release: v2.8.3 — cache news_digest.json to skip Gemini on same-day re-runs

feat: cache news_digest.json by date, skip Gemini on same-day re-runs

.github/workflows/04.1.agentic_v2_publish.yml

@@ -60,7 +60,20 @@ jobs:
       - name: Installation of Dependencies
         run: |
           pip install --no-cache-dir pydantic PyGithub httpx fake-useragent pytz python-dotenv pyyaml tenacity
-          
+
+      - name: Get current date for digest cache key
+        id: digest-date
+        run: echo "date=$(date -u +%Y-%m-%d)" >> $GITHUB_OUTPUT
+
+      - name: Restore News Digest Cache
+        id: cache-digest
+        uses: actions/cache/restore@v5
+        with:
+          path: data/news_digest.json
+          key: news-digest-${{ steps.digest-date.outputs.date }}
+          restore-keys: |
+            news-digest-
+
       - name: Execute Video Portal Generator
         env:
           PYTHONPATH: ${{ github.workspace }}
@@ -87,6 +100,7 @@ jobs:
           python -u -m src.enrichment || echo "Enrichment pipeline skipped (no token or error)"
 
       - name: Generate News Digest
+        if: steps.cache-digest.outputs.cache-hit != 'true'
         env:
           PYTHONPATH: ${{ github.workspace }}
           GEMINI_API_KEY_1: ${{ secrets.GEMINI_API_KEY_1 }}
@@ -94,6 +108,19 @@ jobs:
         run: |
           python -u -m src.news_digest || echo "News digest generation skipped (no API key or error)"
 
+      - name: Generate RSS Feed
+        env:
+          PYTHONPATH: ${{ github.workspace }}
+        run: |
+          python -u -m src.rss_generator || echo "RSS generation skipped"
+
+      - name: Save News Digest Cache
+        if: steps.cache-digest.outputs.cache-hit != 'true' && hashFiles('data/news_digest.json') != ''
+        uses: actions/cache/save@v5
+        with:
+          path: data/news_digest.json
+          key: news-digest-${{ steps.digest-date.outputs.date }}
+
       - name: Run V2 Publisher (Render-Only)
         env:
           PYTHONPATH: ${{ github.workspace }}

.github/workflows/09.weekly_digest.yml

@@ -0,0 +1,96 @@
+name: 09. Weekly Intelligence Digest
+
+on:
+  schedule:
+    # Every Monday at 06:00 UTC (08:00 Madrid time)
+    - cron: '0 6 * * 1'
+  workflow_dispatch:
+
+permissions:
+  contents: write
+  pull-requests: write
+
+concurrency:
+  group: develop-git-write-lock
+  cancel-in-progress: false
+
+jobs:
+  weekly-digest:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Repository Synchronization
+        uses: actions/checkout@v6
+        with:
+          ref: develop
+          fetch-depth: 0
+
+      - name: Python 3.11 Environment Provisioning
+        uses: actions/setup-python@v6
+        with:
+          python-version: '3.11'
+          cache: 'pip'
+
+      - name: Install Dependencies
+        run: pip install -r requirements.txt
+
+      - name: Get current date for digest cache key
+        id: digest-date
+        run: echo "date=$(date -u +%Y-%m-%d)" >> $GITHUB_OUTPUT
+
+      - name: Restore News Digest Cache
+        id: cache-digest
+        uses: actions/cache/restore@v5
+        with:
+          path: data/news_digest.json
+          key: news-digest-${{ steps.digest-date.outputs.date }}
+          restore-keys: |
+            news-digest-
+
+      - name: Generate News Digest (Gemini)
+        if: steps.cache-digest.outputs.cache-hit != 'true'
+        env:
+          PYTHONPATH: ${{ github.workspace }}
+          GEMINI_API_KEY_1: ${{ secrets.GEMINI_API_KEY_1 }}
+          GEMINI_API_KEY_2: ${{ secrets.GEMINI_API_KEY_2 }}
+        run: |
+          python -u -m src.news_digest
+
+      - name: Save News Digest Cache
+        if: steps.cache-digest.outputs.cache-hit != 'true' && hashFiles('data/news_digest.json') != ''
+        uses: actions/cache/save@v5
+        with:
+          path: data/news_digest.json
+          key: news-digest-${{ steps.digest-date.outputs.date }}
+
+      - name: Generate RSS Feed
+        env:
+          PYTHONPATH: ${{ github.workspace }}
+        run: |
+          python -u -m src.rss_generator || echo "RSS generation skipped"
+
+      - name: Render V2 Portal (Digest Pages Only)
+        env:
+          PYTHONPATH: ${{ github.workspace }}
+          PYTHONUNBUFFERED: "1"
+        run: |
+          python -u -m src.v2_optimizer --render-only
+
+      - name: Commit and Push Weekly Digest
+        run: |
+          git config --global user.name "Nubenetes Bot"
+          git config --global user.email "bot@nubenetes.com"
+          git add data/news_digest.json v2-docs/tech-digest.md v2-docs/industry-digest.md v2-docs/feed.xml || true
+          if git diff --staged --quiet; then
+            echo "No digest changes to commit."
+          else
+            git commit -m "feat: weekly intelligence digest update [skip ci]"
+            for i in {1..3}; do
+              git pull origin develop --rebase && git push origin develop && break || sleep 10
+            done
+          fi
+
+      - name: Trigger V2 Publisher
+        uses: peter-evans/repository-dispatch@v3
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          event-type: weekly-digest-ready

