Miscellaneous fixes (#23258)

* render orphaned filter entries as collapsibles instead of the Key/Value editor

* Symlink for various AI files

* change replay confg dialog to platform aware sheet

* change agents title

* fix test

* tweak collapsible

* remove camera ui section in settings

no point to having it anymore with profiles and camera management settings

* fix admin response cache leak to non-admin users via nginx proxy_cache

* add model fetcher endpoint for genai config ui

---------

Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
This commit is contained in:
Josh Hawkins
2026-05-20 08:36:49 -06:00
committed by GitHub
co-authored by Nicolas Mowen
parent 03f4f76b72
commit 8ea46e7c6c
19 changed files with 1111 additions and 596 deletions
+100 -1
View File
@@ -34,15 +34,17 @@ from frigate.api.auth import (
from frigate.api.defs.query.app_query_parameters import AppTimelineHourlyQueryParameters
from frigate.api.defs.request.app_body import (
AppConfigSetBody,
GenAIProbeBody,
MediaSyncBody,
)
from frigate.api.defs.tags import Tags
from frigate.config import FrigateConfig
from frigate.config import FrigateConfig, GenAIConfig, GenAIProviderEnum
from frigate.config.camera.updater import (
CameraConfigUpdateEnum,
CameraConfigUpdateTopic,
)
from frigate.ffmpeg_presets import FFMPEG_HWACCEL_VAAPI, _gpu_selector
from frigate.genai import PROVIDERS, load_providers
from frigate.jobs.media_sync import (
get_current_media_sync_job,
get_media_sync_job_by_id,
@@ -75,6 +77,14 @@ logger = logging.getLogger(__name__)
router = APIRouter(tags=[Tags.app])
# Short timeout for the /genai/probe path. The probe is interactive — fail
# fast on hung providers rather than holding an API worker thread.
_PROBE_TIMEOUT_SECONDS = 10
# Outer cap that returns control to the caller even if the underlying sync
# HTTP call ignores its timeout. The sync work continues in the background
# thread; only the response is bounded.
_PROBE_OUTER_TIMEOUT_SECONDS = 15
@router.get(
"/", response_class=PlainTextResponse, dependencies=[Depends(allow_public())]
@@ -170,6 +180,95 @@ def genai_models(request: Request):
return JSONResponse(content=request.app.genai_manager.list_models())
@router.post(
"/genai/probe",
dependencies=[Depends(require_role(["admin"]))],
summary="Probe a GenAI provider without saving config",
description=(
"Builds a transient client from the request body and returns its "
"available models. Used to validate provider credentials in the UI "
"before saving the configuration."
),
)
async def genai_probe(body: GenAIProbeBody):
load_providers()
provider_cls = PROVIDERS.get(body.provider)
if not provider_cls:
return JSONResponse(
status_code=400,
content={"success": False, "message": "Unknown provider"},
)
# The OpenAI-compatible SDKs accept "timeout" as a constructor kwarg via
# provider_options; other plugins use GenAIClient.timeout passed below.
# Don't inject timeout for Gemini — its HttpOptions interprets the value
# in milliseconds and would clash with the plugin's own default.
probe_provider_options: dict[str, Any] = dict(body.provider_options or {})
if body.provider in (GenAIProviderEnum.openai, GenAIProviderEnum.azure_openai):
probe_provider_options.setdefault("timeout", _PROBE_TIMEOUT_SECONDS)
try:
transient_cfg = GenAIConfig(
provider=body.provider,
api_key=body.api_key,
base_url=body.base_url,
provider_options=probe_provider_options,
# model is required by the schema but irrelevant for listing.
model="probe",
roles=[],
)
except ValidationError:
logger.exception("GenAI probe: invalid configuration")
return JSONResponse(
status_code=400,
content={"success": False, "message": "Invalid provider configuration"},
)
try:
client = provider_cls(
transient_cfg,
timeout=_PROBE_TIMEOUT_SECONDS,
validate_model=False,
)
except Exception:
logger.exception("GenAI probe: failed to construct client")
return JSONResponse(
content={
"success": False,
"message": "Failed to connect to provider",
},
)
try:
models = await asyncio.wait_for(
asyncio.to_thread(client.list_models),
timeout=_PROBE_OUTER_TIMEOUT_SECONDS,
)
except asyncio.TimeoutError:
return JSONResponse(
content={"success": False, "message": "Probe timed out"},
)
except Exception:
logger.exception("GenAI probe: list_models failed")
return JSONResponse(
content={"success": False, "message": "Provider returned no models"},
)
if not models:
return JSONResponse(
content={
"success": False,
"message": (
"No models returned. Check the API key, base URL, and "
"that the provider is reachable."
),
},
)
return JSONResponse(content={"success": True, "models": models})
@router.get("/config", dependencies=[Depends(allow_any_authenticated())])
def config(request: Request):
config_obj: FrigateConfig = request.app.frigate_config
+9
View File
@@ -2,6 +2,8 @@ from typing import Any, Dict, List, Optional
