feat: model + thinking control — the stats bar's picker, on pi-ai's catalog

The model-control wave (user-decided design, 2026-09-12): ONE controller
for the conversation agents (prober/teacher are functionally one agent);
background sub-agents stay config-pinned. pi-ai owns the registry — the
shipped 366-model OpenRouter catalog (cost, context, modality,
thinkingLevelMap), getSupportedThinkingLevels/clampThinkingLevel for the
per-model thinking truth, and streamSimple's automatic clamp. No second
registry to drift out of sync.

Seams:
- config.ts: ReasoningEffort retired for pi's ThinkingLevel
  (off|minimal|low|medium|high|xhigh|max). GLM roles go honest at "low" —
  pi's catalog says GLM-5.3-flash accepts exactly low|high|max, and the old
  "minimal" was silently clamped to low by streamSimple since the swap;
  nothing changes behaviorally. visualMaker → qwen/qwen3.8-flash (fixes
  the dead qwen/qwen3.8-max slug — the catalog only ships -0902; also the
  user's cost pick, 0.15/0.47 per-1M).
- src/agent/models.ts: piEngineFor(role, settings?) — provider+id resolved
  from the catalog, thinking level from settings ?? config, CLAMPED to the
  model's supported list (a settings change between models can never send
  an invalid level). PiEngine gains `level` (observability/tests).
- ChatRecord.settings {model?: {provider, id}, thinkingLevel?} — written
  by PUT /api/chats/[id]/settings (replace-whole, no updatedAt churn),
  read by chat-handler at turn composition: agents are stateless per turn,
  so the change is next-turn-effective by construction. The turns log
  still records the ACTUAL billed model (the honest witness).
- GET /api/models: the configured-provider catalog as client-safe DTOs
  (core/contracts/models.ts) + config defaults; a second provider joins
  the picker by registering it in piModels() — nothing else changes.
- PUT settings validation gate (src/server/model-catalog.ts): unknown
  provider/model or unsupported level → 400 carrying the supported list,
  never a silent clamp.
- scripts/sync-pricing.ts: regenerated PRICES/CONTEXT_LIMITS from pi-ai's
  shipped openrouter.json (offline; same source as the engine + picker).
  All 366 models priced; glm's stale 0.15/0.5 → pi's 0.075/0.25, limit
  1310720 → 1048576 — cost is inferred at read time, so history re-prices.
- UI (components/model-picker.tsx): stats-bar right side becomes model +
  thinking buttons; menus open ABOVE; fuzzy search over "provider id
  name" (core/fuzzy.ts — pi's /model pattern); model rows show name/id/
  price/context; the thinking menu lists exactly the chosen model's
  supported levels (GLM: low|high|max — no dead options, no "off").
  Model switch drops an incompatible pinned level (falls back to config,
  which clamps honestly) rather than carrying a 400.

Tests (350/350, +15): catalog projection + defaults, the settings gate,
pi thinking truth pinned against upgrades (glm low|high|max; minimal→low;
off→low — GLM cannot disable thinking), the engine factory's
override/fallback/clamp/throw matrix, fuzzy ranking, store round-trip,
and the re-priced folds (usage, stats bar, activity dock).

Live smoke (disposable driver, deleted): catalog route 366 + defaults;
glm+minimal → 400 + supported; turn 1 billed qwen/qwen3.8-flash under
the override; mid-session switch flipped turn 2 to glm; clear-overrides
restored the config pin. ALL CHECKS PASS on real OpenRouter.

src/core/contracts/chat.ts

@@ -7,6 +7,7 @@
  * of "ai" (safe everywhere: server, client, tests). See docs/vision.md.
  */
 import type { UIMessage } from "ai";
+import type { ThinkingLevel } from "@earendil-works/pi-agent-core";
 import type { Phase3 } from "../phases.ts";
 import type { PlanNodeStatus, PlanTree } from "./plan.ts";
 import type { EmissionStats } from "./graph.ts";
@@ -38,6 +39,25 @@ export interface ChatRecord {
 	 *  spend too. Same parallel-log discipline as `turns` (nothing rides
 	 *  inside messages). Keyed by startedAt; idempotent appends. */
 	extractions?: ExtractionRunUsage[];
+	/** Per-chat model/thinking overrides for the conversation agents. */
+	settings?: ChatSettings;
+}
+
+/** The conversation agents' runtime model choice (model-control wave,
+ *  2026-09-12): a per-chat override of config.ts's pinned prober/teacher
+ *  spec. Absent fields fall back to config; written by the model picker
+ *  (PUT /api/chats/[id]/settings) and read at turn composition — the
+ *  agents are stateless per turn, so a change takes effect on the next
+ *  turn by construction. Background sub-agents are NEVER overridden
+ *  (config-pinned: they're infrastructure, not conversation). */
+export interface ChatSettings {
+	/** pi-ai catalog coordinates: the provider that owns the model. Only
+	 *  "openrouter" is configured today; the field exists so a second
+	 *  provider needs no schema change. */
+	model?: { provider: string; id: string };
+	/** pi thinking level — must be in the chosen model's supported list
+	 *  (getSupportedThinkingLevels; enforced by the settings route). */
+	thinkingLevel?: ThinkingLevel;
 }
 
 // ─── Background-extraction usage (the money channel, extraction side) ────────
@@ -191,6 +211,10 @@ export interface ChatSummary {
 	phase: Phase3;
 	/** An unanswered quiz/ask question is waiting for the learner. */
 	pendingQuestion: boolean;
+	/** The record's model-control settings — rides the list payload via the
+	 *  summary spread (the picker never needs it from here; the full record
+	 *  is its source). */
+	settings?: ChatSettings;
 }
 
 /** The sidebar's session row: a summary + live liveness. The chats list