Implementation Tracker

Current Status: ✅ All Phases Complete

Last Updated: 2026-02-02

Pollinations Integration Updates

Phase 1: Fix Core Endpoint & Configuration

Status: ✅ Complete

File: lib/env.ts

Update default POLLINATIONS_BASE_URL → https://gen.pollinations.ai
Add POLLINATIONS_CHAT_PATH (default: /v1/chat/completions)
Remove POLLINATIONS_MODEL env var (now dynamic)
Add optional POLLINATIONS_PRIMARY_MODEL for override

Phase 2: SQLite Model Cache Schema

Status: ✅ Complete

File: lib/db.ts

Add model_cache table for discovered models
Add model_config table for selected primary/fallback models
Add upsertModelCache(model) function
Add getModelCache(type) function
Add getModelConfig(key) / setModelConfig(key, value) functions
Add getModelByName(name) function
Add clearModelCache(type?) function
Add getAllModelConfig() function

Phase 3: Model Discovery Service

Status: ✅ Complete

File: lib/llm_pollinations.ts

Add discoverTextModels() - GET /v1/models + /text/models
Add discoverImageModels() - GET /image/models
Add refreshModelCache() - run discovery and cache to SQLite
Add selectBestModel(options) - pick model based on needs
Add getModelWithFallbacks() - return primary + fallback list
Add isDiscoveryNeeded() - check if cache is stale (>24h)
Add ensureModelCache() - run discovery if needed

Phase 4: Smart Request Wrapper with Auto-Fallback

Status: ✅ Complete

File: lib/llm_pollinations.ts

Update generateChat() with model hints (useTools, complexTask)
Add auto-retry with fallback models on error
Add modelUsed and fallbacksAttempted to response
Update generateJSON() to use new wrapper
Update generateText() to use new wrapper
Handle content_blocks in Gemini responses

Phase 5: Image Generation

Status: ✅ Complete

File: lib/llm_pollinations.ts

Add generateImage(prompt, options) function
Download image and store in Val Town blob storage
Add getImageModels() function

File: app/http.ts

Add POST /api/image/generate endpoint
Add GET /api/image/models endpoint

Phase 6: Update Interval Job for Model Discovery

Status: ✅ Complete

File: jobs/sync/interval.ts

Add model cache refresh (daily)
Check last_discovery timestamp before refreshing
Log model discovery results

Phase 7: Update Agent for Smart Model Selection

Status: ✅ Complete

File: lib/agent.ts

Use complexTask: true for plan generation
Log which model was used
Use cheaper model for simple agent interactions

Phase 8: Add Model Management API Routes

Status: ✅ Complete

File: app/http.ts

Add GET /api/ai/models - list cached models + config
Add POST /api/ai/discover - trigger model rediscovery

Summary of Changes

New Endpoints

GET /api/ai/models - List cached text/image models and current config
POST /api/ai/discover - Manually trigger model rediscovery
POST /api/image/generate - Generate image from prompt (stored in blob)
GET /api/image/models - List available image models

New Database Tables

model_cache - Stores discovered models with metadata
model_config - Stores selected primary/fallback models

Model Selection Strategy

Primary: gemini (cheap, tools=true)
Fallback 1: openai (baseline compatibility)
Fallback 2: gemini-large (complex tasks)

Key Behaviors

Model discovery runs automatically once per day via interval job
Models are auto-selected based on task complexity
Automatic fallback on model errors
Images stored in Val Town blob storage

Environment Variables (Final)

# Required
READWISE_TOKEN=your_readwise_token
APP_ADMIN_SECRET=your_secret_for_api_auth
POLLINATIONS_TOKEN=your_pollinations_sk_token

# Optional (with defaults)
POLLINATIONS_BASE_URL=https://gen.pollinations.ai
POLLINATIONS_CHAT_PATH=/v1/chat/completions
POLLINATIONS_PRIMARY_MODEL=  # leave empty for auto-discovery

# Optional (webhooks)
READWISE_WEBHOOK_SECRET=