NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
Go modules · #203 by repository stars
Last release 2 days ago
29 Sep 2026
Ships on a steady schedule
a new release about every 1 weeks
Nearly every release is documented
notes for 12 of 13 stable releases
Nothing withdrawn
no release was ever pulled
7 months old
128 releases · first in 2026
One column per month.
Nothing published for this version
Nothing published for this version
Beta release with Slack Assistant API, DingTalk improvements, MAX platform webhook mode, and numerous platform fixes. No breaking changes.
Beta release with Slack Assistant API, DingTalk improvements, MAX platform webhook mode, and numerous platform fixes. No breaking changes.
env config section (#812)display_mode enum to replace boolean quiet config, with quiet/compact/normal/full options (#655)system_prompt option (#534)Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Beta release with new agents, new features, and broad platform fixes. No breaking changes.
Beta release with new agents, new features, and broad platform fixes. No breaking changes.
/list, /mode, and session management (#672)/ps command (replaces /btw): send a message to a busy session mid-turn; /btw kept as alias for backward compatibility (#620)! shell shortcut: use !ls -la as shorthand for /shell ls -la, with optional --timeout parameter (#658)NO_REPLY to silently skip platform delivery, useful for cron/analysis tasks (#682)app_id now share one WebSocket connection with per-project allow_chat / group_only filtering (#613)[queue] max_depth config option (default 5) (#690)cc-connect send --image/--file now works through bridge protocol (#712)--file flags (#717)Thanks to all contributors who made this release possible:
! prefix and --timeoutNothing published for this version
Nothing published for this version
Nothing published for this version
Hotfix release: session filtering is now configurable and defaults to showing all sessions.
Hotfix release: session filtering is now configurable and defaults to showing all sessions.
/list shows all sessions by default: the session filter introduced in v1.3.0 (which hid sessions not created by cc-connect) was accidentally merged and caused confusion. The filter is now off by default — /list, /switch, and /delete show all agent sessions regardless of origin.filter_external_sessions config option: users who do want to hide externally-created sessions can set filter_external_sessions = true in [[projects]] to restore the old filtering behavior./list → /new → conversation → /list lifecycle with provider-based authentication (no env-var API keys required). Plus 9 adapter-level filter tests using real Codex/Claude Code session file fixtures.Patch release with critical bug fixes for session management, config preservation, and Weibo media support.
Patch release with critical bug fixes for session management, config preservation, and Weibo media support.
/list): historical Codex sessions disappeared after upgrade due to AgentSessionID being cleared on /new or provider switch without preservation. Added PastAgentSessionIDs tracking with legacy data migration so existing sessions remain visible./new xxx): custom session names from /new were not mapped to the agent session ID for agents where the ID is established asynchronously (Codex, Qoder, Kimi, etc.). Added name mapping to all EventResult and EventText handlers across interactive, relay, and drain paths./provider switch, /model, /lang, display settings, and TTS changes now use surgical text-level editing instead of full TOML re-serialization, preserving all comments, unknown fields, and formatting.codex_home path: session listing, history, and deletion now consistently use the configured codex_home instead of hardcoded ~/.codex.card.action.trigger may not be subscribed.send_message payload. Implements ImageSender and FileSender interfaces.SessionManager unit tests covering PastAgentSessionIDs, legacy data migration, and version-based schema detection. 9 new Engine integration tests covering /list visibility across /new, provider switch, and real-world legacy data scenarios, plus end-to-end session name mapping tests for all three agent ID patterns (immediate, EventText, EventResult).SaveActiveProvider, SaveAgentModel, SaveProviderModel, SaveLanguage, SaveDisplayConfig, SaveTTSMode, multi-project config, and global provider refs.Nothing published for this version
First stable release of the 1.3 series. 555 commits since v1.2.1 with major new features, platform improvements, and broad community contributions.
