Long-Running Agent Job with Claude Code: API Runtime Pattern
A production playbook for long-running agent job in cross-industry operations using Claude Code: api runtime pattern, run-scoped inputs, logs, typed results, and artifacts.
Audience: AI product teams running multi-minute workflows
The problem
AI product teams running multi-minute workflows need long-running agent job to run repeatedly against documents, repos, tool access, and output contracts. In cross-industry operations, the pain is not one good answer; it is repeatability, auditability, exception handling, and evidence that survives handoff.
Implementation path
Package the long-running agent job instructions as a skill, send documents, repos, tool access, and output contracts as run-scoped inputs, execute with Claude Code, poll terminal status, and consume argo.result.v1 instead of parsing a transcript.
Tradeoffs and failure modes
The API boundary forces the workflow to define inputs, terminal states, and result shape before customers depend on it. For long-running agent job, the practical test is whether a second run can be debugged, retried, and consumed by a product without reading the raw agent transcript.
Run request
POST /api/skills/<skill_id>/run
provider=claude-code
workflow=long-running-agent-job
inputs[]=@./input-pack.zip
result_schema=argo.result.v1
Run this on Argo