feat(agent): expand tool registry — file, git, shell, web fetch (#126) (#138)

Co-authored-by: Jason Woltje <jason@diversecanvas.com>
Co-committed-by: Jason Woltje <jason@diversecanvas.com>

apps/gateway/src/agent/tools/shell-tools.ts

@@ -0,0 +1,195 @@
+import { Type } from '@sinclair/typebox';
+import type { ToolDefinition } from '@mariozechner/pi-coding-agent';
+import { spawn } from 'node:child_process';
+
+const DEFAULT_TIMEOUT_MS = 30_000;
+const MAX_OUTPUT_BYTES = 100 * 1024; // 100 KB
+
+/**
+ * Commands that are outright blocked for safety.
+ * This is a denylist; the agent should be instructed to use
+ * the least-privilege command necessary.
+ */
+const BLOCKED_COMMANDS = new Set([
+  'rm',
+  'rmdir',
+  'mkfs',
+  'dd',
+  'format',
+  'fdisk',
+  'parted',
+  'shred',
+  'wipefs',
+  'sudo',
+  'su',
+  'chown',
+  'chmod',
+  'passwd',
+  'useradd',
+  'userdel',
+  'groupadd',
+  'shutdown',
+  'reboot',
+  'halt',
+  'poweroff',
+  'kill',
+  'killall',
+  'pkill',
+  'curl',
+  'wget',
+  'nc',
+  'netcat',
+  'ncat',
+  'ssh',
+  'scp',
+  'sftp',
+  'rsync',
+  'iptables',
+  'ip6tables',
+  'nft',
+  'ufw',
+  'firewall-cmd',
+  'docker',
+  'podman',
+  'kubectl',
+  'helm',
+  'terraform',
+  'ansible',
+  'crontab',
+  'at',
+  'batch',
+]);
+
+function extractBaseCommand(command: string): string {
+  // Extract the first word (the binary name), stripping path
+  const trimmed = command.trim();
+  const firstToken = trimmed.split(/\s+/)[0] ?? '';
+  return firstToken.split('/').pop() ?? firstToken;
+}
+
+function runCommand(
+  command: string,
+  options: { timeoutMs: number; cwd?: string },
+): Promise<{ stdout: string; stderr: string; exitCode: number | null; timedOut: boolean }> {
+  return new Promise((resolve) => {
+    const child = spawn('sh', ['-c', command], {
+      cwd: options.cwd,
+      stdio: ['ignore', 'pipe', 'pipe'],
+      detached: false,
+    });
+
+    let stdout = '';
+    let stderr = '';
+    let timedOut = false;
+    let totalBytes = 0;
+    let truncated = false;
+
+    child.stdout?.on('data', (chunk: Buffer) => {
+      if (truncated) return;
+      totalBytes += chunk.length;
+      if (totalBytes > MAX_OUTPUT_BYTES) {
+        stdout += chunk.subarray(0, MAX_OUTPUT_BYTES - (totalBytes - chunk.length)).toString();
+        stdout += '\n[output truncated at 100 KB limit]';
+        truncated = true;
+        child.kill('SIGTERM');
+      } else {
+        stdout += chunk.toString();
+      }
+    });
+
+    child.stderr?.on('data', (chunk: Buffer) => {
+      if (stderr.length < MAX_OUTPUT_BYTES) {
+        stderr += chunk.toString();
+      }
+    });
+
+    const timer = setTimeout(() => {
+      timedOut = true;
+      child.kill('SIGTERM');
+      setTimeout(() => {
+        try {
+          child.kill('SIGKILL');
+        } catch {
+          // already exited
+        }
+      }, 2000);
+    }, options.timeoutMs);
+
+    child.on('close', (exitCode) => {
+      clearTimeout(timer);
+      resolve({ stdout, stderr, exitCode, timedOut });
+    });
+
+    child.on('error', (err) => {
+      clearTimeout(timer);
+      resolve({ stdout, stderr: stderr + String(err), exitCode: null, timedOut: false });
+    });
+  });
+}
+
+export function createShellTools(defaultCwd?: string): ToolDefinition[] {
+  const shellExec: ToolDefinition = {
+    name: 'shell_exec',
+    label: 'Shell Execute',
+    description:
+      'Execute a shell command with timeout and output limits. Dangerous commands (rm, sudo, docker, etc.) are blocked.',
+    parameters: Type.Object({
+      command: Type.String({ description: 'Shell command to execute' }),
+      cwd: Type.Optional(Type.String({ description: 'Working directory for the command.' })),
+      timeout: Type.Optional(
+        Type.Number({ description: 'Timeout in milliseconds (default 30000, max 60000)' }),
+      ),
+    }),
+    async execute(_toolCallId, params) {
+      const { command, cwd, timeout } = params as {
+        command: string;
+        cwd?: string;
+        timeout?: number;
+      };
+
+      const base = extractBaseCommand(command);
+      if (BLOCKED_COMMANDS.has(base)) {
+        return {
+          content: [
+            {
+              type: 'text' as const,
+              text: `Error: command "${base}" is blocked for safety reasons.`,
+            },
+          ],
+          details: undefined,
+        };
+      }
+
+      const timeoutMs = Math.min(timeout ?? DEFAULT_TIMEOUT_MS, 60_000);
+
+      const result = await runCommand(command, {
+        timeoutMs,
+        cwd: cwd ?? defaultCwd,
+      });
+
+      if (result.timedOut) {
+        return {
+          content: [
+            {
+              type: 'text' as const,
+              text: `Command timed out after ${timeoutMs}ms.\nPartial stdout:\n${result.stdout}\nPartial stderr:\n${result.stderr}`,
+            },
+          ],
+          details: undefined,
+        };
+      }
+
+      const parts: string[] = [];
+      if (result.stdout) parts.push(`stdout:\n${result.stdout}`);
+      if (result.stderr) parts.push(`stderr:\n${result.stderr}`);
+      parts.push(`exit code: ${result.exitCode ?? 'null'}`);
+
+      return {
+        content: [{ type: 'text' as const, text: parts.join('\n') }],
+        details: undefined,
+      };
+    },
+  };
+
+  return [shellExec];
+}