From a0317d9926e306b70f2bc22a4c4f4bd00a0d6bc3 Mon Sep 17 00:00:00 2001
From: Ettore Di Giacinto <mudler@localai.io>
Date: Mon, 27 Apr 2026 23:09:20 +0000
Subject: [PATCH] refactor(tests): split app_test.go, move real-backend
 coverage to e2e-backends

core/http/app_test.go had grown to 1495 lines exercising three concerns at
once: HTTP-layer integration, real-backend inference (llama-gguf, tts,
stablediffusion, transformers embeddings, whisper), and service logic that
already has unit-level coverage. Each PR paid for 6 backend builds plus
real-model downloads to satisfy a single suite.

Reorg per layer:

- app_test.go (1495 -> 1003 lines) drives the mock-backend binary only.
  Kept: auth, routing, gallery API, file:// import, /system, agent-jobs
  HTTP plumbing, config-file model loading. Deleted real-inference specs
  (llama-gguf chat, ggml completions/streaming, logprobs, logit_bias,
  transcription, embeddings, External-gRPC, Stores duplicate, Model gallery
  Context). Lifted Agent Jobs out of the deleted Stores Context.
- tests/e2e-backends/backend_test.go gains logprobs, logit_bias, and
  no-first-token-dup specs (the latter folded into PredictStream). Two
  new caps gate them so non-LLM backends opt out.
- tests/e2e-aio/e2e_test.go gains a streaming smoke under Context("text")
  to catch container-level streaming regressions.
- tests/models_fixtures/ removed; all fixtures referenced testmodel.ggml.
  app_test.go now writes per-Context inline mock-model YAMLs.

CI:

- test.yml + tests-e2e.yml gain paths-ignore (docs/, examples/, *.md,
  backend/) so docs and backend-only PRs skip them. test.yml drops the
  6-backend Build step plus TRANSFORMER_BACKEND/GO_TAGS=tts; tests-apple
  drops the llama-cpp-darwin build.
- New tests-aio.yml runs the AIO container nightly + on workflow_dispatch
  + master/tags. The tests-e2e-container job moved out of test.yml so PRs
  no longer pay AIO cost.
- New tests-llama-cpp-smoke job in test-extra.yml runs on every PR with
  no detect-changes gate; pulls quay.io/go-skynet/local-ai-backends:
  master-cpu-llama-cpp (no build on PR) and exercises predict/stream/
  logprobs/logit_bias against Qwen3-0.6B. This is the PR-acceptance
  real-backend gate after AIO moved to nightly. The path-gated heavy
  test-extra-backend-llama-cpp wrapper appends the same caps so it
  exercises the moved specs when the backend actually changes.

Makefile:

- Deleted test-models/testmodel.ggml (the wget chain), test-llama-gguf,
  test-tts, test-stablediffusion, test-realtime-models. test target
  drops --label-filter, HUGGINGFACE_GRPC, TRANSFORMER_BACKEND, TEST_DIR,
  FIXTURES, CONFIG_FILE, MODELS_PATH, BACKENDS_PATH; depends on
  build-mock-backend. test-stores keeps a focused entry point and depends
  on backends/local-store. clean-tests also clears the mock-backend
  binary.

