refactor: remove unused private Go helpers

docs/code-slimming-audit.md

@@ -86,6 +86,17 @@
 - 新增 15 项真实 composable 行为测试，覆盖两个入口、接口路由、缓存、引用抽屉、请求竞争、计时和 Vue 挂载/卸载生命周期。
 - `scripts/verify_frontend_pr.sh` 通过：948 项测试通过，1 项原有浏览器场景测试跳过，类型检查和生产构建通过。嵌入消息 template/style 与本批基线逐字节一致；未做浏览器视觉验收，未修改或测试后端。
 
+## 第五批已实施：Go 未引用私有函数
+
+基于第四批合入后的 `d645334d0`，逐包核实原有 16 个候选，全部确认无调用；同时删除仅被候选使用的 `collectTableAliases` 与 `escapeDoubleQuotes`。共移除 18 个私有函数和 3 个失效 import，生产 Go 源码净减少 235 行。
+
+- 使用 Go AST 检查候选所属 12 个包目录中的 894 个 Go 文件，包括测试、带构建标签和平台后缀的源码；删除集合以外没有对应标识符引用。全仓搜索同时检查文档、脚本和特殊链接引用。
+- 对修改文件逐函数比较：453 个保留函数的签名与函数体完全一致。Qdrant 的 `tokenizeQuery`、Agent 工具包的 `formatFileSize`、JSON 解析包的 `formatValue` 等同名活跃实现继续保留。
+- 更新分块配置相关注释和开发文档，指向仍在使用的 `buildSplitterConfigFromChunking` / `NormalizeSplitterConfig`；迁移历史注释保留旧名称。
+- 13 个受影响包执行 `go test -count=1`：12 个包通过，微信适配包无测试文件但编译通过；3,529 项顶层测试通过、1 项原有测试跳过，计入子测试为 5,274 项通过。跳过项为需要可替换连接探测或真实后端的向量存储创建测试。
+- `integration,e2b_integration,docker_integration` 标签下的 sandbox/tools 测试代码编译通过，未执行需要外部服务的集成测试。未修改前端，未运行前端或浏览器检查。
+- 本批只删除无调用代码，复用现有包测试和编译检查，没有添加仅断言函数不存在的测试。
+
 ## 后续优先级
 
 | 优先级 | 证据 | 建议边界 | 验证重点 |
@@ -100,24 +111,24 @@
 
 ### 后端重复的具体判断
 
-- Qdrant 与 Weaviate 的 `tokenizeQuery` 函数体相同，但只有 Qdrant 的关键字检索调用它；Weaviate 使用 `WithQuery(params.Query)`。后续应验证并删除 Weaviate 的失效函数，而非为了它增加共享分词层。
+- Qdrant 与 Weaviate 的 `tokenizeQuery` 函数体相同，但只有 Qdrant 的关键字检索调用它；Weaviate 使用 `WithQuery(params.Query)`。第五批已删除 Weaviate 的失效函数，保留 Qdrant 实现。
 - IMA、语雀的 `sanitizeFileName` 函数体相同，可以共享；RSS 的近似实现另外处理首尾空白和换行，合并时必须保留这些差异。
 - Milvus/Qdrant/Weaviate 的结果映射体相似，但接收不同后端类型。当前各约 17 行，为此引入通用接口或泛型转换层未必减少维护成本。
 - 终端和桌面 WebSocket ticket handler 重复检查会话、用户、租户和 token，但签发方式不同。后续可共享前置身份校验，保留 ticket 和连接生命周期各自的契约。
 - 资源权限已经有 `internal/application/access`；继续沿已有授权边界收敛，避免新建与其并行的权限工具层。
 
