4.1 KiB
4.1 KiB
Step 12 — Implementation Detail
Built against a scripted decider. No call has been made to the live Jev service, and no evaluation has run on it: the owner holds evaluation runs until the Jev work is in.
app/nodes/router.py.Routerdecides an Orchestrator turn in three stages: readings (_read_ledgerfrom the Ledger and data;_read_messageand_read_gapfrom the decider), a disposition byThresholds(act at 0.75, close at 0.15, choice confidence 0.6), and the playbook in_choose: ordered groups, the strongest action whose conditions hold, escalate when none applies.- Permission stays with the tools. The router calls the same
OrchestratorToolboxtools the model did. A refused action is skipped for the rest of the turn and the next one that holds is taken. Past the Revision limit the user is asked. - What Jev is asked (
Questionobjects, batched when they rest on the same evidence):- of the user's message:
asks_change(noul),change_target(choice over submitted Deliverables),change_clarity(score: vague, partial, specific); - of validation gaps:
gap_material(noul); - of the user's reply about gaps:
wants_revision(noul). What is sent is Deliverable names, the count of waiting questions, the user's message, and for gaps the proposed Check statements and unverifiable Check ids.
- of the user's message:
- Rules when Jev gives no answer. A requested change is acted on only when one Deliverable is named outright, otherwise the user is asked which. A free-text reply is treated as an answer. A gap is revised for when a Check cannot be verified or an addition names a real requirement or recommendation id.
- A new reading from the run of 2026-10-07: a Check that fails in two validations running is sent to the Target architecture, not the code. That run retried one unimplementable Check as code three times.
- Decisions are recorded in the Execution's state under
decisions: turn, group, action and what was judged, with confidence. - The reply writer. A new role,
agents/reply-writer.md, writes the Approval summary from facts (approval_facts) through one tool. When it fails or is absent,assembled_summarybuilds the summary from the same facts. - Wiring.
ORCHESTRATOR=router(the default) ormodel;open_assemblybuilds the router with the decider and the thresholds (JEV_ACT_THRESHOLD,JEV_CLOSE_THRESHOLD,JEV_CONFIDENCE_THRESHOLD). State gainedlast_reply,pending_change,awaiting_gap_decision,validation_settledanddecisions.
Changed from the plan and the ADR's first wording:
- Jev does not propose the next action. It supplies readings, and the playbook in code picks the action. This follows the owner's triage model and keeps every decision explainable by a rule and a threshold.
- The model Orchestrator is kept behind
ORCHESTRATOR=model. The 40 or so engine tests drive the Ledger's rules by scripting its tool calls in arbitrary order, which the router cannot do.agents/orchestrator.mdis therefore unchanged and unused in router mode. - An unclear change is confirmed once. If the reply still does not settle it, a named Deliverable is acted on and anything else is dropped.
- A pre-approved Execution's automatic replies are not routed. There is no user message to read.
Not built from the ADR's routes:
- A message that starts something (new request, Change request, question about delivered work, out of scope). It needs an entry point that can answer from a case's files, and Change requests (iteration 7).
- Which Deliverables a Change request reaches. Iteration 7.
Tests: tests/execution/test_router.py (18), tests/test_assembly.py.
Unverified:
- Whether Jev's answers to these five questions are good enough at these thresholds. The thresholds are the ones in the owner's example and are untuned.
- Whether the reply writer's summaries are accurate. It is instructed to state only the facts it is given; nothing checks that it does.
- Run time. The Orchestrator made 31 model requests in the last run; the router makes none, and one small writer call per Approval. No run has measured it.