Inbound email triage · risk 2

01 / Trigger 02 / Context + preconditions 03 / HITL gate (Mike approves) 04 / Fan-out cascade 05 / Post actions (log_run + reflexion + events) 06 / Verify (SQL / R2 / HTTP checks) How this workflow gets kicked off. Could be a chat-tool invocation, a cron tick, an inbound event (e.g. price.changed), or Mike clicking 'execute' from an admin page. TRIGGER kind: event sources: cf_email_routing invoker: Mike (single-admin) risk_level: 2i Manual Mike invokes risk 2 Before deciding anything, pull related data from D1 (the local mirror of NetSuite). Each query loads a slice of the entity's current state so the AI and Mike can review before any writes happen. LOAD CONTEXT (D1 queries before fan-out) sender_known: SELECT id, type FROM (SELECT id, 'customer' AS type FROM customers WHERE LOWER(… existing_thread: SELECT id, workflow_routed_to FROM inbound_email_log WHERE from_email=? AND sub…i Load context 2 D1 queries Safety checks that must pass before any writes. 'block' severity halts the run; 'warn' surfaces a warning but continues. Without these, a bad input could cascade into NetSuite. PRECONDITIONS (checked before fan-out) [block] valid_from: from_email LIKE '%@%' [warn] not_spam: sender_known IS NOT NULL OR is_known_domaini Preconditions 2 checks The HITL (Human-In-The-Loop) gate. The workflow stages a proposed_action and waits for Mike to approve in /proposed-actions.html. Only fires when risk_level >= 3. This is the invariant: no NS write happens without Mike's go-ahead. HITL GATE (Mike approves before fan-out) action_type: workflow_inbound_email_triage entity_ref: workflow:inbound_email_triage:run_<run_id> approver: mike (single-admin) risk_gate: >= 3 (this workflow = 2) approval window: typical <= 60 min envelope: proposed_actions row staged by runneri No HITL auto-execute (risk ≤ 2) low risk Write to the local D1 mirror (the read-side cache of NetSuite). Used for derived data and platform state. STUB today - per-tool d1_write logic lives in chat_tools/impls.ts. FAN-OUT #log -> D1: multiple kind: d1_write op: INSERT inbound_email_log status: REAL (src/lib/workflow_runner.ts)i log d1_write STUB Repeat the same fan-out for each item in a collection (recipients, aging buckets, sub-workflows). STUB today. FAN-OUT #route_to_workflow -> multiple (loop) kind: dispatch_workflow bid_amendment -> bid_amendment_arrives invoice_dispute -> customer_invoice_dispute vendor_cost -> vendor_cost_update spec_sheet -> new_assembly_item status: STUB (src/lib/workflow_runner.ts)i route_to_workflow dispatch_workflow STUB Draft an email and stage it as a proposed_action for Mike's review. The email is NOT sent - only drafted + queued. STUB today. FAN-OUT #draft_response -> email draft kind: hitl_email_draft if: classification != spam AND requires_response tool: propose_email_to_customer status: STUB (src/lib/workflow_runner.ts)i draft_response hitl_email_draft STUB Always-runs at the end of every workflow execution: writes a row to workflow_run_log with status, duration, step counts, and errors. Real implementation. POST ACTION: log_run -> D1: workflow_run_log fields: run_id, workflow_type, status, started_at, completed_at, summary_json source: runner automatic (always)i log_run workflow_run_log REAL Writes an entry to reflexion_log so the AI 'remembers' what happened. Only fires if the contract has reflexion_enabled=1. Future workflows can search this log for prior context. Real implementation. POST ACTION: reflexion -> D1: reflexion_log tags: inbound_email_triage reflexion_enabled: True fields: run_id, narrative, tags source: runner automatic (when reflexion_enabled=1)i reflexion reflexion_log REAL Fires a workflow.completed / workflow.partial / workflow.failed event into the event ledger so downstream subscriptions can react. Uses an idempotency_key so producer retries collapse. Real implementation (R564). POST ACTION: event -> Event ledger (recordEvent) types: workflow.completed | workflow.partial | workflow.failed idempotency_key per run_id source: runner automatici event workflow.completed REAL A post-execution sanity check. The runner stages this with status='pending'; the verify-scheduler cron (every :08 and :38 hourly) wakes up after the configured window (e.g. +24h) and executes the sql_check, then flips status to pass/fail/timeout. Real implementation (R564). VERIFY: email_logged window: 2s sql_check: SELECT id FROM inbound_email_log WHERE email_uuid=? scheduler: verify cron @ :08/:38 (R563) result row: workflow_verify_resultsi email_logged ≤60m A post-execution sanity check. The runner stages this with status='pending'; the verify-scheduler cron (every :08 and :38 hourly) wakes up after the configured window (e.g. +24h) and executes the sql_check, then flips status to pass/fail/timeout. Real implementation (R564). VERIFY: routed window: 5s sql_check: SELECT workflow_routed_to FROM inbound_email_log WHERE email_uuid=? scheduler: verify cron @ :08/:38 (R563) result row: workflow_verify_resultsi routed ≤60m Legend User UI Agent logic Policy Tool action Context / trace

Contract

  • • Type: inbound_email_triage
  • • Risk: 2
  • • Trigger: manual
  • • Fan-out: 3 targets

HITL semantics

  • • risk ≤ 2 ⇒ auto-execute
  • • No HITL required
  • • REAL = solid green · STUB = dashed

Post actions

  • • log_run → workflow_run_log
  • • reflexion → reflexion_log
  • • event → workflow.completed
  • • verify × 2

Workflow diagram • Built with Archify • Press T for theme and E for export