Merge pull request #221 from CJackHwang/dev

Dev

.github/workflows/quality-gates.yml

@@ -28,6 +28,16 @@ jobs:
           cache: "npm"
           cache-dependency-path: webui/package-lock.json
 
+      - name: Setup golangci-lint
+        uses: golangci/golangci-lint-action@v8
+        with:
+          version: v2.11.4
+          install-mode: binary
+          verify: true
+
+      - name: Go Format & Lint Gates
+        run: ./scripts/lint.sh
+
       - name: Refactor Line Gate
         run: ./tests/scripts/check-refactor-line-gate.sh
 

.gitignore

@@ -59,3 +59,6 @@ Thumbs.db
 # Claude Code
 .claude/
 CLAUDE.local.md
+
+# Local tool bootstrap cache
+.tmp/

.golangci.yml

@@ -0,0 +1,73 @@
+version: "2"
+
+run:
+  tests: true
+
+linters:
+  default: standard
+  enable:
+    - errcheck
+    - govet
+    - ineffassign
+    - staticcheck
+    - unused
+  settings:
+    dupl:
+      threshold: 100
+    goconst:
+      min-len: 2
+      min-occurrences: 2
+    gocritic:
+      enabled-tags:
+        - diagnostic
+        - experimental
+        - opinionated
+        - performance
+        - style
+      disabled-checks:
+        - wrapperFunc
+        - rangeValCopy
+        - hugeParam
+    gocyclo:
+      min-complexity: 15
+    lll:
+      line-length: 140
+    misspell:
+      locale: US
+    nakedret:
+      max-func-lines: 30
+    prealloc:
+      simple: true
+      range-loops: true
+      for-loops: false
+  exclusions:
+    generated: lax
+    rules:
+      - path: (.+)\.go$
+        text: "ST1000: at least one file in a package should have a package comment"
+    paths:
+      - third_party$
+      - builtin$
+      - examples$
+      - vendor$
+      - webui/node_modules$
+
+issues:
+  max-issues-per-linter: 0
+  max-same-issues: 0
+
+formatters:
+  enable:
+    - gofmt
+  settings:
+    goimports:
+      local-prefixes:
+        - ds2api
+  exclusions:
+    generated: lax
+    paths:
+      - third_party$
+      - builtin$
+      - examples$
+      - vendor$
+      - webui/node_modules$

README.MD

@@ -81,7 +81,7 @@ flowchart LR
 - **统一路由内核**：所有协议入口统一汇聚到 `internal/server/router.go`，并在同一路由树中注册 OpenAI / Claude / Gemini / Admin / WebUI 路由，避免多入口行为漂移。
 - **统一执行链路**：Claude / Gemini 入口先经 `internal/translatorcliproxy` 做协议转换，再进入 `openai.ChatCompletions` 统一处理工具调用与流式语义，最后再转换回原协议响应。
 - **适配器分层更清晰**：`internal/adapter/{claude,gemini}` 负责入口/出口协议封装，`internal/adapter/openai` 负责核心执行，DeepSeek 侧调用只保留在 OpenAI 内核中。
-- **Tool Calling 双运行时对齐**：Go 侧（`internal/util`）与 Vercel Node 侧（`internal/js/helpers/stream-tool-sieve`）保持一致的解析/防泄漏语义，覆盖 JSON / XML / invoke / text-kv 多风格输入。
+- **Tool Calling 双运行时对齐**：Go 侧（`internal/toolcall`）与 Vercel Node 侧（`internal/js/helpers/stream-tool-sieve`）保持一致的解析/防泄漏语义，覆盖 JSON / XML / invoke / text-kv 多风格输入。
 - **配置与运行时设置解耦**：静态配置（`config`）与运行时策略（`settings`）通过 Admin API 分离管理，支持热更新和密码轮换失效旧 JWT。
 - **流式能力升级**：`/v1/responses` 与 `/v1/chat/completions` 共享更一致的工具调用增量输出策略，降低不同 SDK 下的行为差异。
 - **可观测与可运维增强**：`/healthz`、`/readyz`、`/admin/version`、`/admin/dev/captures` 形成排障闭环，便于发布后验证。
@@ -466,7 +466,8 @@ ds2api/
 │   ├── stream/              # 统一流式消费引擎
 │   ├── testsuite/           # 端到端测试框架与用例编排
 │   ├── translatorcliproxy/  # CLIProxy 桥接与流写入组件
-│   ├── util/                # 通用工具函数
+│   ├── toolcall/            # Tool Call 解析、修复与格式化（核心业务逻辑）
+│   ├── util/                # 通用工具函数（Token 估算、JSON 辅助等）
 │   ├── version/             # 版本解析 / 比较与 tag 规范化
 │   └── webui/               # WebUI 静态文件托管与自动构建
 ├── webui/                   # React WebUI 源码（Vite + Tailwind）
@@ -543,7 +544,7 @@ npm ci --prefix webui && npm run build --prefix webui
 go test ./...
 
 # 运行 tool calls 相关测试（调试工具调用问题）
-go test -v -run 'TestParseToolCalls|TestRepair' ./internal/util/
+go test -v -run 'TestParseToolCalls|TestRepair' ./internal/toolcall/
 
 # 运行端到端测试
 ./tests/scripts/run-live.sh

README.en.md

@@ -81,7 +81,7 @@ flowchart LR
 - **Unified routing core**: all protocol entries are now centralized through `internal/server/router.go`, with OpenAI / Claude / Gemini / Admin / WebUI routes registered in one tree to avoid multi-entry drift.
 - **Unified execution chain**: Claude/Gemini entries are translated by `internal/translatorcliproxy`, then executed through `openai.ChatCompletions` for shared tool-calling and stream semantics, then translated back to the client protocol.
 - **Cleaner adapter boundaries**: `internal/adapter/{claude,gemini}` handles protocol wrappers, while `internal/adapter/openai` remains the execution core; upstream DeepSeek calls are retained only in the OpenAI core.
-- **Tool-calling parity across runtimes**: Go (`internal/util`) and Vercel Node (`internal/js/helpers/stream-tool-sieve`) follow aligned parsing/anti-leak semantics across JSON / XML / invoke / text-kv inputs.
+- **Tool-calling parity across runtimes**: Go (`internal/toolcall`) and Vercel Node (`internal/js/helpers/stream-tool-sieve`) follow aligned parsing/anti-leak semantics across JSON / XML / invoke / text-kv inputs.
 - **Config/runtime separation**: static config (`config`) and runtime policy (`settings`) are managed independently via Admin APIs, enabling hot updates and password rotation with JWT invalidation.
 - **Streaming behavior upgrade**: `/v1/responses` and `/v1/chat/completions` now share a more consistent incremental tool-call emission strategy across SDK ecosystems.
 - **Improved operability**: `/healthz`, `/readyz`, `/admin/version`, and `/admin/dev/captures` form a tighter post-deploy diagnostics loop.
@@ -464,7 +464,8 @@ ds2api/
 │   ├── stream/              # Unified stream consumption engine
 │   ├── testsuite/           # End-to-end testsuite framework and case orchestration
 │   ├── translatorcliproxy/  # CLIProxy bridge and stream writer components
-│   ├── util/                # Common utilities
+│   ├── toolcall/            # Tool Call parsing, repair, and formatting (core business logic)
+│   ├── util/                # Common utilities (Token estimation, JSON helpers, etc.)
 │   ├── version/             # Version parsing/comparison and tag normalization
 │   └── webui/               # WebUI static file serving and auto-build
 ├── webui/                   # React WebUI source (Vite + Tailwind)

VERSION

@@ -1 +1 @@
-3.1.1
+3.1.2

cmd/ds2api-tests/main.go

@@ -30,8 +30,8 @@ func main() {
 	opts.Timeout = time.Duration(timeoutSeconds) * time.Second
 
 	if err := testsuite.Run(context.Background(), opts); err != nil {
-		fmt.Fprintln(os.Stderr, err.Error())
+		_, _ = fmt.Fprintln(os.Stderr, err.Error())
 		os.Exit(1)
 	}
-	fmt.Fprintln(os.Stdout, "testsuite completed successfully")
+	_, _ = fmt.Fprintln(os.Stdout, "testsuite completed successfully")
 }

docs/CONTRIBUTING.en.md

@@ -59,7 +59,7 @@ docker-compose -f docker-compose.dev.yml up
 
 | Language | Standards |
 | --- | --- |
-| **Go** | Run `gofmt` and ensure `go test ./...` passes before committing |
+| **Go** | Run `./scripts/lint.sh` (gofmt + golangci-lint) and ensure `go test ./...` passes before committing |
 | **JavaScript/React** | Follow existing project style (functional components) |
 | **Commit messages** | Use semantic prefixes: `feat:`, `fix:`, `docs:`, `refactor:`, `style:`, `perf:`, `chore:` |
 

docs/CONTRIBUTING.md

@@ -59,7 +59,7 @@ docker-compose -f docker-compose.dev.yml up
 
 | 语言 | 规范 |
 | --- | --- |
-| **Go** | 提交前运行 `gofmt`，确保 `go test ./...` 通过 |
+| **Go** | 提交前运行 `./scripts/lint.sh`（包含 gofmt+golangci-lint）并确保 `go test ./...` 通过 |
 | **JavaScript/React** | 保持现有代码风格（函数组件） |
 | **提交信息** | 使用语义化前缀：`feat:`、`fix:`、`docs:`、`refactor:`、`style:`、`perf:`、`chore:` |
 

docs/TESTING.md

@@ -180,10 +180,10 @@ go test ./...
 
 ```bash
 # 运行 tool calls 相关测试（推荐用于调试 tool call 解析问题）
-go test -v -run 'TestParseToolCalls|TestRepair' ./internal/util/
+go test -v -run 'TestParseToolCalls|TestRepair' ./internal/toolcall/
 
 # 运行单个测试用例
-go test -v -run TestParseToolCallsWithDeepSeekHallucination ./internal/util/
+go test -v -run TestParseToolCallsWithDeepSeekHallucination ./internal/toolcall/
 
 # 运行 format 相关测试
 go test -v ./internal/format/...
@@ -198,13 +198,13 @@ go test -v ./internal/adapter/openai/...
 
 ```bash
 # 1. 运行 tool calls 相关的所有测试
-go test -v -run 'TestParseToolCalls|TestRepair' ./internal/util/
+go test -v -run 'TestParseToolCalls|TestRepair' ./internal/toolcall/
 
 # 2. 查看测试输出中的详细调试信息
-go test -v -run TestParseToolCallsWithDeepSeekHallucination ./internal/util/ 2>&1
+go test -v -run TestParseToolCallsWithDeepSeekHallucination ./internal/toolcall/ 2>&1
 
 # 3. 检查具体测试用例的修复效果
-# 测试用例位于 internal/util/toolcalls_test.go，包含：
+# 测试用例位于 internal/toolcall/toolcalls_test.go，包含：
 # - TestParseToolCallsWithDeepSeekHallucination: DeepSeek 典型幻觉输出
 # - TestRepairLooseJSONWithNestedObjects: 嵌套对象的方括号修复
 # - TestParseToolCallsWithMixedWindowsPaths: Windows 路径处理

internal/adapter/claude/handler_messages.go

@@ -64,7 +64,7 @@ func (h *Handler) proxyViaOpenAI(w http.ResponseWriter, r *http.Request, store C
 		rec := httptest.NewRecorder()
 		h.OpenAI.ChatCompletions(rec, proxyReq)
 		res := rec.Result()
-		defer res.Body.Close()
+		defer func() { _ = res.Body.Close() }()
 		body, _ := io.ReadAll(res.Body)
 		for k, vv := range res.Header {
 			for _, v := range vv {
@@ -94,7 +94,7 @@ func (h *Handler) proxyViaOpenAI(w http.ResponseWriter, r *http.Request, store C
 	rec := httptest.NewRecorder()
 	h.OpenAI.ChatCompletions(rec, proxyReq)
 	res := rec.Result()
-	defer res.Body.Close()
+	defer func() { _ = res.Body.Close() }()
 	body, _ := io.ReadAll(res.Body)
 	if res.StatusCode < 200 || res.StatusCode >= 300 {
 		for k, vv := range res.Header {
@@ -124,7 +124,7 @@ func (h *Handler) proxyViaOpenAI(w http.ResponseWriter, r *http.Request, store C
 }
 
 func (h *Handler) handleClaudeStreamRealtime(w http.ResponseWriter, r *http.Request, resp *http.Response, model string, messages []any, thinkingEnabled, searchEnabled bool, toolNames []string) {
-	defer resp.Body.Close()
+	defer func() { _ = resp.Body.Close() }()
 	if resp.StatusCode != http.StatusOK {
 		body, _ := io.ReadAll(resp.Body)
 		writeClaudeError(w, http.StatusInternalServerError, string(body))

internal/adapter/claude/handler_utils.go

@@ -1,12 +1,12 @@
 package claude
 
 import (
+	"ds2api/internal/toolcall"
 	"encoding/json"
 	"fmt"
 	"strings"
 
 	"ds2api/internal/prompt"
-	"ds2api/internal/util"
 )
 
 func normalizeClaudeMessages(messages []any) []any {
@@ -98,9 +98,10 @@ func buildClaudeToolPrompt(tools []any) string {
 	}
 	return "You have access to these tools:\n\n" +
 		strings.Join(toolSchemas, "\n\n") + "\n\n" +
-		util.BuildToolCallInstructions(names)
+		toolcall.BuildToolCallInstructions(names)
 }
 
