Bläddra i källkod

docs: 完善测试文档编写

claude-code-best 3 veckor sedan
förälder
incheckning
a426a50c0e

+ 147 - 0
docs/test-plans/01-tool-system.md

@@ -0,0 +1,147 @@
+# Tool 系统测试计划
+
+## 概述
+
+Tool 系统是 Claude Code 的核心,负责工具的定义、注册、发现和过滤。本计划覆盖 `src/Tool.ts` 中的工具接口与工具函数、`src/tools.ts` 中的注册/过滤逻辑,以及各工具目录下可独立测试的纯函数。
+
+## 被测文件
+
+| 文件 | 关键导出 |
+|------|----------|
+| `src/Tool.ts` | `buildTool`, `toolMatchesName`, `findToolByName`, `getEmptyToolPermissionContext`, `filterToolProgressMessages` |
+| `src/tools.ts` | `parseToolPreset`, `filterToolsByDenyRules`, `getAllBaseTools`, `getTools`, `assembleToolPool` |
+| `src/tools/shared/gitOperationTracking.ts` | `parseGitCommitId`, `detectGitOperation` |
+| `src/tools/shared/spawnMultiAgent.ts` | `resolveTeammateModel`, `generateUniqueTeammateName` |
+| `src/tools/GrepTool/GrepTool.ts` | `applyHeadLimit`, `formatLimitInfo`(内部辅助函数) |
+| `src/tools/FileEditTool/utils.ts` | 字符串匹配/补丁相关纯函数 |
+
+---
+
+## 测试用例
+
+### src/Tool.ts
+
+#### describe('buildTool')
+
+- test('fills in default isEnabled as true') — 不传 isEnabled 时,构建的 tool.isEnabled() 应返回 true
+- test('fills in default isConcurrencySafe as false') — 默认值应为 false(fail-closed)
+- test('fills in default isReadOnly as false') — 默认假设有写操作
+- test('fills in default isDestructive as false') — 默认非破坏性
+- test('fills in default checkPermissions as allow') — 默认 checkPermissions 应返回 `{ behavior: 'allow', updatedInput }`
+- test('fills in default userFacingName from tool name') — userFacingName 默认应返回 tool.name
+- test('preserves explicitly provided methods') — 传入自定义 isEnabled 等方法时应覆盖默认值
+- test('preserves all non-defaultable properties') — name, inputSchema, call, description 等属性原样保留
+
+#### describe('toolMatchesName')
+
+- test('returns true for exact name match') — `{ name: 'Bash' }` 匹配 'Bash'
+- test('returns false for non-matching name') — `{ name: 'Bash' }` 不匹配 'Read'
+- test('returns true when name matches an alias') — `{ name: 'Bash', aliases: ['BashTool'] }` 匹配 'BashTool'
+- test('returns false when aliases is undefined') — `{ name: 'Bash' }` 不匹配 'BashTool'
+- test('returns false when aliases is empty') — `{ name: 'Bash', aliases: [] }` 不匹配 'BashTool'
+
+#### describe('findToolByName')
+
+- test('finds tool by primary name') — 从 tools 列表中按 name 找到工具
+- test('finds tool by alias') — 从 tools 列表中按 alias 找到工具
+- test('returns undefined when no match') — 找不到时返回 undefined
+- test('returns first match when duplicates exist') — 多个同名工具时返回第一个
+
+#### describe('getEmptyToolPermissionContext')
+
+- test('returns default permission mode') — mode 应为 'default'
+- test('returns empty maps and arrays') — additionalWorkingDirectories 为空 Map,rules 为空对象
+- test('returns isBypassPermissionsModeAvailable as false')
+
+#### describe('filterToolProgressMessages')
+
+- test('filters out hook_progress messages') — 移除 type 为 hook_progress 的消息
+- test('keeps tool progress messages') — 保留非 hook_progress 的消息
+- test('returns empty array for empty input')
+- test('handles messages without type field') — data 不含 type 时应保留
+
+---
+
+### src/tools.ts
+
+#### describe('parseToolPreset')
+
+- test('returns "default" for "default" input') — 精确匹配
+- test('returns "default" for "Default" input') — 大小写不敏感
+- test('returns null for unknown preset') — 未知字符串返回 null
+- test('returns null for empty string')
+
+#### describe('filterToolsByDenyRules')
+
+- test('returns all tools when no deny rules') — 空 deny 规则不过滤任何工具
+- test('filters out tools matching blanket deny rule') — deny rule `{ toolName: 'Bash' }` 应移除 Bash
+- test('does not filter tools with content-specific deny rules') — deny rule `{ toolName: 'Bash', ruleContent: 'rm -rf' }` 不移除 Bash(只在运行时阻止特定命令)
+- test('filters MCP tools by server name prefix') — deny rule `mcp__server` 应移除该 server 下所有工具
+- test('preserves tools not matching any deny rule')
+
+#### describe('getAllBaseTools')
+
+- test('returns a non-empty array of tools') — 至少包含核心工具
+- test('each tool has required properties') — 每个工具应有 name, inputSchema, call 等属性
+- test('includes BashTool, FileReadTool, FileEditTool') — 核心工具始终存在
+- test('includes TestingPermissionTool when NODE_ENV is test') — 需设置 env
+
+#### describe('getTools')
+
+- test('returns filtered tools based on permission context') — 根据 deny rules 过滤
+- test('returns simple tools in CLAUDE_CODE_SIMPLE mode') — 仅返回 Bash/Read/Edit
+- test('filters disabled tools via isEnabled') — isEnabled 返回 false 的工具被排除
+
+---
+
+### src/tools/shared/gitOperationTracking.ts
+
+#### describe('parseGitCommitId')
+
+- test('extracts commit hash from git commit output') — 从 `[main abc1234] message` 中提取 `abc1234`
+- test('returns null for non-commit output') — 无法解析时返回 null
+- test('handles various branch name formats') — `[feature/foo abc1234]` 等
+
+#### describe('detectGitOperation')
+
+- test('detects git commit operation') — 命令含 `git commit` 时识别为 commit
+- test('detects git push operation') — 命令含 `git push` 时识别
+- test('returns null for non-git commands') — 非 git 命令返回 null
+- test('detects git merge operation')
+- test('detects git rebase operation')
+
+---
+
+### src/tools/shared/spawnMultiAgent.ts
+
+#### describe('resolveTeammateModel')
+
+- test('returns specified model when provided')
+- test('falls back to default model when not specified')
+
+#### describe('generateUniqueTeammateName')
+
+- test('generates a name when no existing names') — 无冲突时返回基础名
+- test('appends suffix when name conflicts') — 与已有名称冲突时添加后缀
+- test('handles multiple conflicts') — 多次冲突时递增后缀
+
+---
+
+## Mock 需求
+
+| 依赖 | Mock 方式 | 说明 |
+|------|-----------|------|
+| `bun:bundle` (feature) | 已 polyfill 为 `() => false` | 不需额外 mock |
+| `process.env` | `bun:test` mock | 测试 `USER_TYPE`、`NODE_ENV`、`CLAUDE_CODE_SIMPLE` |
+| `getDenyRuleForTool` | mock module | `filterToolsByDenyRules` 测试中需控制返回值 |
+| `isToolSearchEnabledOptimistic` | mock module | `getAllBaseTools` 中条件加载 |
+
+## 集成测试场景
+
+放在 `tests/integration/tool-chain.test.ts`:
+
+### describe('Tool registration and discovery')
+
+- test('getAllBaseTools returns tools that can be found by findToolByName') — 注册 → 查找完整链路
+- test('filterToolsByDenyRules + getTools produces consistent results') — 过滤管线一致性
+- test('assembleToolPool deduplicates built-in and MCP tools') — 合并去重逻辑

