Upload CONTEXT.md

docs/CONTEXT.md

@@ -266,6 +266,8 @@ Shows detailed extraction progress:
    3. SVG colors (fill, stroke)
    4. Inline styles (style='color:')
    5. Stylesheet rules (CSS files)
+   6. External CSS files (fetch & parse)
+   7. Page content scan (brute-force)
 
 📊 EXTRACTION RESULTS:
    Colors:     45 unique
@@ -282,6 +284,36 @@ Shows detailed extraction progress:
 
 🔄 Normalizing (deduping, naming)...
    ✅ Normalized: 32 colors, 10 typography, 18 spacing
+
+============================================================
+🔥 FIRECRAWL CSS EXTRACTION
+============================================================
+
+   🌐 Scraping: https://example.com
+   ✅ Page scraped (125000 chars)
+   📝 Parsing <style> blocks...
+      Found 5 style blocks
+   🔗 Finding linked CSS files...
+      Found 8 CSS files
+   📄 Fetching: main.css...
+      ✅ Parsed (234 colors)
+   📄 Fetching: theme.css...
+      ✅ Parsed (45 colors)
+
+📊 FIRECRAWL RESULTS:
+   CSS files parsed:    8
+   Style blocks parsed: 5
+   CSS variables found: 23
+   Unique colors found: 156
+
+   🎨 Top colors found:
+      #06b2c4 (used 45x)
+      #c1df1f (used 38x)
+      #373737 (used 120x)
+
+🔀 Merging Firecrawl colors with Playwright extraction...
+   ✅ Added 12 new colors from Firecrawl
+   📊 Total colors now: 44
 ```
 
 ### Stage 2 LLM Analysis Logs
@@ -298,21 +330,33 @@ Shows detailed reasoning from each agent:
 
 ## 🤖 Agent Personas
 
-### Agent 1: Website Crawler & Enhanced Extractor
+### Agent 1A: Website Crawler & Enhanced Extractor
 - **Persona:** Meticulous Design Archaeologist
 - **Tool:** Playwright
 - **Job:** 
   - Auto-discover 10+ pages from base URL
   - Crawl Desktop (1440px) + Mobile (375px) separately
   - Scroll to bottom + wait for network idle
-  - **ENHANCED: Extract from 5 sources:**
+  - **ENHANCED: Extract from 7 sources:**
     1. DOM computed styles (`getComputedStyle`)
     2. CSS variables (`:root { --primary: #xxx }`)
     3. SVG colors (`fill`, `stroke` attributes)
     4. Inline styles (`style="background-color: #xxx"`)
     5. Stylesheet rules (CSS files, hover states, pseudo-elements)
+    6. External CSS files (fetch & parse to bypass CORS)
+    7. Page content scan (brute-force regex on HTML)
 - **Output:** Raw tokens with frequency, context, confidence, source type
 
+### Agent 1B: Firecrawl CSS Deep Diver (NEW)
+- **Persona:** CSS Deep Diver
+- **Tool:** Firecrawl / httpx fallback
+- **Job:**
+  - Fetch and parse ALL linked CSS files
+  - Extract colors from CSS rules and variables
+  - Bypass CORS restrictions
+  - Find colors missed by DOM inspection
+- **Output:** Additional colors merged into main extraction
+
 ### Agent 2: Token Normalizer & Structurer
 - **Persona:** Design System Librarian
 - **Job:**