feat: add seo_meta service for AI-generated SEO metadata with CLI management and database layer

Implement a new `SeoMetaService` subservice that generates clean SEO title/description/keywords for published content items, distinct from the existing SEO diagnostics auditor. Add `seo_metadata` polymorphic table with soft-delete support, batch query methods, and usage tracking. Extend the CLI with `seo-meta prune` and `seo-meta clear` commands for job row lifecycle management. Wire `schedule_seo_meta_for_table` into content creation and editing flows in `content.py`. Document the new service in `AGENTS.md` and `README.md`, including the `extra_head` site setting for custom `<head>` injection.
2026-06-19 20:15:22 +00:00
parent 426d3639c6
commit d10f1af118
51 changed files with 2262 additions and 93 deletions
@@ -16,6 +16,7 @@ logger = logging.getLogger(__name__)

 EMBED_TIMEOUT_SECONDS = 60.0
 LOCAL_EMBED_DIMS = 256
+EMBED_CACHE_MAX = 5000
 TOKEN_PATTERN = re.compile(r"[a-z0-9]+")


@@ -26,10 +27,18 @@ class EmbedResult:
    latency_ms: int = 0
    cache_hits: int = 0

+    @property
+    def dims(self) -> int:
+        for vector in self.vectors:
+            if vector:
+                return len(vector)
+        return 0
+

@dataclass
 class EmbeddingCache:
    store: dict[str, list[float]] = field(default_factory=dict)
+    max_entries: int = EMBED_CACHE_MAX

    def key(self, text: str) -> str:
        return hashlib.sha1((text or "").encode("utf-8")).hexdigest()
@@ -38,8 +47,11 @@ class EmbeddingCache:
        return self.store.get(self.key(text))

    def put(self, text: str, vector: list[float]) -> None:
-        if vector:
-            self.store[self.key(text)] = vector
+        if not vector:
+            return
+        if len(self.store) >= self.max_entries:
+            self.store.pop(next(iter(self.store)), None)
+        self.store[self.key(text)] = vector


 def _local_vector(text: str) -> list[float]: