fix: custom endpoint no longer leaks OPENROUTER_API_KEY (#560)

API key selection is now base_url-aware: when the resolved base_url
targets OpenRouter, OPENROUTER_API_KEY takes priority (preserving the
#289 fix). When hitting any other endpoint (Z.ai, vLLM, custom, etc.),
OPENAI_API_KEY takes priority so the OpenRouter key doesn't leak.

Applied in both the runtime provider resolver (the real code path) and
the CLI initial default (for consistency).

Fixes #560.

cli.py

@@ -870,7 +870,13 @@ class HermesCLI:
             or os.getenv("OPENAI_BASE_URL")
             or os.getenv("OPENROUTER_BASE_URL", CLI_CONFIG["model"]["base_url"])
         )
-        self.api_key = api_key or os.getenv("OPENROUTER_API_KEY") or os.getenv("OPENAI_API_KEY")
+        # Match key to resolved base_url: OpenRouter URL → prefer OPENROUTER_API_KEY,
+        # custom endpoint → prefer OPENAI_API_KEY (issue #560).
+        # Note: _ensure_runtime_credentials() re-resolves this before first use.
+        if "openrouter.ai" in self.base_url:
+            self.api_key = api_key or os.getenv("OPENROUTER_API_KEY") or os.getenv("OPENAI_API_KEY")
+        else:
+            self.api_key = api_key or os.getenv("OPENAI_API_KEY") or os.getenv("OPENROUTER_API_KEY")
         self._nous_key_expires_at: Optional[str] = None
         self._nous_key_source: Optional[str] = None
         # Max turns priority: CLI arg > config file > env var > default

hermes_cli/runtime_provider.py

@@ -72,12 +72,25 @@ def _resolve_openrouter_runtime(
         or OPENROUTER_BASE_URL
     ).rstrip("/")
 
-    api_key = (
-        explicit_api_key
-        or os.getenv("OPENROUTER_API_KEY")
-        or os.getenv("OPENAI_API_KEY")
-        or ""
-    )
+    # Choose API key based on whether the resolved base_url targets OpenRouter.
+    # When hitting OpenRouter, prefer OPENROUTER_API_KEY (issue #289).
+    # When hitting a custom endpoint, prefer OPENAI_API_KEY so the OpenRouter
+    # key doesn't leak to an unrelated provider (issue #560).
+    _is_openrouter_url = "openrouter.ai" in base_url
+    if _is_openrouter_url:
+        api_key = (
+            explicit_api_key
+            or os.getenv("OPENROUTER_API_KEY")
+            or os.getenv("OPENAI_API_KEY")
+            or ""
+        )
+    else:
+        api_key = (
+            explicit_api_key
+            or os.getenv("OPENAI_API_KEY")
+            or os.getenv("OPENROUTER_API_KEY")
+            or ""
+        )
 
     source = "explicit" if (explicit_api_key or explicit_base_url) else "env/config"
 

tests/test_runtime_provider_resolution.py

@@ -121,6 +121,43 @@ def test_openai_key_used_when_no_openrouter_key(monkeypatch):
     assert resolved["api_key"] == "sk-openai-fallback"
 
 
+def test_custom_endpoint_prefers_openai_key(monkeypatch):
+    """Custom endpoint should use OPENAI_API_KEY, not OPENROUTER_API_KEY.
+
+    Regression test for #560: when base_url is a non-OpenRouter endpoint,
+    OPENROUTER_API_KEY was being sent as the auth header instead of OPENAI_API_KEY.
+    """
+    monkeypatch.setattr(rp, "resolve_provider", lambda *a, **k: "openrouter")
+    monkeypatch.setattr(rp, "_get_model_config", lambda: {})
+    monkeypatch.setenv("OPENAI_BASE_URL", "https://api.z.ai/api/coding/paas/v4")
+    monkeypatch.delenv("OPENROUTER_BASE_URL", raising=False)
+    monkeypatch.setenv("OPENAI_API_KEY", "sk-zai-correct-key")
+    monkeypatch.setenv("OPENROUTER_API_KEY", "sk-or-wrong-key-for-zai")
+
+    resolved = rp.resolve_runtime_provider(requested="custom")
+
+    assert resolved["base_url"] == "https://api.z.ai/api/coding/paas/v4"
+    assert resolved["api_key"] == "sk-zai-correct-key"
+
+
+def test_custom_endpoint_auto_provider_prefers_openai_key(monkeypatch):
+    """Auto provider with non-OpenRouter base_url should prefer OPENAI_API_KEY.
+
+    Same as #560 but via 'hermes model' flow which sets provider to 'auto'.
+    """
+    monkeypatch.setattr(rp, "resolve_provider", lambda *a, **k: "openrouter")
+    monkeypatch.setattr(rp, "_get_model_config", lambda: {})
+    monkeypatch.setenv("OPENAI_BASE_URL", "https://my-vllm-server.example.com/v1")
+    monkeypatch.delenv("OPENROUTER_BASE_URL", raising=False)
+    monkeypatch.setenv("OPENAI_API_KEY", "sk-vllm-key")
+    monkeypatch.setenv("OPENROUTER_API_KEY", "sk-or-should-not-leak")
+
+    resolved = rp.resolve_runtime_provider(requested="auto")
+
+    assert resolved["base_url"] == "https://my-vllm-server.example.com/v1"
+    assert resolved["api_key"] == "sk-vllm-key"
+
+
 def test_resolve_requested_provider_precedence(monkeypatch):
     monkeypatch.setenv("HERMES_INFERENCE_PROVIDER", "nous")
     monkeypatch.setattr(rp, "_get_model_config", lambda: {"provider": "openai-codex"})