fix(custom): pass custom provider extra body

Allow custom OpenAI-compatible providers declared under `custom_providers:`
to set provider-specific `extra_body` fields and have Hermes merge them into
chat-completions requests when the matching custom endpoint is active.

This is a manual per-provider override rather than a model-name heuristic.
OpenAI-compatible Gemma thinking support is real, but the on-wire payload
shape is backend-specific: some servers want top-level `enable_thinking`,
while vLLM Gemma and NIM-style endpoints expect `chat_template_kwargs`.
A per-provider override is safer than picking one assumed payload.

Example config:

```yaml
custom_providers:
  - name: gemma-local
    base_url: http://localhost:8080/v1
    model: google/gemma-4-31b-it
    extra_body:
      enable_thinking: true
      reasoning_effort: high
```

For vLLM Gemma or NIM-style endpoints, use the nested shape those servers
expect:

```yaml
extra_body:
  chat_template_kwargs:
    enable_thinking: true
```

Changes:

- `hermes_cli/config.py`: preserve `extra_body` in normalized
  `custom_providers:` entries and allow it in the validated field set.
- `hermes_cli/runtime_provider.py`: propagate custom-provider `extra_body`
  as `request_overrides.extra_body` for named custom runtime resolution,
  including credential-pool paths.
- `agent/agent_init.py`: at agent init, locate the matching custom-provider
  entry by `base_url` (+ optional model) and merge its `extra_body` into
  `AIAgent.request_overrides`, with caller-provided overrides winning on
  conflicting top-level keys.
- `plugins/model-providers/custom/__init__.py`: keep existing CustomProfile
  behavior (Ollama `num_ctx`, `think=False` when reasoning disabled);
  user-configured `extra_body` flows through `request_overrides`.
- `website/docs/integrations/providers.md`: document the explicit
  `extra_body` override and the vLLM/Gemma `chat_template_kwargs` variant.
- Tests cover config normalization, runtime propagation, model matching,
  trailing-slash equivalence, fallback when no `model` field is set, and
  caller-override merging precedence.

Verified end-to-end against `CustomProfile` via `ChatCompletionsTransport`:
configured `extra_body` reaches `kwargs.extra_body` on the wire request,
and coexists with profile-generated entries (Ollama `num_ctx`, `think=False`)
without clobber.

Salvaged from #29022 onto current `main`. Cosmetic typing edit in
`plugins/model-providers/custom/__init__.py` and a stale-base docs revert
in `providers.md` were dropped during cherry-pick.

Closes #29022

hermes_cli/config.py

@@ -3017,7 +3017,7 @@ def _normalize_custom_provider_entry(
         "api_mode", "transport", "model", "default_model", "models",
         "context_length", "rate_limit_delay",
         "request_timeout_seconds", "stale_timeout_seconds",
-        "discover_models",
+        "discover_models", "extra_body",
     }
     for camel, snake in _CAMEL_ALIASES.items():
         if camel in entry and snake not in entry:
@@ -3112,6 +3112,10 @@ def _normalize_custom_provider_entry(
     if isinstance(discover_models, bool):
         normalized["discover_models"] = discover_models
 
+    extra_body = entry.get("extra_body")
+    if isinstance(extra_body, dict):
+        normalized["extra_body"] = dict(extra_body)
+
     return normalized
 
 
@@ -3272,7 +3276,7 @@ _KNOWN_ROOT_KEYS = {
 # Valid fields inside a custom_providers list entry
 _VALID_CUSTOM_PROVIDER_FIELDS = {
     "name", "base_url", "api_key", "api_mode", "model", "models",
-    "context_length", "rate_limit_delay",
+    "context_length", "rate_limit_delay", "extra_body",
     # key_env is read at runtime by runtime_provider.py and auxiliary_client.py
     # — include it here so the set accurately describes the supported schema.
     "key_env",

hermes_cli/runtime_provider.py

@@ -528,6 +528,9 @@ def _get_named_custom_provider(requested_provider: str) -> Optional[Dict[str, An
                         "api_key": resolved_api_key,
                         "model": entry.get("default_model", ""),
                     }
+                    extra_body = entry.get("extra_body")
+                    if isinstance(extra_body, dict):
+                        result["extra_body"] = dict(extra_body)
                     # The v11→v12 migration writes the API mode under the new
                     # ``transport`` field, but hand-edited configs may still
                     # use the legacy ``api_mode`` spelling.  Accept both —
@@ -553,6 +556,9 @@ def _get_named_custom_provider(requested_provider: str) -> Optional[Dict[str, An
                             "api_key": resolved_api_key,
                             "model": entry.get("default_model", ""),
                         }
+                        extra_body = entry.get("extra_body")
+                        if isinstance(extra_body, dict):
+                            result["extra_body"] = dict(extra_body)
                         api_mode = _parse_api_mode(entry.get("api_mode") or entry.get("transport"))
                         if api_mode:
                             result["api_mode"] = api_mode
@@ -596,6 +602,9 @@ def _get_named_custom_provider(requested_provider: str) -> Optional[Dict[str, An
             result["key_env"] = key_env
         if provider_key:
             result["provider_key"] = provider_key
+        extra_body = entry.get("extra_body")
+        if isinstance(extra_body, dict):
+            result["extra_body"] = dict(extra_body)
         api_mode = _parse_api_mode(entry.get("api_mode"))
         if api_mode:
             result["api_mode"] = api_mode
@@ -607,6 +616,13 @@ def _get_named_custom_provider(requested_provider: str) -> Optional[Dict[str, An
     return None
 
 
+def _custom_provider_request_overrides(custom_provider: Dict[str, Any]) -> Dict[str, Any]:
+    extra_body = custom_provider.get("extra_body")
+    if not isinstance(extra_body, dict) or not extra_body:
+        return {}
+    return {"extra_body": dict(extra_body)}
+
+
 def _resolve_named_custom_runtime(
     *,
     requested_provider: str,
@@ -683,6 +699,12 @@ def _resolve_named_custom_runtime(
         model_name = custom_provider.get("model")
         if model_name:
             pool_result["model"] = model_name
+        request_overrides = _custom_provider_request_overrides(custom_provider)
+        if request_overrides:
+            pool_result["request_overrides"] = {
+                **dict(pool_result.get("request_overrides") or {}),
+                **request_overrides,
+            }
         return pool_result
 
     _cp_is_openai_url   = base_url_host_matches(base_url, "openai.com") or base_url_host_matches(base_url, "openai.azure.com")
@@ -714,6 +736,9 @@ def _resolve_named_custom_runtime(
     # provider name differs from the actual model string the API expects.
     if custom_provider.get("model"):
         result["model"] = custom_provider["model"]
+    request_overrides = _custom_provider_request_overrides(custom_provider)
+    if request_overrides:
+        result["request_overrides"] = request_overrides
     return result