add ovhcloud_ai_endpoints integration#171402
Open
Crocmagnon wants to merge 8 commits into
Open
Conversation
Contributor
There was a problem hiding this comment.
Pull request overview
Note
Copilot was unable to run its full agentic suite in this review.
Adds a new Home Assistant integration for OVHcloud AI Endpoints, providing a conversation agent backed by OVHcloud's OpenAI-compatible API. Includes config flow with conversation subentries, model selection, and support for both <think> tag and reasoning/reasoning_content field extraction.
Changes:
- New
ovhcloud_ai_endpointsintegration with config flow, conversation entity, and subentry-based model configuration - Reasoning/thinking content extraction supporting OpenRouter, vLLM and DeepSeek-style fields plus inline
<think>tags - Comprehensive tests for setup, config flow, and conversation behavior
Reviewed changes
Copilot reviewed 20 out of 22 changed files in this pull request and generated 3 comments.
Show a summary per file
| File | Description |
|---|---|
| homeassistant/components/ovhcloud_ai_endpoints/init.py | Integration setup, OpenAI client init, API key validation |
| homeassistant/components/ovhcloud_ai_endpoints/config_flow.py | User and conversation subentry config flow |
| homeassistant/components/ovhcloud_ai_endpoints/conversation.py | Conversation entity wiring |
| homeassistant/components/ovhcloud_ai_endpoints/entity.py | Base entity, chat log handling, thinking extraction |
| homeassistant/components/ovhcloud_ai_endpoints/const.py | Constants and recommended defaults |
| homeassistant/components/ovhcloud_ai_endpoints/strings.json | Translation strings |
| homeassistant/components/ovhcloud_ai_endpoints/manifest.json | Integration manifest |
| homeassistant/components/ovhcloud_ai_endpoints/quality_scale.yaml | Quality scale tracking |
| tests/components/ovhcloud_ai_endpoints/* | Test fixtures, conftest, and tests for init/config flow/conversation |
| CODEOWNERS, mypy.ini, .strict-typing, requirements_*, generated files | Registration of the new integration |
Crocmagnon
force-pushed
the
devel/ovh-conversation
branch
from
25faa45 to
d1f1c79
Compare
Crocmagnon
force-pushed
the
devel/ovh-conversation
branch
from
d1f1c79 to
da3bf3f
Compare
Crocmagnon
changed the title
Comment on lines
+90
to
+95
| mock_openai_client.models.list.side_effect = None | ||
|
|
||
| result = await hass.config_entries.flow.async_configure( | ||
| result["flow_id"], | ||
| {CONF_API_KEY: "bla"}, | ||
| ) |
Comment on lines
+207
to
+216
| for _iteration in range(MAX_TOOL_ITERATIONS): | ||
| try: | ||
| result = await client.chat.completions.create(**model_args) | ||
| except openai.OpenAIError as err: | ||
| LOGGER.error("Error talking to API: %s", err) | ||
| raise HomeAssistantError("Error talking to API") from err | ||
|
|
||
| if not result.choices: | ||
| LOGGER.error("API returned empty choices") | ||
| raise HomeAssistantError("API returned empty response") |
Contributor
Author
There was a problem hiding this comment.
same implem as openrouter
| ] | ||
| ) | ||
| if not chat_log.unresponded_tool_results: | ||
| break |
Contributor
Author
There was a problem hiding this comment.
same implem as openrouter
Crocmagnon
force-pushed
the
devel/ovh-conversation
branch
from
da3bf3f to
d8d9f2f
Compare
Crocmagnon
force-pushed
the
devel/ovh-conversation
branch
from
d8d9f2f to
ac575e3
Compare
8 tasks
Comment on lines
+31
to
+40
| client = _create_client(hass, entry.data[CONF_API_KEY]) | ||
|
|
||
| try: | ||
| # Unfortunately I couldn't find an endpoint that would authenticate the key | ||
| # without calling an LLM. This always succeeds regardless of auth. | ||
| async for _ in client.with_options(timeout=10.0).models.list(): | ||
| break | ||
| except OpenAIError as err: | ||
| raise ConfigEntryNotReady(err) from err | ||
|
|
Comment on lines
+56
to
+60
| try: | ||
| # Unfortunately I couldn't find an endpoint that would authenticate the key | ||
| # without calling an LLM. This always succeeds regardless of auth. | ||
| async for _ in client.with_options(timeout=10.0).models.list(): | ||
| break |
| ] | ||
| ) | ||
| if not chat_log.unresponded_tool_results: | ||
| break |
| content: conversation.Content, | ||
| ) -> ChatCompletionMessageParam | None: | ||
| """Convert chat message for this agent to the native format.""" | ||
| LOGGER.debug("_convert_content_to_chat_message=%s", content) |
Comment on lines
+90
to
+95
| async def _get_models(self) -> None: | ||
| """Fetch models from OVHcloud AI Endpoints.""" | ||
| client: AsyncOpenAI = self._get_entry().runtime_data | ||
| self.models = [ | ||
| model.id async for model in client.with_options(timeout=10.0).models.list() | ||
| ] |
Crocmagnon
force-pushed
the
devel/ovh-conversation
branch
from
ac575e3 to
4f22457
Compare
Crocmagnon
force-pushed
the
devel/ovh-conversation
branch
from
4f22457 to
30e1650
Compare
10 tasks
Crocmagnon
force-pushed
the
devel/ovh-conversation
branch
from
30e1650 to
cd65fae
Compare
Comment on lines
+125
to
+133
| options = [ | ||
| SelectOptionDict(value=model_id, label=model_id) for model_id in self.models | ||
| ] | ||
|
|
||
| hass_apis: list[SelectOptionDict] = [ | ||
| SelectOptionDict( | ||
| label=api.name, | ||
| value=api.id, | ||
| ) |
Comment on lines
+92
to
+94
| self.models = [ | ||
| model.id async for model in client.with_options(timeout=10.0).models.list() | ||
