Make the region-count injector audible, and stop double-writing the answer

[Robbie1977]

Two defects from the 11 August review, both on the flagship "how many neurons are in the fly brain?" question.

The injector was never actually silent about declining — it was inaudible

maybeInjectRegionNeuronCountStep called log() only on success. log() appends to the per-request trace, and the trace is printed only under VFB_HARNESS_TRACE=true. So the absence of an inject line in the three production runs we read was not evidence that the injector declined. It was not evidence either way, and the diagnosis built on it could not have been supported.

The decision now goes on stderr, on both paths, alongside ABSENCE ESCALATION and GROUNDING — and only once the question has count intent, so it stays quiet on the questions it has nothing to say about. Ontology ids, gate names and term flags only; the question is the user's text and is not logged.

While there: the gate regionTerms.length === 1 declined whenever a second region resolved. VFB answers "fly brain" with 224 documents that are almost all painted domains on JRC_FlyEM_Hemibrain — AB(L), AL(R), AL-DA1(R) — and every one of them is Anatomy-and-not-a-neuron, so every one satisfies isRegionTerm exactly as brain (FBbt:00005095) does. One survivor was enough to take the curated counts off the table. It now prefers the ontology class; two classes is a real ambiguity and still declines, audibly.

The answer could be written out twice

Absence escalation runs a second synthesis. Synthesis streams token by token into one live bubble on the client and the only event that ends that bubble is result, so the second draft was appended to the first — the same paragraph twice, in two slightly different wordings.

The tokens are already sent, so the server cannot unsend them. It tells the client instead: a draft_discarded event fires the moment escalation is accepted, and the client drops the bubble so the replacement opens a fresh one. Best-effort like onStatus — an unwired or throwing hook costs the run nothing.

How to test

npm test (5 new cases in orchestrator_run.test.mjs, 3 in absence.test.mjs). Live: ask "How many neurons are in the fly brain?" on the deployed build and read the container log for REGION COUNT INJECTOR. That line now names the gate whatever happens.

Follow-ups

• The injector fix is unproven against production. If the line comes back no-region-term or already-planned, the remaining fault is upstream of this gate.
• /docs/concepts/neuron-counts/ still 404s until VFB2 is redeployed.