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

agent/auxiliary_client.py

@@ -259,13 +259,68 @@ _PROVIDERS_WITHOUT_VISION: frozenset = frozenset({
     "kimi-coding-cn",
 })
 
-# OpenRouter app attribution headers
-_OR_HEADERS = {
+# OpenRouter app attribution headers (base — always sent)
+_OR_HEADERS_BASE = {
     "HTTP-Referer": "https://hermes-agent.nousresearch.com",
     "X-OpenRouter-Title": "Hermes Agent",
     "X-OpenRouter-Categories": "productivity,cli-agent",
 }
 
+# Truthy values for boolean env-var parsing.
+_TRUTHY_ENV_VALUES = frozenset({"1", "true", "yes", "on"})
+
+
+def build_or_headers(or_config: dict | None = None) -> dict:
+    """Build OpenRouter headers, optionally including response-cache headers.
+
+    Precedence for response cache: env var > config.yaml > default (enabled).
+
+    Environment variables:
+        ``HERMES_OPENROUTER_CACHE`` — truthy (``1``/``true``/``yes``/``on``)
+            enables caching; ``0``/``false``/``no``/``off`` disables.
+            Overrides ``openrouter.response_cache`` in config.yaml.
+        ``HERMES_OPENROUTER_CACHE_TTL`` — integer seconds (1-86400).
+            Overrides ``openrouter.response_cache_ttl`` in config.yaml.
+
+    *or_config* is the ``openrouter`` section from config.yaml.  When *None*,
+    falls back to reading config from disk via ``load_config()``.
+    """
+    headers = dict(_OR_HEADERS_BASE)
+
+    # Resolve config from disk if not provided.
+    if or_config is None:
+        try:
+            from hermes_cli.config import load_config
+            or_config = load_config().get("openrouter", {})
+        except Exception:
+            or_config = {}
+
+    # Determine cache enabled: env var overrides config.
+    env_cache = os.environ.get("HERMES_OPENROUTER_CACHE", "").strip().lower()
+    if env_cache:
+        cache_enabled = env_cache in _TRUTHY_ENV_VALUES
+    else:
+        cache_enabled = or_config.get("response_cache", False)
+
+    if not cache_enabled:
+        return headers
+
+    headers["X-OpenRouter-Cache"] = "true"
+
+    # Determine TTL: env var overrides config.
+    env_ttl = os.environ.get("HERMES_OPENROUTER_CACHE_TTL", "").strip()
+    if env_ttl:
+        if env_ttl.isdigit():
+            ttl = int(env_ttl)
+            if 1 <= ttl <= 86400:
+                headers["X-OpenRouter-Cache-TTL"] = str(ttl)
+    else:
+        ttl = or_config.get("response_cache_ttl", 300)
+        if isinstance(ttl, (int, float)) and 1 <= ttl <= 86400:
+            headers["X-OpenRouter-Cache-TTL"] = str(int(ttl))
+
+    return headers
+
 # Vercel AI Gateway app attribution headers. HTTP-Referer maps to
 # referrerUrl and X-Title maps to appName in the gateway's analytics.
 from hermes_cli import __version__ as _HERMES_VERSION
@@ -1158,14 +1213,14 @@ def _try_openrouter(explicit_api_key: str = None) -> Tuple[Optional[OpenAI], Opt
         base_url = _pool_runtime_base_url(entry, OPENROUTER_BASE_URL) or OPENROUTER_BASE_URL
         logger.debug("Auxiliary client: OpenRouter via pool")
         return OpenAI(api_key=or_key, base_url=base_url,
-                       default_headers=_OR_HEADERS), _OPENROUTER_MODEL
+                       default_headers=build_or_headers()), _OPENROUTER_MODEL
 
     or_key = explicit_api_key or os.getenv("OPENROUTER_API_KEY")
     if not or_key:
         return None, None
     logger.debug("Auxiliary client: OpenRouter")
     return OpenAI(api_key=or_key, base_url=OPENROUTER_BASE_URL,
-                   default_headers=_OR_HEADERS), _OPENROUTER_MODEL
+                   default_headers=build_or_headers()), _OPENROUTER_MODEL
 
 
 def _describe_openrouter_unavailable() -> str:
@@ -1911,7 +1966,7 @@ def _to_async_client(sync_client, model: str, is_vision: bool = False):
     }
     sync_base_url = str(sync_client.base_url)
     if base_url_host_matches(sync_base_url, "openrouter.ai"):
-        async_kwargs["default_headers"] = dict(_OR_HEADERS)
+        async_kwargs["default_headers"] = build_or_headers()
     elif base_url_host_matches(sync_base_url, "api.githubcopilot.com"):
         from hermes_cli.copilot_auth import copilot_request_headers