prompt",
+	}
+
+	ctx, cancel := context.WithCancel(context.Background())
+	cancel()
+
+	req := httptest.NewRequest(http.MethodPost, "/v1/chat/completions", nil).WithContext(ctx)
+	rec := httptest.NewRecorder()
+	streamRuntime := newChatStreamRuntime(
+		rec,
+		http.NewResponseController(rec),
+		true,
+		"cid-cancelled",
+		time.Now().Unix(),
+		"deepseek-v4-flash",
+		"prompt",
+		false,
+		false,
+		true,
+		nil,
+		nil,
+		false,
+		false,
+	)
+	resp := makeOpenAISSEHTTPResponse(
+		`data: {"p":"response/content","v":"hello"}`,
+		`data: [DONE]`,
+	)
+
+	h := &Handler{}
+	terminalWritten, retryable := h.consumeChatStreamAttempt(req, resp, streamRuntime, "text", false, session, true)
+	if !terminalWritten || retryable {
+		t.Fatalf("expected cancelled attempt to terminate without retry, got terminalWritten=%v retryable=%v", terminalWritten, retryable)
+	}
+	if got, want := streamRuntime.finalErrorCode, string(stream.StopReasonContextCancelled); got != want {
+		t.Fatalf("expected cancelled final error code %q, got %q", want, got)
+	}
+	if streamRuntime.finalErrorMessage == "" {
+		t.Fatalf("expected cancelled final error message to be preserved")
+	}
+
+	snapshot, err := historyStore.Snapshot()
+	if err != nil {
+		t.Fatalf("snapshot failed: %v", err)
+	}
+	if len(snapshot.Items) != 1 {
+		t.Fatalf("expected one history item, got %d", len(snapshot.Items))
+	}
+	full, err := historyStore.Get(snapshot.Items[0].ID)
+	if err != nil {
+		t.Fatalf("get detail failed: %v", err)
+	}
+	if full.Status != "stopped" {
+		t.Fatalf("expected stopped status, got %#v", full)
+	}
+}
diff --git a/internal/httpapi/openai/responses/empty_retry_runtime.go b/internal/httpapi/openai/responses/empty_retry_runtime.go
index 45d861d..25131e1 100644
--- a/internal/httpapi/openai/responses/empty_retry_runtime.go
+++ b/internal/httpapi/openai/responses/empty_retry_runtime.go
@@ -222,8 +222,11 @@ func (h *Handler) consumeResponsesStreamAttempt(r *http.Request, resp *http.Resp
 				finalReason = "content_filter"
 			}
 		},
+		OnContextDone: func() {
+			streamRuntime.markContextCancelled()
+		},
 	})
-	if r.Context().Err() != nil {
+	if streamRuntime.finalErrorCode == string(streamengine.StopReasonContextCancelled) {
 		return true, false
 	}
 	terminalWritten := streamRuntime.finalize(finalReason, allowDeferEmpty && finalReason != "content_filter")
@@ -238,6 +241,10 @@ func logResponsesStreamTerminal(streamRuntime *responsesStreamRuntime, attempts
 	if attempts > 0 {
 		source = "synthetic_retry"
 	}
+	if streamRuntime.finalErrorCode == string(streamengine.StopReasonContextCancelled) {
+		config.Logger.Info("[openai_empty_retry] terminal cancelled", "surface", "responses", "stream", true, "retry_attempts", attempts, "error_code", streamRuntime.finalErrorCode)
+		return
+	}
 	if streamRuntime.failed {
 		config.Logger.Info("[openai_empty_retry] terminal empty output", "surface", "responses", "stream", true, "retry_attempts", attempts, "success_source", "none", "error_code", streamRuntime.finalErrorCode)
 		return
diff --git a/internal/httpapi/openai/responses/empty_retry_runtime_test.go b/internal/httpapi/openai/responses/empty_retry_runtime_test.go
new file mode 100644
index 0000000..c40e983
--- /dev/null
+++ b/internal/httpapi/openai/responses/empty_retry_runtime_test.go
@@ -0,0 +1,70 @@
+package responses
+
+import (
+	"context"
+	"io"
+	"net/http"
+	"net/http/httptest"
+	"strings"
+	"testing"
+
+	"ds2api/internal/promptcompat"
+	"ds2api/internal/stream"
+)
+
+func makeResponsesOpenAISSEHTTPResponse(lines ...string) *http.Response {
+	body := strings.Join(lines, "\n")
+	if !strings.HasSuffix(body, "\n") {
+		body += "\n"
+	}
+	return &http.Response{
+		StatusCode: http.StatusOK,
+		Header:     make(http.Header),
+		Body:       io.NopCloser(strings.NewReader(body)),
+	}
+}
+
+func TestConsumeResponsesStreamAttemptMarksContextCancelledState(t *testing.T) {
+	ctx, cancel := context.WithCancel(context.Background())
+	cancel()
+
+	req := httptest.NewRequest(http.MethodPost, "/v1/responses", nil).WithContext(ctx)
+	rec := httptest.NewRecorder()
+	streamRuntime := newResponsesStreamRuntime(
+		rec,
+		http.NewResponseController(rec),
+		true,
+		"resp-cancelled",
+		"deepseek-v4-flash",
+		"prompt",
+		false,
+		false,
+		true,
+		nil,
+		nil,
+		false,
+		false,
+		promptcompat.DefaultToolChoicePolicy(),
+		"",
+		nil,
+	)
+	resp := makeResponsesOpenAISSEHTTPResponse(
+		`data: {"p":"response/content","v":"hello"}`,
+		`data: [DONE]`,
+	)
+
+	h := &Handler{}
+	terminalWritten, retryable := h.consumeResponsesStreamAttempt(req, resp, streamRuntime, "text", false, true)
+	if !terminalWritten || retryable {
+		t.Fatalf("expected cancelled attempt to terminate without retry, got terminalWritten=%v retryable=%v", terminalWritten, retryable)
+	}
+	if !streamRuntime.failed {
+		t.Fatalf("expected cancelled response stream to be marked failed")
+	}
+	if got, want := streamRuntime.finalErrorCode, string(stream.StopReasonContextCancelled); got != want {
+		t.Fatalf("expected cancelled final error code %q, got %q", want, got)
+	}
+	if streamRuntime.finalErrorMessage == "" {
+		t.Fatalf("expected cancelled final error message to be preserved")
+	}
+}
diff --git a/internal/httpapi/openai/responses/responses_stream_runtime_core.go b/internal/httpapi/openai/responses/responses_stream_runtime_core.go
index 7184c3f..a4749c0 100644
--- a/internal/httpapi/openai/responses/responses_stream_runtime_core.go
+++ b/internal/httpapi/openai/responses/responses_stream_runtime_core.go
@@ -139,6 +139,13 @@ func (s *responsesStreamRuntime) failResponse(status int, message, code string)
 	s.sendDone()
 }
 
+func (s *responsesStreamRuntime) markContextCancelled() {
+	s.failed = true
+	s.finalErrorStatus = 499
+	s.finalErrorMessage = "request context cancelled"
+	s.finalErrorCode = string(streamengine.StopReasonContextCancelled)
+}
+
 func (s *responsesStreamRuntime) finalize(finishReason string, deferEmptyOutput bool) bool {
 	s.failed = false
 	s.finalErrorStatus = 0