pc-heini/ha-openai-compatible
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: ask for the model on the first screen of the endpoint flow

Browse Source 
The model field was one screen too late. Reported directly: "this is where
I would have expected to see the model dropdown", on the AI Task init step
that showed only Name and the recommended checkbox.

- CONF_CHAT_MODEL moves from async_step_additional to async_step_init for
  conversation and ai_task_data, so all four endpoint types now ask on the
  first screen. stt and tts already did.
- UNSUPPORTED_MODELS is validated there too, since the recommended path
  creates the subentry from that step and would otherwise skip the check.
- model_list.default_model() picks what to preselect: RECOMMENDED_CHAT_MODEL
  only when the provider actually serves it (or discovery returned nothing),
  otherwise the first advertised model. Offering a stranger's gpt-4o-mini to
  a LiteLLM user preselects a model that fails on first use.

This is the trade I got wrong last commit. I kept the field on the second
step to avoid touching 71 ported tests, having judged them unfixable
mechanically. They were not: the 71 were ~13 functions under parametrize,
and test_subentry_switching's data is already a list of per-step dicts, so
moving a model between steps is moving a key between two dicts. Two scripted
passes moved 14 of them; 5 needed reasoning about (an error that now surfaces
on init rather than the next step, and four cases whose expected data gains
the now-always-recorded model).

async_fetch_model_ids now also catches non-OpenAIError exceptions. Found via
a ported test whose client is a MagicMock: the TypeError from awaiting it
escaped and broke the whole form. A real proxy returning a payload the SDK
cannot parse would do the same, and this runs inside a dialog with a working
free-text fallback, so nothing it raises justifies taking the form down.

Also fixes a string that was simply false on a third-party provider, again
reported from the UI: "Store requests and responses in OpenAI" / "stored by
OpenAI and visible in your OpenAI dashboard logs". It now describes the
Responses API store flag and says support varies. Swept the other 43
OpenAI-mentioning strings while there -- the rest are [%key:...%]
self-references or this fork's own action names, and no other option text
makes a claim about who stores the data.

Local: 170 passed.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01NxJYWgGJtCw13qUHZtG8ki
This commit is contained in:
Adam SmithandClaude Opus 5 committed 2026-09-17 23:18:02 -04:00
1 parent 030822c845
commit 6a599e092a
7 files changed
+112 -75
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

custom_components/openai_compatible/config_flow.py
+25 -11
View File
@@ -104,7 +104,7 @@ from .const import (
UNSUPPORTED_PRIORITY_SERVICE_TIERS_MODELS,
UNSUPPORTED_WEB_SEARCH_MODELS,
)
from .model_list import async_fetch_model_ids, model_field
from .model_list import async_fetch_model_ids, default_model, model_field
from .url_util import (
CredentialsInBaseURL,
InvalidBaseURL,
@@ -325,14 +325,35 @@ class OpenAISubentryFlowHandler(ConfigSubentryFlow):
}
)
# The model belongs on the first screen. Picking one is the entire
# point of adding an endpoint, and behind the "recommended" checkbox
# it was unreachable: ticked, this step creates the subentry and the
# model silently stays RECOMMENDED_CHAT_MODEL -- an OpenAI name a
# third-party provider will not serve. entity.py reads
# CONF_CHAT_MODEL regardless of the recommended flag, so a model
# chosen here takes effect on either path.
model_ids = await async_fetch_model_ids(self._get_entry().runtime_data)
step_schema[
vol.Optional(CONF_CHAT_MODEL, default=default_model(model_ids))
] = model_field(model_ids)
step_schema[
vol.Required(CONF_RECOMMENDED, default=options.get(CONF_RECOMMENDED, False))
] = bool
errors: dict[str, str] = {}
if user_input is not None:
if user_input.get(CONF_LLM_HASS_API) is None:
user_input.pop(CONF_LLM_HASS_API, None)
