diff --git a/.env b/.env
index 854e461..4cb0207 100644
--- a/.env
+++ b/.env
@@ -9,5 +9,5 @@ ROYALTY_IMAGE_API_KEY=
 ROYALTY_IMAGE_PROVIDERS=pixabay,unsplash,pexels,wikimedia,picsum
 PIXABAY_API_KEY=54637577-dbef68c927eec6553190fa4dc
 UNSPLASH_ACCESS_KEY=
-PEXELS_API_KEY=
+PEXELS_API_KEY=fRdPmXg16nsz1pPe0Zmp02eALJkhAz4sG7g4RN56Q3J90Qi6qV3Qvuz8
 SUMMARY_LENGTH_SCALE=3
\ No newline at end of file
diff --git a/README.md b/README.md
index dcd4bea..26623b3 100644
--- a/README.md
+++ b/README.md
@@ -46,6 +46,41 @@ Exit codes:
 - `0`: Command completed successfully (including runs that store zero new rows)
 - `1`: Fatal command failure (for example missing API keys or unrecoverable runtime error)
 
+## Admin Maintenance Commands
+
+ClawFort includes an admin command suite to simplify operational recovery and maintenance.
+
+```bash
+# List admin subcommands
+python -m backend.cli admin --help
+
+# Fetch n articles on demand
+python -m backend.cli admin fetch --count 10
+
+# Refetch images for latest 30 articles (sequential queue + exponential backoff)
+python -m backend.cli admin refetch-images --limit 30
+
+# Clean archived records older than N days
+python -m backend.cli admin clean-archive --days 60 --confirm
+
+# Clear optimized image cache files
+python -m backend.cli admin clear-cache --confirm
+
+# Clear existing news items (includes archived when requested)
+python -m backend.cli admin clear-news --include-archived --confirm
+
+# Rebuild content from scratch (clear + fetch)
+python -m backend.cli admin rebuild-site --count 10 --confirm
+
+# Regenerate translations for existing articles
+python -m backend.cli admin regenerate-translations --limit 100
+```
+
+Safety guardrails:
+- Destructive commands require `--confirm`.
+- Dry-run previews are available for applicable commands via `--dry-run`.
+- Admin output follows a structured format like: `admin:<command> status=<ok|error|blocked> ...`.
+
 ## Multilingual Support
 
 ClawFort supports English (`en`), Tamil (`ta`), and Malayalam (`ml`) content delivery.
diff --git a/backend/__pycache__/cli.cpython-313.pyc b/backend/__pycache__/cli.cpython-313.pyc
index e558b78..8ad57c9 100644
Binary files a/backend/__pycache__/cli.cpython-313.pyc and b/backend/__pycache__/cli.cpython-313.pyc differ
diff --git a/backend/__pycache__/config.cpython-313.pyc b/backend/__pycache__/config.cpython-313.pyc
index 48dd2bc..94ff737 100644
Binary files a/backend/__pycache__/config.cpython-313.pyc and b/backend/__pycache__/config.cpython-313.pyc differ
diff --git a/backend/__pycache__/news_service.cpython-313.pyc b/backend/__pycache__/news_service.cpython-313.pyc
index d8e65a8..0a9dae9 100644
Binary files a/backend/__pycache__/news_service.cpython-313.pyc and b/backend/__pycache__/news_service.cpython-313.pyc differ
diff --git a/backend/cli.py b/backend/cli.py
index ee38231..688e1f5 100644
--- a/backend/cli.py
+++ b/backend/cli.py
@@ -1,13 +1,31 @@
 import argparse
 import asyncio
+import datetime
+import json
 import logging
 import os
+import re
 import sys
 import time
 
+from sqlalchemy import and_, desc
+
 from backend import config
-from backend.database import init_db
-from backend.news_service import process_and_store_news
+from backend.database import SessionLocal, init_db
+from backend.models import NewsItem
+from backend.news_service import (
+    download_and_optimize_image,
+    extract_image_keywords,
+    fetch_royalty_free_image,
+    generate_translations,
+    process_and_store_news,
+)
+from backend.repository import (
+    create_translation,
+    delete_archived_news,
+    get_translation,
+    resolve_tldr_points,
+)
 
 logging.basicConfig(
     level=logging.INFO,
@@ -16,6 +34,131 @@ logging.basicConfig(
 logger = logging.getLogger(__name__)
 
 
+def positive_int(value: str) -> int:
+    try:
+        parsed = int(value)
+    except ValueError as exc:
+        raise argparse.ArgumentTypeError("must be an integer") from exc
+    if parsed <= 0:
+        raise argparse.ArgumentTypeError("must be greater than 0")
+    return parsed
+
+
+def bounded_count(value: str) -> int:
+    parsed = positive_int(value)
+    if parsed > 50:
+        raise argparse.ArgumentTypeError("must be <= 50")
+    return parsed
+
+
+def print_result(command: str, status: str, **fields: object) -> None:
+    parts = [f"admin:{command}", f"status={status}"]
+    parts.extend([f"{key}={value}" for key, value in fields.items()])
+    print(" ".join(parts))
+
+
+def require_confirm(args: argparse.Namespace, action: str) -> bool:
+    if getattr(args, "confirm", False):
+        return True
+    print_result(
+        action,
+        "blocked",
+        reason="missing-confirm",
+        hint="rerun with --confirm",
+    )
+    return False
+
+
+def build_contextual_query(headline: str, summary: str | None) -> str:
+    headline_query = extract_image_keywords(headline)
+    summary_query = extract_image_keywords(summary or "")
+
+    mood_terms: list[str] = []
+    text = f"{headline} {summary or ''}".lower()
+    if any(word in text for word in ("breakthrough", "launch", "record", "surge", "growth")):
+        mood_terms.extend(["innovation", "future"])
+    if any(word in text for word in ("risk", "lawsuit", "ban", "decline", "drop", "crash")):
+        mood_terms.extend(["serious", "technology"])
+
+    combined = " ".join([headline_query, summary_query, " ".join(mood_terms)]).strip()
+    cleaned = re.sub(r"\s+", " ", combined).strip()
+    if not cleaned:
+        return "ai machine learning deep learning"
+    return cleaned
+
+
+async def refetch_images_for_latest(
+    limit: int,
+    max_attempts: int,
+    dry_run: bool,
+) -> tuple[int, int]:
+    db = SessionLocal()
+    processed = 0
+    refreshed = 0
+
+    try:
+        items = (
+            db.query(NewsItem)
+            .filter(NewsItem.archived.is_(False))
+            .order_by(desc(NewsItem.published_at))
+            .limit(limit)
+            .all()
+        )
+
+        total = len(items)
+        for idx, item in enumerate(items, start=1):
+            processed += 1
+            query = build_contextual_query(item.headline, item.summary)
+
+            image_url: str | None = None
+            image_credit: str | None = None
+            local_image: str | None = None
+
+            for attempt in range(max_attempts):
+                try:
+                    image_url, image_credit = await fetch_royalty_free_image(query)
+                    if not image_url:
+                        raise RuntimeError("no-image-url")
+                    local_image = await download_and_optimize_image(image_url)
+                    if not local_image:
+                        raise RuntimeError("image-download-or-optimize-failed")
+                    break
+                except Exception:
+                    if attempt == max_attempts - 1:
+                        logger.exception("Image refetch failed for item=%s after retries", item.id)
+                        image_url = None
+                        local_image = None
+                        break
+                    delay = 2**attempt
+                    logger.warning(
+                        "Refetch retry item=%s attempt=%d delay=%ds",
+                        item.id,
+                        attempt + 1,
+                        delay,
+                    )
+                    await asyncio.sleep(delay)
+
+            if local_image:
+                refreshed += 1
+                if not dry_run:
+                    item.summary_image_url = local_image
+                    item.summary_image_credit = image_credit or item.summary_image_credit
+                    db.commit()
+
+            print_result(
+                "refetch-images",
+                "progress",
+                current=idx,
+                total=total,
+                refreshed=refreshed,
+                article_id=item.id,
+            )
+
+        return processed, refreshed
+    finally:
+        db.close()
+
+
 def build_parser() -> argparse.ArgumentParser:
     parser = argparse.ArgumentParser(prog="clawfort", description="ClawFort operations CLI")
     subparsers = parser.add_subparsers(dest="command", required=True)
@@ -27,6 +170,64 @@ def build_parser() -> argparse.ArgumentParser:
     )
     force_fetch_parser.set_defaults(handler=handle_force_fetch)
 
+    admin_parser = subparsers.add_parser(
+        "admin",
+        help="Administrative maintenance commands",
+        description="Run admin maintenance and recovery operations.",
+    )
+    admin_subparsers = admin_parser.add_subparsers(dest="admin_command", required=True)
+
+    fetch_parser = admin_subparsers.add_parser("fetch", help="Fetch n number of articles")
+    fetch_parser.add_argument("--count", type=bounded_count, default=5)
+    fetch_parser.set_defaults(handler=handle_admin_fetch)
+
+    refetch_parser = admin_subparsers.add_parser(
+        "refetch-images",
+        help="Refetch and optimize latest article images",
+    )
+    refetch_parser.add_argument("--limit", type=positive_int, default=30)
+    refetch_parser.add_argument("--max-attempts", type=positive_int, default=4)
+    refetch_parser.add_argument("--dry-run", action="store_true")
+    refetch_parser.set_defaults(handler=handle_admin_refetch_images)
+
+    clean_archive_parser = admin_subparsers.add_parser(
+        "clean-archive",
+        help="Delete archived items older than retention window",
+    )
+    clean_archive_parser.add_argument("--days", type=positive_int, default=60)
+    clean_archive_parser.add_argument("--confirm", action="store_true")
+    clean_archive_parser.add_argument("--dry-run", action="store_true")
+    clean_archive_parser.set_defaults(handler=handle_admin_clean_archive)
+
+    clear_cache_parser = admin_subparsers.add_parser(
+        "clear-cache", help="Clear optimized image cache"
+    )
+    clear_cache_parser.add_argument("--confirm", action="store_true")
+    clear_cache_parser.add_argument("--dry-run", action="store_true")
+    clear_cache_parser.set_defaults(handler=handle_admin_clear_cache)
+
+    clear_news_parser = admin_subparsers.add_parser("clear-news", help="Clear existing news items")
+    clear_news_parser.add_argument("--include-archived", action="store_true")
+    clear_news_parser.add_argument("--confirm", action="store_true")
+    clear_news_parser.add_argument("--dry-run", action="store_true")
+    clear_news_parser.set_defaults(handler=handle_admin_clear_news)
+
+    rebuild_parser = admin_subparsers.add_parser(
+        "rebuild-site", help="Clear and rebuild site content"
+    )
+    rebuild_parser.add_argument("--count", type=bounded_count, default=5)
+    rebuild_parser.add_argument("--confirm", action="store_true")
+    rebuild_parser.add_argument("--dry-run", action="store_true")
+    rebuild_parser.set_defaults(handler=handle_admin_rebuild_site)
+
+    regen_parser = admin_subparsers.add_parser(
+        "regenerate-translations",
+        help="Regenerate translations for existing articles",
+    )
+    regen_parser.add_argument("--limit", type=positive_int, default=0)
+    regen_parser.add_argument("--dry-run", action="store_true")
+    regen_parser.set_defaults(handler=handle_admin_regenerate_translations)
+
     return parser
 
 
@@ -60,6 +261,221 @@ def handle_force_fetch(_: argparse.Namespace) -> int:
         return 1
 
 
+def handle_admin_fetch(args: argparse.Namespace) -> int:
+    start = time.monotonic()
+    try:
+        validate_runtime()
+        init_db()
+        stored = asyncio.run(process_and_store_news(article_count=args.count))
+        elapsed = time.monotonic() - start
+        print_result("fetch", "ok", requested=args.count, stored=stored, elapsed=f"{elapsed:.1f}s")
+        return 0
+    except Exception:
+        logger.exception("admin fetch failed")
+        print_result("fetch", "error")
+        return 1
+
+
+def handle_admin_refetch_images(args: argparse.Namespace) -> int:
+    start = time.monotonic()
+    try:
+        init_db()
+        processed, refreshed = asyncio.run(
+            refetch_images_for_latest(
+                limit=min(args.limit, 30),
+                max_attempts=args.max_attempts,
+                dry_run=args.dry_run,
+            )
+        )
+        elapsed = time.monotonic() - start
+        print_result(
+            "refetch-images",
+            "ok",
+            processed=processed,
+            refreshed=refreshed,
+            dry_run=args.dry_run,
+            elapsed=f"{elapsed:.1f}s",
+        )
+        return 0
+    except Exception:
+        logger.exception("admin refetch-images failed")
+        print_result("refetch-images", "error")
+        return 1
+
+
+def handle_admin_clean_archive(args: argparse.Namespace) -> int:
+    if not require_confirm(args, "clean-archive"):
+        return 2
+
+    db = SessionLocal()
+    try:
+        cutoff = datetime.datetime.utcnow() - datetime.timedelta(days=args.days)
+        query = db.query(NewsItem).filter(
+            and_(NewsItem.archived.is_(True), NewsItem.created_at < cutoff)
+        )
+        count = query.count()
+        if args.dry_run:
+            print_result("clean-archive", "ok", dry_run=True, would_delete=count)
+            return 0
+        deleted = delete_archived_news(db, days_after_archive=args.days)
+        print_result("clean-archive", "ok", deleted=deleted)
+        return 0
+    except Exception:
+        logger.exception("admin clean-archive failed")
+        print_result("clean-archive", "error")
+        return 1
+    finally:
+        db.close()
+
+
+def handle_admin_clear_cache(args: argparse.Namespace) -> int:
+    if not require_confirm(args, "clear-cache"):
+        return 2
+
+    try:
+        os.makedirs(config.STATIC_IMAGES_DIR, exist_ok=True)
+        files = [
+            os.path.join(config.STATIC_IMAGES_DIR, name)
+            for name in os.listdir(config.STATIC_IMAGES_DIR)
+            if name.lower().endswith((".jpg", ".jpeg", ".png", ".webp"))
+        ]
+        if args.dry_run:
+            print_result("clear-cache", "ok", dry_run=True, would_delete=len(files))
+            return 0
+        deleted = 0
+        for file_path in files:
+            try:
+                os.remove(file_path)
+                deleted += 1
+            except OSError:
+                logger.warning("Failed to remove cache file: %s", file_path)
+        print_result("clear-cache", "ok", deleted=deleted)
+        return 0
+    except Exception:
+        logger.exception("admin clear-cache failed")
+        print_result("clear-cache", "error")
+        return 1
+
+
+def handle_admin_clear_news(args: argparse.Namespace) -> int:
+    if not require_confirm(args, "clear-news"):
+        return 2
+
+    db = SessionLocal()
+    try:
+        query = db.query(NewsItem)
+        if not args.include_archived:
+            query = query.filter(NewsItem.archived.is_(False))
+        items = query.all()
+        if args.dry_run:
+            print_result("clear-news", "ok", dry_run=True, would_delete=len(items))
+            return 0
+        deleted = 0
+        for item in items:
+            db.delete(item)
+            deleted += 1
+        db.commit()
+        print_result("clear-news", "ok", deleted=deleted)
+        return 0
+    except Exception:
+        db.rollback()
+        logger.exception("admin clear-news failed")
+        print_result("clear-news", "error")
+        return 1
+    finally:
+        db.close()
+
+
+def handle_admin_rebuild_site(args: argparse.Namespace) -> int:
+    if not require_confirm(args, "rebuild-site"):
+        return 2
+    if args.dry_run:
+        print_result("rebuild-site", "ok", dry_run=True, steps="clear-news,fetch")
+        return 0
+
+    clear_result = handle_admin_clear_news(
+        argparse.Namespace(include_archived=True, confirm=True, dry_run=False)
+    )
+    if clear_result != 0:
+        print_result("rebuild-site", "error", step="clear-news")
+        return clear_result
+
+    fetch_result = handle_admin_fetch(argparse.Namespace(count=args.count))
+    if fetch_result != 0:
+        print_result("rebuild-site", "error", step="fetch")
+        return fetch_result
+
+    print_result("rebuild-site", "ok", count=args.count)
+    return 0
+
+
+def handle_admin_regenerate_translations(args: argparse.Namespace) -> int:
+    db = SessionLocal()
+    try:
+        query = db.query(NewsItem).filter(NewsItem.archived.is_(False)).order_by(desc(NewsItem.id))
+        if args.limit and args.limit > 0:
+            query = query.limit(args.limit)
+        items = query.all()
+
+        regenerated = 0
+        for item in items:
+            tldr_points = resolve_tldr_points(item, None)
+            translations = asyncio.run(
+                generate_translations(
+                    headline=item.headline,
+                    summary=item.summary,
+                    tldr_points=tldr_points,
+                    summary_body=item.summary_body,
+                    source_citation=item.source_citation,
+                )
+            )
+            for language_code, payload in translations.items():
+                if args.dry_run:
+                    regenerated += 1
+                    continue
+                existing = get_translation(db, item.id, language_code)
+                if existing is None:
+                    create_translation(
+                        db=db,
+                        news_item_id=item.id,
+                        language=language_code,
+                        headline=payload["headline"],
+                        summary=payload["summary"],
+                        tldr_points=payload.get("tldr_points"),
+                        summary_body=payload.get("summary_body"),
+                        source_citation=payload.get("source_citation"),
+                    )
+                else:
+                    existing.headline = payload["headline"]
+                    existing.summary = payload["summary"]
+                    existing.tldr_points = (
+                        json.dumps(payload.get("tldr_points"))
+                        if payload.get("tldr_points")
+                        else None
+                    )
+                    existing.summary_body = payload.get("summary_body")
+                    existing.source_citation = payload.get("source_citation")
+                regenerated += 1
+            if not args.dry_run:
+                db.commit()
+
+        print_result(
+            "regenerate-translations",
+            "ok",
+            articles=len(items),
+            regenerated=regenerated,
+            dry_run=args.dry_run,
+        )
+        return 0
+    except Exception:
+        db.rollback()
+        logger.exception("admin regenerate-translations failed")
+        print_result("regenerate-translations", "error")
+        return 1
+    finally:
+        db.close()
+
+
 def main(argv: list[str] | None = None) -> int:
     parser = build_parser()
     args = parser.parse_args(argv)
diff --git a/backend/news_service.py b/backend/news_service.py
index dbe00e6..64bdd96 100644
--- a/backend/news_service.py
+++ b/backend/news_service.py
@@ -5,6 +5,7 @@ import logging
 import os
 import re
 import time
+from collections.abc import Awaitable, Callable
 from io import BytesIO
 from urllib.parse import quote_plus
 
@@ -23,6 +24,7 @@ from backend.repository import (
 logger = logging.getLogger(__name__)
 
 PLACEHOLDER_IMAGE_PATH = "/static/images/placeholder.png"
+GENERIC_AI_FALLBACK_URL = "https://placehold.co/1200x630/0f172a/e2e8f0/png?text=AI+News"
 
 
 async def call_perplexity_api(query: str) -> dict | None:
@@ -419,7 +421,7 @@ def extract_image_keywords(headline: str) -> str:
     - Handles edge cases (empty, only stop words, special characters)
     """
     if not headline or not headline.strip():
-        return "news technology"
+        return "ai machine learning deep learning"
 
     # Normalize: remove special characters, keep alphanumeric and spaces
     cleaned = re.sub(r"[^\w\s]", " ", headline)
@@ -433,7 +435,7 @@ def extract_image_keywords(headline: str) -> str:
     keywords = keywords[:5]
 
     if not keywords:
-        return "news technology"
+        return "ai machine learning deep learning"
 
     return " ".join(keywords)
 
@@ -465,7 +467,7 @@ async def fetch_pixabay_image(query: str) -> tuple[str | None, str | None]:
     except Exception:
         logger.exception("Pixabay image retrieval failed")
 
-    return None, None
+    return GENERIC_AI_FALLBACK_URL, "Generic AI fallback"
 
 
 async def fetch_unsplash_image(query: str) -> tuple[str | None, str | None]:
@@ -569,7 +571,9 @@ _PROVIDER_REGISTRY: dict[str, tuple] = {
 }
 
 
-def get_enabled_providers() -> list[tuple[str, callable]]:
+def get_enabled_providers() -> list[
+    tuple[str, Callable[[str], Awaitable[tuple[str | None, str | None]]]]
+]:
     """Get ordered list of enabled providers based on config and available API keys."""
     provider_names = [
         p.strip().lower() for p in config.ROYALTY_IMAGE_PROVIDERS.split(",") if p.strip()
@@ -663,8 +667,16 @@ async def download_and_optimize_image(image_url: str) -> str | None:
         return None
 
 
-async def fetch_news_with_retry(max_attempts: int = 3) -> list[dict]:
+async def fetch_news_with_retry(
+    max_attempts: int = 3, article_count: int | None = None
+) -> list[dict]:
     query = "What are the latest AI news from the last hour? Include source URLs and image URLs."
+    if article_count is not None:
+        bounded = max(1, min(50, int(article_count)))
+        query = (
+            f"What are the latest AI news from the last hour? Return exactly {bounded} items. "
+            "Include source URLs and image URLs."
+        )
 
     for attempt in range(max_attempts):
         try:
@@ -687,8 +699,8 @@ async def fetch_news_with_retry(max_attempts: int = 3) -> list[dict]:
     return []
 
 
-async def process_and_store_news() -> int:
-    items = await fetch_news_with_retry()
+async def process_and_store_news(article_count: int | None = None) -> int:
+    items = await fetch_news_with_retry(article_count=article_count)
     if not items:
         logger.warning("No news items fetched this cycle")
         return 0
diff --git a/backend/static/images/03d10966744a543b01f76d3f8f9f5a44.jpg b/backend/static/images/03d10966744a543b01f76d3f8f9f5a44.jpg
new file mode 100644
index 0000000..c1469ef
Binary files /dev/null and b/backend/static/images/03d10966744a543b01f76d3f8f9f5a44.jpg differ
diff --git a/backend/static/images/0f256078c66f1923de1fce7e0ac70ba0.jpg b/backend/static/images/0f256078c66f1923de1fce7e0ac70ba0.jpg
new file mode 100644
index 0000000..bef0715
Binary files /dev/null and b/backend/static/images/0f256078c66f1923de1fce7e0ac70ba0.jpg differ
diff --git a/backend/static/images/16237b1efa58b893b9458713ff8304ad.jpg b/backend/static/images/16237b1efa58b893b9458713ff8304ad.jpg
new file mode 100644
index 0000000..766f3b5
Binary files /dev/null and b/backend/static/images/16237b1efa58b893b9458713ff8304ad.jpg differ
diff --git a/backend/static/images/173c86c39207d39e5684d356369046ef.jpg b/backend/static/images/173c86c39207d39e5684d356369046ef.jpg
new file mode 100644
index 0000000..db3836f
Binary files /dev/null and b/backend/static/images/173c86c39207d39e5684d356369046ef.jpg differ
diff --git a/backend/static/images/1f35b940c79df0d9cd07650a5d439dac.jpg b/backend/static/images/1f35b940c79df0d9cd07650a5d439dac.jpg
new file mode 100644
index 0000000..793c0d7
Binary files /dev/null and b/backend/static/images/1f35b940c79df0d9cd07650a5d439dac.jpg differ
diff --git a/backend/static/images/1fd212a8fb8dfdcb72be46aaf8c27c80.jpg b/backend/static/images/1fd212a8fb8dfdcb72be46aaf8c27c80.jpg
new file mode 100644
index 0000000..939f8d2
Binary files /dev/null and b/backend/static/images/1fd212a8fb8dfdcb72be46aaf8c27c80.jpg differ
diff --git a/backend/static/images/2fbeef6191605d8a528ee5a0d7333d20.jpg b/backend/static/images/2fbeef6191605d8a528ee5a0d7333d20.jpg
new file mode 100644
index 0000000..ea8588e
Binary files /dev/null and b/backend/static/images/2fbeef6191605d8a528ee5a0d7333d20.jpg differ
diff --git a/backend/static/images/3c406d580431ebfa2ec850741540632a.jpg b/backend/static/images/3c406d580431ebfa2ec850741540632a.jpg
new file mode 100644
index 0000000..3657a32
Binary files /dev/null and b/backend/static/images/3c406d580431ebfa2ec850741540632a.jpg differ
diff --git a/backend/static/images/453bc7a5351756e01b681f6be72eddf5.jpg b/backend/static/images/453bc7a5351756e01b681f6be72eddf5.jpg
new file mode 100644
index 0000000..7b4aa5f
Binary files /dev/null and b/backend/static/images/453bc7a5351756e01b681f6be72eddf5.jpg differ
diff --git a/backend/static/images/4d69537bcdf5bee088ba2ad5371bb14d.jpg b/backend/static/images/4d69537bcdf5bee088ba2ad5371bb14d.jpg
new file mode 100644
index 0000000..d970ab2
Binary files /dev/null and b/backend/static/images/4d69537bcdf5bee088ba2ad5371bb14d.jpg differ
diff --git a/backend/static/images/593ebfe0d9f505d189822895e2eedeae.jpg b/backend/static/images/593ebfe0d9f505d189822895e2eedeae.jpg
new file mode 100644
index 0000000..b3f1b6f
Binary files /dev/null and b/backend/static/images/593ebfe0d9f505d189822895e2eedeae.jpg differ
diff --git a/backend/static/images/636a9ea318f9c6d8e81682a4e934480a.jpg b/backend/static/images/636a9ea318f9c6d8e81682a4e934480a.jpg
new file mode 100644
index 0000000..01c7a25
Binary files /dev/null and b/backend/static/images/636a9ea318f9c6d8e81682a4e934480a.jpg differ
diff --git a/backend/static/images/6c9fee8a62ae79475312057f16fb8af0.jpg b/backend/static/images/6c9fee8a62ae79475312057f16fb8af0.jpg
new file mode 100644
index 0000000..b0499ec
Binary files /dev/null and b/backend/static/images/6c9fee8a62ae79475312057f16fb8af0.jpg differ
diff --git a/backend/static/images/7ce1961a9a6d87e0af2a54840e7902a2.jpg b/backend/static/images/7ce1961a9a6d87e0af2a54840e7902a2.jpg
new file mode 100644
index 0000000..c30d951
Binary files /dev/null and b/backend/static/images/7ce1961a9a6d87e0af2a54840e7902a2.jpg differ
diff --git a/backend/static/images/808150f6bed9baf3a20bb4fc61cc6f4c.jpg b/backend/static/images/808150f6bed9baf3a20bb4fc61cc6f4c.jpg
new file mode 100644
index 0000000..2a05ee2
Binary files /dev/null and b/backend/static/images/808150f6bed9baf3a20bb4fc61cc6f4c.jpg differ
diff --git a/backend/static/images/8298d980d5a6fee90d308d170c57549d.jpg b/backend/static/images/8298d980d5a6fee90d308d170c57549d.jpg
new file mode 100644
index 0000000..947271d
Binary files /dev/null and b/backend/static/images/8298d980d5a6fee90d308d170c57549d.jpg differ
diff --git a/backend/static/images/93c252929772709cbd517afce3ceac95.jpg b/backend/static/images/93c252929772709cbd517afce3ceac95.jpg
new file mode 100644
index 0000000..5561d11
Binary files /dev/null and b/backend/static/images/93c252929772709cbd517afce3ceac95.jpg differ
diff --git a/backend/static/images/a3b7c96431c59fb77a87d0a26d9b53b2.jpg b/backend/static/images/a3b7c96431c59fb77a87d0a26d9b53b2.jpg
new file mode 100644
index 0000000..67a953b
Binary files /dev/null and b/backend/static/images/a3b7c96431c59fb77a87d0a26d9b53b2.jpg differ
diff --git a/backend/static/images/a9cd2b37ca1969434e65fb9bed294b74.jpg b/backend/static/images/a9cd2b37ca1969434e65fb9bed294b74.jpg
new file mode 100644
index 0000000..9d5f02d
Binary files /dev/null and b/backend/static/images/a9cd2b37ca1969434e65fb9bed294b74.jpg differ
diff --git a/backend/static/images/b16ae02672911e2bdf655cbf96b9a2f7.jpg b/backend/static/images/b16ae02672911e2bdf655cbf96b9a2f7.jpg
new file mode 100644
index 0000000..60759f3
Binary files /dev/null and b/backend/static/images/b16ae02672911e2bdf655cbf96b9a2f7.jpg differ
diff --git a/backend/static/images/b3edebaad82cdbf32de85d8cc5f274ad.jpg b/backend/static/images/b3edebaad82cdbf32de85d8cc5f274ad.jpg
new file mode 100644
index 0000000..fbfd0ee
Binary files /dev/null and b/backend/static/images/b3edebaad82cdbf32de85d8cc5f274ad.jpg differ
diff --git a/backend/static/images/bdd724aff1b83c6381da2d364b729326.jpg b/backend/static/images/bdd724aff1b83c6381da2d364b729326.jpg
new file mode 100644
index 0000000..7b03547
Binary files /dev/null and b/backend/static/images/bdd724aff1b83c6381da2d364b729326.jpg differ
diff --git a/backend/static/images/c638156b3201d2debc5ba5955fa54aa2.jpg b/backend/static/images/c638156b3201d2debc5ba5955fa54aa2.jpg
new file mode 100644
index 0000000..28b2572
Binary files /dev/null and b/backend/static/images/c638156b3201d2debc5ba5955fa54aa2.jpg differ
diff --git a/backend/static/images/d8e11fc6776d40a9389afe578313071b.jpg b/backend/static/images/d8e11fc6776d40a9389afe578313071b.jpg
new file mode 100644
index 0000000..6d351d8
Binary files /dev/null and b/backend/static/images/d8e11fc6776d40a9389afe578313071b.jpg differ
diff --git a/backend/static/images/e9f56690cf067da751ce58f2f59f4627.jpg b/backend/static/images/e9f56690cf067da751ce58f2f59f4627.jpg
new file mode 100644
index 0000000..fadc48d
Binary files /dev/null and b/backend/static/images/e9f56690cf067da751ce58f2f59f4627.jpg differ
diff --git a/backend/static/images/e9fd9f16cc882f7d112cc174a2efefc7.jpg b/backend/static/images/e9fd9f16cc882f7d112cc174a2efefc7.jpg
new file mode 100644
index 0000000..7a4c050
Binary files /dev/null and b/backend/static/images/e9fd9f16cc882f7d112cc174a2efefc7.jpg differ
diff --git a/data/clawfort.db b/data/clawfort.db
index 12d0ded..576e688 100644
Binary files a/data/clawfort.db and b/data/clawfort.db differ
diff --git a/frontend/index.html b/frontend/index.html
index 6140d76..ff3c0ae 100644
--- a/frontend/index.html
+++ b/frontend/index.html
@@ -126,11 +126,28 @@
         }
         .theme-menu-item:hover { background: rgba(92, 124, 250, 0.15); }
         .hero-overlay {
-            background: linear-gradient(to top, rgba(15, 23, 42, 0.92), rgba(15, 23, 42, 0.45), transparent);
+            background: linear-gradient(to top, rgba(2, 6, 23, 0.94), rgba(15, 23, 42, 0.62), rgba(15, 23, 42, 0.22), transparent);
         }
         .hero-title { color: #e2e8f0; text-shadow: 0 2px 8px rgba(0, 0, 0, 0.55); }
         .hero-summary { color: #cbd5e1; text-shadow: 0 1px 6px rgba(0, 0, 0, 0.55); }
-        .hero-meta { color: #cbd5e1; }
+        .hero-meta { color: #e2e8f0; text-shadow: 0 1px 6px rgba(0, 0, 0, 0.55); }
+        .hero-latest-pill {
+            background: rgba(59, 130, 246, 0.2);
+            color: #dbeafe;
+            border: 1px solid rgba(147, 197, 253, 0.45);
+        }
+        .hero-time-pill {
+            background: rgba(15, 23, 42, 0.55);
+            color: #e2e8f0;
+            border: 1px solid rgba(148, 163, 184, 0.35);
+            padding: 3px 8px;
+            border-radius: 9999px;
+        }
+        .tldr-shimmer {
+            height: 12px;
+            width: 85%;
+            border-radius: 9999px;
+        }
         .news-card-title { color: var(--cf-text-strong); }
         .news-card-summary { color: var(--cf-text-muted); }
         .news-card-meta { color: var(--cf-text-muted); }
@@ -157,7 +174,17 @@
             color: #f8fafc;
         }
         html[data-theme='light'] .hero-overlay {
-            background: linear-gradient(to top, rgba(15, 23, 42, 0.9), rgba(15, 23, 42, 0.35), transparent);
+            background: linear-gradient(to top, rgba(15, 23, 42, 0.92), rgba(30, 41, 59, 0.58), rgba(30, 41, 59, 0.2), transparent);
+        }
+        html[data-theme='light'] .hero-latest-pill {
+            background: rgba(37, 99, 235, 0.24);
+            border-color: rgba(37, 99, 235, 0.55);
+            color: #eff6ff;
+        }
+        html[data-theme='light'] .hero-time-pill {
+            background: rgba(15, 23, 42, 0.52);
+            border-color: rgba(226, 232, 240, 0.35);
+            color: #f8fafc;
         }
         html[data-theme='light'] .news-card-btn { color: #1e3a8a; }
         html[data-theme='light'] .modal-cta {
@@ -257,15 +284,15 @@
                         <div class="absolute inset-0 hero-overlay"></div>
                         <div class="absolute bottom-0 left-0 right-0 p-6 sm:p-10">
                             <div class="flex items-center gap-3 mb-3">
-                                <span class="px-2.5 py-1 bg-cf-500/20 text-cf-400 text-xs font-semibold rounded-full border border-cf-500/30">LATEST</span>
-                                <span class="text-gray-400 text-sm" x-text="timeAgo(item.published_at)"></span>
+                                <span class="px-2.5 py-1 text-xs font-semibold rounded-full hero-latest-pill">LATEST</span>
+                                <span class="text-sm hero-time-pill" x-text="timeAgo(item.published_at)"></span>
                             </div>
                             <h1 class="text-2xl sm:text-3xl lg:text-4xl font-extrabold leading-tight mb-3 max-w-4xl hero-title" x-text="item.headline"></h1>
                             <p class="text-base sm:text-lg max-w-3xl line-clamp-3 mb-4 hero-summary" x-text="item.summary"></p>
                             <div class="flex flex-wrap items-center gap-4 text-sm hero-meta">
                                 <button class="px-3 py-1.5 rounded-md bg-cf-500/20 text-cf-300 hover:bg-cf-500/30 transition-colors"
-                                        @click="trackEvent('hero-cta-click', { article_id: item.id }); window.open(item.source_url || '#', '_blank')">
-                                    Read Full Article
+                                        @click="trackEvent('hero-cta-click', { article_id: item.id }); window.dispatchEvent(new CustomEvent('open-summary', { detail: item }))">
+                                    Read TL;DR
                                 </button>
                                 <a :href="item.source_url" target="_blank" rel="noopener"
                                    class="hover:text-cf-400 transition-colors"
@@ -350,7 +377,7 @@
 
         <div x-show="modalOpen" x-cloak class="fixed inset-0 z-50 flex items-center justify-center" @keydown.escape.window="closeSummary()">
             <div class="absolute inset-0 bg-black/70" @click="closeSummary()"></div>
-            <div role="dialog" aria-modal="true" aria-label="Article summary" class="relative w-full max-w-2xl mx-4 max-h-[90vh] overflow-auto rounded-xl border border-white/10 bg-[#0f172a]">
+            <div role="dialog" aria-modal="true" aria-label="Article summary" class="relative w-full sm:w-[92vw] lg:w-[70vw] xl:w-[60vw] 2xl:w-[50vw] max-w-[1200px] mx-4 max-h-[96vh] overflow-auto rounded-xl border border-white/10 bg-[#0f172a]">
                 <div class="p-6 space-y-5 cf-modal" x-show="modalItem">
                     <div class="flex justify-end">
                         <button @click="closeSummary()" aria-label="Close summary modal" class="transition-colors modal-close-btn">Close</button>
@@ -370,7 +397,11 @@
 
                     <div>
                         <h3 class="text-sm uppercase tracking-wide font-semibold mb-2 modal-section-title">TL;DR</h3>
-                        <ul class="list-disc pl-5 space-y-1 text-sm modal-body-text" x-show="modalItem?.tldr_points && modalItem.tldr_points.length > 0">
+                        <div x-show="modalTldrLoading" class="space-y-2" aria-hidden="true">
+                            <div class="skeleton tldr-shimmer"></div>
+                            <div class="skeleton tldr-shimmer w-[70%]"></div>
+                        </div>
+                        <ul class="list-disc pl-5 space-y-1 text-sm modal-body-text" x-show="!modalTldrLoading && modalItem?.tldr_points && modalItem.tldr_points.length > 0">
                             <template x-for="(point, idx) in (modalItem?.tldr_points || [])" :key="idx">
                                 <li x-text="point"></li>
                             </template>
@@ -797,6 +828,7 @@ function newsFeed() {
         modalOpen: false,
         modalItem: null,
         modalImageLoading: true,
+        modalTldrLoading: true,
         imageLoaded: {},
 
         async init() {
@@ -815,6 +847,11 @@ function newsFeed() {
                 await this.loadMore();
                 this.initialLoading = false;
             });
+
+            window.addEventListener('open-summary', (event) => {
+                if (!event?.detail) return;
+                this.openSummary(event.detail);
+            });
         },
 
         waitForHero() {
@@ -886,6 +923,10 @@ function newsFeed() {
             this.modalItem = item;
             this.modalOpen = true;
             this.modalImageLoading = true;
+            this.modalTldrLoading = true;
+            setTimeout(() => {
+                if (this.modalOpen) this.modalTldrLoading = false;
+            }, 250);
             trackEvent('summary-modal-open', { article_id: item.id });
         },
 
@@ -893,6 +934,7 @@ function newsFeed() {
             const id = this.modalItem ? this.modalItem.id : null;
             this.modalOpen = false;
             this.modalItem = null;
+            this.modalTldrLoading = true;
             trackEvent('summary-modal-close', { article_id: id });
         },
 
diff --git a/openspec/changes/p01-robust-onepager/.openspec.yaml b/openspec/changes/archive/2026-02-13-p01-robust-onepager/.openspec.yaml
similarity index 100%
rename from openspec/changes/p01-robust-onepager/.openspec.yaml
rename to openspec/changes/archive/2026-02-13-p01-robust-onepager/.openspec.yaml
diff --git a/openspec/changes/p01-robust-onepager/design.md b/openspec/changes/archive/2026-02-13-p01-robust-onepager/design.md
similarity index 100%
rename from openspec/changes/p01-robust-onepager/design.md
rename to openspec/changes/archive/2026-02-13-p01-robust-onepager/design.md
diff --git a/openspec/changes/p01-robust-onepager/proposal.md b/openspec/changes/archive/2026-02-13-p01-robust-onepager/proposal.md
similarity index 100%
rename from openspec/changes/p01-robust-onepager/proposal.md
rename to openspec/changes/archive/2026-02-13-p01-robust-onepager/proposal.md
diff --git a/openspec/changes/p01-robust-onepager/specs/containerized-deployment/spec.md b/openspec/changes/archive/2026-02-13-p01-robust-onepager/specs/containerized-deployment/spec.md
similarity index 100%
rename from openspec/changes/p01-robust-onepager/specs/containerized-deployment/spec.md
rename to openspec/changes/archive/2026-02-13-p01-robust-onepager/specs/containerized-deployment/spec.md
diff --git a/openspec/changes/p01-robust-onepager/specs/hero-display/spec.md b/openspec/changes/archive/2026-02-13-p01-robust-onepager/specs/hero-display/spec.md
similarity index 100%
rename from openspec/changes/p01-robust-onepager/specs/hero-display/spec.md
rename to openspec/changes/archive/2026-02-13-p01-robust-onepager/specs/hero-display/spec.md
diff --git a/openspec/changes/p01-robust-onepager/specs/news-aggregator/spec.md b/openspec/changes/archive/2026-02-13-p01-robust-onepager/specs/news-aggregator/spec.md
similarity index 100%
rename from openspec/changes/p01-robust-onepager/specs/news-aggregator/spec.md
rename to openspec/changes/archive/2026-02-13-p01-robust-onepager/specs/news-aggregator/spec.md
diff --git a/openspec/changes/p01-robust-onepager/tasks.md b/openspec/changes/archive/2026-02-13-p01-robust-onepager/tasks.md
similarity index 100%
rename from openspec/changes/p01-robust-onepager/tasks.md
rename to openspec/changes/archive/2026-02-13-p01-robust-onepager/tasks.md
diff --git a/openspec/changes/p02-force-fetch-command/.openspec.yaml b/openspec/changes/archive/2026-02-13-p02-force-fetch-command/.openspec.yaml
similarity index 100%
rename from openspec/changes/p02-force-fetch-command/.openspec.yaml
rename to openspec/changes/archive/2026-02-13-p02-force-fetch-command/.openspec.yaml
diff --git a/openspec/changes/p02-force-fetch-command/design.md b/openspec/changes/archive/2026-02-13-p02-force-fetch-command/design.md
similarity index 100%
rename from openspec/changes/p02-force-fetch-command/design.md
rename to openspec/changes/archive/2026-02-13-p02-force-fetch-command/design.md
diff --git a/openspec/changes/p02-force-fetch-command/proposal.md b/openspec/changes/archive/2026-02-13-p02-force-fetch-command/proposal.md
similarity index 100%
rename from openspec/changes/p02-force-fetch-command/proposal.md
rename to openspec/changes/archive/2026-02-13-p02-force-fetch-command/proposal.md
diff --git a/openspec/changes/p02-force-fetch-command/specs/fetch-run-reporting/spec.md b/openspec/changes/archive/2026-02-13-p02-force-fetch-command/specs/fetch-run-reporting/spec.md
similarity index 100%
rename from openspec/changes/p02-force-fetch-command/specs/fetch-run-reporting/spec.md
rename to openspec/changes/archive/2026-02-13-p02-force-fetch-command/specs/fetch-run-reporting/spec.md
diff --git a/openspec/changes/p02-force-fetch-command/specs/force-fetch-command/spec.md b/openspec/changes/archive/2026-02-13-p02-force-fetch-command/specs/force-fetch-command/spec.md
similarity index 100%
rename from openspec/changes/p02-force-fetch-command/specs/force-fetch-command/spec.md
rename to openspec/changes/archive/2026-02-13-p02-force-fetch-command/specs/force-fetch-command/spec.md
diff --git a/openspec/changes/p02-force-fetch-command/specs/manual-fetch-recovery/spec.md b/openspec/changes/archive/2026-02-13-p02-force-fetch-command/specs/manual-fetch-recovery/spec.md
similarity index 100%
rename from openspec/changes/p02-force-fetch-command/specs/manual-fetch-recovery/spec.md
rename to openspec/changes/archive/2026-02-13-p02-force-fetch-command/specs/manual-fetch-recovery/spec.md
diff --git a/openspec/changes/p02-force-fetch-command/tasks.md b/openspec/changes/archive/2026-02-13-p02-force-fetch-command/tasks.md
similarity index 100%
rename from openspec/changes/p02-force-fetch-command/tasks.md
rename to openspec/changes/archive/2026-02-13-p02-force-fetch-command/tasks.md
diff --git a/openspec/changes/p03-languages-ml-tm/.openspec.yaml b/openspec/changes/archive/2026-02-13-p03-languages-ml-tm/.openspec.yaml
similarity index 100%
rename from openspec/changes/p03-languages-ml-tm/.openspec.yaml
rename to openspec/changes/archive/2026-02-13-p03-languages-ml-tm/.openspec.yaml
diff --git a/openspec/changes/p03-languages-ml-tm/design.md b/openspec/changes/archive/2026-02-13-p03-languages-ml-tm/design.md
similarity index 100%
rename from openspec/changes/p03-languages-ml-tm/design.md
rename to openspec/changes/archive/2026-02-13-p03-languages-ml-tm/design.md
diff --git a/openspec/changes/p03-languages-ml-tm/proposal.md b/openspec/changes/archive/2026-02-13-p03-languages-ml-tm/proposal.md
similarity index 100%
rename from openspec/changes/p03-languages-ml-tm/proposal.md
rename to openspec/changes/archive/2026-02-13-p03-languages-ml-tm/proposal.md
diff --git a/openspec/changes/p03-languages-ml-tm/specs/article-translations-ml-tm/spec.md b/openspec/changes/archive/2026-02-13-p03-languages-ml-tm/specs/article-translations-ml-tm/spec.md
similarity index 100%
rename from openspec/changes/p03-languages-ml-tm/specs/article-translations-ml-tm/spec.md
rename to openspec/changes/archive/2026-02-13-p03-languages-ml-tm/specs/article-translations-ml-tm/spec.md
diff --git a/openspec/changes/p03-languages-ml-tm/specs/language-aware-content-delivery/spec.md b/openspec/changes/archive/2026-02-13-p03-languages-ml-tm/specs/language-aware-content-delivery/spec.md
similarity index 100%
rename from openspec/changes/p03-languages-ml-tm/specs/language-aware-content-delivery/spec.md
rename to openspec/changes/archive/2026-02-13-p03-languages-ml-tm/specs/language-aware-content-delivery/spec.md
diff --git a/openspec/changes/p03-languages-ml-tm/specs/language-preference-persistence/spec.md b/openspec/changes/archive/2026-02-13-p03-languages-ml-tm/specs/language-preference-persistence/spec.md
similarity index 100%
rename from openspec/changes/p03-languages-ml-tm/specs/language-preference-persistence/spec.md
rename to openspec/changes/archive/2026-02-13-p03-languages-ml-tm/specs/language-preference-persistence/spec.md
diff --git a/openspec/changes/p03-languages-ml-tm/tasks.md b/openspec/changes/archive/2026-02-13-p03-languages-ml-tm/tasks.md
similarity index 100%
rename from openspec/changes/p03-languages-ml-tm/tasks.md
rename to openspec/changes/archive/2026-02-13-p03-languages-ml-tm/tasks.md
diff --git a/openspec/changes/p04-summary/.openspec.yaml b/openspec/changes/archive/2026-02-13-p04-summary/.openspec.yaml
similarity index 100%
rename from openspec/changes/p04-summary/.openspec.yaml
rename to openspec/changes/archive/2026-02-13-p04-summary/.openspec.yaml
diff --git a/openspec/changes/p04-summary/design.md b/openspec/changes/archive/2026-02-13-p04-summary/design.md
similarity index 100%
rename from openspec/changes/p04-summary/design.md
rename to openspec/changes/archive/2026-02-13-p04-summary/design.md
diff --git a/openspec/changes/p04-summary/proposal.md b/openspec/changes/archive/2026-02-13-p04-summary/proposal.md
similarity index 100%
rename from openspec/changes/p04-summary/proposal.md
rename to openspec/changes/archive/2026-02-13-p04-summary/proposal.md
diff --git a/openspec/changes/p04-summary/specs/article-tldr-summary/spec.md b/openspec/changes/archive/2026-02-13-p04-summary/specs/article-tldr-summary/spec.md
similarity index 100%
rename from openspec/changes/p04-summary/specs/article-tldr-summary/spec.md
rename to openspec/changes/archive/2026-02-13-p04-summary/specs/article-tldr-summary/spec.md
diff --git a/openspec/changes/p04-summary/specs/royalty-free-image-enrichment/spec.md b/openspec/changes/archive/2026-02-13-p04-summary/specs/royalty-free-image-enrichment/spec.md
similarity index 100%
rename from openspec/changes/p04-summary/specs/royalty-free-image-enrichment/spec.md
rename to openspec/changes/archive/2026-02-13-p04-summary/specs/royalty-free-image-enrichment/spec.md
diff --git a/openspec/changes/p04-summary/specs/summary-analytics-tagging/spec.md b/openspec/changes/archive/2026-02-13-p04-summary/specs/summary-analytics-tagging/spec.md
similarity index 100%
rename from openspec/changes/p04-summary/specs/summary-analytics-tagging/spec.md
rename to openspec/changes/archive/2026-02-13-p04-summary/specs/summary-analytics-tagging/spec.md
diff --git a/openspec/changes/p04-summary/specs/summary-modal-experience/spec.md b/openspec/changes/archive/2026-02-13-p04-summary/specs/summary-modal-experience/spec.md
similarity index 100%
rename from openspec/changes/p04-summary/specs/summary-modal-experience/spec.md
rename to openspec/changes/archive/2026-02-13-p04-summary/specs/summary-modal-experience/spec.md
diff --git a/openspec/changes/p04-summary/tasks.md b/openspec/changes/archive/2026-02-13-p04-summary/tasks.md
similarity index 100%
rename from openspec/changes/p04-summary/tasks.md
rename to openspec/changes/archive/2026-02-13-p04-summary/tasks.md
diff --git a/openspec/changes/p05-no-ownership/.openspec.yaml b/openspec/changes/archive/2026-02-13-p05-no-ownership/.openspec.yaml
similarity index 100%
rename from openspec/changes/p05-no-ownership/.openspec.yaml
rename to openspec/changes/archive/2026-02-13-p05-no-ownership/.openspec.yaml
diff --git a/openspec/changes/p05-no-ownership/design.md b/openspec/changes/archive/2026-02-13-p05-no-ownership/design.md
similarity index 100%
rename from openspec/changes/p05-no-ownership/design.md
rename to openspec/changes/archive/2026-02-13-p05-no-ownership/design.md
diff --git a/openspec/changes/p05-no-ownership/proposal.md b/openspec/changes/archive/2026-02-13-p05-no-ownership/proposal.md
similarity index 100%
rename from openspec/changes/p05-no-ownership/proposal.md
rename to openspec/changes/archive/2026-02-13-p05-no-ownership/proposal.md
diff --git a/openspec/changes/p05-no-ownership/specs/attribution-disclaimer-page/spec.md b/openspec/changes/archive/2026-02-13-p05-no-ownership/specs/attribution-disclaimer-page/spec.md
similarity index 100%
rename from openspec/changes/p05-no-ownership/specs/attribution-disclaimer-page/spec.md
rename to openspec/changes/archive/2026-02-13-p05-no-ownership/specs/attribution-disclaimer-page/spec.md
diff --git a/openspec/changes/p05-no-ownership/specs/footer-policy-links/spec.md b/openspec/changes/archive/2026-02-13-p05-no-ownership/specs/footer-policy-links/spec.md
similarity index 100%
rename from openspec/changes/p05-no-ownership/specs/footer-policy-links/spec.md
rename to openspec/changes/archive/2026-02-13-p05-no-ownership/specs/footer-policy-links/spec.md
diff --git a/openspec/changes/p05-no-ownership/specs/terms-of-use-risk-disclosure/spec.md b/openspec/changes/archive/2026-02-13-p05-no-ownership/specs/terms-of-use-risk-disclosure/spec.md
similarity index 100%
rename from openspec/changes/p05-no-ownership/specs/terms-of-use-risk-disclosure/spec.md
rename to openspec/changes/archive/2026-02-13-p05-no-ownership/specs/terms-of-use-risk-disclosure/spec.md
diff --git a/openspec/changes/p05-no-ownership/tasks.md b/openspec/changes/archive/2026-02-13-p05-no-ownership/tasks.md
similarity index 100%
rename from openspec/changes/p05-no-ownership/tasks.md
rename to openspec/changes/archive/2026-02-13-p05-no-ownership/tasks.md
diff --git a/openspec/changes/p06-theming/.openspec.yaml b/openspec/changes/archive/2026-02-13-p06-theming/.openspec.yaml
similarity index 100%
rename from openspec/changes/p06-theming/.openspec.yaml
rename to openspec/changes/archive/2026-02-13-p06-theming/.openspec.yaml
diff --git a/openspec/changes/p06-theming/design.md b/openspec/changes/archive/2026-02-13-p06-theming/design.md
similarity index 100%
rename from openspec/changes/p06-theming/design.md
rename to openspec/changes/archive/2026-02-13-p06-theming/design.md
diff --git a/openspec/changes/p06-theming/proposal.md b/openspec/changes/archive/2026-02-13-p06-theming/proposal.md
similarity index 100%
rename from openspec/changes/p06-theming/proposal.md
rename to openspec/changes/archive/2026-02-13-p06-theming/proposal.md
diff --git a/openspec/changes/p06-theming/specs/theme-default-system/spec.md b/openspec/changes/archive/2026-02-13-p06-theming/specs/theme-default-system/spec.md
similarity index 100%
rename from openspec/changes/p06-theming/specs/theme-default-system/spec.md
rename to openspec/changes/archive/2026-02-13-p06-theming/specs/theme-default-system/spec.md
diff --git a/openspec/changes/p06-theming/specs/theme-preference-persistence/spec.md b/openspec/changes/archive/2026-02-13-p06-theming/specs/theme-preference-persistence/spec.md
similarity index 100%
rename from openspec/changes/p06-theming/specs/theme-preference-persistence/spec.md
rename to openspec/changes/archive/2026-02-13-p06-theming/specs/theme-preference-persistence/spec.md
diff --git a/openspec/changes/p06-theming/specs/theme-switcher-control/spec.md b/openspec/changes/archive/2026-02-13-p06-theming/specs/theme-switcher-control/spec.md
similarity index 100%
rename from openspec/changes/p06-theming/specs/theme-switcher-control/spec.md
rename to openspec/changes/archive/2026-02-13-p06-theming/specs/theme-switcher-control/spec.md
diff --git a/openspec/changes/p06-theming/tasks.md b/openspec/changes/archive/2026-02-13-p06-theming/tasks.md
similarity index 100%
rename from openspec/changes/p06-theming/tasks.md
rename to openspec/changes/archive/2026-02-13-p06-theming/tasks.md
diff --git a/openspec/changes/p07-tech-robustness/.openspec.yaml b/openspec/changes/archive/2026-02-13-p07-tech-robustness/.openspec.yaml
similarity index 100%
rename from openspec/changes/p07-tech-robustness/.openspec.yaml
rename to openspec/changes/archive/2026-02-13-p07-tech-robustness/.openspec.yaml
diff --git a/openspec/changes/p07-tech-robustness/design.md b/openspec/changes/archive/2026-02-13-p07-tech-robustness/design.md
similarity index 100%
rename from openspec/changes/p07-tech-robustness/design.md
rename to openspec/changes/archive/2026-02-13-p07-tech-robustness/design.md
diff --git a/openspec/changes/p07-tech-robustness/proposal.md b/openspec/changes/archive/2026-02-13-p07-tech-robustness/proposal.md
similarity index 100%
rename from openspec/changes/p07-tech-robustness/proposal.md
rename to openspec/changes/archive/2026-02-13-p07-tech-robustness/proposal.md
diff --git a/openspec/changes/p07-tech-robustness/specs/cookie-consent-tracking-gate/spec.md b/openspec/changes/archive/2026-02-13-p07-tech-robustness/specs/cookie-consent-tracking-gate/spec.md
similarity index 100%
rename from openspec/changes/p07-tech-robustness/specs/cookie-consent-tracking-gate/spec.md
rename to openspec/changes/archive/2026-02-13-p07-tech-robustness/specs/cookie-consent-tracking-gate/spec.md
diff --git a/openspec/changes/p07-tech-robustness/specs/responsive-device-agnostic-layout/spec.md b/openspec/changes/archive/2026-02-13-p07-tech-robustness/specs/responsive-device-agnostic-layout/spec.md
similarity index 100%
rename from openspec/changes/p07-tech-robustness/specs/responsive-device-agnostic-layout/spec.md
rename to openspec/changes/archive/2026-02-13-p07-tech-robustness/specs/responsive-device-agnostic-layout/spec.md
diff --git a/openspec/changes/p07-tech-robustness/specs/wcag-2-2-aa-accessibility/spec.md b/openspec/changes/archive/2026-02-13-p07-tech-robustness/specs/wcag-2-2-aa-accessibility/spec.md
similarity index 100%
rename from openspec/changes/p07-tech-robustness/specs/wcag-2-2-aa-accessibility/spec.md
rename to openspec/changes/archive/2026-02-13-p07-tech-robustness/specs/wcag-2-2-aa-accessibility/spec.md
diff --git a/openspec/changes/p07-tech-robustness/tasks.md b/openspec/changes/archive/2026-02-13-p07-tech-robustness/tasks.md
similarity index 100%
rename from openspec/changes/p07-tech-robustness/tasks.md
rename to openspec/changes/archive/2026-02-13-p07-tech-robustness/tasks.md
diff --git a/openspec/changes/p08-seo-tweaks/.openspec.yaml b/openspec/changes/archive/2026-02-13-p08-seo-tweaks/.openspec.yaml
similarity index 100%
rename from openspec/changes/p08-seo-tweaks/.openspec.yaml
rename to openspec/changes/archive/2026-02-13-p08-seo-tweaks/.openspec.yaml
diff --git a/openspec/changes/p08-seo-tweaks/design.md b/openspec/changes/archive/2026-02-13-p08-seo-tweaks/design.md
similarity index 100%
rename from openspec/changes/p08-seo-tweaks/design.md
rename to openspec/changes/archive/2026-02-13-p08-seo-tweaks/design.md
diff --git a/openspec/changes/p08-seo-tweaks/proposal.md b/openspec/changes/archive/2026-02-13-p08-seo-tweaks/proposal.md
similarity index 100%
rename from openspec/changes/p08-seo-tweaks/proposal.md
rename to openspec/changes/archive/2026-02-13-p08-seo-tweaks/proposal.md
diff --git a/openspec/changes/p08-seo-tweaks/specs/delivery-and-rendering-performance/spec.md b/openspec/changes/archive/2026-02-13-p08-seo-tweaks/specs/delivery-and-rendering-performance/spec.md
similarity index 100%
rename from openspec/changes/p08-seo-tweaks/specs/delivery-and-rendering-performance/spec.md
rename to openspec/changes/archive/2026-02-13-p08-seo-tweaks/specs/delivery-and-rendering-performance/spec.md
diff --git a/openspec/changes/p08-seo-tweaks/specs/news-structured-data/spec.md b/openspec/changes/archive/2026-02-13-p08-seo-tweaks/specs/news-structured-data/spec.md
similarity index 100%
rename from openspec/changes/p08-seo-tweaks/specs/news-structured-data/spec.md
rename to openspec/changes/archive/2026-02-13-p08-seo-tweaks/specs/news-structured-data/spec.md
diff --git a/openspec/changes/p08-seo-tweaks/specs/seo-meta-and-social-tags/spec.md b/openspec/changes/archive/2026-02-13-p08-seo-tweaks/specs/seo-meta-and-social-tags/spec.md
similarity index 100%
rename from openspec/changes/p08-seo-tweaks/specs/seo-meta-and-social-tags/spec.md
rename to openspec/changes/archive/2026-02-13-p08-seo-tweaks/specs/seo-meta-and-social-tags/spec.md
diff --git a/openspec/changes/p08-seo-tweaks/tasks.md b/openspec/changes/archive/2026-02-13-p08-seo-tweaks/tasks.md
similarity index 100%
rename from openspec/changes/p08-seo-tweaks/tasks.md
rename to openspec/changes/archive/2026-02-13-p08-seo-tweaks/tasks.md
diff --git a/openspec/changes/p09-image-choices/.openspec.yaml b/openspec/changes/archive/2026-02-13-p09-image-choices/.openspec.yaml
similarity index 100%
rename from openspec/changes/p09-image-choices/.openspec.yaml
rename to openspec/changes/archive/2026-02-13-p09-image-choices/.openspec.yaml
diff --git a/openspec/changes/p09-image-choices/design.md b/openspec/changes/archive/2026-02-13-p09-image-choices/design.md
similarity index 100%
rename from openspec/changes/p09-image-choices/design.md
rename to openspec/changes/archive/2026-02-13-p09-image-choices/design.md
diff --git a/openspec/changes/p09-image-choices/proposal.md b/openspec/changes/archive/2026-02-13-p09-image-choices/proposal.md
similarity index 100%
rename from openspec/changes/p09-image-choices/proposal.md
rename to openspec/changes/archive/2026-02-13-p09-image-choices/proposal.md
diff --git a/openspec/changes/p09-image-choices/specs/image-provider-fallback-chain/spec.md b/openspec/changes/archive/2026-02-13-p09-image-choices/specs/image-provider-fallback-chain/spec.md
similarity index 100%
rename from openspec/changes/p09-image-choices/specs/image-provider-fallback-chain/spec.md
rename to openspec/changes/archive/2026-02-13-p09-image-choices/specs/image-provider-fallback-chain/spec.md
diff --git a/openspec/changes/p09-image-choices/specs/image-query-refinement/spec.md b/openspec/changes/archive/2026-02-13-p09-image-choices/specs/image-query-refinement/spec.md
similarity index 100%
rename from openspec/changes/p09-image-choices/specs/image-query-refinement/spec.md
rename to openspec/changes/archive/2026-02-13-p09-image-choices/specs/image-query-refinement/spec.md
diff --git a/openspec/changes/p09-image-choices/specs/mcp-image-provider-integration/spec.md b/openspec/changes/archive/2026-02-13-p09-image-choices/specs/mcp-image-provider-integration/spec.md
similarity index 100%
rename from openspec/changes/p09-image-choices/specs/mcp-image-provider-integration/spec.md
rename to openspec/changes/archive/2026-02-13-p09-image-choices/specs/mcp-image-provider-integration/spec.md
diff --git a/openspec/changes/p09-image-choices/tasks.md b/openspec/changes/archive/2026-02-13-p09-image-choices/tasks.md
similarity index 100%
rename from openspec/changes/p09-image-choices/tasks.md
rename to openspec/changes/archive/2026-02-13-p09-image-choices/tasks.md
diff --git a/openspec/changes/archive/2026-02-13-p10-ui-fixes/.openspec.yaml b/openspec/changes/archive/2026-02-13-p10-ui-fixes/.openspec.yaml
new file mode 100644
index 0000000..e99c55a
--- /dev/null
+++ b/openspec/changes/archive/2026-02-13-p10-ui-fixes/.openspec.yaml
@@ -0,0 +1,2 @@
+schema: spec-driven
+created: 2026-02-13
diff --git a/openspec/changes/archive/2026-02-13-p10-ui-fixes/design.md b/openspec/changes/archive/2026-02-13-p10-ui-fixes/design.md
new file mode 100644
index 0000000..6b6e7cc
--- /dev/null
+++ b/openspec/changes/archive/2026-02-13-p10-ui-fixes/design.md
@@ -0,0 +1,88 @@
+## Context
+
+`frontend/index.html` currently renders the hero CTA as an external redirect (`window.open(item.source_url)`), and modal sizing is constrained by `max-w-2xl` with `max-h-[90vh]`. TL;DR content does not expose a dedicated loading placeholder, and hero badges can lose readability over bright images. On the backend, `backend/news_service.py` already performs keyword extraction and provider fallback, but defaults remain too generic (`"news technology"`) and do not explicitly prioritize AI-topic fallback behavior.
+
+## Goals / Non-Goals
+
+**Goals:**
+- Keep users on-site by making the hero primary CTA open the existing TL;DR modal flow.
+- Ensure `LATEST` and relative timestamp remain legible over all hero images in light/dark themes.
+- Increase modal usable area (width and near-full-height scrolling behavior) without breaking mobile usability.
+- Add a small horizontal shimmer placeholder for TL;DR bullets while modal content initializes.
+- Improve image relevance with stronger AI-focused keyword fallback and deterministic generic AI-image fallback when lookup fails.
+
+**Non-Goals:**
+- Rebuilding the full feed card architecture.
+- Replacing existing provider integrations or adding new third-party image providers.
+- Introducing backend sentiment ML models.
+- Reworking scheduler or ingestion cadence.
+
+## Decisions
+
+### Decision: Reuse existing modal interaction path for hero CTA
+**Decision:** Wire hero CTA to the same `openSummary(item)` behavior used by feed cards.
+
+**Rationale:**
+- Reuses existing event tracking and modal rendering logic.
+- Avoids duplicate interaction models and reduces regression risk.
+
+**Alternatives considered:**
+- Add a second hero-only modal implementation: rejected due to duplicate UI state and maintenance cost.
+
+### Decision: Enforce readability with layered overlay + contrast-safe tokens
+**Decision:** Strengthen hero overlay and badge/text color tokens so metadata remains visible independent of image luminance.
+
+**Rationale:**
+- Solves visibility issues without image preprocessing.
+- Keeps responsive behavior in CSS instead of JS image analysis.
+
+**Alternatives considered:**
+- Dynamic luminance detection per image: rejected as unnecessary complexity for current scope.
+
+### Decision: Expand modal dimensions with responsive constraints
+**Decision:** Use a wider desktop container (minimum half viewport intent) while preserving mobile full-width behavior and near-full-height scrolling.
+
+**Rationale:**
+- Improves readability for summary blocks and TL;DR bullets.
+- Keeps accessibility of close controls and keyboard escape path.
+
+**Alternatives considered:**
+- Full-screen modal only: rejected due to excessive visual disruption on desktop.
+
+### Decision: Treat TL;DR loading as explicit skeleton state
+**Decision:** Add a low-height horizontal shimmer placeholder visible when TL;DR is not yet available.
+
+**Rationale:**
+- Reduces perceived latency ambiguity.
+- Matches existing skeleton design language already used for images/cards.
+
+### Decision: Improve fallback query semantics for AI-news image retrieval
+**Decision:** Enhance keyword fallback to AI-focused defaults (`ai machine learning deep learning`) and add explicit generic AI image fallback contract.
+
+**Rationale:**
+- Reduces irrelevant imagery when topic extraction is weak or providers return noisy results.
+- Keeps behavior deterministic and testable.
+
+## Risks / Trade-offs
+
+- **[Risk] Wider modal may crowd smaller laptops** -> Mitigation: use responsive width caps with mobile-first breakpoints and overflow handling.
+- **[Risk] Hero overlay could darken images too much** -> Mitigation: tune gradient opacity and preserve theme-specific token overrides.
+- **[Risk] Fallback image monotony if providers fail frequently** -> Mitigation: keep provider chain first; generic AI fallback only as terminal fallback.
+- **[Trade-off] Stronger AI default keywords may reduce non-AI niche relevance** -> Mitigation: apply defaults only when extracted keywords are insufficient.
+
+## Migration Plan
+
+1. Update hero CTA and hero readability styles in `frontend/index.html`.
+2. Update modal sizing and TL;DR shimmer loading state in `frontend/index.html`.
+3. Update backend keyword fallback and generic AI image fallback behavior in `backend/news_service.py`.
+4. Verify behavior manually on desktop/mobile and run relevant checks.
+
+Rollback:
+- Revert hero CTA to external link behavior.
+- Revert modal class and shimmer additions.
+- Revert keyword/default fallback updates in image pipeline.
+
+## Open Questions
+
+- Should generic AI fallback be local static asset only, or deterministic remote URL with local optimization?
+- Do we need separate fallback keyword sets per language now, or keep English-focused defaults in this change?
diff --git a/openspec/changes/archive/2026-02-13-p10-ui-fixes/proposal.md b/openspec/changes/archive/2026-02-13-p10-ui-fixes/proposal.md
new file mode 100644
index 0000000..00fbbd9
--- /dev/null
+++ b/openspec/changes/archive/2026-02-13-p10-ui-fixes/proposal.md
@@ -0,0 +1,27 @@
+## Why
+
+The current UX for the homepage hero and summary modal still has high-friction behavior and readability issues, and image relevance is still inconsistent for AI news topics. Fixing these now improves retention, trust, and content quality without changing the core product flow.
+
+## What Changes
+
+- Change hero primary CTA behavior to open the in-site TL;DR summary flow instead of immediately sending users off-site.
+- Improve hero readability over images so `LATEST` and relative time metadata remain visible across themes and screen sizes.
+- Increase modal width and adjust modal height behavior so long content can use near full-height viewport scrolling.
+- Add a short horizontal shimmer placeholder for TL;DR bullet content while summary details are loading.
+- Strengthen image relevance by extracting better keywords from news text, adding AI-topic default keywords, and using a generic AI fallback image when providers fail.
+
+## Capabilities
+
+### New Capabilities
+- `hero-summary-entry-and-readability`: Define hero CTA in-site summary entry behavior and image-overlay readability requirements for badges, timestamps, headline, and summary text.
+- `modal-layout-and-loading-feedback`: Define modal sizing/overflow behavior and TL;DR loading placeholders for clearer perceived loading state.
+- `news-image-relevance-and-fallbacks`: Define keyword extraction quality, default AI keyword fallback rules, and generic AI image fallback behavior when no relevant image is found.
+
+### Modified Capabilities
+- None.
+
+## Impact
+
+- **Frontend/UI:** `frontend/index.html` (hero CTA wiring, hero overlay/readability styles, modal width/height classes, TL;DR loading skeleton state).
+- **Backend/Image Pipeline:** `backend/news_service.py` (keyword extraction and provider fallback behavior for summary images).
+- **Assets/Config:** generic AI fallback image path/asset contract and related docs may be updated.
diff --git a/openspec/changes/archive/2026-02-13-p10-ui-fixes/specs/hero-summary-entry-and-readability/spec.md b/openspec/changes/archive/2026-02-13-p10-ui-fixes/specs/hero-summary-entry-and-readability/spec.md
new file mode 100644
index 0000000..285744f
--- /dev/null
+++ b/openspec/changes/archive/2026-02-13-p10-ui-fixes/specs/hero-summary-entry-and-readability/spec.md
@@ -0,0 +1,27 @@
+## ADDED Requirements
+
+### Requirement: Hero primary action opens in-site TL;DR summary
+The homepage hero primary CTA SHALL open the in-site summary modal for the hero article instead of navigating off-site.
+
+#### Scenario: Hero CTA opens summary modal
+- **WHEN** a user clicks the hero primary CTA
+- **THEN** the system opens the summary modal for the current hero article
+- **AND** no external navigation is triggered by that CTA
+
+### Requirement: Hero source link remains available as secondary action
+The hero section SHALL keep an explicit secondary source-link action for external navigation.
+
+#### Scenario: Source link navigates externally
+- **WHEN** a user clicks the hero source link
+- **THEN** the system opens the article source URL in a new tab
+
+### Requirement: Hero metadata readability over images
+Hero metadata (`LATEST`, relative time, headline, and summary) SHALL remain visually legible across bright and dark images on desktop and mobile.
+
+#### Scenario: Bright image background
+- **WHEN** the hero image contains bright regions under metadata text
+- **THEN** overlay and text styles preserve readable contrast for metadata and headline blocks
+
+#### Scenario: Mobile viewport readability
+- **WHEN** the hero renders on a mobile viewport
+- **THEN** metadata and title remain readable without overlapping controls or clipping
diff --git a/openspec/changes/archive/2026-02-13-p10-ui-fixes/specs/modal-layout-and-loading-feedback/spec.md b/openspec/changes/archive/2026-02-13-p10-ui-fixes/specs/modal-layout-and-loading-feedback/spec.md
new file mode 100644
index 0000000..0b8b74c
--- /dev/null
+++ b/openspec/changes/archive/2026-02-13-p10-ui-fixes/specs/modal-layout-and-loading-feedback/spec.md
@@ -0,0 +1,33 @@
+## ADDED Requirements
+
+### Requirement: Modal width supports comfortable desktop reading
+The summary modal SHALL render with a desktop width that is approximately half of viewport width or larger when space allows, while remaining responsive on small screens.
+
+#### Scenario: Desktop width expansion
+- **WHEN** the modal opens on desktop viewport widths
+- **THEN** the modal content area renders wider than the previous narrow baseline
+- **AND** text blocks are readable without excessive line wrapping
+
+#### Scenario: Mobile responsiveness
+- **WHEN** the modal opens on small mobile viewport widths
+- **THEN** modal width remains fully usable without horizontal overflow
+
+### Requirement: Modal height supports near-full viewport scrolling
+The summary modal SHALL use near full-height viewport behavior when content overflows.
+
+#### Scenario: Overflowing summary content
+- **WHEN** summary content exceeds modal viewport height
+- **THEN** modal body remains scrollable with close controls accessible
+- **AND** modal container uses near full viewport height constraints
+
+### Requirement: TL;DR loading placeholder is explicit
+The modal SHALL show a horizontal shimmer placeholder for TL;DR content while TL;DR bullets are not yet available.
+
+#### Scenario: TL;DR pending state
+- **WHEN** the summary modal is open and TL;DR bullet data is pending
+- **THEN** the system displays a low-height horizontal shimmer placeholder
+
+#### Scenario: TL;DR loaded state
+- **WHEN** TL;DR bullet data becomes available
+- **THEN** shimmer placeholder is removed
+- **AND** TL;DR bullet list is rendered
diff --git a/openspec/changes/archive/2026-02-13-p10-ui-fixes/specs/news-image-relevance-and-fallbacks/spec.md b/openspec/changes/archive/2026-02-13-p10-ui-fixes/specs/news-image-relevance-and-fallbacks/spec.md
new file mode 100644
index 0000000..d0db1bc
--- /dev/null
+++ b/openspec/changes/archive/2026-02-13-p10-ui-fixes/specs/news-image-relevance-and-fallbacks/spec.md
@@ -0,0 +1,23 @@
+## ADDED Requirements
+
+### Requirement: Image query fallback uses AI-focused defaults
+When extracted image keywords are insufficient, the system SHALL use AI-focused default fallback terms.
+
+#### Scenario: Empty keyword extraction
+- **WHEN** keyword extraction yields no usable topic keywords
+- **THEN** the system uses default fallback terms including AI-domain keywords (for example `ai`, `machine learning`, `deep learning`)
+
+### Requirement: Generic AI image fallback is guaranteed
+If provider lookups fail to return a usable summary image, the system SHALL use a generic AI-themed fallback image.
+
+#### Scenario: Provider chain failure
+- **WHEN** all configured image providers return no usable image
+- **THEN** the system assigns a generic AI fallback image URL/path for summary image
+
+### Requirement: Fallback behavior remains context-aware first
+The system SHALL attempt context-aware keyword retrieval before any generic fallback image is selected.
+
+#### Scenario: Context-aware attempt precedes fallback
+- **WHEN** summary image selection runs for a news item
+- **THEN** the system first attempts provider queries from extracted context-aware keywords
+- **AND** only falls back to generic AI image if these attempts fail
diff --git a/openspec/changes/archive/2026-02-13-p10-ui-fixes/tasks.md b/openspec/changes/archive/2026-02-13-p10-ui-fixes/tasks.md
new file mode 100644
index 0000000..557bda1
--- /dev/null
+++ b/openspec/changes/archive/2026-02-13-p10-ui-fixes/tasks.md
@@ -0,0 +1,29 @@
+## 1. Hero UX Fixes
+
+- [x] 1.1 Update hero primary CTA in `frontend/index.html` to open the in-site summary modal for the hero item.
+- [x] 1.2 Keep hero source link as a secondary external action and preserve tracking events.
+- [x] 1.3 Strengthen hero overlay and metadata styles so `LATEST` and relative time remain readable across image brightness levels.
+
+## 2. Modal Layout Improvements
+
+- [x] 2.1 Increase modal width for desktop while keeping mobile-safe responsive behavior.
+- [x] 2.2 Update modal height/overflow behavior to support near full-height scrolling for long content.
+- [x] 2.3 Verify close controls and keyboard escape behavior remain intact after sizing changes.
+
+## 3. TL;DR Loading Feedback
+
+- [x] 3.1 Add a dedicated horizontal shimmer placeholder for TL;DR content while modal summary data is initializing.
+- [x] 3.2 Hide the TL;DR shimmer placeholder when TL;DR bullets are available and render the bullet list.
+
+## 4. Image Relevance and Fallback
+
+- [x] 4.1 Update keyword fallback logic in `backend/news_service.py` to use AI-focused default terms when extracted keywords are insufficient.
+- [x] 4.2 Add explicit generic AI summary-image fallback behavior when provider chain returns no usable image.
+- [x] 4.3 Ensure context-aware keyword/provider attempts always run before generic AI fallback selection.
+
+## 5. Validation
+
+- [x] 5.1 Verify hero CTA opens summary modal instead of navigating away.
+- [x] 5.2 Verify modal sizing on desktop/mobile and long-content scrolling behavior.
+- [x] 5.3 Verify TL;DR shimmer appears during pending state and disappears after load.
+- [x] 5.4 Verify generic AI fallback image is used when provider chain fails.
diff --git a/openspec/changes/archive/2026-02-13-p11-superman-jetty/.openspec.yaml b/openspec/changes/archive/2026-02-13-p11-superman-jetty/.openspec.yaml
new file mode 100644
index 0000000..e99c55a
--- /dev/null
+++ b/openspec/changes/archive/2026-02-13-p11-superman-jetty/.openspec.yaml
@@ -0,0 +1,2 @@
+schema: spec-driven
+created: 2026-02-13
diff --git a/openspec/changes/archive/2026-02-13-p11-superman-jetty/design.md b/openspec/changes/archive/2026-02-13-p11-superman-jetty/design.md
new file mode 100644
index 0000000..320cfcb
--- /dev/null
+++ b/openspec/changes/archive/2026-02-13-p11-superman-jetty/design.md
@@ -0,0 +1,85 @@
+## Context
+
+Current operations are concentrated in `backend/cli.py` with a single `force-fetch` command and no unified admin maintenance suite. Operational actions such as archive cleanup, translation regeneration, image refresh, and cache/news reset require manual code/DB operations. Existing backend services already contain reusable primitives: ingestion (`process_and_store_news`), archival helpers (`archive_old_news`, `delete_archived_news`), and translation generation pipelines in `backend/news_service.py`.
+
+## Goals / Non-Goals
+
+**Goals:**
+- Introduce an admin command suite that consolidates common maintenance and recovery actions.
+- Implement queued image refetch for latest 30 items, sequentially processed with exponential backoff.
+- Improve image refresh relevance by combining keyword and mood/sentiment cues with deterministic fallback behavior.
+- Provide safe destructive operations (`clear-news`, `clean-archive`, cache clear) with operator guardrails.
+- Add translation regeneration and parameterized fetch count command to reduce manual intervention.
+
+**Non-Goals:**
+- Replacing the scheduled ingestion model.
+- Introducing external queue infrastructure (RabbitMQ/Redis workers) for this phase.
+- Redesigning storage models or adding new DB tables unless strictly necessary.
+- Building a web-based admin dashboard in this change.
+
+## Decisions
+
+### Decision: Extend existing CLI with subcommands
+**Decision:** Expand `backend/cli.py` into a multi-subcommand admin command suite.
+
+**Rationale:**
+- Reuses existing deployment/runtime assumptions.
+- Keeps operations scriptable via terminal/cron and avoids UI scope expansion.
+
+**Alternatives considered:**
+- New standalone admin binary: rejected due to duplicated bootstrapping/runtime checks.
+
+### Decision: Queue image refetch in-process with sequential workers
+**Decision:** Build a bounded in-memory queue for latest 30 items and process one-by-one.
+
+**Rationale:**
+- Meets rate-limit resilience requirement without new infrastructure.
+- Deterministic and easy to monitor in command output.
+
+**Alternatives considered:**