Net per typical Go-side PR: ~25min (6 backend builds + tests + AIO) +
~8min e2e drops to ~5min mock-backend test + ~8min e2e + ~5-10min
llama-cpp-smoke (image pulled). Docs and backend-only PRs skip the
always-on workflows entirely.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: claude-code:claude-opus-4-7 [Edit] [Write] [Bash]
---
 .github/workflows/test-extra.yml          |  27 +
 .github/workflows/test.yml                |  76 +-
 .github/workflows/tests-aio.yml           |  86 +++
 .github/workflows/tests-e2e.yml           |   6 +
 Makefile                                  |  67 +-
 core/http/app_test.go                     | 831 +++++-----------------
 core/http/http_suite_test.go              |  42 ++
 tests/e2e-aio/e2e_test.go                 |  28 +
 tests/e2e-backends/backend_test.go        |  62 ++
 tests/models_fixtures/completion.tmpl     |   1 -
 tests/models_fixtures/config.yaml         |  32 -
 tests/models_fixtures/embeddings.yaml     |   4 -
 tests/models_fixtures/ggml-gpt4all-j.tmpl |   4 -
 tests/models_fixtures/gpt4.yaml           |  16 -
 tests/models_fixtures/gpt4_2.yaml         |  16 -
 tests/models_fixtures/grpc.yaml           |   5 -
 tests/models_fixtures/rwkv.yaml           |  24 -
 tests/models_fixtures/whisper.yaml        |   4 -
 18 files changed, 451 insertions(+), 880 deletions(-)
 create mode 100644 .github/workflows/tests-aio.yml
 delete mode 100644 tests/models_fixtures/completion.tmpl
 delete mode 100644 tests/models_fixtures/config.yaml
 delete mode 100644 tests/models_fixtures/embeddings.yaml
 delete mode 100644 tests/models_fixtures/ggml-gpt4all-j.tmpl
 delete mode 100644 tests/models_fixtures/gpt4.yaml
 delete mode 100644 tests/models_fixtures/gpt4_2.yaml
 delete mode 100644 tests/models_fixtures/grpc.yaml
 delete mode 100644 tests/models_fixtures/rwkv.yaml
 delete mode 100644 tests/models_fixtures/whisper.yaml

diff --git a/.github/workflows/test-extra.yml b/.github/workflows/test-extra.yml
index 67ab16938..d37f77e01 100644
--- a/.github/workflows/test-extra.yml
+++ b/.github/workflows/test-extra.yml
@@ -507,6 +507,33 @@ jobs:
       - name: Build llama-cpp backend image and run audio transcription gRPC e2e tests
         run: |
           make test-extra-backend-llama-cpp-transcription
+  # PR-acceptance smoke gate: always runs on every PR (no detect-changes gate, no
+  # paths filter). Pulls the pre-built master CPU llama-cpp image from quay
+  # instead of building from source, so the cost is a docker pull (~30s) plus the
+  # short Qwen3-0.6B model download. Exercises the full gRPC surface — health,
+  # load, predict, stream — plus the logprobs/logit_bias specs that moved out of
+  # core/http/app_test.go. Anything heavier or per-backend is gated to the
+  # detect-changes path-filter above.
+  tests-llama-cpp-smoke:
+    runs-on: ubuntu-latest
+    timeout-minutes: 20
+    steps:
+      - name: Clone
+        uses: actions/checkout@v6
+        with:
+          submodules: true
+      - name: Setup Go
+        uses: actions/setup-go@v5
+        with:
+          go-version: '1.25.4'
+      - name: Pull pre-built llama-cpp backend image
+        run: docker pull quay.io/go-skynet/local-ai-backends:master-cpu-llama-cpp
+      - name: Run e2e-backends smoke
+        env:
+          BACKEND_IMAGE: quay.io/go-skynet/local-ai-backends:master-cpu-llama-cpp
+          BACKEND_TEST_CAPS: health,load,predict,stream,logprobs,logit_bias
+        run: |
+          make test-extra-backend
   # Realtime e2e with sherpa-onnx driving VAD + STT + TTS against a mocked LLM.
   # Builds the sherpa-onnx Docker image, extracts the rootfs so the e2e suite
   # can discover the backend binary + shared libs, downloads the three model
diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
index 5b104d1a9..f1c183acd 100644
--- a/.github/workflows/test.yml
+++ b/.github/workflows/test.yml
@@ -3,6 +3,12 @@ name: 'tests'
 
