Add phase 4: AI cleanup and photo/text import via OpenAI

- recipes/ai.py: Chat Completions with strict JSON schema (Structured
  Outputs), Pydantic re-validation, plausibility clamping, prompt treats
  input as data only
- "Mit KI aufbereiten" on create/edit form returns an editable draft
- Import page: photo/screenshot (vision, downscaled JPEG, not stored) and
  pasted text; drafts pre-fill the recipe form with a preview
- Clear UI messages for timeout, rate limit, quota, auth, model and
  connection errors; without OPENAI_API_KEY AI features show a notice
- Optional per-user and global daily AI limits (default unlimited)
- Tests for response parsing, schema strictness, error mapping, views

Co-Authored-By: Claude Opus 5.5 <[email protected]>

config/settings.py

@@ -92,6 +92,7 @@ TEMPLATES = [
                 "django.template.context_processors.request",
                 "django.contrib.auth.context_processors.auth",
                 "django.contrib.messages.context_processors.messages",
+                "recipes.context_processors.ai_status",
             ],
         },
     },
@@ -142,6 +143,16 @@ COMMENT_RATE_LIMIT_PER_HOUR = env_int("COMMENT_RATE_LIMIT_PER_HOUR", 30)
 # Request body limit for non-file fields; files are limited per image above.
 DATA_UPLOAD_MAX_MEMORY_SIZE = 5 * 1024 * 1024
 
+# --- AI (OpenAI) -------------------------------------------------------------------
+OPENAI_API_KEY = env("OPENAI_API_KEY")
+OPENAI_MODEL = env("OPENAI_MODEL", "gpt-5-mini")
+# For reasoning models (gpt-5*, o*): minimal|low|medium|high. Leave empty for other models.
+OPENAI_REASONING_EFFORT = env("OPENAI_REASONING_EFFORT", "low")
+OPENAI_TIMEOUT = env_int("OPENAI_TIMEOUT", 90)
+# 0 = unlimited (default). Counted per call, including failed ones.
+AI_RATE_LIMIT_PER_USER_PER_DAY = env_int("AI_RATE_LIMIT_PER_USER_PER_DAY", 0)
+AI_RATE_LIMIT_GLOBAL_PER_DAY = env_int("AI_RATE_LIMIT_GLOBAL_PER_DAY", 0)
+
 INVITATION_VALID_DAYS = 7
 PASSWORD_RESET_VALID_HOURS = 24