New assembly item (full spec → BOM → NS) · risk 4 (Part 1 of 2)

01 / Trigger 02 / Context + preconditions 03 / HITL gate (Mike approves) 04 / Fan-out (Part 1 of 2) 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: manual sources: spec_sheet_upload, intake_form invoker: Mike (single-admin) risk_level: 4i Manual Mike invokes risk 4 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) existing_item_by_upc: SELECT id, itemid FROM items WHERE upccode=? LIMIT 1 existing_spec: SELECT id FROM spec_items WHERE item_code=? brand_rules: SELECT * FROM brand_routing_rules WHERE brand=? shared_brand_customers: SELECT DISTINCT customer_id FROM pricing_master WHERE item_code IN (SELECT item…i Load context 4 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] item_code_unique: existing_item_by_upc IS NULL AND existing_spec IS NULL [warn] allergens_present: allergen_facts IS NOT NULL [warn] vendor_cost_provided: vendor_costs.length > 0 [block] bom_complete_if_assembly: NOT is_assembly OR bom_components.length > 0i Preconditions 4 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_new_assembly_item entity_ref: workflow:new_assembly_item:run_<run_id> approver: mike (single-admin) risk_gate: >= 3 (this workflow = 4) approval window: typical <= 60 min envelope: proposed_actions row staged by runneri Mike approves stage_proposed_action risk ≥ 3 gate 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 #write_spec_items -> D1: spec_items kind: d1_write op: INSERT INTO spec_items (...) op: INSERT INTO spec_versions (spec_item_id, changed_field=created, new_value=ful… status: REAL (src/lib/workflow_runner.ts)i write_spec_items d1_write STUB 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 #write_items -> D1: items kind: d1_write parallel_with: write_spec_items op: INSERT INTO items shell status: REAL (src/lib/workflow_runner.ts)i write_items d1_write STUB Invoke an existing chat tool (one of 50+ registered in tool_registry) as part of the cascade. STUB today - runner doesn't yet dispatch. FAN-OUT #recompute_assembly -> tool: recompute_assembly_cost_rollup kind: chat_tool if: is_assembly tool: recompute_assembly_cost_rollup status: REAL (src/lib/workflow_runner.ts)i recompute_assembly chat_tool STUB Pushes a write back to NetSuite via the NS_PUSH_QUEUE. The push is staged in ns_pending_pushes first and only flips to 'applied' after NS confirms. STUB today - the runner logs intent but doesn't enqueue yet. FAN-OUT #write_ns_item -> NS_PUSH_QUEUE: item kind: ns_push queue: NS_PUSH_QUEUE on_failure: retry_3_then_alert record_type: item status: REAL (src/lib/workflow_runner.ts)i write_ns_item ns_push STUB Pushes a write back to NetSuite via the NS_PUSH_QUEUE. The push is staged in ns_pending_pushes first and only flips to 'applied' after NS confirms. STUB today - the runner logs intent but doesn't enqueue yet. FAN-OUT #write_ns_bom -> NS_PUSH_QUEUE: bom kind: ns_push if: is_assembly queue: NS_PUSH_QUEUE record_type: bom status: REAL (src/lib/workflow_runner.ts)i write_ns_bom ns_push STUB Fire an HTTP request to another endpoint (often a self-fetch to /api/). STUB today - runner doesn't yet make the call. FAN-OUT #generate_spec_sheet -> HTTP POST /api/spec/generate kind: http_call status: REAL (src/lib/workflow_runner.ts)i generate_spec_sheet http_call 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: new_assembly_item 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: spec_persisted window: 5s sql_check: SELECT id FROM spec_items WHERE item_code=? scheduler: verify cron @ :08/:38 (R563) result row: workflow_verify_resultsi spec_persisted ≤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: items_shell_created window: 5s sql_check: SELECT id FROM items WHERE itemid=? scheduler: verify cron @ :08/:38 (R563) result row: workflow_verify_resultsi items_shell_created ≤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: ns_item_reflects window: 15m sql_check: SELECT id FROM items WHERE itemid=? AND lastmodifieddate > ? scheduler: verify cron @ :08/:38 (R563) result row: workflow_verify_resultsi ns_item_reflects ≤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: assembly_rollup_prese… scheduler: verify cron @ :08/:38 (R563)i assembly_rollup_prese… ≤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: spec_pdf_present window: 60s scheduler: verify cron @ :08/:38 (R563) result row: workflow_verify_resultsi spec_pdf_present ≤60m Legend User UI Agent logic Policy Tool action Context / trace

Contract

  • • Type: new_assembly_item
  • • Risk: 4
  • • Trigger: manual
  • • Fan-out: 6 targets (Part 1 of 2)

HITL semantics

  • • risk ≥ 3 ⇒ stage_proposed_action
  • • Mike approves before fan-out
  • • REAL = solid green · STUB = dashed

Post actions

  • • log_run → workflow_run_log
  • • reflexion → reflexion_log
  • • event → workflow.completed
  • • verify × 5