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.

src/agent/subagents/pi-run.ts

@@ -1,6 +1,6 @@
 import { Agent, type AgentEvent, type AgentMessage, type AgentTool } from "@earendil-works/pi-agent-core";
 import type { AssistantMessage, ToolResultMessage, Usage } from "@earendil-works/pi-ai";
-import { openRouterApiKey, piEngineFor, thinkingLevelFor, type PiEngine } from "../models.ts";
+import { openRouterApiKey, piEngineFor, type PiEngine } from "../models.ts";
 import type { ModelRole } from "../../../config.ts";
 
 /**
@@ -47,6 +47,9 @@ export interface SubagentRunResult {
 }
 
 export function subagentEngine(role: ModelRole, override?: PiEngine): PiEngine {
+	// BYOK (owner, 2026-09-22): no factory pins — the override is the only
+	// real path (the runner injects settings-resolved engines); a missed
+	// injection hits the honest thrower in models.ts instead of a guess.
 	return override ?? piEngineFor(role);
 }
 
@@ -57,7 +60,7 @@ export async function runSubagent(tools: AgentTool<any, any>[], opts: SubagentRu
 		initialState: {
 			systemPrompt: opts.systemPrompt,
 			model: engine.model,
-			thinkingLevel: thinkingLevelFor(opts.role),
+			thinkingLevel: engine.level,
 			tools,
 			messages: opts.messages ?? [],
 		},