search-router

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Search Tool Router

搜索工具路由

Use the most token-efficient search tool for each query type.

为每种查询类型选用最节省Token的搜索工具。

When to Use

适用场景

Searching for code patterns
Finding where something is implemented
Looking for specific identifiers
Understanding how code works

搜索代码模式
查找功能实现位置
定位特定标识符
理解代码工作原理

Decision Tree

决策树

Query Type?
├── CODE EXPLORATION (symbols, call chains, data flow)
│   → TLDR Search - 95% token savings
│   DEFAULT FOR ALL CODE SEARCH - use instead of Grep
│   Examples: "spawn_agent", "DataPoller", "redis usage"
│   Command: tldr search "query" .
│
├── STRUCTURAL (AST patterns)
│   → AST-grep (/ast-grep-find) - ~50 tokens output
│   Examples: "def foo", "class Bar", "import X", "@decorator"
│
├── SEMANTIC (conceptual questions)
│   → TLDR Semantic - 5-layer embeddings (P6)
│   Examples: "how does auth work", "find error handling patterns"
│   Command: tldr semantic search "query"
│
├── LITERAL (exact text, regex)
│   → Grep tool - LAST RESORT
│   Only when TLDR/AST-grep don't apply
│   Examples: error messages, config values, non-code text
│
└── FULL CONTEXT (need complete understanding)
    → Read tool - 1500+ tokens
    Last resort after finding the right file

查询类型？
├── 代码探索（符号、调用链、数据流）
│   → TLDR Search - 节省95% Token
│   所有代码搜索的默认工具 - 替代Grep使用
│   示例："spawn_agent"、"DataPoller"、"redis usage"
│   命令：tldr search "query" .
│
├── 结构型（AST模式）
│   → AST-grep (/ast-grep-find) - 约50个Token输出
│   示例："def foo"、"class Bar"、"import X"、"@decorator"
│
├── 语义型（概念性问题）
│   → TLDR Semantic - 5层嵌入（P6）
│   示例："how does auth work"、"find error handling patterns"
│   命令：tldr semantic search "query"
│
├── 字面量（精确文本、正则表达式）
│   → Grep工具 - 最后选择
│   仅当TLDR/AST-grep不适用时使用
│   示例：错误信息、配置值、非代码文本
│
└── 完整上下文（需要全面理解）
    → Read工具 - 1500+ Token
    找到目标文件后的最后选择

Token Efficiency Comparison

Token效率对比

Tool	Output Size	Best For
TLDR	~50-500	DEFAULT: Code symbols, call graphs, data flow
TLDR Semantic	~100-300	Conceptual queries (P6, embedding-based)
AST-grep	~50 tokens	Function/class definitions, imports, decorators
Grep	~200-2000	LAST RESORT: Non-code text, regex
Read	~1500+	Full understanding after finding the file

工具	输出大小	最佳适用场景
TLDR	~50-500	默认：代码符号、调用图、数据流
TLDR Semantic	~100-300	概念性查询（基于P6嵌入）
AST-grep	~50 tokens	函数/类定义、导入语句、装饰器
Grep	~200-2000	最后选择：非代码文本、正则表达式
Read	~1500+	找到文件后全面理解内容

Examples

示例

bash

undefined

bash

undefined

CODE EXPLORATION → TLDR (DEFAULT)

代码探索 → TLDR（默认）

tldr search "spawn_agent" . tldr search "redis" . --layer call_graph

STRUCTURAL → AST-grep

结构型 → AST-grep

/ast-grep-find "async def $FUNC($$$):" --lang python

SEMANTIC → TLDR Semantic

语义型 → TLDR Semantic

tldr semantic search "how does authentication work"

LITERAL → Grep (LAST RESORT - prefer TLDR)

字面量 → Grep（最后选择 - 优先使用TLDR）

Grep pattern="check_evocation" path=opc/scripts

FULL CONTEXT → Read (after finding file)

完整上下文 → Read（找到文件后）

Read file_path=opc/scripts/z3_erotetic.py

undefined