# Making every harness durable

Source: [Vercel](https://vercel.com/blog/making-every-harness-durable)  
Feed7 permalink: https://feed7.dev/p/making-every-harness-durable-1rmx66o  
Published: 2026-10-19T13:00:00.000Z  
Trust: Official Source (official_source)

## Why Included

Vercel’s open-source durable-harness logs model and tool steps so cloud coding agents can resume after crashes without rerunning completed calls.

## Source Summary

Vercel’s open-source **durable-harness** adds crash recovery to Pi, OpenCode, Codex, Claude Code, and custom harnesses. It records each model or tool-call intent and outcome, then backs the turn with a queue message.

## Practical Implication

For long-running coding agents, persist execution state outside the process. After a crash or timeout, a new function reads the log, restores harness session records, and resumes; **completed calls do not run again**, avoiding repeated model charges.

## Agent-Ready Context

Vercel’s open-source **durable-harness** adds crash recovery to Pi, OpenCode, Codex, Claude Code, and custom harnesses. It records each model or tool-call intent and outcome, then backs the turn with a queue message.

For long-running coding agents, persist execution state outside the process. After a crash or timeout, a new function reads the log, restores harness session records, and resumes; **completed calls do not run again**, avoiding repeated model charges.

Tool recovery is not universally automatic. Interrupted tools marked **replay: 'safe'** run again, while other tools return as possibly executed and leave the model to decide whether to inspect before continuing.

## Connected Context

Feed7 judgment across 898 accumulated Signals:

This turns the prior durability guidance into a reusable implementation across several coding-agent harnesses. Its intent/outcome log and queue-backed turns address crash recovery and duplicate model charges, while replay labels expose the remaining hard boundary: an interrupted external tool may have executed. Recovery therefore still requires idempotent tools or post-failure inspection, not blind replay.

- [AI Agents Are Just Distributed Systems Now — Salman Munaf, TikTok](https://feed7.dev/p/ai-agents-are-just-distributed-systems-now-salman-munaf-tiktok-1v4yc47) — Durable Harness implements the persisted-step and recovery side of the distributed-systems guidance, while its possibly-executed tool state confirms that timeout ambiguity still requires idempotency or reconciliation.
- [Every step you take, every call you make: the reliable agent stack — Giselle van Dongen, Restate](https://feed7.dev/p/every-step-you-take-every-call-you-make-the-reliable-agent-stack-giselle-1ojh38b) — Restate frames durable state, retries, and recovery as infrastructure concerns; Durable Harness supplies a concrete queue-and-log design for applying that pattern to existing coding harnesses.
- [What we’ve learned building cloud agents](https://feed7.dev/p/cloud-agent-lessons-06dh9iq) — Cursor’s Temporal rewrite provides reinforcing operational evidence that durable orchestration matters for cloud-agent reliability, while Durable Harness makes a related recovery pattern portable across multiple harnesses.
- [Agent Frameworks Considered Harmful — Rémi Louf, .txt](https://feed7.dev/p/agent-frameworks-considered-harmful-remi-louf-txt-1ku9s0h) — The append-only intents and outcomes, queue-backed turns, and replay handling closely instantiate the candidate’s call for durable events, causal traces, and replay-oriented runtime primitives.

## Context Map

- Layer: agent
- Domains: coding
- Topics: harness-engineering, agent-reliability, cloud-agents

## Uncertainty

- Tool recovery is not universally automatic. Interrupted tools marked **replay: 'safe'** run again, while other tools return as possibly executed and leave the model to decide whether to inspect before continuing.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.