* feat(wecom): add WebSocket long-connection mode for WeChat Work
Add WeChat Work AI Bot WebSocket support, enabling connection without
public URL, message encryption, or IP allowlist. Key implementation details:
- Use userID as chatid for single-chat scenarios (matching official SDK behavior)
- Add 500ms delay between multi-chunk sends to prevent out-of-order delivery
- Support text and pre-transcribed voice messages
- Exponential backoff reconnection with heartbeat-based dead connection detection
Made-with: Cursor
* docs(readme): add WebSocket mode for WeChat Work; test(wecom): add unit tests for WebSocket implementation
- Update README support matrix, setup guide, config examples and project
structure to include the new WebSocket long-connection mode alongside
existing Webhook
- Add 22 unit tests covering splitByBytes, handleMsgCallback chatID
fallback, writeAndWaitAck, handleFrame ACK dispatch, generateReqID
and newWebSocket
Made-with: Cursor
---------
Co-authored-by: xinlingzhao <xinlingzhao@tencent.com>
* feat: add multi-workspace mode and base_dir config fields
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add WorkspaceBindingManager for channel-to-workspace persistence
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add workspacePool for managing per-workspace agent state
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add ChannelNameResolver interface and Slack implementation
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add multi-workspace fields, SetMultiWorkspace, and idle reaper to Engine
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add resolveWorkspace method for channel-to-directory mapping
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: wire multi-workspace mode setup in main.go
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add workspace init flow for cloning repos and binding channels
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add /workspace commands (init, unbind, list, status)
Add handleWorkspaceCommand with subcommands:
- (no args): show current workspace binding for the channel
- init <git-url>: clone repo and bind workspace to channel
- unbind: remove workspace binding from channel
- list: show all workspace bindings for the project
Only available when multi-workspace mode is enabled.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: wire multi-workspace routing into handleMessage with per-workspace agents
Add workspace resolution to handleMessage that resolves channels to workspace
directories, creates per-workspace agents with correct work_dir, and routes
messages through workspace-specific session managers. The normal (single-workspace)
code path is unchanged — all new logic is gated behind e.multiWorkspace.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* test: add integration tests for multi-workspace resolution
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: resolve multi-workspace bugs found during live testing
Three bugs fixed:
1. App mention events not handled - Slack sends `app_mention` events
(not `message.channels`) when the bot is @mentioned. Added
AppMentionEvent handler in the Slack platform.
2. Bot mention prefix not stripped - app_mention text includes
`<@UBOTID> ` prefix, breaking command parsing and workspace
resolution. Now stripped before passing to engine.
3. Slash command syntax incompatible with Slack - `/workspace` commands
were being intercepted by Slack as slash commands. Changed all
user-facing references and prefix detection to use `workspace`
without the leading slash.
Also added debug logging to handleEvent for diagnosing event delivery.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: instruct agent to use Slack mrkdwn formatting
Add Slack formatting guidelines to the agent system prompt so responses
use Slack's mrkdwn syntax instead of standard Markdown (e.g. *bold*
instead of **bold**, no ## headings).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat(cards): interactive card UI for slash commands on Feishu
- Add platform-agnostic Card model (core/card.go) with builder API
- Add CardSender/CardNavigable interfaces (core/interfaces.go)
- Implement Feishu card renderer using column_set for mobile layout
- Redesign all slash command responses to use interactive cards
- Add handleCardNav router and executeCardAction for in-place updates
- Convert /new /quiet /switch /stop to act: and nav: actions
- /help card uses tab buttons grouped by Session/Agent/Tools/System
- renderUpgradeCard: sync update check with 8s timeout
- Fix: return error card instead of nil in handleCardNav /list /switch
Made-with: Cursor
* fix(cards): address PR #52 review feedback
- Add enable_feishu_card config option (default true) so operators can
fall back to plain-text replies when card permissions are unavailable;
wraps Platform in interactivePlatform only when cards are enabled
- Fix goroutine leak in renderUpgradeCard: use buffered channel (cap 1)
so the background goroutine can always complete even after a timeout
- Fix /stop concurrent logic in executeCardAction: consolidate state
mutation under a single interactiveMu critical section
- Fix code indentation in platform/feishu/card.go (action map and
CardSelect/CardNote case blocks)
- Add unit tests for Card.RenderText and Card.HasButtons (core/card_test.go)
- Add Feishu platform tests for ReplyCard/SendCard and card renderer
(platform/feishu/platform_test.go)
- Update docs/feishu.md and README with enable_feishu_card option
Made-with: Cursor
Merge upstream changes (iFlow agent, multi-bot relay, QQ Beta tag)
with our QQ Bot Official Platform additions. Resolved conflicts in
README.md, README.zh-CN.md, and cmd/cc-connect/main.go by combining
both sets of changes.
Updated iFlow CLI integration flags from `-p` to `-i` for interactive mode.
Modified quiet mode handling to preserve state across session stops.
Added shell command support in i18n messages.
Fixed empty tool ID handling in iFlow session.
generated by llmgit
Co-Authored-By: Claude <noreply@anthropic.com>
Add new `qqbot` platform type using the official QQ Bot API v2
(bot.q.qq.com), coexisting with the existing `qq` (OneBot v11) platform.
