feat(openrouter): add response caching support (#19132)

Enable OpenRouter's response caching feature (beta) via X-OpenRouter-Cache
headers. When enabled, identical API requests return cached responses for
free (zero billing), reducing both latency and cost.

Configuration via config.yaml:
  openrouter:
    response_cache: true       # default: on
    response_cache_ttl: 300    # 1-86400 seconds

Changes:
- Add openrouter config section to DEFAULT_CONFIG (response_cache + TTL)
- Add build_or_headers() in auxiliary_client.py that builds attribution
  headers plus optional cache headers based on config
- Replace inline _OR_HEADERS dicts with build_or_headers() at all 5 sites:
  run_agent.py __init__, _apply_client_headers_for_base_url(), and
  auxiliary_client.py _try_openrouter() + _to_async_client()
- Add _check_openrouter_cache_status() method to AIAgent that reads
  X-OpenRouter-Cache-Status from streaming response headers and logs
  HIT/MISS status
- Document in cli-config.yaml.example
- Add 28 tests (22 unit + 6 integration)

Ref: https://openrouter.ai/docs/guides/features/response-caching

tests/run_agent/test_provider_attribution_headers.py

@@ -81,3 +81,51 @@ def test_unknown_base_url_clears_default_headers(mock_openai):
     agent._apply_client_headers_for_base_url("https://api.example.com/v1")
 
     assert "default_headers" not in agent._client_kwargs
+
+
+@patch("run_agent.OpenAI")
+def test_openrouter_headers_include_response_cache_when_enabled(mock_openai):
+    """When openrouter.response_cache is True, the cache header is injected."""
+    mock_openai.return_value = MagicMock()
+    agent = AIAgent(
+        api_key="test-key",
+        base_url="https://openrouter.ai/api/v1",
+        model="test/model",
+        quiet_mode=True,
+        skip_context_files=True,
+        skip_memory=True,
+    )
+
+    with patch("hermes_cli.config.load_config", return_value={
+        "openrouter": {"response_cache": True, "response_cache_ttl": 600},
+    }):
+        agent._apply_client_headers_for_base_url("https://openrouter.ai/api/v1")
+
+    headers = agent._client_kwargs["default_headers"]
+    assert headers["HTTP-Referer"] == "https://hermes-agent.nousresearch.com"
+    assert headers["X-OpenRouter-Cache"] == "true"
+    assert headers["X-OpenRouter-Cache-TTL"] == "600"
+
+
+@patch("run_agent.OpenAI")
+def test_openrouter_headers_no_cache_when_disabled(mock_openai):
+    """When openrouter.response_cache is False, no cache headers are sent."""
+    mock_openai.return_value = MagicMock()
+    agent = AIAgent(
+        api_key="test-key",
+        base_url="https://openrouter.ai/api/v1",
+        model="test/model",
+        quiet_mode=True,
+        skip_context_files=True,
+        skip_memory=True,
+    )
+
+    with patch("hermes_cli.config.load_config", return_value={
+        "openrouter": {"response_cache": False},
+    }):
+        agent._apply_client_headers_for_base_url("https://openrouter.ai/api/v1")
+
+    headers = agent._client_kwargs["default_headers"]
+    assert headers["HTTP-Referer"] == "https://hermes-agent.nousresearch.com"
+    assert "X-OpenRouter-Cache" not in headers
+    assert "X-OpenRouter-Cache-TTL" not in headers