# Checked here rather than on the next step, because the
# recommended path creates the subentry from this one and would
# otherwise skip the check entirely.
if user_input.get(CONF_CHAT_MODEL) in UNSUPPORTED_MODELS:
errors[CONF_CHAT_MODEL] = "model_not_supported"
if not errors:
if user_input[CONF_RECOMMENDED]:
if self._is_new:
return self.async_create_entry(
@@ -355,6 +376,7 @@ class OpenAISubentryFlowHandler(ConfigSubentryFlow):
data_schema=self.add_suggested_values_to_schema(
vol.Schema(step_schema), options
),
errors=errors,
)
async def async_step_additional(
@@ -365,14 +387,8 @@ class OpenAISubentryFlowHandler(ConfigSubentryFlow):
errors: dict[str, str] = {}
step_schema: VolDictType = {
# Upstream makes this a free-text box defaulting to an OpenAI
# model name. Offer what the provider actually serves instead.
vol.Optional(
CONF_CHAT_MODEL,
default=RECOMMENDED_CHAT_MODEL,
): model_field(
await async_fetch_model_ids(self._get_entry().runtime_data)
),
# CONF_CHAT_MODEL is asked on the init step, so that it is
# reachable without unticking "recommended" first.
vol.Optional(
CONF_MAX_TOKENS,
default=RECOMMENDED_MAX_TOKENS,
@@ -393,8 +409,6 @@ class OpenAISubentryFlowHandler(ConfigSubentryFlow):
if user_input is not None:
options.update(user_input)
if user_input.get(CONF_CHAT_MODEL) in UNSUPPORTED_MODELS:
errors[CONF_CHAT_MODEL] = "model_not_supported"
if not errors:
return await self.async_step_model()
custom_components/openai_compatible/model_list.py
+23 -1
View File
@@ -22,7 +22,7 @@ from homeassistant.helpers.selector import (
SelectSelectorMode,
)
from .const import LOGGER
from .const import LOGGER, RECOMMENDED_CHAT_MODEL
DEFAULT_TIMEOUT = 10.0
@@ -48,6 +48,14 @@ async def async_fetch_model_ids(
except openai.OpenAIError as err:
LOGGER.debug("Could not list models: %s", err)
return []
except Exception: # noqa: BLE001 - see below
# Deliberately broad. This runs inside a config-flow form and has a
# working fallback (a free-text model field), so nothing it can raise
# justifies taking the dialog down: a proxy may return a payload the
# SDK cannot parse, and the failure modes of arbitrary
# OpenAI-compatible servers are not enumerable in advance.
LOGGER.debug("Unexpected error listing models", exc_info=True)
return []
return sorted({model.id for model in page.data if getattr(model, "id", None)})
@@ -71,3 +79,17 @@ def model_field(model_ids: list[str]) -> Any:
sort=True,
)
)
def default_model(model_ids: list[str]) -> str:
"""Return the model to preselect for a new endpoint.
Upstream's default is RECOMMENDED_CHAT_MODEL, an OpenAI name. Offering it
to someone configuring a third-party provider preselects a model that will
fail on first use, so prefer it only when the provider actually serves it
(or when discovery told us nothing) and otherwise start from what is
advertised.
"""
if not model_ids or RECOMMENDED_CHAT_MODEL in model_ids:
return RECOMMENDED_CHAT_MODEL
return model_ids[0]
custom_components/openai_compatible/strings.json
+2 -2
View File
@@ -123,12 +123,12 @@
"data": {
"chat_model": "[%key:common::generic::model%]",
"max_tokens": "Maximum tokens to return in response",
"store_responses": "Store requests and responses in OpenAI",
"store_responses": "Store requests and responses on the provider",
"temperature": "Temperature",
"top_p": "Top P"
},
"data_description": {
"store_responses": "If enabled, requests and responses are stored by OpenAI and visible in your OpenAI dashboard logs"
"store_responses": "Sets the Responses API store flag, asking the provider to keep requests and responses in its own logs. Support varies: OpenAI shows them in its dashboard, while many compatible servers ignore the flag entirely."
},
"title": "Additional settings"
},
custom_components/openai_compatible/translations/en.json
+4 -4
View File
@@ -59,12 +59,12 @@
"data": {
"chat_model": "Model",
"max_tokens": "Maximum tokens to return in response",
"store_responses": "Store requests and responses in OpenAI",
"store_responses": "Store requests and responses on the provider",
"temperature": "Temperature",
"top_p": "Top P"
},
"data_description": {
"store_responses": "If enabled, requests and responses are stored by OpenAI and visible in your OpenAI dashboard logs"
"store_responses": "Sets the Responses API store flag, asking the provider to keep requests and responses in its own logs. Support varies: OpenAI shows them in its dashboard, while many compatible servers ignore the flag entirely."
},
"title": "Additional settings"
},
@@ -123,12 +123,12 @@
"data": {
"chat_model": "Model",
"max_tokens": "Maximum tokens to return in response",
"store_responses": "Store requests and responses in OpenAI",
"store_responses": "Store requests and responses on the provider",
"temperature": "Temperature",
"top_p": "Top P"
},
"data_description": {
"store_responses": "If enabled, requests and responses are stored by OpenAI and visible in your OpenAI dashboard logs"
"store_responses": "Sets the Responses API store flag, asking the provider to keep requests and responses in its own logs. Support varies: OpenAI shows them in its dashboard, while many compatible servers ignore the flag entirely."
},
"title": "Additional settings"
},
tests/test_config_flow.py
+36 -36
View File
@@ -177,6 +177,9 @@ async def test_creating_conversation_subentry(
processed_options = RECOMMENDED_CONVERSATION_OPTIONS.copy()
processed_options[CONF_PROMPT] = processed_options[CONF_PROMPT].strip()
# The init step now asks for the model, so the created subentry records
# one explicitly instead of falling back to the default at request time.
processed_options[CONF_CHAT_MODEL] = RECOMMENDED_CHAT_MODEL
assert result2["data"] == processed_options
@@ -239,23 +242,17 @@ async def test_subentry_unsupported_model(
subentry_flow["flow_id"],
{
CONF_RECOMMENDED: False,
CONF_CHAT_MODEL: "o1-mini",
CONF_PROMPT: "Speak like a pirate",
CONF_LLM_HASS_API: ["assist"],
},
)
await hass.async_block_till_done()
assert subentry_flow["type"] is FlowResultType.FORM
assert subentry_flow["step_id"] == "additional"
# Configure additional step
subentry_flow = await hass.config_entries.subentries.async_configure(
subentry_flow["flow_id"],
{
CONF_CHAT_MODEL: "o1-mini",
},
)
await hass.async_block_till_done()
# The model is asked for, and so validated, on the init step -- the flow
# stays there and reports the error against the field.
assert subentry_flow["type"] is FlowResultType.FORM
assert subentry_flow["step_id"] == "init"