+- Parallel refetch workers: rejected due to higher provider throttling risk.
+
+### Decision: Exponential backoff for external image calls
+**Decision:** Apply exponential backoff with capped retries for rate-limited or transient failures.
+
+**Rationale:**
+- Reduces burst retry amplification.
+- Improves success rate under API pressure.
+
+### Decision: Safety-first destructive command ergonomics
+**Decision:** Destructive operations require explicit confirmation/flags and support dry-run where meaningful.
+
+**Rationale:**
+- Prevents accidental data loss.
+- Makes admin actions auditable and predictable.
+
+### Decision: Fetch-N command reuses ingestion pipeline
+**Decision:** Add a fetch-count option that drives existing ingestion/fetch flow rather than building a second implementation.
+
+**Rationale:**
+- Preserves deduplication/retry logic and minimizes divergence.
+
+## Risks / Trade-offs
+
+- **[Risk] Operator misuse of destructive commands** -> Mitigation: confirmation gate + explicit flags + dry-run.
+- **[Risk] Backoff can increase command runtime** -> Mitigation: cap retries and print progress ETA-style output.
+- **[Risk] Queue processing interruption mid-run** -> Mitigation: idempotent per-item updates and resumable reruns.
+- **[Trade-off] In-process queue is simpler but non-distributed** -> Mitigation: acceptable for admin-invoked maintenance scope.
+
+## Migration Plan
+
+1. Extend CLI parser with admin subcommands and argument validation.
+2. Add reusable maintenance handlers (archive clean, cache clear, clear news, rebuild, regenerate translations, fetch-n).
+3. Implement queued image-refetch handler with exponential backoff and per-item progress logs.
+4. Add safe guards (`--confirm`, optional `--dry-run`) for destructive operations.
+5. Document command usage and examples in README.
+
+Rollback:
+- Keep existing `force-fetch` path intact.
+- Revert new subcommands while preserving unaffected ingestion pipeline.
+
+## Open Questions
+
+- What cache layers are considered in-scope for `clear-cache` (in-memory only vs additional filesystem cache)?
+- Should `rebuild-site` chain all maintenance actions or remain a defined subset with explicit steps?
+- Should `fetch n` enforce an upper bound to avoid accidental high-cost runs?
diff --git a/openspec/changes/archive/2026-02-13-p11-superman-jetty/proposal.md b/openspec/changes/archive/2026-02-13-p11-superman-jetty/proposal.md
new file mode 100644
index 0000000..fe227ae
--- /dev/null
+++ b/openspec/changes/archive/2026-02-13-p11-superman-jetty/proposal.md
@@ -0,0 +1,34 @@
+## Why
+
+Operational recovery and maintenance flows are currently fragmented, manual, and risky for site admins during outages or data-quality incidents. We need a reliable admin command surface that supports safe reset/rebuild workflows without requiring ad-hoc scripts.
+
+## What Changes
+
+- Add a unified admin CLI command with maintenance subcommands for common operational tasks.
+- Add `refetch-images` mode that processes the latest 30 news items through a queue, one-by-one, with exponential backoff to reduce provider/API rate-limit failures.
+- Make image refetch context-aware using article keywords plus mood/sentiment signals to improve image relevance.
+- Add archive cleanup command for archived news maintenance.
+- Add cache clear command for application cache invalidation.
+- Add clear-news command for wiping existing news items.
+- Add rebuild-site command to re-run full rebuild workflow.
+- Add regenerate-translations command for all supported languages.
+- Add fetch command supporting user-provided `n` article count.
+- Add guardrails and operator UX improvements (dry-run where applicable, progress output, failure summaries, and safe defaults).
+
+## Capabilities
+
+### New Capabilities
+- `admin-maintenance-command-suite`: Defines a single admin command surface with subcommands for refetch images, archive cleanup, cache clear, news clear, rebuild, translation regeneration, and fetch-n workflows.
+- `queued-image-refetch-with-backoff`: Defines queue-based image refetch behavior for latest 30 items with sequential processing and exponential backoff for rate-limit resilience.
+- `context-aware-image-selection-recovery`: Defines keyword + sentiment/mood-informed image query rules and generic AI fallback behavior for refetch operations.
+- `site-admin-safety-and-ergonomics`: Defines operational safeguards and usability requirements (dry-run, confirmation for destructive actions, progress reporting, and actionable error summaries).
+
+### Modified Capabilities
+- None.
+
+## Impact
+
+- **Backend/CLI:** new admin command entrypoints and orchestration logic for maintenance workflows.
+- **News/Image Pipeline:** image re-fetch and optimization logic, retry/backoff strategy, and relevance heuristics.
+- **Data Layer:** archive cleanup, cache invalidation, news-clear, translation regeneration, and controlled fetch-count ingestion operations.
+- **Operations:** faster incident recovery, reduced manual intervention, and safer reset/rebuild procedures for admins.
diff --git a/openspec/changes/archive/2026-02-13-p11-superman-jetty/specs/admin-maintenance-command-suite/spec.md b/openspec/changes/archive/2026-02-13-p11-superman-jetty/specs/admin-maintenance-command-suite/spec.md
new file mode 100644
index 0000000..c30237a
--- /dev/null
+++ b/openspec/changes/archive/2026-02-13-p11-superman-jetty/specs/admin-maintenance-command-suite/spec.md
@@ -0,0 +1,32 @@
+## ADDED Requirements
+
+### Requirement: Unified admin command surface
+The system SHALL provide a single admin CLI command family exposing maintenance subcommands.
+
+#### Scenario: Subcommand discovery
+- **WHEN** an operator runs the admin command help output
+- **THEN** available subcommands include refetch-images, clean-archive, clear-cache, clear-news, rebuild-site, regenerate-translations, and fetch
+
+### Requirement: Fetch command supports configurable article count
+The admin fetch command SHALL support an operator-provided article count parameter.
+
+#### Scenario: Fetch with explicit count
+- **WHEN** an operator invokes fetch with `n=25`
+- **THEN** the command executes ingestion targeting the requested count
+- **AND** prints completion summary including processed/stored counts
+
+### Requirement: Translation regeneration command
+The system SHALL provide a command to regenerate translations for existing articles.
+
+#### Scenario: Regenerate translations run
+- **WHEN** an operator runs regenerate-translations
+- **THEN** the system attempts translation regeneration for supported languages
+- **AND** outputs success/failure totals
+
+### Requirement: Rebuild site command
+The system SHALL provide a rebuild-site command that executes the defined rebuild workflow.
+
+#### Scenario: Rebuild execution
+- **WHEN** an operator runs rebuild-site
+- **THEN** the system executes the documented rebuild steps in deterministic order
+- **AND** prints a final success/failure summary
diff --git a/openspec/changes/archive/2026-02-13-p11-superman-jetty/specs/context-aware-image-selection-recovery/spec.md b/openspec/changes/archive/2026-02-13-p11-superman-jetty/specs/context-aware-image-selection-recovery/spec.md
new file mode 100644
index 0000000..03f091a
--- /dev/null
+++ b/openspec/changes/archive/2026-02-13-p11-superman-jetty/specs/context-aware-image-selection-recovery/spec.md
@@ -0,0 +1,23 @@
+## ADDED Requirements
+
+### Requirement: Context-aware image query generation
+Image refetch SHALL construct provider queries from article context including keywords and mood/sentiment cues.
+
+#### Scenario: Context-enriched query
+- **WHEN** a queued article is processed for image refetch
+- **THEN** the system derives query terms from article headline/summary content
+- **AND** includes mood/sentiment-informed cues to improve relevance
+
+### Requirement: AI-domain fallback keywords
+When context extraction is insufficient, the system SHALL use AI-domain fallback keywords.
+
+#### Scenario: Empty or weak context extraction
+- **WHEN** extracted context terms are empty or below quality threshold
+- **THEN** the system applies fallback terms such as `ai`, `machine learning`, `deep learning`
+
+### Requirement: Generic AI fallback image on terminal failure
+If no usable provider image is returned, the system SHALL assign a generic AI fallback image.
+
+#### Scenario: Provider chain exhaustion
+- **WHEN** all provider attempts fail or return unusable images
+- **THEN** the system stores a generic AI fallback image for the article
diff --git a/openspec/changes/archive/2026-02-13-p11-superman-jetty/specs/queued-image-refetch-with-backoff/spec.md b/openspec/changes/archive/2026-02-13-p11-superman-jetty/specs/queued-image-refetch-with-backoff/spec.md
new file mode 100644
index 0000000..2d106bf
--- /dev/null
+++ b/openspec/changes/archive/2026-02-13-p11-superman-jetty/specs/queued-image-refetch-with-backoff/spec.md
@@ -0,0 +1,33 @@
+## ADDED Requirements
+
+### Requirement: Latest-30 queue construction
+The refetch-images command SHALL enqueue up to the latest 30 news items for processing.
+
+#### Scenario: Queue population
+- **WHEN** refetch-images is started
+- **THEN** the command loads recent news items
+- **AND** enqueues at most 30 items ordered from newest to oldest
+
+### Requirement: Sequential processing
+The image refetch queue SHALL be processed one item at a time.
+
+#### Scenario: Single-item worker behavior
+- **WHEN** queue processing runs
+- **THEN** only one queued item is processed concurrently
+- **AND** next item starts only after current item completes/fails
+
+### Requirement: Exponential backoff on transient failures
+The queue processor SHALL retry transient image-provider failures using exponential backoff.
+
+#### Scenario: Rate-limited provider response
+- **WHEN** provider call returns rate-limit or transient error
+- **THEN** command retries with exponential delay between attempts
+- **AND** stops retrying after configured max attempts
+
+### Requirement: Progress and completion reporting
+The command SHALL emit operator-readable progress and final summary output.
+
+#### Scenario: Queue progress output
+- **WHEN** queue processing is in progress
+- **THEN** the command prints per-item progress (processed/succeeded/failed)
+- **AND** prints final totals on completion
diff --git a/openspec/changes/archive/2026-02-13-p11-superman-jetty/specs/site-admin-safety-and-ergonomics/spec.md b/openspec/changes/archive/2026-02-13-p11-superman-jetty/specs/site-admin-safety-and-ergonomics/spec.md
new file mode 100644
index 0000000..f249fea
--- /dev/null
+++ b/openspec/changes/archive/2026-02-13-p11-superman-jetty/specs/site-admin-safety-and-ergonomics/spec.md
@@ -0,0 +1,25 @@
+## ADDED Requirements
+
+### Requirement: Confirmation guard for destructive commands
+Destructive admin commands SHALL require explicit confirmation before execution.
+
+#### Scenario: Missing confirmation flag
+- **WHEN** an operator runs clear-news or clean-archive without required confirmation
+- **THEN** the command exits without applying destructive changes
+- **AND** prints guidance for explicit confirmation usage
+
+### Requirement: Dry-run support where applicable
+Maintenance commands SHALL provide dry-run mode for previewing effects where feasible.
+
+#### Scenario: Dry-run preview
+- **WHEN** an operator invokes a command with dry-run mode
+- **THEN** the command reports intended actions and affected counts
+- **AND** persists no data changes
+
+### Requirement: Actionable failure summaries
+Admin commands SHALL output actionable errors and final status summaries.
+
+#### Scenario: Partial failure reporting
+- **WHEN** a maintenance command partially fails
+- **THEN** output includes succeeded/failed counts
+- **AND** includes actionable next-step guidance
diff --git a/openspec/changes/archive/2026-02-13-p11-superman-jetty/tasks.md b/openspec/changes/archive/2026-02-13-p11-superman-jetty/tasks.md
new file mode 100644
index 0000000..27f851f
--- /dev/null
+++ b/openspec/changes/archive/2026-02-13-p11-superman-jetty/tasks.md
@@ -0,0 +1,41 @@
+## 1. Admin CLI Foundation
+
+- [x] 1.1 Extend `backend/cli.py` parser with an admin maintenance command group and subcommands.
+- [x] 1.2 Add argument validation for subcommands including `fetch --count n`.
+- [x] 1.3 Keep existing `force-fetch` command behavior intact.
+
+## 2. Queue-Based Image Refetch
+
+- [x] 2.1 Implement latest-30 article selection query for refetch queue.
+- [x] 2.2 Implement in-process sequential queue worker for refetch-images.
+- [x] 2.3 Add exponential backoff retry logic for transient/rate-limit provider failures.
+- [x] 2.4 Add per-item progress logging and final queue summary output.
+
+## 3. Context-Aware Image Recovery
+
+- [x] 3.1 Add context-aware query generation using article keywords plus mood/sentiment cues.
+- [x] 3.2 Add AI-domain fallback keyword set when extracted context is weak.
+- [x] 3.3 Add explicit generic AI fallback image assignment for terminal provider failure.
+- [x] 3.4 Ensure refetched images are optimized and persisted using existing image pipeline contracts.
+
+## 4. Maintenance Operations
+
+- [x] 4.1 Implement clean-archive command using existing archival repository helpers.
+- [x] 4.2 Implement clear-cache command for configured cache layers in scope.
+- [x] 4.3 Implement clear-news command for non-archived and/or configured scope items.
+- [x] 4.4 Implement rebuild-site command to execute defined rebuild sequence.
+- [x] 4.5 Implement regenerate-translations command across supported languages.
+- [x] 4.6 Implement fetch command with configurable article count.
+
+## 5. Safety and Operator UX
+
+- [x] 5.1 Add explicit confirmation requirement for destructive commands.
+- [x] 5.2 Add dry-run support for commands where preview is feasible.
+- [x] 5.3 Standardize command output format for success/failure totals and next-step hints.
+
+## 6. Documentation and Validation
+
+- [x] 6.1 Update README command documentation with examples for each new subcommand.
+- [x] 6.2 Add operational guardrail notes (confirmation, dry-run, backoff behavior).
+- [x] 6.3 Validate command help output and argument handling.
+- [x] 6.4 Run end-to-end manual checks for refetch-images queue behavior and failure recovery output.
diff --git a/openspec/changes/p12-umami-events-and-more/.openspec.yaml b/openspec/changes/p12-umami-events-and-more/.openspec.yaml
new file mode 100644
index 0000000..e99c55a
--- /dev/null
+++ b/openspec/changes/p12-umami-events-and-more/.openspec.yaml
@@ -0,0 +1,2 @@
+schema: spec-driven
+created: 2026-02-13
diff --git a/openspec/changes/p12-umami-events-and-more/proposal.md b/openspec/changes/p12-umami-events-and-more/proposal.md
new file mode 100644
index 0000000..08626f8
--- /dev/null
+++ b/openspec/changes/p12-umami-events-and-more/proposal.md
@@ -0,0 +1,23 @@
+## Why
+
+Current Umami event payloads for CTA clicks and summary modal interactions include only `article_id`, which makes analysis harder when reviewing dashboards and raw events. Adding human-readable article context improves analyst speed and reduces lookup friction.
+
+## What Changes
+
+- Add `article_title` to CTA-click event payloads so click analytics can be understood without cross-referencing IDs.
+- Add `article_title` to summary modal open/close event payloads in addition to existing `article_id` context.
+- Keep existing event names and current fields intact for backward compatibility.
+
+## Capabilities
+
+### New Capabilities
+- None.
+
+### Modified Capabilities
+- `hero-display`: Update analytics tracking requirement so CTA click events include both `article_id` and `article_title`.
+- `summary-analytics-tagging`: Update modal open/close analytics requirements so payload includes `article_title` with existing article context identifier.
+
+## Impact
+
+- **Frontend analytics wiring:** `frontend/index.html` event payload construction for hero/feed CTA clicks and summary modal open/close events.
+- **Analytics consumers:** Umami dashboards and downstream event analysis gain readable article context while preserving existing identifiers.
diff --git a/openspec/changes/p13-usability-enhancements/.openspec.yaml b/openspec/changes/p13-usability-enhancements/.openspec.yaml
new file mode 100644
index 0000000..e99c55a
--- /dev/null
+++ b/openspec/changes/p13-usability-enhancements/.openspec.yaml
@@ -0,0 +1,2 @@
+schema: spec-driven
+created: 2026-02-13
diff --git a/openspec/specs/admin-maintenance-command-suite/spec.md b/openspec/specs/admin-maintenance-command-suite/spec.md
new file mode 100644
index 0000000..db7a5cc
--- /dev/null
+++ b/openspec/specs/admin-maintenance-command-suite/spec.md
@@ -0,0 +1,36 @@
+## Purpose
+
+Canonical specification for admin-maintenance-command-suite requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: Unified admin command surface
+The system SHALL provide a single admin CLI command family exposing maintenance subcommands.
+
+#### Scenario: Subcommand discovery
+- **WHEN** an operator runs the admin command help output
+- **THEN** available subcommands include refetch-images, clean-archive, clear-cache, clear-news, rebuild-site, regenerate-translations, and fetch
+
+### Requirement: Fetch command supports configurable article count
+The admin fetch command SHALL support an operator-provided article count parameter.
+
+#### Scenario: Fetch with explicit count
+- **WHEN** an operator invokes fetch with `n=25`
+- **THEN** the command executes ingestion targeting the requested count
+- **AND** prints completion summary including processed/stored counts
+
+### Requirement: Translation regeneration command
+The system SHALL provide a command to regenerate translations for existing articles.
+
+#### Scenario: Regenerate translations run
+- **WHEN** an operator runs regenerate-translations
+- **THEN** the system attempts translation regeneration for supported languages
+- **AND** outputs success/failure totals
+
+### Requirement: Rebuild site command
+The system SHALL provide a rebuild-site command that executes the defined rebuild workflow.
+
+#### Scenario: Rebuild execution
+- **WHEN** an operator runs rebuild-site
+- **THEN** the system executes the documented rebuild steps in deterministic order
+- **AND** prints a final success/failure summary
diff --git a/openspec/specs/article-tldr-summary/spec.md b/openspec/specs/article-tldr-summary/spec.md
new file mode 100644
index 0000000..0b64cad
--- /dev/null
+++ b/openspec/specs/article-tldr-summary/spec.md
@@ -0,0 +1,26 @@
+## Purpose
+
+Canonical specification for article-tldr-summary requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: System generates structured TL;DR summary for each fetched article
+The system SHALL generate a concise summary artifact for each newly fetched article using Perplexity during ingestion.
+
+#### Scenario: Successful summary generation
+- **WHEN** a new article is accepted in ingestion
+- **THEN** the system generates TL;DR bullet points and a concise summary body
+- **AND** output is persisted in a structured, template-compatible format
+
+#### Scenario: Summary generation fallback
+- **WHEN** summary generation fails for an article
+- **THEN** ingestion continues without failing the entire cycle
+- **AND** the article remains available with existing non-summary content
+
+### Requirement: Summary storage includes citation and source context
+The system SHALL persist source/citation information needed to render summary provenance.
+
+#### Scenario: Persist source and citation metadata
