moshcode work: 50 agents, one verifier, and an inbox

说明与用途

Moshcode 实现了一个自动化工作流，使用 50 个并行 AI 代理来验证和修复失败的测试，自动重试失败并聚合成功补丁。

问题

Managing thousands of AI agents for math proofs requires a scalable verification workflow that isolates failures and aggregates results without overwhelming operators.

结果

In the first run on moshcode, 139 local test failures were reduced to 0 by identifying 19 true failures and automatically fixing them with 50 parallel workers. The inbox remained empty, and no assertions were altered.

工作流

• 1. Use moshcode work from-tests fix-tests to create a task per failing test file.
• 2. Run tasks with moshcode work run fix-tests -n 50 --engine claude to launch 50 parallel workers.
• 3. Check progress with moshcode work status fix-tests for aggregated numbers.
• 4. Inspect only failed attempts with moshcode work inbox fix-tests.
• 5. Apply passing patches using moshcode work apply fix-tests.
• 6. Repeat with additional verifiers such as typecheck or URL checks as needed.

证据

Every task carries a verify command, and exit 0 is the only definition of done.

来源

The inbox stayed empty. No assertion was added or removed.

来源

A failed attempt goes back in the queue with the verify output in its next prompt.

来源