.gitignore

@@ -351,6 +351,7 @@ MigrationBackup/
 # Automatización Nubenetes
 src/__pycache__/
 *.json
+!data/news_digest.json
 .env
 nubenetes_agent_env/
 .venv/

README.md

@@ -135,14 +135,14 @@ Additionally, as of May 2026, Nubenetes has reached the **Platinum Operational T
 ## 2. Repository Metrics and Evolution
 
 ### 2.1. The "Heart" of Nubenetes
-(Stats as of 2026-06-18)
+(Stats as of 2026-06-19)
 
 <!-- HEART_STATS_START -->
 | Metric | Value |
 | :--- | :--- |
 | **Total Technical Resources (Links)** | **18647+** |
 | **Specialized MD Pages** | **162** |
-| **Total Commits** | **6013+** |
+| **Total Commits** | **6082+** |
 | **Primary AI Engine** | **Google Gemini (Agentic)** |
 <!-- HEART_STATS_END -->
 
@@ -180,7 +180,7 @@ The growth of Nubenetes reflects the acceleration of the Cloud Native ecosystem.
 | 6 | 2023 | 30 | 123 | Maintenance & Refinement |
 | 7 | 2024 | 53 | 218 | Curation Strategy Pivot |
 | 8 | 2025 | 5 | 20 | Stability & Research Phase |
-| 9 | 2026 | 2454 | 10,135 | **Agentic AI Surge** (May 2026 Inception) |
+| 9 | 2026 | 2523 | 10,419 | **Agentic AI Surge** (May 2026 Inception) |
 <!-- ANNUAL_GROWTH_END -->
 
 <!-- ANNUAL_CHART_START -->
@@ -196,8 +196,8 @@ xychart-beta
     title "Nubenetes Annual Growth Metrics (2018–2026)"
     x-axis ["2018", "2019", "2020", "2021", "2022", "2023", "2024", "2025", "2026"]
     y-axis "Volume (Commits / Estimated New Refs)" 0 --> 11000
-    bar [1445, 586, 8449, 2193, 1660, 123, 218, 20, 10135]
-    bar [350, 142, 2046, 531, 402, 30, 53, 5, 2454]
+    bar [1445, 586, 8449, 2193, 1660, 123, 218, 20, 10419]
+    bar [350, 142, 2046, 531, 402, 30, 53, 5, 2523]
 ```
 <!-- ANNUAL_CHART_END -->
 
@@ -207,7 +207,7 @@ xychart-beta
 | :--- | :---: | :---: | :--- |
 | 2026-04 | 25 | 103 | Active Curation |
 | 2026-05 | 2101 | 8,677 | **Agentic Inception (Gemini Era)** |
-| 2026-06 | 328 | 1,354 | Active Curation |
+| 2026-06 | 397 | 1,639 | Active Curation |
 <!-- MONTHLY_SURGE_END -->
 
 ### 2.4. Content Distribution and Semantic Clustering

docs/static/v2_elite.css

@@ -352,6 +352,22 @@ a {
   border-color: #2dd4bf !important;
 }
 
+.hero-badge-card--amber {
+  border-color: rgba(245, 158, 11, 0.2);
+  background: rgba(245, 158, 11, 0.02);
+}
+.hero-badge-card--amber:hover {
+  background: rgba(245, 158, 11, 0.06) !important;
+  box-shadow: 0 8px 24px rgba(245, 158, 11, 0.18);
+  border-color: #f59e0b !important;
+}
+
+.hero-badge-icon {
+  font-size: 2rem;
+  line-height: 1;
+  margin-bottom: 4px;
+}
+
 .hero-badge-title {
   font-weight: bold;
   font-size: 0.95rem;
@@ -364,6 +380,56 @@ a {
   margin-top: 4px;
 }
 
+/* Intelligence Digest mini-preview on index */
+.digest-preview {
+  background: rgba(245, 158, 11, 0.04);
+  border: 1px solid rgba(245, 158, 11, 0.15);
+  border-radius: 12px;
+  padding: 20px 24px;
+  margin: 24px 0;
+}
+.digest-preview-header {
+  display: flex;
+  align-items: center;
+  justify-content: space-between;
+  margin-bottom: 12px;
+}
+.digest-preview-title {
+  font-weight: 700;
+  font-size: 1rem;
+  color: var(--md-primary-fg-color);
+}
+.digest-preview-link {
+  font-size: 0.8rem;
+  color: #f59e0b;
+  text-decoration: none;
+  font-weight: 600;
+  letter-spacing: 0.02em;
+}
+.digest-preview-link:hover { text-decoration: underline; }
+.digest-preview-list {
+  list-style: none;
+  margin: 0;
+  padding: 0;
+}
+.digest-preview-list li {
+  padding: 5px 0;
+  border-bottom: 1px solid rgba(245, 158, 11, 0.08);
+  font-size: 0.875rem;
+  display: flex;
+  align-items: center;
+  gap: 8px;
+}
+.digest-preview-list li:last-child { border-bottom: none; }
+.digest-preview-cat {
+  font-size: 0.7rem;
+  color: #f59e0b;
+  background: rgba(245, 158, 11, 0.1);
+  border-radius: 4px;
+  padding: 1px 6px;
+  white-space: nowrap;
+}
+
 /* Hero Showcase Image wrapper (4 cars in a container) */
 .hero-showcase-wrapper {
   margin: 24px auto;
@@ -977,6 +1043,18 @@ input[type="text"] {
   display: flex;
   align-items: center;
   gap: 8px;
+  flex-wrap: wrap;
+}
+
+.trending-section__updated {
+  font-size: 0.55em;
+  font-weight: 500;
+  padding: 2px 10px;
+  border-radius: 20px;
+  background: rgba(14, 165, 233, 0.12);
+  color: var(--md-accent-fg-color);
+  border: 1px solid rgba(14, 165, 233, 0.25);
+  letter-spacing: 0.02em;
 }
 
 .trending-grid {

src/dedup.py

@@ -71,7 +71,7 @@ def find_title_duplicates(inventory: Dict, threshold: float = 0.85) -> List[Tupl
         norm = normalize_title(title)
         if len(norm) < 10:
             continue
-        entries.append((url, norm, entry.get("stars", 0)))
+        entries.append((url, norm, entry.get("stars") or 0))
 
     log_event(f"[Dedup] Building title index for {len(entries)} entries...")
 
@@ -105,7 +105,7 @@ def find_title_duplicates(inventory: Dict, threshold: float = 0.85) -> List[Tupl
 
 def _entry_score(entry: Dict) -> Tuple:
     return (
-        entry.get("stars", 0),
+        entry.get("stars") or 0,
         1 if entry.get("ai_summary") else 0,
         1 if entry.get("hierarchy") else 0,
         len(entry.get("tags", [])),

src/enrichment.py

@@ -13,10 +13,10 @@ from src.logger import log_event
 # ---------------------------------------------------------------------------
 # Constants
 # ---------------------------------------------------------------------------
-CNCF_LANDSCAPE_URL = "https://landscape.cncf.io/api/items"
+CNCF_LANDSCAPE_URL = "https://landscape.cncf.io/api/items"  # Legacy, now SPA — fallback to GitHub topic search
 GITHUB_API_BASE = "https://api.github.com"
-GITHUB_RATE_DELAY = 0.75  # seconds between GitHub API calls to stay under 5000/hr
-MAX_REPOS_DEFAULT = 500
+GITHUB_RATE_DELAY = 0.5   # seconds between GitHub API calls (5000/hr limit = ~1.4/s safe)
+MAX_REPOS_DEFAULT = 200   # cap per run — 200 × 0.5s = ~100s, well within CI timeout
 ACTIVITY_STALENESS_DAYS = 30
 
 # Community health thresholds
@@ -74,38 +74,37 @@ def _is_activity_stale(entry: Dict) -> bool:
 # ---------------------------------------------------------------------------
 
 async def fetch_cncf_landscape() -> Dict[str, str]:
-    """Fetch CNCF project graduation status.
