Set the OpenAI-compatible endpoint from the settings panel

Pointing OPENAI_BASE_URL at a local llama-server or Ollama sends every gpt-* call there instead of to OpenAI, and litellm reports that as a bare "Connection Error" — which reads like a network problem even though the host can reach api.openai.com fine. Deploying a .env that still carries the local endpoint reproduces it on the server, with nothing in the message naming the culprit. Add OPENAI_BASE_URL and OPENAI_API_BASE to the settings allowlist so the endpoint can be corrected without editing .env and recreating the container. Both are listed because litellm reads OPENAI_API_BASE while the OpenAI SDK reads OPENAI_BASE_URL, so fixing one can leave the other in effect. Neither is a secret, so the panel shows the current value. No cache invalidation is needed alongside this: litellm keys its client cache on the endpoint, so a changed value takes effect on the next call. Document the trap where it will be read — a commented template in .env.example and a note in the Lightsail deploy guide about carrying a local .env over. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-23 23:12:34 +09:00
parent 904458e7df
commit 1b88d23f21
6 changed files with 27 additions and 2 deletions
@@ -146,6 +146,7 @@ LLM に渡すコンテキストは `app/core/memory_kb/memory.py` の `get_conte
 | `CORS_ORIGINS` | `http://localhost:5173` | 許可する CORS オリジン |
 | `DEBUG` | `false` | LiteLLM デバッグログの有効化 |
 | `OPENAI_API_KEY` | — | OpenAI API キー |
+| `OPENAI_API_BASE` / `OPENAI_BASE_URL` | — | OpenAI 互換エンドポイントの接続先（ローカルの llama-server / Ollama 用）。設定したままだと `gpt-*` を選んでも本家 OpenAI に繋がらない。GUI 設定画面から実行時変更可 |
 | `ANTHROPIC_API_KEY` | — | Anthropic API キー |
 | `OLLAMA_API_BASE` | `http://localhost:11434` | Ollama エンドポイント |
 | `NOTES_TOOL_CONTENT_LIMIT` | `4000` | `read_note` が 1 回に返す本文の最大文字数 |