Propagate DeepSeek SSE token usage to /v1/responses and remove stale POW env docs

API.en.md

@@ -267,6 +267,7 @@ data: [DONE]
 - `deepseek-reasoner` / `deepseek-reasoner-search` models emit `delta.reasoning_content`
 - Text emits `delta.content`
 - Last chunk includes `finish_reason` and `usage`
+- Token counting prefers pass-through from upstream DeepSeek SSE (`accumulated_token_usage` / `token_usage`), and only falls back to local estimation when upstream usage is absent
 
 #### Tool Calls
 
@@ -383,6 +384,7 @@ Business auth required. Returns OpenAI-compatible embeddings shape.
 ## Claude-Compatible API
 
 Besides `/anthropic/v1/*`, DS2API also supports shortcut paths: `/v1/messages`, `/messages`, `/v1/messages/count_tokens`, `/messages/count_tokens`.
+Implementation-wise this path is unified on the OpenAI Chat Completions parse-and-translate pipeline to avoid maintaining divergent parsing chains.
 
 ### `GET /anthropic/v1/models`
 
@@ -517,6 +519,7 @@ Supported paths:
 - `/v1/models/{model}:streamGenerateContent` (compat path)
 
 Authentication is the same as other business routes (`Authorization: Bearer <token>` or `x-api-key`).
+Implementation-wise this path is unified on the OpenAI Chat Completions parse-and-translate pipeline to avoid maintaining divergent parsing chains.
 
 ### `POST /v1beta/models/{model}:generateContent`
 
@@ -535,6 +538,7 @@ Returns SSE (`text/event-stream`), each chunk as `data: <json>`:
 - regular text: incremental text chunks
 - `tools` mode: buffered and emitted as `functionCall` at finalize phase
 - final chunk: includes `finishReason: "STOP"` and `usageMetadata`
+- Token counting prefers pass-through from upstream DeepSeek SSE (`accumulated_token_usage` / `token_usage`), and only falls back to local estimation when upstream usage is absent
 
 ---
 

API.md

@@ -267,6 +267,7 @@ data: [DONE]
 - `deepseek-reasoner` / `deepseek-reasoner-search` 模型输出 `delta.reasoning_content`
 - 普通文本输出 `delta.content`
 - 最后一段包含 `finish_reason` 和 `usage`
+- token 计数优先透传上游 DeepSeek SSE（如 `accumulated_token_usage` / `token_usage`）；仅在上游缺失时回退本地估算
 
 #### Tool Calls
 
@@ -389,6 +390,7 @@ data: [DONE]
 ## Claude 兼容接口
 
 除标准路径 `/anthropic/v1/*` 外，还支持快捷路径 `/v1/messages`、`/messages`、`/v1/messages/count_tokens`、`/messages/count_tokens`。
+实现上统一走 OpenAI Chat Completions 解析与回译链路，避免多套解析逻辑分叉维护。
 
 ### `GET /anthropic/v1/models`
 
@@ -523,6 +525,7 @@ data: {"type":"message_stop"}
 - `/v1/models/{model}:streamGenerateContent`（兼容路径）
 
 鉴权方式同业务接口（`Authorization: Bearer <token>` 或 `x-api-key`）。
+实现上统一走 OpenAI Chat Completions 解析与回译链路，避免多套解析逻辑分叉维护。
 
 ### `POST /v1beta/models/{model}:generateContent`
 
@@ -541,6 +544,7 @@ data: {"type":"message_stop"}
 - 常规文本：持续返回增量文本 chunk
 - `tools` 场景：会缓冲并在结束时输出 `functionCall` 结构
 - 结束 chunk：包含 `finishReason: "STOP"` 与 `usageMetadata`
+- token 计数优先透传上游 DeepSeek SSE（如 `accumulated_token_usage` / `token_usage`）；仅在上游缺失时回退本地估算
 
 ---
 

README.MD

@@ -344,7 +344,6 @@ cp opencode.json.example opencode.json
 | `DS2API_CONFIG_PATH` | 配置文件路径 | `config.json` |
 | `DS2API_CONFIG_JSON` | 直接注入配置（JSON 或 Base64） | — |
 | `DS2API_ENV_WRITEBACK` | 环境变量模式下自动写回配置文件并切换文件模式（`1/true/yes/on`） | 关闭 |
-| `DS2API_POW_CONCURRENCY` | PoW 并行计算协程数（可选） | 默认 CPU 核心数 |
 | `DS2API_STATIC_ADMIN_DIR` | 管理台静态文件目录 | `static/admin` |
 | `DS2API_AUTO_BUILD_WEBUI` | 启动时自动构建 WebUI | 本地开启，Vercel 关闭 |
 | `DS2API_DEV_PACKET_CAPTURE` | 本地开发抓包开关（记录最近会话请求/响应体） | 本地非 Vercel 默认开启 |

README.en.md

@@ -344,7 +344,6 @@ cp opencode.json.example opencode.json
 | `DS2API_CONFIG_PATH` | Config file path | `config.json` |
 | `DS2API_CONFIG_JSON` | Inline config (JSON or Base64) | — |
 | `DS2API_ENV_WRITEBACK` | Auto-write env-backed config to file and transition to file mode (`1/true/yes/on`) | Disabled |
-| `DS2API_POW_CONCURRENCY` | PoW parallel solver goroutine count (optional) | Default CPU core count |
 | `DS2API_STATIC_ADMIN_DIR` | Admin static assets dir | `static/admin` |
 | `DS2API_AUTO_BUILD_WEBUI` | Auto-build WebUI on startup | Enabled locally, disabled on Vercel |
 | `DS2API_ACCOUNT_MAX_INFLIGHT` | Max in-flight requests per account | `2` |

internal/adapter/openai/prompt_build_test.go

@@ -74,16 +74,13 @@ func TestBuildOpenAIFinalPrompt_VercelPreparePathKeepsFinalAnswerInstruction(t *
 	}
 
 	finalPrompt, _ := buildOpenAIFinalPrompt(messages, tools, "")
-	if !strings.Contains(finalPrompt, "After receiving a tool result, use it directly.") {
-		t.Fatalf("vercel prepare finalPrompt missing final-answer instruction: %q", finalPrompt)
-	}
-	if !strings.Contains(finalPrompt, "Only call another tool if the result is insufficient.") {
-		t.Fatalf("vercel prepare finalPrompt missing retry guard instruction: %q", finalPrompt)
+	if !strings.Contains(finalPrompt, "Remember: Output ONLY the <tool_calls>...</tool_calls> XML block when calling tools.") {
+		t.Fatalf("vercel prepare finalPrompt missing final tool-call anchor instruction: %q", finalPrompt)
 	}
 	if !strings.Contains(finalPrompt, "TOOL CALL FORMAT") {
 		t.Fatalf("vercel prepare finalPrompt missing xml format instruction: %q", finalPrompt)
 	}
-	if !strings.Contains(finalPrompt, "Do NOT wrap the XML in markdown code fences") {
+	if !strings.Contains(finalPrompt, "Do NOT wrap XML in markdown fences") {
 		t.Fatalf("vercel prepare finalPrompt missing no-fence xml instruction: %q", finalPrompt)
 	}
 	if strings.Contains(finalPrompt, "```json") {

internal/adapter/openai/responses_handler.go

@@ -130,12 +130,17 @@ func (h *Handler) handleResponsesNonStream(w http.ResponseWriter, resp *http.Res
 	}
 
 	responseObj := openaifmt.BuildResponseObject(responseID, model, finalPrompt, sanitizedThinking, sanitizedText, toolNames)
-	if result.OutputTokens > 0 {
+	if result.PromptTokens > 0 || result.OutputTokens > 0 {
 		if usage, ok := responseObj["usage"].(map[string]any); ok {
-			usage["output_tokens"] = result.OutputTokens
-			if input, ok := usage["input_tokens"].(int); ok {
-				usage["total_tokens"] = input + result.OutputTokens
+			if result.PromptTokens > 0 {
+				usage["input_tokens"] = result.PromptTokens
 			}
+			if result.OutputTokens > 0 {
+				usage["output_tokens"] = result.OutputTokens
+			}
+			input, _ := usage["input_tokens"].(int)
+			output, _ := usage["output_tokens"].(int)
+			usage["total_tokens"] = input + output
 		}
 	}
 	h.getResponseStore().put(owner, responseID, responseObj)

internal/adapter/openai/responses_stream_runtime_core.go

@@ -51,6 +51,7 @@ type responsesStreamRuntime struct {
 	messagePartAdded  bool
 	sequence          int
 	failed            bool
+	promptTokens      int
 	outputTokens      int
 
