mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-29 06:31:32 +00:00
ba9964ff0d
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
93 lines
2.4 KiB
Python
93 lines
2.4 KiB
Python
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 == {}
|