Wrap each Telegram initialize() attempt in asyncio.wait_for(HERMES_TELEGRAM_INIT_TIMEOUT, default 30s). When api.telegram.org and all fallback IPs are unreachable, the connect chain has no outer bound, so a single initialize() blocks for minutes and the retry-on-exception loop never fires — the gateway appears to hang after the banner. The timeout guarantees each attempt is bounded, then retries with backoff, then fails with an actionable error. Also adds WARNING-level progress logs before DoH discovery and each connect attempt (visible at default log level). Salvaged onto plugins/platforms/telegram/adapter.py (Telegram moved from gateway/platforms/ since the PR was opened). Adds env var to docs + AUTHOR_MAP. Co-authored-by: Hermes Agent <127238744+teknium1@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| _category_.json | ||
| automation-blueprints-catalog.mdx | ||
| cli-commands.md | ||
| environment-variables.md | ||
| faq.md | ||
| mcp-config-reference.md | ||
| model-catalog.md | ||
| optional-skills-catalog.md | ||
| profile-commands.md | ||
| skills-catalog.md | ||
| slash-commands.md | ||
| tools-reference.md | ||
| toolsets-reference.md | ||