+ 416 - 0
docs/test-plans/02-utils-pure-functions.md

@@ -0,0 +1,416 @@
+# 工具函数(纯函数)测试计划
+
+## 概述
+
+覆盖 `src/utils/` 下所有可独立单元测试的纯函数。这些函数无外部依赖,输入输出确定性强,是测试金字塔的底层基石。
+
+## 被测文件
+
+| 文件 | 状态 | 关键导出 |
+|------|------|----------|
+| `src/utils/array.ts` | **已有测试** | intersperse, count, uniq |
+| `src/utils/set.ts` | **已有测试** | difference, intersects, every, union |
+| `src/utils/xml.ts` | 待测 | escapeXml, escapeXmlAttr |
+| `src/utils/hash.ts` | 待测 | djb2Hash, hashContent, hashPair |
+| `src/utils/stringUtils.ts` | 待测 | escapeRegExp, capitalize, plural, firstLineOf, countCharInString, normalizeFullWidthDigits, normalizeFullWidthSpace, safeJoinLines, truncateToLines, EndTruncatingAccumulator |
+| `src/utils/semver.ts` | 待测 | gt, gte, lt, lte, satisfies, order |
+| `src/utils/uuid.ts` | 待测 | validateUuid, createAgentId |
+| `src/utils/format.ts` | 待测 | formatFileSize, formatSecondsShort, formatDuration, formatNumber, formatTokens, formatRelativeTime, formatRelativeTimeAgo |
+| `src/utils/json.ts` | 待测 | safeParseJSON, safeParseJSONC, parseJSONL, addItemToJSONCArray |
+| `src/utils/truncate.ts` | 待测 | truncatePathMiddle, truncateToWidth, truncateStartToWidth, truncateToWidthNoEllipsis, truncate, wrapText |
+| `src/utils/diff.ts` | 待测 | adjustHunkLineNumbers, getPatchFromContents |
+| `src/utils/frontmatterParser.ts` | 待测 | parseFrontmatter, splitPathInFrontmatter, parsePositiveIntFromFrontmatter, parseBooleanFrontmatter, parseShellFrontmatter |
+| `src/utils/file.ts` | 待测(纯函数部分) | convertLeadingTabsToSpaces, addLineNumbers, stripLineNumberPrefix, pathsEqual, normalizePathForComparison |
+| `src/utils/glob.ts` | 待测(纯函数部分) | extractGlobBaseDirectory |
+| `src/utils/tokens.ts` | 待测 | getTokenCountFromUsage |
+| `src/utils/path.ts` | 待测(纯函数部分) | containsPathTraversal, normalizePathForConfigKey |
+
+---
+
+## 测试用例
+
+### src/utils/xml.ts — 测试文件: `src/utils/__tests__/xml.test.ts`
+
+#### describe('escapeXml')
+
+- test('escapes ampersand') — `&` → `&`
+- test('escapes less-than') — `<` → `&lt;`
+- test('escapes greater-than') — `>` → `&gt;`
+- test('does not escape quotes') — `"` 和 `'` 保持原样
+- test('handles empty string') — `""` → `""`
+- test('handles string with no special chars') — `"hello"` 原样返回
+- test('escapes multiple special chars in one string') — `<a & b>` → `&lt;a &amp; b&gt;`
+
+#### describe('escapeXmlAttr')
+
+- test('escapes all xml chars plus quotes') — `"` → `&quot;`, `'` → `&apos;`
+- test('escapes double quotes') — `he said "hi"` 正确转义
+- test('escapes single quotes') — `it's` 正确转义
+
+---
+
+### src/utils/hash.ts — 测试文件: `src/utils/__tests__/hash.test.ts`
+
+#### describe('djb2Hash')
+
+- test('returns consistent hash for same input') — 相同输入返回相同结果
+- test('returns different hashes for different inputs') — 不同输入大概率不同
+- test('returns a 32-bit integer') — 结果在 int32 范围内
+- test('handles empty string') — 空字符串有确定的哈希值
+- test('handles unicode strings') — 中文/emoji 等正确处理
+
+#### describe('hashContent')
+
+- test('returns consistent hash for same content') — 确定性
+- test('returns string result') — 返回值为字符串
+
+#### describe('hashPair')
+
+- test('returns consistent hash for same pair') — 确定性
+- test('order matters') — hashPair(a, b) ≠ hashPair(b, a)
+- test('handles empty strings')
+
+---
+
+### src/utils/stringUtils.ts — 测试文件: `src/utils/__tests__/stringUtils.test.ts`
+
+#### describe('escapeRegExp')
+
+- test('escapes dots') — `.` → `\\.`
+- test('escapes asterisks') — `*` → `\\*`
+- test('escapes brackets') — `[` → `\\[`
+- test('escapes all special chars') — `.*+?^${}()|[]\` 全部转义
+- test('leaves normal chars unchanged') — `hello` 原样
+- test('escaped string works in RegExp') — `new RegExp(escapeRegExp('a.b'))` 精确匹配 `a.b`
+
+#### describe('capitalize')
+
+- test('uppercases first char') — `"foo"` → `"Foo"`
+- test('does NOT lowercase rest') — `"fooBar"` → `"FooBar"`(区别于 lodash capitalize)
+- test('handles single char') — `"a"` → `"A"`
+- test('handles empty string') — `""` → `""`
+- test('handles already capitalized') — `"Foo"` → `"Foo"`
+
+#### describe('plural')
+
+- test('returns singular for n=1') — `plural(1, 'file')` → `'file'`
+- test('returns plural for n=0') — `plural(0, 'file')` → `'files'`
+- test('returns plural for n>1') — `plural(3, 'file')` → `'files'`
+- test('uses custom plural form') — `plural(2, 'entry', 'entries')` → `'entries'`
+
+#### describe('firstLineOf')
+
+- test('returns first line of multi-line string') — `"a\nb\nc"` → `"a"`
+- test('returns full string when no newline') — `"hello"` → `"hello"`
+- test('handles empty string') — `""` → `""`
+- test('handles string starting with newline') — `"\nhello"` → `""`
+
+#### describe('countCharInString')
+
+- test('counts occurrences') — `countCharInString("aabac", "a")` → `3`
+- test('returns 0 when char not found') — `countCharInString("hello", "x")` → `0`
+- test('handles empty string') — `countCharInString("", "a")` → `0`
+- test('respects start position') — `countCharInString("aaba", "a", 2)` → `1`
+
+#### describe('normalizeFullWidthDigits')
+
+- test('converts full-width digits to half-width') — `"0123"` → `"0123"`
+- test('leaves half-width digits unchanged') — `"0123"` → `"0123"`
+- test('mixed content') — `"port 8080"` → `"port 8080"`
+
+#### describe('normalizeFullWidthSpace')
+
+- test('converts ideographic space to regular space') — `"\u3000"` → `" "`
+- test('converts multiple spaces') — `"a\u3000b\u3000c"` → `"a b c"`
+
+#### describe('safeJoinLines')
+
+- test('joins lines with default delimiter') — `["a","b"]` → `"a,b"`
+- test('truncates when exceeding maxSize') — 超限时截断并添加 `...[truncated]`
+- test('handles empty array') — `[]` → `""`
+- test('uses custom delimiter') — delimiter 为 `"\n"` 时按行连接
+
+#### describe('truncateToLines')
+
+- test('returns full text when within limit') — 行数不超限时原样返回
+- test('truncates and adds ellipsis') — 超限时截断并加 `…`
+- test('handles exact limit') — 刚好等于 maxLines 时不截断
+- test('handles single line') — 单行文本不截断
+
+#### describe('EndTruncatingAccumulator')
+
+- test('accumulates strings normally within limit')
+- test('truncates when exceeding maxSize')
+- test('reports truncated status correctly')
+- test('reports totalBytes including truncated content')
+- test('toString includes truncation marker')
+- test('clear resets all state')
+- test('append with Buffer works') — 接受 Buffer 类型
+
+---
+
+### src/utils/semver.ts — 测试文件: `src/utils/__tests__/semver.test.ts`
+
+#### describe('gt / gte / lt / lte')
+
+- test('gt: 2.0.0 > 1.0.0') → true
+- test('gt: 1.0.0 > 1.0.0') → false
+- test('gte: 1.0.0 >= 1.0.0') → true
+- test('lt: 1.0.0 < 2.0.0') → true
+- test('lte: 1.0.0 <= 1.0.0') → true
+- test('handles pre-release versions') — `1.0.0-beta < 1.0.0`
+
+#### describe('satisfies')
+
+- test('version satisfies caret range') — `satisfies('1.2.3', '^1.0.0')` → true
+- test('version does not satisfy range') — `satisfies('2.0.0', '^1.0.0')` → false
+- test('exact match') — `satisfies('1.0.0', '1.0.0')` → true
+
+#### describe('order')
+
+- test('returns -1 for lesser') — `order('1.0.0', '2.0.0')` → -1
+- test('returns 0 for equal') — `order('1.0.0', '1.0.0')` → 0
+- test('returns 1 for greater') — `order('2.0.0', '1.0.0')` → 1
+
+---
+
+### src/utils/uuid.ts — 测试文件: `src/utils/__tests__/uuid.test.ts`
+
+#### describe('validateUuid')
+
+- test('accepts valid v4 UUID') — `'550e8400-e29b-41d4-a716-446655440000'` → 返回 UUID
+- test('returns null for invalid format') — `'not-a-uuid'` → null
+- test('returns null for empty string') — `''` → null
+- test('returns null for null/undefined input')
+- test('accepts uppercase UUIDs') — 大写字母有效
+
+#### describe('createAgentId')
+
+- test('returns string starting with "a"') — 前缀为 `a`
+- test('has correct length') — 前缀 + 16 hex 字符
+- test('generates unique ids') — 连续两次调用结果不同
+
+---
+
+### src/utils/format.ts — 测试文件: `src/utils/__tests__/format.test.ts`
+
+#### describe('formatFileSize')
+
+- test('formats bytes') — `500` → `"500 bytes"`
+- test('formats kilobytes') — `1536` → `"1.5KB"`
+- test('formats megabytes') — `1572864` → `"1.5MB"`
+- test('formats gigabytes') — `1610612736` → `"1.5GB"`
+- test('removes trailing .0') — `1024` → `"1KB"` (不是 `"1.0KB"`)
+
+#### describe('formatSecondsShort')
+
+- test('formats milliseconds to seconds') — `1234` → `"1.2s"`
+- test('formats zero') — `0` → `"0.0s"`
+
+#### describe('formatDuration')
+
+- test('formats seconds') — `5000` → `"5s"`
+- test('formats minutes and seconds') — `65000` → `"1m 5s"`
+- test('formats hours') — `3661000` → `"1h 1m 1s"`
+- test('formats days') — `90061000` → `"1d 1h 1m"`
+- test('returns "0s" for zero') — `0` → `"0s"`
+- test('hideTrailingZeros omits zero components') — `3600000` + `hideTrailingZeros` → `"1h"`
+- test('mostSignificantOnly returns largest unit') — `3661000` + `mostSignificantOnly` → `"1h"`
+
+#### describe('formatNumber')
+
+- test('formats thousands') — `1321` → `"1.3k"`
+- test('formats small numbers as-is') — `900` → `"900"`
+- test('lowercase output') — `1500` → `"1.5k"` (不是 `"1.5K"`)
+
+#### describe('formatTokens')
+
+- test('strips .0 suffix') — `1000` → `"1k"` (不是 `"1.0k"`)
+- test('keeps non-zero decimal') — `1500` → `"1.5k"`
+
+#### describe('formatRelativeTime')
+
+- test('formats past time') — now - 3600s → `"1h ago"` (narrow style)
+- test('formats future time') — now + 3600s → `"in 1h"` (narrow style)
+- test('formats less than 1 second') — now → `"0s ago"`
+- test('uses custom now parameter for deterministic output')
+
+---
+
+### src/utils/json.ts — 测试文件: `src/utils/__tests__/json.test.ts`
+
+#### describe('safeParseJSON')
+
+- test('parses valid JSON') — `'{"a":1}'` → `{ a: 1 }`
+- test('returns null for invalid JSON') — `'not json'` → null
+- test('returns null for null input') — `null` → null
+- test('returns null for undefined input') — `undefined` → null
+- test('returns null for empty string') — `""` → null
+- test('handles JSON with BOM') — BOM 前缀不影响解析
+- test('caches results for repeated calls') — 同一输入不重复解析
+
+#### describe('safeParseJSONC')
+
+- test('parses JSON with comments') — 含 `//` 注释的 JSON 正确解析
+- test('parses JSON with trailing commas') — 宽松模式
+- test('returns null for invalid input')
+- test('returns null for null input')
+
+#### describe('parseJSONL')
+
+- test('parses multiple JSON lines') — `'{"a":1}\n{"b":2}'` → `[{a:1}, {b:2}]`
+- test('skips malformed lines') — 含错误行时跳过该行
+- test('handles empty input') — `""` → `[]`
+- test('handles trailing newline') — 尾部换行不产生空元素
+- test('accepts Buffer input') — Buffer 类型同样工作
+- test('handles BOM prefix')
+
+#### describe('addItemToJSONCArray')
+
+- test('adds item to existing array') — `[1, 2]` + 3 → `[1, 2, 3]`
+- test('creates new array for empty content') — `""` + item → `[item]`
+- test('creates new array for non-array content') — `'"hello"'` + item → `[item]`
+- test('preserves comments in JSONC') — 注释不被丢弃
+- test('handles empty array') — `"[]"` + item → `[item]`
+
+---
+
+### src/utils/diff.ts — 测试文件: `src/utils/__tests__/diff.test.ts`
+
+#### describe('adjustHunkLineNumbers')
+
+- test('shifts line numbers by positive offset') — 所有 hunk 的 oldStart/newStart 增加 offset
+- test('shifts by negative offset') — 负 offset 减少行号
+- test('handles empty hunk array') — `[]` → `[]`
+
+#### describe('getPatchFromContents')
+
+- test('returns empty array for identical content') — 相同内容无差异
+- test('detects added lines') — 新内容多出行
+- test('detects removed lines') — 旧内容缺少行
+- test('detects modified lines') — 行内容变化
+- test('handles empty old content') — 从空文件到有内容
+- test('handles empty new content') — 删除所有内容
+
+---
+
+### src/utils/frontmatterParser.ts — 测试文件: `src/utils/__tests__/frontmatterParser.test.ts`
+
+#### describe('parseFrontmatter')
+
+- test('extracts YAML frontmatter between --- delimiters') — 正确提取 frontmatter 并返回 body
+- test('returns empty frontmatter for content without ---') — 无 frontmatter 时 data 为空
+- test('handles empty content') — `""` 正确处理
+- test('handles frontmatter-only content') — 只有 frontmatter 无 body
+- test('falls back to quoting on YAML parse error') — 无效 YAML 不崩溃
+
+#### describe('splitPathInFrontmatter')
+
+- test('splits comma-separated paths') — `"a.ts, b.ts"` → `["a.ts", "b.ts"]`
+- test('expands brace patterns') — `"*.{ts,tsx}"` → `["*.ts", "*.tsx"]`
+- test('handles string array input') — `["a.ts", "b.ts"]` → `["a.ts", "b.ts"]`
+- test('respects braces in comma splitting') — 大括号内的逗号不作为分隔符
+
+#### describe('parsePositiveIntFromFrontmatter')
+
+- test('returns number for valid positive int') — `5` → `5`
+- test('returns undefined for negative') — `-1` → undefined
+- test('returns undefined for non-number') — `"abc"` → undefined
+- test('returns undefined for float') — `1.5` → undefined
+
+#### describe('parseBooleanFrontmatter')
+
+- test('returns true for true') — `true` → true
+- test('returns true for "true"') — `"true"` → true
+- test('returns false for false') — `false` → false
+- test('returns false for other values') — `"yes"`, `1` → false
+
+#### describe('parseShellFrontmatter')
+
+- test('returns bash for "bash"') — 正确识别
+- test('returns powershell for "powershell"')
+- test('returns undefined for invalid value') — `"zsh"` → undefined
+
+---
+
+### src/utils/file.ts(纯函数部分)— 测试文件: `src/utils/__tests__/file.test.ts`
+
+#### describe('convertLeadingTabsToSpaces')
+
+- test('converts single tab to 2 spaces') — `"\thello"` → `"  hello"`
+- test('converts multiple leading tabs') — `"\t\thello"` → `"    hello"`
+- test('does not convert tabs within line') — `"a\tb"` 保持原样
+- test('handles mixed content')
+
+#### describe('addLineNumbers')
+
+- test('adds line numbers starting from 1') — 每行添加 `N\t` 前缀
+- test('respects startLine parameter') — 从指定行号开始
+- test('handles empty content')
+
+#### describe('stripLineNumberPrefix')
+
+- test('strips tab-prefixed line number') — `"1\thello"` → `"hello"`
+- test('strips padded line number') — `"  1\thello"` → `"hello"`
+- test('returns line unchanged when no prefix')
+
+#### describe('pathsEqual')
+
+- test('returns true for identical paths')
+- test('handles trailing slashes') — 带/不带尾部斜杠视为相同
+- test('handles case sensitivity based on platform')
+
+#### describe('normalizePathForComparison')
+
+- test('normalizes forward slashes')
+- test('resolves path for comparison')
+
+---
+
+### src/utils/glob.ts(纯函数部分)— 测试文件: `src/utils/__tests__/glob.test.ts`
+
+#### describe('extractGlobBaseDirectory')
+
+- test('extracts static prefix from glob') — `"src/**/*.ts"` → `{ baseDir: "src", relativePattern: "**/*.ts" }`
+- test('handles root-level glob') — `"*.ts"` → `{ baseDir: ".", relativePattern: "*.ts" }`
+- test('handles deep static path') — `"src/utils/model/*.ts"` → baseDir 为 `"src/utils/model"`
+- test('handles Windows drive root') — `"C:\\Users\\**\\*.ts"` 正确分割
+
+---
+
+### src/utils/tokens.ts(纯函数部分)— 测试文件: `src/utils/__tests__/tokens.test.ts`
+
+#### describe('getTokenCountFromUsage')
+
+- test('sums input and output tokens') — `{ input_tokens: 100, output_tokens: 50 }` → 150
+- test('includes cache tokens') — cache_creation + cache_read 加入总数
+- test('handles zero values') — 全 0 时返回 0
+
+---
+
+### src/utils/path.ts(纯函数部分)— 测试文件: `src/utils/__tests__/path.test.ts`
+
+#### describe('containsPathTraversal')
+
+- test('detects ../ traversal') — `"../etc/passwd"` → true
+- test('detects mid-path traversal') — `"foo/../../bar"` → true
+- test('returns false for safe paths') — `"src/utils/file.ts"` → false
+- test('returns false for paths containing .. in names') — `"foo..bar"` → false
+
+#### describe('normalizePathForConfigKey')
+
+- test('converts backslashes to forward slashes') — `"src\\utils"` → `"src/utils"`
+- test('leaves forward slashes unchanged')
+
+---
+
+## Mock 需求
+
+本计划中的函数大部分为纯函数,**不需要 mock**。少数例外:
+
+| 函数 | 依赖 | 处理 |
+|------|------|------|
+| `hashContent` / `hashPair` | `Bun.hash` | Bun 运行时下自动可用 |
+| `formatRelativeTime` | `Date` | 使用 `now` 参数注入确定性时间 |
+| `safeParseJSON` | `logError` | 可通过 `shouldLogError: false` 跳过 |
+| `safeParseJSONC` | `logError` | mock `logError` 避免测试输出噪音 |

