feat(channel): stream LLM responses to Telegram via draft message edits

Wire the existing provider-layer streaming infrastructure through the
channel trait and agent loop so Telegram users see tokens arrive
progressively via editMessageText, instead of waiting for the full
response.

Changes:
- Add StreamMode enum (off/partial/block) and draft_update_interval_ms
  to TelegramConfig (backward-compatible defaults: off, 1000ms)
- Add supports_draft_updates/send_draft/update_draft/finalize_draft to
  Channel trait with no-op defaults (zero impact on existing channels)
- Implement draft methods on TelegramChannel using sendMessage +
  editMessageText with rate limiting and Markdown fallback
- Add on_delta mpsc::Sender<String> parameter to run_tool_call_loop
  (None preserves existing behavior)
- Wire streaming in process_channel_message: when channel supports
  drafts, send initial draft, spawn updater task, finalize on completion

Edge cases handled:
- 4096-char limit: finalize draft and fall back to chunked send
- Broken Markdown: use no parse_mode during streaming, apply on finalize
- Edit failures: fall back to sending complete response as new message
- Rate limiting: configurable draft_update_interval_ms (default 1s)

src/onboard/wizard.rs

@@ -1,4 +1,4 @@
-use crate::config::schema::{DingTalkConfig, IrcConfig, QQConfig, WhatsAppConfig};
+use crate::config::schema::{DingTalkConfig, IrcConfig, QQConfig, StreamMode, WhatsAppConfig};
 use crate::config::{
     AutonomyConfig, BrowserConfig, ChannelsConfig, ComposioConfig, Config, DiscordConfig,
     HeartbeatConfig, IMessageConfig, MatrixConfig, MemoryConfig, ObservabilityConfig,
@@ -2665,6 +2665,8 @@ fn setup_channels() -> Result<ChannelsConfig> {
                 config.telegram = Some(TelegramConfig {
                     bot_token: token,
                     allowed_users,
+                    stream_mode: StreamMode::default(),
+                    draft_update_interval_ms: 1000,
                 });
             }
             1 => {