 	persistResponse func(obj map[string]any)
@@ -152,9 +153,19 @@ func (s *responsesStreamRuntime) finalize() {
 	if s.outputTokens > 0 {
 		if usage, ok := obj["usage"].(map[string]any); ok {
 			usage["output_tokens"] = s.outputTokens
-			if input, ok := usage["input_tokens"].(int); ok {
-				usage["total_tokens"] = input + s.outputTokens
+		}
+	}
+	if s.promptTokens > 0 || s.outputTokens > 0 {
+		if usage, ok := obj["usage"].(map[string]any); ok {
+			if s.promptTokens > 0 {
+				usage["input_tokens"] = s.promptTokens
 			}
+			if s.outputTokens > 0 {
+				usage["output_tokens"] = s.outputTokens
+			}
+			input, _ := usage["input_tokens"].(int)
+			output, _ := usage["output_tokens"].(int)
+			usage["total_tokens"] = input + output
 		}
 	}
 	if s.persistResponse != nil {
@@ -185,6 +196,9 @@ func (s *responsesStreamRuntime) onParsed(parsed sse.LineResult) streamengine.Pa
 	if !parsed.Parsed {
 		return streamengine.ParsedDecision{}
 	}
+	if parsed.PromptTokens > 0 {
+		s.promptTokens = parsed.PromptTokens
+	}
 	if parsed.OutputTokens > 0 {
 		s.outputTokens = parsed.OutputTokens
 	}

internal/adapter/openai/stream_status_test.go

@@ -238,3 +238,97 @@ func TestChatCompletionsStreamContentFilterStopsNormallyWithoutLeak(t *testing.T
 		t.Fatalf("expected finish_reason=stop for content-filter upstream stop, got %#v", choice["finish_reason"])
 	}
 }
+
+func TestResponsesStreamUsageOverridesFromBatchAccumulatedTokenUsage(t *testing.T) {
+	statuses := make([]int, 0, 1)
+	h := &Handler{
+		Store: mockOpenAIConfig{wideInput: true},
+		Auth:  streamStatusAuthStub{},
+		DS: streamStatusDSStub{resp: makeOpenAISSEHTTPResponse(
+			`data: {"p":"response/content","v":"hello"}`,
+			`data: {"p":"response","o":"BATCH","v":[{"p":"accumulated_token_usage","v":190},{"p":"quasi_status","v":"FINISHED"}]}`,
+		)},
+	}
+	r := chi.NewRouter()
+	r.Use(captureStatusMiddleware(&statuses))
+	RegisterRoutes(r, h)
+
+	reqBody := `{"model":"deepseek-chat","input":"hi","stream":true}`
+	req := httptest.NewRequest(http.MethodPost, "/v1/responses", strings.NewReader(reqBody))
+	req.Header.Set("Authorization", "Bearer direct-token")
+	req.Header.Set("Content-Type", "application/json")
+	rec := httptest.NewRecorder()
+	r.ServeHTTP(rec, req)
+
+	if rec.Code != http.StatusOK {
+		t.Fatalf("expected 200, got %d body=%s", rec.Code, rec.Body.String())
+	}
+	if len(statuses) != 1 || statuses[0] != http.StatusOK {
+		t.Fatalf("expected captured status 200, got %#v", statuses)
+	}
+	frames, done := parseSSEDataFrames(t, rec.Body.String())
+	if !done {
+		t.Fatalf("expected [DONE], body=%s", rec.Body.String())
+	}
+	if len(frames) == 0 {
+		t.Fatalf("expected at least one json frame, body=%s", rec.Body.String())
+	}
+	last := frames[len(frames)-1]
+	resp, _ := last["response"].(map[string]any)
+	if resp == nil {
+		t.Fatalf("expected response payload in final frame, got %#v", last)
+	}
+	usage, _ := resp["usage"].(map[string]any)
+	if usage == nil {
+		t.Fatalf("expected usage in response payload, got %#v", resp)
+	}
+	if got, _ := usage["output_tokens"].(float64); int(got) != 190 {
+		t.Fatalf("expected output_tokens=190, got %#v", usage["output_tokens"])
+	}
+}
+
+func TestResponsesNonStreamUsageOverridesPromptAndOutputTokenUsage(t *testing.T) {
+	statuses := make([]int, 0, 1)
+	h := &Handler{
+		Store: mockOpenAIConfig{wideInput: true},
+		Auth:  streamStatusAuthStub{},
+		DS: streamStatusDSStub{resp: makeOpenAISSEHTTPResponse(
+			`data: {"p":"response/content","v":"ok"}`,
+			`data: {"p":"response","o":"BATCH","v":[{"p":"token_usage","v":{"prompt_tokens":11,"completion_tokens":29}},{"p":"quasi_status","v":"FINISHED"}]}`,
+		)},
+	}
+	r := chi.NewRouter()
+	r.Use(captureStatusMiddleware(&statuses))
+	RegisterRoutes(r, h)
+
+	reqBody := `{"model":"deepseek-chat","input":"hi","stream":false}`
+	req := httptest.NewRequest(http.MethodPost, "/v1/responses", strings.NewReader(reqBody))
+	req.Header.Set("Authorization", "Bearer direct-token")
+	req.Header.Set("Content-Type", "application/json")
+	rec := httptest.NewRecorder()
+	r.ServeHTTP(rec, req)
+
+	if rec.Code != http.StatusOK {
+		t.Fatalf("expected 200, got %d body=%s", rec.Code, rec.Body.String())
+	}
+	if len(statuses) != 1 || statuses[0] != http.StatusOK {
+		t.Fatalf("expected captured status 200, got %#v", statuses)
+	}
+	var out map[string]any
+	if err := json.Unmarshal(rec.Body.Bytes(), &out); err != nil {
+		t.Fatalf("decode response failed: %v body=%s", err, rec.Body.String())
+	}
+	usage, _ := out["usage"].(map[string]any)
+	if usage == nil {
+		t.Fatalf("expected usage object, got %#v", out)
+	}
+	if got, _ := usage["input_tokens"].(float64); int(got) != 11 {
+		t.Fatalf("expected input_tokens=11, got %#v", usage["input_tokens"])
+	}
+	if got, _ := usage["output_tokens"].(float64); int(got) != 29 {
+		t.Fatalf("expected output_tokens=29, got %#v", usage["output_tokens"])
+	}
+	if got, _ := usage["total_tokens"].(float64); int(got) != 40 {
+		t.Fatalf("expected total_tokens=40, got %#v", usage["total_tokens"])
+	}
+}