 on:
   pull_request:
+    paths-ignore:
+      - 'docs/**'
+      - 'examples/**'
+      - 'README.md'
+      - '**/*.md'
+      - 'backend/**'
   push:
     branches:
       - master
@@ -97,73 +103,9 @@ jobs:
           node-version: '22'
       - name: Build React UI
         run: make react-ui
-      - name: Build backends
-        run: |
-          make backends/transformers
-          mkdir external && mv backends/transformers external/transformers
-          make backends/llama-cpp backends/local-store backends/silero-vad backends/piper backends/whisper backends/stablediffusion-ggml
       - name: Test
         run: |
-          TRANSFORMER_BACKEND=$PWD/external/transformers/run.sh PATH="$PATH:/root/go/bin" GO_TAGS="tts" make --jobs 5 --output-sync=target test
-      - name: Setup tmate session if tests fail
-        if: ${{ failure() }}
-        uses: mxschmitt/action-tmate@v3.23
-        with:
-          detached: true
-          connect-timeout-seconds: 180
-          limit-access-to-actor: true
-
-  tests-e2e-container:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Release space from worker
-        run: |
-          echo "Listing top largest packages"
-          pkgs=$(dpkg-query -Wf '${Installed-Size}\t${Package}\t${Status}\n' | awk '$NF == "installed"{print $1 "\t" $2}' | sort -nr)
-          head -n 30 <<< "${pkgs}"
-          echo
-          df -h
-          echo
-          sudo apt-get remove -y '^llvm-.*|^libllvm.*' || true
-          sudo apt-get remove --auto-remove android-sdk-platform-tools || true
-          sudo apt-get purge --auto-remove android-sdk-platform-tools || true
-          sudo rm -rf /usr/local/lib/android
-          sudo apt-get remove -y '^dotnet-.*|^aspnetcore-.*' || true
-          sudo rm -rf /usr/share/dotnet
-          sudo apt-get remove -y '^mono-.*' || true
-          sudo apt-get remove -y '^ghc-.*' || true
-          sudo apt-get remove -y '.*jdk.*|.*jre.*' || true
-          sudo apt-get remove -y 'php.*' || true
-          sudo apt-get remove -y hhvm powershell firefox monodoc-manual msbuild || true
-          sudo apt-get remove -y '^google-.*' || true
-          sudo apt-get remove -y azure-cli || true
-          sudo apt-get remove -y '^mongo.*-.*|^postgresql-.*|^mysql-.*|^mssql-.*' || true
-          sudo apt-get remove -y '^gfortran-.*' || true
-          sudo apt-get autoremove -y
-          sudo apt-get clean
-          echo
-          echo "Listing top largest packages"
-          pkgs=$(dpkg-query -Wf '${Installed-Size}\t${Package}\t${Status}\n' | awk '$NF == "installed"{print $1 "\t" $2}' | sort -nr)
-          head -n 30 <<< "${pkgs}"
-          echo
-          sudo rm -rfv build || true
-          df -h
-      - name: Clone
-        uses: actions/checkout@v6
-        with:
-          submodules: true
-      - name: Dependencies
-        run: |
-          # Install protoc
-          curl -L -s https://github.com/protocolbuffers/protobuf/releases/download/v26.1/protoc-26.1-linux-x86_64.zip -o protoc.zip && \
-          unzip -j -d /usr/local/bin protoc.zip bin/protoc && \
-          rm protoc.zip
-          go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2
-          go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
-          PATH="$PATH:$HOME/go/bin" make protogen-go
-      - name: Test
-        run: |
-            PATH="$PATH:$HOME/go/bin" make backends/local-store backends/silero-vad backends/llama-cpp backends/whisper backends/piper backends/stablediffusion-ggml docker-build-e2e e2e-aio
+          PATH="$PATH:/root/go/bin" make --jobs 5 --output-sync=target test
       - name: Setup tmate session if tests fail
         if: ${{ failure() }}
         uses: mxschmitt/action-tmate@v3.23
@@ -200,10 +142,6 @@ jobs:
           node-version: '22'
       - name: Build React UI
         run: make react-ui
-      - name: Build llama-cpp-darwin
-        run: |
-          make protogen-go
-          make backends/llama-cpp-darwin
       - name: Test
         run: |
