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.

components/stats-bar.tsx

@@ -1,8 +1,9 @@
 "use client";
 
 import { useState } from "react";
-import { contextWindow, sessionCost, turnCost, type TurnUsage } from "@/src/core";
+import { contextWindow, sessionCost, turnCost, type ChatSettings, type TurnUsage } from "@/src/core";
 import { formatTokens, formatUsd, prettyModel } from "@/components/usage-format";
+import { ModelControl } from "@/components/model-picker";
 
 /**
  * The below-composer stats bar (wave 4 observability): the session's
@@ -14,11 +15,23 @@ import { formatTokens, formatUsd, prettyModel } from "@/components/usage-format"
  * — no cost math lives here. Absent data renders "—", never zero (the
  * doctrine): no turns yet → every figure is "—"; turns the price table
  * can't price count as unpriced, shown in the popover, never folded into a
- * fake $0. The RIGHT side is a PLACEHOLDER for the model + thinking-level
- * control (later work, with its contract changes): display-only for now,
- * model read from the last turn's usage.
+ * fake $0. The RIGHT side is the model + thinking control (components/
+ * model-picker.tsx): one controller for the conversation agents, backed by
+ * pi-ai's catalog; the buttons show the EFFECTIVE model (the record's
+ * settings, else config's pin), while the left-side figures still fold the
+ * turn log's actual billed models.
  */
-export function StatsBar({ turns }: { turns: TurnUsage[] }) {
+export function StatsBar({
+	turns,
+	chatId,
+	settings,
+	onSettingsSaved,
+}: {
+	turns: TurnUsage[];
+	chatId: string;
+	settings?: ChatSettings;
+	onSettingsSaved: (settings: ChatSettings) => void;
+}) {
 	const [open, setOpen] = useState(false);
 	const ctx = contextWindow({ turns });
 	const { cost, unpriced } = sessionCost({ turns });
@@ -47,15 +60,15 @@ export function StatsBar({ turns }: { turns: TurnUsage[] }) {
 				<span aria-hidden>·</span>
 				<span data-testid="stats-cost">{costLabel}</span>
 			</button>
-			{/* Model + thinking level — a placeholder for the coming control
-			    (contract changes land with it); display-only today. */}
-			<div className="flex items-center gap-1.5" data-testid="stats-model-chip">
-				<span data-testid="stats-model">{lastModel ? prettyModel(lastModel) : "—"}</span>
-				<span aria-hidden>·</span>
-				<span data-testid="stats-thinking" title="Thinking level control lands soon">
-					Thinking —
-				</span>
-			</div>
+			{/* The model + thinking control — one controller for the conversation
+			    agents (prober/teacher); the record's `turns` above still folds
+			    the ACTUAL models billed, regardless of what the picker says. */}
+			<ModelControl
+				chatId={chatId}
+				settings={settings}
+				onSaved={onSettingsSaved}
+				fallbackModelId={lastModel}
+			/>
 
 			{open && (
 				<div