| ] |
|
|
||
| async def _transform_response( | ||
| message: ChatCompletionMessage, | ||
| ) -> AsyncGenerator[conversation.AssistantContentDeltaDict]: |
| ] | ||
| ) | ||
| if not chat_log.unresponded_tool_results: | ||
| break |
| content: conversation.Content, | ||
| ) -> ChatCompletionMessageParam | None: | ||
| """Convert chat message for this agent to the native format.""" | ||
| LOGGER.debug("_convert_content_to_chat_message=%s", content) |
| We send a chat completion request with an unknown ``extra_body`` field | ||
| to prevent valid usage and billing. | ||
| A valid key triggers a 400 (BadRequestError), which we treat as success. | ||
| An invalid key triggers a 401 (AuthenticationError),which propagates |
joostlek
requested changes
May 21, 2026
Comment on lines
+28
to
+44
| async def _validate_api_key(client: AsyncOpenAI) -> None: | ||
| """Validate the API key against the chat completions endpoint. | ||
|
|
||
| We send a chat completion request with an unknown ``extra_body`` field | ||
| to prevent valid usage and billing. | ||
| A valid key triggers a 400 (BadRequestError), which we treat as success. | ||
| An invalid key triggers a 401 (AuthenticationError),which propagates | ||
| along with any other exception. | ||
| """ | ||
| try: | ||
| await client.with_options(timeout=10.0).chat.completions.create( | ||
| model="llama@latest", | ||
| messages=[ChatCompletionUserMessageParam(role="user", content="ping")], | ||
| extra_body={"foo": "bar"}, | ||
| ) | ||
| except BadRequestError: | ||
| return |
Member
There was a problem hiding this comment.
What about just fetching the models?
Contributor
Author
There was a problem hiding this comment.
Models list is not authenticated. Calling it with an invalid key results in a HTTP 200. I had a chat with the product team and this is what they suggested, for lack of a better option.
| from homeassistant.const import CONF_LLM_HASS_API, CONF_PROMPT | ||
| from homeassistant.helpers import llm | ||
|
|
||
| DOMAIN = "ovhcloud_ai_endpoints" |
Member
There was a problem hiding this comment.
why do we call this _endpoints?
Contributor
Author
There was a problem hiding this comment.
That’s the name of the product, see https://www.ovhcloud.com/fr/public-cloud/ai-endpoints/
Comment on lines
+44
to
+55
| async def test_dynamic_subentry_creates_entity_and_device( | ||
| hass: HomeAssistant, | ||
| mock_openai_client: AsyncMock, | ||
| entity_registry: er.EntityRegistry, | ||
| device_registry: dr.DeviceRegistry, | ||
| ) -> None: | ||
| """A subentry added after setup must spawn its conversation entity and device.""" | ||
| entry = MockConfigEntry( | ||
| title="OVHcloud AI Endpoints", | ||
| domain=DOMAIN, | ||
| data={CONF_API_KEY: "bla"}, | ||
| ) |
Member
There was a problem hiding this comment.
dynamic subentry? What does that mean?
Contributor
Author
There was a problem hiding this comment.
like an entry added after the initial setup
maybe new_subentry?
Contributor
|
Please take a look at the requested changes, and use the Ready for review button when you are done, thanks 👍 |
| ] | ||
| ) | ||
| if not chat_log.unresponded_tool_results: | ||
| break |
| content: conversation.Content, | ||
| ) -> ChatCompletionMessageParam | None: | ||
| """Convert chat message for this agent to the native format.""" | ||
| LOGGER.debug("_convert_content_to_chat_message=%s", content) |
Comment on lines
+28
to
+44
| async def _validate_api_key(client: AsyncOpenAI) -> None: | ||
| """Validate the API key against the chat completions endpoint. | ||
|
|
||
| We send a chat completion request with an unknown ``extra_body`` field | ||
| to prevent valid usage and billing. | ||
| A valid key triggers a 400 (BadRequestError), which we treat as success. | ||
| An invalid key triggers a 401 (AuthenticationError),which propagates | ||
| along with any other exception. | ||
| """ | ||
| try: | ||
| await client.with_options(timeout=10.0).chat.completions.create( | ||
| model="llama@latest", | ||
| messages=[ChatCompletionUserMessageParam(role="user", content="ping")], | ||
| extra_body={"foo": "bar"}, | ||
| ) | ||
| except BadRequestError: | ||
| return |
| We send a chat completion request with an unknown ``extra_body`` field | ||
| to prevent valid usage and billing. | ||
| A valid key triggers a 400 (BadRequestError), which we treat as success. | ||
| An invalid key triggers a 401 (AuthenticationError),which propagates |
| comment: No actions are implemented | ||
| appropriate-polling: | ||
| status: exempt | ||
| comment: the integration does not poll |
| from . import OVHcloudAIEndpointsConfigEntry | ||
| from .const import DOMAIN, LOGGER | ||
|
|
||
| MAX_TOOL_ITERATIONS = 10 |
|
|
||
| client = self.entry.runtime_data | ||
|
|
||
| for _iteration in range(MAX_TOOL_ITERATIONS): |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Proposed change
Add integration for OVH AI endpoints, starting with conversation only.
Type of change
Additional information
Checklist
ruff format homeassistant tests)If user exposed functionality or configuration variables are added/changed:
If the code communicates with devices, web services, or third-party tools:
Updated and included derived files by running:
python3 -m script.hassfest.requirements_all.txt.Updated by running
python3 -m script.gen_requirements_all.To help with the load of incoming pull requests: