Jukebox-OS：面向 AI Agent 的确定性时光倒流回放与 ACID 工具沙箱

英文标题：🔶 Jukebox-OS: Deterministic time-travel replay and ACID tool sandbox for AI agents

针对当前主流 Agent 框架在工具调用副作用（Side Effects）处理上缺乏回滚机制的痛点，开发者 Marius Carlsson 推出了基于 Rust 构建并提供 Python 绑定的系统级运行时 Jukebox-OS。该系统引入了数据库级 ACID 事务沙箱与基于 Merkle CAS 的黑匣子记录机制，支持在 0.4 毫秒内离线且零 API 成本地确定性回放 50 步 Agent 执行过程，并支持在任意步骤分叉调试。基准测试显示，其回放性能较重跑 API 提升约 9.3 万倍，副作用回滚延迟仅 0.19 毫秒，并内置循环检测熔断器，为构建高可靠生产级 Agent 提供了坚实的基础设施底座。

3.2 KB 1.9 KB 1.8 KB 652 B 615 B 6.2 KB 2.7 KB 621 B 65.7 KB

git clone https://github.com/socrates6969/jukebox-os.git
cd jukebox-os
pip install -e .

import asyncio
from jukebox import Jukebox, SandboxPolicy, CircuitBreaker

jb = Jukebox(
    tape_dir="./tapes",
    sandbox=SandboxPolicy(filesystem="copy_on_write", mcp_mode="staged_acid"),
    breaker=CircuitBreaker(max_cost_usd=0.50, max_semantic_repeat=3),
)

@jb.track(name="invoice-reconciliation-agent")
async def run_accounting_agent(customer_id: str, amount_usd: float) -> dict:
    async with jb.transaction(tape_id="tr_8f92a1c4") as tx:
        tx.record_agent_turn(
            agent_name="planner",
            message=f"Staging refund of ${amount_usd} for {customer_id}",
            model="gpt-4o",
            cost_usd=0.008,
        )
        tx.stage_file_write(
            path="./tapes/staged_ledger_demo.json",
            content=f'{{"customer": "{customer_id}", "refund_usd": {amount_usd}}}',
        )

        if amount_usd > 500.0:
            await tx.rollback(reason="Refund exceeds $500 autonomous threshold")
            return {"status": "ROLLED_BACK", "tape_id": tx.tape_id}

        await tx.commit()
        return {"status": "COMMITTED", "tape_id": tx.tape_id}

if __name__ == "__main__":
    print(asyncio.run(run_accounting_agent("cust_9981", 420.00)))

from jukebox import Tape

tape = Tape.load("./tapes/tr_8f92a1c4.jbx")
b_side = tape.fork(
    at_frame=3,
    override_model="claude-3-7-sonnet-latest",
    override_system_prompt="You are a strict SQL auditor. Never issue DELETE without a WHERE clause.",
)
print(b_side.replay_and_diff().to_markdown())

+-----------------------------------------------------------------------------------+
|                        APPLICATION & ORCHESTRATION LAYER                          |
|     [ LangGraph ]     [ CrewAI ]     [ AutoGen ]     [ OpenAI / Anthropic SDK ]   |
+-----------------------------------------+-----------------------------------------+
                                          |  @jukebox.track / MCP Proxy
                                          v
+-----------------------------------------------------------------------------------+
|                    🍒 JUKEBOX RUST CORE RUNTIME (libjukebox) 🔮                   |
|                                                                                   |
|  +-------------------------+  +-----------------------+  +---------------------+  |
|  |   ANTI-SKIP NEEDLE      |  |  BLAKE3 MERKLE CAS    |  |   OTEL GEN_AI       |  |
|  |  • Cosine Loop Breaker  |  |  • Zero-Cost Replay   |  |   EXPORTER          |  |
|  |  • Token Budget Gate    |  |  • .jbx Binary Tape   |  |  • Spans & Metrics  |  |
|  +-------------------------+  +-----------------------+  +---------------------+  |
|                                                                                   |
|  +-----------------------------------------------------------------------------+  |
|  |               SHADOW BOOTH: TRANSACTIONAL WASI & CoW SANDBOX                |  |
|  |   [ Virtual CoW Filesystem ]   [ SQL Savepoint Proxy ]   [ MCP Stage Gate ] |  |
|  +--------------------------------------+--------------------------------------+  |
+-----------------------------------------|-----------------------------------------+
                                          |
                     +--------------------+--------------------+
                     |                                         |
            [ VERIFIER PASSES ]                       [ VERIFIER FAILS ]
                     |                                         |
                     v                                         v
         ( ATOMIC WORLD COMMIT )                   ( INSTANT ZERO-RESIDUE )
         Writes flushed to Disk/API                  ROLLBACK & ALERT

# 列出本地包厢中最近的 Agent 飞行记录
$ jukebox ls --tape-dir ./tapes
🍒 JUKEBOX 24-HOUR FLIGHT RECORDER // LOCAL BOOTH TAPES 🔮
------------------------------------------------------------------------------
TRACK ID         AGENT NAME                     FRAMES   COST      STATUS      
------------------------------------------------------------------------------
tr_8f92a1c4      invoice-reconciliation-agent   5        $0.0080   COMMITTED   