+//nolint:unused // retained for compatibility with pending Claude tool-result prompt flow.
 func formatClaudeToolResultForPrompt(block map[string]any) string {
 	if block == nil {
 		return ""

internal/adapter/claude/handler_utils_sanitize.go

@@ -96,6 +96,7 @@ func looksLikeBase64Payload(v string) bool {
 	return true
 }
 
+//nolint:unused // helper kept for compatibility with upcoming sanitize pipeline.
 func marshalCompactJSON(v any) string {
 	b, err := json.Marshal(v)
 	if err != nil {

internal/adapter/claude/standard_request.go

@@ -18,7 +18,7 @@ func normalizeClaudeRequest(store ConfigReader, req map[string]any) (claudeNorma
 	model, _ := req["model"].(string)
 	messagesRaw, _ := req["messages"].([]any)
 	if strings.TrimSpace(model) == "" || len(messagesRaw) == 0 {
-		return claudeNormalizedRequest{}, fmt.Errorf("Request must include 'model' and 'messages'.")
+		return claudeNormalizedRequest{}, fmt.Errorf("request must include 'model' and 'messages'")
 	}
 	if _, ok := req["max_tokens"]; !ok {
 		req["max_tokens"] = 8192

internal/adapter/claude/stream_runtime_finalize.go

@@ -1,6 +1,7 @@
 package claude
 
 import (
+	"ds2api/internal/toolcall"
 	"encoding/json"
 	"fmt"
 	"time"
@@ -46,9 +47,9 @@ func (s *claudeStreamRuntime) finalize(stopReason string) {
 	finalText := cleanVisibleOutput(s.text.String(), s.stripReferenceMarkers)
 
 	if s.bufferToolContent {
-		detected := util.ParseStandaloneToolCalls(finalText, s.toolNames)
+		detected := toolcall.ParseStandaloneToolCalls(finalText, s.toolNames)
 		if len(detected) == 0 && finalText == "" && finalThinking != "" {
-			detected = util.ParseStandaloneToolCalls(finalThinking, s.toolNames)
+			detected = toolcall.ParseStandaloneToolCalls(finalThinking, s.toolNames)
 		}
 		if len(detected) > 0 {
 			stopReason = "tool_use"

internal/adapter/gemini/convert_passthrough.go

@@ -5,6 +5,7 @@ import (
 	"strings"
 )
 
+//nolint:unused // compatibility hook for native Gemini request normalization path.
 func collectGeminiPassThrough(req map[string]any) map[string]any {
 	cfg, _ := req["generationConfig"].(map[string]any)
 	if len(cfg) == 0 {

internal/adapter/gemini/convert_request.go

@@ -9,6 +9,7 @@ import (
 	"ds2api/internal/util"
 )
 
+//nolint:unused // kept for native Gemini adapter route compatibility.
 func normalizeGeminiRequest(store ConfigReader, routeModel string, req map[string]any, stream bool) (util.StandardRequest, error) {
 	requestedModel := strings.TrimSpace(routeModel)
 	if requestedModel == "" {
@@ -17,13 +18,13 @@ func normalizeGeminiRequest(store ConfigReader, routeModel string, req map[strin
 
 	resolvedModel, ok := config.ResolveModel(store, requestedModel)
 	if !ok {
-		return util.StandardRequest{}, fmt.Errorf("Model '%s' is not available.", requestedModel)
+		return util.StandardRequest{}, fmt.Errorf("model %q is not available", requestedModel)
 	}
 	thinkingEnabled, searchEnabled, _ := config.GetModelConfig(resolvedModel)
 
 	messagesRaw := geminiMessagesFromRequest(req)
 	if len(messagesRaw) == 0 {
-		return util.StandardRequest{}, fmt.Errorf("Request must include non-empty contents.")
+		return util.StandardRequest{}, fmt.Errorf("request must include non-empty contents")
 	}
 
 	toolsRaw := convertGeminiTools(req["tools"])

internal/adapter/gemini/convert_tools.go

@@ -2,6 +2,7 @@ package gemini
 
 import "strings"
 
+//nolint:unused // kept for native Gemini adapter route compatibility.
 func convertGeminiTools(raw any) []any {
 	tools, _ := raw.([]any)
 	if len(tools) == 0 {

internal/adapter/gemini/handler_generate.go

@@ -2,6 +2,7 @@ package gemini
 
 import (
 	"bytes"
+	"ds2api/internal/toolcall"
 	"encoding/json"
 	"io"
 	"net/http"
@@ -57,7 +58,7 @@ func (h *Handler) proxyViaOpenAI(w http.ResponseWriter, r *http.Request, stream
 		rec := httptest.NewRecorder()
 		h.OpenAI.ChatCompletions(rec, proxyReq)
 		res := rec.Result()
-		defer res.Body.Close()
+		defer func() { _ = res.Body.Close() }()
 		body, _ := io.ReadAll(res.Body)
 		for k, vv := range res.Header {
 			for _, v := range vv {
@@ -87,7 +88,7 @@ func (h *Handler) proxyViaOpenAI(w http.ResponseWriter, r *http.Request, stream
 	rec := httptest.NewRecorder()
 	h.OpenAI.ChatCompletions(rec, proxyReq)
 	res := rec.Result()
-	defer res.Body.Close()
+	defer func() { _ = res.Body.Close() }()
 	body, _ := io.ReadAll(res.Body)
 	if res.StatusCode < 200 || res.StatusCode >= 300 {
 		for k, vv := range res.Header {
@@ -131,8 +132,9 @@ func writeGeminiErrorFromOpenAI(w http.ResponseWriter, status int, raw []byte) {
 	writeGeminiError(w, status, message)
 }
 
+//nolint:unused // retained for native Gemini non-stream handling path.
 func (h *Handler) handleNonStreamGenerateContent(w http.ResponseWriter, resp *http.Response, model, finalPrompt string, thinkingEnabled bool, toolNames []string) {
-	defer resp.Body.Close()
+	defer func() { _ = resp.Body.Close() }()
 	if resp.StatusCode != http.StatusOK {
 		body, _ := io.ReadAll(resp.Body)
 		writeGeminiError(w, resp.StatusCode, strings.TrimSpace(string(body)))
@@ -151,6 +153,7 @@ func (h *Handler) handleNonStreamGenerateContent(w http.ResponseWriter, resp *ht
 	))
 }
 
+//nolint:unused // retained for native Gemini non-stream handling path.
 func buildGeminiGenerateContentResponse(model, finalPrompt, finalThinking, finalText string, toolNames []string, outputTokens int) map[string]any {
 	parts := buildGeminiPartsFromFinal(finalText, finalThinking, toolNames)
 	usage := buildGeminiUsage(finalPrompt, finalThinking, finalText, outputTokens)
@@ -170,6 +173,7 @@ func buildGeminiGenerateContentResponse(model, finalPrompt, finalThinking, final
 	}
 }
 
+//nolint:unused // retained for native Gemini non-stream handling path.
 func buildGeminiUsage(finalPrompt, finalThinking, finalText string, outputTokens int) map[string]any {
 	promptTokens := util.EstimateTokens(finalPrompt)
 	reasoningTokens := util.EstimateTokens(finalThinking)
@@ -185,10 +189,11 @@ func buildGeminiUsage(finalPrompt, finalThinking, finalText string, outputTokens
 	}
 }
 
+//nolint:unused // retained for native Gemini non-stream handling path.
 func buildGeminiPartsFromFinal(finalText, finalThinking string, toolNames []string) []map[string]any {
-	detected := util.ParseToolCalls(finalText, toolNames)
+	detected := toolcall.ParseToolCalls(finalText, toolNames)
 	if len(detected) == 0 && finalThinking != "" {
-		detected = util.ParseToolCalls(finalThinking, toolNames)
+		detected = toolcall.ParseToolCalls(finalThinking, toolNames)
 	}
 	if len(detected) > 0 {
 		parts := make([]map[string]any, 0, len(detected))

internal/adapter/gemini/handler_routes.go

@@ -17,6 +17,7 @@ type Handler struct {
 	OpenAI OpenAIChatRunner
 }
 
+//nolint:unused // used by native Gemini stream/non-stream runtime helpers.
 func (h *Handler) compatStripReferenceMarkers() bool {
 	if h == nil || h.Store == nil {
 		return true

internal/adapter/gemini/handler_stream_runtime.go

@@ -12,8 +12,9 @@ import (
 	streamengine "ds2api/internal/stream"
 )
 
+//nolint:unused // retained for native Gemini stream handling path.
 func (h *Handler) handleStreamGenerateContent(w http.ResponseWriter, r *http.Request, resp *http.Response, model, finalPrompt string, thinkingEnabled, searchEnabled bool, toolNames []string) {
-	defer resp.Body.Close()
+	defer func() { _ = resp.Body.Close() }()
 	if resp.StatusCode != http.StatusOK {
 		body, _ := io.ReadAll(resp.Body)
 		writeGeminiError(w, resp.StatusCode, strings.TrimSpace(string(body)))
@@ -49,6 +50,7 @@ func (h *Handler) handleStreamGenerateContent(w http.ResponseWriter, r *http.Req
 	})
 }
 
+//nolint:unused // retained for native Gemini stream handling path.
 type geminiStreamRuntime struct {
 	w        http.ResponseWriter
 	rc       *http.ResponseController
@@ -68,6 +70,7 @@ type geminiStreamRuntime struct {
 	outputTokens int
 }
 
+//nolint:unused // retained for native Gemini stream handling path.
 func newGeminiStreamRuntime(
 	w http.ResponseWriter,
 	rc *http.ResponseController,
@@ -93,6 +96,7 @@ func newGeminiStreamRuntime(
 	}
 }
 
+//nolint:unused // retained for native Gemini stream handling path.
 func (s *geminiStreamRuntime) sendChunk(payload map[string]any) {
 	b, _ := json.Marshal(payload)
 	_, _ = s.w.Write([]byte("data: "))
@@ -103,6 +107,7 @@ func (s *geminiStreamRuntime) sendChunk(payload map[string]any) {
 	}
 }
 
+//nolint:unused // retained for native Gemini stream handling path.
 func (s *geminiStreamRuntime) onParsed(parsed sse.LineResult) streamengine.ParsedDecision {
 	if !parsed.Parsed {
 		return streamengine.ParsedDecision{}
@@ -158,6 +163,7 @@ func (s *geminiStreamRuntime) onParsed(parsed sse.LineResult) streamengine.Parse
 	return streamengine.ParsedDecision{ContentSeen: contentSeen}
 }
 
+//nolint:unused // retained for native Gemini stream handling path.
 func (s *geminiStreamRuntime) finalize() {
 	finalThinking := s.thinking.String()
 	finalText := cleanVisibleOutput(s.text.String(), s.stripReferenceMarkers)

internal/adapter/gemini/handler_test.go

@@ -42,19 +42,23 @@ func (m testGeminiAuth) Determine(_ *http.Request) (*auth.RequestAuth, error) {
 
 func (testGeminiAuth) Release(_ *auth.RequestAuth) {}
 
+//nolint:unused // reserved test double for native Gemini DS-call path coverage.
 type testGeminiDS struct {
 	resp *http.Response
 	err  error
 }
 
+//nolint:unused // reserved test double for native Gemini DS-call path coverage.
 func (m testGeminiDS) CreateSession(_ context.Context, _ *auth.RequestAuth, _ int) (string, error) {
 	return "session-id", nil
 }
 
+//nolint:unused // reserved test double for native Gemini DS-call path coverage.
 func (m testGeminiDS) GetPow(_ context.Context, _ *auth.RequestAuth, _ int) (string, error) {
 	return "pow", nil
 }
 
+//nolint:unused // reserved test double for native Gemini DS-call path coverage.
 func (m testGeminiDS) CallCompletion(_ context.Context, _ *auth.RequestAuth, _ map[string]any, _ string, _ int) (*http.Response, error) {
 	if m.err != nil {
 		return nil, m.err
@@ -100,6 +104,7 @@ func (s geminiOpenAISuccessStub) ChatCompletions(w http.ResponseWriter, _ *http.
 	_, _ = w.Write([]byte(out))
 }
 
+//nolint:unused // helper retained for native Gemini stream fixture tests.
 func makeGeminiUpstreamResponse(lines ...string) *http.Response {
 	body := strings.Join(lines, "\n")
 	if !strings.HasSuffix(body, "\n") {

internal/adapter/gemini/output_clean.go

@@ -2,6 +2,7 @@ package gemini
 
 import textclean "ds2api/internal/textclean"
 
