feat: integrate MiniMax Code as a native ACP agent (#4846)

* feat: integrate MiniMax Code as an ACP agent

* Potential fix for pull request finding

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

README.md

@@ -210,6 +210,23 @@ That prompt is intended for coding agents. It tells the agent to clone the repo
    - Codex CLI reads `~/.codex/auth.json`
    - Claude Code accepts `CLAUDE_CODE_OAUTH_TOKEN`, `ANTHROPIC_AUTH_TOKEN`, `CLAUDE_CODE_CREDENTIALS_PATH`, or `~/.claude/.credentials.json`
    - ACP agent entries are separate from model providers — if you configure `acp_agents.codex`, point it at a Codex ACP adapter such as `npx -y @zed-industries/codex-acp`
+   - MiniMax Code speaks ACP directly. Install and authenticate it, then add it as an ACP agent:
+
+   ```bash
+   npm install --global @minimax-ai/code
+   mcode login
+   ```
+
+   ```yaml
+   acp_agents:
+     mcode:
+       command: mcode
+       args: ["acp"]
+       description: MiniMax Code for implementation, refactoring, debugging, and repository tasks
+       auto_approve_permissions: false
+   ```
+
+   `mcode` must be on the Gateway process's `PATH`; installing it only on the Docker host does not make it available inside the Gateway container. DeerFlow invokes it through `invoke_acp_agent` in a per-thread ACP workspace and forwards enabled MCP servers. Keep `auto_approve_permissions: false` for untrusted tasks; enable it only when MCode must edit files or run commands and you trust the task.
    - On macOS, export Claude Code auth explicitly if needed:
 
    ```bash

README_zh.md

@@ -196,6 +196,23 @@ DeerFlow 新近集成了 BytePlus 自研的智能搜索与抓取工具集——[
    - Codex CLI 会读取 `~/.codex/auth.json`
    - Claude Code 支持 `CLAUDE_CODE_OAUTH_TOKEN`、`ANTHROPIC_AUTH_TOKEN`、`CLAUDE_CODE_CREDENTIALS_PATH`，或 `~/.claude/.credentials.json`
    - ACP agent 条目与 model provider 是分开配置的——如果你配置了 `acp_agents.codex`，请把它指向一个 Codex ACP 适配器，例如 `npx -y @zed-industries/codex-acp`
+   - MiniMax Code 原生支持 ACP，不需要额外适配器。先安装并登录，再把它配置成 ACP agent：
+
+   ```bash
+   npm install --global @minimax-ai/code
+   mcode login
+   ```
+
+   ```yaml
+   acp_agents:
+     mcode:
+       command: mcode
+       args: ["acp"]
+       description: MiniMax Code for implementation, refactoring, debugging, and repository tasks
+       auto_approve_permissions: false
+   ```
+
+   `mcode` 必须位于 Gateway 进程的 `PATH` 中；只安装在 Docker host 上并不会让 Gateway 容器内可用。DeerFlow 会通过 `invoke_acp_agent` 在每个 thread 独立的 ACP workspace 中调用 MCode，并转发已启用的 MCP server。处理不可信任务时请保持 `auto_approve_permissions: false`；只有在任务可信且确实需要 MCode 修改文件或执行命令时才启用它。
    - 在 macOS 上，如有需要可显式导出 Claude Code 的认证信息：
 
    ```bash

backend/docs/CONFIGURATION.md

@@ -742,7 +742,7 @@ To keep this off the default attack surface:
 > for CLI auto-auth in **all** modes. These hold long-lived CLI credentials;
 > scope or omit them when the gateway runs untrusted workloads.
 
-### CLI Credential Mounts (Claude Code / Codex)
+### CLI Credential Mounts (Claude Code / Codex / MiniMax Code)
 
 DeerFlow can reuse your Claude Code / Codex CLI subscription login as a model
 provider (`ClaudeChatModel`, the Codex provider) or for ACP agents that run the
@@ -771,6 +771,16 @@ adapter's documented env auth, and reach for the
 `docker-compose.cli-auth.yaml` overlay only as a fallback for an adapter that
 genuinely reads the full CLI config directory.
 
+MiniMax Code is a native ACP agent, so it does not need an adapter. For local
+Gateway runs, install it with `npm install --global @minimax-ai/code`, run
+`mcode login`, and configure `acp_agents.mcode` with `command: mcode` and
+`args: ["acp"]`. The executable and its authenticated runtime must be available
+inside the Gateway environment; a host-only installation is not visible to a
+Docker container. DeerFlow forwards enabled MCP servers to the MCode session.
+Leave `auto_approve_permissions` disabled for untrusted tasks, and enable it
+only when the agent is expected to edit files or run commands for a trusted
+task.
+
 
