fix(copilot): recognize enterprise subdomains in host checks

The earlier enterprise base URL change (proxy-ep parsing) gave us URLs
like `api.enterprise.githubcopilot.com`, but ~15 host-matching call
sites still hard-coded `api.githubcopilot.com`. Enterprise users would
therefore drop the `Copilot-Integration-Id: vscode-chat` header at
client-build time, and upstream rejected requests with:

    The requested model is not available for integrator "zed"
    (or "copilot-language-server") — verify the correct
    Copilot-Integration-Id header is being sent.

The header was correct in copilot_default_headers(); it just never
made it into default_headers for non-default hostnames because every
detector compared against the exact string "api.githubcopilot.com".

This commit broadens all those checks to "githubcopilot.com" via
base_url_host_matches (which already does proper subdomain matching),
so api.enterprise.githubcopilot.com, api.business.githubcopilot.com,
etc. all share the same headers, vision routing, max_completion_tokens
selection, and reasoning-effort detection as the default endpoint.

Also adds ".githubcopilot.com" to _URL_TO_PROVIDER so context-window
resolution via models.dev works for enterprise base URLs, and tightens
_is_github_copilot_url to use suffix matching instead of strict equality.

Tests:
- New: enterprise Copilot endpoint preserves Copilot-Integration-Id
- New: enterprise endpoint returns max_completion_tokens (not max_tokens)
- Existing 333 base_url / copilot / aux-client / credential-pool tests pass

Parts 5 of #7731.

agent/agent_init.py

@@ -828,7 +828,7 @@ def init_agent(
                 client_kwargs["default_headers"] = build_nvidia_nim_headers(effective_base)
             elif base_url_host_matches(effective_base, "api.routermint.com"):
                 client_kwargs["default_headers"] = _ra()._routermint_headers()
-            elif base_url_host_matches(effective_base, "api.githubcopilot.com"):
+            elif base_url_host_matches(effective_base, "githubcopilot.com"):
                 from hermes_cli.models import copilot_default_headers
 
                 client_kwargs["default_headers"] = copilot_default_headers()

agent/auxiliary_client.py

@@ -1624,7 +1624,7 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
             extra = {}
             if base_url_host_matches(base_url, "api.kimi.com"):
                 extra["default_headers"] = {"User-Agent": "claude-code/0.1.0"}
-            elif base_url_host_matches(base_url, "api.githubcopilot.com"):
+            elif base_url_host_matches(base_url, "githubcopilot.com"):
                 from hermes_cli.models import copilot_default_headers
 
                 extra["default_headers"] = copilot_default_headers()
@@ -1664,7 +1664,7 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
         extra = {}
         if base_url_host_matches(base_url, "api.kimi.com"):
             extra["default_headers"] = {"User-Agent": "claude-code/0.1.0"}
-        elif base_url_host_matches(base_url, "api.githubcopilot.com"):
+        elif base_url_host_matches(base_url, "githubcopilot.com"):
             from hermes_cli.models import copilot_default_headers
 
             extra["default_headers"] = copilot_default_headers()
@@ -2954,7 +2954,7 @@ def _recoverable_pool_provider(
         return "nous"
     if base_url_host_matches(base, "api.anthropic.com"):
         return "anthropic"
-    if base_url_host_matches(base, "api.githubcopilot.com"):
+    if base_url_host_matches(base, "githubcopilot.com"):
         return "copilot"
     if base_url_host_matches(base, "api.kimi.com"):
         return "kimi-coding"
@@ -3823,7 +3823,7 @@ 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"] = build_or_headers()
-    elif base_url_host_matches(sync_base_url, "api.githubcopilot.com"):
+    elif base_url_host_matches(sync_base_url, "githubcopilot.com"):
         from hermes_cli.copilot_auth import copilot_request_headers
 
         async_kwargs["default_headers"] = copilot_request_headers(
@@ -4128,7 +4128,7 @@ def resolve_provider_client(
                 extra["default_query"] = _dq
             if base_url_host_matches(custom_base, "api.kimi.com"):
                 extra["default_headers"] = {"User-Agent": "claude-code/0.1.0"}
-            elif base_url_host_matches(custom_base, "api.githubcopilot.com"):
+            elif base_url_host_matches(custom_base, "githubcopilot.com"):
                 from hermes_cli.copilot_auth import copilot_request_headers
                 extra["default_headers"] = copilot_request_headers(
                     is_agent_turn=True, is_vision=is_vision
@@ -4381,7 +4381,7 @@ def resolve_provider_client(
         headers = {}
         if base_url_host_matches(base_url, "api.kimi.com"):
             headers["User-Agent"] = "claude-code/0.1.0"
-        elif base_url_host_matches(base_url, "api.githubcopilot.com"):
+        elif base_url_host_matches(base_url, "githubcopilot.com"):
             from hermes_cli.copilot_auth import copilot_request_headers
 
             headers.update(copilot_request_headers(
@@ -4854,9 +4854,14 @@ def auxiliary_max_tokens_param(value: int, *, model: Optional[str] = None) -> di
     or_key = os.getenv("OPENROUTER_API_KEY")
     # Use max_completion_tokens for direct OpenAI-compatible providers that reject
     # max_tokens on newer GPT-4o/o-series/GPT-5-style models.
+    _custom_host = base_url_hostname(custom_base) or ""
     if (not or_key
             and _read_nous_auth() is None
-            and base_url_hostname(custom_base) in {"api.openai.com", "api.githubcopilot.com"}):
+            and (
+                _custom_host == "api.openai.com"
+                or _custom_host == "api.githubcopilot.com"
+                or _custom_host.endswith(".githubcopilot.com")
+            )):
         return {"max_completion_tokens": value}
     # ...and for any caller serving a newer OpenAI-family model by name.
     if model_forces_max_completion_tokens(model):

agent/chat_completion_helpers.py

@@ -632,7 +632,7 @@ def build_api_kwargs(agent, api_messages: list) -> dict:
         _ct = agent._get_transport()
         is_github_responses = (
             base_url_host_matches(agent.base_url, "models.github.ai")
-            or base_url_host_matches(agent.base_url, "api.githubcopilot.com")
+            or base_url_host_matches(agent.base_url, "githubcopilot.com")
         )
         is_codex_backend = (
             agent.provider == "openai-codex"
@@ -702,7 +702,7 @@ def build_api_kwargs(agent, api_messages: list) -> dict:
     _is_or = agent._is_openrouter_url()
     _is_gh = (
         base_url_host_matches(agent._base_url_lower, "models.github.ai")
-        or base_url_host_matches(agent._base_url_lower, "api.githubcopilot.com")
+        or base_url_host_matches(agent._base_url_lower, "githubcopilot.com")
     )
     _is_nous = "nousresearch" in agent._base_url_lower
     _is_nvidia = "integrate.api.nvidia.com" in agent._base_url_lower

agent/model_metadata.py

@@ -429,6 +429,10 @@ _URL_TO_PROVIDER: Dict[str, str] = {
     "inference-api.nousresearch.com": "nous",
     "api.deepseek.com": "deepseek",
     "api.githubcopilot.com": "copilot",
+    # Enterprise Copilot endpoints look like api.enterprise.githubcopilot.com,
+    # api.business.githubcopilot.com, etc.  Match the suffix so context-window
+    # resolution works for enterprise accounts too.
+    ".githubcopilot.com": "copilot",
     "models.github.ai": "copilot",
     # GitHub Models free tier (Azure-hosted prototyping endpoint) — same
     # canonical provider as the Copilot API.  Hard per-request token cap