fix: ChatContext is not a sequence — use .items for len/list; add test suite

Bug fix:
- GemmaLLM.chat(): len(chat_ctx) → len(chat_ctx.items)
- GemmaLLM._compact_context(): list(chat_ctx) → list(chat_ctx.items)
  ChatContext in livekit-agents 1.7 is not iterable or sized directly;
  it exposes an .items list. The TypeError was silently killing all LLM
  responses (agent heard user but never spoke back).

Test suite (tests/):
- test_web_ui.py: static assets, token endpoint, LiveKit WS proxy
- test_llm_api.py: completion, tool calling, thinking-disabled latency, streaming
- test_mcp_tools.py: weather (Fahrenheit), time, memory, skills — all via
  docker exec + in-container MCP client
- test_agent_integration.py: process alive, worker registered, supervisord,
  container health, LiveKit API
- test_compaction.py: size-triggered compaction, system prompt preservation,
  short-context no-op
- conftest.py: shared fixtures (HTTPS client, token, LLM, docker exec helpers)
- Run with: .venv-tests/bin/python -m pytest tests/ -v

tests/conftest.py

@@ -0,0 +1,136 @@
+"""Shared fixtures for the Hope voice-assistant test suite.
+
+Tests run on the HOST machine against the live "voice" container:
+- HTTPS web UI  -> https://localhost:8090 (self-signed cert, verify=False)
+- Token server  -> http://127.0.0.1:8091 (host network mode)
+- LLM API       -> GEMMA_BASE_URL (default http://192.168.86.2:8023/v1)
+- In-container  -> docker exec voice ...
+"""
+
+import json
+import os
+import subprocess
+
+import httpx
+import pytest
+
+CONTAINER = "voice"
+WEB_BASE_URL = os.environ.get("VOICE_WEB_URL", "https://localhost:8090")
+TOKEN_URL = os.environ.get("VOICE_TOKEN_URL", "http://127.0.0.1:8091/token")
+GEMMA_BASE_URL = os.environ.get("GEMMA_BASE_URL", "http://192.168.86.2:8023/v1").rstrip("/")
+GEMMA_MODEL = os.environ.get("GEMMA_MODEL", "gemma-4-e4b")
+
+# Path to the agent's venv python inside the container (has mcp, livekit.agents)
+CONTAINER_PYTHON = "/opt/voice-agent/.venv/bin/python"
+AGENT_DIR_IN_CONTAINER = "/opt/voice-agent"
+
+
+def pytest_configure(config):
+    config.addinivalue_line("markers", "slow: marks tests as slow (LLM / network calls)")
+
+
+# ── docker helpers ───────────────────────────────────────────────────────────
+
+
+def docker_exec(*args, timeout=60, env=None, check=True) -> subprocess.CompletedProcess:
+    """Run a command inside the voice container. Returns CompletedProcess."""
+    cmd = ["docker", "exec"]
+    if env:
+        for k, v in env.items():
+            cmd += ["-e", f"{k}={v}"]
+    cmd += [CONTAINER, *args]
+    return subprocess.run(
+        cmd,
+        capture_output=True,
+        text=True,
+        timeout=timeout,
+        check=check,
+    )
+
+
+def docker_exec_python(
+    code: str, *, timeout=120, cwd=None, env=None, check=True
+) -> subprocess.CompletedProcess:
+    """Run a python snippet inside the container with the agent venv."""
+    return docker_exec(CONTAINER_PYTHON, "-c", code, timeout=timeout, env=env, check=check)
+
+
+# ── fixtures ─────────────────────────────────────────────────────────────────
+
+
+@pytest.fixture(scope="session")
+def base_url() -> str:
+    """Base URL of the web UI (HTTPS, self-signed)."""
+    return WEB_BASE_URL
+
+
+@pytest.fixture(scope="session")
+def client(base_url):
+    """httpx client for the HTTPS web UI with TLS verification disabled."""
+    with httpx.Client(base_url=base_url, verify=False, timeout=15) as c:
+        yield c
+
+
+@pytest.fixture(scope="session")
+def token() -> dict:
+    """Fetch a fresh LiveKit token from the token endpoint (direct, no proxy)."""
+    resp = httpx.post(TOKEN_URL, json={}, timeout=10)
+    resp.raise_for_status()
+    data = resp.json()
+    assert "token" in data, f"token endpoint did not return a token: {data.keys()}"
+    return data
+
+
+@pytest.fixture(scope="session")
+def llm_client():
+    """httpx client pointed at the Gemma LLM API (same one Hope uses)."""
+    with httpx.Client(base_url=GEMMA_BASE_URL, timeout=60) as c:
+        yield c
+
+
+@pytest.fixture(scope="session")
+def mcp_client_factory():
+    """Factory that runs an MCP stdio tool call inside the container.
+
+    Returns (result_text, is_error). Spawns the MCP server script via the
+    agent venv python and drives it with a raw JSON-RPC session using the
+    mcp client library (available in the container, not on the host).
+    """
+
+    def _call(script: str, tool_name: str, args: dict | None = None, env: dict | None = None) -> tuple[str, bool]:
+        import os as host_os
+
+        merged_env = {**host_os.environ, **(env or {})}
+        code = f"""
+import asyncio, json
+from mcp import ClientSession, StdioServerParameters
+from mcp.client.stdio import stdio_client
+
+async def main():
+    params = StdioServerParameters(
+        command={CONTAINER_PYTHON!r},
+        args=[{AGENT_DIR_IN_CONTAINER + "/" + script!r}],
+        env={json.dumps(merged_env)},
+    )
+    async with stdio_client(params) as (read, write):
+        async with ClientSession(read, write) as session:
+            await session.initialize()
+            result = await session.call_tool({tool_name!r}, {json.dumps(args or {})})
+            text = ""
+            for block in result.content:
+                if getattr(block, "type", None) == "text":
+                    text += block.text
+            print(json.dumps({{"text": text, "isError": bool(result.isError)}}))
+
+asyncio.run(main())
+"""
+        proc = docker_exec_python(code, timeout=120, check=False)
+        if proc.returncode != 0:
+            raise AssertionError(
+                f"MCP call {tool_name} failed (rc={proc.returncode}): "
+                f"stderr={proc.stderr[-800:]}"
+            )
+        data = json.loads(proc.stdout.strip().splitlines()[-1])
+        return data["text"], data["isError"]
+
+    return _call