feat: add multi-app support with app switcher, per-app branding, and filtered queries

Apps share the same backend, API keys, and publishing flow but each gets its own
branding (name, colors, icon, app URL), knowledge files (brand identity, product
info, platform guidelines), and campaigns. The pipeline dynamically writes
_knowledge/ files and copies app assets before each run.

- Add App model with slug, colors, appUrl, and knowledge markdown fields
- Add appId FK to Campaign, seed honeyDue as first app with existing knowledge
- App switcher dropdown in sidebar with icon previews
- Filter campaigns, stats, and assets by active app (cookie-based)
- De-hardcode lib/claude.ts: AppConfig interface, templated prompts, dynamic
  _knowledge/ and Remotion asset copying
- App management pages (list, create, edit) with icon upload and color pickers
- Asset library sort options (newest, oldest, name, platform, type)
- Asset cards show creation date
- Remotion HoneyDueAd accepts colors/appName props

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

pipeline/CLAUDE.md

@@ -22,9 +22,11 @@ Seven agents running in sequence:
 
 # Knowledge Files (READ FIRST)
 Every agent MUST read these before generating ANY content:
-- `knowledge/brand_identity.md` — tone, voice, personality, CTA patterns
-- `knowledge/platform_guidelines.md` — per-platform specs and formatting
-- `knowledge/product_campaign.md` — product details, features, campaign direction
+- `_knowledge/brand_identity.md` — tone, voice, personality, CTA patterns
+- `_knowledge/platform_guidelines.md` — per-platform specs and formatting
+- `_knowledge/product_campaign.md` — product details, features, campaign direction
+
+NOTE: The `_knowledge/` directory is dynamically written per-pipeline-run with the active app's content. The original `knowledge/` directory contains the honeyDue defaults.
 
 # Available Tools