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

tests/agent/test_custom_provider_extra_body.py

@@ -0,0 +1,93 @@
+from types import SimpleNamespace
+
+from agent.agent_init import _merge_custom_provider_extra_body
+
+
+def test_custom_provider_extra_body_merges_into_request_overrides():
+    agent = SimpleNamespace(
+        provider="custom",
+        model="google/gemma-4-31b-it",
+        base_url="https://example.test/v1",
+        request_overrides={"service_tier": "priority"},
+    )
+
+    _merge_custom_provider_extra_body(
+        agent,
+        [
+            {
+                "name": "gemma",
+                "base_url": "https://example.test/v1/",
+                "model": "google/gemma-4-31b-it",
+                "extra_body": {
+                    "enable_thinking": True,
+                    "reasoning_effort": "high",
+                },
+            }
+        ],
+    )
+
+    assert agent.request_overrides == {
+        "service_tier": "priority",
+        "extra_body": {
+            "enable_thinking": True,
+            "reasoning_effort": "high",
+        },
+    }
+
+
+def test_custom_provider_extra_body_preserves_caller_override():
+    agent = SimpleNamespace(
+        provider="custom",
+        model="google/gemma-4-31b-it",
+        base_url="https://example.test/v1",
+        request_overrides={
+            "extra_body": {
+                "reasoning_effort": "low",
+                "caller_only": True,
+            }
+        },
+    )
+
+    _merge_custom_provider_extra_body(
+        agent,
+        [
+            {
+                "name": "gemma",
+                "base_url": "https://example.test/v1",
+                "model": "google/gemma-4-31b-it",
+                "extra_body": {
+                    "enable_thinking": True,
+                    "reasoning_effort": "high",
+                },
+            }
+        ],
+    )
+
+    assert agent.request_overrides["extra_body"] == {
+        "enable_thinking": True,
+        "reasoning_effort": "low",
+        "caller_only": True,
+    }
+
+
+def test_custom_provider_extra_body_ignores_other_custom_models():
+    agent = SimpleNamespace(
+        provider="custom",
+        model="other-model",
+        base_url="https://example.test/v1",
+        request_overrides={},
+    )
+
+    _merge_custom_provider_extra_body(
+        agent,
+        [
+            {
+                "name": "gemma",
+                "base_url": "https://example.test/v1",
+                "model": "google/gemma-4-31b-it",
+                "extra_body": {"enable_thinking": True},
+            }
+        ],
+    )
+
+    assert agent.request_overrides == {}

tests/hermes_cli/test_runtime_provider_resolution.py

@@ -1631,6 +1631,33 @@ def test_named_custom_runtime_propagates_model_direct_path(monkeypatch):
     assert resolved["provider"] == "custom"
 
 
+def test_named_custom_runtime_propagates_extra_body_direct_path(monkeypatch):
+    """Custom provider extra_body should become runtime request_overrides."""
+    monkeypatch.setattr(rp, "resolve_provider", lambda *a, **k: "my-gemma")
+    monkeypatch.setattr(
+        rp, "_get_named_custom_provider",
+        lambda p: {
+            "name": "my-gemma",
+            "base_url": "http://localhost:8000/v1",
+            "api_key": "test-key",
+            "model": "google/gemma-4-31b-it",
+            "extra_body": {
+                "enable_thinking": True,
+                "reasoning_effort": "high",
+            },
+        },
+    )
+    monkeypatch.setattr(rp, "_try_resolve_from_custom_pool", lambda *a, **k: None)
+
+    resolved = rp.resolve_runtime_provider(requested="my-gemma")
+    assert resolved["request_overrides"] == {
+        "extra_body": {
+            "enable_thinking": True,
+            "reasoning_effort": "high",
+        }
+    }
+
+
 def test_named_custom_runtime_propagates_model_pool_path(monkeypatch):
     """Model should propagate even when credential pool handles credentials."""
     monkeypatch.setattr(rp, "resolve_provider", lambda *a, **k: "my-server")
@@ -1662,6 +1689,36 @@ def test_named_custom_runtime_propagates_model_pool_path(monkeypatch):
     assert resolved["api_key"] == "pool-key", "pool credentials should be used"
 
 
+def test_named_custom_runtime_propagates_extra_body_pool_path(monkeypatch):
+    """Custom provider extra_body should survive credential-pool resolution."""
+    monkeypatch.setattr(rp, "resolve_provider", lambda *a, **k: "my-gemma")
+    monkeypatch.setattr(
+        rp, "_get_named_custom_provider",
+        lambda p: {
+            "name": "my-gemma",
+            "base_url": "http://localhost:8000/v1",
+            "api_key": "test-key",
+            "model": "google/gemma-4-31b-it",
+            "extra_body": {"enable_thinking": True},
+        },
+    )
+    monkeypatch.setattr(
+        rp, "_try_resolve_from_custom_pool",
+        lambda *a, **k: {
+            "provider": "custom",
+            "api_mode": "chat_completions",
+            "base_url": "http://localhost:8000/v1",
+            "api_key": "pool-key",
+            "source": "pool:custom:my-gemma",
+        },
+    )
+
+    resolved = rp.resolve_runtime_provider(requested="my-gemma")
+    assert resolved["request_overrides"] == {
+        "extra_body": {"enable_thinking": True}
+    }
+
+
 def test_named_custom_runtime_no_model_when_absent(monkeypatch):
     """When custom_providers entry has no model field, runtime should not either."""
     monkeypatch.setattr(rp, "resolve_provider", lambda *a, **k: "my-server")
@@ -2150,6 +2207,24 @@ class TestProviderEntryApiKeyEnvAlias:
         key_env so the set stays in sync with what the runtime actually reads."""
         from hermes_cli.config import _VALID_CUSTOM_PROVIDER_FIELDS
         assert "key_env" in _VALID_CUSTOM_PROVIDER_FIELDS
+
+    def test_extra_body_is_supported_schema(self):
+        from hermes_cli.config import (
+            _VALID_CUSTOM_PROVIDER_FIELDS,
+            _normalize_custom_provider_entry,
+        )
+        entry = {
+            "name": "vendor",
+            "base_url": "https://api.vendor.example.com/v1",
+            "extra_body": {
+                "chat_template_kwargs": {"enable_thinking": True},
+                "include_reasoning": True,
+            },
+        }
+        normalized = _normalize_custom_provider_entry(dict(entry), provider_key="vendor")
+        assert normalized is not None
+        assert "extra_body" in _VALID_CUSTOM_PROVIDER_FIELDS
+        assert normalized["extra_body"] == entry["extra_body"]
 # =============================================================================
 # Tencent TokenHub — API-key provider runtime resolution
 # =============================================================================

tests/providers/test_transport_parity.py

@@ -236,7 +236,7 @@ class TestQwenParity:
 
 
 class TestCustomOllamaParity:
-    """Custom/Ollama: num_ctx, think=false — now tested via profile."""
+    """Custom/Ollama: num_ctx, thinking controls — now tested via profile."""
 
     def test_ollama_num_ctx(self, transport):
         kw = transport.build_kwargs(