whyihaveyou · whyihaveyou · Aug 15, 2026 · Aug 13, 2026 · Aug 13, 2026 · Aug 13, 2026
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,4 +1,4 @@
-# Changelog
+# Changelog
 
 ## Unreleased
 
@@ -20,11 +20,25 @@
 - **feishu**: coalesce consecutive image messages from the same session into a single multi-image dispatch to fix first-image drop on batch sends (#1395). When the Feishu mobile client sends N images in quick succession, each image arrives as a separate `image` event with very close `create_time` values. Dispatching each immediately caused core/engine's `create_time` watermark (PR #1168) to drop the oldest image, so the agent only saw N-1 images. A per-session image buffer with a 150ms quiet window now merges the burst into one `core.Message` carrying all images, in send order. Single-image sends and quoted-image replies are unaffected.
 - **claudecode**: fix per-spawn system-prompt temp file EACCES under `run_as_user` (#1429). The per-spawn temp file written by `writeTempAppendPromptFile` (the 1% edge-case path used when the prompt has session-specific platform formatting or user `append_system_prompt`) inherited `os.CreateTemp`'s 0600 mode and was owned by the cc-connect process user (often root under systemd). When the agent was spawned under a different `run_as_user`, it could not read the file and exited before any prompt was loaded. The file is now `chmod 0o644` immediately after write, matching the shared `ensureSharedSystemPromptFile` path. Prompt content is non-secret (a superset of the already-shared base prompt), so 0644 is consistent with the shared file. Does not affect the shared-file path (already 0644 since #1376) or the daemon-mode path resolution (#1419).
 - **kimi**: gate `--work-dir` flag on `kimiFlagSupport.WorkDir` so the Kimi Code CLI build that dropped the flag no longer exits with `error: unknown option --work-dir` (#1476). Same probe-based pattern as the `--print` fix in #1456 / PR #1461: the agent probes `kimi --help` once at construction, then `buildArgs` emits the flag only when the installed CLI advertises it. The agent still runs in the correct directory because `exec.Command.Dir` is set separately, so legacy kimi-cli users (who still have `--work-dir`) keep non-default workspace support while modern-CLI users get clean startup.
+- **kimi**: native Kimi Code CLI (Node.js `kimi-code`) dialect support (#1561). The newer CLI removed `--quiet` and `--resume`, moved the session resume hint from a plain-text line to a stdout JSON meta event (`{"role":"meta","type":"session.resume_hint",...}`), and emits assistant/tool `content` as a plain string instead of typed blocks — causing `error: unknown option`, silently dropped replies, and broken multi-turn continuity. The probe now also gates `--quiet` (emulated locally by suppressing thinking/tool events when unsupported), resume uses `-r <id>` on the modern dialect (the command the CLI's own hint prints), the meta resume-hint event restores the session ID, and the stream parser accepts both content shapes regardless of probed flavor. Session listing additionally scans `~/.kimi-code/sessions` with its `state.json` schema (`title`/`workDir`, honoring the workDir filter) and counts messages from `agents/main/wire.jsonl` so `/list` and `/delete` work for both CLI flavors. Legacy kimi-cli behavior is unchanged.
 - **core**: queue post-restart notification and dispatch on platform ready (#1383). Previously `/restart` sent the success notification immediately after engine startup, racing the platform's async connect window (Telegram: ~2.6s). On a not-yet-ready platform the send was silently dropped at debug log level. The notify is now queued on the engine and dispatched when the target platform reaches `OnPlatformReady`, with bounded retry (3 attempts, 0/500/1500 ms backoff) on transient send failure. Failed sends log at warn level. A 10s safety timeout drops the notify with a warning if the target platform never reaches ready, so startup is never blocked indefinitely. Also covers Discord / Weixin / Matrix (other AsyncRecoverablePlatform implementations) for free.
 - **core**: `SaveFilesToDisk` / `AppendFileRefs` always emit absolute paths (#1459). When a user configured a relative `work_dir` (e.g. `~/project` or `.cc-connect`), `SaveFilesToDisk` joined relative paths into the attachments directory and the resulting paths were passed verbatim into the agent's prompt. The spawned agent process — typically run from a different cwd by the platform adapter — could not resolve them and silently dropped every attachment. `SaveFilesToDisk` now calls `filepath.Abs(workDir)` up front and falls back to the raw value on error, and `AppendFileRefs` defensively absolutizes each entry. Both behaviors are covered by new tests for relative, absolute, and empty workDir; the empty-workDir case falls back to the process cwd so misconfigured deploys still get a writable attachments directory.
 
 - **core**: prevent same-name file attachments from overwriting each other. `SaveFilesToDisk` now scopes files by message ID, keeps duplicate names distinct within one message, and uses an atomic no-overwrite fallback for legacy callers without a message ID (#1552).
 
+## Unreleased
+
+### Fixed
+- **/model switch confirmation copy**: `MsgModelChanged` now explicitly states the
+  new model applies to the current session and all future sessions, removing the
+  misleading "new sessions" wording that made users think they needed `/new` to
+  see the change take effect (#1368).
+
+## Unreleased
+
+### Fixed
+- **DingTalk message list title**: derive the `markdown.title` field on outgoing DingTalk messages from the message content (markdown stripped, first non-empty line, truncated to 20 runes) instead of the hardcoded `"reply"`. The DingTalk chat list now shows the actual reply preview instead of "reply" on every entry. Empty / pure-format / pure-emoji messages still fall back to "reply" so the title is never blank (#1269).
+
 ## v1.3.3 (2026-06-15)
 
 First stable release of the 1.3.3 series. Stabilizes the v1.3.3-beta.1 → v1.3.3-beta.5

diff --git a/Makefile b/Makefile
@@ -36,7 +36,7 @@ PLATFORMS := \
 ALL_AGENTS    := acp antigravity claudecode codex copilot cursor devin gemini iflow kimi opencode pi qoder tmux
 ALL_PLATFORMS := feishu telegram discord slack dingtalk wecom weixin qq qqbot line weibo max matrix webex wps-agentspace tuitui
 ALL_AGENTS    := acp antigravity claudecode codex copilot cursor devin gemini iflow kimi opencode pi qoder reasonix tmux
-ALL_PLATFORMS := feishu telegram discord slack dingtalk wecom weixin qq qqbot line weibo max matrix webex cloud_web tuitui
+ALL_PLATFORMS := feishu telegram discord slack dingtalk wecom weixin qq qqbot line weibo max matrix webex cloud_web tuitui googlechat
 ALL_EXTRAS    := web
 
 COMMA := ,

diff --git a/README.md b/README.md
@@ -276,6 +276,91 @@ High-level view of what each **built-in platform** can do in cc-connect.
 </p>
 
