Merge pull request 'U4 第三步：textextract 抽包，消除 materialindex→squad 反向依赖' (#7) from feature/textextract-package-2026-09-29 into dev

.doc/system-design/module-boundaries.yaml

@@ -27,8 +27,8 @@ imports:
     - docduty
   bizdev:
     - agent
-    - authz
     - app/uow
+    - authz
     - config
     - conflictresolve
     - contracts/vocabulary
@@ -50,6 +50,7 @@ imports:
     - squad
     - storage
     - stream
+    - textextract
     - workflowdef
     - workspace
   chat:
@@ -214,6 +215,7 @@ imports:
     - kb
     - mineru
     - squad
+    - textextract
   maturity: []
   mineru: []
   notification: []
@@ -272,22 +274,22 @@ imports:
     - storage
     - stream
     - stream/transport
+    - supplementimpact
     - swboot
     - sysadmin
     - taskrun
+    - textextract
     - traceimpact
     - upload
     - workflowdef
     - workflowscope
     - workspace
-    - supplementimpact
   squad:
     - agent
     - config
-    - quote
     - stream
     - template
-    - workspace
+    - textextract
     - workflowdef
   storage:
     - config
@@ -306,6 +308,7 @@ imports:
     - projectworkflow
     - stream
     - workspace
+  textextract: []
   template:
     - workflowdef
   upload: []

internal/bizdev/engine.go

@@ -1,25 +1,9 @@
 package bizdev
 
 import (
-	"chat-agent-system/internal/quote"
 	"chat-agent-system/internal/squad"
 )
 
-// FormatMoney formats a currency amount for display in markdown (no grouping separators).
-func FormatMoney(v float64) string {
-	return squad.FormatMoney(v)
-}
-
-// RenderCDOQuoteTable builds the pricing table from quote summary lines and total.
-func RenderCDOQuoteTable(summary *quote.Summary) string {
-	return squad.RenderCDOQuoteTable(summary)
-}
-
-// BackfillCDOQuoteMarkdown replaces placeholder sections with computed pricing from summary.
-func BackfillCDOQuoteMarkdown(body string, summary *quote.Summary) string {
-	return squad.BackfillCDOQuoteMarkdown(body, summary)
-}
-
 // WriteMaterials persists uploaded material text into workspace materials_text/.
 func WriteMaterials(workDir string, materials []MaterialInput) error {
 	var items []squad.MaterialItem

internal/bizdev/materials.go

@@ -12,6 +12,7 @@ import (
 
 	"chat-agent-system/internal/materialindex"
 	"chat-agent-system/internal/squad"
+	"chat-agent-system/internal/textextract"
 	"chat-agent-system/internal/storage"
 )
 
@@ -154,7 +155,7 @@ func (s *Service) materialToItems(
 			meta["parse_engine"] = "mineru"
 		}
 	} else {
-		text, err = squad.ExtractTextWithAnchors(fileName, data)
+		text, err = textextract.ExtractTextWithAnchors(fileName, data)
 		if err != nil {
 			return nil, nil, fmt.Errorf("extract material %q: %w", fileName, err)
 		}

internal/bizdev/quote_backfill.go

@@ -1,4 +1,4 @@
-package squad
+package bizdev
 
 import (
 	"fmt"

