feat: add company/geo_region extraction to Gemini prompts, add enrichment/dedup to cron, fix nav sync for digest pages

- Update curator Gemini prompt with Phase 5: Company & Geo Classification
  to extract company name and geo_region (americas/europe/spain/asia_pacific)
  for industry digest categories
- Store company and geo_region from AI response in eval_data
- Add Intelligence Digest nav entries to _sync_enterprise_navigation so
  digest pages persist across nav rebuilds
- Add dedup scan and enrichment pipeline steps to monthly cron workflow
  (01.1.agentic_cron.yml) in addition to publish workflow

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

.github/workflows/01.1.agentic_cron.yml

@@ -178,6 +178,21 @@ jobs:
             gh workflow run 01.1.agentic_cron.yml -f historical_mode=true -f historical_chunked=true -f historical_until_date=$NEXT_DATE
           fi
 
+      - name: Run Deduplication Scan
+        if: success()
+        env:
+          PYTHONPATH: .
+        run: |
+          python -u -c "import asyncio; from src.dedup import run_dedup; asyncio.run(run_dedup(dry_run=False))" || echo "Dedup scan skipped"
+
+      - name: Run Enrichment Pipeline
+        if: success()
+        env:
+          PYTHONPATH: .
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          python -u -m src.enrichment || echo "Enrichment pipeline skipped"
+
       - name: Upload Visual Dashboard Artifact
         if: always()
         uses: actions/upload-artifact@v7

src/agentic_curator.py

@@ -143,7 +143,10 @@ async def evaluate_extracted_assets(raw_assets: List[Dict]) -> Dict[str, Dict]:
             "- Assign tags. You MUST include:\n"
             "  1. 1 to 2 maturity tags from: [DE FACTO STANDARD], [ENTERPRISE-STABLE], [EMERGING], [GUIDE], [CASE STUDY], [COMMUNITY-TOOL], [LEGACY].\n"
             "  2. Fine-grained technical/architectural tags from the content (e.g., [EBPF], [WASM], [GITOPS], [IAC], [SERVICE-MESH], [SERVERLESS], [MLOPS], [DB]). Keep them uppercase and wrapped in brackets.\n"
-            "Respond ONLY JSON list: [{\"url\": \"...\", \"impact_score\": int, \"reputation_penalty\": bool, \"reputation_summary\": \"...\", \"pub_date\": \"YYYY-MM-DD\", \"primary_category\": \"...\", \"suggested_new_category\": \"...\", \"title\": \"...\", \"desc\": \"...\", \"en_summary\": \"High-density summary...\", \"language\": \"...\", \"type\": \"...\", \"level\": \"...\", \"technical_hierarchy\": [...], \"tags\": [...], \"is_microservice\": bool}, ...]\n\n"
+            "PHASE 5: COMPANY & GEO CLASSIFICATION\n"
+            "- Identify 'company': The company/organization that authored or is the primary subject (e.g., 'Google', 'Netflix', 'CNCF', 'Independent').\n"
+            "- Identify 'geo_region': The HQ region of that company. Use one of: 'americas', 'europe', 'spain', 'asia_pacific', 'global'.\n"
+            "Respond ONLY JSON list: [{\"url\": \"...\", \"impact_score\": int, \"reputation_penalty\": bool, \"reputation_summary\": \"...\", \"pub_date\": \"YYYY-MM-DD\", \"primary_category\": \"...\", \"suggested_new_category\": \"...\", \"title\": \"...\", \"desc\": \"...\", \"en_summary\": \"High-density summary...\", \"language\": \"...\", \"type\": \"...\", \"level\": \"...\", \"technical_hierarchy\": [...], \"tags\": [...], \"is_microservice\": bool, \"company\": \"...\", \"geo_region\": \"...\"}, ...]\n\n"
             "RESOURCES:\n" + "\n".join([f"- {d['asset']['url']}: (MVQ Penalty: {d['mvq_penalty']}) {d['content']}" for d in batch_data])
         )
 
@@ -208,6 +211,7 @@ async def evaluate_extracted_assets(raw_assets: List[Dict]) -> Dict[str, Dict]:
                             "reputation_status": "Vetted" if not data.get("reputation_penalty") else "Suspicious",
                             "reputation_summary": data.get("reputation_summary", ""),
                             "source_provenance": d["asset"].get("source_type", "Social"), "social_preview_url": d["rich_meta"].get("og_image", ""),
+                            "company": data.get("company", ""), "geo_region": data.get("geo_region", ""),
                             "category": primary_cat, "status": "online", "last_checked": datetime.now().timestamp(),
                             "discovered_at": datetime.now(MADRID_TZ).isoformat(),
                             "last_ai_eval": datetime.now(MADRID_TZ).isoformat(),

src/v2_optimizer.py

@@ -1463,10 +1463,13 @@ class V2VisionEngine:
         try:
             with open("v2-mkdocs.yml", "r") as f: content = f.read()
             nav = [
-                "nav:", 
-                "  - \"🔙 Back to V1 (Exhaustive)\": https://nubenetes.com/v1/", 
+                "nav:",
+                "  - \"🔙 Back to V1 (Exhaustive)\": https://nubenetes.com/v1/",
                 "  - \"The 2026 Vision\": index.md",
                 "  - \"Technical Tags\": tags.md",
+                "  - \"Intelligence Digest\":",
+                "    - \"Tech & Cloud Digest\": tech-digest.md",
+                "    - \"Industry & Geo Digest\": industry-digest.md",
                 "  - \"Agentic Video Hub\":",
                 "      - videos/index.md",
                 "      - \"AI Agents and MCP\": videos/ai-agents.md",