Slack has no native table support, so Markdown tables are passed
through verbatim by slackify-markdown. Pre-process tables into
readable key-value rows before converting to mrkdwn.
Assisted-by: Claude 4.6 Opus (Anthropic)
Replace the regex-based Markdown-to-Slack converter with the
slackify-markdown library, which uses a proper Markdown parser
(markdown-it-py, already a dependency) to correctly handle headings,
bold/italic, code blocks, links, bullet lists, and strikethrough.
The regex approach didn't handle headings (###), bullet lists (* ),
or code block protection, causing raw Markdown to leak into Slack
messages.
Net -40 lines.
Assisted-by: Claude 4.6 Opus (Anthropic)
- Added _split_message() helper for cleaner separation of concerns
- Simplified send() method by using the helper
- Net -18 lines for the message splitting feature
Telegram has a 4096 character limit per message. This fix:
- Splits messages longer than 4000 chars into multiple chunks
- Prefers breaking at newline boundaries to preserve formatting
- Falls back to space boundaries if no newlines available
- Forces split at max length if no good boundaries exist
- Adds comprehensive tests for message splitting logic
Add SiliconFlow (硅基流动) as an OpenAI-compatible gateway provider.
SiliconFlow hosts multiple models (Qwen, DeepSeek, etc.) via an
OpenAI-compatible API at https://api.siliconflow.cn/v1.
Changes:
- Add ProviderSpec for siliconflow in providers/registry.py
- Add siliconflow field to ProvidersConfig in config/schema.py
Co-authored-by: Cursor <cursoragent@cursor.com>
Newly added the _extract_post_text function to extract plain text content from Feishu rich text messages, supporting the parsing of titles, text, links, and @mentions.
With tz: Use the specified timezone (e.g., "Asia/Shanghai").
Without tz: Use the local timezone (datetime.now().astimezone().tzinfo) instead of defaulting to UTC
