feat(models): strong/cheap/vision model slots + multi-provider engine federation

Model slots wave (2026-09-20), chunk B:

- settings: new `models` section {strong, cheap, vision} slots (each
  field independent, same shape as a role override); ROLE_SLOT maps all
  nine roles to tiers (strong=prober+teacher, cheap=researcher/
  demoBuilder/extractor/auditor/labeler, vision=visualMaker+pdfReader);
  resolution chain per role: override → slot → factory pin.
- config: ModelSpec gains provider (all pins openrouter, the BYOK
  default); MODEL_PINS in stores.ts now spans all nine roles (the strong
  slot's factory rep IS the prober pin).
- engine: piModels() registers EVERY builtin provider catalog;
  piEngineForSpec(resolved spec) is the new engine factory (pi-ai
  resolves per-provider keys from env itself); piEngineFor stays as the
  config-pin fallback. chat-handler resolves the conversation chain
  (chat override → strong slot → pin) and injects engineFor into the job
  runner, closing the old gap where per-role overrides never reached
  job engines.
- /api/models: models federate ONLY keyed providers (providers surface
  with keyPresent, env-wins, fresh per call); slots (resolved tier pins)
  join rolePins; catalogDefaultsFor inherits the strong slot; the models
  settings section gets the same catalog gate as chat.
- pricing: PRICES/CONTEXT_LIMITS uniformly keyed provider:id
  (regenerated from ALL pi-ai catalogs, 1354 keys); usage stamps
  (TurnUsage, JobUsage, extraction stages) switch to provider:id —
  owner decision: no legacy compat, old stamps render unpriced.

config.ts

@@ -46,7 +46,12 @@ export const PATHS = {
 export type ThinkingLevel = "off" | "minimal" | "low" | "medium" | "high" | "xhigh" | "max";
 
 export interface ModelSpec {
-	/** OpenRouter model id (e.g. "z-ai/glm-5.3-flash") — must exist in pi-ai's catalog. */
+	/** The provider that owns the model (model slots wave, 2026-09-20):
+	 *  pi-ai provider id. Native ids are plain strings ("glm-5.3-flash" on
+	 *  zai); OpenRouter ids are vendor slugs ("z-ai/glm-5.3-flash"). The
+	 *  factory pins stay OpenRouter (the BYOK default provider). */
+	provider: string;
+	/** The model id on that provider — must exist in pi-ai's catalog. */
 	model: string;
 	/** Thinking budget — what the model may spend on reasoning tokens. */
 	effort: ThinkingLevel;
@@ -54,28 +59,28 @@ export interface ModelSpec {
 
 export const MODELS = {
 	/** The prober (agent A) — edge-bracketing questions; keep it lively and adaptive. */
-	prober: { model: "z-ai/glm-5.3-flash", effort: "low" },
+	prober: { provider: "openrouter", model: "z-ai/glm-5.3-flash", effort: "low" },
 	/** The teacher (agent B) — planning + streaming, lesson-facing: smart, but keep it lively. */
-	teacher: { model: "z-ai/glm-5.3-flash", effort: "low" },
+	teacher: { provider: "openrouter", model: "z-ai/glm-5.3-flash", effort: "low" },
 	/** Background sub-agents: fast and cheap beats deep thought. */
-	researcher: { model: "z-ai/glm-5.3-flash", effort: "low" },
-	demoBuilder: { model: "z-ai/glm-5.3-flash", effort: "low" },
+	researcher: { provider: "openrouter", model: "z-ai/glm-5.3-flash", effort: "low" },
+	demoBuilder: { provider: "openrouter", model: "z-ai/glm-5.3-flash", effort: "low" },
 	/** Must be vision-capable: it looks at rendered SVGs. */
-	visualMaker: { model: "qwen/qwen3.8-flash", effort: "low" },
+	visualMaker: { provider: "openrouter", model: "qwen/qwen3.8-flash", effort: "low" },
 	/** SEAM (master-approved 2026-09, revised by the user 2026-09-19): the
 	 *  pdf-reader sub-agent. Must be vision-capable — it looks at rendered
 	 *  PDF pages; its briefs are text. The user overrode the initial
 	 *  glm-5.3-flash pick (catalog says it accepts images, but qwen is
 	 *  proven for exactly this look-at-renders job — visualMaker's daily
 	 *  workload). */
-	pdfReader: { model: "qwen/qwen3.8-flash", effort: "low" },
+	pdfReader: { provider: "openrouter", model: "qwen/qwen3.8-flash", effort: "low" },
 	/** Extraction is judgment over given evidence — light thinking suffices. */
-	extractor: { model: "z-ai/glm-5.3-flash", effort: "low" },
+	extractor: { provider: "openrouter", model: "z-ai/glm-5.3-flash", effort: "low" },
 	/** The auditor verifies evidence exists; keep it cheap. */
-	auditor: { model: "z-ai/glm-5.3-flash", effort: "low" },
+	auditor: { provider: "openrouter", model: "z-ai/glm-5.3-flash", effort: "low" },
 	/** Names detected communities — one singular call, given member names
 	 * + statements. Purely a labeling flourish; keep it cheap. */
-	labeler: { model: "z-ai/glm-5.3-flash", effort: "low" },
+	labeler: { provider: "openrouter", model: "z-ai/glm-5.3-flash", effort: "low" },
 } satisfies Record<string, ModelSpec>;
 
 export type ModelRole = keyof typeof MODELS;