internal/bizdev/quote_preparer.go

@@ -0,0 +1,74 @@
+package bizdev
+
+import (
+	"os"
+	"path/filepath"
+
+	"chat-agent-system/internal/quote"
+	"chat-agent-system/internal/squad"
+	"chat-agent-system/internal/workflowdef"
+)
+
+// handleCDOQuotePreparation 为 CDO 报价任务执行 Excel 核算并生成回填内容
+// （KTD1：报价领域规则、核算与 xlsx 资产归 Core；只计算，不写 squad 工作区，
+// 文件由 squad 经 TaskPreparation.Backfills 统一写入）。
+func (s *Service) handleCDOQuotePreparation(workDir string, req squad.SquadRunRequest) (*squad.TaskPreparation, error) {
+	in := quote.Input{
+		CustomerName: req.CustomerName,
+		ProductName:  req.ProjectName,
+		Hours: map[string]float64{
+			"结构工程师": 320,
+			"硬件工程师": 320,
+			"软件工程师": 480,
+			"项目经理":  160,
+		},
+	}
+	// 核算写入临时文件后读回字节；工作区文件由 squad 写入。
+	tmp, err := os.CreateTemp("", "cdo-quote-*.xlsx")
+	if err != nil {
+		return nil, err
+	}
+	tmpPath := tmp.Name()
+	tmp.Close()
+	defer os.Remove(tmpPath)
+
+	summary, err := quote.CalculateAndFill(in, "templates/xlsx/cdo_quote.xlsx", tmpPath)
+	if err != nil {
+		return nil, err
+	}
+	data, err := os.ReadFile(tmpPath)
+	if err != nil {
+		return nil, err
+	}
+
+	backfills := map[string][]byte{
+		"CDO报价核算-V01.xlsx":            data,
+		"artifacts/CDO报价核算-V01.xlsx": data,
+	}
+	// 回填 template.md 报价占位（模板存在时）；output.md 镜像由 squad 决定
+	tmplBytes, tmplErr := os.ReadFile(filepath.Join(workDir, "template.md"))
+	mirror := false
+	if tmplErr == nil {
+		filled := BackfillCDOQuoteMarkdown(string(tmplBytes), summary)
+		backfills["template.md"] = []byte(filled)
+		mirror = true
+	}
+
+	return &squad.TaskPreparation{
+		Attachment: &squad.Attachment{
+			Filename:    "CDO报价核算-V01.xlsx",
+			ContentType: "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
+			Data:        data,
+		},
+		Backfills:              backfills,
+		MirrorTemplateToOutput: mirror,
+	}, nil
+}
+
+// squadTaskPreparer 仅对 CDO 报价任务触发领域准备，其余任务快速跳过。
+func (s *Service) squadTaskPreparer(workDir string, req squad.SquadRunRequest) (*squad.TaskPreparation, error) {
+	if !workflowdef.SameTaskKey(req.TaskKey, "cdo_quote") {
+		return nil, nil
+	}
+	return s.handleCDOQuotePreparation(workDir, req)
+}

internal/bizdev/service.go

@@ -193,14 +193,6 @@ func NewService(cfg *config.Config) (*Service, error) {
 	svc := &Service{
 		cfg:             cfg,
 		kb:              kb.NewClient(cfg),
-		squad: squad.NewService(squad.Options{
-			BackendName:    cfg.AgentBackend,
-			BackendTimeout: cfg.AgentTimeout,
-			DataDir:        cfg.DataDir,
-			NewBackend: func(name string) agent.Backend {
-				return agent.NewBackend(name, cfg)
-			},
-		}),
 		ctxMgr:          ctxMgr,
 		cas:             casStore,
 		materialIndex:   matIndex,
@@ -211,6 +203,15 @@ func NewService(cfg *config.Config) (*Service, error) {
 		pool:            pool,
 		schemaVersion:   schemaVersion,
 	}
+	svc.squad = squad.NewService(squad.Options{
+		BackendName:    cfg.AgentBackend,
+		BackendTimeout: cfg.AgentTimeout,
+		DataDir:        cfg.DataDir,
+		NewBackend: func(name string) agent.Backend {
+			return agent.NewBackend(name, cfg)
+		},
+		TaskPreparer: svc.squadTaskPreparer,
+	})
 	svc.parts = Parts{
 		Pool:          pool,
 		Gov:           docGov,

internal/materialindex/pipeline.go

@@ -18,7 +18,7 @@ import (
 	"chat-agent-system/internal/config"
 	"chat-agent-system/internal/kb"
 	"chat-agent-system/internal/mineru"
-	"chat-agent-system/internal/squad"
+	"chat-agent-system/internal/textextract"
 