assert subentry_flow["errors"] == {"chat_model": "model_not_supported"}
@@ -295,6 +292,7 @@ async def test_subentry_reasoning_effort_list(
subentry_flow["flow_id"],
{
CONF_RECOMMENDED: False,
CONF_CHAT_MODEL: model,
CONF_PROMPT: "Speak like a pirate",
CONF_LLM_HASS_API: ["assist"],
},
@@ -305,9 +303,7 @@ async def test_subentry_reasoning_effort_list(
# Configure additional step
subentry_flow = await hass.config_entries.subentries.async_configure(
subentry_flow["flow_id"],
{
CONF_CHAT_MODEL: model,
},
{},
)
assert subentry_flow["type"] is FlowResultType.FORM
assert subentry_flow["step_id"] == "model"
@@ -349,6 +345,7 @@ async def test_subentry_reasoning_summary_visibility(
subentry_flow["flow_id"],
{
CONF_RECOMMENDED: False,
CONF_CHAT_MODEL: model,
CONF_PROMPT: "Speak like a pirate",
CONF_LLM_HASS_API: ["assist"],
},
@@ -359,9 +356,7 @@ async def test_subentry_reasoning_summary_visibility(
# Configure additional step
subentry_flow = await hass.config_entries.subentries.async_configure(
subentry_flow["flow_id"],
{
CONF_CHAT_MODEL: model,
},
{},
)
assert subentry_flow["type"] is FlowResultType.FORM
assert subentry_flow["step_id"] == "model"
@@ -398,6 +393,7 @@ async def test_subentry_reasoning_summary_options(
subentry_flow["flow_id"],
{
CONF_RECOMMENDED: False,
CONF_CHAT_MODEL: model,
CONF_PROMPT: "Speak like a pirate",
CONF_LLM_HASS_API: ["assist"],
},
@@ -407,9 +403,7 @@ async def test_subentry_reasoning_summary_options(
subentry_flow = await hass.config_entries.subentries.async_configure(
subentry_flow["flow_id"],
{
CONF_CHAT_MODEL: model,
},
{},
)
assert subentry_flow["type"] is FlowResultType.FORM
assert subentry_flow["step_id"] == "model"
@@ -446,6 +440,7 @@ async def test_subentry_reasoning_summary_default_sanitized_on_model_switch(
subentry_flow["flow_id"],
{
CONF_RECOMMENDED: False,
CONF_CHAT_MODEL: "o3",
CONF_PROMPT: "Speak like a pirate",
CONF_LLM_HASS_API: ["assist"],
},
@@ -454,7 +449,7 @@ async def test_subentry_reasoning_summary_default_sanitized_on_model_switch(
subentry_flow = await hass.config_entries.subentries.async_configure(
subentry_flow["flow_id"],
{CONF_CHAT_MODEL: "o3"},
{},
)
assert subentry_flow["step_id"] == "model"
@@ -512,6 +507,7 @@ async def test_subentry_service_tier_list(
subentry_flow["flow_id"],
{
CONF_RECOMMENDED: False,
CONF_CHAT_MODEL: model,
CONF_PROMPT: "Speak like a pirate",
CONF_LLM_HASS_API: ["assist"],
},
@@ -522,9 +518,7 @@ async def test_subentry_service_tier_list(
# Configure additional step
subentry_flow = await hass.config_entries.subentries.async_configure(
subentry_flow["flow_id"],
{
CONF_CHAT_MODEL: model,
},
{},
)
assert subentry_flow["type"] is FlowResultType.FORM
assert subentry_flow["step_id"] == "model"
@@ -558,6 +552,7 @@ async def test_subentry_unsupported_reasoning_effort(