+//nolint:unused // retained for native Gemini output post-processing path.
 func cleanVisibleOutput(text string, stripReferenceMarkers bool) string {
 	if text == "" {
 		return text

internal/adapter/openai/chat_stream_runtime.go

@@ -1,6 +1,7 @@
 package openai
 
 import (
+	"ds2api/internal/toolcall"
 	"encoding/json"
 	"net/http"
 	"strings"
@@ -8,7 +9,6 @@ import (
 	openaifmt "ds2api/internal/format/openai"
 	"ds2api/internal/sse"
 	streamengine "ds2api/internal/stream"
-	"ds2api/internal/util"
 )
 
 type chatStreamRuntime struct {
@@ -102,7 +102,7 @@ func (s *chatStreamRuntime) sendDone() {
 func (s *chatStreamRuntime) finalize(finishReason string) {
 	finalThinking := s.thinking.String()
 	finalText := cleanVisibleOutput(s.text.String(), s.stripReferenceMarkers)
-	detected := util.ParseStandaloneToolCallsDetailed(finalText, s.toolNames)
+	detected := toolcall.ParseStandaloneToolCallsDetailed(finalText, s.toolNames)
 	if len(detected.Calls) > 0 && !s.toolCallsDoneEmitted {
 		finishReason = "tool_calls"
 		delta := map[string]any{

internal/adapter/openai/handler_chat.go

@@ -116,7 +116,7 @@ func (h *Handler) autoDeleteRemoteSession(ctx context.Context, a *auth.RequestAu
 
 func (h *Handler) handleNonStream(w http.ResponseWriter, ctx context.Context, resp *http.Response, completionID, model, finalPrompt string, thinkingEnabled bool, toolNames []string) {
 	if resp.StatusCode != http.StatusOK {
-		defer resp.Body.Close()
+		defer func() { _ = resp.Body.Close() }()
 		body, _ := io.ReadAll(resp.Body)
 		writeOpenAIError(w, resp.StatusCode, string(body))
 		return
@@ -143,7 +143,7 @@ func (h *Handler) handleNonStream(w http.ResponseWriter, ctx context.Context, re
 }
 
 func (h *Handler) handleStream(w http.ResponseWriter, r *http.Request, resp *http.Response, completionID, model, finalPrompt string, thinkingEnabled, searchEnabled bool, toolNames []string) {
-	defer resp.Body.Close()
+	defer func() { _ = resp.Body.Close() }()
 	if resp.StatusCode != http.StatusOK {
 		body, _ := io.ReadAll(resp.Body)
 		writeOpenAIError(w, resp.StatusCode, string(body))

internal/adapter/openai/handler_chat_auto_delete_test.go

@@ -107,7 +107,7 @@ type autoDeleteCtxDSStub struct {
 }
 
 func (m *autoDeleteCtxDSStub) DeleteSessionForToken(ctx context.Context, token string, sessionID string) (*deepseek.DeleteSessionResult, error) {
-	return m.autoDeleteModeDSStub.DeleteSessionForTokenCtx(ctx, token, sessionID)
+	return m.DeleteSessionForTokenCtx(ctx, token, sessionID)
 }
 
 func (m *autoDeleteCtxDSStub) DeleteAllSessionsForToken(_ context.Context, _ string) error {

internal/adapter/openai/handler_toolcall_format.go

@@ -1,6 +1,7 @@
 package openai
 
 import (
+	"ds2api/internal/toolcall"
 	"encoding/json"
 	"fmt"
 	"strings"
@@ -75,7 +76,7 @@ func injectToolPrompt(messages []map[string]any, tools []any, policy util.ToolCh
 
 // buildToolCallInstructions delegates to the shared util implementation.
 func buildToolCallInstructions(toolNames []string) string {
-	return util.BuildToolCallInstructions(toolNames)
+	return toolcall.BuildToolCallInstructions(toolNames)
 }
 
 func formatIncrementalStreamToolCallDeltas(deltas []toolCallDelta, ids map[int]string) []map[string]any {
@@ -138,7 +139,7 @@ func filterIncrementalToolCallDeltasByAllowed(deltas []toolCallDelta, allowedNam
 	return out
 }
 
-func formatFinalStreamToolCallsWithStableIDs(calls []util.ParsedToolCall, ids map[int]string) []map[string]any {
+func formatFinalStreamToolCallsWithStableIDs(calls []toolcall.ParsedToolCall, ids map[int]string) []map[string]any {
 	if len(calls) == 0 {
 		return nil
 	}

internal/adapter/openai/responses_handler.go

@@ -1,6 +1,7 @@
 package openai
 
 import (
+	"ds2api/internal/toolcall"
 	"encoding/json"
 	"io"
 	"net/http"
@@ -106,7 +107,7 @@ func (h *Handler) Responses(w http.ResponseWriter, r *http.Request) {
 }
 
 func (h *Handler) handleResponsesNonStream(w http.ResponseWriter, resp *http.Response, owner, responseID, model, finalPrompt string, thinkingEnabled bool, toolNames []string, toolChoice util.ToolChoicePolicy, traceID string) {
-	defer resp.Body.Close()
+	defer func() { _ = resp.Body.Close() }()
 	if resp.StatusCode != http.StatusOK {
 		body, _ := io.ReadAll(resp.Body)
 		writeOpenAIError(w, resp.StatusCode, strings.TrimSpace(string(body)))
@@ -119,7 +120,7 @@ func (h *Handler) handleResponsesNonStream(w http.ResponseWriter, resp *http.Res
 	if writeUpstreamEmptyOutputError(w, sanitizedThinking, sanitizedText, result.ContentFilter) {
 		return
 	}
-	textParsed := util.ParseStandaloneToolCallsDetailed(sanitizedText, toolNames)
+	textParsed := toolcall.ParseStandaloneToolCallsDetailed(sanitizedText, toolNames)
 	logResponsesToolPolicyRejection(traceID, toolChoice, textParsed, "text")
 
 	callCount := len(textParsed.Calls)
@@ -142,7 +143,7 @@ func (h *Handler) handleResponsesNonStream(w http.ResponseWriter, resp *http.Res
 }
 
 func (h *Handler) handleResponsesStream(w http.ResponseWriter, r *http.Request, resp *http.Response, owner, responseID, model, finalPrompt string, thinkingEnabled, searchEnabled bool, toolNames []string, toolChoice util.ToolChoicePolicy, traceID string) {
-	defer resp.Body.Close()
+	defer func() { _ = resp.Body.Close() }()
 	if resp.StatusCode != http.StatusOK {
 		body, _ := io.ReadAll(resp.Body)
 		writeOpenAIError(w, resp.StatusCode, strings.TrimSpace(string(body)))
@@ -200,7 +201,7 @@ func (h *Handler) handleResponsesStream(w http.ResponseWriter, r *http.Request,
 	})
 }
 
-func logResponsesToolPolicyRejection(traceID string, policy util.ToolChoicePolicy, parsed util.ToolCallParseResult, channel string) {
+func logResponsesToolPolicyRejection(traceID string, policy util.ToolChoicePolicy, parsed toolcall.ToolCallParseResult, channel string) {
 	rejected := filteredRejectedToolNamesForLog(parsed.RejectedToolNames)
 	if !parsed.RejectedByPolicy || len(rejected) == 0 {
 		return

internal/adapter/openai/responses_stream_runtime_core.go

@@ -1,6 +1,7 @@
 package openai
 
 import (
+	"ds2api/internal/toolcall"
 	"net/http"
 	"strings"
 
@@ -107,7 +108,7 @@ func (s *responsesStreamRuntime) finalize() {
 		s.processToolStreamEvents(flushToolSieve(&s.sieve, s.toolNames), true)
 	}
 
-	textParsed := util.ParseStandaloneToolCallsDetailed(finalText, s.toolNames)
+	textParsed := toolcall.ParseStandaloneToolCallsDetailed(finalText, s.toolNames)
 	detected := textParsed.Calls
 	s.logToolPolicyRejections(textParsed)
 
@@ -163,8 +164,8 @@ func (s *responsesStreamRuntime) finalize() {
 	s.sendDone()
 }
 
-func (s *responsesStreamRuntime) logToolPolicyRejections(textParsed util.ToolCallParseResult) {
-	logRejected := func(parsed util.ToolCallParseResult, channel string) {
+func (s *responsesStreamRuntime) logToolPolicyRejections(textParsed toolcall.ToolCallParseResult) {
+	logRejected := func(parsed toolcall.ToolCallParseResult, channel string) {
 		rejected := filteredRejectedToolNamesForLog(parsed.RejectedToolNames)
 		if !parsed.RejectedByPolicy || len(rejected) == 0 {
 			return

internal/adapter/openai/responses_stream_runtime_toolcalls.go

@@ -1,11 +1,11 @@
 package openai
 
 import (
+	"ds2api/internal/toolcall"
 	"encoding/json"
 	"strings"
 
 	openaifmt "ds2api/internal/format/openai"
-	"ds2api/internal/util"
 
 	"github.com/google/uuid"
 )
@@ -208,7 +208,7 @@ func (s *responsesStreamRuntime) emitFunctionCallDeltaEvents(deltas []toolCallDe
 	}
 }
 
-func (s *responsesStreamRuntime) emitFunctionCallDoneEvents(calls []util.ParsedToolCall) {
+func (s *responsesStreamRuntime) emitFunctionCallDoneEvents(calls []toolcall.ParsedToolCall) {
 	for idx, tc := range calls {
 		if strings.TrimSpace(tc.Name) == "" {
 			continue

internal/adapter/openai/responses_stream_runtime_toolcalls_finalize.go

@@ -1,12 +1,12 @@
 package openai
 
 import (
+	"ds2api/internal/toolcall"
 	"encoding/json"
 	"sort"
 	"strings"
 
 	openaifmt "ds2api/internal/format/openai"
-	"ds2api/internal/util"
 )
 
 func (s *responsesStreamRuntime) closeIncompleteFunctionItems() {
@@ -57,7 +57,7 @@ func (s *responsesStreamRuntime) closeIncompleteFunctionItems() {
 	}
 }
 
-func (s *responsesStreamRuntime) buildCompletedResponseObject(finalThinking, finalText string, calls []util.ParsedToolCall) map[string]any {
+func (s *responsesStreamRuntime) buildCompletedResponseObject(finalThinking, finalText string, calls []toolcall.ParsedToolCall) map[string]any {
 	type indexedItem struct {
 		index int
 		item  map[string]any

internal/adapter/openai/standard_request.go

@@ -12,11 +12,11 @@ func normalizeOpenAIChatRequest(store ConfigReader, req map[string]any, traceID
 	model, _ := req["model"].(string)
 	messagesRaw, _ := req["messages"].([]any)
 	if strings.TrimSpace(model) == "" || len(messagesRaw) == 0 {
-		return util.StandardRequest{}, fmt.Errorf("Request must include 'model' and 'messages'.")
+		return util.StandardRequest{}, fmt.Errorf("request must include 'model' and 'messages'")
 	}
 	resolvedModel, ok := config.ResolveModel(store, model)
 	if !ok {
-		return util.StandardRequest{}, fmt.Errorf("Model '%s' is not available.", model)
+		return util.StandardRequest{}, fmt.Errorf("model %q is not available", model)
 	}
 	thinkingEnabled, searchEnabled, _ := config.GetModelConfig(resolvedModel)
 	responseModel := strings.TrimSpace(model)
@@ -48,11 +48,11 @@ func normalizeOpenAIResponsesRequest(store ConfigReader, req map[string]any, tra
 	model, _ := req["model"].(string)
 	model = strings.TrimSpace(model)
 	if model == "" {
-		return util.StandardRequest{}, fmt.Errorf("Request must include 'model'.")
+		return util.StandardRequest{}, fmt.Errorf("request must include 'model'")
 	}
 	resolvedModel, ok := config.ResolveModel(store, model)
 	if !ok {
-		return util.StandardRequest{}, fmt.Errorf("Model '%s' is not available.", model)
+		return util.StandardRequest{}, fmt.Errorf("model %q is not available", model)
 	}
 	thinkingEnabled, searchEnabled, _ := config.GetModelConfig(resolvedModel)
 
@@ -68,7 +68,7 @@ func normalizeOpenAIResponsesRequest(store ConfigReader, req map[string]any, tra
 		messagesRaw = msgs
 	}
 	if len(messagesRaw) == 0 {
-		return util.StandardRequest{}, fmt.Errorf("Request must include 'input' or 'messages'.")
+		return util.StandardRequest{}, fmt.Errorf("request must include 'input' or 'messages'")
 	}
 	toolPolicy, err := parseToolChoicePolicy(req["tool_choice"], req["tools"])
 	if err != nil {
@@ -152,7 +152,7 @@ func parseToolChoicePolicy(toolChoiceRaw any, toolsRaw any) (util.ToolChoicePoli
 		case "required":
 			policy.Mode = util.ToolChoiceRequired
 		default:
-			return util.ToolChoicePolicy{}, fmt.Errorf("Unsupported tool_choice: %q", v)
+			return util.ToolChoicePolicy{}, fmt.Errorf("unsupported tool_choice: %q", v)
 		}
 	case map[string]any:
 		allowedOverride, hasAllowedOverride, err := parseAllowedToolNames(v["allowed_tools"])
@@ -198,7 +198,7 @@ func parseToolChoicePolicy(toolChoiceRaw any, toolsRaw any) (util.ToolChoicePoli
 			policy.ForcedName = name
 			policy.Allowed = namesToSet([]string{name})
 		default:
-			return util.ToolChoicePolicy{}, fmt.Errorf("Unsupported tool_choice.type: %q", typ)
+			return util.ToolChoicePolicy{}, fmt.Errorf("unsupported tool_choice.type: %q", typ)
 		}
 	default:
 		return util.ToolChoicePolicy{}, fmt.Errorf("tool_choice must be a string or object")
@@ -206,7 +206,7 @@ func parseToolChoicePolicy(toolChoiceRaw any, toolsRaw any) (util.ToolChoicePoli
 
 	if policy.Mode == util.ToolChoiceRequired || policy.Mode == util.ToolChoiceForced {
 		if len(declaredNames) == 0 {
-			return util.ToolChoicePolicy{}, fmt.Errorf("tool_choice=%s requires non-empty tools.", policy.Mode)
+			return util.ToolChoicePolicy{}, fmt.Errorf("tool_choice=%s requires non-empty tools", policy.Mode)
 		}
 	}
 	if policy.Mode == util.ToolChoiceForced {

internal/adapter/openai/tool_sieve_core.go

@@ -3,7 +3,7 @@ package openai
 import (
 	"strings"
 
