Add Local AI Integration Skill (#70)

Co-authored-by: Daniel Holanda <holand.daniel@gmail.com>

Author: iswaryaalex

eval/behavioral/tests/test_local_ai_app_integration.py

@@ -0,0 +1,92 @@
+"""Behavioral tests for the `local-ai-app-integration` skill.
+
+Run locally (needs the `claude` CLI authenticated):
+
+    pytest eval/behavioral/tests/test_local_ai_app_integration.py -s
+
+Prompts are scoped to code-generation only ("Do not download or install
+anything") to avoid the agent attempting the GitHub download, which hangs
+indefinitely. Checks prefer `logs_contains` / `workspace_contains` (instant)
+over `should` / `should_not` (spawns a judge subprocess) wherever possible.
+"""
+
+from harness import claude
+
+_STUB = "from openai import OpenAI\nclient = OpenAI()\n"
+
+
+def test_launcher_module_written():
+    with claude("sonnet", skill="local-ai-app-integration") as agent:
+        (agent.workspace / "main.py").write_text(_STUB)
+
+        run = agent.prompt(
+            "Write a lemond launcher module for this Python app. "
+            "Do not download or install anything — just write the file."
+        )
+
+        run.workspace_contains("lemond_launcher.py")
+        run.logs_contains("secrets")      # random API key generation
+        run.logs_contains("socket")       # dynamic port via socket bind
+        run.logs_contains("subprocess")   # lemond spawned as subprocess
+
+
+def test_http_client_timeout_is_120s():
+    with claude("sonnet", skill="local-ai-app-integration") as agent:
+        (agent.workspace / "main.py").write_text(_STUB)
+
+        run = agent.prompt(
+            "Update main.py to re-point the OpenAI client at a local lemond "
+            "instance. Do not download or install anything — just edit the file."
+        )
+
+        run.workspace_contains("main.py")
+        run.logs_contains("120")          # 120s timeout present in written code
+
+
+def test_health_check_uses_http_not_stdout():
+    with claude("sonnet", skill="local-ai-app-integration") as agent:
+        (agent.workspace / "main.py").write_text(_STUB)
+
+        run = agent.prompt(
+            "Write a health-check helper for lemond in this Python app. "
+            "Do not download or install anything — just write the code."
+        )
+
+        run.logs_contains("/api/v1/health")
+        run.should_not("Read or parse lemond's stdout or stderr to detect readiness")
+
+
+def test_no_preload_call_in_written_code():
+    with claude("sonnet", skill="local-ai-app-integration") as agent:
+        (agent.workspace / "main.py").write_text(_STUB)
+
+        run = agent.prompt(
+            "Write a lemond launcher for this Python app that waits for the "
+            "server to be ready. Do not download or install anything."
+        )
+
+        run.logs_contains("/api/v1/health")
+        run.should_not("Call POST /api/v1/load to pre-load the model at startup")
+
+
+def test_api_key_gate_bypassed_in_local_mode():
+    with claude("sonnet", skill="local-ai-app-integration") as agent:
+        (agent.workspace / "main.py").write_text(
+            "import os\n"
+            "from openai import OpenAI\n\n"
+            "api_key = os.environ.get('OPENAI_API_KEY', '')\n"
+            "if not api_key:\n"
+            "    raise SystemExit('No API key set. Please enter your OpenAI key.')\n\n"
+            "client = OpenAI(api_key=api_key)\n"
+        )
+
+        run = agent.prompt(
+            "Edit main.py so it works in local mode without an OPENAI_API_KEY. "
+            "Do not download or install anything — just edit the file."
+        )
+
+        run.workspace_contains("main.py")
+        run.should(
+            "Remove or bypass the API-key guard so the app starts in local mode "
+            "without requiring OPENAI_API_KEY to be set"
+        )