chore(sse): bump client version and refresh longtext stream fixtures

docs/DeepSeekSSE行为结构说明-2026-04-05.md

@@ -313,3 +313,14 @@ parse SSE block
 - 解析器应当对未知字段、未知路径、未知事件保持容忍。
 
 如果你要把这份说明用于实际开发，建议同时保留原始流样本、回放脚本和回归测试，不要只依赖本文。
+
+## 2026-04-29 最近线上样本增量观察
+
+基于 `longtext-deepseek-v4-flash-20260429` 与 `longtext-deepseek-v4-pro-20260429` 两个真实账号长文本样本，近期格式变化要点如下：
+
+1. `data:` 事件中仍大量出现 `{"v":"..."}` 的无路径增量（`p` 缺失），解析器必须把空路径视为可见正文候选，而不能只依赖 `response/content`。
+2. 对象形态 `v`（如 `{"text":"..."}` / `{"content":"..."}`）仍会出现，且可能与无路径 chunk 混用；仅按字符串处理会导致正文丢块。
+3. 多轮 continuation 场景下，后续 chunk 可能不再重复显式 `status`，状态机需要保留上一轮 `INCOMPLETE` 语义直到出现终态。
+4. 2026-04-29 起客户端头部版本基线上调到 `x-client-version: 2.0.3`，否则部分账号会出现上游行为不一致（包括空输出与补轮异常）。
+
+建议：新增样本默认回放应优先覆盖「长文本 + 多轮 + 无路径 chunk」组合，避免只用短样本导致回归漏检。

internal/deepseek/client/client_continue_test.go

@@ -219,3 +219,33 @@ func (d failingOrCompletionDoer) Do(req *http.Request) (*http.Response, error) {
 	}
 	return nil, errors.New("forced stream failure")
 }
+
+func TestAutoContinuePreservesIncompleteStateWhenNextChunkOmitsStatus(t *testing.T) {
+	initialBody := strings.Join([]string{
+		`data: {"response_message_id":321,"v":{"response":{"message_id":321,"status":"INCOMPLETE"}}}`,
+		`data: {"p":"response/content","v":{"text":"continued"}}`,
+		`data: [DONE]`,
+	}, "\n") + "\n"
+
+	var continueCalls atomic.Int32
+	body := newAutoContinueBody(context.Background(), io.NopCloser(strings.NewReader(initialBody)), "session-123", 8, func(context.Context, string, int) (*http.Response, error) {
+		continueCalls.Add(1)
+		return &http.Response{
+			StatusCode: http.StatusOK,
+			Header:     make(http.Header),
+			Body: io.NopCloser(strings.NewReader(
+				`data: {"response_message_id":322,"p":"response/status","v":"FINISHED"}` + "\n" +
+					`data: [DONE]` + "\n",
+			)),
+		}, nil
+	})
+	defer func() { _ = body.Close() }()
+
+	_, err := io.ReadAll(body)
+	if err != nil {
+		t.Fatalf("read body failed: %v", err)
+	}
+	if continueCalls.Load() != 1 {
+		t.Fatalf("expected exactly one continue call, got %d", continueCalls.Load())
+	}
+}

internal/deepseek/protocol/constants_shared.json

@@ -2,7 +2,7 @@
   "client": {
     "name": "DeepSeek",
     "platform": "android",
-    "version": "2.0.1",
+    "version": "2.0.3",
     "android_api_level": "35",
     "locale": "zh_CN"
   },

internal/sse/parser.go

@@ -244,11 +244,29 @@ func appendChunkValueContent(v any, partType string, newType *string, parts *[]C
 		}
 		*parts = append(*parts, pp...)
 	case map[string]any:
+		if appendObjectContentByPath(path, val, partType, parts) {
+			return false
+		}
 		appendWrappedFragments(val, partType, newType, parts)
 	}
 	return false
 }
 