First stable release of the 1.3 series. 555 commits since v1.2.1 with major new features, platform improvements, and broad community contributions.
go:embed. Project CRUD, session monitoring, cron editor, provider management, chat interface, and i18n (en/zh/zh-TW/ja/es). Use cc-connect web to open directly in the browser with auto-login.[[hooks]] config to trigger shell commands or HTTP webhooks on 7 event types: message.received, message.sent, session.started, session.ended, cron.triggered, permission.requested, error. Async by default, fail-open, non-blocking./skills page in the web UI with local skill browser (per-project, per-agent) and recommended skill presets fetched from remote.cc-connect web CLI command: auto-configure web admin, open browser with token-based login@name mentions to clickable at-tags (resolve_mentions config)cli_path; /effort command for reasoning effort; auto permission mode; disallowed_tools config@everyone/@here broadcastapi_base_url for private deployments; file receiving via HTTP callback${ENV_VAR} placeholders in TOML values/workspace init with local directory paths; /dir directory history; agent-sid command; auto-compress context on token threshold; outgoing rate limiting/list to cc-connect owned sessionsformatTOML no longer strips user-set zero values/api/v1/status; path traversal protection for static filesThanks to all contributors who made this release possible:
/effort commandNothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Beta release with embedded web admin, Discord proxy support, multimodal fixes, and major platform improvements.
Beta release with embedded web admin, Discord proxy support, multimodal fixes, and major platform improvements.
go:embed — no separate npm install needed. Use /web setup to configure, or build with no_web tag to exclude. Binary size increases ~1MB (#356)proxy, proxy_username, proxy_password options for HTTP API and WebSocket Gateway connectionsauto permission mode for Claude Code agent (#329)go-telegram/bot library with forum topic support (#321)/tmp so Gemini CLI tools can access them; use prompt-based file references instead of unsupported --image flag/api/v1/status endpoint; add path traversal protection for static file servingformatTOML no longer strips user-set zero values (e.g. quiet = false)no_web tag for e2e/smoke testsno_web build tag to exclude web assets from binarySpecial thanks to all contributors who made this release possible:
Nothing published for this version
Nothing published for this version
Nothing published for this version
Beta release with Weixin (ilink) personal chat support, session/continue improvements, and platform fixes.
Beta release with Weixin (ilink) personal chat support, session/continue improvements, and platform fixes.
getUpdates / sendMessage, QR weixin setup, CDN decrypt for inbound media and ImageSender/FileSender outbound (#257)@everyone / @here broadcast support (#132)disallowed_tools configuration option (#232)--continue to avoid context contamination (#244); replace persisted ContinueSession sentinel with real agent session id; reserve CLI --continue bridge for real user traffic/dir directory history; /model switching aligned with provider flow (#246)sendMessage JSON ret != 0 as failure so quota/API errors surface correctly--json flag position fixes (#240, #239)ContinueSession sentinel where inappropriate (#244 follow-up)config, core, agents, and platformsSpecial thanks to all contributors who made this release possible:
--continue (#244)/model provider flow (#225, #246)disallowed_tools (#232)/dir directory historyBeta release with major multi-user mode, improved workspace stability, and platform enhancements.
Beta release with major multi-user mode, improved workspace stability, and platform enhancements.
models list for per-provider model selection via aliasSpecial thanks to all contributors who made this release possible:
Nothing published for this version
Beta release with significant improvements to agent stability, platform onboarding, and user experience.
Beta release with significant improvements to agent stability, platform onboarding, and user experience.
cc-connect feishu setup command with QR code terminal display for quick bot configuration, supporting both new bot creation and existing bot bindingcc-connect sessions subcommand with terminal UI for browsing session history--continue on first connection, resume-failure fallback, and context usage indicators/cron setup for easy cron job configuration with memory file integrationdrainEventsexecuteCardAction using wrong key for interactiveStates lookup in multi-workspace modeStartSession to prevent race conditionSession.AgentSessionID writes with mutex to prevent data races/new runs during active turnMessageCreate events causing duplicate responsessplitMessage to prevent invalid UTF-8 sequences/btw command for adding context during processingSpecial thanks to all contributors who made this release possible:
Nothing published for this version
Beta release with major new features and security improvements.