from pydantic import BaseModel, Field
from frigate.config import GenAIProviderEnum
class AppConfigSetBody(BaseModel):
requires_restart: int = 1
@@ -10,6 +12,13 @@ class AppConfigSetBody(BaseModel):
skip_save: bool = False
class GenAIProbeBody(BaseModel):
provider: GenAIProviderEnum
api_key: Optional[str] = None
base_url: Optional[str] = None
provider_options: Dict[str, Any] = Field(default_factory=dict)
class AppPutPasswordBody(BaseModel):
password: str
old_password: Optional[str] = None
+1 -1
View File
@@ -37,7 +37,7 @@ class GenAIConfig(FrigateBaseModel):
description="Base URL for self-hosted or compatible providers (for example an Ollama instance).",
)
model: str = Field(
default="gpt-4o",
default="",
title="Model",
description="The model to use from the provider for generating descriptions or summaries.",
)
+7 -1
View File
@@ -50,9 +50,15 @@ def register_genai_provider(key: GenAIProviderEnum) -> Callable:
class GenAIClient:
"""Generative AI client for Frigate."""
def __init__(self, genai_config: GenAIConfig, timeout: int = 120) -> None:
def __init__(
self,
genai_config: GenAIConfig,
timeout: int = 120,
validate_model: bool = True,
) -> None:
self.genai_config: GenAIConfig = genai_config
self.timeout = timeout
self.validate_model = validate_model
self.provider = self._init_provider()
def generate_review_description(
+4
View File
@@ -150,6 +150,10 @@ class LlamaCppClient(GenAIClient):
else:
base_url = base_url.replace("/v1", "") # Strip /v1 if included in base_url
if not self.validate_model:
# Probe path
return base_url
configured_model = self.genai_config.model
info = self._get_model_info(base_url, configured_model)
+3
View File
@@ -118,6 +118,9 @@ class OllamaClient(GenAIClient):
timeout=self.timeout,
headers=self._auth_headers(),
)
if not self.validate_model:
# Probe path
return client
# ensure the model is available locally
response = client.show(self.genai_config.model)
if response.get("error"):
+95 -1
View File
@@ -1,5 +1,8 @@
from unittest.mock import Mock
from unittest.mock import Mock, patch
import frigate.genai
from frigate.config import GenAIProviderEnum
from frigate.genai import GenAIClient
from frigate.models import Event, Recordings, ReviewSegment
from frigate.stats.emitter import StatsEmitter
from frigate.test.http_api.base_http_test import AuthTestClient, BaseTestHttp
@@ -71,3 +74,94 @@ class TestHttpApp(BaseTestHttp):
assert response.status_code == 200
assert app.frigate_config.cameras["front_door"].objects.track == ["person"]
####################################################################################################################
################################### POST /genai/probe Endpoint ##################################################
####################################################################################################################
def test_genai_probe_requires_admin(self):
app = super().create_app()
with AuthTestClient(app) as client:
response = client.post(
"/genai/probe",
json={"provider": "openai"},
headers={"remote-user": "viewer", "remote-role": "viewer"},
)
assert response.status_code == 403
def test_genai_probe_returns_models_from_transient_client(self):
class FakeClient(GenAIClient):
def list_models(self):
return ["fake-model-a", "fake-model-b"]
app = super().create_app()
with (
AuthTestClient(app) as client,
patch.dict(
frigate.genai.PROVIDERS,
{GenAIProviderEnum.openai: FakeClient},
),
):
response = client.post(
"/genai/probe",
json={
"provider": "openai",
"api_key": "sk-test",
"base_url": "https://example.invalid",
},
)
assert response.status_code == 200
assert response.json() == {
"success": True,
"models": ["fake-model-a", "fake-model-b"],
}
def test_genai_probe_empty_list_is_treated_as_failure(self):
# The plugin's list_models() returns [] on connection failure rather
# than raising. The endpoint should surface that as success=false so
# the UI can show a meaningful error.
class EmptyClient(GenAIClient):
def list_models(self):
return []
app = super().create_app()
with (
AuthTestClient(app) as client,
patch.dict(
frigate.genai.PROVIDERS,
{GenAIProviderEnum.openai: EmptyClient},
),
):
response = client.post(
"/genai/probe",
json={"provider": "openai"},
)
assert response.status_code == 200
payload = response.json()
assert payload["success"] is False
assert "message" in payload
def test_genai_probe_handles_provider_failure(self):
class FailingClient(GenAIClient):
def list_models(self):
raise RuntimeError("provider unreachable")
app = super().create_app()
with (
AuthTestClient(app) as client,
patch.dict(
frigate.genai.PROVIDERS,
{GenAIProviderEnum.openai: FailingClient},
),
):
response = client.post(
"/genai/probe",
json={"provider": "openai"},
)
assert response.status_code == 200
payload = response.json()
assert payload["success"] is False
assert "message" in payload