-### 未引用 Go 私有自由函数候选
+### 第五批已核实并删除的 Go 私有自由函数
 
-扫描发现 16 个，第一批暂未改动后端。后续逐包确认调用、构建入口和测试后处理：
+初次扫描的 16 个候选和 2 个仅被候选调用的辅助函数已清理：
 
 | 文件（相对 `internal`） | 函数 |
 | --- | --- |
 | `application/repository/retriever/weaviate/repository.go` | `tokenizeQuery` |
 | `im/wechat/crypto.go` | `encryptAES128ECB` |
-| `application/repository/retriever/milvus/filter.go` | `formatValue` |
+| `application/repository/retriever/milvus/filter.go` | `formatValue`、`escapeDoubleQuotes` |
 | `agent/tools/todo_write.go` | `getStringArrayField`、`getStringField` |
 | `agent/prompts.go` | `formatFileSize` |
-| `utils/inject.go` | `extractTableAliasMap` |
+| `utils/inject.go` | `extractTableAliasMap`、`collectTableAliases` |
 | `application/service/wiki_ingest_dedup.go` | `countEntityConceptPages` |
 | `agent/tools/sandbox_ls.go` | `relativeSkillFileFromImagePath` |
 | `infrastructure/docparser/json_converter.go` | `indentJSON` |
@@ -140,4 +151,4 @@
 - 构建仍报告大 chunk 提示；本轮未以 bundle 体积为目标，也没有测量构建前后的体积差异。
 - 未修改后端，未运行后端测试；未做浏览器视觉验收。
 
-下一批优先逐包核实并清理未引用 Go 私有函数候选，再处理后端具体重复逻辑。涉及聊天、任务重试、权限或共享状态的改动应单独成批，以可验证的行为等价为边界。
+下一批优先处理 IMA、语雀等外部来源的重复文件名清理逻辑，核实调用与差异后再决定共享边界。涉及聊天、任务重试、权限或共享状态的改动应单独成批，以可验证的行为等价为边界。

internal/agent/prompts.go

@@ -11,24 +11,6 @@ import (
 	"github.com/Tencent/WeKnora/internal/types"
 )
 
-// formatFileSize formats file size in human-readable format
-func formatFileSize(size int64) string {
-	const (
-		KB = 1024
-		MB = 1024 * KB
-		GB = 1024 * MB
-	)
-
-	if size < KB {
-		return fmt.Sprintf("%d B", size)
-	} else if size < MB {
-		return fmt.Sprintf("%.2f KB", float64(size)/KB)
-	} else if size < GB {
-		return fmt.Sprintf("%.2f MB", float64(size)/MB)
-	}
-	return fmt.Sprintf("%.2f GB", float64(size)/GB)
-}
-
 // formatDocSummary cleans and truncates document summaries for table display
 func formatDocSummary(summary string, maxLen int) string {
 	cleaned := strings.TrimSpace(summary)

internal/agent/tools/sandbox_ls.go

@@ -281,18 +281,6 @@ func inspectablePathError(requested string) string {
 	return base + ". Use read_file with a listed skill:// resource for skill packages."
 }
 
-func relativeSkillFileFromImagePath(clean, skillName string) string {
-	dir, err := sandbox.SkillDirFor(skillName)
-	if err != nil || clean == dir {
-		return ""
-	}
-	prefix := dir + "/"
-	if strings.HasPrefix(clean, prefix) {
-		return strings.TrimPrefix(clean, prefix)
-	}
-	return ""
-}
-
 // matchingInspectableRoot returns the allowlisted root that contains
 // clean, or ("", false) when the path sits outside every root.
 func matchingInspectableRoot(clean string) (string, bool) {

internal/agent/tools/todo_write.go

@@ -199,32 +199,6 @@ func (t *TodoWriteTool) Execute(ctx context.Context, args json.RawMessage) (*typ
 	}, nil
 }
 
-// Helper function to safely get string field from map
-func getStringField(m map[string]interface{}, key string) string {
-	if val, ok := m[key].(string); ok {
-		return val
-	}
-	return ""
-}
-
-// Helper function to safely get string array field from map
-func getStringArrayField(m map[string]interface{}, key string) []string {
-	if val, ok := m[key].([]interface{}); ok {
-		result := make([]string, 0, len(val))
-		for _, item := range val {
-			if str, ok := item.(string); ok {
-				result = append(result, str)
-			}
-		}
-		return result
-	}
-	// Handle legacy string format for backward compatibility
-	if val, ok := m[key].(string); ok && val != "" {
-		return []string{val}
-	}
-	return []string{}
-}
-
 // generatePlanOutput generates a formatted plan output
 func generatePlanOutput(task string, steps []PlanStep) string {
 	output := "Plan created\n\n"

internal/application/repository/retriever/milvus/filter.go

@@ -6,7 +6,6 @@ import (
 	"maps"
 	"reflect"
 	"strings"
-	"time"
 )
 
 const (
@@ -204,33 +203,6 @@ func (c *filter) convertBetweenCondition(
 	}, nil
 }
 
