feat: show thinking content

.env.example

@@ -104,6 +104,10 @@ OPENCODE_MODEL_ID=big-pickle
 # Hide thinking indicator messages (default: false)
 # HIDE_THINKING_MESSAGES=false
 
+# Show full model reasoning in the thinking message (default: false)
+# Uses RESPONSE_STREAMING_MODE for edit vs draft streaming. Ignored when HIDE_THINKING_MESSAGES=true.
+# SHOW_THINKING_CONTENT=false
+
 # Hide tool call service messages (default: false)
 # HIDE_TOOL_CALL_MESSAGES=false
 

PRODUCT.md

@@ -59,7 +59,7 @@ No public inbound ports are required for normal usage.
 ### Result delivery
 
 - Send each completed assistant response after completion signal from SSE
-- Do not expose raw chain-of-thought; send a lightweight thinking indicator instead
+- Hide full model reasoning by default; optionally stream it in the thinking message when explicitly enabled
 - Split long responses into multiple Telegram messages
 - Send code updates as files (size-limited)
 
@@ -86,6 +86,7 @@ No public inbound ports are required for normal usage.
 - Configurable scheduled task limit (default: 10)
 - Configurable bot locale
 - Configurable visibility for service messages (thinking/tool calls)
+- Configurable opt-in display of full thinking/reasoning content
 - Configurable max code file size in KB (default: 100)
 - Optional STT settings for voice transcription (`STT_API_URL`, `STT_API_KEY`, `STT_MODEL`, `STT_LANGUAGE`)
 - Optional TTS settings for global audio replies (`TTS_PROVIDER`, `TTS_API_URL`, `TTS_API_KEY`, `TTS_MODEL`, `TTS_VOICE`)

README.md

@@ -231,6 +231,7 @@ When installed via npm, the configuration wizard handles the initial setup. The
 | `BASH_TOOL_DISPLAY_MAX_LENGTH`             | Maximum displayed length for `bash` tool commands in Telegram summaries; longer commands are truncated                |    No    | `128`                    |
 | `SERVICE_MESSAGES_INTERVAL_SEC`            | Service messages interval (thinking + tool calls); keep `>=2` to avoid Telegram rate limits, `0` = immediate          |    No    | `5`                      |
 | `HIDE_THINKING_MESSAGES`                   | Hide `💭 Thinking...` service messages                                                                                |    No    | `false`                  |
+| `SHOW_THINKING_CONTENT`                    | Show full model reasoning in the thinking message; uses `RESPONSE_STREAMING_MODE` for edit vs draft streaming         |    No    | `false`                  |
 | `HIDE_TOOL_CALL_MESSAGES`                  | Hide tool-call service messages (`💻 bash ...`, `📖 read ...`, etc.)                                                  |    No    | `false`                  |
 | `HIDE_TOOL_FILE_MESSAGES`                  | Hide file edit documents sent as `.txt` attachments (`edit_*.txt`, `write_*.txt`)                                     |    No    | `false`                  |
 | `TRACK_BACKGROUND_SESSIONS`                | Track detached/non-current sessions in the current selected project/worktree and send short notifications             |    No    | `true`                   |