From f3c90166761861df987cc416653ad2cf7abbb64a Mon Sep 17 00:00:00 2001
From: ArthurErlich <a.erlich@live.de>
Date: Sun, 6 Sep 2026 16:54:43 +0200
Subject: [PATCH] Add README

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CRnb5Gqdu7gVTQrwAqFdfJ
---
 README.md | 69 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 69 insertions(+)
 create mode 100644 README.md

diff --git a/README.md b/README.md
new file mode 100644
index 0000000..bfbf303
--- /dev/null
+++ b/README.md
@@ -0,0 +1,69 @@
+# delegate-ai-mcp
+
+An MCP server that lets Claude Code delegate light, low-stakes work to a local
+[qwen-code](https://github.com/QwenLM/qwen-code) CLI instance, instead of spending its own
+budget on it.
+
+## How it works
+
+- `src/qwen-delegate.ts` — core logic: spawns `qwen -p "<prompt>"`, captures stdout, handles
+  timeouts and errors. Exported separately from the MCP wiring so it's unit-testable without a
+  live MCP connection or a live qwen endpoint.
+- `src/qwen-delegate-server.ts` — thin MCP stdio server exposing one tool, `qwen_delegate`.
+
+qwen-code runs natively on Windows here (no WSL), backed by a local OpenAI-compatible model
+proxy configured in `~/.qwen/settings.json`. See `research/qwen-mcp-delegation.md` for how that
+was confirmed. Replies can take several minutes on a cold local model, so the tool uses a
+generous (10 min) timeout rather than trying to enforce "light work" in code — that's a
+judgment call left to whoever's calling the tool.
+
+## Prerequisites
+
+- Node.js 24+ (the server runs `.ts` source directly via Node's native TypeScript
+  type-stripping — no build step, no compiler)
+- `qwen` on `PATH` and working (`qwen -p "test"` should return a reply)
+
+## Setup
+
+```bash
+npm install
+npm test
+```
+
+## Register with Claude Code
+
+Global (available in every project):
+
+```bash
+claude mcp add --scope user qwen-delegate -- node /absolute/path/to/src/qwen-delegate-server.ts
+```
+
+Verify it connected:
+
+```bash
+claude mcp list
+```
+
+## Usage
+
+Once registered, Claude Code can call the `qwen_delegate` tool directly. The routing
+convention — *when* to delegate — lives in `~/.claude/CLAUDE.md` under "Delegating light work
+to qwen": simple lookups, quick research, boilerplate text, small single-file edits. Claude
+decides per-request; there's no enforced dispatcher.
+
+## Testing
+
+```bash
+npm test
+```
+
+Runs `test/qwen-delegate.test.ts` on Node's built-in test runner (`node --test`) — no test
+framework dependency. The subprocess spawn is mocked, so tests run in milliseconds and don't
+require a live `qwen` install.
+
+## Status / roadmap
+
+Project conventions (build/typecheck strategy, lint/format tooling, multi-tool source
+structure, publish-shaped `package.json`) are being worked through a
+[wayfinder map](https://git.arthurerlich.de/haylan/delegate-ai-mcp/issues/1) on this repo's
+issue tracker — see `docs/agents/issue-tracker.md` for how issues/tickets work here.