internal/translatorcliproxy/bridge_test.go

@@ -26,6 +26,26 @@ func TestFromOpenAINonStreamClaude(t *testing.T) {
 	}
 }
 
+func TestFromOpenAINonStreamClaudePreservesUsageFromOpenAI(t *testing.T) {
+	original := []byte(`{"model":"claude-sonnet-4-5","messages":[{"role":"user","content":"hi"}],"stream":false}`)
+	translatedReq := []byte(`{"model":"claude-sonnet-4-5","messages":[{"role":"user","content":"hi"}],"stream":false}`)
+	openaibody := []byte(`{"id":"chatcmpl_1","object":"chat.completion","created":1,"model":"claude-sonnet-4-5","choices":[{"index":0,"message":{"role":"assistant","content":"hello"},"finish_reason":"stop"}],"usage":{"prompt_tokens":11,"completion_tokens":29,"total_tokens":40}}`)
+	got := string(FromOpenAINonStream(sdktranslator.FormatClaude, "claude-sonnet-4-5", original, translatedReq, openaibody))
+	if !strings.Contains(got, `"input_tokens":11`) || !strings.Contains(got, `"output_tokens":29`) {
+		t.Fatalf("expected claude usage to preserve prompt/completion tokens, got: %s", got)
+	}
+}
+
+func TestFromOpenAINonStreamGeminiPreservesUsageFromOpenAI(t *testing.T) {
+	original := []byte(`{"contents":[{"role":"user","parts":[{"text":"hi"}]}]}`)
+	translatedReq := []byte(`{"model":"gemini-2.5-pro","messages":[{"role":"user","content":"hi"}],"stream":false}`)
+	openaibody := []byte(`{"id":"chatcmpl_1","object":"chat.completion","created":1,"model":"gemini-2.5-pro","choices":[{"index":0,"message":{"role":"assistant","content":"hello"},"finish_reason":"stop"}],"usage":{"prompt_tokens":11,"completion_tokens":29,"total_tokens":40}}`)
+	got := string(FromOpenAINonStream(sdktranslator.FormatGemini, "gemini-2.5-pro", original, translatedReq, openaibody))
+	if !strings.Contains(got, `"promptTokenCount":11`) || !strings.Contains(got, `"candidatesTokenCount":29`) || !strings.Contains(got, `"totalTokenCount":40`) {
+		t.Fatalf("expected gemini usageMetadata to preserve prompt/completion tokens, got: %s", got)
+	}
+}
+
 func TestParseFormatAliases(t *testing.T) {
 	cases := map[string]sdktranslator.Format{
 		"responses":        sdktranslator.FormatOpenAIResponse,