           export C_INCLUDE_PATH=/usr/local/include
diff --git a/.github/workflows/tests-aio.yml b/.github/workflows/tests-aio.yml
new file mode 100644
index 000000000..7c8579266
--- /dev/null
+++ b/.github/workflows/tests-aio.yml
@@ -0,0 +1,86 @@
+---
+name: 'tests-aio'
+
+# Runs the all-in-one (AIO) Docker image with real backends + real models.
+# Heavy: builds llama-cpp/whisper/piper/silero-vad/stablediffusion-ggml/local-store
+# and exercises end-to-end inference inside the container. Moved out of test.yml
+# (which used to run on every PR) so PR CI no longer pays this cost.
+#
+# Triggers:
+#   - schedule (nightly @ 04:00 UTC) — catches packaging/image regressions within 24h
+#   - workflow_dispatch — manual run on-demand
+#   - push to master/tags — sanity check after merge / before release
+
+on:
+  schedule:
+    - cron: '0 4 * * *'
+  workflow_dispatch:
+  push:
+    branches:
+      - master
+    tags:
+      - '*'
+
+concurrency:
+  group: ci-tests-aio-${{ github.head_ref || github.ref }}-${{ github.repository }}
+  cancel-in-progress: true
+
+jobs:
+  tests-aio:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Release space from worker
+        run: |
+          echo "Listing top largest packages"
+          pkgs=$(dpkg-query -Wf '${Installed-Size}\t${Package}\t${Status}\n' | awk '$NF == "installed"{print $1 "\t" $2}' | sort -nr)
+          head -n 30 <<< "${pkgs}"
+          echo
+          df -h
+          echo
+          sudo apt-get remove -y '^llvm-.*|^libllvm.*' || true
+          sudo apt-get remove --auto-remove android-sdk-platform-tools || true
+          sudo apt-get purge --auto-remove android-sdk-platform-tools || true
+          sudo rm -rf /usr/local/lib/android
+          sudo apt-get remove -y '^dotnet-.*|^aspnetcore-.*' || true
+          sudo rm -rf /usr/share/dotnet
+          sudo apt-get remove -y '^mono-.*' || true
+          sudo apt-get remove -y '^ghc-.*' || true
+          sudo apt-get remove -y '.*jdk.*|.*jre.*' || true
+          sudo apt-get remove -y 'php.*' || true
+          sudo apt-get remove -y hhvm powershell firefox monodoc-manual msbuild || true
+          sudo apt-get remove -y '^google-.*' || true
+          sudo apt-get remove -y azure-cli || true
+          sudo apt-get remove -y '^mongo.*-.*|^postgresql-.*|^mysql-.*|^mssql-.*' || true
+          sudo apt-get remove -y '^gfortran-.*' || true
+          sudo apt-get autoremove -y
+          sudo apt-get clean
+          echo
+          echo "Listing top largest packages"
+          pkgs=$(dpkg-query -Wf '${Installed-Size}\t${Package}\t${Status}\n' | awk '$NF == "installed"{print $1 "\t" $2}' | sort -nr)
+          head -n 30 <<< "${pkgs}"
+          echo
+          sudo rm -rfv build || true
+          df -h
+      - name: Clone
+        uses: actions/checkout@v6
+        with:
+          submodules: true
+      - name: Dependencies
+        run: |
+          # Install protoc
+          curl -L -s https://github.com/protocolbuffers/protobuf/releases/download/v26.1/protoc-26.1-linux-x86_64.zip -o protoc.zip && \
+          unzip -j -d /usr/local/bin protoc.zip bin/protoc && \
+          rm protoc.zip
+          go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2
+          go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
+          PATH="$PATH:$HOME/go/bin" make protogen-go
+      - name: Test
+        run: |
+            PATH="$PATH:$HOME/go/bin" make backends/local-store backends/silero-vad backends/llama-cpp backends/whisper backends/piper backends/stablediffusion-ggml docker-build-e2e e2e-aio
+      - name: Setup tmate session if tests fail
+        if: ${{ failure() }}
+        uses: mxschmitt/action-tmate@v3.23
+        with:
+          detached: true
+          connect-timeout-seconds: 180
+          limit-access-to-actor: true
diff --git a/.github/workflows/tests-e2e.yml b/.github/workflows/tests-e2e.yml
index 73a9535b6..de916cc4a 100644
--- a/.github/workflows/tests-e2e.yml
+++ b/.github/workflows/tests-e2e.yml
@@ -3,6 +3,12 @@ name: 'E2E Backend Tests'
 
