rebunoFetch, so every model call is
recorded as an llm_call step, and tools run through defineTool, so every
tool call is recorded as a tool_call step. On a re-dispatch the agent runs
from the top and recorded steps replay instead of calling the model or the tool
again.
Install
Model calls
Build theOpenAI client yourself with rebunoFetch, and hand it to the model:
Tools
Declare the Rebuno side withdefineTool, and pass it as the execute of an
SDK tool:
errorFunction: null to let
it unwind the run instead. A denied tool still returns the rule’s reason to the
model, since a denial doesn’t throw.
Mark anything with a side effect, such as sending an email or creating a
ticket, at_most_once. See idempotency.
The agent
The SDK’sAgent and Rebuno’s Agent share a name, so import one under an
alias:
What Rebuno adds
- Policy. Every model and tool call is checked against policy before it runs. A denied tool returns the rule’s reason to the model as the tool result, so the agent can take a different path.
- Approvals. A tool that requires approval parks the execution. Once it’s approved, the agent is dispatched again, the earlier steps replay, and the approved call runs.
- Recovery. If the worker dies partway through, the next dispatch replays every completed step and continues from the first one that didn’t finish. Model calls that already ran are not paid for twice.
Full example
examples/frameworks/typescript/openai_agents_agent.ts
is a support agent that investigates a customer issue, creates a ticket, and
emails a summary after approval.