Skip to main content
Replay lets you run agent logic without re-calling external systems by returning recorded outputs for instrumented actions.

​
Use replay mode

from agent_sentinel import replay_mode, guarded_action

@guarded_action(name="fetch_data", cost_usd=0.01)
def fetch_data(url: str) -> dict:
    return {"url": url, "data": "..."}

# First run: records to ledger
fetch_data("https://example.com")

# Later: replay from ledger
with replay_mode(ledger_path=None, strict=True):
    fetch_data("https://example.com")  # returns recorded output

​
Divergence detection

In strict mode, replay raises ReplayDivergenceError when inputs don’t match what was recorded.

​
v0.1 limitation (run_id filtering)

In v0.1 the local ledger format does not store run_id per entry, so ReplayMode.from_run_id(...) cannot reliably filter a single run from a shared ledger file. Replay currently operates over ledger entries in recorded order.
If you need per-run replay isolation today, write to separate ledgers per run (e.g., via process-level separation or separate AGENT_SENTINEL_HOME per run).