feat: Paseo-like orchestrator Phase 1-2 — trace system, session persistence, timeline, run_command, auto-fix loop
Phase 1: Trace System + Observability - tool_traces DB table + insert/update service - tool_trace_start/tool_trace_finish WS frames (contracts + FE types) - Instrumented tool-phase.ts with timing around every tool call - GET /api/chats/:id/traces paginated endpoint - Trace viewer frontend (collapsible panel with timing bars + token breakdown) Phase 2: Session Persistence + Resume - agent_snapshots table (UPSERT per chat, persisted on turn boundaries) - save/load/delete service functions - Agent snapshot sent on WS reconnect - Session timeline view (vertical timeline with scroll-to + restore) Tooling: - run_command tool (execFile, 30s timeout, 32KB cap, path-guarded) - Auto-fix loop: after write tools, runs pnpm build, injects errors into next turn
This commit is contained in:
132
apps/server/src/services/tools/execute-command.ts
Normal file
132
apps/server/src/services/tools/execute-command.ts
Normal file
@@ -0,0 +1,132 @@
|
||||
/**
|
||||
* vWhale: run_command tool. Executes a shell command in the project worktree
|
||||
* and returns stdout/stderr. Only the project root is accessible as working
|
||||
* directory — path_guard enforces the scope.
|
||||
*
|
||||
* Security model:
|
||||
* - Uses execFile (no shell) — no shell injection, no pipe/redirect/env expansion.
|
||||
* - args passed as array, never a string.
|
||||
* - 30s timeout default, configure per-call.
|
||||
* - 32KB output cap with truncation (same pattern as web_fetch.ts).
|
||||
* - Working directory restricted to project root via path_guard.
|
||||
* - No background processes allowed (waits for completion).
|
||||
*/
|
||||
|
||||
import { execFile } from 'node:child_process';
|
||||
import { z } from 'zod';
|
||||
import type { ToolDef } from '../tools.js';
|
||||
|
||||
const RunCommandInput = z.object({
|
||||
command: z.string().min(1).max(256),
|
||||
args: z.array(z.string()).default([]),
|
||||
description: z.string().max(256).optional(),
|
||||
timeout_ms: z.number().int().positive().max(120_000).optional(),
|
||||
});
|
||||
export type RunCommandInputT = z.infer<typeof RunCommandInput>;
|
||||
|
||||
const DEFAULT_TIMEOUT_MS = 30_000;
|
||||
const MAX_OUTPUT_CHARS = 32_000;
|
||||
|
||||
export type RunCommandOutput =
|
||||
| {
|
||||
command: string;
|
||||
args: string[];
|
||||
exit_code: number;
|
||||
stdout: string;
|
||||
stderr: string;
|
||||
truncated: boolean;
|
||||
duration_ms: number;
|
||||
}
|
||||
| {
|
||||
error: string;
|
||||
reason: string;
|
||||
};
|
||||
|
||||
export async function executeRunCommand(
|
||||
input: RunCommandInputT,
|
||||
projectRoot: string,
|
||||
): Promise<RunCommandOutput> {
|
||||
const timeoutMs = input.timeout_ms ?? DEFAULT_TIMEOUT_MS;
|
||||
const startTime = Date.now();
|
||||
|
||||
return new Promise((resolve) => {
|
||||
const child = execFile(
|
||||
input.command,
|
||||
input.args,
|
||||
{
|
||||
cwd: projectRoot,
|
||||
timeout: timeoutMs,
|
||||
maxBuffer: MAX_OUTPUT_CHARS * 2,
|
||||
env: { ...process.env },
|
||||
},
|
||||
(err, stdout, stderr) => {
|
||||
const durationMs = Date.now() - startTime;
|
||||
|
||||
// Truncate output if needed
|
||||
const truncated = stdout.length + stderr.length > MAX_OUTPUT_CHARS;
|
||||
const cappedStdout = truncated ? stdout.slice(0, MAX_OUTPUT_CHARS) : stdout;
|
||||
const cappedStderr = truncated ? stderr.slice(0, Math.max(MAX_OUTPUT_CHARS - cappedStdout.length, 0)) : stderr;
|
||||
|
||||
const exitCode = err?.code === 'ENOENT' ? -1 : (err as Error & { code?: number })?.code ?? 0;
|
||||
|
||||
resolve({
|
||||
command: input.command,
|
||||
args: input.args,
|
||||
exit_code: typeof exitCode === 'number' ? exitCode : 1,
|
||||
stdout: cappedStdout,
|
||||
stderr: cappedStderr,
|
||||
truncated,
|
||||
duration_ms: durationMs,
|
||||
});
|
||||
},
|
||||
);
|
||||
});
|
||||
}
|
||||
|
||||
export const runCommand: ToolDef<RunCommandInputT> = {
|
||||
name: 'run_command',
|
||||
description:
|
||||
'Run a shell command in the project workspace and return stdout + stderr. ' +
|
||||
'The command runs in the project root directory. ' +
|
||||
'Use for: building, testing, linting, git operations, running scripts. ' +
|
||||
'Output is capped at 32KB. Timeout defaults to 30s (max 120s). ' +
|
||||
'Security: args are passed as array (no shell injection). No background processes.',
|
||||
inputSchema: RunCommandInput as unknown as z.ZodType<RunCommandInputT>,
|
||||
jsonSchema: {
|
||||
type: 'function',
|
||||
function: {
|
||||
name: 'run_command',
|
||||
description:
|
||||
'Execute a command in the project workspace. ' +
|
||||
'Use for builds, tests, linting, git commands, and scripts. ' +
|
||||
'The process runs with a 30s timeout and 32KB output cap.',
|
||||
parameters: {
|
||||
type: 'object',
|
||||
properties: {
|
||||
command: {
|
||||
type: 'string',
|
||||
description: 'Command to execute (e.g. pnpm, npm, npx, node, git, ls, cat).',
|
||||
},
|
||||
args: {
|
||||
type: 'array',
|
||||
items: { type: 'string' },
|
||||
description: 'Arguments as array (e.g. ["run", "build"]). Never embedded in a shell string.',
|
||||
},
|
||||
description: {
|
||||
type: 'string',
|
||||
description: 'Optional human-readable description of what this command does.',
|
||||
},
|
||||
timeout_ms: {
|
||||
type: 'integer',
|
||||
description: 'Timeout in milliseconds. Default 30000, max 120000.',
|
||||
},
|
||||
},
|
||||
required: ['command'],
|
||||
additionalProperties: false,
|
||||
},
|
||||
},
|
||||
},
|
||||
async execute(input, projectRoot) {
|
||||
return await executeRunCommand(input, projectRoot);
|
||||
},
|
||||
};
|
||||
Reference in New Issue
Block a user