+    """Fetch CNCF project graduation status via GitHub topic search.
 
-    Returns dict mapping repo_url (normalized) -> maturity
-    ("sandbox" | "incubating" | "graduated" | "archived").
+    The legacy landscape.cncf.io/api/items endpoint is now a SPA and no
+    longer returns JSON.  Instead, we search GitHub for repos with CNCF
+    maturity topics (cncf-sandbox, cncf-incubating, cncf-graduated).
+
+    Returns dict mapping repo_url (normalized) -> maturity.
     """
     result: Dict[str, str] = {}
+    headers = _github_headers()
+    maturity_queries = {
+        "graduated": "topic:cncf-graduated",
+        "incubating": "topic:cncf-incubating",
+        "sandbox": "topic:cncf-sandbox",
+    }
+
     async with httpx.AsyncClient(timeout=30.0) as client:
-        try:
-            resp = await client.get(CNCF_LANDSCAPE_URL)
-            resp.raise_for_status()
-            items = resp.json()
-        except Exception as e:
-            log_event(f"[WARN] Failed to fetch CNCF landscape: {str(e)[:200]}")
-            return result
-
-    if not isinstance(items, list):
-        log_event("[WARN] CNCF landscape response is not a list; skipping")
-        return result
-
-    for item in items:
-        repo_url = item.get("repo_url") or ""
-        project = item.get("project")
-        if not repo_url or not project:
-            continue
-        maturity = project if isinstance(project, str) else project.get("maturity", "")
-        if not maturity:
-            continue
-        maturity = maturity.lower()
-        if maturity not in ("sandbox", "incubating", "graduated", "archived"):
-            continue
-        normalized = _normalize_repo_url(repo_url)
-        result[normalized] = maturity
+        for maturity, query in maturity_queries.items():
+            try:
+                url = f"{GITHUB_API_BASE}/search/repositories?q={query}&per_page=100"
+                resp = await client.get(url, headers=headers)
+                resp.raise_for_status()
+                data = resp.json()
+                for repo in data.get("items", []):
+                    repo_url = repo.get("html_url", "")
+                    if repo_url:
+                        result[_normalize_repo_url(repo_url)] = maturity
+                log_event(f"  [CNCF] {maturity}: {len(data.get('items', []))} repos found")
+            except Exception as e:
+                log_event(f"[WARN] CNCF {maturity} search failed: {str(e)[:100]}")
+            await asyncio.sleep(GITHUB_RATE_DELAY)
 
     log_event(f"[CNCF] Fetched {len(result)} projects from CNCF landscape")
     return result
@@ -156,15 +155,15 @@ async def _fetch_repo_activity(
     client: httpx.AsyncClient,
     owner_repo: str,
 ) -> Tuple[int, int]:
-    """Fetch open issue count and recent open PR count for a single repo.
+    """Fetch open issue + PR count for a single repo in one API call.
 
-    Returns (open_issues_count, open_prs_count).
+    GitHub's open_issues_count includes PRs, so a single /repos endpoint
+    call is sufficient. Returns (open_issues_count, 0) — the caller uses
+    the combined metric for health classification.
     """
     headers = _github_headers()
     open_issues = 0
-    open_prs = 0
 
-    # Fetch repo-level stats (open_issues_count includes PRs on GitHub)
     try:
         resp = await client.get(
             f"{GITHUB_API_BASE}/repos/{owner_repo}",
@@ -174,37 +173,15 @@ async def _fetch_repo_activity(
         if resp.status_code == 200:
             data = resp.json()
             open_issues = data.get("open_issues_count", 0)
+        elif resp.status_code == 429:
+            # Rate limited — back off
+            await asyncio.sleep(5.0)
     except Exception as e:
         log_event(f"[WARN] GitHub repo fetch failed for {owner_repo}: {str(e)[:120]}")
 
     await asyncio.sleep(GITHUB_RATE_DELAY)
 
-    # Fetch open PRs (page 1 only — we use total_count from search or headers)
-    try:
-        resp = await client.get(
-            f"{GITHUB_API_BASE}/repos/{owner_repo}/pulls",
-            headers=headers,
-            params={"state": "open", "sort": "created", "per_page": 1},
-            timeout=15.0,
-        )
-        if resp.status_code == 200:
-            # The total count of open PRs is not directly in the body for the
-            # list endpoint, but we can parse the Link header for the last page.
-            # As a simpler approach, the body is a list; if it has items the repo
-            # has open PRs. We use the repo-level open_issues_count as the
-            # combined metric (GitHub counts PRs as issues).
-            pr_data = resp.json()
-            if isinstance(pr_data, list) and len(pr_data) > 0:
-                # Parse Link header for total pages
-                link_header = resp.headers.get("Link", "")
-                last_match = re.search(r'page=(\d+)>;\s*rel="last"', link_header)
-                open_prs = int(last_match.group(1)) if last_match else len(pr_data)
-    except Exception as e:
-        log_event(f"[WARN] GitHub PRs fetch failed for {owner_repo}: {str(e)[:120]}")
-
-    await asyncio.sleep(GITHUB_RATE_DELAY)
-
-    return open_issues, open_prs
+    return open_issues, 0
 
 
 def _classify_health(total_activity: int) -> str:
@@ -329,6 +306,7 @@ async def detect_license_changes(inventory: Dict) -> List[Dict]:
         log_event("[License] No repos with stored licenses to check")
         return []
 
+    candidates = candidates[:MAX_REPOS_DEFAULT]  # cap to same limit as activity enrichment
     log_event(f"[License] Checking {len(candidates)} repos for license changes")
 
     changes: List[Dict] = []

src/news_digest.py

@@ -145,6 +145,12 @@ class NewsDigestEngine:
         "12_months": 365,
     }
 
+    ITEMS_PER_PERIOD: Dict[str, int] = {
+        "3_months": 10,
+        "6_months": 15,
+        "12_months": 20,
+    }
+
     # ------------------------------------------------------------------ #
 
     def __init__(self) -> None:
@@ -176,26 +182,56 @@ class NewsDigestEngine:
         return None
 
     def _get_entry_geo(self, entry: dict) -> str | None:
-        """Return the geo digest category if ``geo_region`` matches."""
+        """Return the geo digest category using geo_region field, falling back to URL TLD inference."""
         region = entry.get("geo_region", "")
         for geo_name, geo_val in self.GEO_CATEGORIES.items():
             if region == geo_val:
                 return geo_name
+        # Fallback: infer from URL TLD
+        return self._infer_geo_from_url(entry.get("url", ""))
+
+    @staticmethod
+    def _infer_geo_from_url(url: str) -> str | None:
+        """Infer geo category from URL TLD. Returns GEO_CATEGORIES key or None."""
+        try:
+            from urllib.parse import urlparse
+            host = urlparse(url).hostname or ""
+            # Ordered longest-first to avoid .uk matching before .co.uk
+            tld_to_region = [
+                (".com.au", "Asia-Pacific"), (".co.uk", "Europe"), (".co.jp", "Asia-Pacific"),
+                (".co.kr", "Asia-Pacific"), (".com.br", "Americas"), (".com.mx", "Americas"),
+                (".es", "España"), (".de", "Europe"), (".fr", "Europe"), (".it", "Europe"),
+                (".pt", "Europe"), (".nl", "Europe"), (".be", "Europe"), (".se", "Europe"),
+                (".dk", "Europe"), (".fi", "Europe"), (".no", "Europe"), (".ch", "Europe"),
+                (".at", "Europe"), (".pl", "Europe"), (".cz", "Europe"), (".uk", "Europe"),
+                (".ie", "Europe"), (".eu", "Europe"), (".cn", "Asia-Pacific"),
+                (".jp", "Asia-Pacific"), (".kr", "Asia-Pacific"), (".sg", "Asia-Pacific"),
+                (".in", "Asia-Pacific"), (".au", "Asia-Pacific"), (".nz", "Asia-Pacific"),
+                (".ca", "Americas"), (".mx", "Americas"), (".br", "Americas"),
+            ]
+            for tld, region in tld_to_region:
+                if host.endswith(tld):
+                    return region
+        except Exception:
+            pass
         return None
 
     @staticmethod
     def _is_within_period(entry: dict, cutoff_iso: str) -> bool:
-        """Return *True* when the entry's ``discovered_at`` is on or after
-        the ISO-formatted *cutoff_iso* string.  ISO 8601 strings sort
-        lexicographically so a simple ``>=`` comparison is sufficient.
-        """
+        """Check if entry falls within the time period using discovered_at,
+        with year field as fallback for backfilled entries."""
         discovered = entry.get("discovered_at", "")
-        if not discovered:
-            return False
-        try:
-            return discovered >= cutoff_iso
-        except Exception:
-            return False
+        if discovered:
+            try:
+                if discovered >= cutoff_iso:
+                    return True
+            except Exception:
+                pass
+        year = entry.get("year", "")
+        if year and isinstance(year, str) and year.isdigit():
+            cutoff_year = cutoff_iso[:4] if len(cutoff_iso) >= 4 else "2020"
+            return year >= cutoff_year
+        return False
 
     # ------------------------------------------------------------------ #
     # Prompt builder                                                      #
@@ -253,8 +289,8 @@ class NewsDigestEngine:
                 "url": e["url"],
                 "title": e.get("title", "Unknown"),
                 "date": e.get("discovered_at", "")[:10],
-                "stars": e.get("stars", 0),
-                "impact": "high" if e.get("stars", 0) >= 4 else "medium",
+                "stars": e.get("stars") or 0,
+                "impact": "high" if (e.get("stars") or 0) >= 4 else "medium",
                 "why": (e.get("ai_summary", "") or "")[:200],
                 "category": cat_name,
             }
@@ -310,20 +346,20 @@ class NewsDigestEngine:
             for cat_name, entries in category_pools.items():
                 entries.sort(