-func formatValue(value any) string {
-	switch v := value.(type) {
-	case string:
-		return fmt.Sprintf("\"%s\"", escapeDoubleQuotes(v))
-	case int, int8, int16, int32, int64:
-		return fmt.Sprintf("%d", v)
-	case uint, uint8, uint16, uint32, uint64:
-		return fmt.Sprintf("%d", v)
-	case float32, float64:
-		return fmt.Sprintf("%v", v)
-	case bool:
-		if v {
-			return "true"
-		}
-		return "false"
-	case time.Time:
-		return fmt.Sprintf("%d", v.Unix())
-	default:
-		return fmt.Sprintf("\"%v\"", value)
-	}
-}
-
-// escapeDoubleQuotes escapes double quotes in a string for use in Milvus expressions.
-func escapeDoubleQuotes(s string) string {
-	return strings.ReplaceAll(s, "\"", "\\\"")
-}
-
 // convertParamName converts field name to a valid Milvus template parameter name.
 // Milvus template parameters don't support '.' character, so we replace it with '_'.
 func (c *filter) convertParamName(field string, counter *int) string {

internal/application/repository/retriever/weaviate/repository.go

@@ -6,7 +6,6 @@ import (
 	"maps"
 	"slices"
 	"strings"
-	"unicode/utf8"
 
 	"github.com/Tencent/WeKnora/internal/logger"
 	"github.com/Tencent/WeKnora/internal/types"
@@ -1035,30 +1034,3 @@ func fromWeaviateVectorEmbedding(id string,
 		MatchType:       matchType,
 	}
 }
-
-// tokenizeQuery splits a query string into tokens for OR-based full-text search.
-// It uses jieba for professional Chinese word segmentation.
-func tokenizeQuery(query string) []string {
-	query = strings.TrimSpace(query)
-	if query == "" {
-		return nil
-	}
-
-	// Use jieba for segmentation (search mode for better recall)
-	words := types.Jieba.CutForSearch(query, true)
-
-	// Filter and deduplicate
-	seen := make(map[string]bool)
-	result := make([]string, 0, len(words))
-	for _, word := range words {
-		word = strings.TrimSpace(strings.ToLower(word))
-		// Skip empty, single-char, and already seen words
-		if utf8.RuneCountInString(word) < 2 || seen[word] {
-			continue
-		}
-		seen[word] = true
-		result = append(result, word)
-	}
-
-	return result
-}

internal/application/service/knowledge_process.go

@@ -250,14 +250,8 @@ func markKnowledgeProcessing(knowledge *types.Knowledge, now time.Time) {
 	knowledge.UpdatedAt = now
 }
 
-// buildSplitterConfig creates a SplitterConfig with fallbacks from a KnowledgeBase.
-// Defaults mirror chunker.DefaultChunkSize / DefaultChunkOverlap so behavior is
-// identical whether callers come through this path or invoke the chunker
-// directly with a zero-value config.
-func buildSplitterConfig(kb *types.KnowledgeBase) chunker.SplitterConfig {
-	return buildSplitterConfigFromChunking(kb.ChunkingConfig)
-}
-
+// buildSplitterConfigFromChunking normalizes effective chunking settings with
+// the shared chunker defaults.
 func buildSplitterConfigFromChunking(cc types.ChunkingConfig) chunker.SplitterConfig {
 	return chunker.NormalizeSplitterConfig(chunker.SplitterConfig{
 		ChunkSize:    cc.ChunkSize,

internal/application/service/tenant_skill_source.go

@@ -853,11 +853,6 @@ func getSkillURL(
 	return body, resp.Header.Get("Content-Type"), nil
 }
 
-func normalizeFetchedSkillArchive(body []byte, contentType, subdir string) ([]byte, error) {
-	_, archive, err := normalizeFetchedSkill(body, contentType, subdir)
-	return archive, err
-}
-
 func normalizeFetchedSkill(body []byte, contentType, subdir string) (*SkillBundle, []byte, error) {
 	if looksLikeSkillMarkdown(body) {
 		files := map[string][]byte{"SKILL.md": body}

internal/application/service/wiki_ingest_dedup.go

@@ -67,22 +67,6 @@ type dedupSurface struct {
 	nameGramSets []map[string]struct{}
 }
 
-// countEntityConceptPages returns how many of the given pages are
-// entity- or concept-typed. Used only for logging the prefilter's
-// reduction ratio.
-func countEntityConceptPages(pages []*types.WikiPage) int {
-	n := 0
-	for _, p := range pages {
-		if p == nil {
-			continue
-		}
-		if p.PageType == types.WikiPageTypeEntity || p.PageType == types.WikiPageTypeConcept {
-			n++
-		}
-	}
-	return n
-}
-
 // selectDedupCandidatePages returns the subset of allPages plausibly
 // related to at least one of newItems. Non-entity/concept pages are
 // dropped unconditionally. The returned slice preserves the input order

internal/handler/knowledge.go

@@ -1512,12 +1512,6 @@ func (h *KnowledgeHandler) DownloadKnowledgeFile(c *gin.Context) {
 	}
 }
 
