[Feature Request] Configurable Retry Mechanism via opencode.json

This is a request to add a retry mechanism that can be configured through opencode.json.

For example, we should be able to define retry settings per provider—such as allowing up to 3 retries within a customizable time window (e.g., 5 seconds). This would improve reliability, especially since the current implementation lacks configurable retries.

This issue might be a duplicate of existing issues. Please check:

handle LLM overload errors (e.g. {"type": "overloaded_error", "message": "Overloaded"}) #833: Already requests automatic retry handling for LLM overload errors with configurable retry limits and delays
Needs improved handling and reporting for errors/LLM inference failed #2455: Requests improved error handling with retry counters and timeout displays (mentions "Retrying 1 or 10" with countdown)
Feature Request: Request delay setting #1592: Requests configurable request delay settings between API calls
[Bug] Timeout not working for Local LLM with MLX Models #2974: Related timeout configuration issues that aren't being respected in opencode.json

Feel free to ignore if none of these address your specific case.

Also This retry mechanism should also handle provider-specific API errors.

Yeah we do already have retries setup but making it configurable makes sense. This is probably a lower priotiery currently tho

@rekram1-node

Yeah we do already have retries setup but making it configurable makes sense. This is probably a lower priotiery currently tho

@rekram1-node, regarding the configurable retry mechanism for handling API errors, I think it would be better to use a fixed interval. For example, we could set 4 retries over 10 seconds—so each retry happens every 2.5 seconds—or simply retry every 10 seconds. This would be simpler than increasing the delay between retries (i.e., exponential backoff).

Yeah we do already have retries setup but making it configurable makes sense. This is probably a lower priotiery currently tho

What's the default for retries at the moment? It might be low priority for those using stable internet, reliable providers, and perfectly compatible models... but for those who aren't so lucky... it's an easy way to recover from errors and hiccups without having to habitually say "Continue".

Claude Code has the ENV var CLAUDE_CODE_MAX_RETRIES which I have set to 100. That works for API errors as well as API timeouts. Opencode seems to give up after a single timeout?

There is also this! #2116

yeah it looks like itd be pretty simple to add a config setting or an env var, I will take a look at pr later

Using OpenCode with gpt-5.2-codex from Azure, I frequently get ratelimit errors and timeouts. In Codex, setting max retries to 100 mostly solves the problem. In OpenCode, I frequently have to say "continue".
Very annoying for unsupervised sessions.

To stay organized issues are automatically closed after 90 days of no activity. If the issue is still relevant please open a new one.

The configurable retry mechanism is now implemented natively in #26292 — supports array in config, , per-agent overrides, and header parsing.

The configurable retry mechanism is now implemented natively in #26292 — supports fallbacks array in config, cooldown_seconds, per-agent overrides, and retry-after header parsing.

is there a way to bind a mapping to a 'retry' action? So that when I kill the subagent elsewhere etc. that was stalling my main agent because of api parallel limits I would be able to immediately tell the main agent to continue instead of waiting the given interval?

Navigation Menu

Repository navigation

[Feature Request] Configurable Retry Mechanism via opencode.json #3011

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

[Feature Request] Configurable Retry Mechanism via opencode.json #3011

Description

Activity

github-actions commented on Oct 7, 2025

H0llyW00dzZ commented on Oct 7, 2025

rekram1-node commented on Oct 7, 2025

H0llyW00dzZ commented on Oct 7, 2025

kierr commented on Oct 8, 2025

kierr commented on Oct 8, 2025

rekram1-node commented on Oct 8, 2025

adamal commented on Jan 24, 2026

github-actions commented on Mar 27, 2026

j3k0 commented on May 17, 2026

j3k0 commented on May 17, 2026

litoj commented on Oct 14, 2026

Metadata

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Issue actions