                     key=lambda x: (
-                        x.get("stars", 0),
-                        x.get("discovered_at", ""),
+                        x.get("stars") or 0,
+                        x.get("discovered_at") or "",
                     ),
                     reverse=True,
                 )
 
+                max_items = self.ITEMS_PER_PERIOD.get(period_name, 10)
+
                 if len(entries) < 3:
-                    # Too few entries – include all without AI ranking
                     digest[period_name][cat_name] = self._fallback_items(
-                        entries, cat_name
+                        entries, cat_name, limit=max_items
                     )
                     continue
 
-                # Ask Gemini to rank
                 try:
                     prompt = self._build_ranking_prompt(
                         cat_name, entries, period_name
@@ -351,7 +387,7 @@ class NewsDigestEngine:
                                 }
                             )
 
-                    digest[period_name][cat_name] = ranked[:10]
+                    digest[period_name][cat_name] = ranked[:max_items]
                     log_event(
                         f"  [Digest] {period_name}/{cat_name}: "
                         f"{len(ranked)} items ranked"
@@ -364,7 +400,7 @@ class NewsDigestEngine:
                         "using star-based fallback"
                     )
                     digest[period_name][cat_name] = self._fallback_items(
-                        entries, cat_name
+                        entries, cat_name, limit=max_items
                     )
 
                 # Respect Gemini rate limits

src/rss_generator.py

@@ -0,0 +1,111 @@
+"""RSS 2.0 feed generator for the Nubenetes Intelligence Digest.
+
+Reads data/news_digest.json and writes v2-docs/feed.xml with the top
+items from the 3-month digest window across all tech categories.
+"""
+
+from __future__ import annotations
+
+import json
+import os
+from datetime import datetime
+from email.utils import format_datetime
+from xml.sax.saxutils import escape
+
+from src.logger import log_event
+
+DIGEST_PATH = "data/news_digest.json"
+OUTPUT_PATH = "v2-docs/feed.xml"
+FEED_TITLE = "Nubenetes Intelligence Digest"
+FEED_LINK = "https://nubenetes.com/"
+FEED_DESCRIPTION = "AI-curated top picks from the Cloud Native & Kubernetes ecosystem"
+FEED_LANGUAGE = "en"
+ITEMS_PER_FEED = 20
+
+TECH_CATS = [
+    "Kubernetes & Orchestration", "AI & Agents", "Security & Compliance",
+    "CI/CD & GitOps", "Observability, SRE & Testing", "Infrastructure as Code",
+    "Containers & Runtime", "Networking & Service Mesh", "Cloud Providers & FinOps",
+    "MLOps & Data Science", "Data, Messaging & Storage",
+]
+
+
+def _rfc822(dt: datetime) -> str:
+    return format_datetime(dt)
+
+
+def generate_rss() -> None:
+    if not os.path.exists(DIGEST_PATH):
+        log_event("[WARN] rss_generator: news_digest.json not found, skipping RSS generation")
+        return
+
+    try:
+        with open(DIGEST_PATH, "r", encoding="utf-8") as f:
+            digest = json.load(f)
+    except Exception as e:
+        log_event(f"[WARN] rss_generator: failed to load digest: {str(e)[:100]}")
+        return
+
+    period_data = digest.get("3_months", {})
+    items: list[dict] = []
+
+    for cat in TECH_CATS:
+        for entry in period_data.get(cat, []):
+            items.append({**entry, "_cat": cat})
+
+    # Sort by impact then date
+    impact_rank = {"critical": 3, "high": 2, "medium": 1}
+    items.sort(
+        key=lambda x: (impact_rank.get(x.get("impact", "medium"), 0), x.get("date", "")),
+        reverse=True,
+    )
+    items = items[:ITEMS_PER_FEED]
+
+    build_date = _rfc822(datetime.utcnow())
+
+    lines = [
+        '<?xml version="1.0" encoding="UTF-8"?>',
+        '<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">',
+        "  <channel>",
+        f"    <title>{escape(FEED_TITLE)}</title>",
+        f"    <link>{FEED_LINK}</link>",
+        f"    <description>{escape(FEED_DESCRIPTION)}</description>",
+        f"    <language>{FEED_LANGUAGE}</language>",
+        f"    <lastBuildDate>{build_date}</lastBuildDate>",
+        f'    <atom:link href="{FEED_LINK}feed.xml" rel="self" type="application/rss+xml"/>',
+    ]
+
+    for item in items:
+        title = escape(item.get("title", "Unknown"))
+        url = item.get("url", "#")
+        why = escape(item.get("why", ""))
+        cat = escape(item.get("_cat", ""))
+        impact = item.get("impact", "medium")
+        date_str = item.get("date", "")
+        try:
+            pub_date = _rfc822(datetime.strptime(date_str, "%Y-%m-%d")) if date_str else build_date
+        except Exception:
+            pub_date = build_date
+
+        lines += [
+            "    <item>",
+            f"      <title>{title}</title>",
+            f"      <link>{url}</link>",
+            f"      <guid isPermaLink=\"true\">{url}</guid>",
+            f"      <pubDate>{pub_date}</pubDate>",
