v1.1.0:4 — multi-config AI, background generation, ollama auto-detect, system prompt overhaul

User-feedback-driven release after testing v1.1.0:3. Nine themes:

1. Multi-config persistence
   - New AIConfigProfile table (per-user). Save N configs, toggle one
     active. Switching providers no longer wipes the previous setup.
   - UserPreferences gains activeAIConfigId; legacy single-config
     columns are mirrored from the active profile so existing reads
     keep working without conditional logic.
   - Idempotent boot migration lifts any existing single-config row
     into a default profile.

2. Ollama auto-detect
   - The "Add config" form probes /api/tags on the StartOS internal
     addresses (ollama.startos / ollama.embassy on :11434). If
     reachable: URL pre-fills, model field becomes a dropdown of
     installed models. Fixes the copy-paste UX.

3. Curated model dropdowns for major providers
   - Claude: Opus 4.7, Sonnet 4.6 (1M ctx), Haiku 4.5
   - OpenAI: GPT-5.5, 5.4, 5.4-mini, 5.4-nano
   - Gemini: 3.1-pro-preview, 2.5-pro, 2.5-flash, etc.
   - "Other (type your own)" stays for niche models.
   - Fixes "I tried gemini-3.0-pro and got 404."

4. Background generation
   - lib/ai/generationRunner.ts: detached runner with in-memory
     pub/sub bus. POST /api/ai/generate kicks it off and returns
     immediately. SSE stream attaches by id. The runner survives
     request cancellation; navigating away no longer kills it.
   - New AIGeneration columns: progressText (in-flight stream),
     durationMs (final wall-clock).
   - Generate UI shows a banner explaining background-safety.
   - History detail page polls progress + renders partial JSON
     live for cross-process resume (page refresh, new tab).

5. System prompt overhaul
   - lib/ai/systemPromptBase.ts: structural contract prepended to
     every template. Forces JSON-only output, library-exerciseId
     usage (kills "exerciseId doesn't belong to this user" errors),
     and per-resistance-exercise suggestedWeight (with-history vs
     without-history variants).
   - aiExerciseSchema + ProgramExercise gain suggestedWeight +
     suggestedWeightUnit. Starting a workout from a ProgramDay
     pre-populates SetLog.weight from the suggestion.

6. Test connection improvements
   - Latency in seconds (was ms — confusing for slow Ollama).
   - Stale "✓ Connected" clears on form change.
   - Per-config Test (no need to activate first).
   - Generous maxOutputTokens for thinking models.
   - Gemini surfaces finishReason on empty response (e.g. "blocked
     by safety filter") instead of generic "empty response."
   - Test endpoint accepts a draft body so you can verify before
     saving + before activating.

7. History detail view
   - Click row → full program tree + exact prompts sent. Apply from
     here without re-generating. Pending rows poll for progress.

8. Sidebar sub-navigation
   - AI: Generate / History / Templates
   - Settings: General / Password / Sessions / AI integration /
     Export / Instance (admin) / Danger zone, with anchor scroll.

9. API key UX
   - "Key saved" indicator on saved configs (was confusing to see
     an empty input after a successful save).

Schema migrations (additive, idempotent in entrypoint):
  - AIConfigProfile table created
  - UserPreferences.activeAIConfigId
  - AIGeneration.progressText + durationMs
  - ProgramExercise.suggestedWeight + suggestedWeightUnit

Tests: 16 new (systemPromptBase, modelMenu, generationRunner). 177
total pass.

proof-of-work/app/api/ai/configs/route.ts

@@ -0,0 +1,119 @@
+import { NextRequest, NextResponse } from 'next/server';
+import { z } from 'zod';
+import { getCurrentUser } from '@/lib/auth';
+import { prisma } from '@/lib/prisma';
+import { activate } from '@/lib/ai/activateConfig';
+
+/**
+ * v1.1.0:4 — Multi-config CRUD.
+ *
+ * GET  /api/ai/configs       List the actor's saved AI configs +
+ *                            their active id. apiKey is REDACTED in
+ *                            list output (only `keyConfigured: bool`).
+ * POST /api/ai/configs       Create a new config. Pass `setActive: true`
+ *                            to also activate it.
+ *
+ * Per-row endpoints in [id]/route.ts. "Activate" is its own POST in
+ * [id]/activate/route.ts so the action is explicit + auditable.
+ */
+
+const PROVIDERS = ['claude', 'openai', 'openai-compatible', 'gemini', 'ollama'] as const;
+
+export async function GET() {
+  const user = await getCurrentUser();
+  if (!user) return NextResponse.json({ error: 'Unauthorized' }, { status: 401 });
+
+  const [profiles, prefs] = await Promise.all([
+    prisma.aIConfigProfile.findMany({
+      where: { userId: user.id },
+      orderBy: { createdAt: 'asc' },
+      select: {
+        id: true,
+        name: true,
+        provider: true,
+        model: true,
+        baseUrl: true,
+        apiKey: true, // pulled only to compute keyConfigured; never returned
+        createdAt: true,
+      },
+    }),
+    prisma.userPreferences.findUnique({
+      where: { userId: user.id },
+      select: { activeAIConfigId: true },
+    }),
+  ]);
+
+  return NextResponse.json({
+    activeId: prefs?.activeAIConfigId ?? null,
+    configs: profiles.map((p) => ({
+      id: p.id,
+      name: p.name,
+      provider: p.provider,
+      model: p.model,
+      baseUrl: p.baseUrl,
+      keyConfigured: !!p.apiKey,
+      createdAt: p.createdAt.toISOString(),
+    })),
+  });
+}
+
+const createSchema = z.object({
+  name: z.string().min(1).max(80).optional(),
+  provider: z.enum(PROVIDERS),
+  model: z.string().min(1).max(200),
+  baseUrl: z.string().url().nullable().optional().or(z.literal('')),
+  apiKey: z.string().nullable().optional(),
+  setActive: z.boolean().optional(),
+});
+
+export async function POST(request: NextRequest) {
+  const user = await getCurrentUser();
+  if (!user) return NextResponse.json({ error: 'Unauthorized' }, { status: 401 });
+
+  const body = await request.json().catch(() => ({}));
+  const parsed = createSchema.safeParse(body);
+  if (!parsed.success) {
+    return NextResponse.json(
+      { error: 'Invalid body', details: parsed.error.errors },
+      { status: 400 },
+    );
+  }
+
+  const { name, provider, model, baseUrl, apiKey, setActive } = parsed.data;
+  const profile = await prisma.aIConfigProfile.create({
+    data: {
+      userId: user.id,
+      name: name ?? defaultName(provider, model),
+      provider,
+      model,
+      baseUrl: baseUrl || null,
+      apiKey: apiKey || null,
+    },
+  });
+
+  if (setActive) {
+    await activate(user.id, profile.id, { provider, model, baseUrl, apiKey });
+  }
+
+  return NextResponse.json({
+    id: profile.id,
+    name: profile.name,
+    provider: profile.provider,
+    model: profile.model,
+    baseUrl: profile.baseUrl,
+    keyConfigured: !!profile.apiKey,
+    activated: !!setActive,
+  });
+}
+
+function defaultName(provider: string, model: string): string {
+  const PRETTY: Record<string, string> = {
+    claude: 'Claude',
+    openai: 'OpenAI',
+    'openai-compatible': 'Custom',
+    gemini: 'Gemini',
+    ollama: 'Ollama',
+  };
+  const label = PRETTY[provider] ?? provider;
+  return `${label} · ${model}`;
+}