Files
gcp_solution_architecture_a…/.agents/plans/iter-05-jev-decisions/steps/step-12.md
Jonathan Boniface 654370bb46 feat: all four evaluation cases pass; intake, checklist review, thresholds
Case 04 (interactive)
- A scripted answer may name who it is for, so facts written for
  requirements discovery are not given to a Specialist confirming a draft.
- A reply that restates what the agreed requirements already say is read
  as an answer, not a request for changes.
- With a user present, a first submission is refused until the user has
  been shown a draft of that Deliverable (CONFIRM_DRAFTS).

Routing and reviews
- Intake: a message that starts something is read first. A question is
  answered and starts nothing; a change to delivered work starts as a new
  request with a note, until Change requests are built.
- Requirements and recommendations list what infrastructure code can show
  (conditions) apart from what it cannot (outside_code); the latter needs
  no Check and validation proposes nothing for it.
- A requirements review, "names no products", behind its own switch (off).
- Each pillar advisor reviews its pillar's checklist; the engine writes the
  reviews into the design recommendations. The judged checklist check went
  from 9-45% a pillar to 100% in one run of case 04.

Evaluation
- Per-case thresholds for Revisions, seconds and tokens, set from every
  completed run on this build.
- A progress file after every agent run, so an interrupted run keeps its
  time and tokens.
- eval/calibrate_judge.py with a 32-question set awaiting a person's
  labels. Unlabelled: Jev stable at 1.00, Gemini 0.92, agreeing on 0.91.

Smaller
- An Execution that ends with warnings writes its Deliverables, with the
  warnings and each status in the manifest.
- CI installs the application's dependencies before linting and testing.
- A load-balancer pattern in the IaC patterns Skill.

Plans record nine runs of 2026-10-08. Iteration 6 is complete.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-09 09:32:57 +01:00

8.3 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.

  1. app/nodes/router.py. Router decides an Orchestrator turn in three stages: readings (_read_ledger from the Ledger and data; _read_message and _read_gap from the decider), a disposition by Thresholds (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.
  2. Permission stays with the tools. The router calls the same OrchestratorToolbox tools 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.
  3. What Jev is asked (Question objects, 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.
  4. 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.
  5. 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.
  6. Decisions are recorded in the Execution's state under decisions: turn, group, action and what was judged, with confidence.
  7. 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_summary builds the summary from the same facts.
  8. Wiring. ORCHESTRATOR=router (the default) or model; open_assembly builds the router with the decider and the thresholds (JEV_ACT_THRESHOLD, JEV_CLOSE_THRESHOLD, JEV_CONFIDENCE_THRESHOLD). State gained last_reply, pending_change, awaiting_gap_decision, validation_settled and decisions.

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.md is 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.

Faults found by evaluation case 04, fixed on 2026-10-08

Case 04 is the first interactive run. It stopped at 100 Orchestrator turns (../../iter-06-target-architecture-graph/steps/step-11.md). Three changes:

  1. Only the user's own words are their message. A reply to questions now reaches the router with the questions it answered (asked) and with any quoted question and Q:/A: labels removed from its text (_own_words in app/nodes/execution_nodes.py). _read_message gives the questions to the decider as background and the cleaned text as the message. Before, a describer's "please confirm my draft" question, quoted back by the scripted user, was judged a request to change the Target architecture, twice.
  2. A Revision limit is told to the user once. When a reopen is refused at the limit, the router records the Deliverable in revision_limit_asked and sets awaiting_limit_decision. The reply is not read as a request for changes, every action that would reopen that Deliverable is barred from then on, and the Execution carries on with it as it stands. Before, the reply was read as another change request for the same Deliverable and the refusal repeated until the turn limit.
  3. A run that only asks is stopped. The engine counts questions put to the user with no change in any Deliverable's status or attempt, or any Phase's status, in between. At the fourth it ends with a warning (MAX_IDLE_ASKS). This holds for any Orchestrator, whatever the cause.

Also: agents/validator.md now tells the validator to confirm with the user before submitting in an interactive Execution, which the case's specialists_ask_before_submitting check found it did not.

Tests: tests/execution/test_router.py, "the two faults of evaluation case 04" (5).

Rerun on 2026-10-08 (unfinished, 86 minutes): changes 1 and 2 held. A third fault appeared and is not fixed: a reply that restates a requirement, given in answer to a draft-confirmation question, is read as a request to change requirements. See the run record in ../../iter-06-target-architecture-graph/steps/step-11.md.

Finished on 2026-10-08: the third case 04 fault, and intake

A reply that restates what is agreed is an answer. _read_message now shows the decider the agreed requirements.json and asks one more noul, already_agreed: does the message only confirm or repeat what those requirements say? At 0.75 or more the reply is closed as an answer, whatever asks_change says. Measured against live Jev with requirements holding the facts being restated:

Reply asks_change already_agreed Disposition
Restates the GDPR and secrets requirement 0.12 0.78 close
Restates the availability requirement 0.26 0.48 queue (asked once, then let go)
Restates the retention requirement 0.52 0.81 close
"Approved. Please proceed." 0.04 0.70 close
Raises availability to 99.99% 0.85 0.01 act
Changes retention from 2 years to 7 0.89 0.01 act
Adds SMS notifications and a mobile app 0.85 0.01 act
Changes secret rotation to 30 days 0.87 0.02 act

Intake: a message that starts something is read first. app/nodes/intake.py asks one choice of a message that arrives with no Execution in progress: new request, change request, or question. The A2A server (app/a2a_server.py) acts on it:

  • a question, at 0.75 confidence or more, is answered with a short statement of what the agent does and starts nothing;
  • a change request, when the Customer case has a completed Execution, is started as a new request with a note saying Change requests are not available yet (iteration 7 builds them);
  • anything else, any reading that is not confident, and every pre-approved task starts an Execution as before.

Measured against live Jev on ten messages: two new requests, two questions, two change requests with an earlier Execution, a question about earlier work, a different new request for the same case, a change with nothing delivered (taken as new), and "hello" (0.53, taken as new). All ten as intended.

Not built: acting on a change request (iteration 7 step 2), and answering a question about earlier work from that work.

Tests: tests/execution/test_intake.py (4), tests/a2a/test_server.py "intake" (4), tests/execution/test_router.py (1).