+            f"      <category>{cat}</category>",
+            f"      <description>[{impact.upper()}] {why}</description>",
+            "    </item>",
+        ]
+
+    lines += ["  </channel>", "</rss>"]
+
+    os.makedirs(os.path.dirname(OUTPUT_PATH), exist_ok=True)
+    with open(OUTPUT_PATH, "w", encoding="utf-8") as f:
+        f.write("\n".join(lines) + "\n")
+
+    log_event(f"[INFO] rss_generator: wrote {len(items)} items to {OUTPUT_PATH}")
+
+
+if __name__ == "__main__":
+    generate_rss()

src/v2_optimizer.py

@@ -629,7 +629,7 @@ class V2VisionEngine:
         # 1. GitHub Objective Reality (Mandate 43)
         raw_gh = item.get("gh_stars", 0)
         gh_stars = int(raw_gh) if str(raw_gh).isdigit() else 0
-        curator_stars = int(item.get("stars", 0))
+        curator_stars = int(item.get("stars") or 0)
 
         if gh_stars > 15000 or curator_stars >= 5: 
             tags.add("[DE FACTO STANDARD]")
@@ -639,7 +639,7 @@ class V2VisionEngine:
             if "[COMMUNITY-TOOL]" in tags: tags.remove("[COMMUNITY-TOOL]")
         
         # 2. Type Mapping (AI based labels)
-        res_type = item.get("resource_type", "Reference").lower()
+        res_type = (item.get("resource_type") or "Reference").lower()
         if any(x in res_type for x in ["guide", "tutorial", "hands-on", "learning", "course"]): 
             tags.add("[GUIDE]")
         if any(x in res_type for x in ["case study", "report", "whitepaper", "success story", "usage"]): 
@@ -753,7 +753,7 @@ class V2VisionEngine:
                 current["__links__"].append(item)
 
         def sort_rec(node):
-            if "__links__" in node: node["__links__"].sort(key=lambda x: (-x.get("stars", 1), -(int(x["year"]) if str(x.get("year", "")).isdigit() else 0)))
+            if "__links__" in node: node["__links__"].sort(key=lambda x: (-(x.get("stars") or 1), -(int(x["year"]) if str(x.get("year", "")).isdigit() else 0)))
             for k, v in node.items():
                 if k != "__links__" and isinstance(v, dict): sort_rec(v)
                 
@@ -953,8 +953,9 @@ class V2VisionEngine:
         geo_cats = ["Americas", "Europe", "España", "Asia-Pacific"]
         period_labels = {"3_months": "Last 3 Months", "6_months": "Last 6 Months", "12_months": "Last 12 Months"}
 
-        def render_digest_page(title, categories, digest_data):
-            md = f"# {title}\n\n"
+        def render_digest_page(title, categories, digest_data, search_boost=1):
+            md = f"---\nsearch:\n  boost: {search_boost}\n---\n\n"
+            md += f"# {title}\n\n"
             md += "!!! tip \"Nubenetes Intelligence Digest\"\n"
             md += "    AI-curated ranking of the most impactful resources, updated monthly.\n\n"
             for period_key, period_label in period_labels.items():
@@ -964,22 +965,23 @@ class V2VisionEngine:
                     items = period_data.get(cat, [])
                     if not items:
                         continue
-                    md += f"    ## {cat}\n\n"
+                    md += f"    **{cat}**\n\n"
                     md += "    | Date | Resource | Impact | Why It Matters |\n"
                     md += "    | :--- | :--- | :---: | :--- |\n"
                     for item in items:
                         impact_badge = {"critical": "🔴", "high": "🟡", "medium": "🔵"}.get(item.get("impact", "medium"), "🔵")
                         t = nuclear_strip(item.get("title", "Unknown"))
-                        md += f'    | {item.get("date", "")} | [{t}]({item.get("url", "#")}) | {impact_badge} {item.get("impact", "medium")} | {item.get("why", "")} |\n'
+                        why = (item.get("why", "") or "").replace("|", "-").replace("\n", " ")
+                        md += f'    | {item.get("date", "")} | [{t}]({item.get("url", "#")}) | {impact_badge} {item.get("impact", "medium")} | {why} |\n'
                     md += "\n"
                 md += "\n"
             return md
 
-        tech_md = render_digest_page("📊 Nubenetes Tech & Cloud Intelligence Digest", tech_cats, digest_data)
+        tech_md = render_digest_page("📊 Nubenetes Tech & Cloud Intelligence Digest", tech_cats, digest_data, search_boost=2)
         with open(os.path.join(V2_DIR, "tech-digest.md"), "w", encoding="utf-8") as f:
             f.write(tech_md)
 
-        industry_md = render_digest_page("🌍 Nubenetes Industry & Geo Intelligence Digest", geo_cats, digest_data)
+        industry_md = render_digest_page("🌍 Nubenetes Industry & Geo Intelligence Digest", geo_cats, digest_data, search_boost=2)
         with open(os.path.join(V2_DIR, "industry-digest.md"), "w", encoding="utf-8") as f:
             f.write(industry_md)
 
@@ -1005,7 +1007,14 @@ class V2VisionEngine:
             top_items = top_items[:6]
 
             impact_icons = {"critical": "🔴", "high": "🟡", "medium": "🔵"}
-            cards_html = '<div class="trending-section">\n<div class="trending-section__title">🔥 Trending Now — Cloud Native Intelligence</div>\n<div class="trending-grid">\n'
