feat(index): add markdown/yaml indexing

README.md

@@ -80,6 +80,8 @@ Supports multiple mainstream programming languages:
 | Go | `.go` |
 | Rust | `.rs` |
 | C | `.c`, `.h` |
+| Markdown | `.md`, `.mdx` |
+| YAML | `.yml`, `.yaml` |
 
 ---
 
@@ -168,23 +170,22 @@ Claude will automatically invoke git-ai tools to provide deep analysis. *Enablin
 
 ```mermaid
 graph TB
-    A[Git Repository] -->|On Commit| B["DSR (Deterministic Semantic Record)"]
-    B --> C[".git-ai/dsr/<commit>.json<br/>Semantic Snapshot"]
-    C -->|Index Rebuild| D[LanceDB Vector DB]
-    C -->|Index Rebuild| E[CozoDB Graph DB]
+    A[Git Repository] -->|On Commit| B[DSR\nDeterministic Semantic Record]
+    B --> C[.git-ai/dsr/commit.json\nSemantic Snapshot]
+    C -->|Index Rebuild| D[LanceDB\nVector Database]
+    C -->|Index Rebuild| E[CozoDB\nGraph Database]
     D --> F[MCP Server]
     E --> F
-    F -->|Tool Call| G["AI Agent<br/>Claude Desktop / Trae"]
+    F -->|Tool Call| G[AI Agent\nClaude Desktop / Trae]
     F -->|CLI| H[Developer]
-    C -->|Cross-Version| I{"Semantic Timeline<br/>Traceable, Comparable, Evolvable"}
-
-    style B fill:#e1f5ff
-    style C fill:#e8f5e9
-    style D fill:#fff4e1
-    style E fill:#fff4e1
-    style F fill:#e8f5e9
-    style G fill:#f3e5f5
-    style I fill:#fce4ec
+    C -->|Cross-Version| I[Semantic Timeline\nTraceable · Comparable · Evolvable]
+    style B fill:#e1f5ff,stroke:#333
+    style C fill:#e8f5e9,stroke:#333
+    style D fill:#fff4e1,stroke:#333
+    style E fill:#fff4e1,stroke:#333
+    style F fill:#e8f5e9,stroke:#333
+    style G fill:#f3e5f5,stroke:#333
+    style I fill:#fce4ec,stroke:#333
 ```
 
 **Core Components**:
@@ -296,6 +297,8 @@ We provide carefully designed Agent templates to help AI use git-ai better:
 - [Skill Template](./templates/agents/common/skills/git-ai-mcp/SKILL.md): Guides Agents on how to use tools
 - [Rule Template](./templates/agents/common/rules/git-ai-mcp/RULE.md): Constrains Agent behavior
 
+Skills/Rules docs (Markdown/YAML) are indexed as part of semantic search, so agents can retrieve MCP guidance via `semantic_search`.
+
 One-click install to your project:
 
 ```bash

README.zh-CN.md

@@ -80,6 +80,8 @@ git-ai ai dsr context
 | Go | `.go` |
 | Rust | `.rs` |
 | C | `.c`, `.h` |
+| Markdown | `.md`, `.mdx` |
+| YAML | `.yml`, `.yaml` |
 
 ---
 
@@ -296,6 +298,8 @@ Claude 会自动调用 git-ai 的工具，为你提供深入的分析。
 - [Skill 模版](./templates/agents/common/skills/git-ai-mcp/SKILL.md)：指导 Agent 如何使用工具
 - [Rule 模版](./templates/agents/common/rules/git-ai-mcp/RULE.md)：约束 Agent 的行为
 
+Skills/Rules 文档（Markdown/YAML）会被纳入语义索引，便于通过 `semantic_search` 检索 MCP 指南。
+
 一键安装到你的项目：
 
