From 1fa25d8c3ab8b326ab698e40f774443917332dc6 Mon Sep 17 00:00:00 2001
From: "DistributedApps.AI" <kenhuangus@users.noreply.github.com>
Date: Mon, 31 Aug 2026 11:32:08 -0400
Subject: [PATCH] CI workflow (pytest + CLI demo + live smoke on py3.10/3.13);
 evolve CLI now reports test evaluation; add python -m wikiskill entry; README
 badges

---
 .github/workflows/ci.yml  | 27 +++++++++++++++++++++++++++
 README.md                 |  7 ++++++-
 smoke_test.py             |  3 +++
 src/wikiskill/__main__.py |  4 ++++
 src/wikiskill/cli.py      |  5 ++++-
 5 files changed, 44 insertions(+), 2 deletions(-)
 create mode 100644 .github/workflows/ci.yml
 create mode 100644 src/wikiskill/__main__.py

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
new file mode 100644
index 0000000..1277b83
--- /dev/null
+++ b/.github/workflows/ci.yml
@@ -0,0 +1,27 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10", "3.13"]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install
+        run: pip install -e ".[dev,ui]"
+      - name: Run tests
+        run: pytest -q --timeout=120
+      - name: CLI demo (mock, end-to-end)
+        run: python -m wikiskill.demo --root ci_demo --iterations 3
+      - name: Live-server smoke test
+        run: python smoke_test.py
diff --git a/README.md b/README.md
index 09a6f70..696f20b 100644
--- a/README.md
+++ b/README.md
@@ -1,5 +1,9 @@
 # WikiSkill — Implementation
 
+[![CI](https://github.com/kenhuangus/wikiskill/actions/workflows/ci.yml/badge.svg)](https://github.com/kenhuangus/wikiskill/actions/workflows/ci.yml)
+[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
+![Python](https://img.shields.io/badge/python-3.9%2B-blue)
+
 Python implementation of **"WikiSkill: Compiling Agent Experience into Persistent
 Knowledge for Skill Evolution"** (arXiv:2608.27454v1, Tang et al., Google Research).
 
@@ -81,8 +85,9 @@ Tabs (see `ui_design.md` for the full design):
 
 ```bash
 pip install -e ".[dev]"
-pytest                                  # 30 tests incl. UI + end-to-end loop
+pytest                                  # 29 tests: unit + end-to-end + UI
 python -m wikiskill.demo                # offline demo with the deterministic MockLLM
+python -m wikiskill serve               # same as `wikiskill serve`
 ```
 
 Demo output: a `wikiskill_demo_workspace/` with `raw/`, `wiki/`, `skills/` populated,
diff --git a/smoke_test.py b/smoke_test.py
index 704d410..de9ded8 100644
--- a/smoke_test.py
+++ b/smoke_test.py
@@ -1,5 +1,6 @@
 """Live smoke test: boots the real wikiskill serve stack and exercises it over HTTP."""
 import json
+import shutil
 import subprocess
 import sys
 import time
@@ -9,6 +10,8 @@ PORT = 8765
 BASE = f"http://127.0.0.1:{PORT}"
 ok = True
 
+shutil.rmtree("smoke_run", ignore_errors=True)  # fresh workspace per invocation
+
 
 def check(name, cond, extra=""):
     global ok
diff --git a/src/wikiskill/__main__.py b/src/wikiskill/__main__.py
new file mode 100644
index 0000000..0ef3024
--- /dev/null
+++ b/src/wikiskill/__main__.py
@@ -0,0 +1,4 @@
+from .cli import main
+
+if __name__ == "__main__":
+    raise SystemExit(main())
\ No newline at end of file
diff --git a/src/wikiskill/cli.py b/src/wikiskill/cli.py
index 8662a47..bb31b6c 100644
--- a/src/wikiskill/cli.py
+++ b/src/wikiskill/cli.py
@@ -79,7 +79,10 @@ def main(argv=None) -> int:
                                  ws=Workspace(args.root), tools=tools,
                                  K=args.iterations)
     result = orch.run()
-    print(json.dumps(result, indent=2))
+    # Paper §4: report final skills vs no-skill baseline on the test split with
+    # paired bootstrap significance (paper Appendix C).
+    evaluation = orch.evaluate_test()
+    print(json.dumps({**result, "evaluation": evaluation}, indent=2))
     return 0