-	"ds2api/internal/util"
+	"ds2api/internal/toolcall"
 )
 
 func processToolSieveChunk(state *toolStreamSieveState, chunk string, toolNames []string) []toolStreamEvent {
@@ -226,7 +226,7 @@ func findToolSegmentStart(s string) int {
 	return start
 }
 
-func consumeToolCapture(state *toolStreamSieveState, toolNames []string) (prefix string, calls []util.ParsedToolCall, suffix string, ready bool) {
+func consumeToolCapture(state *toolStreamSieveState, toolNames []string) (prefix string, calls []toolcall.ParsedToolCall, suffix string, ready bool) {
 	captured := state.capture.String()
 	if captured == "" {
 		return "", nil, "", false
@@ -267,7 +267,7 @@ func consumeToolCapture(state *toolStreamSieveState, toolNames []string) (prefix
 	}
 	prefixPart := captured[:start]
 	suffixPart := captured[end:]
-	parsed := util.ParseStandaloneToolCallsDetailed(obj, toolNames)
+	parsed := toolcall.ParseStandaloneToolCallsDetailed(obj, toolNames)
 	if len(parsed.Calls) == 0 {
 		if parsed.SawToolCallSyntax && parsed.RejectedByPolicy {
 			// Parsed as tool-call payload but rejected by schema/policy:

internal/adapter/openai/tool_sieve_state.go

@@ -1,9 +1,8 @@
 package openai
 
 import (
+	"ds2api/internal/toolcall"
 	"strings"
-
-	"ds2api/internal/util"
 )
 
 type toolStreamSieveState struct {
@@ -12,7 +11,7 @@ type toolStreamSieveState struct {
 	capturing        bool
 	recentTextTail   string
 	pendingToolRaw   string
-	pendingToolCalls []util.ParsedToolCall
+	pendingToolCalls []toolcall.ParsedToolCall
 	disableDeltas    bool
 	toolNameSent     bool
 	toolName         string
@@ -24,7 +23,7 @@ type toolStreamSieveState struct {
 
 type toolStreamEvent struct {
 	Content        string
-	ToolCalls      []util.ParsedToolCall
+	ToolCalls      []toolcall.ParsedToolCall
 	ToolCallDeltas []toolCallDelta
 }
 

internal/adapter/openai/tool_sieve_xml.go

@@ -1,14 +1,14 @@
 package openai
 
 import (
+	"ds2api/internal/toolcall"
 	"regexp"
 	"strings"
-
-	"ds2api/internal/util"
 )
 
 // --- XML tool call support for the streaming sieve ---
 
+//nolint:unused // kept as explicit tag inventory for future XML sieve refinements.
 var xmlToolCallClosingTags = []string{"</tool_calls>", "</tool_call>", "</invoke>", "</function_call>", "</function_calls>", "</tool_use>",
 	// Agent-style XML tags (Roo Code, Cline, etc.)
 	"</attempt_completion>", "</ask_followup_question>", "</new_task>", "</result>"}
@@ -34,6 +34,8 @@ var xmlToolCallTagPairs = []struct{ open, close string }{
 }
 
 // xmlToolCallBlockPattern matches a complete XML tool call block (wrapper or standalone).
+//
+//nolint:unused // reserved for future fast-path XML block detection.
 var xmlToolCallBlockPattern = regexp.MustCompile(`(?is)(<tool_calls>\s*(?:.*?)\s*</tool_calls>|<tool_call>\s*(?:.*?)\s*</tool_call>|<invoke\b[^>]*>(?:.*?)</invoke>|<function_calls?\b[^>]*>(?:.*?)</function_calls?>|<tool_use>(?:.*?)</tool_use>|<attempt_completion>(?:.*?)</attempt_completion>|<ask_followup_question>(?:.*?)</ask_followup_question>|<new_task>(?:.*?)</new_task>)`)
 
 // xmlToolTagsToDetect is the set of XML tag prefixes used by findToolSegmentStart.
@@ -43,7 +45,7 @@ var xmlToolTagsToDetect = []string{"<tool_calls>", "<tool_calls\n", "<tool_call>
 	"<attempt_completion>", "<ask_followup_question>", "<new_task>"}
 
 // consumeXMLToolCapture tries to extract complete XML tool call blocks from captured text.
-func consumeXMLToolCapture(captured string, toolNames []string) (prefix string, calls []util.ParsedToolCall, suffix string, ready bool) {
+func consumeXMLToolCapture(captured string, toolNames []string) (prefix string, calls []toolcall.ParsedToolCall, suffix string, ready bool) {
 	lower := strings.ToLower(captured)
 	// Find the FIRST matching open/close pair, preferring wrapper tags.
 	// Tag pairs are ordered longest-first (e.g. <tool_calls before <tool_call)
@@ -66,7 +68,7 @@ func consumeXMLToolCapture(captured string, toolNames []string) (prefix string,
 		xmlBlock := captured[openIdx:closeEnd]
 		prefixPart := captured[:openIdx]
 		suffixPart := captured[closeEnd:]
-		parsed := util.ParseToolCalls(xmlBlock, toolNames)
+		parsed := toolcall.ParseToolCalls(xmlBlock, toolNames)
 		if len(parsed) > 0 {
 			prefixPart, suffixPart = trimWrappingJSONFence(prefixPart, suffixPart)
 			return prefixPart, parsed, suffixPart, true

internal/admin/handler_accounts_testing.go

@@ -165,7 +165,7 @@ func (h *Handler) testAccount(ctx context.Context, acc config.Account, model, me
 		return result
 	}
 	if resp.StatusCode != http.StatusOK {
-		defer resp.Body.Close()
+		defer func() { _ = resp.Body.Close() }()
 		result["message"] = fmt.Sprintf("请求失败: HTTP %d", resp.StatusCode)
 		return result
 	}
@@ -218,7 +218,7 @@ func (h *Handler) testAPI(w http.ResponseWriter, r *http.Request) {
 		writeJSON(w, http.StatusOK, map[string]any{"success": false, "error": err.Error()})
 		return
 	}
-	defer resp.Body.Close()
+	defer func() { _ = resp.Body.Close() }()
 	body, _ := io.ReadAll(resp.Body)
 	if resp.StatusCode == http.StatusOK {
 		var parsed any

internal/admin/handler_config_write.go

@@ -85,7 +85,7 @@ func (h *Handler) addKey(w http.ResponseWriter, r *http.Request) {
 	err := h.Store.Update(func(c *config.Config) error {
 		for _, k := range c.Keys {
 			if k == key {
-				return fmt.Errorf("Key 已存在")
+				return fmt.Errorf("key 已存在")
 			}
 		}
 		c.Keys = append(c.Keys, key)
@@ -109,7 +109,7 @@ func (h *Handler) deleteKey(w http.ResponseWriter, r *http.Request) {
 			}
 		}
 		if idx < 0 {
-			return fmt.Errorf("Key 不存在")
+			return fmt.Errorf("key 不存在")
 		}
 		c.Keys = append(c.Keys[:idx], c.Keys[idx+1:]...)
 		return nil

internal/admin/handler_raw_samples_test.go

@@ -288,17 +288,17 @@ func TestQueryRawSampleCapturesGroupsBySessionAndMatchesQuestion(t *testing.T) {
 func TestBuildCaptureChainsPreservesCaptureOrderWhenTimestampsCollide(t *testing.T) {
 	snapshot := []devcapture.Entry{
 		{
-			ID:          "cap_continue",
-			CreatedAt:   1712365200,
-			Label:       "deepseek_continue",
-			RequestBody: `{"chat_session_id":"session-collision","message_id":2}`,
+			ID:           "cap_continue",
+			CreatedAt:    1712365200,
+			Label:        "deepseek_continue",
+			RequestBody:  `{"chat_session_id":"session-collision","message_id":2}`,
 			ResponseBody: "data: {\"v\":\"第二段\"}\n\n",
 		},
 		{
-			ID:          "cap_completion",
-			CreatedAt:   1712365200,
-			Label:       "deepseek_completion",
-			RequestBody: `{"chat_session_id":"session-collision","prompt":"题目"}`,
+			ID:           "cap_completion",
+			CreatedAt:    1712365200,
+			Label:        "deepseek_completion",
+			RequestBody:  `{"chat_session_id":"session-collision","prompt":"题目"}`,
 			ResponseBody: "data: {\"v\":\"第一段\"}\n\n",
 		},
 	}

internal/admin/handler_vercel.go

@@ -301,7 +301,7 @@ func vercelRequest(ctx context.Context, client *http.Client, method, endpoint st
 	if err != nil {
 		return nil, 0, err
 	}
-	defer resp.Body.Close()
+	defer func() { _ = resp.Body.Close() }()
 	b, _ := io.ReadAll(resp.Body)
 	parsed := map[string]any{}
 	_ = json.Unmarshal(b, &parsed)

internal/admin/handler_version.go

@@ -43,7 +43,7 @@ func (h *Handler) getVersion(w http.ResponseWriter, _ *http.Request) {
 		writeJSON(w, http.StatusOK, resp)
 		return
 	}
-	defer r.Body.Close()
+	defer func() { _ = r.Body.Close() }()
 	if r.StatusCode < 200 || r.StatusCode >= 300 {
 		resp["check_error"] = "github api status: " + r.Status
 		writeJSON(w, http.StatusOK, resp)

internal/auth/auth_edge_test.go

@@ -130,9 +130,7 @@ func TestMarkTokenInvalidNotConfigToken(t *testing.T) {
 	a := &RequestAuth{UseConfigToken: false, DeepSeekToken: "direct", resolver: r}
 	r.MarkTokenInvalid(a)
 	// Should not panic, token should be unchanged for non-config
-	if a.DeepSeekToken != "" {
-		// Actually it does clear it; that's fine - let's check behavior
-	}
+	_ = a.DeepSeekToken // Actual behavior may clear it; this test only asserts no panic.
 }
 
 func TestMarkTokenInvalidEmptyAccountID(t *testing.T) {

internal/compat/go_compat_test.go

@@ -1,6 +1,7 @@
 package compat
 
 import (
+	"ds2api/internal/toolcall"
 	"encoding/json"
 	"os"
 	"path/filepath"
@@ -86,22 +87,22 @@ func TestGoCompatToolcallFixtures(t *testing.T) {
 		mustLoadJSON(t, fixturePath, &fixture)
 
 		var expected struct {
-			Calls             []util.ParsedToolCall `json:"calls"`
-			SawToolCallSyntax bool                  `json:"sawToolCallSyntax"`
-			RejectedByPolicy  bool                  `json:"rejectedByPolicy"`
-			RejectedToolNames []string              `json:"rejectedToolNames"`
+			Calls             []toolcall.ParsedToolCall `json:"calls"`
+			SawToolCallSyntax bool                      `json:"sawToolCallSyntax"`
+			RejectedByPolicy  bool                      `json:"rejectedByPolicy"`
+			RejectedToolNames []string                  `json:"rejectedToolNames"`
 		}
 		mustLoadJSON(t, expectedPath, &expected)
 
-		var got util.ToolCallParseResult
+		var got toolcall.ToolCallParseResult
 		switch strings.ToLower(strings.TrimSpace(fixture.Mode)) {
 		case "standalone":
-			got = util.ParseStandaloneToolCallsDetailed(fixture.Text, fixture.ToolNames)
+			got = toolcall.ParseStandaloneToolCallsDetailed(fixture.Text, fixture.ToolNames)
 		default:
-			got = util.ParseToolCallsDetailed(fixture.Text, fixture.ToolNames)
+			got = toolcall.ParseToolCallsDetailed(fixture.Text, fixture.ToolNames)
 		}
 		if got.Calls == nil {
-			got.Calls = []util.ParsedToolCall{}
+			got.Calls = []toolcall.ParsedToolCall{}
 		}
 		if got.RejectedToolNames == nil {
 			got.RejectedToolNames = []string{}

internal/config/config_test.go

@@ -58,8 +58,7 @@ func TestLoadStorePreservesFileBackedTokensForRuntime(t *testing.T) {
 	if err != nil {
 		t.Fatalf("create temp config: %v", err)
 	}
-	defer tmp.Close()
-
+	defer func() { _ = tmp.Close() }()
 	if _, err := tmp.WriteString(`{
 		"accounts":[{"email":"u@example.com","password":"p","token":"persisted-token"}]
 	}`); err != nil {
@@ -355,7 +354,7 @@ func TestAccountTestStatusIsRuntimeOnlyAndNotPersisted(t *testing.T) {
 	if err != nil {
 		t.Fatalf("create temp config: %v", err)
 	}
-	defer tmp.Close()
+	defer func() { _ = tmp.Close() }()
 	if _, err := tmp.WriteString(`{
 		"accounts":[{"email":"u@example.com","password":"p","test_status":"ok"}]
 	}`); err != nil {

internal/deepseek/client_continue_test.go

@@ -31,7 +31,7 @@ func TestCallContinuePropagatesPowHeaderToFallbackRequest(t *testing.T) {
 	var seenURL string
 
 	client := &Client{
-		stream:   failingDoer{err: errors.New("stream transport failed")},
+		stream: failingDoer{err: errors.New("stream transport failed")},
 		fallbackS: &http.Client{
 			Transport: roundTripperFunc(func(req *http.Request) (*http.Response, error) {
 				seenPow = req.Header.Get("x-ds-pow-response")
@@ -54,8 +54,7 @@ func TestCallContinuePropagatesPowHeaderToFallbackRequest(t *testing.T) {
 	if err != nil {
 		t.Fatalf("callContinue returned error: %v", err)
 	}
-	defer resp.Body.Close()
-
+	defer func() { _ = resp.Body.Close() }()
 	if seenPow != "pow-response-abc" {
 		t.Fatalf("continue request pow header=%q want=%q", seenPow, "pow-response-abc")
 	}
@@ -105,8 +104,7 @@ func TestCallCompletionAutoContinueThreadsPowHeader(t *testing.T) {
 	if err != nil {
 		t.Fatalf("CallCompletion returned error: %v", err)
 	}
-	defer resp.Body.Close()
-
+	defer func() { _ = resp.Body.Close() }()
 	out, err := io.ReadAll(resp.Body)
 	if err != nil {
 		t.Fatalf("read auto-continued body failed: %v", err)

internal/deepseek/client_http_helpers.go

@@ -19,7 +19,7 @@ func readResponseBody(resp *http.Response) ([]byte, error) {
 		if err != nil {
 			return nil, err
 		}
-		defer gz.Close()
+		defer func() { _ = gz.Close() }()
 		reader = gz
 	case "br":
 		reader = brotli.NewReader(resp.Body)

internal/deepseek/client_http_json.go

@@ -49,7 +49,7 @@ func (c *Client) postJSONWithStatus(ctx context.Context, doer trans.Doer, url st
 			return nil, 0, err
 		}
 	}
-	defer resp.Body.Close()
+	defer func() { _ = resp.Body.Close() }()
 	payloadBytes, err := readResponseBody(resp)
 	if err != nil {
 		return nil, resp.StatusCode, err
@@ -86,7 +86,7 @@ func (c *Client) getJSONWithStatus(ctx context.Context, doer trans.Doer, url str
 			return nil, 0, err
 		}
 	}
-	defer resp.Body.Close()
+	defer func() { _ = resp.Body.Close() }()
 	payloadBytes, err := readResponseBody(resp)
 	if err != nil {
 		return nil, resp.StatusCode, err

internal/deepseek/constants.go

@@ -6,13 +6,13 @@ import (
 )
 
 const (
-	DeepSeekHost             = "chat.deepseek.com"
-	DeepSeekLoginURL         = "https://chat.deepseek.com/api/v0/users/login"
-	DeepSeekCreateSessionURL = "https://chat.deepseek.com/api/v0/chat_session/create"
-	DeepSeekCreatePowURL     = "https://chat.deepseek.com/api/v0/chat/create_pow_challenge"
-	DeepSeekCompletionURL    = "https://chat.deepseek.com/api/v0/chat/completion"
-	DeepSeekContinueURL      = "https://chat.deepseek.com/api/v0/chat/continue"
-	DeepSeekFetchSessionURL  = "https://chat.deepseek.com/api/v0/chat_session/fetch_page"
+	DeepSeekHost                 = "chat.deepseek.com"
+	DeepSeekLoginURL             = "https://chat.deepseek.com/api/v0/users/login"
+	DeepSeekCreateSessionURL     = "https://chat.deepseek.com/api/v0/chat_session/create"
+	DeepSeekCreatePowURL         = "https://chat.deepseek.com/api/v0/chat/create_pow_challenge"
+	DeepSeekCompletionURL        = "https://chat.deepseek.com/api/v0/chat/completion"
+	DeepSeekContinueURL          = "https://chat.deepseek.com/api/v0/chat/continue"
+	DeepSeekFetchSessionURL      = "https://chat.deepseek.com/api/v0/chat_session/fetch_page"
 	DeepSeekDeleteSessionURL     = "https://chat.deepseek.com/api/v0/chat_session/delete"
 	DeepSeekDeleteAllSessionsURL = "https://chat.deepseek.com/api/v0/chat_session/delete_all"
 )

internal/format/claude/render.go

@@ -1,6 +1,7 @@
 package claude
 
 import (
+	"ds2api/internal/toolcall"
 	"fmt"
 	"time"
 
@@ -8,9 +9,9 @@ import (
 )
 
 func BuildMessageResponse(messageID, model string, normalizedMessages []any, finalThinking, finalText string, toolNames []string) map[string]any {
-	detected := util.ParseToolCalls(finalText, toolNames)
+	detected := toolcall.ParseToolCalls(finalText, toolNames)
 	if len(detected) == 0 && finalText == "" && finalThinking != "" {
-		detected = util.ParseToolCalls(finalThinking, toolNames)
+		detected = toolcall.ParseToolCalls(finalThinking, toolNames)
 	}
 	content := make([]map[string]any, 0, 4)
 	if finalThinking != "" {

internal/format/openai/render_chat.go

@@ -1,14 +1,13 @@
 package openai
 
 import (
+	"ds2api/internal/toolcall"
 	"strings"
 	"time"
-
-	"ds2api/internal/util"
 )
 
 func BuildChatCompletion(completionID, model, finalPrompt, finalThinking, finalText string, toolNames []string) map[string]any {
-	detected := util.ParseStandaloneToolCallsDetailed(finalText, toolNames)
+	detected := toolcall.ParseStandaloneToolCallsDetailed(finalText, toolNames)
 	finishReason := "stop"
 	messageObj := map[string]any{"role": "assistant", "content": finalText}
 	if strings.TrimSpace(finalThinking) != "" {
@@ -16,7 +15,7 @@ func BuildChatCompletion(completionID, model, finalPrompt, finalThinking, finalT
 	}
 	if len(detected.Calls) > 0 {
 		finishReason = "tool_calls"
-		messageObj["tool_calls"] = util.FormatOpenAIToolCalls(detected.Calls)
+		messageObj["tool_calls"] = toolcall.FormatOpenAIToolCalls(detected.Calls)
 		messageObj["content"] = nil
 	}
 

internal/format/openai/render_responses.go

@@ -1,19 +1,18 @@
 package openai
 
 import (
+	"ds2api/internal/toolcall"
 	"encoding/json"
 	"strings"
 	"time"
 
 	"github.com/google/uuid"
-
-	"ds2api/internal/util"
 )
 
 func BuildResponseObject(responseID, model, finalPrompt, finalThinking, finalText string, toolNames []string) map[string]any {
 	// Strict mode: only standalone, structured tool-call payloads are treated
 	// as executable tool calls.
-	detected := util.ParseStandaloneToolCallsDetailed(finalText, toolNames)
+	detected := toolcall.ParseStandaloneToolCallsDetailed(finalText, toolNames)
 	exposedOutputText := finalText
 	output := make([]any, 0, 2)
 	if len(detected.Calls) > 0 {
@@ -71,7 +70,7 @@ func BuildResponseObjectFromItems(responseID, model, finalPrompt, finalThinking,
 	}
 }
 
-func toResponsesFunctionCallItems(toolCalls []util.ParsedToolCall) []any {
+func toResponsesFunctionCallItems(toolCalls []toolcall.ParsedToolCall) []any {
 	if len(toolCalls) == 0 {
 		return nil
 	}

internal/format/openai/render_stream_events.go

@@ -71,7 +71,6 @@ func BuildResponsesTextDeltaPayload(responseID, itemID string, outputIndex, cont
 	}
 }
 
-
 func BuildResponsesTextDonePayload(responseID, itemID string, outputIndex, contentIndex int, text string) map[string]any {
 	return map[string]any{
 		"type":          "response.output_text.done",

internal/js/chat-stream/sse_parse_impl.js

@@ -20,6 +20,8 @@ function parseChunkForContent(chunk, thinkingEnabled, currentType, stripReferenc
     };
   }
 
+  const outputTokens = extractAccumulatedTokenUsage(chunk);
+
   if (Object.prototype.hasOwnProperty.call(chunk, 'error')) {
     return {
       parsed: true,
@@ -33,7 +35,6 @@ function parseChunkForContent(chunk, thinkingEnabled, currentType, stripReferenc
   }
 
   const pathValue = asString(chunk.p);
-  const outputTokens = extractAccumulatedTokenUsage(chunk);
 
   if (hasContentFilterStatus(chunk)) {
     return {
@@ -465,10 +466,19 @@ function findAccumulatedTokenUsage(v) {
 }
 
 function toInt(v) {
-  if (typeof v !== 'number' || !Number.isFinite(v)) {
+  if (typeof v === 'number' && Number.isFinite(v)) {
+    return Math.trunc(v);
+  }
+  if (typeof v === 'string' && v.trim() !== '') {
+    const n = Number(v);
+    if (Number.isFinite(n)) {
+      return Math.trunc(n);
+    }
+  }
+  if (typeof v !== 'number') {
     return 0;
   }
-  return Math.trunc(v);
+  return Number.isFinite(v) ? Math.trunc(v) : 0;
 }
 
 function formatErrorMessage(v) {

internal/rawsample/visible_text.go

@@ -5,6 +5,7 @@ import (
 	"strings"
 )
 
+//nolint:unused // retained for raw-sample processing entrypoints.
 func extractProcessedVisibleText(raw []byte, kind, contentType string) string {
 	if len(raw) == 0 {
 		return ""
@@ -22,6 +23,7 @@ func extractProcessedVisibleText(raw []byte, kind, contentType string) string {
 	return parseOpenAIStreamText(string(raw))
 }
 
+//nolint:unused // retained for raw-sample processing entrypoints.
 func parseOpenAIStreamText(raw string) string {
 	if strings.TrimSpace(raw) == "" {
 		return ""
@@ -54,6 +56,7 @@ func parseOpenAIStreamText(raw string) string {
 	return out.String()
 }
 
+//nolint:unused // retained for raw-sample processing entrypoints.
 func parseOpenAIJSONText(raw string) string {
 	if strings.TrimSpace(raw) == "" {
 		return ""
@@ -65,6 +68,7 @@ func parseOpenAIJSONText(raw string) string {
 	return extractOpenAIVisibleTextValue(decoded)
 }
 
+//nolint:unused // retained for raw-sample processing entrypoints.
 func extractOpenAIVisibleTextValue(v any) string {
 	switch x := v.(type) {
 	case nil:

internal/sse/consumer.go

@@ -24,7 +24,7 @@ type CollectResult struct {
 // The caller is responsible for closing resp.Body unless closeBody is true.
 func CollectStream(resp *http.Response, thinkingEnabled bool, closeBody bool) CollectResult {
 	if closeBody {
-		defer resp.Body.Close()
+		defer func() { _ = resp.Body.Close() }()
 	}
 	text := strings.Builder{}
 	thinking := strings.Builder{}

internal/sse/line.go

@@ -20,8 +20,9 @@ func ParseDeepSeekContentLine(raw []byte, thinkingEnabled bool, currentType stri
 	if !parsed {
 		return LineResult{NextType: currentType}
 	}
+	outputTokens := extractAccumulatedTokenUsage(chunk)
 	if done {
-		return LineResult{Parsed: true, Stop: true, NextType: currentType}
+		return LineResult{Parsed: true, Stop: true, NextType: currentType, OutputTokens: outputTokens}
 	}
 	if errObj, hasErr := chunk["error"]; hasErr {
 		return LineResult{
@@ -29,6 +30,7 @@ func ParseDeepSeekContentLine(raw []byte, thinkingEnabled bool, currentType stri
 			Stop:         true,
 			ErrorMessage: fmt.Sprintf("%v", errObj),
 			NextType:     currentType,
+			OutputTokens: outputTokens,
 		}
 	}
 	if code, _ := chunk["code"].(string); code == "content_filter" {
@@ -37,7 +39,7 @@ func ParseDeepSeekContentLine(raw []byte, thinkingEnabled bool, currentType stri
 			Stop:          true,
 			ContentFilter: true,
 			NextType:      currentType,
-			OutputTokens:  extractAccumulatedTokenUsage(chunk),
+			OutputTokens:  outputTokens,
 		}
 	}
 	if hasContentFilterStatus(chunk) {
@@ -46,16 +48,16 @@ func ParseDeepSeekContentLine(raw []byte, thinkingEnabled bool, currentType stri
 			Stop:          true,
 			ContentFilter: true,
 			NextType:      currentType,
-			OutputTokens:  extractAccumulatedTokenUsage(chunk),
+			OutputTokens:  outputTokens,
 		}
 	}
 	parts, finished, nextType := ParseSSEChunkForContent(chunk, thinkingEnabled, currentType)
 	parts = filterLeakedContentFilterParts(parts)
 	return LineResult{
-		Parsed:   true,
-		Stop:     finished,
-		Parts:    parts,
-		NextType: nextType,
-		OutputTokens: extractAccumulatedTokenUsage(chunk),
+		Parsed:       true,
+		Stop:         finished,
+		Parts:        parts,
+		NextType:     nextType,
+		OutputTokens: outputTokens,
 	}
 }

internal/sse/line_test.go

@@ -53,6 +53,23 @@ func TestParseDeepSeekContentLineCapturesAccumulatedTokenUsage(t *testing.T) {
 	}
 }
 
+func TestParseDeepSeekContentLineCapturesAccumulatedTokenUsageString(t *testing.T) {
+	res := ParseDeepSeekContentLine([]byte(`data: {"p":"response","o":"BATCH","v":[{"p":"accumulated_token_usage","v":"190"},{"p":"quasi_status","v":"FINISHED"}]}`), false, "text")
+	if res.OutputTokens != 190 {
+		t.Fatalf("expected output token usage 190, got %d", res.OutputTokens)
+	}
+}
+
+func TestParseDeepSeekContentLineErrorIncludesOutputTokens(t *testing.T) {
+	res := ParseDeepSeekContentLine([]byte(`data: {"error":"boom","accumulated_token_usage":123}`), false, "text")
+	if !res.Parsed || !res.Stop {
+		t.Fatalf("expected stop on error: %#v", res)
+	}
+	if res.OutputTokens != 123 {
+		t.Fatalf("expected output token usage 123 on error, got %d", res.OutputTokens)
+	}
+}
+
 func TestParseDeepSeekContentLineContent(t *testing.T) {
 	res := ParseDeepSeekContentLine([]byte(`data: {"p":"response/content","v":"hi"}`), false, "text")
 	if !res.Parsed || res.Stop {

internal/sse/parser.go

@@ -4,6 +4,7 @@ import (
 	"bytes"
 	"encoding/json"
 	"math"
+	"strconv"
 	"strings"
 
 	"ds2api/internal/deepseek"
@@ -56,9 +57,7 @@ func isFragmentStatusPath(path string) bool {
 	if mid == "" {
 		return false
 	}
-	if strings.HasPrefix(mid, "-") {
-		mid = mid[1:]
-	}
+	mid = strings.TrimPrefix(mid, "-")
 	if mid == "" {
 		return false
 	}
@@ -309,11 +308,12 @@ func extractContentRecursive(items []any, defaultType string) ([]ContentPart, bo
 					}
 					typeName, _ := x["type"].(string)
 					typeName = strings.ToUpper(typeName)
-					if typeName == "THINK" || typeName == "THINKING" {
+					switch typeName {
+					case "THINK", "THINKING":
 						parts = append(parts, ContentPart{Text: ct, Type: "thinking"})
-					} else if typeName == "RESPONSE" {
+					case "RESPONSE":
 						parts = append(parts, ContentPart{Text: ct, Type: "text"})
-					} else {
+					default:
 						parts = append(parts, ContentPart{Text: ct, Type: partType})
 					}
 				case string:
@@ -413,6 +413,19 @@ func toInt(v any) (int, bool) {
 			return 0, false
 		}
 		return int(i), true
+	case string:
+		s := strings.TrimSpace(x)
+		if s == "" {
+			return 0, false
+		}
+		if i, err := strconv.Atoi(s); err == nil {
+			return i, true
+		}
+		f, err := strconv.ParseFloat(s, 64)
+		if err != nil || math.IsNaN(f) || math.IsInf(f, 0) {
+			return 0, false
+		}
+		return int(f), true
 	default:
 		return 0, false
 	}

internal/sse/raw_stream_token_replay_test.go

@@ -0,0 +1,134 @@
+package sse
+
+import (
+	"bufio"
+	"encoding/json"
+	"errors"
+	"os"
+	"path/filepath"
+	"strconv"
+	"strings"
+	"testing"
+)
+
+func TestRawStreamSamplesTokenReplay(t *testing.T) {
+	root := filepath.Join("..", "..", "tests", "raw_stream_samples")
+	entries, err := os.ReadDir(root)
+	if err != nil {
+		t.Fatalf("read samples root: %v", err)
+	}
+
+	found := 0
+	for _, entry := range entries {
+		if !entry.IsDir() {
+			continue
+		}
+		ssePath := filepath.Join(root, entry.Name(), "upstream.stream.sse")
+		if _, err := os.Stat(ssePath); err != nil {
+			continue
+		}
+		found++
+		t.Run(entry.Name(), func(t *testing.T) {
+			raw, err := os.ReadFile(ssePath)
+			if err != nil {
+				t.Fatalf("read sample: %v", err)
+			}
+			parsedTokens, expectedTokens, err := replayAndCollectTokens(string(raw))
+			if err != nil {
+				t.Fatalf("replay token collection failed: %v", err)
+			}
+			if expectedTokens <= 0 {
+				t.Fatalf("expected positive token usage from raw stream, got %d", expectedTokens)
+			}
+			if parsedTokens != expectedTokens {
+				t.Fatalf("token mismatch parsed=%d expected=%d", parsedTokens, expectedTokens)
+			}
+		})
+	}
+
+	if found == 0 {
+		t.Fatalf("no upstream.stream.sse samples found under %s", root)
+	}
+}
+
+func replayAndCollectTokens(raw string) (parsedTokens int, expectedTokens int, err error) {
+	currentType := "thinking"
+	scanner := bufio.NewScanner(strings.NewReader(raw))
+	scanner.Buffer(make([]byte, 0, 64*1024), 2*1024*1024)
+	for scanner.Scan() {
+		line := strings.TrimSpace(scanner.Text())
+		if !strings.HasPrefix(line, "data:") {
+			continue
+		}
+		payload := strings.TrimSpace(strings.TrimPrefix(line, "data:"))
+		if payload == "" || payload == "[DONE]" || !strings.HasPrefix(payload, "{") {
+			continue
+		}
+		var chunk map[string]any
+		if err := json.Unmarshal([]byte(payload), &chunk); err != nil {
+			continue
+		}
+		if n := rawAccumulatedTokenUsage(chunk); n > 0 {
+			expectedTokens = n
+		}
+		res := ParseDeepSeekContentLine([]byte(line), true, currentType)
+		currentType = res.NextType
+		if res.OutputTokens > 0 {
+			parsedTokens = res.OutputTokens
+		}
+	}
+	if scanErr := scanner.Err(); scanErr != nil {
+		if errors.Is(scanErr, bufio.ErrTooLong) {
+			return 0, 0, errors.New("raw stream line exceeds 2MiB scanner limit")
+		}
+		return 0, 0, scanErr
+	}
+	return parsedTokens, expectedTokens, nil
+}
+
+func rawAccumulatedTokenUsage(v any) int {
+	switch x := v.(type) {
+	case []any:
+		for _, item := range x {
+			if n := rawAccumulatedTokenUsage(item); n > 0 {
+				return n
+			}
+		}
+	case map[string]any:
+		if n := rawToInt(x["accumulated_token_usage"]); n > 0 {
+			return n
+		}
+		if p, _ := x["p"].(string); strings.Contains(strings.ToLower(strings.TrimSpace(p)), "accumulated_token_usage") {
+			if n := rawToInt(x["v"]); n > 0 {
+				return n
+			}
+		}
+		for _, vv := range x {
+			if n := rawAccumulatedTokenUsage(vv); n > 0 {
+				return n
+			}
+		}
+	}
+	return 0
+}
+
+func rawToInt(v any) int {
+	switch x := v.(type) {
+	case float64:
+		return int(x)
+	case int:
+		return x
+	case string:
+		s := strings.TrimSpace(x)
+		if s == "" {
+			return 0
+		}
+		if n, err := strconv.Atoi(s); err == nil {
+			return n
+		}
+		if f, err := strconv.ParseFloat(s, 64); err == nil {
+			return int(f)
+		}
+	}
+	return 0
+}

internal/sse/stream_edge_test.go

@@ -103,7 +103,7 @@ func TestStartParsedLinePumpContextCancellation(t *testing.T) {
 	// Cancel context - this will cause the pump to exit on next send
 	cancel()
 	// Close the pipe to unblock scanner.Scan()
-	pw.Close()
+	_ = pw.Close()
 
 	// Drain remaining results
 	for range results {

internal/testsuite/edge_cases.go

@@ -170,7 +170,7 @@ func (r *Runner) caseToolcallStreamMixed(ctx context.Context, cc *caseContext) e
 	cc.assert("tool_calls_delta_present", hasTool, "tool_calls delta missing")
 	cc.assert("no_raw_tool_json_leak", !rawLeak, "raw tool_calls leaked")
 	cc.assert("done_terminated", done, "expected [DONE]")
-	if !(hasTool && hasText) {
+	if !hasTool || !hasText {
 		r.warnings = append(r.warnings, "toolcall mixed stream did not produce both text and tool_calls in this run (model-side behavior dependent)")
 	}
 	return nil

internal/testsuite/edge_cases_abort.go

@@ -58,7 +58,7 @@ func (cc *caseContext) abortStreamRequest(ctx context.Context, spec requestSpec)
 		})
 		return err
 	}
-	defer resp.Body.Close()
+	defer func() { _ = resp.Body.Close() }()
 	buf := make([]byte, 512)
 	_, _ = resp.Body.Read(buf)
 	_ = resp.Body.Close()

internal/testsuite/runner_env.go

@@ -66,7 +66,7 @@ func (r *Runner) pruneOldRuns() error {
 		if err := os.RemoveAll(dirPath); err != nil {
 			errs = append(errs, fmt.Sprintf("remove %s: %v", name, err))
 		} else {
-			fmt.Fprintf(os.Stdout, "pruned old test run: %s\n", name)
+			_, _ = fmt.Fprintf(os.Stdout, "pruned old test run: %s\n", name)
 		}
 	}
 
@@ -82,7 +82,7 @@ func (r *Runner) runPreflight(ctx context.Context) error {
 	if err != nil {
 		return err
 	}
-	defer f.Close()
+	defer func() { _ = f.Close() }()
 	for _, step := range steps {
 		if _, err := fmt.Fprintf(f, "\n$ %s\n", strings.Join(step, " ")); err != nil {
 			return err
@@ -218,7 +218,7 @@ func (r *Runner) ping(path string) error {
 	if err != nil {
 		return err
 	}
-	defer resp.Body.Close()
+	defer func() { _ = resp.Body.Close() }()
 	if resp.StatusCode != http.StatusOK {
 		return fmt.Errorf("status=%d", resp.StatusCode)
 	}

internal/testsuite/runner_http.go

@@ -115,7 +115,7 @@ func (cc *caseContext) requestOnce(ctx context.Context, spec requestSpec, attemp
 		cc.mu.Unlock()
 		return nil, err
 	}
-	defer resp.Body.Close()
+	defer func() { _ = resp.Body.Close() }()
 	body, _ := io.ReadAll(resp.Body)
 
 	cc.mu.Lock()
@@ -131,7 +131,7 @@ func (cc *caseContext) requestOnce(ctx context.Context, spec requestSpec, attemp
 	})
 
 	if spec.Stream {
-		cc.streamRaw.WriteString(fmt.Sprintf("### trace=%s url=%s\n", traceID, fullURL))
+		_, _ = fmt.Fprintf(&cc.streamRaw, "### trace=%s url=%s\n", traceID, fullURL)
 		cc.streamRaw.Write(body)
 		cc.streamRaw.WriteString("\n\n")
 	}

internal/testsuite/runner_utils.go

@@ -126,7 +126,7 @@ func findFreePort() (int, error) {
 	if err != nil {
 		return 0, err
 	}
-	defer ln.Close()
+	defer func() { _ = ln.Close() }()
 	addr, ok := ln.Addr().(*net.TCPAddr)
 	if !ok {
 		return 0, errors.New("failed to detect tcp port")

internal/toolcall/tool_prompt.go

@@ -1,4 +1,4 @@
-package util
+package toolcall
 
 import "strings"
 

internal/toolcall/tool_prompt_test.go

@@ -1,4 +1,4 @@
-package util
+package toolcall
 
 import (
 	"strings"

internal/toolcall/toolcall_edge_test.go

@@ -0,0 +1,92 @@
+package toolcall
+
+import (
+	"testing"
+)
+
+// ─── FormatOpenAIStreamToolCalls ─────────────────────────────────────
+
+func TestFormatOpenAIStreamToolCalls(t *testing.T) {
+	formatted := FormatOpenAIStreamToolCalls([]ParsedToolCall{
+		{Name: "search", Input: map[string]any{"q": "test"}},
+	})
+	if len(formatted) != 1 {
+		t.Fatalf("expected 1, got %d", len(formatted))
+	}
+	fn, _ := formatted[0]["function"].(map[string]any)
+	if fn["name"] != "search" {
+		t.Fatalf("unexpected function name: %#v", fn)
+	}
+	if formatted[0]["index"] != 0 {
+		t.Fatalf("expected index 0, got %v", formatted[0]["index"])
+	}
+}
+
+// ─── ParseToolCalls more edge cases ──────────────────────────────────
+
+func TestParseToolCallsNoToolNames(t *testing.T) {
+	text := `{"tool_calls":[{"name":"search","input":{"q":"go"}}]}`
+	calls := ParseToolCalls(text, nil)
+	if len(calls) != 1 {
+		t.Fatalf("expected 1 call with nil tool names, got %d", len(calls))
+	}
+}
+
+func TestParseToolCallsEmptyText(t *testing.T) {
+	calls := ParseToolCalls("", []string{"search"})
+	if len(calls) != 0 {
+		t.Fatalf("expected 0 calls for empty text, got %d", len(calls))
+	}
+}
+
+func TestParseToolCallsMultipleTools(t *testing.T) {
+	text := `{"tool_calls":[{"name":"search","input":{"q":"go"}},{"name":"get_weather","input":{"city":"beijing"}}]}`
+	calls := ParseToolCalls(text, []string{"search", "get_weather"})
+	if len(calls) != 2 {
+		t.Fatalf("expected 2 calls, got %d", len(calls))
+	}
+}
+
+func TestParseToolCallsInputAsString(t *testing.T) {
+	text := `{"tool_calls":[{"name":"search","input":"{\"q\":\"golang\"}"}]}`
+	calls := ParseToolCalls(text, []string{"search"})
+	if len(calls) != 1 {
+		t.Fatalf("expected 1 call, got %d", len(calls))
+	}
+	if calls[0].Input["q"] != "golang" {
+		t.Fatalf("expected parsed string input, got %#v", calls[0].Input)
+	}
+}
+
+func TestParseToolCallsWithFunctionWrapper(t *testing.T) {
+	text := `{"tool_calls":[{"function":{"name":"calc","arguments":{"x":1,"y":2}}}]}`
+	calls := ParseToolCalls(text, []string{"calc"})
+	if len(calls) != 1 {
+		t.Fatalf("expected 1 call, got %d", len(calls))
+	}
+	if calls[0].Name != "calc" {
+		t.Fatalf("expected calc, got %q", calls[0].Name)
+	}
+}
+
+func TestParseStandaloneToolCallsFencedCodeBlock(t *testing.T) {
+	fenced := "Here's an example:\n```json\n{\"tool_calls\":[{\"name\":\"search\",\"input\":{\"q\":\"go\"}}]}\n```\nDon't execute this."
+	calls := ParseStandaloneToolCalls(fenced, []string{"search"})
+	if len(calls) != 0 {
+		t.Fatalf("expected fenced code block to be ignored, got %d calls", len(calls))
+	}
+}
+
+// ─── looksLikeToolExampleContext ─────────────────────────────────────
+
+func TestLooksLikeToolExampleContextNone(t *testing.T) {
+	if looksLikeToolExampleContext("I will call the tool now") {
+		t.Fatal("expected false for non-example context")
+	}
+}
+
+func TestLooksLikeToolExampleContextFenced(t *testing.T) {
+	if !looksLikeToolExampleContext("```json") {
+		t.Fatal("expected true for fenced code block context")
+	}
+}