# 在 1ms 内回放并加密验证 .jbx Merkle 磁带
$ jukebox replay ./tapes/tr_8f92a1c4.jbx

   ░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
   ░  BUILT WITH CHROME, NEON & RUST BY MARIUS CARLSSON (@mariuscarlsson)   ░
   ░         "THANK YOU FOR DINING AT JUKEBOX — DRIVE SAFELY!"              ░
   ░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░

git clone https://github.com/socrates6969/jukebox-os.git
cd jukebox-os
pip install -e .

import asyncio
from jukebox import Jukebox, SandboxPolicy, CircuitBreaker

jb = Jukebox(
    tape_dir="./tapes",
    sandbox=SandboxPolicy(filesystem="copy_on_write", mcp_mode="staged_acid"),
    breaker=CircuitBreaker(max_cost_usd=0.50, max_semantic_repeat=3),
)

@jb.track(name="invoice-reconciliation-agent")
async def run_accounting_agent(customer_id: str, amount_usd: float) -> dict:
    async with jb.transaction(tape_id="tr_8f92a1c4") as tx:
        tx.record_agent_turn(
            agent_name="planner",
            message=f"Staging refund of ${amount_usd} for {customer_id}",
            model="gpt-4o",
            cost_usd=0.008,
        )
        tx.stage_file_write(
            path="./tapes/staged_ledger_demo.json",
            content=f'{{"customer": "{customer_id}", "refund_usd": {amount_usd}}}',
        )

        if amount_usd > 500.0:
            await tx.rollback(reason="Refund exceeds $500 autonomous threshold")
            return {"status": "ROLLED_BACK", "tape_id": tx.tape_id}

        await tx.commit()
        return {"status": "COMMITTED", "tape_id": tx.tape_id}

if __name__ == "__main__":
    print(asyncio.run(run_accounting_agent("cust_9981", 420.00)))

from jukebox import Tape

tape = Tape.load("./tapes/tr_8f92a1c4.jbx")
b_side = tape.fork(
    at_frame=3,
    override_model="claude-3-7-sonnet-latest",
    override_system_prompt="You are a strict SQL auditor. Never issue DELETE without a WHERE clause.",
)
print(b_side.replay_and_diff().to_markdown())

+-----------------------------------------------------------------------------------+
|                        APPLICATION & ORCHESTRATION LAYER                          |
|     [ LangGraph ]     [ CrewAI ]     [ AutoGen ]     [ OpenAI / Anthropic SDK ]   |
+-----------------------------------------+-----------------------------------------+
                                          |  @jukebox.track / MCP Proxy
                                          v
+-----------------------------------------------------------------------------------+
|                    🍒 JUKEBOX RUST CORE RUNTIME (libjukebox) 🔮                   |
|                                                                                   |
|  +-------------------------+  +-----------------------+  +---------------------+  |
|  |   ANTI-SKIP NEEDLE      |  |  BLAKE3 MERKLE CAS    |  |   OTEL GEN_AI       |  |
|  |  • Cosine Loop Breaker  |  |  • Zero-Cost Replay   |  |   EXPORTER          |  |
|  |  • Token Budget Gate    |  |  • .jbx Binary Tape   |  |  • Spans & Metrics  |  |
|  +-------------------------+  +-----------------------+  +---------------------+  |
|                                                                                   |
|  +-----------------------------------------------------------------------------+  |
|  |               SHADOW BOOTH: TRANSACTIONAL WASI & CoW SANDBOX                |  |
|  |   [ Virtual CoW Filesystem ]   [ SQL Savepoint Proxy ]   [ MCP Stage Gate ] |  |
|  +--------------------------------------+--------------------------------------+  |
+-----------------------------------------|-----------------------------------------+
                                          |
                     +--------------------+--------------------+
                     |                                         |
            [ VERIFIER PASSES ]                       [ VERIFIER FAILS ]
                     |                                         |
                     v                                         v
         ( ATOMIC WORLD COMMIT )                   ( INSTANT ZERO-RESIDUE )
         Writes flushed to Disk/API                  ROLLBACK & ALERT

# List recent agent flight recordings in your local booth
$ jukebox ls --tape-dir ./tapes
🍒 JUKEBOX 24-HOUR FLIGHT RECORDER // LOCAL BOOTH TAPES 🔮
------------------------------------------------------------------------------
TRACK ID         AGENT NAME                     FRAMES   COST      STATUS      
------------------------------------------------------------------------------
tr_8f92a1c4      invoice-reconciliation-agent   5        $0.0080   COMMITTED   

# Replay & cryptographically verify a .jbx Merkle tape in <1ms
$ jukebox replay ./tapes/tr_8f92a1c4.jbx

   ░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
   ░  BUILT WITH CHROME, NEON & RUST BY MARIUS CARLSSON (@mariuscarlsson)   ░
   ░         "THANK YOU FOR DINING AT JUKEBOX — DRIVE SAFELY!"              ░
   ░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░