dsh-omp-retry

An OMP-style retry policy for HTTP 429 responses in the DeepSeek Harness.

DSH's built-in dsh-llm-retry uses one bounded exponential policy for every transient failure. With defaults that is five retries from 500 ms to 10 s, so a TPM/RPM window can still be active when the budget is gone. OMP treats rate limits differently: it keeps retrying for up to ten attempts, waits at least 30 seconds, and accepts a provider Retry-After up to five minutes.

This bundle adds that rate-limit behavior without forking DSH. It prepends one agent/request-error listener ahead of dsh-llm-retry and owns only RATE_LIMIT; every other failure code stays with the built-in executor.

Behavior

• Up to 10 rate-limit retries per failed step (configurable).
• Delay is max(30 s, provider Retry-After).
• A required wait above 5 minutes ends the retry chain instead of sleeping.
• Each scheduled retry appends durable llm/retry / llm/retry-started events, so the normal retry UI and session history still work.
• Cancellation, turn end, and plugin disposal abort the active wait.
• SERVER, TIMEOUT, TRANSPORT, and EMPTY_RESPONSE are left to dsh-llm-retry with the provider's own policy.
• CONTEXT_WINDOW_EXCEEDED, QUOTA, AUTH, and INVALID_REQUEST are never retried by this plugin.

Install

dsh plugin --profile desktop add github:Rinai-R/dsh-omp-retry

Use your profile name instead of desktop for a web or custom profile, then restart DSH. The bundle inserts the omp-rate-limit-retry row itself.

Configuration

The defaults are maxRetries: 10, floorMs: 30000, and maxDelayMs: 300000. Override the row in the profile's cordis.patch.yml:

- id: omp-rate-limit-retry
  config:
    maxRetries: 10
    floorMs: 30000
    maxDelayMs: 300000

maxRetries: 0 disables the plugin. The plugin's budget is independent of the provider's retryPolicy.maxRetries: a provider left at the default five still gets ten rate-limit attempts.

For fast non-429 retries, keep the provider policy close to OMP's local backoff:

retryPolicy:
  mode: normal
  maxRetries: 10
  retryableCodes:
    - EMPTY_RESPONSE
    - RATE_LIMIT
    - SERVER
    - TIMEOUT
    - TRANSPORT
  backoff:
    initialDelayMs: 500
    maxDelayMs: 8000
    jitterRatio: 0.25

Keeping RATE_LIMIT in the list is a fallback for when this bundle is removed; while the bundle is active it takes 429s first.

Compatibility

Tested against DSH Desktop 0.2.1-rc.2. The plugin relies on:

• the agent/request-error waterfall,
• the llm-retry session projection (llmRetry),
• the llm/retry event shape used by the built-in retry executor.

If a future DSH changes those contracts, the plugin may need an update; it fails closed by delegating to the next listener.

Development

No build step, no runtime dependencies:

npm test

Limitations

• This is not Ghostty, and it is not a general retry framework: it only covers HTTP 429 rate limits.
• OMP's model/credential fallback chains are not implemented.
• A provider Retry-After above maxDelayMs is not waited out.

License

MIT