+ 134 - 0
docs/test-plans/03-context-building.md

@@ -0,0 +1,134 @@
+# Context 构建测试计划
+
+## 概述
+
+Context 构建系统负责组装发送给 Claude API 的系统提示和用户上下文。包括 git 状态获取、CLAUDE.md 文件发现与加载、系统提示拼装三部分。
+
+## 被测文件
+
+| 文件 | 关键导出 |
+|------|----------|
+| `src/context.ts` | `getSystemContext`, `getUserContext`, `getGitStatus`, `setSystemPromptInjection` |
+| `src/utils/claudemd.ts` | `stripHtmlComments`, `getClaudeMds`, `isMemoryFilePath`, `getLargeMemoryFiles`, `filterInjectedMemoryFiles`, `getExternalClaudeMdIncludes`, `hasExternalClaudeMdIncludes`, `processMemoryFile`, `getMemoryFiles` |
+| `src/utils/systemPrompt.ts` | `buildEffectiveSystemPrompt` |
+
+---
+
+## 测试用例
+
+### src/utils/claudemd.ts — 纯函数部分
+
+#### describe('stripHtmlComments')
+
+- test('strips block-level HTML comments') — `"text <!-- comment --> more"` → content 不含注释
+- test('preserves inline content') — 行内文本保留
+- test('preserves code block content') — ` ```html\n<!-- not stripped -->\n``` ` 内的注释不移除
+- test('returns stripped: false when no comments') — 无注释时 stripped 为 false
+- test('returns stripped: true when comments exist')
+- test('handles empty string') — `""` → `{ content: "", stripped: false }`
+- test('handles multiple comments') — 多个注释全部移除
+
+#### describe('getClaudeMds')
+
+- test('assembles memory files with type descriptions') — 不同 type 的文件有不同前缀描述
+- test('includes instruction prompt prefix') — 输出包含指令前缀
+- test('handles empty memory files array') — 空数组返回空字符串或最小前缀
+- test('respects filter parameter') — filter 函数可过滤特定类型
+- test('concatenates multiple files with separators')
+
+#### describe('isMemoryFilePath')
+
+- test('returns true for CLAUDE.md path') — `"/project/CLAUDE.md"` → true
+- test('returns true for .claude/rules/ path') — `"/project/.claude/rules/foo.md"` → true
+- test('returns true for memory file path') — `"~/.claude/memory/foo.md"` → true
+- test('returns false for regular file') — `"/project/src/main.ts"` → false
+- test('returns false for unrelated .md file') — `"/project/README.md"` → false
+
+#### describe('getLargeMemoryFiles')
+
+- test('returns files exceeding 40K chars') — 内容 > MAX_MEMORY_CHARACTER_COUNT 的文件被返回
+- test('returns empty array when all files are small')
+- test('correctly identifies threshold boundary')
+
+#### describe('filterInjectedMemoryFiles')
+
+- test('filters out AutoMem type files') — feature flag 开启时移除自动记忆
+- test('filters out TeamMem type files')
+- test('preserves other types') — 非 AutoMem/TeamMem 的文件保留
+
+#### describe('getExternalClaudeMdIncludes')
+
+- test('returns includes from outside CWD') — 外部 @include 路径被识别
+- test('returns empty array when all includes are internal')
+
+#### describe('hasExternalClaudeMdIncludes')
+
+- test('returns true when external includes exist')
+- test('returns false when no external includes')
+
+---
+
+### src/utils/systemPrompt.ts
+
+#### describe('buildEffectiveSystemPrompt')
+
+- test('returns default system prompt when no overrides') — 无任何覆盖时使用默认提示
+- test('overrideSystemPrompt replaces everything') — override 模式替换全部内容
+- test('customSystemPrompt replaces default') — `--system-prompt` 参数替换默认
+- test('appendSystemPrompt is appended after main prompt') — append 在主提示之后
+- test('agent definition replaces default prompt') — agent 模式使用 agent prompt
+- test('agent definition with append combines both') — agent prompt + append
+- test('override takes precedence over agent and custom') — 优先级最高
+- test('returns array of strings') — 返回值为 SystemPrompt 类型(字符串数组)
+
+---
+
+### src/context.ts — 需 Mock 的部分
+
+#### describe('getGitStatus')
+
+- test('returns formatted git status string') — 包含 branch、status、log、user
+- test('truncates status at 2000 chars') — 超长 status 被截断
+- test('returns null in test environment') — `NODE_ENV=test` 时返回 null
+- test('returns null in non-git directory') — 非 git 仓库返回 null
+- test('runs git commands in parallel') — 多个 git 命令并行执行
+
+#### describe('getSystemContext')
+
+- test('includes gitStatus key') — 返回对象包含 gitStatus
+- test('returns memoized result on subsequent calls') — 多次调用返回同一结果
+- test('skips git when instructions disabled')
+
+#### describe('getUserContext')
+
+- test('includes currentDate key') — 返回对象包含当前日期
+- test('includes claudeMd key when CLAUDE.md exists') — 加载 CLAUDE.md 内容
+- test('respects CLAUDE_CODE_DISABLE_CLAUDE_MDS env') — 设置后不加载 CLAUDE.md
+- test('returns memoized result')
+
+#### describe('setSystemPromptInjection')
+
+- test('clears memoized context caches') — 调用后下次 getSystemContext/getUserContext 重新计算
+- test('injection value is accessible via getSystemPromptInjection')
+
+---
+
+## Mock 需求
+
+| 依赖 | Mock 方式 | 用途 |
+|------|-----------|------|
+| `execFileNoThrow` | `mock.module` | `getGitStatus` 中的 git 命令 |
+| `getMemoryFiles` | `mock.module` | `getUserContext` 中的 CLAUDE.md 加载 |
+| `getCwd` | `mock.module` | 路径解析上下文 |
+| `process.env.NODE_ENV` | 直接设置 | 测试环境检测 |
+| `process.env.CLAUDE_CODE_DISABLE_CLAUDE_MDS` | 直接设置 | 禁用 CLAUDE.md |
+
+## 集成测试场景
+
+放在 `tests/integration/context-build.test.ts`:
+
+### describe('Context assembly pipeline')
+
+- test('getUserContext produces claudeMd containing CLAUDE.md content') — 端到端验证 CLAUDE.md 被正确加载到 context
+- test('buildEffectiveSystemPrompt + getUserContext produces complete prompt') — 系统提示 + 用户上下文完整性
+- test('setSystemPromptInjection invalidates and rebuilds context') — 注入后重新构建上下文

+ 104 - 0
docs/test-plans/04-permission-system.md

@@ -0,0 +1,104 @@
+# 权限系统测试计划
+
+## 概述
+
+权限系统控制工具是否可以执行,包含规则解析器、权限检查管线和权限模式判断。测试重点是纯函数解析器和规则匹配逻辑。
+
+## 被测文件
+
+| 文件 | 关键导出 |
+|------|----------|
+| `src/utils/permissions/permissionRuleParser.ts` | `permissionRuleValueFromString`, `permissionRuleValueToString`, `escapeRuleContent`, `unescapeRuleContent`, `normalizeLegacyToolName`, `getLegacyToolNames` |
+| `src/utils/permissions/PermissionMode.ts` | 权限模式常量和辅助函数 |
+| `src/utils/permissions/permissions.ts` | `hasPermissionsToUseTool`, `getDenyRuleForTool`, `checkRuleBasedPermissions` |
+| `src/types/permissions.ts` | `PermissionMode`, `PermissionBehavior`, `PermissionRule` 类型定义 |
+
+---
+
+## 测试用例
+
+### src/utils/permissions/permissionRuleParser.ts
+
+#### describe('escapeRuleContent')
+
+- test('escapes backslashes first') — `'test\\value'` → `'test\\\\value'`
+- test('escapes opening parentheses') — `'print(1)'` → `'print\\(1\\)'`
+- test('escapes closing parentheses') — `'func()'` → `'func\\(\\)'`
+- test('handles combined escape') — `'echo "test\\nvalue"'` 中的 `\\` 先转义
+- test('handles empty string') — `''` → `''`
+- test('no-op for string without special chars') — `'npm install'` 原样返回
+
+#### describe('unescapeRuleContent')
+
+- test('unescapes parentheses') — `'print\\(1\\)'` → `'print(1)'`
+- test('unescapes backslashes last') — `'test\\\\nvalue'` → `'test\\nvalue'`
+- test('handles empty string')
+- test('roundtrip: escape then unescape returns original') — `unescapeRuleContent(escapeRuleContent(x)) === x`
+
+#### describe('permissionRuleValueFromString')
+
+- test('parses tool name only') — `'Bash'` → `{ toolName: 'Bash' }`
+- test('parses tool name with content') — `'Bash(npm install)'` → `{ toolName: 'Bash', ruleContent: 'npm install' }`
+- test('parses content with escaped parentheses') — `'Bash(python -c "print\\(1\\)")'` → ruleContent 为 `'python -c "print(1)"'`
+- test('treats empty parens as tool-wide rule') — `'Bash()'` → `{ toolName: 'Bash' }`(无 ruleContent)
+- test('treats wildcard content as tool-wide rule') — `'Bash(*)'` → `{ toolName: 'Bash' }`
+- test('normalizes legacy tool names') — `'Task'` → `{ toolName: 'Agent' }`(或对应的 AGENT_TOOL_NAME)
+- test('handles malformed input: no closing paren') — `'Bash(npm'` → 整个字符串作为 toolName
+- test('handles malformed input: content after closing paren') — `'Bash(npm)extra'` → 整个字符串作为 toolName
+- test('handles missing tool name') — `'(foo)'` → 整个字符串作为 toolName
+
+#### describe('permissionRuleValueToString')
+
+- test('serializes tool name only') — `{ toolName: 'Bash' }` → `'Bash'`
+- test('serializes with content') — `{ toolName: 'Bash', ruleContent: 'npm install' }` → `'Bash(npm install)'`
+- test('escapes content with parentheses') — ruleContent 含 `()` 时正确转义
+- test('roundtrip: fromString then toString preserves value') — 往返一致
+
+#### describe('normalizeLegacyToolName')
+
+- test('maps Task to Agent tool name') — `'Task'` → AGENT_TOOL_NAME
+- test('maps KillShell to TaskStop tool name') — `'KillShell'` → TASK_STOP_TOOL_NAME
+- test('maps AgentOutputTool to TaskOutput tool name')
+- test('returns unknown names unchanged') — `'UnknownTool'` → `'UnknownTool'`
+
+#### describe('getLegacyToolNames')
+
+- test('returns legacy names for canonical name') — 给定 AGENT_TOOL_NAME 返回包含 `'Task'`
+- test('returns empty array for name with no legacy aliases')
+
+---
+
+### src/utils/permissions/permissions.ts — 需 Mock
+
+#### describe('getDenyRuleForTool')
+
+- test('returns deny rule matching tool name') — 匹配到 blanket deny 规则时返回
+- test('returns null when no deny rules match') — 无匹配时返回 null
+- test('matches MCP tools by server prefix') — `mcp__server` 规则匹配该 server 下的 MCP 工具
+- test('does not match content-specific deny rules') — 有 ruleContent 的 deny 规则不作为 blanket deny
+
+#### describe('checkRuleBasedPermissions')(集成级别)
+
+- test('deny rule takes precedence over allow') — 同时有 allow 和 deny 时 deny 优先
+- test('ask rule prompts user') — 匹配 ask 规则返回 `{ behavior: 'ask' }`
+- test('allow rule permits execution') — 匹配 allow 规则返回 `{ behavior: 'allow' }`
+- test('passthrough when no rules match') — 无匹配规则返回 passthrough
+
+---
+
+## Mock 需求
+
+| 依赖 | Mock 方式 | 说明 |
+|------|-----------|------|
+| `bun:bundle` (feature) | 已 polyfill | BRIEF_TOOL_NAME 条件加载 |
+| Tool 常量导入 | 实际值 | AGENT_TOOL_NAME 等从常量文件导入 |
+| `appState` | mock object | `hasPermissionsToUseTool` 中的状态依赖 |
+| Tool 对象 | mock object | 模拟 tool 的 name, checkPermissions 等 |
+
+## 集成测试场景
+
+### describe('Permission pipeline end-to-end')
+
+- test('deny rule blocks tool before it runs') — deny 规则在 call 前拦截
+- test('bypassPermissions mode allows all') — bypass 模式下 ask → allow
+- test('dontAsk mode converts ask to deny') — dontAsk 模式下 ask → deny