 	"github.com/jackc/pgx/v5"
 	"github.com/jackc/pgx/v5/pgxpool"
@@ -233,7 +233,7 @@ func (p *Pipeline) ResetForReparse(ctx context.Context, blobSHA string) bool {
 // fallback text from squad.ExtractTextWithAnchors (may be empty).
 func (p *Pipeline) EnsureParsed(ctx context.Context, fileName string, blobSHA string, data []byte) (markdown string, fromMinerU bool, err error) {
 	fallback := func() (string, bool, error) {
-		txt, e := squad.ExtractTextWithAnchors(fileName, data)
+		txt, e := textextract.ExtractTextWithAnchors(fileName, data)
 		return strings.TrimSpace(txt), false, e
 	}
 	if p == nil {

internal/server/chat_document_reader.go

@@ -15,7 +15,7 @@ import (
 	"chat-agent-system/internal/docgov"
 	"chat-agent-system/internal/intent"
 	"chat-agent-system/internal/projectinstance"
-	"chat-agent-system/internal/squad"
+	"chat-agent-system/internal/textextract"
 	"chat-agent-system/internal/storage"
 	"chat-agent-system/internal/stream"
 	"chat-agent-system/internal/workflowscope"
@@ -179,7 +179,7 @@ func (s *Server) resolveLatestUploadDocument(ctx context.Context, projectID int6
 		}
 		markdown = strings.TrimSpace(md)
 	} else {
-		md, extractErr := squad.ExtractTextWithAnchors(ref.FileName, data)
+		md, extractErr := textextract.ExtractTextWithAnchors(ref.FileName, data)
 		if extractErr != nil {
 			return nil, extractErr
 		}

internal/squad/context.go

@@ -1,6 +1,7 @@
 package squad
 
 import (
+	"chat-agent-system/internal/textextract"
 	"encoding/json"
 	"fmt"
 	"os"
@@ -145,7 +146,7 @@ func (cm *ContextManager) InjectMaterials(wsDir string, materials []MaterialItem
 			name = "material.txt"
 		}
 
-		textContent, err := ExtractTextWithAnchors(name, m.Content)
+		textContent, err := textextract.ExtractTextWithAnchors(name, m.Content)
 		if err != nil || strings.TrimSpace(textContent) == "" {
 			textContent = string(m.Content)
 		}

internal/squad/extract.go

@@ -1,183 +1,12 @@
 package squad
 
 import (
-	"archive/zip"
-	"bytes"
-	"encoding/xml"
 	"fmt"
-	"io"
-	"path/filepath"
 	"strings"
-	"unicode/utf8"
 
 	"chat-agent-system/internal/workflowdef"
 )
 
-// ExtractTextWithAnchors 从不同格式材料中提取纯文本，并自动注入物理页码锚点 <!-- page N -->
-func ExtractTextWithAnchors(filename string, data []byte) (string, error) {
-	if len(data) == 0 {
-		return "", nil
-	}
-
-	ext := strings.ToLower(filepath.Ext(filename))
-	switch ext {
-	case ".txt", ".md", ".json", ".yaml", ".yml":
-		return string(data), nil
-	case ".docx":
-		txt, err := extractTextFromDOCX(data)
-		if err == nil && len(strings.TrimSpace(txt)) > 0 {
-			return injectPageAnchorsForText(txt), nil
-		}
-		// 降级：从二进制中提取可见字符
-		return injectPageAnchorsForText(extractAsciiUtf8Strings(data)), nil
-	default:
-		// 通用降级
-		return injectPageAnchorsForText(extractAsciiUtf8Strings(data)), nil
-	}
-}
-
-// injectPageAnchorsForText 将连续文本按约 1200 字符切分，并注入 <!-- page N --> 锚点
-func injectPageAnchorsForText(raw string) string {
-	raw = strings.TrimSpace(raw)
-	if raw == "" {
-		return ""
-	}
-
-	// 若原始文本中包含换页符 \f
-	if strings.Contains(raw, "\f") {
-		pages := strings.Split(raw, "\f")
-		var sb strings.Builder
-		for i, page := range pages {
-			pTrim := strings.TrimSpace(page)
-			if pTrim == "" {
-				continue
-			}
-			sb.WriteString(fmt.Sprintf("\n<!-- page %d -->\n%s\n", i+1, pTrim))
-		}
-		return strings.TrimSpace(sb.String())
-	}
-
-	// 否则按段落累加约 1200 字符为一页
-	paragraphs := strings.Split(raw, "\n")
-	var sb strings.Builder
-	currentPage := 1
-	currentLen := 0
-
-	sb.WriteString(fmt.Sprintf("<!-- page %d -->\n", currentPage))
-	for _, p := range paragraphs {
-		pTrim := strings.TrimRight(p, "\r\t ")
-		pLen := utf8.RuneCountInString(pTrim)
-		if currentLen > 0 && currentLen+pLen > 1200 {
-			currentPage++
-			sb.WriteString(fmt.Sprintf("\n<!-- page %d -->\n", currentPage))
-			currentLen = 0
-		}
-		sb.WriteString(pTrim)
-		sb.WriteString("\n")
-		currentLen += pLen + 1
-	}
-
-	return strings.TrimSpace(sb.String())
-}
-
-// extractTextFromDOCX 解析 docx 的 word/document.xml 提取段落文本
-func extractTextFromDOCX(data []byte) (string, error) {
-	r, err := zip.NewReader(bytes.NewReader(data), int64(len(data)))
-	if err != nil {
-		return "", err
-	}
-
-	var docFile *zip.File
-	for _, f := range r.File {
-		if f.Name == "word/document.xml" {
-			docFile = f
-			break
-		}
-	}
-	if docFile == nil {
-		return "", fmt.Errorf("word/document.xml not found in docx")
-	}
-
-	rc, err := docFile.Open()
-	if err != nil {
-		return "", err
-	}
-	defer rc.Close()
-
-	xmlBytes, err := io.ReadAll(rc)
-	if err != nil {
-		return "", err
-	}
-
-	decoder := xml.NewDecoder(bytes.NewReader(xmlBytes))
-	var sb strings.Builder
-	inParagraph := false
-
-	for {
-		tok, err := decoder.Token()
-		if err != nil {
-			break
-		}
-		switch elem := tok.(type) {
-		case xml.StartElement:
-			if elem.Name.Local == "p" {
-				inParagraph = true
-			} else if elem.Name.Local == "br" {
-				for _, attr := range elem.Attr {
-					if attr.Name.Local == "type" && attr.Value == "page" {
-						sb.WriteString("\f")
-					}
-				}
-			} else if elem.Name.Local == "lastRenderedPageBreak" {
-				sb.WriteString("\f")
-			}
-		case xml.EndElement:
-			if elem.Name.Local == "p" {
-				if inParagraph {
-					sb.WriteString("\n")
-					inParagraph = false
-				}
-			}
-		case xml.CharData:
-			sb.Write(elem)
-		}
-	}
-
-	return sb.String(), nil
-}
-
-// extractAsciiUtf8Strings 降级算法：从二进制流中提取连续的有效可读 UTF-8 文本
-func extractAsciiUtf8Strings(data []byte) string {
-	var sb strings.Builder
-	var cur bytes.Buffer
-
-	flush := func() {
-		if cur.Len() >= 4 {
-			s := cur.String()
-			s = strings.TrimSpace(s)
-			if s != "" {
-				sb.WriteString(s)
-				sb.WriteString("\n")
-			}
-		}
-		cur.Reset()
-	}
-
-	for i := 0; i < len(data); {
-		r, size := utf8.DecodeRune(data[i:])
-		if size > 0 && r != utf8.RuneError && (r >= 32 || r == '\n' || r == '\t' || r == '\r') {
-			cur.WriteRune(r)
-			i += size
-		} else {
-			flush()
-			i++
-		}
-	}
-	flush()
-
-	return sb.String()
-}
-
 // ExtractAdvisorBriefing 从 output.md 与黑板事实中提取 B 轨业务参谋决策锦囊
 func ExtractAdvisorBriefing(taskKey string, markdownBody string, fields map[string]string) *AdvisorBriefing {
 	if fields == nil {

internal/squad/service.go

@@ -10,7 +10,6 @@ import (
 	"time"
 
 	"chat-agent-system/internal/agent"
-	"chat-agent-system/internal/quote"
 	"chat-agent-system/internal/workflowdef"
 )
 
@@ -119,6 +118,20 @@ type Options struct {
 	// NewBackend 由调用方注入的后端工厂（Core 装配：凭证、环境、并发上限
 	// 留在产品侧）。nil 时返回错误，不静默降级 Stub。
 	NewBackend func(name string) agent.Backend
+	// TaskPreparer 为可选的任务准备钩子（KTD1：报价领域规则、核算与 xlsx
+	// 资产归 Core；Core 只做计算并返回产物，工作区文件由 squad 统一写入）。
+	// nil 或返回 nil 表示无预处理。
+	TaskPreparer func(workDir string, req SquadRunRequest) (*TaskPreparation, error)
+}
+
+// TaskPreparation 是领域准备钩子的产物：附件与工作区内回写内容。
+// 路径均为工作区相对路径；物理写入由 squad 执行（工作区单写者）。
+type TaskPreparation struct {
+	Attachment *Attachment
+	Backfills  map[string][]byte
+	// MirrorTemplateToOutput 为 true 时，template.md 回填内容同时镜像到
+	// output.md（工作区产物镜像语义归 squad，Core 不直接命名 output.md）。
+	MirrorTemplateToOutput bool
 }
 
 func (o Options) withDefaults() Options {
@@ -265,12 +278,23 @@ func (s *Service) ExecuteTask(ctx context.Context, req SquadRunRequest) (*SquadR
 		return nil, fmt.Errorf("prepare workspace: %w", err)
 	}
 
-	// 2. 若为 CDO 报价任务，先执行 Excel 报价核算引擎并回填
+	// 2. 任务领域预处理（如 CDO 报价核算+xlsx 回填）：Core 计算，squad 写入
 	var attachments []Attachment
-	if workflowdef.SameTaskKey(req.TaskKey, "cdo_quote") {
-		att, err := s.handleCDOQuotePreparation(workDir, req)
-		if err == nil && att != nil {
-			attachments = append(attachments, *att)
+	if s.opts.TaskPreparer != nil {
+		prep, err := s.opts.TaskPreparer(workDir, req)
+		if err == nil && prep != nil {
+			for rel, content := range prep.Backfills {
+				_ = os.MkdirAll(filepath.Dir(filepath.Join(workDir, rel)), 0o755)
+				_ = os.WriteFile(filepath.Join(workDir, rel), content, 0o644)
+			}
+			if prep.MirrorTemplateToOutput {
+				if filled, ok := prep.Backfills["template.md"]; ok {
+					_ = os.WriteFile(filepath.Join(workDir, "output.md"), filled, 0o644)
+				}
+			}
+			if prep.Attachment != nil {
+				attachments = append(attachments, *prep.Attachment)
+			}
 		}
 	}
 
@@ -535,45 +559,6 @@ func (s *Service) ResumeOrModifyWorkspace(ctx context.Context, req ModifyWorkflo
 	return s.ExecuteWorkflow(ctx, req.WorkDir, backendName, opts)
 }
 