 ## Best Practices
 

backend/packages/harness/deerflow/tools/AGENTS.md

@@ -31,5 +31,7 @@ E2B output sync records remote file versions and actual host file metadata in a
 **ACP agent tools**:
 - `invoke_acp_agent` - Invokes external ACP-compatible agents from `config.yaml`
 - ACP launchers must be real ACP adapters. The standard `codex` CLI is not ACP-compatible by itself; configure a wrapper such as `npx -y @zed-industries/codex-acp` or an installed `codex-acp` binary
+- MiniMax Code speaks ACP directly: configure `command: mcode` with `args: ["acp"]`. It receives DeerFlow's enabled MCP servers and uses the per-thread ACP workspace; the Gateway process must have an authenticated `mcode` executable on `PATH`
+- ACP results collect only `agent_message_chunk` text. Thought chunks remain internal and must not be concatenated into the tool result
 - Missing ACP executables now return an actionable error message instead of a raw `[Errno 2]`
 - Each ACP agent uses a per-thread workspace at `{base_dir}/users/{user_id}/threads/{thread_id}/acp-workspace/`. The workspace is accessible to the lead agent via the virtual path `/mnt/acp-workspace/` (read-only). In docker sandbox mode, the directory is volume-mounted into the container at `/mnt/acp-workspace` (read-only); in local sandbox mode, path translation is handled by `tools.py`

backend/packages/harness/deerflow/tools/builtins/invoke_acp_agent_tool.py

@@ -134,6 +134,11 @@ def _format_invocation_error(agent: str, cmd: str, exc: Exception) -> str:
     if cmd == "codex-acp" and shutil.which("codex"):
         return f"{message} The installed `codex` CLI does not speak ACP directly. Install a Codex ACP adapter (for example `npx @zed-industries/codex-acp`) or update `acp_agents.codex.command` and `args` in config.yaml."
 
+    if agent == "mcode":
+        return (
+            f"{message} Install it with `npm install --global @minimax-ai/code`, run `mcode login`, and restart DeerFlow so it inherits the updated PATH. "
+            "If the Gateway runs in Docker, ensure `mcode` is installed and authenticated inside the Gateway container/image."
+        )
     return f"{message} Install the agent binary or update `acp_agents.{agent}.command` in config.yaml."
 
 
@@ -193,7 +198,7 @@ def build_invoke_acp_agent_tool(agents: dict) -> BaseTool:
                 try:
                     from acp.schema import TextContentBlock
 
-                    if hasattr(update, "content") and isinstance(update.content, TextContentBlock):
+                    if getattr(update, "session_update", None) == "agent_message_chunk" and isinstance(update.content, TextContentBlock):
                         self._chunks.append(update.content.text)
                 except Exception:
                     pass

backend/tests/test_invoke_acp_agent_tool.py

@@ -14,6 +14,7 @@ from deerflow.tools.builtins.invoke_acp_agent_tool import (
     _build_acp_mcp_servers,
     _build_mcp_servers,
     _build_permission_response,
+    _format_invocation_error,
     _get_work_dir,
     build_invoke_acp_agent_tool,
 )
@@ -122,6 +123,14 @@ def test_build_permission_response_denies_when_auto_approve_false():
     assert response.outcome.outcome == "cancelled"
 
 
+def test_missing_mcode_command_returns_install_and_login_guidance():
+    result = _format_invocation_error("mcode", "mcode", FileNotFoundError())
+
+    assert "npm install --global @minimax-ai/code" in result
+    assert "mcode login" in result
+    assert "restart DeerFlow" in result
+
+
 @pytest.mark.anyio
 async def test_build_invoke_tool_description_and_unknown_agent_error():
     tool = build_invoke_acp_agent_tool(
@@ -223,7 +232,17 @@ async def test_invoke_acp_agent_uses_fixed_acp_workspace(monkeypatch, tmp_path):
             client = captured["client"]
             await client.session_update(
                 "session-1",
-                SimpleNamespace(content=text_content_block("ACP result")),
+                SimpleNamespace(
+                    session_update="agent_thought_chunk",
+                    content=text_content_block("internal reasoning"),
+                ),
+            )
+            await client.session_update(
+                "session-1",
+                SimpleNamespace(
+                    session_update="agent_message_chunk",
+                    content=text_content_block("ACP result"),
+                ),
             )
 
     class DummyProcessContext:

config.example.yaml

@@ -1494,6 +1494,15 @@ sandbox:
 # Configure external ACP-compatible agents for the built-in `invoke_acp_agent` tool.
 
 # acp_agents:
+#   mcode:
+#     # MiniMax Code speaks ACP directly; no adapter package is required.
+#     # Install with `npm install --global @minimax-ai/code`, then run `mcode login`.
+#     command: mcode
+#     args: ["acp"]
+#     description: MiniMax Code for implementation, refactoring, debugging, and repository tasks
+#     # auto_approve_permissions: false  # Enable only for trusted tasks that need MCode to edit files or run commands
+#     # timeout_seconds: 1800            # Abort + kill the subprocess if it doesn't respond in time (default: 1800 = 30 min)
+#
 #   claude_code:
 #     # DeerFlow expects an ACP adapter here. The standard `claude` CLI does not
 #     # speak ACP directly. Install `claude-agent-acp` separately or use: