Restore dropped regression fixes

routes/cookbook_routes.py

@@ -1219,6 +1219,12 @@ def setup_cookbook_routes() -> APIRouter:
             # pip cache so they don't fail mid-build with "No space left" (#1219)
             # and leave the dep installed-but-unusable (#1459).
             req.cmd = _pip_install_no_cache(req.cmd)
+            # Accept common aliases and enforce server extras for llama-cpp so
+            # `python -m llama_cpp.server` has all runtime dependencies.
+            req.cmd = re.sub(r"(?<![A-Za-z0-9_.-])llama_cpp(?![A-Za-z0-9_.-])", "llama-cpp-python[server]", req.cmd)
+            req.cmd = re.sub(r"(?<![A-Za-z0-9_.-])llama-cpp-python(?!\[)", "llama-cpp-python[server]", req.cmd)
+            if "llama-cpp-python" in req.cmd and "--extra-index-url" not in req.cmd:
+                req.cmd += " --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu"
             # PEP-508-style package spec — letters, digits, `.-_` for the
             # name; `[` `]` for extras; `<>=!~,` for version specifiers.
             # v2 review HIGH-14: tightened from the previous regex which

routes/model_routes.py

@@ -503,6 +503,24 @@ def _is_chat_model(model_id: str) -> bool:
     return True
 
 
+def _delete_orphaned_provider_auth(db, auth_id: Optional[str], exclude_ep_id: Optional[str] = None) -> bool:
+    """Delete a ProviderAuthSession once no endpoint still references it."""
+    if not auth_id:
+        return False
+    from core.database import ProviderAuthSession
+    still_referenced = db.query(ModelEndpoint.id).filter(
+        ModelEndpoint.provider_auth_id == auth_id,
+        ModelEndpoint.id != exclude_ep_id,
+    ).first()
+    if still_referenced is not None:
+        return False
+    auth_row = db.query(ProviderAuthSession).filter(ProviderAuthSession.id == auth_id).first()
+    if auth_row is None:
+        return False
+    db.delete(auth_row)
+    return True
+
+
 def _safe_detect_provider(base_url: str) -> str:
     """Best-effort provider detection that must not break endpoint probing."""
     try:
@@ -2173,7 +2191,9 @@ def setup_model_routes(model_discovery):
             cleared_user_preferences = _clear_user_prefs_for_endpoint(ep_id)
             cleared_sessions = _clear_sessions_for_endpoint(db, ep.base_url)
             cleared_loaded_sessions = _clear_loaded_sessions_for_endpoint(ep.base_url)
+            auth_id = getattr(ep, "provider_auth_id", None)
             db.delete(ep)
+            cleared_provider_auth = _delete_orphaned_provider_auth(db, auth_id, exclude_ep_id=ep_id)
             db.commit()
             _invalidate_models_cache()
             _local_probe_cache["data"] = None
@@ -2183,6 +2203,7 @@ def setup_model_routes(model_discovery):
                 "cleared_user_preferences": cleared_user_preferences,
                 "cleared_sessions": cleared_sessions,
                 "cleared_loaded_sessions": cleared_loaded_sessions,
+                "cleared_provider_auth": cleared_provider_auth,
             }
         finally:
             db.close()