 ```bash

docs/zh-CN/mcp.md

@@ -24,8 +24,8 @@ git-ai ai serve
 - `unpack_index({ path })`：解包索引归档
 
 ### 检索
-- `search_symbols({ path, query, mode?, case_insensitive?, max_candidates?, limit?, lang?, with_repo_map?, repo_map_max_files?, repo_map_max_symbols?, wiki_dir? })`：符号检索（lang: auto/all/java/ts；可选附带 repo_map）
-- `semantic_search({ path, query, topk?, lang?, with_repo_map?, repo_map_max_files?, repo_map_max_symbols?, wiki_dir? })`：基于 LanceDB + SQ8 的语义检索（lang: auto/all/java/ts；可选附带 repo_map）
+- `search_symbols({ path, query, mode?, case_insensitive?, max_candidates?, limit?, lang?, with_repo_map?, repo_map_max_files?, repo_map_max_symbols?, wiki_dir? })`：符号检索（lang: auto/all/java/ts/python/go/rust/c/markdown/yaml；可选附带 repo_map）
+- `semantic_search({ path, query, topk?, lang?, with_repo_map?, repo_map_max_files?, repo_map_max_symbols?, wiki_dir? })`：基于 LanceDB + SQ8 的语义检索（lang: auto/all/java/ts/python/go/rust/c/markdown/yaml；可选附带 repo_map）
 - `repo_map({ path, max_files?, max_symbols?, wiki_dir? })`：生成 repo map（重要文件/符号排名、引导 Wiki 阅读）
 - `ast_graph_find({ path, prefix, limit?, lang? })`：按名字前缀查找符号定义（大小写不敏感；lang: auto/all/java/ts）
 - `ast_graph_children({ path, id, as_file? })`：列出包含关系的直接子节点（文件→顶层符号、类→方法等）
@@ -122,6 +122,8 @@ semantic_search({ path: "/ABS/PATH/TO/REPO", query: "where is auth handled", top
 
 本仓库提供了 Agent 可直接复用的 Skill/Rule 模板，旨在让 Agent 能够遵循最佳实践来使用上述工具。
 
+这些模板文档（Markdown/YAML）会被索引，便于 Agent 通过 `semantic_search` 检索 MCP 规则与技能说明。
+
 ### YAML 格式模板
 
 - **Skill**: [`templates/agents/common/skills/git-ai/skill.yaml`](../../templates/agents/common/skills/git-ai/skill.yaml) - 指导 Agent 如何使用 git-ai 的 Git-native 语义体系（包含 DSR 约束）与 MCP 工具
@@ -174,6 +176,9 @@ git-ai ai agent install --agent trae
 - **use_dsr_for_history**: 追溯历史必须使用 DSR 工具
 - **respect_dsr_risk**: 重视 DSR 报告的 high 风险变更
 
+文档/规则检索建议：
+- 当问题涉及 MCP/Skill/Rule 时，先用 `semantic_search` 定位对应文档片段，再给出结论。
+
 禁止事项包括：
 - 假设符号位置而不搜索
 - 直接修改未读过的文件

package.json

@@ -1,6 +1,6 @@
 {
   "name": "git-ai",
-  "version": "2.0.0",
+  "version": "2.1.0",
   "main": "dist/index.js",
   "bin": {
     "git-ai": "dist/bin/git-ai.js"

src/commands/graph.ts

@@ -31,7 +31,7 @@ export const graphCommand = new Command('graph')
       .description('Find symbols by name prefix')
       .argument('<prefix>', 'Name prefix (case-insensitive)')
       .option('-p, --path <path>', 'Path inside the repository', '.')
-      .option('--lang <lang>', 'Language: auto|all|java|ts|python|go|rust|c', 'auto')
+      .option('--lang <lang>', 'Language: auto|all|java|ts|python|go|rust|c|markdown|yaml', 'auto')
       .action(async (prefix, options) => {
         const log = createLogger({ component: 'cli', cmd: 'ai graph find' });
         const startedAt = Date.now();
@@ -77,7 +77,7 @@ export const graphCommand = new Command('graph')
       .argument('<name>', 'Symbol name')
       .option('-p, --path <path>', 'Path inside the repository', '.')
       .option('--limit <n>', 'Limit results', '200')
-      .option('--lang <lang>', 'Language: auto|all|java|ts|python|go|rust|c', 'auto')
+      .option('--lang <lang>', 'Language: auto|all|java|ts|python|go|rust|c|markdown|yaml', 'auto')
       .action(async (name, options) => {
         const log = createLogger({ component: 'cli', cmd: 'ai graph refs' });
         const startedAt = Date.now();
@@ -108,7 +108,7 @@ export const graphCommand = new Command('graph')
       .argument('<name>', 'Callee name')
       .option('-p, --path <path>', 'Path inside the repository', '.')
       .option('--limit <n>', 'Limit results', '200')
-      .option('--lang <lang>', 'Language: auto|all|java|ts|python|go|rust|c', 'auto')
+      .option('--lang <lang>', 'Language: auto|all|java|ts|python|go|rust|c|markdown|yaml', 'auto')
       .action(async (name, options) => {
         const log = createLogger({ component: 'cli', cmd: 'ai graph callers' });
         const startedAt = Date.now();
@@ -139,7 +139,7 @@ export const graphCommand = new Command('graph')
       .argument('<name>', 'Caller name')
       .option('-p, --path <path>', 'Path inside the repository', '.')
       .option('--limit <n>', 'Limit results', '200')
-      .option('--lang <lang>', 'Language: auto|all|java|ts|python|go|rust|c', 'auto')
+      .option('--lang <lang>', 'Language: auto|all|java|ts|python|go|rust|c|markdown|yaml', 'auto')
       .action(async (name, options) => {
         const log = createLogger({ component: 'cli', cmd: 'ai graph callees' });
         const startedAt = Date.now();
@@ -173,7 +173,7 @@ export const graphCommand = new Command('graph')
       .option('--depth <n>', 'Max depth', '3')
       .option('--limit <n>', 'Limit results', '500')
       .option('--min-name-len <n>', 'Filter out edges with very short names (default: 1)', '1')
-      .option('--lang <lang>', 'Language: auto|all|java|ts|python|go|rust|c', 'auto')
+      .option('--lang <lang>', 'Language: auto|all|java|ts|python|go|rust|c|markdown|yaml', 'auto')
       .action(async (name, options) => {
         const log = createLogger({ component: 'cli', cmd: 'ai graph chain' });
         const startedAt = Date.now();