 
+## 📋 Prerequisites
+
+> **Install in this exact order** — cc-connect is a bridge for local AI coding agents, so the agent CLI must be installed and authenticated *before* cc-connect starts. Skipping ahead will cause `cc-connect` to exit with `claudecode: claude CLI not found in PATH` (or similar for your chosen agent), and the Web UI on `:9820` will never come up.
+
+### 1️⃣ Install your AI Agent CLI
+
+Pick the agent you want to bridge. You need **at least one**.
+
+```bash
+# Claude Code (most common)
+brew install --cask claude-code            # macOS / Linux Homebrew
+# or
+npm install -g @anthropic-ai/claude-code   # any platform via npm
+
+# OpenAI Codex
+npm install -g @openai/codex
+
+# Google Gemini CLI
+npm install -g @google/gemini-cli
+
+# iFlow CLI
+npm install -g @iflow-ai/iflow-cli
+
+# Qoder CLI
+curl -fsSL https://qoder.com/install | bash
+```
+
+For **Cursor Agent** and **OpenCode**, follow the official install pages:
+- Cursor Agent: <https://docs.cursor.com/agent>
+- OpenCode: <https://github.com/opencode-ai/opencode>
+
+Verify the binary is on your `PATH`:
+
+```bash
+claude --version       # or: codex / gemini / opencode / qodercli / cursor-agent ...
+```
+
+### 2️⃣ Authenticate the agent
+
+Each agent has its own login flow — run the agent once interactively so it stores credentials in your home directory:
+
+```bash
+claude login           # opens a browser to authenticate
+# or
+codex login            # /gemini / opencode auth — see the agent's docs
+```
+
+If you skip this step, `cc-connect` will still start, but the agent will reject every prompt with an auth error.
+
+### 3️⃣ Install cc-connect
+
+```bash
+# npm (any platform)
+npm install -g cc-connect
+
+# Homebrew (macOS / Linux)
+brew install cc-connect
+
+# Or download a binary from https://github.com/chenhg5/cc-connect/releases
+```
+
+### 4️⃣ Start cc-connect and open the Web UI
+
+```bash
+cc-connect             # starts the service; first run auto-creates ~/.cc-connect/config.toml
+```
+
+On first launch, cc-connect prints something like:
+
+```
+Web admin:  http://localhost:9820
+```
+
+Open that URL in your browser. If `9820` is already in use, pass `--web-port 9821` or set `web_port` in `config.toml`.
+
+> **Note:** `cc-connect web` *only* opens the browser and the config UI — it does **not** start the service. You still need `cc-connect` running in another terminal.
+
+### 5️⃣ Configure platform bot tokens in the Web UI
+
+In the Web UI, create a project, then add at least one platform (Feishu / Telegram / Discord / Slack / DingTalk / WeChat Work / QQ / LINE / Weixin) and paste the bot token from that platform's developer console. Save and cc-connect will hot-reload.
+
+That's it — send a message to your bot and cc-connect will relay it to your local agent.
+
+---
+
 ## 🚀 Quick Start
 
 ### 🤖 Install & Configure via AI Agent (Recommended)
@@ -401,6 +486,7 @@ cc-connect update --pre     # Include pre-releases
 | WPS Xiezuo | [docs/wps-xiezuo.md](docs/wps-xiezuo.md) | WebSocket | No |
 | Telegram | [docs/telegram.md](docs/telegram.md) | Long Polling | No |
 | Slack | [docs/slack.md](docs/slack.md) | Socket Mode | No |
+| Google Chat | [docs/googlechat.md](docs/googlechat.md) | Cloud Pub/Sub | No |
 | Discord | [docs/discord.md](docs/discord.md) | Gateway | No |
 | Weibo | [docs/weibo.md](docs/weibo.md) | WebSocket | No |
 | WeChat Work | [docs/wecom.md](docs/wecom.md) | WebSocket / Webhook | No (WS) / Yes (Webhook) |

