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.

tests/usage.test.ts

@@ -41,8 +41,9 @@ test("sumSteps folds steps; absent stays absent until a value appears", () => {
 test("callCost: glm-5.3-flash math — fresh input, cached read, output", () => {
 	const cost = callCost(call({ inputTokens: 100_000, outputTokens: 20_000, cacheReadTokens: 10_000 }), "z-ai/glm-5.3-flash");
 	assert.ok(cost !== null);
-	// fresh 90k @ $0.15/M + cached 10k @ $0.03/M + output 20k @ $0.50/M
-	assert.ok(Math.abs(cost! - (0.0135 + 0.0003 + 0.01)) < 1e-9);
+	// fresh 90k @ $0.075/M + cached 10k @ $0.015/M + output 20k @ $0.25/M
+	// (pi-ai catalog prices — regenerated tables, scripts/sync-pricing)
+	assert.ok(Math.abs(cost! - (0.00675 + 0.00015 + 0.005)) < 1e-9);
 });
 
 test("callCost: cache writes bill at the cacheWrite rate", () => {
@@ -86,7 +87,7 @@ test("contextWindow: last call's footprint against the model's limit", () => {
 	assert.ok(cw);
 	assert.equal(cw.model, "z-ai/glm-5.3-flash");
 	assert.equal(cw.usedTokens, 100_000);
-	assert.equal(cw.limit, 1_310_720);
+	assert.equal(cw.limit, 1_048_576);
 	assert.equal(contextWindow({ turns: [] }), null);
 });