+- **WHEN** summary content is stored
+- **THEN** associated source/citation fields are stored with the article summary artifact
+- **AND** response payloads can render a "Source and Citation" section
diff --git a/openspec/specs/article-translations-ml-tm/spec.md b/openspec/specs/article-translations-ml-tm/spec.md
new file mode 100644
index 0000000..6676767
--- /dev/null
+++ b/openspec/specs/article-translations-ml-tm/spec.md
@@ -0,0 +1,31 @@
+## Purpose
+
+Canonical specification for article-translations-ml-tm requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: System generates Tamil and Malayalam translations at article creation time
+The system SHALL generate Tamil (`ta`) and Malayalam (`ml`) translations for each newly created article during ingestion.
+
+#### Scenario: Translation generation for new article
+- **WHEN** a new source article is accepted for storage
+- **THEN** the system requests Tamil and Malayalam translations for headline and summary
+- **AND** translation generation occurs in the same ingestion flow for that article
+
+#### Scenario: Translation failure fallback
+- **WHEN** translation generation fails for one or both target languages
+- **THEN** the system stores the base article in English
+- **AND** marks missing translations as unavailable without failing the whole ingestion cycle
+
+### Requirement: System stores translation variants linked to the same article
+The system SHALL persist language-specific translated content as translation items associated with the base article.
+
+#### Scenario: Persist linked translations
+- **WHEN** Tamil and Malayalam translations are generated successfully
+- **THEN** the system stores them as language-specific content variants linked to the base article identifier
+- **AND** translation records remain queryable by language code
+
+#### Scenario: No duplicate translation variants per language
+- **WHEN** translation storage is attempted for an article-language pair that already exists
+- **THEN** the system avoids creating duplicate translation items for the same language
+- **AND** preserves one authoritative translation variant per article per language in this phase
diff --git a/openspec/specs/attribution-disclaimer-page/spec.md b/openspec/specs/attribution-disclaimer-page/spec.md
new file mode 100644
index 0000000..926758e
--- /dev/null
+++ b/openspec/specs/attribution-disclaimer-page/spec.md
@@ -0,0 +1,18 @@
+## Purpose
+
+Canonical specification for attribution-disclaimer-page requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: Attribution page discloses AI generation and non-ownership
+The system SHALL provide an Attribution page with explicit statements that content is AI-generated and not personally authored by the site owner.
+
+#### Scenario: Attribution page title and disclosure content
+- **WHEN** a user opens the Attribution page
+- **THEN** the page title clearly indicates attribution/disclaimer purpose
+- **AND** the body states that content is AI-generated and not generated by the owner as an individual
+
+#### Scenario: Attribution page includes non-involvement statement
+- **WHEN** a user reads the Attribution page
+- **THEN** the page explicitly states owner non-involvement in generated content claims
+- **AND** wording is presented in primary readable content area
diff --git a/openspec/specs/containerized-deployment/spec.md b/openspec/specs/containerized-deployment/spec.md
new file mode 100644
index 0000000..da030aa
--- /dev/null
+++ b/openspec/specs/containerized-deployment/spec.md
@@ -0,0 +1,47 @@
+## Purpose
+
+Canonical specification for containerized-deployment requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: Containerized deployment
+The system SHALL run entirely within Docker containers with all dependencies included.
+
+#### Scenario: Single container build
+- **WHEN** building the Docker image
+- **THEN** the Dockerfile SHALL include Python runtime, Node.js (for Tailwind if needed), and all application code
+- **AND** expose port 8000 for web traffic
+
+#### Scenario: Environment configuration
+- **WHEN** running the container
+- **THEN** the system SHALL read PERPLEXITY_API_KEY from environment variables
+- **AND** fail to start if the key is missing or invalid
+- **AND** support optional configuration for retention days (default: 30)
+- **AND** support optional IMAGE_QUALITY for image compression (default: 85)
+- **AND** support optional OPENROUTER_API_KEY for fallback LLM provider
+- **AND** support optional UMAMI_SCRIPT_URL and UMAMI_WEBSITE_ID for analytics
+
+#### Scenario: Data persistence
+- **WHEN** the container restarts
+- **THEN** the SQLite database SHALL persist via Docker volume mount
+- **AND** news data SHALL remain intact across restarts
+
+### Requirement: Responsive single-page design
+The system SHALL provide a stunning, responsive one-page website with ClawFort branding.
+
+#### Scenario: Brand consistency
+- **WHEN** viewing the website
+- **THEN** the design SHALL feature ClawFort branding (logo, colors, typography)
+- **AND** maintain visual consistency across all sections
+
+#### Scenario: Responsive layout
+- **WHEN** viewing on mobile, tablet, or desktop
+- **THEN** the layout SHALL adapt appropriately
+- **AND** the hero block SHALL resize proportionally
+- **AND** the news feed SHALL use appropriate column layouts
+
+#### Scenario: Performance
+- **WHEN** loading the page
+- **THEN** initial page load SHALL complete within 2 seconds
+- **AND** images SHALL lazy load outside viewport
+- **AND** JavaScript bundle SHALL be under 100KB gzipped
diff --git a/openspec/specs/context-aware-image-selection-recovery/spec.md b/openspec/specs/context-aware-image-selection-recovery/spec.md
new file mode 100644
index 0000000..61a8bd5
--- /dev/null
+++ b/openspec/specs/context-aware-image-selection-recovery/spec.md
@@ -0,0 +1,27 @@
+## Purpose
+
+Canonical specification for context-aware-image-selection-recovery requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: Context-aware image query generation
+Image refetch SHALL construct provider queries from article context including keywords and mood/sentiment cues.
+
+#### Scenario: Context-enriched query
+- **WHEN** a queued article is processed for image refetch
+- **THEN** the system derives query terms from article headline/summary content
+- **AND** includes mood/sentiment-informed cues to improve relevance
+
+### Requirement: AI-domain fallback keywords
+When context extraction is insufficient, the system SHALL use AI-domain fallback keywords.
+
+#### Scenario: Empty or weak context extraction
+- **WHEN** extracted context terms are empty or below quality threshold
+- **THEN** the system applies fallback terms such as `ai`, `machine learning`, `deep learning`
+
+### Requirement: Generic AI fallback image on terminal failure
+If no usable provider image is returned, the system SHALL assign a generic AI fallback image.
+
+#### Scenario: Provider chain exhaustion
+- **WHEN** all provider attempts fail or return unusable images
+- **THEN** the system stores a generic AI fallback image for the article
diff --git a/openspec/specs/cookie-consent-tracking-gate/spec.md b/openspec/specs/cookie-consent-tracking-gate/spec.md
new file mode 100644
index 0000000..65ba31f
--- /dev/null
+++ b/openspec/specs/cookie-consent-tracking-gate/spec.md
@@ -0,0 +1,18 @@
+## Purpose
+
+Canonical specification for cookie-consent-tracking-gate requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: Consent banner captures and persists tracking consent
+The system SHALL display a cookie consent banner and persist user consent decision in cookies before enabling analytics tracking.
+
+#### Scenario: Consent capture and persistence
+- **WHEN** a user interacts with the consent banner and accepts
+- **THEN** consent state is stored in a cookie
+- **AND** stored consent is honored on subsequent visits
+
+#### Scenario: Tracking gated by consent
+- **WHEN** consent has not been granted
+- **THEN** analytics/tracking scripts and events do not execute
+- **AND** tracking begins only after consent state indicates acceptance
diff --git a/openspec/specs/delivery-and-rendering-performance/spec.md b/openspec/specs/delivery-and-rendering-performance/spec.md
new file mode 100644
index 0000000..c65a7b4
--- /dev/null
+++ b/openspec/specs/delivery-and-rendering-performance/spec.md
@@ -0,0 +1,39 @@
+## Purpose
+
+Canonical specification for delivery-and-rendering-performance requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: HTTP delivery applies compression and cache policy
+The system SHALL apply transport-level compression and explicit cache directives for static assets, API responses, and public HTML routes.
+
+#### Scenario: Compressed responses are available for eligible payloads
+- **WHEN** a client requests compressible content that exceeds the compression threshold
+- **THEN** the response is served with gzip compression
+- **AND** response headers advertise the selected content encoding
+
+#### Scenario: Route classes receive deterministic cache-control directives
+- **WHEN** clients request static assets, API responses, or HTML page routes
+- **THEN** each route class returns a cache policy aligned to its freshness requirements
+- **AND** cache directives are explicit and testable from response headers
+
+### Requirement: Media rendering optimizes perceived loading performance
+The system SHALL lazy-load non-critical images and render shimmer placeholders until image load completion or fallback resolution.
+
+#### Scenario: Feed and modal images lazy-load with placeholders
+- **WHEN** feed or modal images have not completed loading
+- **THEN** a shimmer placeholder is visible for the pending image region
+- **AND** the placeholder is removed after load or fallback error handling completes
+
+#### Scenario: Image rendering reduces layout shift risk
+- **WHEN** article images are rendered in hero, feed, or modal contexts
+- **THEN** image elements include explicit dimensions and async decoding hints
+- **AND** layout remains stable while content loads
+
+### Requirement: Smooth scrolling behavior is consistently enabled
+The system SHALL provide smooth scrolling behavior for in-page navigation and user-initiated scroll interactions.
+
+#### Scenario: In-page navigation uses smooth scrolling
+- **WHEN** users navigate to in-page anchors or equivalent interactions
+- **THEN** scrolling transitions occur smoothly rather than jumping abruptly
+- **AND** behavior is consistent across supported breakpoints
diff --git a/openspec/specs/fetch-run-reporting/spec.md b/openspec/specs/fetch-run-reporting/spec.md
new file mode 100644
index 0000000..4559b8d
--- /dev/null
+++ b/openspec/specs/fetch-run-reporting/spec.md
@@ -0,0 +1,31 @@
+## Purpose
+
+Canonical specification for fetch-run-reporting requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: Command reports run outcome to operator
+The system SHALL present operator-facing output that describes whether the forced run succeeded or failed.
+
+#### Scenario: Successful run reporting
+- **WHEN** a forced fetch command completes without fatal errors
+- **THEN** the command output includes a success indication
+- **AND** includes the number of items stored in that run
+
+#### Scenario: Failed run reporting
+- **WHEN** a forced fetch command encounters a fatal execution error
+- **THEN** the command output includes a failure indication
+- **AND** includes actionable error details for operator diagnosis
+
+### Requirement: Command exposes automation-friendly exit semantics
+The system SHALL return deterministic process exit codes for command success and failure.
+
+#### Scenario: Exit code on success
+- **WHEN** the force-fetch command execution completes successfully
+- **THEN** the process exits with code 0
+- **AND** automation tooling can treat the run as successful
+
+#### Scenario: Exit code on fatal failure
+- **WHEN** the force-fetch command execution fails fatally
+- **THEN** the process exits with a non-zero code
+- **AND** automation tooling can detect the failure state
diff --git a/openspec/specs/footer-policy-links/spec.md b/openspec/specs/footer-policy-links/spec.md
new file mode 100644
index 0000000..47bdb8a
--- /dev/null
+++ b/openspec/specs/footer-policy-links/spec.md
@@ -0,0 +1,18 @@
+## Purpose
+
+Canonical specification for footer-policy-links requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: Footer exposes policy navigation links
+The system SHALL display footer links for Terms of Use and Attribution on the landing page.
+
+#### Scenario: Footer links visible on landing page
+- **WHEN** a user loads the main page
+- **THEN** the footer includes links labeled "Terms of Use" and "Attribution"
+- **AND** links are visually distinguishable and keyboard focusable
+
+#### Scenario: Footer links navigate correctly
+- **WHEN** a user activates either policy link
+- **THEN** the browser navigates to the corresponding policy page
+- **AND** navigation succeeds without API dependency
diff --git a/openspec/specs/force-fetch-command/spec.md b/openspec/specs/force-fetch-command/spec.md
new file mode 100644
index 0000000..3ea9f1e
--- /dev/null
+++ b/openspec/specs/force-fetch-command/spec.md
@@ -0,0 +1,31 @@
+## Purpose
+
+Canonical specification for force-fetch-command requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: Operator can trigger immediate news fetch via Python command
+The system SHALL provide a Python command that triggers one immediate news aggregation run outside of the hourly scheduler.
+
+#### Scenario: Successful forced fetch invocation
+- **WHEN** an operator runs the documented force-fetch command with valid runtime configuration
+- **THEN** the system executes one full fetch cycle using the existing aggregation pipeline
+- **AND** the command terminates after the run completes
+
+#### Scenario: Command does not reconfigure scheduler
+- **WHEN** an operator runs the force-fetch command while the service scheduler exists
+- **THEN** the command performs a one-off run only
+- **AND** scheduler job definitions and cadence remain unchanged
+
+### Requirement: Forced fetch reuses existing aggregation behavior
+The system SHALL use the same retry, fallback, deduplication, image processing, and persistence logic as scheduled fetch runs.
+
+#### Scenario: Retry and fallback parity
+- **WHEN** the primary news provider request fails during a forced run
+- **THEN** the system applies the configured retry behavior
+- **AND** uses the configured fallback provider path if available
+
+#### Scenario: Deduplication parity
+- **WHEN** fetched headlines match existing duplicate rules
+- **THEN** duplicate items are skipped according to existing deduplication policy
+- **AND** only eligible items are persisted
diff --git a/openspec/specs/hero-display/spec.md b/openspec/specs/hero-display/spec.md
new file mode 100644
index 0000000..12e87f9
--- /dev/null
+++ b/openspec/specs/hero-display/spec.md
@@ -0,0 +1,57 @@
+## Purpose
+
+Canonical specification for hero-display requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: Hero block display
+The system SHALL display the most recent news item as a featured hero block with full attribution.
+
+#### Scenario: Hero rendering
+- **WHEN** the page loads
+- **THEN** the hero block SHALL display the latest news headline, summary, and featured image
+- **AND** show source attribution (e.g., "Via: TechCrunch")
+- **AND** show image credit (e.g., "Image: DALL-E")
+
+#### Scenario: Hero update
+- **WHEN** new news is fetched hourly
+- **THEN** the hero block SHALL automatically update to show the newest item
+- **AND** the previous hero item SHALL move to the news feed
+
+### Requirement: Infinite scroll news feed
+The system SHALL display news items in reverse chronological order with infinite scroll pagination.
+
+#### Scenario: Initial load
+- **WHEN** the page first loads
+- **THEN** the system SHALL display the 10 most recent non-archived news items
+- **AND** exclude the hero item from the feed
+
+#### Scenario: Infinite scroll
+- **WHEN** the user scrolls to the bottom of the feed
+- **THEN** the system SHALL fetch the next 10 news items via API
+- **AND** append them to the feed without page reload
+- **AND** show a loading indicator during fetch
+
+#### Scenario: End of feed
+- **WHEN** all non-archived news items have been loaded
+- **THEN** the system SHALL display "No more news" message
+- **AND** disable further scroll triggers
+
+### Requirement: News attribution display
+The system SHALL clearly attribute all news content and images to their sources.
+
+#### Scenario: Source attribution
+- **WHEN** displaying any news item
+- **THEN** the system SHALL show the original source name and link
+- **AND** display image credit if available
+
+#### Scenario: Perplexity attribution
+- **WHEN** displaying aggregated content
+- **THEN** the system SHALL include "Powered by Perplexity" in the footer
+
+#### Scenario: Analytics tracking
+- **WHEN** Umami analytics is configured via `UMAMI_SCRIPT_URL` and `UMAMI_WEBSITE_ID`
+- **THEN** the system SHALL inject Umami tracking script into page head
+- **AND** track page view events on initial load
+- **AND** track scroll depth events (25%, 50%, 75%, 100%)
+- **AND** track CTA click events (news item clicks, source link clicks)
diff --git a/openspec/specs/hero-summary-entry-and-readability/spec.md b/openspec/specs/hero-summary-entry-and-readability/spec.md
new file mode 100644
index 0000000..4d23d8a
--- /dev/null
+++ b/openspec/specs/hero-summary-entry-and-readability/spec.md
@@ -0,0 +1,31 @@
+## Purpose
+
+Canonical specification for hero-summary-entry-and-readability requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: Hero primary action opens in-site TL;DR summary
+The homepage hero primary CTA SHALL open the in-site summary modal for the hero article instead of navigating off-site.
+
+#### Scenario: Hero CTA opens summary modal
+- **WHEN** a user clicks the hero primary CTA
+- **THEN** the system opens the summary modal for the current hero article
+- **AND** no external navigation is triggered by that CTA
+
+### Requirement: Hero source link remains available as secondary action
+The hero section SHALL keep an explicit secondary source-link action for external navigation.
+
+#### Scenario: Source link navigates externally
+- **WHEN** a user clicks the hero source link
+- **THEN** the system opens the article source URL in a new tab
+
+### Requirement: Hero metadata readability over images
+Hero metadata (`LATEST`, relative time, headline, and summary) SHALL remain visually legible across bright and dark images on desktop and mobile.
+
+#### Scenario: Bright image background
+- **WHEN** the hero image contains bright regions under metadata text
+- **THEN** overlay and text styles preserve readable contrast for metadata and headline blocks
+
+#### Scenario: Mobile viewport readability
+- **WHEN** the hero renders on a mobile viewport
+- **THEN** metadata and title remain readable without overlapping controls or clipping
diff --git a/openspec/specs/image-provider-fallback-chain/spec.md b/openspec/specs/image-provider-fallback-chain/spec.md
new file mode 100644
index 0000000..bd533fa
--- /dev/null
+++ b/openspec/specs/image-provider-fallback-chain/spec.md
@@ -0,0 +1,63 @@
+## Purpose
+
+Canonical specification for image-provider-fallback-chain requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: Configurable provider priority
+The system SHALL support configuring image provider order via `ROYALTY_IMAGE_PROVIDERS` environment variable.
+
+#### Scenario: Custom provider order
+- **WHEN** `ROYALTY_IMAGE_PROVIDERS=unsplash,pexels,pixabay,wikimedia,picsum`
+- **THEN** system tries providers in order: Unsplash → Pexels → Pixabay → Wikimedia → Picsum
+
+#### Scenario: Default provider order
+- **WHEN** `ROYALTY_IMAGE_PROVIDERS` is not set or empty
+- **THEN** system uses default order: `pixabay,unsplash,pexels,wikimedia,picsum`
+
+#### Scenario: Single provider configured
+- **WHEN** `ROYALTY_IMAGE_PROVIDERS=pexels`
+- **THEN** system only tries Pexels provider
+- **AND** returns `(None, None)` if Pexels fails or is not configured
+
+### Requirement: Sequential fallback execution
+The system SHALL try providers sequentially until one returns a valid image.
+
+#### Scenario: First provider succeeds
+- **WHEN** provider chain is `pixabay,unsplash,pexels` AND Pixabay returns valid image
+- **THEN** system returns Pixabay image immediately
+- **AND** does NOT call Unsplash or Pexels APIs
+
+#### Scenario: First provider fails, second succeeds
+- **WHEN** provider chain is `pixabay,unsplash,pexels` AND Pixabay returns no results AND Unsplash returns valid image
+- **THEN** system returns Unsplash image
+- **AND** does NOT call Pexels API
+
+#### Scenario: All providers fail
+- **WHEN** all configured providers return `(None, None)`
+- **THEN** system returns `(None, None)` as final result
+- **AND** caller handles fallback to article image or placeholder
+
+### Requirement: MCP endpoint override
+The existing `ROYALTY_IMAGE_MCP_ENDPOINT` SHALL take priority over the provider chain when configured.
+
+#### Scenario: MCP endpoint configured
+- **WHEN** `ROYALTY_IMAGE_MCP_ENDPOINT` is set to valid URL
+- **THEN** system tries MCP endpoint first before provider chain
+- **AND** falls back to provider chain only if MCP endpoint fails
+
+#### Scenario: MCP endpoint not configured
+- **WHEN** `ROYALTY_IMAGE_MCP_ENDPOINT` is empty or unset
+- **THEN** system skips MCP endpoint and proceeds directly to provider chain
+
+### Requirement: Provider skip on missing credentials
+Providers without required API keys SHALL be skipped silently.
+
+#### Scenario: Skip unconfigured provider
+- **WHEN** provider chain includes `pixabay` AND `PIXABAY_API_KEY` is not set
+- **THEN** Pixabay is skipped without error
+- **AND** chain continues to next provider
+
+#### Scenario: All providers skipped
+- **WHEN** no providers in chain have valid API keys configured
+- **THEN** system falls back to Wikimedia (no key required) or Picsum (always available)
diff --git a/openspec/specs/image-query-refinement/spec.md b/openspec/specs/image-query-refinement/spec.md
new file mode 100644
index 0000000..5bff70c
--- /dev/null
+++ b/openspec/specs/image-query-refinement/spec.md
@@ -0,0 +1,75 @@
+## Purpose
+
+Canonical specification for image-query-refinement requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: Keyword extraction from headline
+The system SHALL extract relevant keywords from article headlines for image search.
+
+#### Scenario: Extract keywords from standard headline
+- **WHEN** headline is "OpenAI Announces GPT-5 with Revolutionary Reasoning Capabilities"
+- **THEN** extracted query is "OpenAI GPT-5 Revolutionary Reasoning"
+- **AND** stop words like "Announces", "with", "Capabilities" are removed
+
+#### Scenario: Handle short headline
+- **WHEN** headline is "AI Breakthrough"
+- **THEN** extracted query is "AI Breakthrough"
+- **AND** no keywords are removed (headline too short)
+
+#### Scenario: Handle headline with special characters
+- **WHEN** headline is "Tesla's Self-Driving AI: 99.9% Accuracy Achieved!"
+- **THEN** extracted query is "Tesla Self-Driving AI Accuracy"
+- **AND** special characters like apostrophes, colons, and punctuation are normalized
+
+### Requirement: Stop word removal
+The system SHALL remove common English stop words from search queries.
+
+#### Scenario: Remove articles and prepositions
+- **WHEN** headline is "The Future of AI in the Healthcare Industry"
+- **THEN** extracted query is "Future AI Healthcare Industry"
+- **AND** "The", "of", "in", "the" are removed
+
+#### Scenario: Preserve technical terms
+- **WHEN** headline is "How Machine Learning Models Learn from Data"
+- **THEN** extracted query is "Machine Learning Models Learn Data"
+- **AND** technical terms "Machine", "Learning", "Models" are preserved
+
+### Requirement: Query length limit
+The system SHALL limit search query length to optimize API results.
+
+#### Scenario: Truncate long query
+- **WHEN** extracted keywords exceed 10 words
+- **THEN** query is limited to first 5 most significant keywords
+- **AND** remaining keywords are dropped
+
+#### Scenario: Preserve short query
+- **WHEN** extracted keywords are 5 words or fewer
+- **THEN** all keywords are included in query
+- **AND** no truncation occurs
+
+### Requirement: URL-safe query encoding
+The system SHALL URL-encode queries before sending to provider APIs.
+
+#### Scenario: Encode spaces and special characters
+- **WHEN** query is "AI Machine Learning"
+- **THEN** encoded query is "AI+Machine+Learning" or "AI%20Machine%20Learning"
+- **AND** query is safe for HTTP GET parameters
+
+#### Scenario: Handle Unicode characters
+- **WHEN** query contains Unicode like "AI für Deutschland"
+- **THEN** Unicode characters are properly percent-encoded
+- **AND** API request succeeds without encoding errors
+
+### Requirement: Empty query handling
+The system SHALL handle edge cases where no keywords can be extracted.
+
+#### Scenario: Headline with only stop words
+- **WHEN** headline is "The and a or but"
+- **THEN** system uses fallback query "news technology"
+- **AND** image search proceeds with generic query
+
+#### Scenario: Empty headline
+- **WHEN** headline is empty string or whitespace only
+- **THEN** system uses fallback query "news technology"
+- **AND** image search proceeds with generic query
diff --git a/openspec/specs/language-aware-content-delivery/spec.md b/openspec/specs/language-aware-content-delivery/spec.md
new file mode 100644
index 0000000..96e2982
--- /dev/null
+++ b/openspec/specs/language-aware-content-delivery/spec.md
@@ -0,0 +1,31 @@
+## Purpose
+
+Canonical specification for language-aware-content-delivery requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: API supports language-aware content retrieval
+The system SHALL support language-aware content delivery for hero and feed reads using selected language input.
+
+#### Scenario: Language-specific latest article response
+- **WHEN** a client requests latest article data with a supported language selection
+- **THEN** the system returns headline and summary in the selected language when available
+- **AND** includes the corresponding base article metadata and media attribution
+
+#### Scenario: Language-specific paginated feed response
+- **WHEN** a client requests paginated feed data with a supported language selection
+- **THEN** the system returns each feed item's headline and summary in the selected language when available
+- **AND** preserves existing pagination behavior and ordering semantics
+
+### Requirement: Language fallback to English is deterministic
+The system SHALL return English source content when the requested translation is unavailable.
+
+#### Scenario: Missing translation fallback
+- **WHEN** a client requests Tamil or Malayalam content for an article lacking that translation
+- **THEN** the system returns the English headline and summary for that article
+- **AND** response shape remains consistent with language-aware responses
+
+#### Scenario: Unsupported language handling
+- **WHEN** a client requests a language outside supported values (`en`, `ta`, `ml`)
+- **THEN** the system applies the defined default language behavior for this phase
+- **AND** avoids breaking existing consumers of news endpoints
diff --git a/openspec/specs/language-preference-persistence/spec.md b/openspec/specs/language-preference-persistence/spec.md
new file mode 100644
index 0000000..0f10376
--- /dev/null
+++ b/openspec/specs/language-preference-persistence/spec.md
@@ -0,0 +1,31 @@
+## Purpose
+
+Canonical specification for language-preference-persistence requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: Landing page provides language selector
+The system SHALL display a language selector on the landing page that allows switching between English, Tamil, and Malayalam content views.
+
+#### Scenario: User selects language from landing page
+- **WHEN** a user chooses Tamil or Malayalam from the language selector
+- **THEN** hero and feed content update to requested language-aware rendering
+- **AND** subsequent API requests use the selected language context
+
+#### Scenario: User switches back to English
+- **WHEN** a user selects English in the language selector
+- **THEN** content renders in English
+- **AND** language state updates immediately in the frontend view
+
+### Requirement: User language preference is persisted and restored
+The system SHALL persist selected language preference in client-side storage and restore it for returning users.
+
+#### Scenario: Persist language selection
+- **WHEN** a user selects a supported language on the landing page
+- **THEN** the selected language code is stored in local storage or a client cookie
+- **AND** the persisted value is used as preferred language for future visits on the same browser
+
+#### Scenario: Restore preference on return visit
+- **WHEN** a returning user opens the landing page
+- **THEN** the system reads persisted language preference from client storage
+- **AND** initializes the UI and content requests with that language by default
diff --git a/openspec/specs/manual-fetch-recovery/spec.md b/openspec/specs/manual-fetch-recovery/spec.md
new file mode 100644
index 0000000..9e5e795
--- /dev/null
+++ b/openspec/specs/manual-fetch-recovery/spec.md
@@ -0,0 +1,26 @@
+## Purpose
+
+Canonical specification for manual-fetch-recovery requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: Manual command supports bootstrap and recovery workflows
+The system SHALL allow operators to run the forced fetch command during first-time setup and after failed scheduled cycles.
+
+#### Scenario: Bootstrap content population
+- **WHEN** the system is newly deployed and contains no current news items
+- **THEN** an operator can run the force-fetch command immediately
+- **AND** the command attempts to populate the dataset without waiting for the next hourly schedule
+
+#### Scenario: Recovery after failed scheduled fetch
+- **WHEN** a prior scheduled fetch cycle failed or produced incomplete results
+- **THEN** an operator can run the force-fetch command on demand
+- **AND** the system performs a fresh one-off fetch attempt
+
+### Requirement: Repeated manual runs remain operationally safe
+The system SHALL support repeated operator-triggered runs without corrupting data integrity.
+
+#### Scenario: Repeated invocation in same day
+- **WHEN** an operator runs the force-fetch command multiple times within the same day
+- **THEN** existing deduplication behavior prevents duplicate persistence for matching items
+- **AND** each command run completes with explicit run status output
diff --git a/openspec/specs/mcp-image-provider-integration/spec.md b/openspec/specs/mcp-image-provider-integration/spec.md
new file mode 100644
index 0000000..66aa1f2
--- /dev/null
+++ b/openspec/specs/mcp-image-provider-integration/spec.md
@@ -0,0 +1,83 @@
+## Purpose
+
+Canonical specification for mcp-image-provider-integration requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: Pixabay image retrieval
+The system SHALL support retrieving images from Pixabay API when `PIXABAY_API_KEY` is configured.
+
+#### Scenario: Successful Pixabay image search
+- **WHEN** Pixabay is enabled in provider chain AND query is "artificial intelligence breakthrough"
+- **THEN** system sends GET request to `https://pixabay.com/api/?key={key}&q=artificial+intelligence+breakthrough&image_type=photo&per_page=3&safesearch=true`
+- **AND** returns first hit's `webformatURL` as image URL
+- **AND** returns credit as `"Photo by {user} on Pixabay"`
+
+#### Scenario: Pixabay returns no results
+- **WHEN** Pixabay search returns empty `hits` array
+- **THEN** system returns `(None, None)` for this provider
+- **AND** fallback chain continues to next provider
+
+#### Scenario: Pixabay API key not configured
+- **WHEN** `PIXABAY_API_KEY` environment variable is empty or unset
+- **THEN** Pixabay provider is skipped in the fallback chain
+
+### Requirement: Unsplash image retrieval
+The system SHALL support retrieving images from Unsplash API when `UNSPLASH_ACCESS_KEY` is configured.
+
+#### Scenario: Successful Unsplash image search
+- **WHEN** Unsplash is enabled in provider chain AND query is "machine learning robot"
+- **THEN** system sends GET request to `https://api.unsplash.com/search/photos?query=machine+learning+robot&per_page=3` with header `Authorization: Client-ID {key}`
+- **AND** returns first result's `urls.regular` as image URL
+- **AND** returns credit as `"Photo by {user.name} on Unsplash"`
+
+#### Scenario: Unsplash returns no results
+- **WHEN** Unsplash search returns empty `results` array
+- **THEN** system returns `(None, None)` for this provider
+- **AND** fallback chain continues to next provider
+
+#### Scenario: Unsplash API key not configured
+- **WHEN** `UNSPLASH_ACCESS_KEY` environment variable is empty or unset
+- **THEN** Unsplash provider is skipped in the fallback chain
+
+### Requirement: Pexels image retrieval
+The system SHALL support retrieving images from Pexels API when `PEXELS_API_KEY` is configured.
+
+#### Scenario: Successful Pexels image search
+- **WHEN** Pexels is enabled in provider chain AND query is "tech startup office"
+- **THEN** system sends GET request to `https://api.pexels.com/v1/search?query=tech+startup+office&per_page=3` with header `Authorization: {key}`
+- **AND** returns first photo's `src.large` as image URL
+- **AND** returns credit as `"Photo by {photographer} on Pexels"`
+
+#### Scenario: Pexels returns no results
+- **WHEN** Pexels search returns empty `photos` array
+- **THEN** system returns `(None, None)` for this provider
+- **AND** fallback chain continues to next provider
+
+#### Scenario: Pexels API key not configured
+- **WHEN** `PEXELS_API_KEY` environment variable is empty or unset
+- **THEN** Pexels provider is skipped in the fallback chain
+
+### Requirement: Provider timeout handling
+Each provider API call SHALL timeout after 15 seconds.
+
+#### Scenario: Provider request timeout
+- **WHEN** provider API does not respond within 15 seconds
+- **THEN** system logs timeout warning
+- **AND** returns `(None, None)` for this provider
+- **AND** fallback chain continues to next provider
+
+### Requirement: Provider error handling
+The system SHALL gracefully handle provider API errors without crashing.
+
+#### Scenario: Provider returns HTTP error
+- **WHEN** provider API returns 4xx or 5xx status code
+- **THEN** system logs error with status code
+- **AND** returns `(None, None)` for this provider
+- **AND** fallback chain continues to next provider
+
+#### Scenario: Provider returns malformed response
+- **WHEN** provider API returns invalid JSON or unexpected schema
+- **THEN** system logs parsing error
+- **AND** returns `(None, None)` for this provider
+- **AND** fallback chain continues to next provider
diff --git a/openspec/specs/modal-layout-and-loading-feedback/spec.md b/openspec/specs/modal-layout-and-loading-feedback/spec.md
new file mode 100644
index 0000000..92a5e8f
--- /dev/null
+++ b/openspec/specs/modal-layout-and-loading-feedback/spec.md
@@ -0,0 +1,37 @@
+## Purpose
+
+Canonical specification for modal-layout-and-loading-feedback requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: Modal width supports comfortable desktop reading
+The summary modal SHALL render with a desktop width that is approximately half of viewport width or larger when space allows, while remaining responsive on small screens.
+
+#### Scenario: Desktop width expansion
+- **WHEN** the modal opens on desktop viewport widths
+- **THEN** the modal content area renders wider than the previous narrow baseline
+- **AND** text blocks are readable without excessive line wrapping
+
+#### Scenario: Mobile responsiveness
+- **WHEN** the modal opens on small mobile viewport widths
+- **THEN** modal width remains fully usable without horizontal overflow
+
+### Requirement: Modal height supports near-full viewport scrolling
+The summary modal SHALL use near full-height viewport behavior when content overflows.
+
+#### Scenario: Overflowing summary content
+- **WHEN** summary content exceeds modal viewport height
+- **THEN** modal body remains scrollable with close controls accessible
+- **AND** modal container uses near full viewport height constraints
+
+### Requirement: TL;DR loading placeholder is explicit
+The modal SHALL show a horizontal shimmer placeholder for TL;DR content while TL;DR bullets are not yet available.
+
+#### Scenario: TL;DR pending state
+- **WHEN** the summary modal is open and TL;DR bullet data is pending
+- **THEN** the system displays a low-height horizontal shimmer placeholder
+
+#### Scenario: TL;DR loaded state
+- **WHEN** TL;DR bullet data becomes available
+- **THEN** shimmer placeholder is removed
+- **AND** TL;DR bullet list is rendered
diff --git a/openspec/specs/news-aggregator/spec.md b/openspec/specs/news-aggregator/spec.md
new file mode 100644
index 0000000..43a9a52
--- /dev/null
+++ b/openspec/specs/news-aggregator/spec.md
@@ -0,0 +1,58 @@
+## Purpose
+
+Canonical specification for news-aggregator requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: News aggregation via Perplexity API
+The system SHALL fetch AI news hourly from Perplexity API and store it with full attribution.
+
+#### Scenario: Hourly news fetch
+- **WHEN** the scheduled job runs every hour
+- **THEN** the system calls Perplexity API with query "latest AI news"
+- **AND** stores the response with headline, summary, source URL, and timestamp
+
+#### Scenario: API error handling
+- **WHEN** Perplexity API returns an error or timeout
+- **THEN** the system logs the error with cost tracking
+- **AND** retries with exponential backoff up to 3 times
+- **AND** falls back to OpenRouter API if `OPENROUTER_API_KEY` is configured
+- **AND** continues using cached content if all retries and fallback fail
+
+### Requirement: Featured image generation
+The system SHALL generate or fetch a relevant featured image for each news item.
+
+#### Scenario: Image acquisition
+- **WHEN** a new news item is fetched
+- **THEN** the system SHALL request a relevant image URL from Perplexity
+- **AND** download and optimize the image locally using Pillow
+- **AND** apply quality compression based on `IMAGE_QUALITY` env var (1-100, default 85)
+- **AND** store the optimized image path and original image credit/source information
+
+#### Scenario: Image optimization configuration
+- **WHEN** the system processes an image
+- **THEN** it SHALL read `IMAGE_QUALITY` from environment (default: 85)
+- **AND** apply JPEG compression at specified quality level
+- **AND** resize images exceeding 1200px width while maintaining aspect ratio
+- **AND** store optimized images in `/app/static/images/` directory
+
+#### Scenario: Image fallback
+- **WHEN** image generation fails or returns no result
+- **THEN** the system SHALL use a default ClawFort branded placeholder image
+
+### Requirement: News data persistence with retention
+The system SHALL store news items for exactly 30 days with automatic archiving.
+
+#### Scenario: News storage
+- **WHEN** a news item is fetched from Perplexity
+- **THEN** the system SHALL store it in SQLite with fields: id, headline, summary, source_url, image_url, image_credit, published_at, created_at
+- **AND** set archived=false by default
+
+#### Scenario: Automatic archiving
+- **WHEN** a nightly cleanup job runs
+- **THEN** the system SHALL mark all news items older than 30 days as archived=true
+- **AND** delete archived items older than 60 days permanently
+
+#### Scenario: Duplicate prevention
+- **WHEN** fetching news that matches an existing headline (within 24 hours)
+- **THEN** the system SHALL skip insertion to prevent duplicates
diff --git a/openspec/specs/news-image-relevance-and-fallbacks/spec.md b/openspec/specs/news-image-relevance-and-fallbacks/spec.md
new file mode 100644
index 0000000..07c5095
--- /dev/null
+++ b/openspec/specs/news-image-relevance-and-fallbacks/spec.md
@@ -0,0 +1,27 @@
+## Purpose
+
+Canonical specification for news-image-relevance-and-fallbacks requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: Image query fallback uses AI-focused defaults
+When extracted image keywords are insufficient, the system SHALL use AI-focused default fallback terms.
+
+#### Scenario: Empty keyword extraction
+- **WHEN** keyword extraction yields no usable topic keywords
+- **THEN** the system uses default fallback terms including AI-domain keywords (for example `ai`, `machine learning`, `deep learning`)
+
+### Requirement: Generic AI image fallback is guaranteed
+If provider lookups fail to return a usable summary image, the system SHALL use a generic AI-themed fallback image.
+
+#### Scenario: Provider chain failure
+- **WHEN** all configured image providers return no usable image
+- **THEN** the system assigns a generic AI fallback image URL/path for summary image
+
+### Requirement: Fallback behavior remains context-aware first
+The system SHALL attempt context-aware keyword retrieval before any generic fallback image is selected.
+
+#### Scenario: Context-aware attempt precedes fallback
+- **WHEN** summary image selection runs for a news item
+- **THEN** the system first attempts provider queries from extracted context-aware keywords
+- **AND** only falls back to generic AI image if these attempts fail
diff --git a/openspec/specs/news-structured-data/spec.md b/openspec/specs/news-structured-data/spec.md
new file mode 100644
index 0000000..e0d8614
--- /dev/null
+++ b/openspec/specs/news-structured-data/spec.md
@@ -0,0 +1,31 @@
+## Purpose
+
+Canonical specification for news-structured-data requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: Homepage publishes Newspaper structured data
+The system SHALL expose a valid JSON-LD entity of type `Newspaper` on the homepage.
+
+#### Scenario: Newspaper entity is emitted on homepage
+- **WHEN** the homepage HTML is rendered
+- **THEN** a JSON-LD script block includes an entity with `@type` set to `Newspaper`
+- **AND** the entity includes stable publisher and site identity fields
+
+#### Scenario: Newspaper entity remains language-aware
+- **WHEN** homepage content is rendered in a selected language
+- **THEN** the structured data includes language context for the active locale
+- **AND** language output stays consistent with visible content language
+
+### Requirement: Each rendered news item publishes NewsArticle structured data
+The system SHALL expose a valid JSON-LD entity of type `NewsArticle` for each rendered news item in hero and feed contexts.
+
+#### Scenario: NewsArticle entities include required semantic fields
+- **WHEN** news items are present on the homepage
+- **THEN** each `NewsArticle` entity includes headline, description, image, publication dates, and URL fields
+- **AND** publisher and author context are present for each item
+
+#### Scenario: Structured data avoids duplicate article entities
+- **WHEN** article data appears across hero and feed sections
+- **THEN** structured-data output deduplicates entities for the same article URL
+- **AND** only one canonical semantic entry remains for each unique article
diff --git a/openspec/specs/queued-image-refetch-with-backoff/spec.md b/openspec/specs/queued-image-refetch-with-backoff/spec.md
new file mode 100644
index 0000000..ce06336
--- /dev/null
+++ b/openspec/specs/queued-image-refetch-with-backoff/spec.md
@@ -0,0 +1,37 @@
+## Purpose
+
+Canonical specification for queued-image-refetch-with-backoff requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: Latest-30 queue construction
+The refetch-images command SHALL enqueue up to the latest 30 news items for processing.
+
+#### Scenario: Queue population
+- **WHEN** refetch-images is started
+- **THEN** the command loads recent news items
+- **AND** enqueues at most 30 items ordered from newest to oldest
+
+### Requirement: Sequential processing
+The image refetch queue SHALL be processed one item at a time.
+
+#### Scenario: Single-item worker behavior
+- **WHEN** queue processing runs
+- **THEN** only one queued item is processed concurrently
+- **AND** next item starts only after current item completes/fails
+
+### Requirement: Exponential backoff on transient failures
+The queue processor SHALL retry transient image-provider failures using exponential backoff.
+
+#### Scenario: Rate-limited provider response
+- **WHEN** provider call returns rate-limit or transient error
+- **THEN** command retries with exponential delay between attempts
+- **AND** stops retrying after configured max attempts
+
+### Requirement: Progress and completion reporting
+The command SHALL emit operator-readable progress and final summary output.
+
+#### Scenario: Queue progress output
+- **WHEN** queue processing is in progress
+- **THEN** the command prints per-item progress (processed/succeeded/failed)
+- **AND** prints final totals on completion
diff --git a/openspec/specs/responsive-device-agnostic-layout/spec.md b/openspec/specs/responsive-device-agnostic-layout/spec.md
new file mode 100644
index 0000000..4252b74
--- /dev/null
+++ b/openspec/specs/responsive-device-agnostic-layout/spec.md
@@ -0,0 +1,18 @@
+## Purpose
+
+Canonical specification for responsive-device-agnostic-layout requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: Core layout is device-agnostic and responsive
+The system SHALL render key surfaces (header, hero, feed, modal, footer) responsively across mobile, tablet, and desktop viewports.
+
+#### Scenario: Mobile layout behavior
+- **WHEN** a user opens the site on a mobile viewport
+- **THEN** content remains readable without horizontal overflow
+- **AND** interactive controls remain reachable and usable
+
+#### Scenario: Desktop and tablet adaptation
+- **WHEN** a user opens the site on tablet or desktop viewports
+- **THEN** layout reflows according to breakpoint design rules
+- **AND** no key content or controls are clipped
diff --git a/openspec/specs/royalty-free-image-enrichment/spec.md b/openspec/specs/royalty-free-image-enrichment/spec.md
new file mode 100644
index 0000000..d0e97d0
--- /dev/null
+++ b/openspec/specs/royalty-free-image-enrichment/spec.md
@@ -0,0 +1,26 @@
+## Purpose
+
+Canonical specification for royalty-free-image-enrichment requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: System enriches summaries with appropriate royalty-free images
+The system SHALL attach an appropriate royalty-free image to each summarized article.
+
+#### Scenario: Successful royalty-free image retrieval
+- **WHEN** summary generation succeeds for an article
+- **THEN** the system retrieves an appropriate royalty-free image for that article context
+- **AND** stores image URL and attribution metadata for rendering
+
+#### Scenario: MCP-preferred retrieval path
+- **WHEN** MCP image integration is available in runtime
+- **THEN** the system uses MCP-based retrieval as the preferred image sourcing path
+- **AND** falls back to configured non-MCP royalty-free source path when MCP retrieval fails or is unavailable
+
+### Requirement: Image retrieval failures do not block article availability
+The system SHALL remain resilient when image sourcing fails.
+
+#### Scenario: Image fallback behavior
+- **WHEN** no suitable royalty-free image can be retrieved
+- **THEN** the article summary remains available for modal display
+- **AND** UI uses configured placeholder/fallback image behavior
diff --git a/openspec/specs/seo-meta-and-social-tags/spec.md b/openspec/specs/seo-meta-and-social-tags/spec.md
new file mode 100644
index 0000000..d13ae2d
--- /dev/null
+++ b/openspec/specs/seo-meta-and-social-tags/spec.md
@@ -0,0 +1,31 @@
+## Purpose
+
+Canonical specification for seo-meta-and-social-tags requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: Core SEO metadata is present on public pages
+The system SHALL expose standards-compliant SEO metadata on the homepage and policy pages, including description, robots, canonical URL, and social preview metadata.
+
+#### Scenario: Homepage metadata baseline exists
+- **WHEN** a crawler or browser loads the homepage
+- **THEN** the document includes `description`, `robots`, and canonical metadata
+- **AND** Open Graph and Twitter card metadata fields are present with non-empty values
+
+#### Scenario: Policy pages include indexable metadata
+- **WHEN** a crawler loads `/terms` or `/attribution`
+- **THEN** the page includes page-specific `title` and `description` metadata
+- **AND** Open Graph and Twitter card metadata are present for link previews
+
+### Requirement: Canonical and preview metadata remain deterministic
+The system SHALL keep canonical and preview metadata deterministic for each route to avoid conflicting crawler signals.
+
+#### Scenario: Canonical URL reflects active route
+- **WHEN** metadata is rendered for a public route
+- **THEN** exactly one canonical link is emitted for that route
+- **AND** canonical metadata does not point to unrelated routes
+
+#### Scenario: Social preview tags map to current page context
+- **WHEN** the page metadata is generated or updated
+- **THEN** `og:title`, `og:description`, and corresponding Twitter fields reflect the current page context
+- **AND** preview image fields resolve to a valid absolute URL
diff --git a/openspec/specs/site-admin-safety-and-ergonomics/spec.md b/openspec/specs/site-admin-safety-and-ergonomics/spec.md
new file mode 100644
index 0000000..f1c0c2c
--- /dev/null
+++ b/openspec/specs/site-admin-safety-and-ergonomics/spec.md
@@ -0,0 +1,29 @@
+## Purpose
+
+Canonical specification for site-admin-safety-and-ergonomics requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: Confirmation guard for destructive commands
+Destructive admin commands SHALL require explicit confirmation before execution.
+
+#### Scenario: Missing confirmation flag
+- **WHEN** an operator runs clear-news or clean-archive without required confirmation
+- **THEN** the command exits without applying destructive changes
+- **AND** prints guidance for explicit confirmation usage
+
+### Requirement: Dry-run support where applicable
+Maintenance commands SHALL provide dry-run mode for previewing effects where feasible.
+
+#### Scenario: Dry-run preview
+- **WHEN** an operator invokes a command with dry-run mode
+- **THEN** the command reports intended actions and affected counts
+- **AND** persists no data changes
+
+### Requirement: Actionable failure summaries
+Admin commands SHALL output actionable errors and final status summaries.
+
+#### Scenario: Partial failure reporting
+- **WHEN** a maintenance command partially fails
+- **THEN** output includes succeeded/failed counts
+- **AND** includes actionable next-step guidance
diff --git a/openspec/specs/summary-analytics-tagging/spec.md b/openspec/specs/summary-analytics-tagging/spec.md
new file mode 100644
index 0000000..cc2be1f
--- /dev/null
+++ b/openspec/specs/summary-analytics-tagging/spec.md
@@ -0,0 +1,26 @@
+## Purpose
+
+Canonical specification for summary-analytics-tagging requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: Modal interactions are tagged for analytics
+The system SHALL emit Umami analytics events for summary modal open and close actions.
+
+#### Scenario: Modal open event tagging
+- **WHEN** a user opens the summary modal
+- **THEN** the system emits a modal-open Umami event
+- **AND** event payload includes article context identifier
+
+#### Scenario: Modal close event tagging
+- **WHEN** a user closes the summary modal
+- **THEN** the system emits a modal-close Umami event
+- **AND** event payload includes article context identifier when available
+
+### Requirement: Source link-out interactions are tagged for analytics
+The system SHALL emit Umami analytics events for source/citation link-outs from summary modal.
+
+#### Scenario: Source link-out event tagging
+- **WHEN** a user clicks source/citation link in summary modal
+- **THEN** the system emits a link-out Umami event before or at navigation trigger
+- **AND** event includes source URL or source identifier metadata
diff --git a/openspec/specs/summary-modal-experience/spec.md b/openspec/specs/summary-modal-experience/spec.md
new file mode 100644
index 0000000..942ebdf
--- /dev/null
+++ b/openspec/specs/summary-modal-experience/spec.md
@@ -0,0 +1,26 @@
+## Purpose
+
+Canonical specification for summary-modal-experience requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: Summary is rendered in a modal dialog using standard template
+The system SHALL render article summary content in a modal dialog using the required structure.
+
+#### Scenario: Open summary modal
+- **WHEN** a user triggers summary view for an article
+- **THEN** a modal dialog opens and displays content in this order: relevant image, TL;DR bullets, summary body, source and citation, and "Powered by Perplexity"
+- **AND** modal content corresponds to the selected article
+
+#### Scenario: Close summary modal
+- **WHEN** a user closes the modal via close control or backdrop interaction
+- **THEN** the modal is dismissed cleanly
+- **AND** user returns to previous feed context without page navigation
+
+### Requirement: Modal content preserves source link-out behavior
+The system SHALL provide source link-outs from the summary modal.
+
+#### Scenario: Source link-out from modal
+- **WHEN** a user clicks source/citation link in the modal
+- **THEN** the original source opens in a new tab/window
+- **AND** modal behavior remains stable for continued browsing
diff --git a/openspec/specs/terms-of-use-risk-disclosure/spec.md b/openspec/specs/terms-of-use-risk-disclosure/spec.md
new file mode 100644
index 0000000..46ac4b3
--- /dev/null
+++ b/openspec/specs/terms-of-use-risk-disclosure/spec.md
@@ -0,0 +1,18 @@
+## Purpose
+
+Canonical specification for terms-of-use-risk-disclosure requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: Terms page states unverified-content risk
+The system SHALL provide a Terms of Use page that states information is unverified and use is at the user’s own risk.
+
+#### Scenario: Terms page risk statement visible
+- **WHEN** a user opens the Terms of Use page
+- **THEN** the page includes clear at-own-risk usage language
+- **AND** the page states information is not independently verified
+
+#### Scenario: Terms page references source uncertainty
+- **WHEN** a user reads terms details
+- **THEN** the page explains content is surfaced from external/AI-generated sources
+- **AND** users are informed responsibility remains with their own decisions
diff --git a/openspec/specs/theme-default-system/spec.md b/openspec/specs/theme-default-system/spec.md
new file mode 100644
index 0000000..b955c52
--- /dev/null
+++ b/openspec/specs/theme-default-system/spec.md
@@ -0,0 +1,18 @@
+## Purpose
+
+Canonical specification for theme-default-system requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: System theme is default when no preference exists
+The system SHALL default to system theme behavior if no persisted theme preference is found.
+
+#### Scenario: No saved preference on first visit
+- **WHEN** a user visits the site with no stored theme value
+- **THEN** the UI resolves theme from system color-scheme preference
+- **AND** switcher indicates system mode as active
+
+#### Scenario: Persisted preference overrides system default
+- **WHEN** a user has an existing stored theme preference
+- **THEN** stored preference is applied instead of system mode
+- **AND** user-selected theme remains stable across reloads
diff --git a/openspec/specs/theme-preference-persistence/spec.md b/openspec/specs/theme-preference-persistence/spec.md
new file mode 100644
index 0000000..191b5b9
--- /dev/null
+++ b/openspec/specs/theme-preference-persistence/spec.md
@@ -0,0 +1,18 @@
+## Purpose
+
+Canonical specification for theme-preference-persistence requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: Theme choice persists across sessions
+The system SHALL persist user-selected theme with localStorage as primary storage and cookie fallback when localStorage is unavailable.
+
+#### Scenario: Persist theme in localStorage
+- **WHEN** localStorage is available and user selects a theme
+- **THEN** selected theme is saved in localStorage
+- **AND** stored value is used on next visit in same browser
+
+#### Scenario: Cookie fallback persistence
+- **WHEN** localStorage is unavailable or blocked
+- **THEN** selected theme is saved in cookie storage
+- **AND** cookie value is used to restore theme on return visit
diff --git a/openspec/specs/theme-switcher-control/spec.md b/openspec/specs/theme-switcher-control/spec.md
new file mode 100644
index 0000000..1aea970
--- /dev/null
+++ b/openspec/specs/theme-switcher-control/spec.md
@@ -0,0 +1,18 @@
+## Purpose
+
+Canonical specification for theme-switcher-control requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: Header provides icon-based theme switcher
+The system SHALL display a theme switcher in the top-right header area with icon controls for system, light, dark, and high-contrast modes.
+
+#### Scenario: Theme options visible as icons
+- **WHEN** a user views the header
+- **THEN** all four theme options are represented by distinct icons
+- **AND** each option is keyboard-accessible and screen-reader labeled
+
+#### Scenario: Theme selection applies immediately
+- **WHEN** a user selects a theme option
+- **THEN** the page updates visual theme without full page reload
+- **AND** selected option has a visible active state
diff --git a/openspec/specs/wcag-2-2-aa-accessibility/spec.md b/openspec/specs/wcag-2-2-aa-accessibility/spec.md
new file mode 100644
index 0000000..906eebc
--- /dev/null
+++ b/openspec/specs/wcag-2-2-aa-accessibility/spec.md
@@ -0,0 +1,18 @@
+## Purpose
+
+Canonical specification for wcag-2-2-aa-accessibility requirements synced from OpenSpec change deltas.
+
+## Requirements
+
+### Requirement: Core user flows comply with WCAG 2.2 AA baseline
+The system SHALL meet WCAG 2.2 AA accessibility requirements for primary interactions and content presentation.
+
+#### Scenario: Keyboard-only interaction flow
+- **WHEN** a keyboard-only user navigates the page
+- **THEN** all primary interactive elements are reachable and operable
+- **AND** visible focus indication is present at each step
+
+#### Scenario: Contrast and non-text alternatives
+- **WHEN** users consume text and non-text UI content
+- **THEN** color contrast meets AA thresholds for relevant text and controls
+- **AND** meaningful images and controls include accessible labels/alternatives