thincoder 0.4.0 → 0.6.0

package/src/tools.mjs

@@ -15,7 +15,9 @@ const __dirname = dirname(fileURLToPath(import.meta.url))
 const DESC = (name) => readFileSync(join(__dirname, "tools", `${name}.md`), "utf8")
 
 const MAX_READ_LINES = 2000
-const MAX_OUTPUT_CHARS = 50_000
+// 输出上限只是内存安全阀：超过 16k 的输出由 agent 层 offload 整体落盘（全量保留、预览+路径回喂），
+// 这里截断必须远高于落盘阈值，否则被截掉的内容在落盘前就永远丢了
+const MAX_OUTPUT_CHARS = 200_000
 const BASH_TIMEOUT_MS = 120_000
 const IGNORED_DIRS = new Set(["node_modules", ".git", "dist", "build", ".turbo", "coverage"])
 
@@ -36,7 +38,7 @@ export function toOpenAISchema(tool) {
 /** 剥离 ANSI 转义序列（vim/less/颜色码会冲花 TUI 渲染），并把 \r 进度条改写转成换行 */
 function sanitizeOutput(s) {
   return s
-    .replace(/\x1b\[[0-9;?]*[a-zA-Z]|\x1b\][^\x07\x1b]*(?:\x07|\x1b\\)|\x1b[()][0-9A-B]|\x1b[=>#][0-9]?/g, "")
+    .replace(/\x1b\[[0-9;?]*[\x40-\x7E]|\x1b\][^\x07\x1b]*(?:\x07|\x1b\\)|\x1b[()][0-9A-B]|\x1b[=>#][0-9]?/g, "")
     .replace(/\r\n/g, "\n")
     .replace(/\r/g, "\n")
 }
@@ -46,8 +48,26 @@ function truncate(text, max = MAX_OUTPUT_CHARS) {
   return text.slice(0, max) + `\n... (truncated, ${text.length - max} chars omitted)`
 }
 
+/** 对单个文件取 git diff，失败静默返回空 */
+function gitDiffOne(cwd, abs) {
+  try {
+    const diff = execFileSync("git", ["--no-pager", "diff", "--no-color", "--", abs], {
+      cwd, encoding: "utf8", stdio: ["ignore", "pipe", "ignore"], maxBuffer: 1024 * 1024,
+    }).trim()
+    if (!diff) return ""
+    // 截断超长 diff（超大文件改动 diff 可能几十 KB），只保留前 200 行
+    const lines = diff.split("\n")
+    if (lines.length <= 200) return diff
+    return lines.slice(0, 200).join("\n") + `\n... (${lines.length - 200} more diff lines)`
+  } catch {
+    return ""
+  }
+}
+
 function resolveInCwd(ctx, p) {
-  return resolve(ctx.cwd, p)
+  const resolved = resolve(ctx.cwd, p)
+  if (relative(ctx.cwd, resolved).startsWith("..")) throw new Error(`Access denied outside working directory: ${p}`)
+  return resolved
 }
 
 // ---------------------------------------------------------------- read
@@ -95,8 +115,11 @@ const writeTool = {
   async execute(args, ctx) {
     const abs = resolveInCwd(ctx, args.path)
     await mkdir(dirname(abs), { recursive: true })
+    const st = await stat(abs).catch(() => null)
+    if (st?.isDirectory()) throw new Error(`Path is a directory: ${abs}`)
     await writeFile(abs, args.content, "utf8")
-    return `Wrote ${args.content.length} chars to ${abs}`
+    const diff = gitDiffOne(ctx.cwd, abs)
+    return `Wrote ${args.content.length} chars to ${abs}${diff ? "\n" + diff : ""}`
   },
 }
 
@@ -121,7 +144,13 @@ const editTool = {
     const content = await readFile(abs, "utf8")
     const occurrences = content.split(args.old_string).length - 1
     if (occurrences === 0) {
-      throw new Error(`old_string not found in ${abs}`)
+      // 给出线索帮模型定位：首行预览 + 常见原因
+      const preview = args.old_string.slice(0, 100).split("\n")[0]
+      throw new Error(
+        `old_string not found in ${abs}\n` +
+        `  searched: "${preview}${args.old_string.length > 100 ? "…" : ""}"\n` +
+        `  hints: whitespace mismatch? file already changed? try reading the file first`
+      )
     }
     if (occurrences > 1 && !args.replace_all) {
       throw new Error(`old_string matches ${occurrences} times in ${abs}; provide more context or set replace_all`)
@@ -130,7 +159,8 @@ const editTool = {
       ? content.split(args.old_string).join(args.new_string)
       : content.replace(args.old_string, args.new_string)
     await writeFile(abs, updated, "utf8")
-    return `Edited ${abs}: replaced ${args.replace_all ? occurrences : 1} occurrence(s)`
+    const diff = gitDiffOne(ctx.cwd, abs)
+    return `Edited ${abs}: replaced ${args.replace_all ? occurrences : 1} occurrence(s)${diff ? "\n" + diff : ""}`
   },
 }
 
