fix: pass editorial brief to LLM prompt + improve missing API key error

- Add 'brief' field to GenerateContentRequest schema
- Pass brief from router to generate_post_text service
- Inject brief as mandatory instructions in LLM prompt with highest priority
- Return structured error when LLM provider/API key not configured
- Show dedicated warning banner with link to Settings when API key missing

Fixes: content ignoring editorial brief, unhelpful API key error messages

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

backend/app/routers/content.py

@@ -78,9 +78,21 @@ def generate_content(
     model = request.model or _get_setting(db, "llm_model", current_user.id)
 
     if not provider_name:
-        raise HTTPException(status_code=400, detail="LLM provider not configured. Set 'llm_provider' in settings.")
+        raise HTTPException(
+            status_code=400,
+            detail={
+                "message": "Provider AI non configurato. Vai in Impostazioni → Provider AI per scegliere il provider e inserire la API key.",
+                "missing_settings": True,
+            },
+        )
     if not api_key:
-        raise HTTPException(status_code=400, detail="LLM API key not configured. Set 'llm_api_key' in settings.")
+        raise HTTPException(
+            status_code=400,
+            detail={
+                "message": "API key non configurata. Vai in Impostazioni → Provider AI per inserire la tua API key.",
+                "missing_settings": True,
+            },
+        )
 
     # Build character dict for content service
     char_dict = {
@@ -98,6 +110,7 @@ def generate_content(
         llm_provider=llm,
         platform=request.effective_platform,
         topic_hint=request.topic_hint,
+        brief=request.brief,
     )
 
     # Generate hashtags

backend/app/schemas.py

@@ -108,6 +108,7 @@ class GenerateContentRequest(BaseModel):
     platforms: List[str] = []              # new: multi-platform (overrides platform if non-empty)
     content_types: List[str] = []          # new: multi-type (overrides content_type if non-empty)
     topic_hint: Optional[str] = None
+    brief: Optional[str] = None           # editorial brief: technique + instructions for the LLM
     include_affiliates: bool = True
     provider: Optional[str] = None
     model: Optional[str] = None

backend/app/services/content.py

@@ -15,6 +15,7 @@ def generate_post_text(
     llm_provider: LLMProvider,
     platform: str,
     topic_hint: str | None = None,
+    brief: str | None = None,
 ) -> str:
     """Generate social media post text based on a character profile.
 
@@ -23,6 +24,7 @@ def generate_post_text(
         topic_hint: Optional topic suggestion to guide generation.
         llm_provider: LLM provider instance for text generation.
         platform: Target platform (e.g. 'instagram', 'facebook', 'tiktok', 'youtube').
+        brief: Optional editorial brief with narrative technique and detailed instructions.
 
     Returns:
         Generated post text as a string.
@@ -78,8 +80,17 @@ def generate_post_text(
     if topic_hint:
         topic_instruction = f" The post should be about: {topic_hint}."
 
+    # Brief is the highest-priority instruction — it overrides defaults
+    brief_instruction = ""
+    if brief:
+        brief_instruction = (
+            f"\n\nISRUZIONI OBBLIGATORIE DAL BRIEF EDITORIALE:\n{brief}\n"
+            f"Rispetta TUTTE le istruzioni del brief. "
+            f"Il brief ha priorità su qualsiasi altra indicazione."
+        )
+
     prompt = (
-        f"{guidance}{topic_instruction}\n\n"
+        f"{guidance}{topic_instruction}{brief_instruction}\n\n"
         f"Write the post now. Output ONLY the post text, nothing else."
     )