-func (s *Service) handleCDOQuotePreparation(workDir string, req SquadRunRequest) (*Attachment, error) {
-	xlsxPath := filepath.Join(workDir, "CDO报价核算-V01.xlsx")
-	artifactXlsxPath := filepath.Join(workDir, "artifacts", "CDO报价核算-V01.xlsx")
-
-	in := quote.Input{
-		CustomerName: req.CustomerName,
-		ProductName:  req.ProjectName,
-		Hours: map[string]float64{
-			"结构工程师": 320,
-			"硬件工程师": 320,
-			"软件工程师": 480,
-			"项目经理":  160,
-		},
-	}
-	summary, err := quote.CalculateAndFill(in, "templates/xlsx/cdo_quote.xlsx", xlsxPath)
-	if err != nil {
-		return nil, err
-	}
-
-	data, err := os.ReadFile(xlsxPath)
-	if err != nil {
-		return nil, err
-	}
-	_ = os.WriteFile(artifactXlsxPath, data, 0o644)
-
-	// 回填 template.md 中的报价数据
-	tmplPath := filepath.Join(workDir, "template.md")
-	if tmplBytes, err := os.ReadFile(tmplPath); err == nil {
-		filled := BackfillCDOQuoteMarkdown(string(tmplBytes), summary)
-		_ = os.WriteFile(tmplPath, []byte(filled), 0o644)
-		_ = os.WriteFile(filepath.Join(workDir, "output.md"), []byte(filled), 0o644)
-	}
-
-	return &Attachment{
-		Filename:    "CDO报价核算-V01.xlsx",
-		ContentType: "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
-		Data:        data,
-	}, nil
-}
 
 func (s *Service) loadWorkspaceMeta(wsDir string) (WorkspaceMetadata, error) {
 	p := filepath.Join(wsDir, "workspace.json")

internal/squad/workspace_adapter.go

@@ -1,15 +0,0 @@
-package squad
-
-import "chat-agent-system/internal/workspace"
-
-// WorkspaceRefForRun is the only squad→workspace DTO. Physical paths stay inside workspace.
-func WorkspaceRefForRun(runID string, projectID int64, env, token string) workspace.WorkspaceRef {
-	return workspace.WorkspaceRef{
-		ID:            "run-" + runID,
-		SchemaVersion: workspace.SchemaVersion,
-		FencingToken:  token,
-		ProjectScope:  projectID,
-		RunID:         runID,
-		Environment:   env,
-	}
-}

internal/squad/workspace_context_build.go

@@ -1,6 +1,7 @@
 package squad
 
 import (
+	"chat-agent-system/internal/textextract"
 	"fmt"
 	"os"
 	"path/filepath"
@@ -68,7 +69,7 @@ func (e *WorkspaceEngine) buildContextSystem(workDir string, req WorkspacePrepar
 			}
 
 			// 自动提取纯文本并注入页码锚点 <!-- page N -->
-			textContent, err := ExtractTextWithAnchors(name, m.Content)
+			textContent, err := textextract.ExtractTextWithAnchors(name, m.Content)
 			if err != nil || strings.TrimSpace(textContent) == "" {
 				textContent = string(m.Content)
 			}