src/commands/query.ts

@@ -17,7 +17,7 @@ export const queryCommand = new Command('query')
   .option('--mode <mode>', 'Mode: substring|prefix|wildcard|regex|fuzzy (default: auto)')
   .option('--case-insensitive', 'Case-insensitive matching', false)
   .option('--max-candidates <n>', 'Max candidates to fetch before filtering', '1000')
-  .option('--lang <lang>', 'Language: auto|all|java|ts|python|go|rust|c', 'auto')
+  .option('--lang <lang>', 'Language: auto|all|java|ts|python|go|rust|c|markdown|yaml', 'auto')
   .option('--with-repo-map', 'Attach a lightweight repo map (ranked files + top symbols + wiki links)', false)
   .option('--repo-map-files <n>', 'Max repo map files', '20')
   .option('--repo-map-symbols <n>', 'Max repo map symbols per file', '5')
@@ -110,6 +110,8 @@ function resolveWikiDir(repoRoot: string, wikiOpt: string): string {
 
 function inferLangFromFile(file: string): IndexLang {
   const f = String(file);
+  if (f.endsWith('.md') || f.endsWith('.mdx')) return 'markdown';
+  if (f.endsWith('.yml') || f.endsWith('.yaml')) return 'yaml';
   if (f.endsWith('.java')) return 'java';
   if (f.endsWith('.c') || f.endsWith('.h')) return 'c';
   if (f.endsWith('.go')) return 'go';

src/commands/semantic.ts

@@ -13,7 +13,7 @@ export const semanticCommand = new Command('semantic')
   .argument('<text>', 'Query text')
   .option('-p, --path <path>', 'Path inside the repository', '.')
   .option('-k, --topk <k>', 'Top K results', '10')
-  .option('--lang <lang>', 'Language: auto|all|java|ts|python|go|rust|c', 'auto')
+  .option('--lang <lang>', 'Language: auto|all|java|ts|python|go|rust|c|markdown|yaml', 'auto')
   .option('--with-repo-map', 'Attach a lightweight repo map (ranked files + top symbols + wiki links)', false)
   .option('--repo-map-files <n>', 'Max repo map files', '20')
   .option('--repo-map-symbols <n>', 'Max repo map symbols per file', '5')

src/core/dsr/snapshotParser.ts

@@ -7,6 +7,8 @@ import { CAdapter } from '../parser/c';
 import { GoAdapter } from '../parser/go';
 import { PythonAdapter } from '../parser/python';
 import { RustAdapter } from '../parser/rust';
+import { parseMarkdown } from '../parser/markdown';
+import { parseYaml } from '../parser/yaml';
 
 export interface ParsedSymbolSnapshot {
   symbol: SymbolInfo;
@@ -31,6 +33,8 @@ export class SnapshotCodeParser {
   }
 
   parseContent(filePath: string, content: string): ParseResult {
+    if (isMarkdownFile(filePath)) return parseMarkdown(content, filePath);
+    if (isYamlFile(filePath)) return parseYaml(content, filePath);
     const adapter = this.pickAdapter(filePath);
     if (!adapter) return { symbols: [], refs: [] };
     try {
@@ -59,3 +63,11 @@ export class SnapshotCodeParser {
     return null;
   }
 }
+
+function isMarkdownFile(filePath: string): boolean {
+  return filePath.endsWith('.md') || filePath.endsWith('.mdx');
+}
+
+function isYamlFile(filePath: string): boolean {
+  return filePath.endsWith('.yml') || filePath.endsWith('.yaml');
+}

src/core/indexCheck.ts

@@ -44,7 +44,7 @@ export function resolveLangs(meta: IndexMetaV21 | null, selector: LangSelector):
   const available = filtered.length > 0 ? filtered : (['java', 'ts'] as IndexLang[]);
   if (selector === 'all') return available;
   if (selector !== 'auto') return available.includes(selector) ? [selector] : [];
-  const preferred: IndexLang[] = ['java', 'ts', 'python', 'go', 'rust', 'c'];
+  const preferred: IndexLang[] = ['java', 'ts', 'python', 'go', 'rust', 'c', 'markdown', 'yaml'];
   for (const lang of preferred) {
     if (available.includes(lang)) return [lang];
   }

src/core/indexer.ts

@@ -41,6 +41,8 @@ function buildChunkText(file: string, symbol: { name: string; kind: string; sign
 }
 
 function inferIndexLang(file: string): IndexLang {
+  if (file.endsWith('.md') || file.endsWith('.mdx')) return 'markdown';
+  if (file.endsWith('.yml') || file.endsWith('.yaml')) return 'yaml';
   if (file.endsWith('.java')) return 'java';
   if (file.endsWith('.c') || file.endsWith('.h')) return 'c';
   if (file.endsWith('.go')) return 'go';
@@ -73,7 +75,7 @@ export class IndexerV2 {
 
     const aiIgnore = await loadIgnorePatterns(this.repoRoot, '.aiignore');
     const gitIgnore = await loadIgnorePatterns(this.repoRoot, '.gitignore');
-    const files = await glob('**/*.{ts,tsx,js,jsx,java,c,h,go,py,rs}', {
+    const files = await glob('**/*.{ts,tsx,js,jsx,java,c,h,go,py,rs,md,mdx,yml,yaml}', {
       cwd: this.scanRoot,
       nodir: true,
       ignore: [

src/core/indexerIncremental.ts

@@ -25,6 +25,8 @@ function buildChunkText(file: string, symbol: { name: string; kind: string; sign
 }
 
 function inferIndexLang(file: string): IndexLang {
+  if (file.endsWith('.md') || file.endsWith('.mdx')) return 'markdown';
+  if (file.endsWith('.yml') || file.endsWith('.yaml')) return 'yaml';
   if (file.endsWith('.java')) return 'java';
   if (file.endsWith('.c') || file.endsWith('.h')) return 'c';
   if (file.endsWith('.go')) return 'go';
@@ -34,7 +36,7 @@ function inferIndexLang(file: string): IndexLang {
 }
 
 function isIndexableFile(file: string): boolean {
-  return /\.(ts|tsx|js|jsx|java|c|h|go|py|rs)$/i.test(file);
+  return /\.(ts|tsx|js|jsx|java|c|h|go|py|rs|md|mdx|yml|yaml)$/i.test(file);
 }
 
 function escapeQuotes(s: string): string {

src/core/lancedb.ts

@@ -3,9 +3,9 @@ import { Field, Float32, Int32, Schema, Utf8 } from 'apache-arrow';
 import fs from 'fs-extra';
 import path from 'path';
 
-export type IndexLang = 'java' | 'ts' | 'c' | 'go' | 'python' | 'rust';
+export type IndexLang = 'java' | 'ts' | 'c' | 'go' | 'python' | 'rust' | 'markdown' | 'yaml';
 
-export const ALL_INDEX_LANGS: IndexLang[] = ['java', 'ts', 'c', 'go', 'python', 'rust'];
+export const ALL_INDEX_LANGS: IndexLang[] = ['java', 'ts', 'c', 'go', 'python', 'rust', 'markdown', 'yaml'];
 
 export interface LanceTables {
   db: lancedb.Connection;

src/core/parser.ts

@@ -8,6 +8,8 @@ import { CAdapter } from './parser/c';
 import { GoAdapter } from './parser/go';
 import { PythonAdapter } from './parser/python';
 import { RustAdapter } from './parser/rust';
+import { parseMarkdown } from './parser/markdown';
+import { parseYaml } from './parser/yaml';
 
 export class CodeParser {
   private parser: Parser;
@@ -28,6 +30,8 @@ export class CodeParser {
 
   async parseFile(filePath: string): Promise<ParseResult> {
     const content = await fs.readFile(filePath, 'utf-8');
+    if (isMarkdownFile(filePath)) return parseMarkdown(content, filePath);
+    if (isYamlFile(filePath)) return parseYaml(content, filePath);
     const adapter = this.pickAdapter(filePath);
     if (!adapter) return { symbols: [], refs: [] };
 
@@ -58,3 +62,11 @@ export class CodeParser {
     return null;
   }
 }
+
+function isMarkdownFile(filePath: string): boolean {
+  return filePath.endsWith('.md') || filePath.endsWith('.mdx');
+}
+
+function isYamlFile(filePath: string): boolean {
+  return filePath.endsWith('.yml') || filePath.endsWith('.yaml');
+}