Expand AI insight: fix broken competitor query, add continuity, 30-day horizon, holidays

- Fix gather_competitor_data() tier filter: it queried tier IN ('primary','secondary'),
  values that never exist (real values are 'own'/'competitor'/'market'), so the
  cheapest-competitor comparison has always silently returned nothing.
- Feed the previous insight back into the prompt so the model can note what's
  changed/resolved instead of repeating itself.
- Extend forecast horizon from 14 to 30 days; add a per-day revenue table
  alongside the existing occupancy table.
- Annotate the occupancy table with UK (England) bank holidays.
- Add a same-channel market-movement section (B.com vs B.com, rack vs rack)
  diffing rates against the last insight's snapshot, threshold £3.
- Add a parsed headline field + insight history list on the Dashboard,
  collapsed to headline/age and expandable to full content.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

backend/api/ai_insights.py

@@ -28,7 +28,7 @@ async def get_latest_insight(
     """Get the most recent AI insight for the dashboard card."""
     result = await db.execute(
         text("""
-            SELECT id, generated_at, insight_type, content, model,
+            SELECT id, generated_at, insight_type, headline, content, model,
                    input_tokens, output_tokens, triggered_by
             FROM ai_insights
             ORDER BY generated_at DESC
@@ -43,6 +43,7 @@ async def get_latest_insight(
         "id": row.id,
         "generated_at": row.generated_at.isoformat(),
         "insight_type": row.insight_type,
+        "headline": row.headline,
         "content": row.content,
         "model": row.model,
         "input_tokens": row.input_tokens,
@@ -61,7 +62,7 @@ async def get_insight_history(
     """Get historical AI insights with pagination."""
     result = await db.execute(
         text("""
-            SELECT id, generated_at, insight_type, content, model,
+            SELECT id, generated_at, insight_type, headline, content, model,
                    input_tokens, output_tokens, triggered_by
             FROM ai_insights
             ORDER BY generated_at DESC
@@ -79,6 +80,7 @@ async def get_insight_history(
             "id": row.id,
             "generated_at": row.generated_at.isoformat(),
             "insight_type": row.insight_type,
+            "headline": row.headline,
             "content": row.content,
             "model": row.model,
             "input_tokens": row.input_tokens,
@@ -166,6 +168,7 @@ async def generate_insight_manual(
         return {
             "success": True,
             "content": result["content"],
+            "headline": result.get("headline"),
             "input_tokens": result["input_tokens"],
             "output_tokens": result["output_tokens"],
             "model": result["model"],

backend/api/config.py

@@ -1223,7 +1223,7 @@ class AIInsightsSettingsResponse(BaseModel):
     api_key_set: bool = False
     model: str = "claude-haiku-4-5-20251001"
     schedule_time: str = "07:15"
-    daily_token_budget: int = 5000
+    daily_token_budget: int = 12000
 
 
 class AIInsightsSettingsUpdate(BaseModel):
@@ -1258,7 +1258,7 @@ async def get_ai_insights_settings(
         api_key_set=config.get('_api_key_set', False),
         model=config.get('ai_insights_model', 'claude-haiku-4-5-20251001'),
         schedule_time=config.get('ai_insights_schedule_time', '07:15'),
-        daily_token_budget=int(config.get('ai_insights_daily_token_budget', '5000')),
+        daily_token_budget=int(config.get('ai_insights_daily_token_budget', '12000')),
     )