Skills
.Work. You
Rest

long-running-server

Community

Run agent tasks past HTTP timeouts.

Software Engineering#background tasks#polling#responses api#databricks#lakebase#agent server#async streaming
Authorkeqingli1129
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Long-running agent requests fail or time out when an HTTP client or gateway limits execution duration, forcing you to retry and losing progress.

Core Features & Use Cases

  • LongRunningAgentServer background execution: Enables background/async execution so requests can continue after the initial HTTP call finishes.
  • Client-friendly polling and streaming: Supports background=true with GET /responses/{id} polling, and background=true&stream=true with cursor-based resumption via starting_after.
  • Lakebase persistence for resilience: Persists long-running task state to Lakebase PostgreSQL so results can be retrieved reliably even when the original request times out.

Quick Start

Add databricks-ai-bridge[agent-server]>=0.18.0, replace AgentServer with LongRunningAgentServer, configure Lakebase env vars in .env (or databricks.yml), and start the server so background requests can be polled or streamed.

Dependency Matrix

Required Modules

databricks-ai-bridge[agent-server]mlflow

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: long-running-server
Download link: https://github.com/keqingli1129/agent-langgraph-one/archive/main.zip#long-running-server

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.