You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
-**Voice prompts** — send voice/audio messages, transcribe them via a Whisper-compatible API, then forward recognized text to OpenCode
29
29
-**Context control** — compact context when it gets too large, right from the chat
30
30
-**Input flow control** — when an interactive flow is active, the bot accepts only relevant input to keep context consistent and avoid accidental actions
31
+
-**Configurable reply formatting** — assistant replies use Telegram MarkdownV2 by default, with optional raw mode (`MESSAGE_FORMAT_MODE=markdown|raw`)
31
32
-**Security** — strict user ID whitelist; no one else can access your bot, even if they find it
32
33
-**Localization** — English and Russian UI (`BOT_LOCALE=en|ru`)
33
34
@@ -134,6 +135,7 @@ When installed via npm, the configuration wizard handles the initial setup. The
134
135
|`SERVICE_MESSAGES_INTERVAL_SEC`| Service messages interval (thinking + tool calls); keep `>=2` to avoid Telegram rate limits, `0` = immediate | No |`5`|
135
136
|`HIDE_THINKING_MESSAGES`| Hide `💭 Thinking...` service messages | No |`false`|
136
137
|`HIDE_TOOL_CALL_MESSAGES`| Hide tool-call service messages (`💻 bash ...`, `📖 read ...`, etc.) | No |`false`|
138
+
|`MESSAGE_FORMAT_MODE`| Assistant reply formatting mode: `markdown` (Telegram MarkdownV2) or `raw`| No |`markdown`|
137
139
|`CODE_FILE_MAX_SIZE_KB`| Max file size (KB) to send as document | No |`100`|
138
140
|`STT_API_URL`| Whisper-compatible API base URL (enables voice/audio transcription) | No | — |
139
141
|`STT_API_KEY`| API key for your STT provider | No | — |
0 commit comments