@@ -149,6 +179,20 @@ const bashTool = {
   },
   readonly: false,
   async execute(args, ctx) {
+    // 安全预检：销毁性 git 操作（checkout -- / reset --hard）先检查未提交改动，
+    // 有则拒绝——防一键清掉几小时工作（像今天 git checkout -- 六个文件那次）
+    const DESTRUCTIVE_GIT = /^git\s+(?:checkout\s+--?\s+|reset\s+--hard\b)/
+    if (DESTRUCTIVE_GIT.test(args.command)) {
+      const status = execFileSync("git", ["status", "--porcelain"], {
+        cwd: ctx.cwd, encoding: "utf8", stdio: ["ignore", "pipe", "ignore"],
+      }).trim()
+      if (status) {
+        throw new Error(
+          `Refusing destructive git command: uncommitted changes exist. Commit or stash first.\n\n${status}`
+        )
+      }
+    }
+
     return new Promise((resolve) => {
       const child = spawn(args.command, {
         cwd: ctx.cwd,
@@ -170,6 +214,8 @@ const bashTool = {
       // 编码嗅探：cmd 自带消息是 GBK，git/node 等程序是 UTF-8，平台判断不了。
       // 策略：纯 ASCII 段两种编码一致，直接透传不判定；遇到高位字节才用
       // fatal UTF-8 试解（容忍尾部 1~3 字节截断），失败则判 GBK；一经判定不再变更。
+      // 已知边界：GBK 字节流极低概率恰好构成合法 UTF-8 序列，会误判为 UTF-8 产生乱码。
+      // 更严谨的做法是 chcp 探测控制台代码页，但当前策略覆盖 99.9% 场景，不值得那份复杂度。
       let decoder = null
       let pending = Buffer.alloc(0)
       const feed = (d, flush = false) => {
@@ -250,7 +296,7 @@ const globTool = {
   },
   readonly: true,
   async execute(args, ctx) {
-    const base = resolve(ctx.cwd, args.path ?? ".")
+    const base = resolveInCwd(ctx, args.path ?? ".")
     const regex = globToRegex(args.pattern)
     const results = []
     for await (const relPath of walkFiles(base)) {
@@ -314,7 +360,7 @@ const grepTool = {
   },
   readonly: true,
   async execute(args, ctx) {
-    const base = resolve(ctx.cwd, args.path ?? ".")
+    const base = resolveInCwd(ctx, args.path ?? ".")
     const regex = new RegExp(args.pattern)
     const fileFilter = args.glob ? globToRegex(args.glob) : null
     const matches = []
@@ -374,14 +420,16 @@ const websearchTool = {
     required: ["query"],
   },
   readonly: true,
-  async execute(args) {
+  async execute(args, ctx) {
     const limit = args.limit ?? 8
     const url = `https://www.bing.com/search?q=${encodeURIComponent(args.query)}`
     let html
     try {
       const response = await fetch(url, {
         headers: { "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36" },
-        signal: AbortSignal.timeout(15_000),
+        signal: ctx?.signal
+          ? AbortSignal.any([ctx.signal, AbortSignal.timeout(15_000)])
+          : AbortSignal.timeout(15_000),
       })
       if (!response.ok) throw new Error(`HTTP ${response.status}`)
       html = await response.text()
@@ -437,7 +485,7 @@ const lsTool = {
   },
   readonly: true,
   async execute(args, ctx) {
-    const abs = resolve(ctx.cwd, args.path ?? ".")
+    const abs = resolveInCwd(ctx, args.path ?? ".")
     const entries = await readdir(abs, { withFileTypes: true })
     const rows = await Promise.all(
       entries.slice(0, 500).map(async (e) => {
@@ -471,14 +519,16 @@ const fetchTool = {
     required: ["url"],
   },
   readonly: true,
-  async execute(args) {
+  async execute(args, ctx) {
     if (!/^https?:\/\//.test(args.url)) throw new Error("url must start with http:// or https://")
     let response
     try {
       response = await fetch(args.url, {
         headers: { "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36" },
         redirect: "follow",
-        signal: AbortSignal.timeout(20_000),
+        signal: ctx?.signal
+          ? AbortSignal.any([ctx.signal, AbortSignal.timeout(20_000)])
+          : AbortSignal.timeout(20_000),
       })
     } catch (error) {
       throw new Error(`fetch failed: ${error.cause?.code ?? error.message}`)