diff --git a/README.zh-CN.md b/README.zh-CN.md
@@ -275,6 +275,91 @@
 </p>
 
 
+## 📋 准备工作
+
+> **请严格按照以下顺序安装** — cc-connect 是本地 AI 编程 Agent 的桥接工具，因此对应的 Agent CLI 必须先安装并完成登录认证，之后 cc-connect 才能正常启动。如果跳过前面的步骤直接启动 cc-connect，进程会直接退出并报错 `claudecode: claude CLI not found in PATH`（其他 Agent 报错类似），Web UI 在 `:9820` 也就无从访问。
+
+### 1️⃣ 安装 AI Agent CLI
+
+选择你要桥接的 Agent，至少装一个。
+
+```bash
+# Claude Code（最常用）
+brew install --cask claude-code            # macOS / Linux Homebrew
+# 或
+npm install -g @anthropic-ai/claude-code   # 任意平台通过 npm
+
+# OpenAI Codex
+npm install -g @openai/codex
+
+# Google Gemini CLI
+npm install -g @google/gemini-cli
+
+# iFlow CLI
+npm install -g @iflow-ai/iflow-cli
+
+# Qoder CLI
+curl -fsSL https://qoder.com/install | bash
+```
+
+**Cursor Agent** 和 **OpenCode** 请参考各自的官方安装文档：
+- Cursor Agent: <https://docs.cursor.com/agent>
+- OpenCode: <https://github.com/opencode-ai/opencode>
+
+确认可执行文件在 `PATH` 中：
+
+```bash
+claude --version       # 或 codex / gemini / opencode / qodercli / cursor-agent ...
+```
+
+### 2️⃣ 完成 Agent 登录认证
+
+每个 Agent 都有自己的登录流程 — 先在终端交互式跑一次，让它把凭据存到你的 home 目录：
+
+```bash
+claude login           # 会在浏览器里打开授权页面
+# 或
+codex login            # / gemini / opencode 等也类似，请参考各自文档
+```
+
+跳过这一步的话，cc-connect 仍能启动，但 Agent 会因为未认证拒绝所有请求。
+
+### 3️⃣ 安装 cc-connect
+
+```bash
+# npm（任意平台）
+npm install -g cc-connect
+
+# Homebrew（macOS / Linux）
+brew install cc-connect
+
+# 也可以从 https://github.com/chenhg5/cc-connect/releases 直接下载二进制
+```
+
+### 4️⃣ 启动 cc-connect 并打开 Web UI
+
+```bash
+cc-connect             # 启动服务；首次运行会自动生成 ~/.cc-connect/config.toml
+```
+
+首次启动时，cc-connect 会打印类似：
+
+```
+Web admin:  http://localhost:9820
+```
+
+在浏览器里打开该地址。如果 `9820` 已被占用，可以传 `--web-port 9821` 或在 `config.toml` 里设置 `web_port`。
+
+> **注意：** `cc-connect web` *只* 打开浏览器和配置界面，并**不会**启动服务本身。仍需要在另一个终端里跑 `cc-connect`。
+
+### 5️⃣ 在 Web UI 里配置平台 Bot Token
+
+在 Web UI 里新建一个项目，然后添加至少一个平台（飞书 / Telegram / Discord / Slack / 钉钉 / 企业微信 / QQ / LINE / 微信 ilink），把该平台开发者后台的 Bot Token 粘贴进去。保存后 cc-connect 会热加载。
+
+至此完成 — 给你的 Bot 发条消息，cc-connect 就会把它转给本地的 Agent。
+
+---
+
 ## 🚀 快速开始
 
 ### 🤖 通过 AI Agent 安装配置（推荐）

diff --git a/agent/antigravity/antigravity.go b/agent/antigravity/antigravity.go
@@ -26,7 +26,7 @@ func init() {
 // Agent drives the Antigravity CLI (agy) in headless mode.
 //
 // Modes (maps to agy approval and sandbox flags):
-//   - "default":   standard approval mode (prompt for each tool use)
+//   - "default":   ask for each tool through the cc-connect permission bridge
 //   - "yolo":      auto-approve all tools (--dangerously-skip-permissions)
 //   - "plan":      read-only plan mode with terminal sandbox constraints (--sandbox)
 type Agent struct {
@@ -284,7 +284,7 @@ func (a *Agent) GetMode() string {
 
 func (a *Agent) PermissionModes() []core.PermissionModeInfo {
 	return []core.PermissionModeInfo{
-		{Key: "default", Name: "Default", NameZh: "默认", Desc: "Prompt for approval on each tool use", DescZh: "每次工具调用都需要确认"},
+		{Key: "default", Name: "Default", NameZh: "默认", Desc: "Ask for approval through cc-connect on each tool use", DescZh: "每次工具调用都通过 cc-connect 请求确认"},
 		{Key: "yolo", Name: "YOLO", NameZh: "全自动", Desc: "Auto-approve all tool calls", DescZh: "自动批准所有工具调用"},
 		{Key: "plan", Name: "Plan", NameZh: "规划模式", Desc: "Read-only plan mode in sandbox", DescZh: "只读沙箱规划模式"},
 	}