+ 113 - 0
docs/test-plans/05-model-routing.md

@@ -0,0 +1,113 @@
+# 模型路由测试计划
+
+## 概述
+
+模型路由系统负责 API provider 选择、模型别名解析、模型名规范化和运行时模型决策。测试重点是纯函数和环境变量驱动的逻辑。
+
+## 被测文件
+
+| 文件 | 关键导出 |
+|------|----------|
+| `src/utils/model/aliases.ts` | `MODEL_ALIASES`, `MODEL_FAMILY_ALIASES`, `isModelAlias`, `isModelFamilyAlias` |
+| `src/utils/model/providers.ts` | `APIProvider`, `getAPIProvider`, `isFirstPartyAnthropicBaseUrl` |
+| `src/utils/model/model.ts` | `firstPartyNameToCanonical`, `getCanonicalName`, `parseUserSpecifiedModel`, `normalizeModelStringForAPI`, `getRuntimeMainLoopModel`, `getDefaultMainLoopModelSetting` |
+
+---
+
+## 测试用例
+
+### src/utils/model/aliases.ts
+
+#### describe('isModelAlias')
+
+- test('returns true for "sonnet"') — 有效别名
+- test('returns true for "opus"')
+- test('returns true for "haiku"')
+- test('returns true for "best"')
+- test('returns true for "sonnet[1m]"')
+- test('returns true for "opus[1m]"')
+- test('returns true for "opusplan"')
+- test('returns false for full model ID') — `'claude-sonnet-4-6-20250514'` → false
+- test('returns false for unknown string') — `'gpt-4'` → false
+- test('is case-sensitive') — `'Sonnet'` → false(别名是小写)
+
+#### describe('isModelFamilyAlias')
+
+- test('returns true for "sonnet"')
+- test('returns true for "opus"')
+- test('returns true for "haiku"')
+- test('returns false for "best"') — best 不是 family alias
+- test('returns false for "opusplan"')
+- test('returns false for "sonnet[1m]"')
+
+---
+
+### src/utils/model/providers.ts
+
+#### describe('getAPIProvider')
+
+- test('returns "firstParty" by default') — 无相关 env 时返回 firstParty
+- test('returns "bedrock" when CLAUDE_CODE_USE_BEDROCK is set') — env 为 truthy 值
+- test('returns "vertex" when CLAUDE_CODE_USE_VERTEX is set')
+- test('returns "foundry" when CLAUDE_CODE_USE_FOUNDRY is set')
+- test('bedrock takes precedence over vertex') — 多个 env 同时设置时 bedrock 优先
+
+#### describe('isFirstPartyAnthropicBaseUrl')
+
+- test('returns true when ANTHROPIC_BASE_URL is not set') — 默认 API
+- test('returns true for api.anthropic.com') — `'https://api.anthropic.com'` → true
+- test('returns false for custom URL') — `'https://my-proxy.com'` → false
+- test('returns false for invalid URL') — 非法 URL → false
+- test('returns true for staging URL when USER_TYPE is ant') — `'https://api-staging.anthropic.com'` + ant → true
+
+---
+
+### src/utils/model/model.ts
+
+#### describe('firstPartyNameToCanonical')
+
+- test('maps opus-4-6 full name to canonical') — `'claude-opus-4-6-20250514'` → `'claude-opus-4-6'`
+- test('maps sonnet-4-6 full name') — `'claude-sonnet-4-6-20250514'` → `'claude-sonnet-4-6'`
+- test('maps haiku-4-5') — `'claude-haiku-4-5-20251001'` → `'claude-haiku-4-5'`
+- test('maps 3P provider format') — `'us.anthropic.claude-opus-4-6-v1:0'` → `'claude-opus-4-6'`
+- test('maps claude-3-7-sonnet') — `'claude-3-7-sonnet-20250219'` → `'claude-3-7-sonnet'`
+- test('maps claude-3-5-sonnet') → `'claude-3-5-sonnet'`
+- test('maps claude-3-5-haiku') → `'claude-3-5-haiku'`
+- test('maps claude-3-opus') → `'claude-3-opus'`
+- test('is case insensitive') — `'Claude-Opus-4-6'` → `'claude-opus-4-6'`
+- test('falls back to input for unknown model') — `'unknown-model'` → `'unknown-model'`
+- test('differentiates opus-4 vs opus-4-5 vs opus-4-6') — 更具体的版本优先匹配
+
+#### describe('parseUserSpecifiedModel')
+
+- test('resolves "sonnet" to default sonnet model')
+- test('resolves "opus" to default opus model')
+- test('resolves "haiku" to default haiku model')
+- test('resolves "best" to best model')
+- test('resolves "opusplan" to default sonnet model') — opusplan 默认用 sonnet
+- test('appends [1m] suffix when alias has [1m]') — `'sonnet[1m]'` → 模型名 + `'[1m]'`
+- test('preserves original case for custom model names') — `'my-Custom-Model'` 保留大小写
+- test('handles [1m] suffix on non-alias models') — `'custom-model[1m]'` → `'custom-model[1m]'`
+- test('trims whitespace') — `'  sonnet  '` → 正确解析
+
+#### describe('getRuntimeMainLoopModel')
+
+- test('returns mainLoopModel by default') — 无特殊条件时原样返回
+- test('returns opus in plan mode when opusplan is set') — opusplan + plan mode → opus
+- test('returns sonnet in plan mode when haiku is set') — haiku + plan mode → sonnet 升级
+- test('returns mainLoopModel in non-plan mode') — 非 plan 模式不做替换
+
+---
+
+## Mock 需求
+
+| 依赖 | Mock 方式 | 说明 |
+|------|-----------|------|
+| `process.env.CLAUDE_CODE_USE_BEDROCK/VERTEX/FOUNDRY` | 直接设置/恢复 | provider 选择 |
+| `process.env.ANTHROPIC_BASE_URL` | 直接设置/恢复 | URL 检测 |
+| `process.env.USER_TYPE` | 直接设置/恢复 | staging URL 和 ant 功能 |
+| `getModelStrings()` | mock.module | 返回固定模型 ID |
+| `getMainLoopModelOverride` | mock.module | 会话中模型覆盖 |
+| `getSettings_DEPRECATED` | mock.module | 用户设置中的模型 |
+| `getUserSpecifiedModelSetting` | mock.module | `getRuntimeMainLoopModel` 依赖 |
+| `isModelAllowed` | mock.module | allowlist 检查 |

+ 165 - 0
docs/test-plans/06-message-handling.md

@@ -0,0 +1,165 @@
+# 消息处理测试计划
+
+## 概述
+
+消息处理系统负责消息的创建、查询、规范化和文本提取。覆盖消息类型定义、消息工厂函数、消息过滤/查询工具和 API 规范化管线。
+
+## 被测文件
+
+| 文件 | 关键导出 |
+|------|----------|
+| `src/types/message.ts` | `MessageType`, `Message`, `AssistantMessage`, `UserMessage`, `SystemMessage` 等类型 |
+| `src/utils/messages.ts` | 消息创建、查询、规范化、文本提取等函数(~3100 行) |
+| `src/utils/messages/mappers.ts` | 消息映射工具 |
+
+---
+
+## 测试用例
+
+### src/utils/messages.ts — 消息创建
+
+#### describe('createAssistantMessage')
+
+- test('creates message with type "assistant"') — type 字段正确
+- test('creates message with role "assistant"') — role 正确
+- test('creates message with empty content array') — 默认 content 为空
+- test('generates unique uuid') — 每次调用 uuid 不同
+- test('includes costUsd as 0')
+
+#### describe('createUserMessage')
+
+- test('creates message with type "user"') — type 字段正确
+- test('creates message with provided content') — content 正确传入
+- test('generates unique uuid')
+
+#### describe('createSystemMessage')
+
+- test('creates system message with correct type')
+- test('includes message content')
+
+#### describe('createProgressMessage')
+
+- test('creates progress message with data')
+- test('has correct type "progress"')
+
+---
+
+### src/utils/messages.ts — 消息查询
+
+#### describe('getLastAssistantMessage')
+
+- test('returns last assistant message from array') — 多条消息中返回最后一条 assistant
+- test('returns undefined for empty array')
+- test('returns undefined when no assistant messages exist')
+
+#### describe('hasToolCallsInLastAssistantTurn')
+
+- test('returns true when last assistant has tool_use content') — content 含 tool_use block
+- test('returns false when last assistant has only text')
+- test('returns false for empty messages')
+
+#### describe('isSyntheticMessage')
+
+- test('identifies interrupt message as synthetic') — INTERRUPT_MESSAGE 标记
+- test('identifies cancel message as synthetic')
+- test('returns false for normal user messages')
+
+#### describe('isNotEmptyMessage')
+
+- test('returns true for message with content')
+- test('returns false for message with empty content array')
+- test('returns false for message with empty text content')
+
+---
+
+### src/utils/messages.ts — 文本提取
+
+#### describe('getAssistantMessageText')
+
+- test('extracts text from text blocks') — content 含 `{ type: 'text', text: 'hello' }` 时提取
+- test('returns empty string for non-text content') — 仅含 tool_use 时返回空
+- test('concatenates multiple text blocks')
+
+#### describe('getUserMessageText')
+
+- test('extracts text from string content') — content 为纯字符串
+- test('extracts text from content array') — content 为数组时提取 text 块
+- test('handles empty content')
+
+#### describe('extractTextContent')
+
+- test('extracts text items from mixed content') — 过滤出 type: 'text' 的项
+- test('returns empty array for all non-text content')
+
+---
+
+### src/utils/messages.ts — 规范化
+
+#### describe('normalizeMessages')
+
+- test('converts raw messages to normalized format') — 消息数组规范化
+- test('handles empty array') — `[]` → `[]`
+- test('preserves message order')
+- test('handles mixed message types')
+
+#### describe('normalizeMessagesForAPI')
+
+- test('filters out system messages') — 系统消息不发送给 API
+- test('filters out progress messages')
+- test('filters out attachment messages')
+- test('preserves user and assistant messages')
+- test('reorders tool results to match API expectations')
+- test('handles empty array')
+
+---
+
+### src/utils/messages.ts — 合并
+
+#### describe('mergeUserMessages')
+
+- test('merges consecutive user messages') — 相邻用户消息合并
+- test('does not merge non-consecutive user messages')
+- test('preserves assistant messages between user messages')
+
+#### describe('mergeAssistantMessages')
+
+- test('merges consecutive assistant messages')
+- test('combines content arrays')
+
+---
+
+### src/utils/messages.ts — 辅助函数
+
+#### describe('buildMessageLookups')
+
+- test('builds index by message uuid') — 按 uuid 建立查找表
+- test('returns empty lookups for empty messages')
+- test('handles duplicate uuids gracefully')
+
+---
+
+## Mock 需求
+
+| 依赖 | Mock 方式 | 说明 |
+|------|-----------|------|
+| `crypto.randomUUID` | `mock` 或 spy | 消息创建中的 uuid 生成 |
+| Message 对象 | 手动构造 | 创建符合类型的 mock 消息对象 |
+
+### Mock 消息工厂(放在 `tests/mocks/messages.ts`)
+
+```typescript
+// 通用 mock 消息构造器
+export function mockAssistantMessage(overrides?: Partial<AssistantMessage>): AssistantMessage
+export function mockUserMessage(content: string, overrides?: Partial<UserMessage>): UserMessage
+export function mockSystemMessage(overrides?: Partial<SystemMessage>): SystemMessage
+export function mockToolUseBlock(name: string, input: unknown): ToolUseBlock
+export function mockToolResultMessage(toolUseId: string, content: string): UserMessage
+```
+
+## 集成测试场景
+
+### describe('Message pipeline')
+
+- test('create → normalize → API format produces valid request') — 创建消息 → normalizeMessagesForAPI → 验证输出结构
+- test('tool use and tool result pairing is preserved through normalization')
+- test('merge + normalize handles conversation with interruptions')

+ 112 - 0
docs/test-plans/07-cron.md

@@ -0,0 +1,112 @@
+# Cron 调度测试计划
+
+## 概述
+
+Cron 模块提供 cron 表达式解析、下次运行时间计算和人类可读描述。全部为纯函数,无外部依赖,是最适合单元测试的模块之一。
+
+## 被测文件
+
+| 文件 | 关键导出 |
+|------|----------|
+| `src/utils/cron.ts` | `CronFields`, `parseCronExpression`, `computeNextCronRun`, `cronToHuman` |
+
+---
+
+## 测试用例
+
+### describe('parseCronExpression')
+
+#### 有效表达式
+
+- test('parses wildcard fields') — `'* * * * *'` → 每个字段为完整范围
+- test('parses specific values') — `'30 14 1 6 3'` → minute=[30], hour=[14], dom=[1], month=[6], dow=[3]
+- test('parses step syntax') — `'*/5 * * * *'` → minute=[0,5,10,...,55]
+- test('parses range syntax') — `'1-5 * * * *'` → minute=[1,2,3,4,5]
+- test('parses range with step') — `'1-10/3 * * * *'` → minute=[1,4,7,10]
+- test('parses comma-separated list') — `'1,15,30 * * * *'` → minute=[1,15,30]
+- test('parses day-of-week 7 as Sunday alias') — `'0 0 * * 7'` → dow=[0]
+- test('parses range with day-of-week 7') — `'0 0 * * 5-7'` → dow=[0,5,6]
+- test('parses complex combined expression') — `'0,30 9-17 * * 1-5'` → 工作日 9-17 每半小时
+
+#### 无效表达式
+
+- test('returns null for wrong field count') — `'* * *'` → null
+- test('returns null for out-of-range values') — `'60 * * * *'` → null(minute max=59)
+- test('returns null for invalid step') — `'*/0 * * * *'` → null(step=0)
+- test('returns null for reversed range') — `'10-5 * * * *'` → null(lo>hi)
+- test('returns null for empty string') — `''` → null
+- test('returns null for non-numeric tokens') — `'abc * * * *'` → null
+
+#### 字段范围验证
+
+- test('minute: 0-59')
+- test('hour: 0-23')
+- test('dayOfMonth: 1-31')
+- test('month: 1-12')
+- test('dayOfWeek: 0-6 (plus 7 alias)')
+
+---
+
+### describe('computeNextCronRun')
+
+#### 基本匹配
+
+- test('finds next minute') — from 14:30:45, cron `'31 14 * * *'` → 14:31:00 同天
+- test('finds next hour') — from 14:30, cron `'0 15 * * *'` → 15:00 同天
+- test('rolls to next day') — from 14:30, cron `'0 10 * * *'` → 10:00 次日
+- test('rolls to next month') — from 1月31日, cron `'0 0 1 * *'` → 2月1日
+- test('is strictly after from date') — from 恰好匹配时应返回下一次而非当前时间
+
+#### DOM/DOW 语义
+
+- test('OR semantics when both dom and dow constrained') — dom=15, dow=3 → 匹配 15 号 OR 周三
+- test('only dom constrained uses dom') — dom=15, dow=* → 只匹配 15 号
+- test('only dow constrained uses dow') — dom=*, dow=3 → 只匹配周三
+- test('both wildcarded matches every day') — dom=*, dow=* → 每天
+
+#### 边界情况
+
+- test('handles month boundary') — 从 2 月 28 日寻找 2 月 29 日或 3 月 1 日
+- test('returns null after 366-day search') — 不可能匹配的表达式返回 null(理论上不会发生)
+- test('handles step across midnight') — `'0 0 * * *'` 从 23:59 → 次日 0:00
+
+#### 每 N 分钟
+
+- test('every 5 minutes from arbitrary time') — `'*/5 * * * *'` from 14:32 → 14:35
+- test('every minute') — `'* * * * *'` from 14:32:45 → 14:33:00
+
+---
+
+### describe('cronToHuman')
+
+#### 常见模式
+
+- test('every N minutes') — `'*/5 * * * *'` → `'Every 5 minutes'`
+- test('every minute') — `'*/1 * * * *'` → `'Every minute'`
+- test('every hour at :00') — `'0 * * * *'` → `'Every hour'`
+- test('every hour at :30') — `'30 * * * *'` → `'Every hour at :30'`
+- test('every N hours') — `'0 */2 * * *'` → `'Every 2 hours'`
+- test('daily at specific time') — `'30 9 * * *'` → `'Every day at 9:30 AM'`
+- test('specific day of week') — `'0 9 * * 3'` → `'Every Wednesday at 9:00 AM'`
+- test('weekdays') — `'0 9 * * 1-5'` → `'Weekdays at 9:00 AM'`
+
+#### Fallback
+
+- test('returns raw cron for complex patterns') — 非常见模式返回原始 cron 字符串
+- test('returns raw cron for wrong field count') — `'* * *'` → 原样返回
+
+#### UTC 模式
+
+- test('UTC option formats time in local timezone') — `{ utc: true }` 时 UTC 时间转本地显示
+- test('UTC midnight crossing adjusts day name') — UTC 时间跨天时本地星期名正确
+
+---
+
+## Mock 需求
+
+**无需 Mock**。所有函数为纯函数,唯一的外部依赖是 `Date` 构造器和 `toLocaleTimeString`,可通过传入确定性的 `from` 参数控制。
+
+## 注意事项
+
+- `cronToHuman` 的时间格式化依赖系统 locale,测试中建议使用 `'en-US'` locale 或只验证部分输出
+- `computeNextCronRun` 使用本地时区,DST 相关测试需注意运行环境

+ 106 - 0
docs/test-plans/08-git-utils.md

@@ -0,0 +1,106 @@
+# Git 工具测试计划
+
+## 概述
+
+Git 工具模块提供 git 远程 URL 规范化、仓库根目录查找、裸仓库安全检测等功能。测试重点是纯函数的 URL 规范化和需要文件系统 mock 的仓库发现逻辑。
+
+## 被测文件
+
+| 文件 | 关键导出 |
+|------|----------|
+| `src/utils/git.ts` | `normalizeGitRemoteUrl`, `findGitRoot`, `findCanonicalGitRoot`, `getIsGit`, `isAtGitRoot`, `getRepoRemoteHash`, `isCurrentDirectoryBareGitRepo`, `gitExe`, `getGitState`, `stashToCleanState`, `preserveGitStateForIssue` |
+
+---
+
+## 测试用例
+
+### describe('normalizeGitRemoteUrl')(纯函数)
+
+#### SSH 格式
+
+- test('normalizes SSH URL') — `'git@github.com:owner/repo.git'` → `'github.com/owner/repo'`
+- test('normalizes SSH URL without .git suffix') — `'git@github.com:owner/repo'` → `'github.com/owner/repo'`
+- test('handles GitLab SSH') — `'git@gitlab.com:group/subgroup/repo.git'` → `'gitlab.com/group/subgroup/repo'`
+
+#### HTTPS 格式
+
+- test('normalizes HTTPS URL') — `'https://github.com/owner/repo.git'` → `'github.com/owner/repo'`
+- test('normalizes HTTPS URL without .git suffix') — `'https://github.com/owner/repo'` → `'github.com/owner/repo'`
+- test('normalizes HTTP URL') — `'http://github.com/owner/repo.git'` → `'github.com/owner/repo'`
+
+#### SSH:// 协议格式
+
+- test('normalizes ssh:// URL') — `'ssh://git@github.com/owner/repo'` → `'github.com/owner/repo'`
+- test('handles user prefix in ssh://') — `'ssh://user@host/path'` → `'host/path'`
+
+#### 代理 URL(CCR git proxy)
+
+- test('normalizes legacy proxy URL') — `'http://local_proxy@127.0.0.1:16583/git/owner/repo'` → `'github.com/owner/repo'`
+- test('normalizes GHE proxy URL') — `'http://user@127.0.0.1:8080/git/ghe.company.com/owner/repo'` → `'ghe.company.com/owner/repo'`
+
+#### 边界情况
+
+- test('returns null for empty string') — `''` → null
+- test('returns null for whitespace') — `'  '` → null
+- test('returns null for unrecognized format') — `'not-a-url'` → null
+- test('output is lowercase') — `'git@GitHub.com:Owner/Repo.git'` → `'github.com/owner/repo'`
+- test('SSH and HTTPS for same repo produce same result') — 相同仓库不同协议 → 相同输出
+
+---
+
+### describe('findGitRoot')(需文件系统 Mock)
+
+- test('finds git root from nested directory') — `/project/src/utils/` → `/project/`(假设 `/project/.git` 存在)
+- test('finds git root from root directory') — `/project/` → `/project/`
+- test('returns null for non-git directory') — 无 `.git` → null
+- test('handles worktree .git file') — `.git` 为文件时也识别
+- test('memoizes results') — 同一路径不重复查找
+
+### describe('findCanonicalGitRoot')
+
+- test('returns same as findGitRoot for regular repo')
+- test('resolves worktree to main repo root') — worktree 路径 → 主仓库根目录
+- test('returns null for non-git directory')
+
+### describe('gitExe')
+
+- test('returns git path string') — 返回字符串
+- test('memoizes the result') — 多次调用返回同一值
+
+---
+
+### describe('getRepoRemoteHash')(需 Mock)
+
+- test('returns 16-char hex hash') — 返回值为 16 位十六进制字符串
+- test('returns null when no remote') — 无 remote URL 时返回 null
+- test('same repo SSH/HTTPS produce same hash') — 不同协议同一仓库 hash 相同
+
+---
+
+### describe('isCurrentDirectoryBareGitRepo')(需文件系统 Mock)
+
+- test('detects bare git repo attack vector') — 目录含 HEAD + objects/ + refs/ 但无有效 .git/HEAD → true
+- test('returns false for normal directory') — 普通目录 → false
+- test('returns false for regular git repo') — 有效 .git 目录 → false
+
+---
+
+## Mock 需求
+
+| 依赖 | Mock 方式 | 说明 |
+|------|-----------|------|
+| `statSync` | mock module | `findGitRoot` 中的 .git 检测 |
+| `readFileSync` | mock module | worktree .git 文件读取 |
+| `realpathSync` | mock module | 路径解析 |
+| `execFileNoThrow` | mock module | git 命令执行 |
+| `whichSync` | mock module | `gitExe` 中的 git 路径查找 |
+| `getCwd` | mock module | 当前工作目录 |
+| `getRemoteUrl` | mock module | `getRepoRemoteHash` 依赖 |
+| 临时目录 | `mkdtemp` | 集成测试中创建临时 git 仓库 |
+
+## 集成测试场景
+
+### describe('Git repo discovery')(放在 tests/integration/)
+
+- test('findGitRoot works in actual git repo') — 在临时 git init 的目录中验证
+- test('normalizeGitRemoteUrl + getRepoRemoteHash produces stable hash') — URL → hash 端到端验证

+ 161 - 0
docs/test-plans/09-config-settings.md

@@ -0,0 +1,161 @@
+# 配置系统测试计划
+
+## 概述
+
+配置系统包含全局配置(GlobalConfig)、项目配置(ProjectConfig)和设置(Settings)三层。测试重点是纯函数校验逻辑、Zod schema 验证和配置合并策略。
+
+## 被测文件
+
+| 文件 | 关键导出 |
+|------|----------|
+| `src/utils/config.ts` | `getGlobalConfig`, `saveGlobalConfig`, `getCurrentProjectConfig`, `checkHasTrustDialogAccepted`, `isPathTrusted`, `getOrCreateUserID`, `isAutoUpdaterDisabled` |
+| `src/utils/settings/settings.ts` | `getSettingsForSource`, `parseSettingsFile`, `getSettingsFilePathForSource`, `getInitialSettings` |
+| `src/utils/settings/types.ts` | `SettingsSchema`(Zod schema) |
+| `src/utils/settings/validation.ts` | 设置验证函数 |
+| `src/utils/settings/constants.ts` | 设置常量 |
+
+---
+
+## 测试用例
+
+### src/utils/config.ts — 纯函数/常量
+
+#### describe('DEFAULT_GLOBAL_CONFIG')
+
+- test('has all required fields') — 默认配置对象包含所有必需字段
+- test('has null auth fields by default') — oauthAccount 等为 null
+
+#### describe('DEFAULT_PROJECT_CONFIG')
+
+- test('has empty allowedTools') — 默认为空数组
+- test('has empty mcpServers') — 默认为空对象
+
+#### describe('isAutoUpdaterDisabled')
+
+- test('returns true when CLAUDE_CODE_DISABLE_AUTOUPDATER is set') — env 设置时禁用
+- test('returns true when disableAutoUpdater config is true')
+- test('returns false by default')
+
+---
+
+### src/utils/config.ts — 需 Mock
+
+#### describe('getGlobalConfig')
+
+- test('returns cached config on subsequent calls') — 缓存机制
+- test('returns TEST_GLOBAL_CONFIG_FOR_TESTING in test mode')
+- test('reads config from ~/.claude.json')
+- test('returns default config when file does not exist')
+
+#### describe('saveGlobalConfig')
+
+- test('applies updater function to current config') — updater 修改被保存
+- test('creates backup before writing') — 写入前备份
+- test('prevents auth state loss') — `wouldLoseAuthState` 检查
+
+#### describe('getCurrentProjectConfig')
+
+- test('returns project config for current directory')
+- test('returns default config when no project config exists')
+
+#### describe('checkHasTrustDialogAccepted')
+
+- test('returns true when trust is accepted in current directory')
+- test('returns true when parent directory is trusted') — 父目录信任传递
+- test('returns false when no trust accepted')
+- test('caches positive results')
+
+#### describe('isPathTrusted')
+
+- test('returns true for trusted path')
+- test('returns false for untrusted path')
+
+#### describe('getOrCreateUserID')
+
+- test('returns existing user ID from config')
+- test('creates and persists new ID when none exists')
+- test('returns consistent ID across calls')
+
+---
+
+### src/utils/settings/settings.ts
+
+#### describe('getSettingsFilePathForSource')
+
+- test('returns ~/.claude/settings.json for userSettings') — 全局用户设置路径
+- test('returns .claude/settings.json for projectSettings') — 项目设置路径
+- test('returns .claude/settings.local.json for localSettings') — 本地设置路径
+
+#### describe('parseSettingsFile')(需 Mock 文件读取)
+
+- test('parses valid settings JSON') — 有效 JSON → `{ settings, errors: [] }`
+- test('returns errors for invalid fields') — 无效字段 → errors 非空
+- test('returns empty settings for non-existent file')
+- test('handles JSON with comments') — JSONC 格式支持
+
+#### describe('getInitialSettings')
+
+- test('merges settings from all sources') — user + project + local 合并
+- test('later sources override earlier ones') — 优先级:policy > user > project > local
+
+---
+
+### src/utils/settings/types.ts — Zod Schema 验证
+
+#### describe('SettingsSchema validation')
+
+- test('accepts valid minimal settings') — `{}` → 有效
+- test('accepts permissions block') — `{ permissions: { allow: ['Bash(*)'] } }` → 有效
+- test('accepts model setting') — `{ model: 'sonnet' }` → 有效
+- test('accepts hooks configuration') — 有效的 hooks 对象被接受
+- test('accepts env variables') — `{ env: { FOO: 'bar' } }` → 有效
+- test('rejects unknown top-level keys') — 未知字段被拒绝或忽略(取决于 schema 配置)
+- test('rejects invalid permission mode') — `{ permissions: { defaultMode: 'invalid' } }` → 错误
+- test('rejects non-string model') — `{ model: 123 }` → 错误
+- test('accepts mcpServers configuration') — MCP server 配置有效
+- test('accepts sandbox configuration')
+
+---
+
+### src/utils/settings/validation.ts
+
+#### describe('settings validation')
+
+- test('validates permission rules format') — `'Bash(npm install)'` 格式正确
+- test('rejects malformed permission rules')
+- test('validates hook configuration structure')
+- test('provides helpful error messages') — 错误信息包含字段路径
+
+---
+
+## Mock 需求
+
+| 依赖 | Mock 方式 | 说明 |
+|------|-----------|------|
+| 文件系统 | 临时目录 + mock | config 文件读写 |
+| `lockfile` | mock module | 文件锁 |
+| `getCwd` | mock module | 项目路径判断 |
+| `findGitRoot` | mock module | 项目根目录 |
+| `process.env` | 直接设置/恢复 | `CLAUDE_CODE_DISABLE_AUTOUPDATER` 等 |
+
+### 测试用临时文件结构
+
+```
+/tmp/claude-test-xxx/
+├── .claude/
+│   ├── settings.json        # projectSettings
+│   └── settings.local.json  # localSettings
+├── home/
+│   └── .claude/
+│       └── settings.json    # userSettings(mock HOME)
+└── project/
+    └── .git/
+```
+
+## 集成测试场景
+
+### describe('Config + Settings merge pipeline')
+
+- test('user settings + project settings merge correctly') — 验证合并优先级
+- test('deny rules from settings are reflected in tool permission context')
+- test('trust dialog state persists across config reads')

