feat: 添加可配置的命令前缀以避免与Claude Code冲突

引入可配置的COMMAND_PREFIX参数，默认设置为"//"以避免与Claude Code的"/"命令冲突
修改相关文件以支持新的命令前缀，包括配置解析、路由逻辑和命令处理
更新帮助文档和提示信息以反映新的命令前缀

orchestrator/agent.py

@@ -21,7 +21,7 @@ from langchain_core.messages import (
 from langchain_openai import ChatOpenAI
 
 from agent.manager import manager
-from config import OPENAI_API_KEY, OPENAI_BASE_URL, OPENAI_MODEL, WORKING_DIR
+from config import OPENAI_API_KEY, OPENAI_BASE_URL, OPENAI_MODEL, WORKING_DIR, COMMAND_PREFIX as _P
 from orchestrator.tools import TOOLS, set_current_user
 
 logger = logging.getLogger(__name__)
@@ -39,27 +39,29 @@ Pass these names directly to `create_conversation` — the tool resolves them au
 
 {active_session_line}
 
+Bot command prefix: {prefix}
+
 ## Tools — two distinct categories
 
 ### Bot control commands (use `run_command`)
-`run_command` executes PhoneWork slash commands. Use it when the user asks to:
-- Change permission mode: "切换到只读模式" → run_command("/perm plan")
-- Close/switch sessions: "关掉第一个" → run_command("/close 1")
-- Change routing mode: "切换到直连模式" → run_command("/direct")
-- Set a reminder: "10分钟后提醒我" → run_command("/remind 10m 提醒我")
-- Check status: "看看现在有哪些 session" → run_command("/status")
-- Any other /command the user would type manually
+`run_command` executes PhoneWork commands. Use it when the user asks to:
+- Change permission mode: "切换到只读模式" → run_command("{prefix}perm plan")
+- Close/switch sessions: "关掉第一个" → run_command("{prefix}close 1")
+- Change routing mode: "切换到直连模式" → run_command("{prefix}direct")
+- Set a reminder: "10分钟后提醒我" → run_command("{prefix}remind 10m 提醒我")
+- Check status: "看看现在有哪些 session" → run_command("{prefix}status")
+- Any other command the user would type manually
 
 Available bot commands (pass verbatim to run_command):
-  /new <dir> [msg] [--perm bypass|accept|plan]  — create session
-  /close [n|conv_id]   — close session
-  /switch <n>          — switch active session
-  /perm <mode> [conv_id] — permission mode: bypass (default), accept, plan
-  /direct              — direct mode (bypass LLM for CC messages)
-  /smart               — smart mode (LLM routing, default)
-  /status              — list sessions
-  /remind <Ns|Nm|Nh> <msg> — one-shot reminder
-  /tasks               — list background tasks
+  {prefix}new <dir> [msg] [--perm bypass|accept|plan]  — create session
+  {prefix}close [n|conv_id]   — close session
+  {prefix}switch <n>          — switch active session
+  {prefix}perm <mode> [conv_id] — permission mode: bypass (default), accept, plan
+  {prefix}direct              — direct mode (bypass LLM for CC messages)
+  {prefix}smart               — smart mode (LLM routing, default)
+  {prefix}status              — list sessions
+  {prefix}remind <Ns|Nm|Nh> <msg> — one-shot reminder
+  {prefix}tasks               — list background tasks
 
 ### Host shell commands (use `run_shell`)
 `run_shell` executes shell commands on the host machine (git, ls, cat, pip, etc.).
@@ -69,7 +71,7 @@ NEVER use `run_shell` for bot control. NEVER use `run_command` for shell command
 1. NEW session: call `create_conversation` with the project name/path. \
    If the user's message also contains a task, pass it as `initial_message` too.
 2. Follow-up to ACTIVE session: call `send_to_conversation` with the active conv_id shown above.
-3. BOT CONTROL: call `run_command` with the appropriate slash command.
+3. BOT CONTROL: call `run_command` with the appropriate command.
 4. GENERAL QUESTIONS: answer directly — do NOT create a session for simple Q&A.
 5. WEB / SEARCH: use `web` at most twice, then synthesize and reply.
 6. BACKGROUND TASKS: when a task starts, reply immediately — do NOT poll `task_status`.
@@ -119,6 +121,7 @@ class OrchestrationAgent:
             working_dir=WORKING_DIR,
             active_session_line=active_line,
             today=today,
+            prefix=_P,
         )
 
     def get_active_conv(self, user_id: str) -> Optional[str]:
@@ -143,6 +146,16 @@ class OrchestrationAgent:
         logger.info(">>> user=...%s  conv=%s  msg=%r", short_uid, active_conv, text[:80])
         logger.debug("    history_len=%d", len(self._history[user_id]))
 
+        # Always handle bot commands first — even in passthrough mode.
+        # Bot commands must never reach Claude Code.
+        from config import COMMAND_PREFIX
+        if text.strip().startswith(COMMAND_PREFIX):
+            from bot.commands import handle_command
+            result = await handle_command(user_id, text)
+            if result is not None:
+                return result
+            logger.debug("    unknown command, falling through to LLM")
+
         # Passthrough mode: if enabled and active session, bypass LLM
         if self._passthrough[user_id] and active_conv:
             try: