When it does not work

Troubleshooting

Almost every problem is visible in one of two places: the error body (code, message, field errors) or the run trace. Start there before anything else.

Common failures

symptomlikely causefix
401 on every callKey revoked, or sandbox key against productionmynd auth status; check the key prefix
scope_denied mid-runRun requested a source the key lacksGrant the scope named in the error, or drop the source
step_limit on simple promptsVague prompt forcing exploratory planningNarrow the ask; raise max_steps only if genuinely multi-step
Summary cites wrong documentRetrieval pulled a near-duplicateRead the trace's context items; tighten filters or dedupe ingestion
Webhook never arrivesEndpoint paused after failures, or signature rejectsDashboard → endpoint status; mynd webhooks tail to compare
Agent stops without actingApproval gate reached, nobody approvingPoll run.pending_actions or subscribe to run.awaiting_approval
429 at low trafficBurst concentration inside one windowSmooth bursts; batch embeddings; check per-bucket headers

Reading a trace for debugging

GET the run with include_trace=true. Check, in order: the plan (did it decompose the way you expected?), the context entries (what was fetched, what was not), each step's action, and the result. Most 'the model is wrong' reports are actually 'the model never saw the right context' — and the trace shows that directly.

When to contact support

Include the run id and the X-Request-Id of the failing call — with those two we can replay the exact execution. 500s with the same request id recurring, audit-log discrepancies, or suspected cross-project visibility go straight to support@myndlabs.ai with [urgent] in the subject.