internal/textextract/extract.go

@@ -0,0 +1,178 @@
+package textextract
+
+import (
+	"archive/zip"
+	"bytes"
+	"encoding/xml"
+	"fmt"
+	"io"
+	"path/filepath"
+	"strings"
+	"unicode/utf8"
+
+)
+
+// ExtractTextWithAnchors 从不同格式材料中提取纯文本，并自动注入物理页码锚点 <!-- page N -->
+func ExtractTextWithAnchors(filename string, data []byte) (string, error) {
+	if len(data) == 0 {
+		return "", nil
+	}
+
+	ext := strings.ToLower(filepath.Ext(filename))
+	switch ext {
+	case ".txt", ".md", ".json", ".yaml", ".yml":
+		return string(data), nil
+	case ".docx":
+		txt, err := extractTextFromDOCX(data)
+		if err == nil && len(strings.TrimSpace(txt)) > 0 {
+			return injectPageAnchorsForText(txt), nil
+		}
+		// 降级：从二进制中提取可见字符
+		return injectPageAnchorsForText(extractAsciiUtf8Strings(data)), nil
+	default:
+		// 通用降级
+		return injectPageAnchorsForText(extractAsciiUtf8Strings(data)), nil
+	}
+}
+
+// injectPageAnchorsForText 将连续文本按约 1200 字符切分，并注入 <!-- page N --> 锚点
+func injectPageAnchorsForText(raw string) string {
+	raw = strings.TrimSpace(raw)
+	if raw == "" {
+		return ""
+	}
+
+	// 若原始文本中包含换页符 \f
+	if strings.Contains(raw, "\f") {
+		pages := strings.Split(raw, "\f")
+		var sb strings.Builder
+		for i, page := range pages {
+			pTrim := strings.TrimSpace(page)
+			if pTrim == "" {
+				continue
+			}
+			sb.WriteString(fmt.Sprintf("\n<!-- page %d -->\n%s\n", i+1, pTrim))
+		}
+		return strings.TrimSpace(sb.String())
+	}
+
+	// 否则按段落累加约 1200 字符为一页
+	paragraphs := strings.Split(raw, "\n")
+	var sb strings.Builder
+	currentPage := 1
+	currentLen := 0
+
+	sb.WriteString(fmt.Sprintf("<!-- page %d -->\n", currentPage))
+	for _, p := range paragraphs {
+		pTrim := strings.TrimRight(p, "\r\t ")
+		pLen := utf8.RuneCountInString(pTrim)
+		if currentLen > 0 && currentLen+pLen > 1200 {
+			currentPage++
+			sb.WriteString(fmt.Sprintf("\n<!-- page %d -->\n", currentPage))
+			currentLen = 0
+		}
+		sb.WriteString(pTrim)
+		sb.WriteString("\n")
+		currentLen += pLen + 1
+	}
+
+	return strings.TrimSpace(sb.String())
+}
+
+// extractTextFromDOCX 解析 docx 的 word/document.xml 提取段落文本
+func extractTextFromDOCX(data []byte) (string, error) {
+	r, err := zip.NewReader(bytes.NewReader(data), int64(len(data)))
+	if err != nil {
+		return "", err
+	}
+
+	var docFile *zip.File
+	for _, f := range r.File {
+		if f.Name == "word/document.xml" {
+			docFile = f
+			break
+		}
+	}
+	if docFile == nil {
+		return "", fmt.Errorf("word/document.xml not found in docx")
+	}
+
+	rc, err := docFile.Open()
+	if err != nil {
+		return "", err
+	}
+	defer rc.Close()
+
+	xmlBytes, err := io.ReadAll(rc)
+	if err != nil {
+		return "", err
+	}
+
+	decoder := xml.NewDecoder(bytes.NewReader(xmlBytes))
+	var sb strings.Builder
+	inParagraph := false
+
+	for {
+		tok, err := decoder.Token()
+		if err != nil {
+			break
+		}
+		switch elem := tok.(type) {
+		case xml.StartElement:
+			if elem.Name.Local == "p" {
+				inParagraph = true
+			} else if elem.Name.Local == "br" {
+				for _, attr := range elem.Attr {
+					if attr.Name.Local == "type" && attr.Value == "page" {
+						sb.WriteString("\f")
+					}
+				}
+			} else if elem.Name.Local == "lastRenderedPageBreak" {
+				sb.WriteString("\f")
+			}
+		case xml.EndElement:
+			if elem.Name.Local == "p" {
+				if inParagraph {
+					sb.WriteString("\n")
+					inParagraph = false
+				}
+			}
+		case xml.CharData:
+			sb.Write(elem)
+		}
+	}
+
+	return sb.String(), nil
+}
+
+// extractAsciiUtf8Strings 降级算法：从二进制流中提取连续的有效可读 UTF-8 文本
+func extractAsciiUtf8Strings(data []byte) string {
+	var sb strings.Builder
+	var cur bytes.Buffer
+
+	flush := func() {
+		if cur.Len() >= 4 {
+			s := cur.String()
+			s = strings.TrimSpace(s)
+			if s != "" {
+				sb.WriteString(s)
+				sb.WriteString("\n")
+			}
+		}
+		cur.Reset()
+	}
+
+	for i := 0; i < len(data); {
+		r, size := utf8.DecodeRune(data[i:])
+		if size > 0 && r != utf8.RuneError && (r >= 32 || r == '\n' || r == '\t' || r == '\r') {
+			cur.WriteRune(r)
+			i += size
+		} else {
+			flush()
+			i++
+		}
+	}
+	flush()
+
+	return sb.String()
+}