Add OPENAI_BASE_URL and end-to-end AI tests through the SDK

- Optional OPENAI_BASE_URL for OpenAI-compatible endpoints or proxies
- Tests run the real openai SDK against a local stub server: request
  shape (model, auth, strict json_schema), text cleanup, photo import
  and an authentication error mapped to the UI message

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

config/settings.py

@@ -149,6 +149,8 @@ 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)
+# Optional: OpenAI-compatible endpoint or proxy (default: api.openai.com)
+OPENAI_BASE_URL = env("OPENAI_BASE_URL")
 # 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)

config/settings_test.py

@@ -22,6 +22,7 @@ import ipaddress  # noqa: E402
 OPENAI_API_KEY = ""
 OPENAI_MODEL = "gpt-5-mini"
 OPENAI_REASONING_EFFORT = "low"
+OPENAI_BASE_URL = ""
 AI_RATE_LIMIT_PER_USER_PER_DAY = 0
 AI_RATE_LIMIT_GLOBAL_PER_DAY = 0
 COMMENT_RATE_LIMIT_PER_HOUR = 30