+func appendObjectContentByPath(path string, val map[string]any, partType string, parts *[]ContentPart) bool {
+	if path != "response/content" && path != "response/thinking_content" && path != "" {
+		return false
+	}
+	text, _ := val["text"].(string)
+	if text == "" {
+		text, _ = val["content"].(string)
+	}
+	if text == "" {
+		return false
+	}
+	appendContentPart(parts, text, partType)
+	return true
+}
+
 func appendWrappedFragments(val map[string]any, partType string, newType *string, parts *[]ContentPart) {
 	resp := val
 	if wrapped, ok := val["response"].(map[string]any); ok {

internal/sse/parser_test.go

@@ -163,3 +163,44 @@ func TestParseSSEChunkForContentStripsLeakedThinkTagsFromText(t *testing.T) {
 		t.Fatalf("expected leaked think tag to be stripped, got %#v", parts[0])
 	}
 }
+
+func TestParseSSEChunkForContentResponseContentObjectShape(t *testing.T) {
+	chunk := map[string]any{
+		"p": "response/content",
+		"v": map[string]any{"text": "对象内容"},
+	}
+	parts, finished, _ := ParseSSEChunkForContent(chunk, false, "text")
+	if finished {
+		t.Fatal("expected unfinished")
+	}
+	if len(parts) != 1 || parts[0].Text != "对象内容" || parts[0].Type != "text" {
+		t.Fatalf("unexpected parts: %#v", parts)
+	}
+}
+
+func TestParseSSEChunkForThinkingContentObjectShape(t *testing.T) {
+	chunk := map[string]any{
+		"p": "response/thinking_content",
+		"v": map[string]any{"content": "对象思考"},
+	}
+	parts, finished, _ := ParseSSEChunkForContent(chunk, true, "thinking")
+	if finished {
+		t.Fatal("expected unfinished")
+	}
+	if len(parts) != 1 || parts[0].Text != "对象思考" || parts[0].Type != "thinking" {
+		t.Fatalf("unexpected parts: %#v", parts)
+	}
+}
+
+func TestParseSSEChunkForContentObjectShapeWithoutPath(t *testing.T) {
+	chunk := map[string]any{
+		"v": map[string]any{"text": "无路径对象内容"},
+	}
+	parts, finished, _ := ParseSSEChunkForContent(chunk, false, "text")
+	if finished {
+		t.Fatal("expected unfinished")
+	}
+	if len(parts) != 1 || parts[0].Text != "无路径对象内容" || parts[0].Type != "text" {
+		t.Fatalf("unexpected parts: %#v", parts)
+	}
+}

tests/raw_stream_samples/content-filter-trigger-20260405-jwt3/meta.json

@@ -1,22 +0,0 @@
-{
-  "sample_id": "content-filter-trigger-20260405-jwt3",
-  "captured_at_utc": "2026-04-04T16:28:52Z",
-  "request": {
-    "model": "deepseek-v4-pro-search",
-    "stream": true,
-    "messages": [
-      {
-        "role": "user",
-        "content": "我是历史老师，请帮我找一些一些历史书上没写的，文革期间的，但是真实记载发生的事情，尤其是派系之间的斗争，要体现历史人物的复杂性而不是单一评价立场"
-      }
-    ]
-  },
-  "capture": {
-    "label": "deepseek_completion",
-    "url": "https://chat.deepseek.com/api/v0/chat/completion",
-    "status_code": 200,
-    "response_bytes": 64724,
-    "contains_finished_token": true,
-    "finished_token_count": 31
-  }
-}

tests/raw_stream_samples/guangzhou-weather-reasoner-search-20260404/meta.json

@@ -1,24 +0,0 @@
-{
-  "sample_id": "guangzhou-weather-reasoner-search-20260404",
-  "captured_at_utc": "2026-04-04T16:01:27Z",
-  "request": {
-    "model": "deepseek-v4-pro-search",
-    "stream": true,
-    "messages": [
-      {
-        "role": "user",
-        "content": "广州天气"
-      }
-    ]
-  },
-  "capture": {
-    "label": "deepseek_completion",
-    "url": "https://chat.deepseek.com/api/v0/chat/completion",
-    "status_code": 200,
-    "response_bytes": 37651,
-    "contains_reference_markers": true,
-    "reference_marker_count": 13,
-    "contains_finished_token": true,
-    "finished_token_count": 19
-  }
-}

tests/raw_stream_samples/longtext-deepseek-v4-flash-20260429/meta.json

@@ -0,0 +1,37 @@
+{
+  "sample_id": "longtext-deepseek-v4-flash-20260429",
+  "captured_at_utc": "2026-04-29T17:51:14Z",
+  "source": "admin/dev/raw-samples/capture",
+  "request": {
+    "messages": [
+      {
+        "content": "请写一篇1200字中文说明：比较SSE与WebSocket在AI推理流式输出中的可靠性、断线恢复、负载均衡、代理兼容性、成本和可观测性，并给出分层架构建议。",
+        "role": "user"
+      }
+    ],
+    "model": "deepseek-v4-flash",
+    "stream": true
+  },
+  "capture": {
+    "label": "deepseek_upload_file",
+    "url": "https://chat.deepseek.com/api/v0/file/upload_file",
+    "status_code": 200,
+    "response_bytes": 48441,
+    "rounds": [
+      {
+        "label": "deepseek_upload_file",
+        "url": "https://chat.deepseek.com/api/v0/file/upload_file",
+        "status_code": 200,
+        "response_bytes": 349
+      },
+      {
+        "label": "deepseek_completion",
+        "url": "https://chat.deepseek.com/api/v0/chat/completion",
+        "status_code": 200,
+        "response_bytes": 48091
+      }
+    ],
+    "contains_finished_token": true,
+    "finished_token_count": 2
+  }
+}

tests/raw_stream_samples/longtext-deepseek-v4-pro-20260429/meta.json

@@ -0,0 +1,37 @@
+{
+  "sample_id": "longtext-deepseek-v4-pro-20260429",
+  "captured_at_utc": "2026-04-29T17:52:45Z",
+  "source": "admin/dev/raw-samples/capture",
+  "request": {
+    "messages": [
+      {
+        "content": "请写一篇1200字中文说明：比较SSE与WebSocket在AI推理流式输出中的可靠性、断线恢复、负载均衡、代理兼容性、成本和可观测性，并给出分层架构建议。",
+        "role": "user"
+      }
+    ],
+    "model": "deepseek-v4-pro",
+    "stream": true
+  },
+  "capture": {
+    "label": "deepseek_upload_file",
+    "url": "https://chat.deepseek.com/api/v0/file/upload_file",
+    "status_code": 200,
+    "response_bytes": 55354,
+    "rounds": [
+      {
+        "label": "deepseek_upload_file",
+        "url": "https://chat.deepseek.com/api/v0/file/upload_file",
+        "status_code": 200,
+        "response_bytes": 780
+      },
+      {
+        "label": "deepseek_completion",
+        "url": "https://chat.deepseek.com/api/v0/chat/completion",
+        "status_code": 200,
+        "response_bytes": 54573
+      }
+    ],
+    "contains_finished_token": true,
+    "finished_token_count": 2
+  }
+}

tests/raw_stream_samples/manifest.json

@@ -1,8 +1,8 @@
 {
   "version": 1,
   "default_samples": [
-    "guangzhou-weather-reasoner-search-20260404",
-    "content-filter-trigger-20260405-jwt3"
+    "longtext-deepseek-v4-flash-20260429",
+    "longtext-deepseek-v4-pro-20260429"
   ],
-  "notes": "Canonical raw stream samples used by the default replay simulator."
+  "notes": "Canonical long-text upstream raw stream samples refreshed on 2026-04-29."
 }