model availability pings for OpenRouter (:free models) and NVIDIA NIM profiles, plus a 429 retry middleware for generation calls

[Pento95]

Make room for a usable nvidia nim provider!

Model health pings

• New pingEnabled flag per profile (opt-in, only shown for OpenRouter / NIM).
• Periodic low-cost chat/completions probe (max_tokens: 1) classifies each model as ok / slow / down / auth / rate_limited, with latency and quota headers captured when available.
• Results persisted in new model_health_cache table (migration 034), keyed by (provider_id, model_id, api_key_hash). API key hashed to 8-byte SHA-256 prefix.
• Reactive SvelteMap-based store with DB hydration, concurrency-limited batch pings (5 parallel), provider-specific TTLs (auto vs manual trigger).
• Warmup on app start: pings only models actually referenced by main narrative + generation presets, deduped by provider|baseUrl|apiKey.
• UI: health indicator (signal icon + latency) inline in ModelSelector; ProfileWarningBanner blocks sending when the main narrative model is down or auth-failed.

429 retry middleware

• Wraps both doGenerate and doStream with up to 3 retries (10s / 20s / 30s + jitter).
• Respects Retry-After (delta-seconds or HTTP-date), caps at 60s to fail fast on long cooldowns.
• Abort-aware sleep: user cancellation interrupts the backoff immediately.
• Note: only catches pre-stream 429s (rejected doStream() promise), not mid-stream errors.

Other

• NVIDIA NIM profiles now ship with a default hiddenModels list to hide embedding / guard / reward / vision-only / legacy models from the selector.
• DatabaseService.init guarded against concurrent double-open via a shared pending promise.
• updateProfile purges the health cache when apiKey or providerType changes (prevents orphan rows under stale hashes).

Files

• Migration: src-tauri/migrations/034_model_health_cache.sql, registered in src-tauri/src/lib.rs
• New: src/lib/services/modelHealth{Cache,Orchestrator}.ts, src/lib/stores/modelHealth.svelte.ts, src/lib/services/ai/sdk/{middleware/retryMiddleware,providers/modelPing}.ts, src/lib/constants/modelHealth.ts,
  src/lib/utils/hashApiKey.ts, src/lib/components/settings/HealthIndicator.svelte
• Touched: generate.ts, providers/config.ts, database.ts, settings.svelte.ts, ModelSelector.svelte, ProfileForm.svelte, AgentProfiles.svelte, tabs/api-connection.svelte, ProfileWarningBanner.svelte, +page.svelte

[gemini-code-assist]

Code Review

This pull request introduces a model health monitoring system that pings OpenRouter and NVIDIA NIM models to track availability and latency, supported by a persistent SQLite cache and reactive UI indicators. It also includes a retry middleware for 429 errors. Feedback identifies a potential SQLite parameter limit issue in batch upserts, suggests optimizing reactivity by using a standard variable instead of state for tracking previous values, and recommends respecting server-provided Retry-After headers by avoiding jitter on those specific values.

[Pento95]

still testing 429 with a few providers. help with tests is welcome