Beta release with major new features and security improvements.
/usage Command: Add a built-in quota usage command with a generic agent usage-reporting interface; Codex now supports ChatGPT OAuth usage lookup via ~/.codex/auth.json/reasoning command to switch reasoning effort levels (low/medium/high)/model command now falls back to local ~/.codex/models_cache.json when API is unavailabletimeout_mins option to configure per-turn timeout for Gemini agent/delete now supports comma lists, ranges, and mixed forms for batch deletionshare_session_in_channel optionallow_fromPatch release with bug fixes and minor enhancements.
Patch release with bug fixes and minor enhancements.
SenderId.OpenId and msg.Content to prevent panicsjson.Unmarshal errors instead of silently ignoring when cron file is corrupteddrainEvents utility to clear buffered events between turns/bind setup writes relay instructions to memory file for better bot-to-bot relay configurationNothing published for this version
Nothing published for this version
This is the first stable release of cc-connect 1.2.0, consolidating all beta changes and adding new features.
This is the first stable release of cc-connect 1.2.0, consolidating all beta changes and adding new features.
exec field in config/quiet now supports both per-session and global scope modes/compress command handling and code refactoringNothing published for this version
Multi-Bot Relay Binding: /bind now supports binding multiple bots in a group chat; use /bind to add, /bind - to remove specific project
/bind now supports binding multiple bots in a group chat; use /bind <project> to add, /bind -<project> to remove specific project/etc/systemd/system/) when running as root, useful for servers and containerscc-connect config-example prints embedded config template for quick reference/lang, /model, /mode commands now show interactive button menus for easy selectionexec field in configidle_timeout_mins in configNothing published for this version
Bot-to-Bot Relay: Forward messages between different messaging platforms via CLI (cc-connect relay) and internal API; enables cross-platform bot commu
cc-connect relay) and internal API; enables cross-platform bot communication/search <keyword> command/list now supports pagination with --page and --page-size flags for large session countsstreaming_preview setting (Telegram, Discord, Feishu)silent = true in cron job config/status command output with better formatting and Feishu message rendering fixesmaxChars check that caused premature preview terminationStreaming Preview: Real-time message preview that updates in-place as the agent streams output; supported on Telegram, Discord, and Feishu with config
max_messages and window_secs[[aliases]] in config.toml or /alias add); e.g. map "帮助" → "/help"banned_words in config.toml)disabled_commands config/del command/switch Fuzzy Matching: Switch sessions by name, ID prefix, or summary substring in addition to numeric index/perm commands (consistent with Claude-to-IM)<b><i>...</b></i> nesting issues by using placeholder-based formatting pipeline" in URLs breaking <a href> attributes (escape to ")▍ cursor from final messagesim.message.reaction.deleted_v1 to suppress error logsfmt.Sprintf Warnings: Remove non-constant format strings flagged by go vet`/upgrade` Command: Check for available updates (including beta) and self-update the binary in-place; queries both GitHub and Gitee releases
/upgrade Command: Check for available updates (including beta) and self-update the binary in-place; queries both GitHub and Gitee releases/restart Command: Restart cc-connect service from chat with post-restart success notification/config reload Command: Hot-reload configuration (display, providers, commands) without restarting/name Command: Set custom display names for sessions (e.g. /name my-feature, /name 3 bugfix); names persist across restarts and show in /list, /switch, /statusquiet = true globally or per-project in config.toml to suppress thinking/tool progress by default; users can still toggle with /quiet/pro l for /provider list, /sw 2 for /switch 2; works for all commands and subcommands/list shows numbered sessions; /switch 3 switches by number instead of copying long IDsthinking parameters for third-party LLM providers (e.g. SiliconFlow)/history now works after /switch by reading from agent JSONL files/list now shows the most recent user message as summary instead of the first/list, /switch, /statussync.Once for channel close, mutex protection for concurrent fields, non-blocking event sendsCustom Slash Commands: Define reusable prompt templates as global slash commands ([[commands]] in config.toml or /commands add); supports positional p
[[commands]] in config.toml or /commands add); supports positional parameters ({{1}}), rest parameters ({{2*}}), default values ({{1:default}}), and runtime add/del/list.claude/skills/<name>/SKILL.md); list with /skills, invoke with /<skill-name> [args]; supports all agents (Claude Code, Cursor, Gemini, Codex, Qoder)/config Command: View and modify runtime configuration (e.g. thinking_max_len, tool_max_len) from chat, with persistent save to config.toml/doctor Command: Run system diagnostics covering agent authentication, platform connectivity, system resources, dependencies, and network latency; fully i18n-supported/ shows an autocomplete menu; supports per-guild instant registration via guild_id configcc-connect daemon install/start/stop/status/logs); supports systemd (Linux) and launchd (macOS)proxy_username / proxy_password for authenticated forward proxies--stdin Support: Read prompt from stdin for CLI usage (echo "hello" | cc-connect send --stdin)turn_durationtool_max_len=0 Fix: Remove hardcoded 200-char truncation in all agent sessions (Claude Code, Cursor, Codex, Gemini, Qoder), making the user-configurable tool_max_len setting authoritative/list Improvements: Parse binary blob structure to show accurate message counts and first user message summaryhttp.Transport when proxy is actually configured`/compress` Command: Compress/compact conversation context by forwarding native commands to agents (Claude Code /compact, Codex /compact, Gemini /comp
/compress Command: Compress/compact conversation context by forwarding native commands to agents (Claude Code /compact, Codex /compact, Gemini /compress); keeps long sessions manageable[projects.auto_compress])./model Command: View and switch AI models at runtime; supports numbered quick-select and custom model names. Fetches available models from provider API in real-time (Anthropic, OpenAI, Google), with built-in fallback list/memory Command: View and edit agent memory files (CLAUDE.md, AGENTS.md, GEMINI.md) directly from chat; supports both project-level and global-level (/memory global)/status Command: Display system status including project, agent, platforms, uptime, language, permission mode, session info, and cron job count/model now starts a fresh agent session instead of resuming the old one, preventing stale context from affecting the new model/list summary: Fixed session list showing raw JSON ({"dummy": true}) instead of actual user message summary(see v1.1.0 above — beta.7 changes are included in the stable release)
(see v1.1.0 above — beta.7 changes are included in the stable release)
QQ Platform (Beta): Support QQ messaging via OneBot v11 / NapCat WebSocket
/cron command or CLI (cc-connect cron add), with JSON persistence and agent-aware session injectionreaction_emoji[display] config section to control thinking/tool message truncation (thinking_max_len, tool_max_len); set to 0 to disable truncation/version Command: Check current cc-connect version from within chat/list fix: Claude Code sessions now discoverable on Windows despite drive letter colon in project key paths~/.cc-connect/config.toml in INSTALL.mdGemini CLI Agent: Full support for gemini CLI with streaming JSON, mode switching, and provider management
gemini CLI with streaming JSON, mode switching, and provider managementagent) with mode and provider supportFixed npm install: check binary version on install, replace outdated binary instead of skipping
run.jsVoice Messages (STT): Transcribe voice messages to text via OpenAI Whisper, Groq Whisper, or SiliconFlow SenseVoice; requires ffmpeg
ffmpegcc-connect send command and internal Unix socket API for programmatic message sendingProvider Management: /provider command for runtime API provider switching; CLI cc-connect provider add/list
/provider command for runtime API provider switching; CLI cc-connect provider add/list~/.cc-connect/ by default (configurable via data_dir)Codex Agent: OpenAI Codex CLI integration
cc-connect update and cc-connect check-update commands/lang command to switch between English and ChineseBug fixes and stability improvements
Your coding agent can read these notes before it upgrades. Set up the MCP server →