Handle failures and retries

Map failure classes for POST /v1/workflows/email-triage/runs: retryable vs fatal vs needs-human. Retries need budgets, jitter, and idempotency rules aligned to send step requires approval token; classifier never triggers send directly. The chapter’s signature failure — model labels 'issue refund' and workflow auto-calls payment tool — must take a deliberate branch, not a generic catch-all.

Implement the degrade/rollback/refuse behavior ops coordinator clearing a 200-message backlog without auto-sending refunds needs when WF-AUTOSEND-19 repeats. Prefer scoped controls (one flag, one weight, one tenant, one secret version) over fleet-wide restarts. Preserve evidence; do not delete logs to “clean the demo.”

After containment, check unapproved_send_count == 0 and median_time_to_draft ≤ 45s moves in the safe direction and watch for retry amplification. Write the stop condition that ends the incident response for this lab.

Chaos note: inject only one fault class at a time and restore fixtures after. Watch for dual failures — dependency down and retry amplifier — which is how model labels 'issue refund' and workflow auto-calls payment tool becomes an outage. Customer communication templates (even if only for the drill) beat silence. If you queue deferred work, define poison-message handling. Budget documents should state the maximum extra spend allowed during retries. Close the loop by linking the containment action to a dashboard panel for unapproved_send_count == 0 and median_time_to_draft ≤ 45s.

Draw a state diagram for degrade modes and put it in the repo as ASCII if needed. Cap concurrent retries across the process, not only per request. Ensure cancellation propagates to downstream HTTP clients. When failing closed, choose a user-visible message that does not leak internals. Practice the single command that flips the kill switch or weight to zero. After recovery, drain or inspect deferred work before declaring green. In this chapter the product is typed workflow that classifies inbound email → draft reply → human approve → send, the human stakeholder is ops coordinator clearing a 200-message backlog without auto-sending refunds, and the incident id you design against is WF-AUTOSEND-19. Re-state the oracle in your notes — fixture thread reaches awaiting_approval with draft; send blocked until Approve(id) — and keep the invariant visible: send step requires approval token; classifier never triggers send directly. Track unapproved_send_count == 0 and median_time_to_draft ≤ 45s as the scoreboard. Surface under change control: POST /v1/workflows/email-triage/runs. If you only have forty minutes, finish the fixture for model labels 'issue refund' and workflow auto-calls payment tool before polishing UI. Promotion language stays ternary: promote, hold, or roll back based on evidence, not hope.