+ 304 - 0
docs/testing-spec.md

@@ -0,0 +1,304 @@
+# Testing Specification
+
+本文档定义了 claude-code 项目的测试规范,作为编写和维护测试代码的统一标准。
+
+## 1. 测试目标
+
+| 目标 | 说明 |
+|------|------|
+| **防止回归** | 确保已有功能不被新改动破坏,每次 PR 必须通过全部测试 |
+| **验证核心流程** | 覆盖 CLI 核心交互流程:Tool 调用链、Context 构建、消息处理 |
+| **文档化行为** | 通过测试用例记录各模块的预期行为,作为活文档供开发者参考 |
+
+## 2. 技术栈
+
+| 项 | 选型 | 说明 |
+|----|------|------|
+| 测试框架 | `bun:test` | Bun 内置,零配置,与运行时一致 |
+| 断言库 | `bun:test` 内置 `expect` | 兼容 Jest `expect` API |
+| Mock | `bun:test` 内置 `mock`/`spyOn` | 配合手动 mock fixtures |
+| 覆盖率 | `bun test --coverage` | 内置覆盖率报告 |
+
+## 3. 测试层次
+
+本项目采用 **单元测试 + 集成测试** 两层结构,不做 E2E 或快照测试。
+
+### 3.1 单元测试
+
+- **对象**:纯函数、工具类、解析器、独立模块
+- **特征**:无外部依赖、执行快、可并行
+- **示例场景**:
+  - `src/utils/array.ts` — 数组操作函数
+  - `src/utils/path.ts` — 路径解析
+  - `src/utils/diff.ts` — diff 算法
+  - `src/utils/permissions/` — 权限判断逻辑
+  - `src/utils/model/` — 模型选择与 provider 路由
+  - Tool 的 `inputSchema` 校验逻辑
+
+### 3.2 集成测试
+
+- **对象**:多模块协作流程
+- **特征**:可能需要 mock 外部服务(API、文件系统),测试模块间协作
+- **示例场景**:
+  - Tool 调用链:`tools.ts` 注册 → `findToolByName` → tool `call()` 执行
+  - Context 构建:`context.ts` 组装系统提示(CLAUDE.md 加载 + git status + 日期)
+  - 消息处理管线:用户输入 → 消息格式化 → API 请求构建
+
+## 4. 文件结构
+
+采用 **混合模式**:单元测试就近放置,集成测试集中管理。
+
+```
+src/
+├── utils/
+│   ├── array.ts
+│   ├── __tests__/              # 单元测试:就近放置
+│   │   ├── array.test.ts
+│   │   ├── set.test.ts
+│   │   └── path.test.ts
+│   ├── model/
+│   │   ├── providers.ts
+│   │   └── __tests__/
+│   │       └── providers.test.ts
+│   └── permissions/
+│       ├── index.ts
+│       └── __tests__/
+│           └── permissions.test.ts
+├── tools/
+│   ├── BashTool/
+│   │   ├── index.ts
+│   │   └── __tests__/
+│   │       └── BashTool.test.ts
+│   └── FileEditTool/
+│       ├── index.ts
+│       └── __tests__/
+│           └── FileEditTool.test.ts
+tests/                          # 集成测试:集中管理
+├── integration/
+│   ├── tool-chain.test.ts
+│   ├── context-build.test.ts
+│   └── message-pipeline.test.ts
+├── mocks/                      # 通用 mock / fixtures
+│   ├── api-responses.ts        # Claude API mock 响应
+│   ├── file-system.ts          # 文件系统 mock 工具
+│   └── fixtures/
+│       ├── sample-claudemd.md
+│       └── sample-messages.json
+└── helpers/                    # 测试辅助函数
+    └── setup.ts
+```
+
+### 命名规则
+
+| 项 | 规则 |
+|----|------|
+| 测试文件 | `<module-name>.test.ts` |
+| 测试目录 | `__tests__/`(单元)、`tests/integration/`(集成) |
+| Fixture 文件 | `tests/mocks/fixtures/` 下按用途命名 |
+| Helper 文件 | `tests/helpers/` 下按功能命名 |
+
+## 5. 命名与编写规范
+
+### 5.1 命名风格
+
+使用 `describe` + `it`/`test` 英文描述:
+
+```typescript
+import { describe, expect, test } from "bun:test";
+
+describe("findToolByName", () => {
+  test("returns the tool when name matches exactly", () => {
+    // ...
+  });
+
+  test("returns undefined when no tool matches", () => {
+    // ...
+  });
+
+  test("is case-insensitive for tool name lookup", () => {
+    // ...
+  });
+});
+```
+
+### 5.2 describe 块组织原则
+
+- 顶层 `describe` 对应被测函数/类/模块名
+- 可嵌套 `describe` 对分支场景分组(如 `describe("when input is empty", ...)`)
+- 每个 `test` 应测试一个行为,命名采用 **"动作 + 预期结果"** 格式
+
+### 5.3 编写原则
+
+| 原则 | 说明 |
+|------|------|
+| **Arrange-Act-Assert** | 每个测试分三段:准备数据、执行操作、验证结果 |
+| **单一职责** | 一个 `test` 只验证一个行为 |
+| **独立性** | 测试之间无顺序依赖,无共享可变状态 |
+| **可读性优先** | 测试代码是文档,宁可重复也不过度抽象 |
+| **边界覆盖** | 空值、边界值、异常输入必须覆盖 |
+
+### 5.4 异步测试
+
+```typescript
+test("reads file content correctly", async () => {
+  const content = await readFile("/tmp/test.txt");
+  expect(content).toContain("expected");
+});
+```
+
+## 6. Mock 策略
+
+采用 **混合管理**:通用 mock 集中于 `tests/mocks/`,专用 mock 就近定义。
+
+### 6.1 Claude API Mock(集中管理)
+
+所有 API 测试全部使用 mock,不调用真实 API。
+
+```typescript
+// tests/mocks/api-responses.ts
+export const mockStreamResponse = {
+  type: "message_start",
+  message: {
+    id: "msg_mock_001",
+    type: "message",
+    role: "assistant",
+    content: [],
+    model: "claude-sonnet-4-20250514",
+    // ...
+  },
+};
+
+export const mockToolUseResponse = {
+  type: "content_block_start",
+  content_block: {
+    type: "tool_use",
+    id: "toolu_mock_001",
+    name: "Read",
+    input: { file_path: "/tmp/test.txt" },
+  },
+};
+```
+
+### 6.2 模块级 Mock(就近定义)
+
+```typescript
+import { mock } from "bun:test";
+
+// mock 整个模块
+mock.module("src/services/api/claude.ts", () => ({
+  createApiClient: () => ({
+    stream: mock(() => mockStreamResponse),
+  }),
+}));
+```
+
+### 6.3 文件系统 Mock
+
+对于需要文件系统交互的测试,使用临时目录:
+
+```typescript
+import { mkdtemp, rm } from "node:fs/promises";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import { afterAll, beforeAll } from "bun:test";
+
+let tempDir: string;
+
+beforeAll(async () => {
+  tempDir = await mkdtemp(join(tmpdir(), "claude-test-"));
+});
+
+afterAll(async () => {
+  await rm(tempDir, { recursive: true });
+});
+```
+
+## 7. 优先测试模块
+
+按优先级从高到低排列,括号内为目标覆盖率:
+
+### P0 — 核心(行覆盖率 >= 80%)
+
+| 模块 | 路径 | 测试重点 |
+|------|------|----------|
+| **Tool 系统** | `src/tools/`, `src/Tool.ts`, `src/tools.ts` | tool 注册/发现、inputSchema 校验、call() 执行与错误处理 |
+| **工具函数** | `src/utils/` 下纯函数 | 各种 utility 的正确性与边界情况 |
+| **Context 构建** | `src/context.ts`, `src/utils/claudemd.ts` | 系统提示拼装、CLAUDE.md 发现与加载、context 内容完整性 |
+
+### P1 — 重要(行覆盖率 >= 60%)
+
+| 模块 | 路径 | 测试重点 |
+|------|------|----------|
+| **权限系统** | `src/utils/permissions/` | 权限模式判断、tool 许可/拒绝逻辑 |
+| **模型路由** | `src/utils/model/` | provider 选择、模型名映射、fallback 逻辑 |
+| **消息处理** | `src/types/message.ts`, `src/utils/messages.ts` | 消息类型构造、格式化、过滤 |
+| **CLI 参数** | `src/main.tsx` 中的 Commander 配置 | 参数解析、模式切换(REPL/pipe) |
+
+### P2 — 补充
+
+| 模块 | 路径 | 测试重点 |
+|------|------|----------|
+| **Cron 调度** | `src/utils/cron*.ts` | cron 表达式解析、任务调度逻辑 |
+| **Git 工具** | `src/utils/git.ts` | git 命令构造、输出解析 |
+| **Config** | `src/utils/config.ts`, `src/utils/settings/` | 配置加载、合并、默认值 |
+
+## 8. 覆盖率要求
+
+| 范围 | 目标 | 说明 |
+|------|------|------|
+| P0 核心模块 | **>= 80%** 行覆盖率 | Tool 系统、工具函数、Context 构建 |
+| P1 重要模块 | **>= 60%** 行覆盖率 | 权限、模型路由、消息处理 |
+| 整体 | 不设强制指标 | 逐步提升,不追求数字 |
+
+运行覆盖率报告:
+
+```bash
+bun test --coverage
+```
+
+## 9. CI 集成
+
+已有 GitHub Actions 配置(`.github/workflows/ci.yml`),`bun test` 步骤已就位。
+
+### CI 中测试的运行条件
+
+- **push** 到 `main` 或 `feature/*` 分支时自动运行
+- **pull_request** 到 `main` 分支时自动运行
+- 测试失败将阻止合并
+
+### 本地运行
+
+```bash
+# 运行全部测试
+bun test
+
+# 运行特定文件
+bun test src/utils/__tests__/array.test.ts
+
+# 运行匹配模式
+bun test --filter "findToolByName"
+
+# 带覆盖率
+bun test --coverage
+
+# watch 模式(开发时)
+bun test --watch
+```
+
+## 10. 编写测试 Checklist
+
+每次新增或修改测试时,确认以下事项:
+
+- [ ] 测试文件位置正确(单元 → `__tests__/`,集成 → `tests/integration/`)
+- [ ] 命名遵循 `describe` + `test` 英文格式
+- [ ] 每个 test 只验证一个行为
+- [ ] 覆盖了正常路径、边界情况和错误情况
+- [ ] 无硬编码的绝对路径或系统特定值
+- [ ] Mock 使用得当(通用 → `tests/mocks/`,专用 → 就近)
+- [ ] 测试可独立运行,无顺序依赖
+- [ ] `bun test` 本地全部通过后再提交
+
+## 11. 参考
+
+- [Bun Test 文档](https://bun.sh/docs/cli/test)
+- 现有测试示例:`src/utils/__tests__/set.test.ts`, `src/utils/__tests__/array.test.ts`