-// mimeTypeByExt returns the MIME type for a given file extension.
-func mimeTypeByExt(filename string) string {
-	ct, _ := secutils.SafeContentTypeByFilename(filename)
-	return ct
-}
-
 // PreviewKnowledgeFile godoc
 // @Summary      预览知识文件
 // @Description  返回知识条目关联的原始文件，Content-Type 根据文件类型设置，用于浏览器内嵌预览

internal/handler/session/helpers.go

@@ -440,11 +440,6 @@ func (h *Handler) writeAgentQueryEvent(
 	}
 }
 
-// getRequestID gets the request ID from gin context
-func getRequestID(c *gin.Context) string {
-	return c.GetString(types.RequestIDContextKey.String())
-}
-
 // Helper function for type assertion with default value
 func getString(m map[string]interface{}, key string) string {
 	if val, ok := m[key].(string); ok {

internal/im/service.go

@@ -193,10 +193,6 @@ func cleanIMContent(ctx context.Context, content string, tenant *types.Tenant, d
 	return content
 }
 
-func imLocalStorageBaseDir() string {
-	return storageurl.LocalStorageBaseDir()
-}
-
 // newIMFileServiceResolver builds a per-message storage backend resolver. The
 // cache lives for one cleanIMContent / outbound message so a long answer does
 // not re-create an SDK client for every reference.

internal/im/wechat/crypto.go

@@ -44,29 +44,3 @@ func decryptAES128ECB(ciphertext, key []byte) ([]byte, error) {
 
 	return plaintext, nil
 }
-
-// encryptAES128ECB encrypts data with AES-128-ECB and PKCS#7 padding.
-// Used for uploading media files to the iLink CDN.
-func encryptAES128ECB(plaintext, key []byte) ([]byte, error) {
-	block, err := aes.NewCipher(key)
-	if err != nil {
-		return nil, fmt.Errorf("new aes cipher: %w", err)
-	}
-
-	bs := block.BlockSize()
-
-	// PKCS#7 padding
-	padLen := bs - len(plaintext)%bs
-	padded := make([]byte, len(plaintext)+padLen)
-	copy(padded, plaintext)
-	for i := len(plaintext); i < len(padded); i++ {
-		padded[i] = byte(padLen)
-	}
-
-	ciphertext := make([]byte, len(padded))
-	for i := 0; i < len(padded); i += bs {
-		block.Encrypt(ciphertext[i:i+bs], padded[i:i+bs])
-	}
-
-	return ciphertext, nil
-}

internal/infrastructure/chunker/splitter.go

@@ -74,10 +74,9 @@ type SplitterConfig struct {
 }
 
 // Default chunk sizing constants. Single source of truth for the entire
-// chunker package and (via knowledge.go::buildSplitterConfig) the
-// knowledge service. The frontend KnowledgeBaseEditorModal mirrors these
-// numbers in its initial form state — keep them in sync if you change
-// either value here.
+// chunker package and the knowledge service via NormalizeSplitterConfig.
+// The frontend KnowledgeBaseEditorModal mirrors these numbers in its initial
+// form state — keep them in sync if you change either value here.
 //
 // DefaultChunkSize = 512 chars: ~100–130 English tokens / ~300 Chinese
 // tokens. Validated as a strong baseline by the Vecta Feb-2026 benchmark

internal/infrastructure/chunker/strategy.go

@@ -314,8 +314,8 @@ func runTier(tier StrategyTier, text string, cfg SplitterConfig, profile *DocPro
 }
 
 // ensureDefaults fills in zero-value config fields with sane defaults.
-// Mirrors buildSplitterConfig in internal/application/service/knowledge.go
-// so direct callers of this package get the same numbers.
+// NormalizeSplitterConfig also uses these defaults so service callers and
+// direct callers of this package get the same numbers.
 //
 // When cfg.TokenLimit is set, ChunkSize is clamped to the character budget
 // that fits within that token limit (with a 10% safety factor). This makes

internal/infrastructure/docparser/json_converter.go

@@ -1,7 +1,6 @@
 package docparser
 
 import (
-	"bytes"
 	"encoding/json"
 	"fmt"
 	"sort"
@@ -205,15 +204,6 @@ func formatValue(v interface{}) string {
 	return string(b)
 }
 
-// indentJSON formats raw JSON bytes with indentation.
-func indentJSON(data []byte) (string, error) {
-	var buf bytes.Buffer
-	if err := json.Indent(&buf, data, "", "  "); err != nil {
-		return string(data), err
-	}
-	return buf.String(), nil
-}
-
 // wrapCodeBlock wraps content in a fenced JSON code block.
 func wrapCodeBlock(content string) string {
 	return "```json\n" + content + "\n```"

internal/sandbox/gateway_transport.go

@@ -154,13 +154,8 @@ func (p *SandboxGatewayTransportPool) dataTransport(target string) http.RoundTri
 	return actual.(http.RoundTripper)
 }
 
-// newGatewayDataTransport dials target regardless of the request's authority,
-// mirroring the SDK's proxy rewrite while adding the outbound address guard
-// the SDKs have no notion of.
-func newGatewayDataTransport(target string) *http.Transport {
-	return newGatewayDataTransportWithPolicy(target, DefaultOutboundURLPolicy())
-}
-
+// newGatewayDataTransportWithPolicy dials target regardless of the request's
+// authority, preserving the gateway rewrite and the configured outbound guard.
 func newGatewayDataTransportWithPolicy(target string, policy OutboundURLPolicy) *http.Transport {
 	dialer := &net.Dialer{
 		Timeout:   10 * time.Second,

internal/utils/inject.go

@@ -976,45 +976,6 @@ func ValidateAndSecureSQL(sql string, opts ...SQLValidationOption) (string, *SQL
 	return securedSQL, validationResult, nil
 }
 
-// extractTableAliasMap walks the parse tree to build a table_name→alias map.
-// When a table has an alias (e.g., "knowledge_bases kb"), the map entry is
-// {"knowledge_bases": "kb"}. Without an alias, both key and value are the table name.
-func extractTableAliasMap(parseResult *pg_query.ParseResult) map[string]string {
-	m := make(map[string]string)
-	if len(parseResult.Stmts) == 0 || parseResult.Stmts[0].Stmt == nil {
-		return m
-	}
-	selectStmt := parseResult.Stmts[0].Stmt.GetSelectStmt()
-	if selectStmt == nil {
-		return m
-	}
-	for _, fromItem := range selectStmt.FromClause {
-		collectTableAliases(fromItem, m)
-	}
-	return m
-}
-
-// collectTableAliases recursively collects table→alias mappings from FROM clause nodes.
-func collectTableAliases(node *pg_query.Node, m map[string]string) {
-	if node == nil {
-		return
-	}
-	if rv := node.GetRangeVar(); rv != nil {
-		tableName := strings.ToLower(rv.Relname)
-		alias := tableName
-		if rv.Alias != nil && rv.Alias.Aliasname != "" {
-			alias = strings.ToLower(rv.Alias.Aliasname)
-		}
-		m[tableName] = alias
-		return
-	}
-	if je := node.GetJoinExpr(); je != nil {
-		collectTableAliases(je.Larg, m)
-		collectTableAliases(je.Rarg, m)
-		return
-	}
-}
-
 // walkSQLMessages visits children before their parent so rewriting a SELECT
 // does not revisit trusted predicates added by the server.
 func walkSQLMessages(message protoreflect.Message, visit func(protoreflect.Message) error) error {

website-docs/06-development/03-extension-points.md

@@ -192,7 +192,7 @@ var splitByHeuristics = func(text string, cfg SplitterConfig, _ *DocProfile) []C
    - 增加策略常量（如 `StrategyMine = "mine"`）与新的 `StrategyTier`；
    - 在 `resolveChain`/`resolveChainWithProfile` 的 switch 中为新策略返回 tier 链（建议以 `TierLegacy` 兜底）；
    - 在 `runTier()` 中新增 case；
-3. 调用方无需改动：知识库的 `chunking_config.strategy`（JSONB）经 `internal/application/service/knowledge.go` 的 `buildSplitterConfig` 传入；
+3. 调用方无需改动：知识库的 `chunking_config.strategy`（JSONB）经 `internal/application/service/knowledge_process.go` 的 `buildSplitterConfigFromChunking` 传入；
 4. 用 `SplitWithDiagnostics` 写单测验证 tier 选择与 `ValidateChunks` 验收行为。
 
 ---