Error while using omni route api

[ganeshgupta2004]

Request exceeded OmniRoute's local rate-limit execution expiration (legacy resilienceSettings.requestQueue.maxWaitMs=15000ms) for antigravity/claude-opus-4-6-thinking. Bottleneck applies this deadline only after dispatch; it does not bound queue wait and is not an upstream-generated timeout." This subagent session can be resumed: call the task tool again with task_id="ses_f801c1beaffevhFjW7zwNuEOA6" and a prompt describing how to continue or recover. Its prior context is preserved.

Got the above error while using api in Antigravity, someone help

[geekyNads]

This looks like OmniRoute's local Bottleneck execution expiration rather than an upstream Claude timeout. The important part is that maxWaitMs=15000ms applies after dispatch, so increasing it may help with slow Opus Thinking requests, but it won't fix an upstream 429/rate-limit if Antigravity is the actual bottleneck.

I'd try increasing RATE_LIMIT_MAX_WAIT_MS to 30000 and restarting OmniRoute, then check the OmniRoute logs for the same request. If it still fails, test the same request with another model/provider to determine whether this is specific to antigravity/claude-opus-4-6-thinking.

Also, the session ID in the error indicates the task context is preserved, so you should be able to resume the existing task rather than starting over.

If you can share the OmniRoute logs from the failed request, that should make it possible to distinguish between the local execution expiration and an Antigravity-side rate limit.