+            try:
+                digest_mtime = os.path.getmtime(digest_path)
+                from datetime import datetime as _dt
+                digest_updated = _dt.fromtimestamp(digest_mtime).strftime("%b %d, %Y")
+            except Exception:
+                digest_updated = ""
+            updated_badge = f'<span class="trending-section__updated">Updated {digest_updated}</span>' if digest_updated else ""
+            cards_html = f'<div class="trending-section">\n<div class="trending-section__title">🔥 Trending Now — Cloud Native Intelligence {updated_badge}</div>\n<div class="trending-grid">\n'
             for item in top_items:
                 impact = item.get("impact", "medium")
                 cards_html += (
@@ -1024,7 +1033,7 @@ class V2VisionEngine:
             cards_html += '</div>\n</div>\n'
             pulse_md = cards_html
         else:
-            trending_pool = sorted([dict(meta, url=url) for url, meta in self.inventory.items() if isinstance(meta, dict) and meta.get("stars", 0) >= 4], key=lambda x: (str(x.get("year", "0000")) if str(x.get("year", "")).isdigit() else "0000", -x.get("stars", 0)), reverse=True)
+            trending_pool = sorted([dict(meta, url=url) for url, meta in self.inventory.items() if isinstance(meta, dict) and (meta.get("stars") or 0) >= 4], key=lambda x: (str(x.get("year", "0000")) if str(x.get("year", "")).isdigit() else "0000", -(x.get("stars") or 0)), reverse=True)
             pulse_md = "## The Agentic Pulse\n" + "\n".join([f"- **({l.get('year', 'N/A')})** [**=={nuclear_strip(l['title'])}==**]({l['url'].strip()}) {'🌟'*l.get('stars',3)}" for l in trending_pool[:5]])
         
         # Calculate coverage for the index
@@ -1092,6 +1101,13 @@ class V2VisionEngine:
             "      <div class=\"hero-badge-subtitle\">Agentic Ecosystem</div>\n"
             "    </div>\n"
             "  </a>\n"
+            "  <a href=\"./tech-digest/\" style=\"text-decoration: none; color: inherit; display: block;\">\n"
+            "    <div class=\"hero-badge-card hero-badge-card--amber\">\n"
+            "      <div class=\"hero-badge-icon\">📊</div>\n"
+            "      <div class=\"hero-badge-title\">Intelligence Digest</div>\n"
+            "      <div class=\"hero-badge-subtitle\">Top picks · 3/6/12 months</div>\n"
+            "    </div>\n"
+            "  </a>\n"
             "  <a href=\"./videos/\" style=\"text-decoration: none; color: inherit; display: block;\">\n"
             "    <div class=\"hero-badge-card hero-badge-card--pink\">\n"
             "      <img src=\"/images/video_hub_logo.png\" alt=\"Agentic Video Hub\"/>\n"
@@ -1437,7 +1453,7 @@ class V2VisionEngine:
             md += f"<summary>{summary_text}</summary>\n\n"
             
             # Sort links under this tag by impact stars and then by year
-            sorted_links = sorted(by_tag[tag], key=lambda x: (-x.get("stars", 1), -(int(x["year"]) if str(x.get("year", "")).isdigit() else 0)))
+            sorted_links = sorted(by_tag[tag], key=lambda x: (-(x.get("stars") or 1), -(int(x["year"]) if str(x.get("year", "")).isdigit() else 0)))
             
             rendered_links = sorted_links[:100]
             for l in rendered_links:

v2-docs/index.md

@@ -39,6 +39,13 @@
       <div class="hero-badge-subtitle">Agentic Ecosystem</div>
     </div>
   </a>
+  <a href="./tech-digest/" style="text-decoration: none; color: inherit; display: block;">
+    <div class="hero-badge-card hero-badge-card--amber">
+      <div class="hero-badge-icon">📊</div>
+      <div class="hero-badge-title">Intelligence Digest</div>
+      <div class="hero-badge-subtitle">Top picks · 3/6/12 months</div>
+    </div>
+  </a>
   <a href="./videos/" style="text-decoration: none; color: inherit; display: block;">
     <div class="hero-badge-card hero-badge-card--pink">
       <img src="/images/video_hub_logo.png" alt="Agentic Video Hub"/>

v2-docs/industry-digest.md

@@ -3,7 +3,12 @@
 !!! tip "Nubenetes Intelligence Digest"
     AI-curated ranking of the most impactful resources, updated monthly.
 
-!!! info "Coming Soon"
-    The Industry & Geo Digest will be populated automatically when the monthly pipeline runs with Gemini AI ranking. Check back after the next curation cycle.
+=== "Last 3 Months"
+
+
+=== "Last 6 Months"
+
+
+=== "Last 12 Months"
+
 
-    **4 geographic categories** (Americas, Europe, Spain, Asia-Pacific) will surface industry-relevant resources classified by company and region.

v2-mkdocs.yml

@@ -96,10 +96,13 @@ extra:
   version:
     provider: mike # Ready for version switching
 
+extra_head:
+  - '<link rel="alternate" type="application/rss+xml" title="Nubenetes Intelligence Digest" href="/feed.xml"/>'
+
 extra_css:
   - https://fonts.googleapis.com/css2?family=Inter:wght@400;500;700&display=swap
   - static/extra.css
-  - static/v2_elite.css?v=2.4.0
+  - static/v2_elite.css?v=2.7.0
 
 extra_javascript:
   - static/v2_filter.js