Releases: Mtrya/kimi-bridge
Releases · Mtrya/kimi-bridge
Release list
kimi-bridge v0.5.2
What's Changed
- Prepare kimi-bridge 0.5.2 for Kimi Code 0.33.0 by @github-actions[bot] in #63
Full Changelog: v0.5.1...v0.5.2
kimi-bridge v0.5.1
What's Changed
- Prepare kimi-bridge 0.5.1 for Kimi Code 0.32.0 by @github-actions[bot] in #62
Full Changelog: v0.5.0...v0.5.1
kimi-bridge v0.5.0
What's changed
- Add arbitrary QQ outbound file delivery in #59.
- Add layered inbound voice transcription for QQ and Feishu, including configurable multipart or JSON/base64 external ASR, in #60.
Full changelog: v0.4.6...v0.5.0
kimi-bridge v0.4.6
What's Changed
- Prepare kimi-bridge 0.4.6 for Kimi Code 0.31.1 by @github-actions[bot] in #55
Full Changelog: v0.4.5...v0.4.6
kimi-bridge v0.4.5
What's Changed
- Prepare kimi-bridge 0.4.5 for Kimi Code 0.31.0 by @github-actions[bot] in #54
Full Changelog: v0.4.4...v0.4.5
kimi-bridge v0.4.4
kimi-bridge v0.4.3
What's Changed
- Prepare kimi-bridge 0.4.3 for Kimi Code 0.30.0 by @github-actions[bot] in #35
- Fix compatibility tests and remove meta-tests by @Mtrya in #36
- Clarify compatibility workflows and stabilize CI gate by @Mtrya in #37
- Fix pre-tag compatibility release validation by @Mtrya in #38
- Create compatibility release tags separately by @Mtrya in #39
- Handle missing remote release tags correctly by @Mtrya in #40
- Release compatibility builds from current main by @Mtrya in #41
Full Changelog: v0.4.2...v0.4.3
kimi-bridge v0.4.2
What's changed
- Consolidated Kimi Code compatibility metadata into the bridge release history and improved compatibility verdict handling.
- Reworked the human and setup-agent installation guides with explicit platform preflights, ownership boundaries, and safe cleanup behavior.
- Added coordinated compatibility-promotion, patch-version, and guarded post-merge release automation.
- Rendered expected adapter configuration failures as concise startup errors while preserving tracebacks for unexpected runtime defects.
See PR #34 and the full changelog.
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
kimi-bridge v0.4.0
What's changed
- Added a supported QQ C2C bot adapter with gateway resume and heartbeat handling, append-monotonic streaming, Markdown and media support, inbound vision/files, allowlisting, deduplication, and passive-to-active reply fallback in #25.
- Expanded session discovery with title-based switching, cross-workspace search, ambiguity handling, and a configurable list size in #24.
- Added detailed in-chat command help through
/<command> ?while keeping the main help index compact in #23. - Hardened credential-safe diagnostics, Feishu allowlist guidance and WebSocket shutdown, and QQ attachment and heartbeat behavior in #27.
Full changelog: v0.3.1...v0.4.0