feat(models): BYOK all the way down — factory pins deleted, per-need refusal gates

Owner decision 2026-09-22: 'it doesn't make sense to have any default
model configured anywhere; the application is bring your own keys.'

config.ts: MODELS deleted; ModelRole becomes an explicit 9-role union;
DEFAULT_THINKING_ORDER (medium, low, high, minimal, xhigh, max) bakes
the unset-level default — first entry the model supports; explicitly
set levels keep pi's native nearest-clamp.

core/settings-resolution: the factory layer dissolves — the chain is
role override → slot → NOTHING. resolveSettings(record) takes no
factory. Empty chains resolve to null/undefined; a thinkingLevel-only
slot is inert (stored, never run). resolveConversationSpec: chat.model
override over the strong slot, null when both empty. resolveRoleSpec
spans all nine roles for the job/extraction engines.

Refusal envelope (core/settings.ts): modelsNotConfigured(missing) —
{error, code: 'models_not_configured', missing: [slot tiers]} +
ModelsNotConfiguredError with .envelope. Per-need gates, each honest:
- chat-handler: universal turn gate (new + continuing turns) returns
  503 before beginTurn — no liveness, no write-ahead persist, no graph
  trigger before the gate fires.
- runner.runJob: unresolvable engine lands the job as error with the
  envelope wording; no phantom loop, no result steer.
- extraction: refuseIfStagesUnconfigured throws before any stage
  (turn-service info-skips so coverage retries next turn; the import
  route surfaces per-file code+missing); labeler-less runs skip
  cluster naming with a console line and still merge.

Write side: slot entries must carry a model — level-only slot writes
are 400s (absent slot key = clear). piEngineForSpec resolves unset
thinking levels via DEFAULT_THINKING_ORDER; piEngineFor now throws
honestly; thinkingLevelFor/modelIdFor deleted; teacher-agent, pi-run,
visual-maker, pdf-reader all read engine.level.

model-catalog: defaults/slots/rolePins null when the chain is empty
(contracts nullable) — no phantom ids in payloads. Stores drop
MODEL_PINS entirely.

Tests: pin-leaners converted to explicit injection (per-chat model
pins on scripted chats — exactly what the setup flow writes; faux
engines for agent-construction tests). New coverage: the 503 gate
envelope, the runner refusal, the extraction refusal + labeler skip.

Gates: typecheck, lint, 815/815, build.

app/api/graph/import/route.ts

@@ -14,7 +14,7 @@
  * /api/graph/status, as with session runs.
  */
 import { extraction } from "@/src/server";
-import type { EmissionStats } from "@/src/core";
+import { ModelsNotConfiguredError, type EmissionStats } from "@/src/core";
 
 export const dynamic = "force-dynamic";
 
@@ -23,6 +23,10 @@ interface ImportResult {
 	ok: boolean;
 	stats?: EmissionStats;
 	error?: string;
+	/** The machine discriminator when ok:false is the BYOK refusal (owner,
+	 *  2026-09-22) — the client can open the setup flow off it. */
+	code?: "models_not_configured";
+	missing?: string[];
 }
 
 export async function POST(request: Request) {
@@ -43,6 +47,16 @@ export async function POST(request: Request) {
 				const stats = await extraction.importNotes({ filePath: file.name, text });
 				results.push({ filePath: file.name, ok: true, stats });
 			} catch (err) {
+				if (err instanceof ModelsNotConfiguredError) {
+					results.push({
+						filePath: file.name,
+						ok: false,
+						error: err.envelope.error,
+						code: "models_not_configured",
+						missing: err.envelope.missing,
+					});
+					continue;
+				}
 				results.push({ filePath: file.name, ok: false, error: err instanceof Error ? err.message : String(err) });
 			}
 		}