kimi-bridge v0.4.1
What's changed
- Agent-driven setup: new INSTALL_AI.md — an interview-driven setup decision tree for coding agents ("Read INSTALL_AI.md and help me configure kimi-bridge"), with external-first handoffs to official docs and hardcoded bridge-specific requirements (Feishu scopes/events/publish, per-platform ID discovery, doctor output vocabulary, smoke-test contract) in #31, closing #29
- New
kimi-bridge compatcommand: reports whether an installed or given Kimi Code version is tested with this bridge and which bridge releases tested it, backed by a packaged compatibility map in #31 - Telegram now logs non-allowlisted sender IDs with copy-paste guidance, matching Feishu and QQ in #31
- Startup failures (auth, config, state) render as one clean line instead of a traceback; the auth guidance covers both
/loginOAuth and own-provider configuration in #31 kimi-bridge doctorwarns on unknown configuration keys instead of silently ignoring typos in #31- README quick start leads with the agent-driven path; platform credential walkthroughs consolidated into INSTALL_AI.md in #31
- Support kimi-code 0.29.2 in #30
Full Changelog: v0.4.0...v0.4.1