docs: Dokumentation an aktuellen Code-Stand anpassen

- agents-Tabelle: use_auto_context, use_github_search, use_serper_search ergänzt
- api_keys-Tabelle: is_public, refresh_token, access_token_expires_at, oauth_provider ergänzt
- scanned_keys-Tabelle: source, type Spalten ergänzt
- scanner_logs-Tabelle: nicht-existierende details-Spalte entfernt
- models_cache.json: OpenAI als vierten Provider ergänzt
- Internal-Endpunkt: POST /api/chat/choice-respond dokumentiert

ARCHITECTURE.md

@@ -311,7 +311,7 @@ gott/
         ├── images/               # Krea-generierte Bilder
         ├── models/               # ONNX-Modelle (Embedding)
         │   └── all-MiniLM-L6-v2/ # Sentence-Embedding-Modell (model.onnx + vocab.txt)
-        ├── models_cache.json     # Gecachte Provider-Modelle (Nvidia, Pollinations, Gemini)
+        ├── models_cache.json     # Gecachte Provider-Modelle (Nvidia, Pollinations, Gemini, OpenAI)
         ├── logs/                 # Payload-Logs (optional)
         └── backup/               # Backup-Archive
 ```
@@ -347,7 +347,7 @@ TelegramBot (1) ─── (*) Session  (via telegram_bot_id)
 |-------------------|-----------------------------------------------------|
 | `users`           | Benutzer (username, password_hash, display_name, is_admin, persona, settings, default_path) |
 | `tokens`          | Auth-Tokens (token → user_id)                       |
-| `agents`          | AI-Agenten (model – z.B. `claude-sonnet-4-6` oder `nvidia:deepseek-ai/deepseek-r1`, custom_commands, auto_commit, use_soul/identity/user_info/memory, use_web_search, web_search_version, allow_user_choice, task_instruction, avatar_scale/offset, avatar_small, is_public) |
+| `agents`          | AI-Agenten (model – z.B. `claude-sonnet-4-6` oder `nvidia:deepseek-ai/deepseek-r1`, custom_commands, auto_commit, use_soul/identity/user_info/memory/auto_context, use_github_search, use_serper_search, use_web_search, web_search_version, allow_user_choice, task_instruction, avatar_scale/offset, avatar_small, is_public) |
 | `sessions`        | Chat-Sessions (description, image, image_small, workspace, context, custom_commands, telegram_bot_id, telegram_chat_id, avatar_scale/offset, preparer_agent_id, review_agent_id, max_review_iterations, finalizer_agent_id) |
 | `chains`          | Request-Chains (model, tokens, iterations, timing, tool_choice, tool_names, stream_error_info, plan_mode, archive_id) |
 | `messages`        | Einzelne Nachrichten (text, tool_use, tool_result, error, web_search_result), Tag für Sub-Agent-Markierung oder Import-Herkunft (`openclaw-import`), SortKey für korrekte Reihenfolge, thought_signature (Gemini) |
@@ -357,10 +357,10 @@ TelegramBot (1) ─── (*) Session  (via telegram_bot_id)
 | `cronjobs`        | Geplante Tasks (cron expression, prompt, notify_session_id, is_enabled, last_run, next_run) |
 | `shared_messages` | Geteilte Nachrichten (Share-Token, Ablaufdatum)     |
 | `telegram_bots`   | Telegram Bots (bot_token, webhook_secret, name, is_public) – eigenständige Entität |
-| `api_keys`        | API-Keys (key_id, provider, name, api_key, is_active, status, plan, usage_7d, usage_5h, source_url, checked_at) – mehrere Keys pro Provider möglich, Zuweisung pro Agent über `agent_api_keys` |
+| `api_keys`        | API-Keys (key_id, provider, name, api_key, is_active, status, plan, usage_7d, usage_5h, source_url, checked_at, is_public, refresh_token, access_token_expires_at, oauth_provider) – mehrere Keys pro Provider möglich, Zuweisung pro Agent über `agent_api_keys` |
 | `agent_api_keys`  | API-Key-Zuweisung pro User+Agent (user_id, agent_id, key_id) – ersetzt globales `users.selected_api_key_id` |
-| `scanned_keys`    | Gescannte GitHub-Keys (scanned_key_id, api_key, source_url, status, plan, usage_7d, usage_5h, adopted_api_key_id, deleted) |
-| `scanner_logs`    | Scanner-Logs (timestamp, type, message, scanner, details) – Logs von Key-Scanner und Event-Scanner |
+| `scanned_keys`    | Gescannte GitHub-Keys (scanned_key_id, api_key, source_url, source, type, status, plan, usage_7d, usage_5h, adopted_api_key_id, deleted) |
+| `scanner_logs`    | Scanner-Logs (timestamp, type, message, scanner) – Logs von Key-Scanner und Event-Scanner |
 | `server_settings` | Server-Settings (key, value, type) – In-Memory-Cache über `ServerSettingsService` |
 | `message_embeddings` | Sentence-Embeddings für semantische Suche (message_id, vector BLOB, session_id, agent_id) |
 | `memory_file_embeddings` | Embeddings von Memory-Dateien (agent_id, file_path, chunk_index, vector BLOB) |