Agent harness

Long jobs

A long job lets the agent work through a bigger task over several turns, in a folder you choose.

Copy page
View as Markdown

What a long job is

A long job is the same agent loop with a bigger budget and a folder to work in. Long jobs are part of the Python SDK (pip install harny, module harny.agent). They are off by default. You turn them on with long_task in AgentConfig.

The model runs on your own model key. Harny never sees it. For the basic agent setup, see Agent harness overview. For the memory a job can read, see Memory API.

Set up a long job

Pass a LongTaskConfig with a workspace folder, then start the job with run_task:

from harny.agent import Agent, AgentConfig, FileSessionStore
from harny.agent.long_task import LongTaskConfig

agent = await Agent.create(
    harny=harny,
    provider="your-provider",
    model="your-model-id",
    config=AgentConfig(
        instructions="You work through a folder of tenant emails for the office manager.",
        long_task=LongTaskConfig(workspace="./jobs/renewals"),
    ),
    store=FileSessionStore("./data/sessions"),
)
result = await agent.run_task(user="demo-user", message="List the tenants whose lease ends within 45 days.")

Limits per turn

LimitDefault
Model calls per turn100
Seconds per turn3,600
Turns in a chainup to 10
Spend cap5,000,000 tokens

Folder and shell

The folder and any shell are yours. Harny hosts nothing for a long job. Choose a workspace path your deploy can write to, and review what the job can run before you turn it on.

Backup model on errors

The job runs on the one model you set. On a transient provider error, the SDK retries the call twice. If it still fails, the turn stops and says why. You can run the same job again with the same message to resume.

Example: leases ending soon

Put the tenant emails in the workspace folder. Then ask the job:

List the tenants whose lease ends within 45 days.

The run answers with the list it finds. Check the answer against the emails before you act on it.

Next