internal/toolcall/toolcalls_candidates.go

@@ -1,4 +1,4 @@
-package util
+package toolcall
 
 import (
 	"regexp"
@@ -8,6 +8,8 @@ import (
 var toolCallPattern = regexp.MustCompile(`\{\s*["']tool_calls["']\s*:\s*\[(.*?)\]\s*\}`)
 var fencedJSONPattern = regexp.MustCompile("(?s)```(?:json)?\\s*(.*?)\\s*```")
 var fencedCodeBlockPattern = regexp.MustCompile("(?s)```[\\s\\S]*?```")
+
+//nolint:unused // retained for future markup tool-call heuristics.
 var markupToolSyntaxPattern = regexp.MustCompile(`(?i)<(?:(?:[a-z0-9_:-]+:)?(?:tool_call|function_call|invoke)\b|(?:[a-z0-9_:-]+:)?function_calls\b|(?:[a-z0-9_:-]+:)?tool_use\b)`)
 
 func buildToolCallCandidates(text string) []string {
@@ -190,6 +192,7 @@ func shouldSkipToolCallParsingForCodeFenceExample(text string) bool {
 	return !looksLikeToolCallSyntax(stripped)
 }
 
+//nolint:unused // retained for future markup tool-call heuristics.
 func looksLikeMarkupToolSyntax(text string) bool {
 	return markupToolSyntaxPattern.MatchString(text)
 }

internal/toolcall/toolcalls_format.go

@@ -1,4 +1,4 @@
-package util
+package toolcall
 
 import (
 	"encoding/json"

internal/toolcall/toolcalls_input_parse.go

@@ -1,4 +1,4 @@
-package util
+package toolcall
 
 import (
 	"encoding/json"

internal/toolcall/toolcalls_json_repair.go

@@ -1,4 +1,4 @@
-package util
+package toolcall
 
 import (
 	"regexp"
@@ -27,7 +27,7 @@ func repairInvalidJSONBackslashes(s string) string {
 						isHex := true
 						for j := 1; j <= 4; j++ {
 							r := runes[i+1+j]
-							if !((r >= '0' && r <= '9') || (r >= 'a' && r <= 'f') || (r >= 'A' && r <= 'F')) {
+							if (r < '0' || r > '9') && (r < 'a' || r > 'f') && (r < 'A' || r > 'F') {
 								isHex = false
 								break
 							}

internal/toolcall/toolcalls_markup.go

@@ -1,4 +1,4 @@
-package util
+package toolcall
 
 import (
 	"encoding/json"

internal/toolcall/toolcalls_name_match.go

@@ -1,12 +1,14 @@
-package util
+package toolcall
 
 import (
 	"regexp"
 	"strings"
 )
 
+//nolint:unused // retained for policy-level tool-name matching compatibility.
 var toolNameLoosePattern = regexp.MustCompile(`[^a-z0-9]+`)
 
+//nolint:unused // retained for policy-level tool-name matching compatibility.
 func resolveAllowedToolNameWithLooseMatch(name string, allowed map[string]struct{}, allowedCanonical map[string]string) string {
 	if _, ok := allowed[name]; ok {
 		return name

internal/toolcall/toolcalls_parse.go

@@ -1,4 +1,4 @@
-package util
+package toolcall
 
 import (
 	"encoding/json"
@@ -164,6 +164,7 @@ func filterToolCallsDetailed(parsed []ParsedToolCall, availableToolNames []strin
 	return out, nil
 }
 
+//nolint:unused // retained for policy-level tool-name matching compatibility.
 func resolveAllowedToolName(name string, allowed map[string]struct{}, allowedCanonical map[string]string) string {
 	return resolveAllowedToolNameWithLooseMatch(name, allowed, allowedCanonical)
 }

internal/toolcall/toolcalls_parse_item.go

@@ -1,4 +1,4 @@
-package util
+package toolcall
 
 import "strings"
 
@@ -7,7 +7,7 @@ func isLikelyJSONToolPayloadCandidate(candidate string) bool {
 	if trimmed == "" {
 		return false
 	}
-	if !(strings.HasPrefix(trimmed, "{") || strings.HasPrefix(trimmed, "[")) {
+	if !strings.HasPrefix(trimmed, "{") && !strings.HasPrefix(trimmed, "[") {
 		return false
 	}
 	lower := strings.ToLower(trimmed)
@@ -73,7 +73,6 @@ func parseToolCallItem(m map[string]any) (ParsedToolCall, bool) {
 		for _, key := range []string{"arguments", "args", "parameters", "params"} {
 			if v, ok := m[key]; ok {
 				inputRaw = v
-				hasInput = true
 				break
 			}
 		}

internal/toolcall/toolcalls_parse_markup.go

@@ -1,4 +1,4 @@
-package util
+package toolcall
 
 import (
 	"encoding/json"

internal/toolcall/toolcalls_test.go

@@ -1,4 +1,4 @@
-package util
+package toolcall
 
 import (
 	"strings"

internal/toolcall/toolcalls_textkv.go

@@ -1,4 +1,4 @@
-package util
+package toolcall
 
 import (
 	"regexp"

internal/toolcall/toolcalls_textkv_test.go

@@ -1,4 +1,4 @@
-package util
+package toolcall
 
 import (
 	"testing"

internal/util/render.go

@@ -1,6 +1,7 @@
 package util
 
 import (
+	"ds2api/internal/toolcall"
 	"fmt"
 	"strings"
 	"time"
@@ -11,7 +12,7 @@ import (
 // BuildOpenAIChatCompletion is kept for backward compatibility.
 // Prefer internal/format/openai.BuildChatCompletion for new code.
 func BuildOpenAIChatCompletion(completionID, model, finalPrompt, finalThinking, finalText string, toolNames []string) map[string]any {
-	detected := ParseToolCalls(finalText, toolNames)
+	detected := toolcall.ParseToolCalls(finalText, toolNames)
 	finishReason := "stop"
 	messageObj := map[string]any{"role": "assistant", "content": finalText}
 	if strings.TrimSpace(finalThinking) != "" {
@@ -19,7 +20,7 @@ func BuildOpenAIChatCompletion(completionID, model, finalPrompt, finalThinking,
 	}
 	if len(detected) > 0 {
 		finishReason = "tool_calls"
-		messageObj["tool_calls"] = FormatOpenAIToolCalls(detected)
+		messageObj["tool_calls"] = toolcall.FormatOpenAIToolCalls(detected)
 		messageObj["content"] = nil
 	}
 	promptTokens := EstimateTokens(finalPrompt)
@@ -46,7 +47,7 @@ func BuildOpenAIChatCompletion(completionID, model, finalPrompt, finalThinking,
 // BuildOpenAIResponseObject is kept for backward compatibility.
 // Prefer internal/format/openai.BuildResponseObject for new code.
 func BuildOpenAIResponseObject(responseID, model, finalPrompt, finalThinking, finalText string, toolNames []string) map[string]any {
-	detected := ParseToolCalls(finalText, toolNames)
+	detected := toolcall.ParseToolCalls(finalText, toolNames)
 	exposedOutputText := finalText
 	output := make([]any, 0, 2)
 	if len(detected) > 0 {
@@ -108,7 +109,7 @@ func BuildOpenAIResponseObject(responseID, model, finalPrompt, finalThinking, fi
 // BuildClaudeMessageResponse is kept for backward compatibility.
 // Prefer internal/format/claude.BuildMessageResponse for new code.
 func BuildClaudeMessageResponse(messageID, model string, normalizedMessages []any, finalThinking, finalText string, toolNames []string) map[string]any {
-	detected := ParseToolCalls(finalText, toolNames)
+	detected := toolcall.ParseToolCalls(finalText, toolNames)
 	content := make([]map[string]any, 0, 4)
 	if finalThinking != "" {
 		content = append(content, map[string]any{"type": "thinking", "thinking": finalThinking})

internal/util/util_edge_test.go

@@ -355,90 +355,3 @@ func TestConvertClaudeToDeepSeekOpusUsesSlowMapping(t *testing.T) {
 		t.Fatalf("expected opus to use slow mapping, got %q", out["model"])
 	}
 }
-
-// ─── FormatOpenAIStreamToolCalls ─────────────────────────────────────
-
-func TestFormatOpenAIStreamToolCalls(t *testing.T) {
-	formatted := FormatOpenAIStreamToolCalls([]ParsedToolCall{
-		{Name: "search", Input: map[string]any{"q": "test"}},
-	})
-	if len(formatted) != 1 {
-		t.Fatalf("expected 1, got %d", len(formatted))
-	}
-	fn, _ := formatted[0]["function"].(map[string]any)
-	if fn["name"] != "search" {
-		t.Fatalf("unexpected function name: %#v", fn)
-	}
-	if formatted[0]["index"] != 0 {
-		t.Fatalf("expected index 0, got %v", formatted[0]["index"])
-	}
-}
-
-// ─── ParseToolCalls more edge cases ──────────────────────────────────
-
-func TestParseToolCallsNoToolNames(t *testing.T) {
-	text := `{"tool_calls":[{"name":"search","input":{"q":"go"}}]}`
-	calls := ParseToolCalls(text, nil)
-	if len(calls) != 1 {
-		t.Fatalf("expected 1 call with nil tool names, got %d", len(calls))
-	}
-}
-
-func TestParseToolCallsEmptyText(t *testing.T) {
-	calls := ParseToolCalls("", []string{"search"})
-	if len(calls) != 0 {
-		t.Fatalf("expected 0 calls for empty text, got %d", len(calls))
-	}
-}
-
-func TestParseToolCallsMultipleTools(t *testing.T) {
-	text := `{"tool_calls":[{"name":"search","input":{"q":"go"}},{"name":"get_weather","input":{"city":"beijing"}}]}`
-	calls := ParseToolCalls(text, []string{"search", "get_weather"})
-	if len(calls) != 2 {
-		t.Fatalf("expected 2 calls, got %d", len(calls))
-	}
-}
-
-func TestParseToolCallsInputAsString(t *testing.T) {
-	text := `{"tool_calls":[{"name":"search","input":"{\"q\":\"golang\"}"}]}`
-	calls := ParseToolCalls(text, []string{"search"})
-	if len(calls) != 1 {
-		t.Fatalf("expected 1 call, got %d", len(calls))
-	}
-	if calls[0].Input["q"] != "golang" {
-		t.Fatalf("expected parsed string input, got %#v", calls[0].Input)
-	}
-}
-
-func TestParseToolCallsWithFunctionWrapper(t *testing.T) {
-	text := `{"tool_calls":[{"function":{"name":"calc","arguments":{"x":1,"y":2}}}]}`
-	calls := ParseToolCalls(text, []string{"calc"})
-	if len(calls) != 1 {
-		t.Fatalf("expected 1 call, got %d", len(calls))
-	}
-	if calls[0].Name != "calc" {
-		t.Fatalf("expected calc, got %q", calls[0].Name)
-	}
-}
-
-func TestParseStandaloneToolCallsFencedCodeBlock(t *testing.T) {
-	fenced := "Here's an example:\n```json\n{\"tool_calls\":[{\"name\":\"search\",\"input\":{\"q\":\"go\"}}]}\n```\nDon't execute this."
-	calls := ParseStandaloneToolCalls(fenced, []string{"search"})
-	if len(calls) != 0 {
-		t.Fatalf("expected fenced code block to be ignored, got %d calls", len(calls))
-	}
-}
-
-// ─── looksLikeToolExampleContext ─────────────────────────────────────
-
-func TestLooksLikeToolExampleContextNone(t *testing.T) {
-	if looksLikeToolExampleContext("I will call the tool now") {
-		t.Fatal("expected false for non-example context")
-	}
-}
-
-func TestLooksLikeToolExampleContextFenced(t *testing.T) {
-	if !looksLikeToolExampleContext("```json") {
-		t.Fatal("expected true for fenced code block context")
-	}
-}

plans/refactor-line-gate-targets.txt

@@ -56,9 +56,9 @@ internal/adapter/openai/tool_sieve_core.go
 internal/adapter/openai/tool_sieve_xml.go
 internal/adapter/openai/tool_sieve_jsonscan.go
 