subentry_flow["flow_id"],
{
CONF_RECOMMENDED: False,
CONF_CHAT_MODEL: "gpt-5",
CONF_PROMPT: "Speak like a pirate",
CONF_LLM_HASS_API: ["assist"],
},
@@ -568,9 +563,7 @@ async def test_subentry_unsupported_reasoning_effort(
# Configure additional step
subentry_flow = await hass.config_entries.subentries.async_configure(
subentry_flow["flow_id"],
{
CONF_CHAT_MODEL: "gpt-5",
},
{},
)
assert subentry_flow["type"] is FlowResultType.FORM
assert subentry_flow["step_id"] == "model"
@@ -706,11 +699,11 @@ async def test_form_credentials_in_base_url(hass: HomeAssistant) -> None:
(
{
CONF_RECOMMENDED: False,
CONF_CHAT_MODEL: "o1-pro",
CONF_PROMPT: "Speak like a pro",
},
{
CONF_TEMPERATURE: 1.0,
CONF_CHAT_MODEL: "o1-pro",
CONF_TOP_P: RECOMMENDED_TOP_P,
CONF_MAX_TOKENS: 10000,
},
@@ -740,11 +733,11 @@ async def test_form_credentials_in_base_url(hass: HomeAssistant) -> None:
(
{
CONF_RECOMMENDED: False,
CONF_CHAT_MODEL: RECOMMENDED_CHAT_MODEL,
CONF_PROMPT: "Speak like a pirate",
},
{
CONF_TEMPERATURE: 0.3,
CONF_CHAT_MODEL: RECOMMENDED_CHAT_MODEL,
CONF_TOP_P: RECOMMENDED_TOP_P,
CONF_MAX_TOKENS: RECOMMENDED_MAX_TOKENS,
},
@@ -797,11 +790,11 @@ async def test_form_credentials_in_base_url(hass: HomeAssistant) -> None:
(
{
CONF_RECOMMENDED: False,
CONF_CHAT_MODEL: "gpt-4o",
CONF_PROMPT: "Speak like super Mario",
},
{
CONF_TEMPERATURE: 0.8,
CONF_CHAT_MODEL: "gpt-4o",
CONF_TOP_P: 0.9,
CONF_MAX_TOKENS: 1000,
CONF_STORE_RESPONSES: True,
@@ -852,11 +845,11 @@ async def test_form_credentials_in_base_url(hass: HomeAssistant) -> None:
(
{
CONF_RECOMMENDED: False,
CONF_CHAT_MODEL: "gpt-5.6",
CONF_PROMPT: "Speak like a pirate",
},
{
CONF_TEMPERATURE: 0.8,
CONF_CHAT_MODEL: "gpt-5.6",
CONF_TOP_P: 0.9,
CONF_MAX_TOKENS: 1000,
},
@@ -975,11 +968,11 @@ async def test_form_credentials_in_base_url(hass: HomeAssistant) -> None:
(
{
CONF_RECOMMENDED: False,
CONF_CHAT_MODEL: "o3-mini",
CONF_PROMPT: "Speak like a pirate",
},
{
CONF_TEMPERATURE: 0.8,
CONF_CHAT_MODEL: "o3-mini",
CONF_TOP_P: 0.9,
CONF_MAX_TOKENS: 1000,
},
@@ -1020,11 +1013,11 @@ async def test_form_credentials_in_base_url(hass: HomeAssistant) -> None:
(
{
CONF_RECOMMENDED: False,
CONF_CHAT_MODEL: "gpt-4o",
CONF_PROMPT: "Speak like a pirate",
},
{
CONF_TEMPERATURE: 0.8,
CONF_CHAT_MODEL: "gpt-4o",
CONF_TOP_P: 0.9,
CONF_MAX_TOKENS: 1000,
},
@@ -1075,11 +1068,11 @@ async def test_form_credentials_in_base_url(hass: HomeAssistant) -> None:
(
{
CONF_RECOMMENDED: False,
CONF_CHAT_MODEL: "gpt-5-pro",
CONF_PROMPT: "Speak like a pirate",
},
{
CONF_TEMPERATURE: 0.8,
CONF_CHAT_MODEL: "gpt-5-pro",
CONF_TOP_P: 0.9,
CONF_MAX_TOKENS: 1000,
},
@@ -1155,7 +1148,13 @@ async def test_subentry_switching(
assert subentry_flow["type"] is FlowResultType.ABORT
assert subentry_flow["reason"] == "reconfigure_successful"
assert subentry.data == expected_options
# The init step always asks for a model, so every subentry records one.
# Cases that do not name one get the default, which is what the flow
# submits for them; cases that do still win, being unpacked second.
assert subentry.data == {
CONF_CHAT_MODEL: RECOMMENDED_CHAT_MODEL,
**expected_options,
}
@pytest.mark.parametrize("store_responses", [False, True])
@@ -1183,6 +1182,7 @@ async def test_subentry_web_search_user_location(
{
CONF_RECOMMENDED: False,
CONF_PROMPT: "Speak like a pirate",
CONF_CHAT_MODEL: RECOMMENDED_CHAT_MODEL,
},
)
assert subentry_flow["type"] is FlowResultType.FORM
@@ -1193,7 +1193,6 @@ async def test_subentry_web_search_user_location(
subentry_flow["flow_id"],
{
CONF_TEMPERATURE: 1.0,
CONF_CHAT_MODEL: RECOMMENDED_CHAT_MODEL,
CONF_TOP_P: RECOMMENDED_TOP_P,
CONF_MAX_TOKENS: RECOMMENDED_MAX_TOKENS,
CONF_STORE_RESPONSES: store_responses,
@@ -1307,6 +1306,7 @@ async def test_creating_ai_task_subentry(
assert result2.get("title") == "Custom AI Task"
assert result2.get("data") == {
CONF_RECOMMENDED: True,
CONF_CHAT_MODEL: RECOMMENDED_CHAT_MODEL,
}
assert (
@@ -1354,6 +1354,7 @@ async def test_creating_ai_task_subentry_additional(
{
"name": "Advanced AI Task",
CONF_RECOMMENDED: False,
CONF_CHAT_MODEL: "gpt-4o",
},
)
@@ -1364,7 +1365,6 @@ async def test_creating_ai_task_subentry_additional(
result3 = await hass.config_entries.subentries.async_configure(
result["flow_id"],
{
CONF_CHAT_MODEL: "gpt-4o",
CONF_MAX_TOKENS: 200,
CONF_STORE_RESPONSES: True,
CONF_TEMPERATURE: 0.5,
tests/test_model_list.py
+14
View File
@@ -73,6 +73,20 @@ async def test_fetch_survives_an_endpoint_that_will_not_list(error: Exception) -
assert await async_fetch_model_ids(_client(error=error)) == []
async def test_fetch_survives_a_non_openai_error() -> None:
"""Discovery must never break the form it runs inside.
A proxy can return a payload the SDK cannot parse, or a client can be
wired in a way that raises something other than an OpenAIError; either way
the dropdown should degrade to a text box, not take the dialog down.
"""
client = MagicMock()
client.with_options.return_value = client
client.models.list = MagicMock(return_value="not awaitable")
assert await async_fetch_model_ids(client) == []
async def test_field_is_a_dropdown_that_still_accepts_a_typed_name() -> None:
"""A proxy may serve a model it does not advertise, so allow free text."""
field = model_field(["claude-sonnet", "gpt-4o-mini"])
tests/test_model_picker.py
+8 -21
View File
@@ -47,8 +47,8 @@ async def _model_step(
) -> dict:
"""Return the form that asks for the model, for any endpoint type.
stt and tts are single-step flows that ask on init; conversation and
ai_task_data ask on the step after it.
All four types ask on the first screen, so that picking a model never
depends on noticing the "recommended" checkbox first.
"""
with patch(DISCOVERY, return_value=models):
result = await hass.config_entries.subentries.async_init(
@@ -57,16 +57,6 @@ async def _model_step(
)
assert result["type"] is FlowResultType.FORM
assert result["step_id"] == "init"
if subentry_type in ("stt", "tts"):
return result
result = await hass.config_entries.subentries.async_configure(
result["flow_id"],
{CONF_NAME: "An endpoint", CONF_RECOMMENDED: False},
)
assert result["type"] is FlowResultType.FORM
assert result["step_id"] == "additional"
return result
@@ -133,17 +123,14 @@ async def test_a_non_openai_model_name_survives_the_flow(
(mock_config_entry.entry_id, "conversation"),
context={"source": config_entries.SOURCE_USER},
)
# The model is chosen on the very first screen, alongside the name.
result = await hass.config_entries.subentries.async_configure(
result["flow_id"],
{CONF_NAME: "Sonnet via LiteLLM", CONF_RECOMMENDED: False},
)
result = await hass.config_entries.subentries.async_configure(
result["flow_id"], {CONF_CHAT_MODEL: "claude-sonnet-4-6"}
)
# remaining steps take their defaults
while result["type"] is FlowResultType.FORM:
result = await hass.config_entries.subentries.async_configure(
result["flow_id"], {}
{
CONF_NAME: "Sonnet via LiteLLM",
CONF_CHAT_MODEL: "claude-sonnet-4-6",
CONF_RECOMMENDED: True,
},
)
await hass.async_block_till_done()