- OAuth2 token management with auto-refresh
- WebSocket gateway with heartbeat, reconnection, and resume
- GROUP_AT_MESSAGE_CREATE and C2C_MESSAGE_CREATE event handling
- REST API v2 message sending with msg_seq tracking
- No new dependencies (reuses gorilla/websocket)
Add ability to define custom slash commands that execute shell commands directly:
- Extend CommandConfig with Exec and WorkDir fields
- Add cmdCommandsAddExec handler for exec commands
- Implement executeShellCommand with timeout and output handling
- Add work_dir support for exec commands
- Update documentation and i18n messages
- Add tests and error handling
generated by llmgit
Co-Authored-By: Claude <noreply@anthropic.com>
Add support for configuring agent idle timeout duration via config file
(idle_timeout_mins). Defaults to 2 hours (changed from previous fixed 30 mins).
Timeout can be disabled by setting to 0.
generated by llmgit
Co-Authored-By: Claude <noreply@anthropic.com>
Streaming Preview:
- Real-time message preview during agent response (like "typing" indicator)
- Supported on Telegram, Discord, and Feishu
- Configurable interval, min delta chars, and max preview length
Rate Limiting:
- Per-session sliding-window rate limiter
- Prevents users from flooding the bot with messages
- Configurable max messages and window size
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Implement disabled commands functionality for projects, including config parsing, engine integration, and i18n support. Allows disabling specific commands per-project via config.
generated by llmgit
Co-Authored-By: Claude <noreply@anthropic.com>
Add banned words configuration and filtering logic to block messages containing prohibited content. Includes:
- Config file support for banned_words list
- Engine methods to set and check banned words
- Case-insensitive matching during message processing
- Localization support for blocked message response
- Documentation updates in config example
generated by llmgit
Co-Authored-By: Claude <noreply@anthropic.com>
Add support for routing Claude Code requests through Claude Code Router,
enabling multi-provider support (OpenRouter, DeepSeek, Gemini, etc.) and
dynamic model switching.
Changes:
- Add router_url and router_api_key configuration options
- Automatically set ANTHROPIC_BASE_URL when router is configured
- Set NO_PROXY, DISABLE_TELEMETRY, DISABLE_COST_WARNINGS for clean integration
- Update documentation with setup guide and usage examples
- Add configuration examples in config.example.toml
The integration is backward compatible - when router_url is not configured,
the agent behaves exactly as before. When configured, all requests are
transparently routed through Claude Code Router.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add OpenCode to support matrix (4 agents → 5 agents)
- Add OpenCode permission modes section
- Add OpenCode to prerequisites, provider env mapping, project structure
- Add OpenCode config example in config.example.toml
- Update both English and Chinese README
Add support for customizable slash commands that expand prompt templates with arguments. Includes:
- CommandProvider interface for agent-specific command directories
- Command registry with config.toml and agent file support
- Template expansion with placeholders ({{1}}, {{args}}, etc.)
- Dynamic command management via `/commands add/del`
- Multi-language support and documentation
- Example config additions and implementation for Claude/Gemini agents
generated by llmgit
Co-Authored-By: Claude <noreply@anthropic.com>
Add support for running cc-connect as a daemon managed by OS init system:
- Linux: systemd user service
- macOS: launchd LaunchAgent
New CLI commands:
- cc-connect daemon install/uninstall
- cc-connect daemon start/stop/restart/status
- cc-connect daemon logs [-f] [-n N] [--log-file PATH]
Features:
- Auto log rotation with configurable max size
- Cross-platform support (systemd/launchd)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Implement agent system prompts explaining cc-connect capabilities
Add AllowList function for platform user authorization
generated by llmgit
Co-Authored-By: Claude <noreply@anthropic.com>
Add support for Google Gemini CLI as a new agent type. Includes:
- New gemini agent implementation with session management
generated by llmgit
Co-Authored-By: Claude <noreply@anthropic.com>
Add full integration for Cursor Agent with support for CLI interactions via `agent --print --output-format stream-json`. Includes:
- New cursor package with Agent and Session implementations
generated by llmgit
Co-Authored-By: Claude <noreply@anthropic.com>
Add speech-to-text functionality for voice messages using OpenAI/Groq Whisper API. Includes:
- Configurable speech provider (OpenAI or Groq)
- Audio format conversion via ffmpeg
- Support for voice messages on Feishu, WeChat Work, Telegram, LINE, Discord, Slack
- Internationalization messages for voice transcription flow
- Documentation updates in README and config example
generated by llmgit
Co-Authored-By: Claude <noreply@anthropic.com>
Add provider management system allowing dynamic switching between API providers (Anthropic, relay services, AWS Bedrock, etc.) without restarting. Includes:
generated by llmgit
Co-Authored-By: Claude <noreply@anthropic.com>
Add new Codex agent implementation with permission modes, session management, and history retrieval. Update installation docs, README files, and config templates to reflect Codex support. Enhance session listing and history commands to work with both Claude and Codex agents.
generated by llmgit
Co-Authored-By: Claude <noreply@anthropic.com>
Add support for WeChat Work (企业微信) as a new platform with full HTTP Webhook integration. Includes:
- AES-256-CBC message encryption/decryption
- Token verification and message handling
- API client for sending messages with access token caching
- Documentation updates in README and config
- Chinese language README support
- Example configuration
generated by llmgit
Co-Authored-By: Claude <noreply@anthropic.com>
The changes introduce support for four new messaging platforms:
Includes implementation code for LINE platform adapter, documentation updates in READMEs, and configuration examples. Also adds required dependencies to go.mod.
generated by llmgit
Co-Authored-By: Claude <noreply@anthropic.com>
Add new platform integrations with configuration examples and dependencies:
- Telegram long polling bot support
- Slack Socket Mode WebSocket integration
- Discord Gateway WebSocket connection
- Include required dependencies in go.mod
generated by llmgit
Co-Authored-By: Claude <noreply@anthropic.com>