-internal/util/toolcalls_parse.go
-internal/util/toolcalls_candidates.go
-internal/util/toolcalls_format.go
+internal/toolcall/toolcalls_parse.go
+internal/toolcall/toolcalls_candidates.go
+internal/toolcall/toolcalls_format.go
 
 internal/adapter/claude/handler_routes.go
 internal/adapter/claude/handler_messages.go

scripts/lint.sh

@@ -0,0 +1,105 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+ROOT_DIR="$(cd "$(dirname "$0")/.." && pwd)"
+cd "$ROOT_DIR"
+
+LINT_BIN="${GOLANGCI_LINT_BIN:-golangci-lint}"
+BOOTSTRAP_VERSION="${GOLANGCI_LINT_VERSION:-v2.11.4}"
+BOOTSTRAP_BIN="${ROOT_DIR}/.tmp/golangci-lint-${BOOTSTRAP_VERSION}"
+
+bootstrap_golangci_lint() {
+  local version_no_v os arch artifact archive_url tmp_dir
+  version_no_v="${BOOTSTRAP_VERSION#v}"
+  os="$(uname -s | tr '[:upper:]' '[:lower:]')"
+  arch="$(uname -m | tr '[:upper:]' '[:lower:]')"
+
+  case "$os" in
+    linux|darwin|windows) ;;
+    *)
+      echo "unsupported OS for bootstrap: ${os}" >&2
+      return 1
+      ;;
+  esac
+
+  case "$arch" in
+    x86_64|amd64) arch="amd64" ;;
+    aarch64|arm64) arch="arm64" ;;
+    *)
+      echo "unsupported architecture for bootstrap: ${arch}" >&2
+      return 1
+      ;;
+  esac
+
+  artifact="${os}-${arch}"
+  archive_url="https://github.com/golangci/golangci-lint/releases/download/${BOOTSTRAP_VERSION}/golangci-lint-${version_no_v}-${artifact}.tar.gz"
+
+  mkdir -p "${ROOT_DIR}/.tmp"
+  tmp_dir="$(mktemp -d)"
+  trap 'rm -rf "${tmp_dir}"' RETURN
+
+  curl -sSfL "${archive_url}" -o "${tmp_dir}/golangci-lint.tar.gz"
+  tar -xzf "${tmp_dir}/golangci-lint.tar.gz" -C "${tmp_dir}"
+  cp "${tmp_dir}/golangci-lint-${version_no_v}-${artifact}/golangci-lint" "${BOOTSTRAP_BIN}"
+  chmod +x "${BOOTSTRAP_BIN}"
+
+  echo "bootstrapped golangci-lint ${BOOTSTRAP_VERSION} to ${BOOTSTRAP_BIN}" >&2
+}
+
+run_lint() {
+  local bin="$1"
+  if [[ "$bin" == *" "* ]]; then
+    eval "$bin fmt --diff -c .golangci.yml" && eval "$bin run -c .golangci.yml"
+  else
+    "$bin" fmt --diff -c .golangci.yml && "$bin" run -c .golangci.yml
+  fi
+}
+
+is_compatibility_error() {
+  case "$1" in
+    *"command not found"*|\
+    *"not recognized as an internal or external command"*|\
+    *"No such file or directory"*|\
+    *"unknown command \"fmt\""*|\
+    *"unknown command \"run\""*|\
+    *"unknown flag"*|\
+    *"no such flag"*|\
+    *"unsupported version of the configuration"*|\
+    *"can't load config"*)
+      return 0
+      ;;
+    *)
+      return 1
+      ;;
+  esac
+}
+
+# v2 separates formatters from linters; enforce both in one entrypoint.
+if lint_output="$(run_lint "$LINT_BIN" 2>&1)"; then
+  [[ -n "$lint_output" ]] && echo "$lint_output"
+  exit 0
+fi
+
+if [[ -n "${GOLANGCI_LINT_BIN:-}" ]]; then
+  echo "$lint_output" >&2
+  echo "lint failed with explicit GOLANGCI_LINT_BIN=${GOLANGCI_LINT_BIN}; skip auto-bootstrap." >&2
+  exit 1
+fi
+
+if ! is_compatibility_error "$lint_output"; then
+  echo "$lint_output" >&2
+  exit 1
+fi
+
+echo "default golangci-lint appears incompatible; bootstrapping ${BOOTSTRAP_VERSION}..." >&2
+if [[ ! -x "${BOOTSTRAP_BIN}" ]]; then
+  bootstrap_golangci_lint
+fi
+
+if lint_output="$(run_lint "${BOOTSTRAP_BIN}" 2>&1)"; then
+  [[ -n "$lint_output" ]] && echo "$lint_output"
+  exit 0
+fi
+
+echo "$lint_output" >&2
+exit 1

tests/raw_stream_samples/README.md

@@ -76,6 +76,23 @@ POST /admin/dev/raw-samples/save
 ./tests/scripts/run-raw-stream-sim.sh
 ```
 
+运行**全部样本目录**（不只 manifest 默认样本），并逐个打印 token 对齐结果：
+
+```bash
+for d in tests/raw_stream_samples/*; do
+  [ -d "$d" ] || continue
+  sid="$(basename "$d")"
+  [ -f "$d/upstream.stream.sse" ] || continue
+  node tests/tools/deepseek-sse-simulator.mjs --samples-root tests/raw_stream_samples --sample-id "$sid"
+done
+```
+
+回放输出会显示 `tokens=<parsed>/<expected>`，并在不一致时判定失败；`report.json` 中也会包含：
+
+- `raw_expected_output_tokens`
+- `raw_parsed_output_tokens`
+- `raw_token_mismatch`
+
 运行单个样本并和已有基线比对：
 
 ```bash

tests/repair_json_tool.go

@@ -27,7 +27,7 @@ func repairInvalidJSONBackslashes(s string) string {
 						isHex := true
 						for j := 1; j <= 4; j++ {
 							r := runes[i+1+j]
-							if !((r >= '0' && r <= '9') || (r >= 'a' && r <= 'f') || (r >= 'A' && r <= 'F')) {
+							if (r < '0' || r > '9') && (r < 'a' || r > 'f') && (r < 'A' || r > 'F') {
 								isHex = false
 								break
 							}

tests/scripts/run-unit-node.sh

@@ -17,6 +17,10 @@ trap cleanup EXIT
 if ! node --test --test-concurrency=1 tests/node/stream-tool-sieve.test.js tests/node/chat-stream.test.js tests/node/js_compat_test.js "$@" 2>&1 | tee "$NODE_TEST_LOG"; then
   echo
   echo "[run-unit-node] Node tests failed. 失败摘要如下："
-  rg -n "^(not ok|# fail)|ERR_TEST_FAILURE" "$NODE_TEST_LOG" || true
+  if command -v rg >/dev/null 2>&1; then
+    rg -n "^(not ok|# fail)|ERR_TEST_FAILURE" "$NODE_TEST_LOG" || true
+  else
+    grep -nE "^(not ok|# fail)|ERR_TEST_FAILURE" "$NODE_TEST_LOG" || true
+  fi
   exit 1
 fi

tests/tools/deepseek-sse-simulator.mjs

@@ -20,6 +20,7 @@ function parseArgs(argv) {
     failOnReferenceLeak: true,
     failOnMissingFinish: true,
     failOnBaselineMismatch: true,
+    failOnTokenMismatch: true,
     showOutput: false,
     writeReplayText: false,
   };
@@ -43,6 +44,8 @@ function parseArgs(argv) {
       out.failOnMissingFinish = false;
     } else if (a === '--no-fail-on-baseline-mismatch' || a === '--no-fail-on-processed-mismatch') {
       out.failOnBaselineMismatch = false;
+    } else if (a === '--no-fail-on-token-mismatch') {
+      out.failOnTokenMismatch = false;
     } else if (a === '--show-output') {
       out.showOutput = true;
     } else if (a === '--write-replay-text' || a === '--write-processed-text') {
@@ -183,6 +186,8 @@ function parseDeepSeekReplay(raw) {
   let thinkingText = '';
   let textOutput = '';
   let parsedChunks = 0;
+  let parsedOutputTokens = 0;
+  let expectedOutputTokens = 0;
 
   for (const evt of events) {
     if (evt.event === 'finish') {
@@ -198,7 +203,14 @@ function parseDeepSeekReplay(raw) {
       continue;
     }
     parsedChunks += 1;
+    const expected = extractAccumulatedTokenUsageFromRawChunk(obj);
+    if (expected > 0) {
+      expectedOutputTokens = expected;
+    }
     const parsed = parseChunkForContent(obj, true, currentType);
+    if (parsed.outputTokens > 0) {
+      parsedOutputTokens = parsed.outputTokens;
+    }
     currentType = parsed.newType;
     if (parsed.finished) {
       sawFinish = true;
@@ -220,6 +232,9 @@ function parseDeepSeekReplay(raw) {
     events: events.length,
     parsedChunks,
     sawFinish,
+    parsedOutputTokens,
+    expectedOutputTokens,
+    tokenMismatch: expectedOutputTokens > 0 && parsedOutputTokens !== expectedOutputTokens,
     outputText,
     outputChars: outputText.length,
     leakedFinishedText: outputText.includes('FINISHED'),
@@ -228,6 +243,52 @@ function parseDeepSeekReplay(raw) {
   };
 }
 
+function extractAccumulatedTokenUsageFromRawChunk(v) {
+  if (Array.isArray(v)) {
+    for (const item of v) {
+      const n = extractAccumulatedTokenUsageFromRawChunk(item);
+      if (n > 0) {
+        return n;
+      }
+    }
+    return 0;
+  }
+  if (!v || typeof v !== 'object') {
+    return 0;
+  }
+  const direct = toTokenInt(v.accumulated_token_usage);
+  if (direct > 0) {
+    return direct;
+  }
+  const pathValue = typeof v.p === 'string' ? v.p.trim().toLowerCase() : '';
+  if (pathValue.includes('accumulated_token_usage')) {
+    const n = toTokenInt(v.v);
+    if (n > 0) {
+      return n;
+    }
+  }
+  for (const value of Object.values(v)) {
+    const n = extractAccumulatedTokenUsageFromRawChunk(value);
+    if (n > 0) {
+      return n;
+    }
+  }
+  return 0;
+}
+
+function toTokenInt(v) {
+  if (typeof v === 'number' && Number.isFinite(v)) {
+    return Math.trunc(v);
+  }
+  if (typeof v === 'string' && v.trim() !== '') {
+    const n = Number(v);
+    if (Number.isFinite(n)) {
+      return Math.trunc(n);
+    }
+  }
+  return 0;
+}
+
 function parseOpenAIStream(raw) {
   const events = parseSSE(raw);
   let outputText = '';
@@ -410,12 +471,18 @@ function replaySample(dir, opts) {
   if (baselineResult && opts.failOnBaselineMismatch && !baselineMatch) {
     errors.push('baseline output mismatch');
   }
+  if (opts.failOnTokenMismatch && rawResult.tokenMismatch) {
+    errors.push(`token mismatch expected=${rawResult.expectedOutputTokens} parsed=${rawResult.parsedOutputTokens}`);
+  }
 
   return {
     sample_id: path.basename(dir),
     raw_events: rawResult.events,
     raw_parsed_chunks: rawResult.parsedChunks,
     raw_saw_finish: rawResult.sawFinish,
+    raw_expected_output_tokens: rawResult.expectedOutputTokens,
+    raw_parsed_output_tokens: rawResult.parsedOutputTokens,
+    raw_token_mismatch: rawResult.tokenMismatch,
     raw_output_chars: rawResult.outputChars,
     raw_leaked_finished_text: rawResult.leakedFinishedText,
     raw_leaked_reference_markers: rawResult.leakedReferenceMarkers,
@@ -485,6 +552,9 @@ function main() {
       raw_events: sample.raw_events,
       raw_parsed_chunks: sample.raw_parsed_chunks,
       raw_saw_finish: sample.raw_saw_finish,
+      raw_expected_output_tokens: sample.raw_expected_output_tokens,
+      raw_parsed_output_tokens: sample.raw_parsed_output_tokens,
+      raw_token_mismatch: sample.raw_token_mismatch,
       raw_output_chars: sample.raw_output_chars,
       raw_leaked_finished_text: sample.raw_leaked_finished_text,
       raw_leaked_reference_markers: sample.raw_leaked_reference_markers,
@@ -508,7 +578,7 @@ function main() {
       ? ` baseline=${sample.baseline_output_matches_replay ? 'match' : 'mismatch'}`
       : ' baseline=missing';
     const note = errors.length > 0 ? ` errors=${errors.join(';')}` : '';
-    console.log(`[sim] ${status} ${sample.sample_id} events=${sample.raw_events} parsed=${sample.raw_parsed_chunks} chars=${sample.raw_output_chars}${leakNote}${matchNote}${note}`);
+    console.log(`[sim] ${status} ${sample.sample_id} events=${sample.raw_events} parsed=${sample.raw_parsed_chunks} tokens=${sample.raw_parsed_output_tokens}/${sample.raw_expected_output_tokens} chars=${sample.raw_output_chars}${leakNote}${matchNote}${note}`);
     if (opts.showOutput) {
       console.log(`[sim] replay output for ${sample.sample_id}:`);
       console.log(sample.replay_output_text || '(empty)');