 on:
   pull_request:
+    paths-ignore:
+      - 'docs/**'
+      - 'examples/**'
+      - 'README.md'
+      - '**/*.md'
+      - 'backend/**'
   push:
     branches:
       - master
diff --git a/Makefile b/Makefile
index 2f3ee1dea..a76f7975a 100644
--- a/Makefile
+++ b/Makefile
@@ -85,6 +85,7 @@ clean: ## Remove build related file
 clean-tests:
 	rm -rf test-models
 	rm -rf test-dir
+	rm -f tests/e2e/mock-backend/mock-backend
 
 ## Install Go tools
 install-go-tools:
@@ -143,32 +144,24 @@ osx-signed: build
 run: ## run local-ai
 	CGO_LDFLAGS="$(CGO_LDFLAGS)" $(GOCMD) run ./
 
-test-models/testmodel.ggml:
-	mkdir -p test-models
-	mkdir -p test-dir
-	wget -q https://huggingface.co/mradermacher/gpt2-alpaca-gpt4-GGUF/resolve/main/gpt2-alpaca-gpt4.Q4_K_M.gguf -O test-models/testmodel.ggml
-	wget -q https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.en.bin -O test-models/whisper-en
-	wget -q https://cdn.openai.com/whisper/draft-20220913a/micro-machines.wav -O test-dir/audio.wav
-	cp tests/models_fixtures/* test-models
-
-prepare-test: protogen-go
-	cp tests/models_fixtures/* test-models
+prepare-test: protogen-go build-mock-backend
 
 ########################################################
 ## Tests
 ########################################################
 
 ## Test targets
-test: test-models/testmodel.ggml protogen-go
+## After the test-suite reorg (see plans/test-reorg) the default `make test`
+## no longer downloads multi-GB GGUF/whisper fixtures or builds llama-cpp /
+## transformers / piper / whisper / stablediffusion-ggml. core/http/app_test.go
+## now drives the mock-backend binary built by build-mock-backend; real-backend
+## inference moved into tests/e2e-backends/ (per-backend, path-filtered) and
+## tests/e2e-aio/ (nightly).
+test: prepare-test
 	@echo 'Running tests'
 	export GO_TAGS="debug"
-	$(MAKE) prepare-test
 	OPUS_SHIM_LIBRARY=$(abspath ./pkg/opus/shim/libopusshim.so) \
-	HUGGINGFACE_GRPC=$(abspath ./)/backend/python/transformers/run.sh TEST_DIR=$(abspath ./)/test-dir/ FIXTURES=$(abspath ./)/tests/fixtures CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models BACKENDS_PATH=$(abspath ./)/backends \
-	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="!llama-gguf"  --flake-attempts $(TEST_FLAKES) --fail-fast -v -r $(TEST_PATHS)
-	$(MAKE) test-llama-gguf
-	$(MAKE) test-tts
-	$(MAKE) test-stablediffusion
+	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --flake-attempts $(TEST_FLAKES) --fail-fast -v -r $(TEST_PATHS)
 
 ########################################################
 ## E2E AIO tests (uses standard image with pre-configured models)
@@ -235,20 +228,12 @@ teardown-e2e:
 ## Integration and unit tests
 ########################################################
 
-test-llama-gguf: prepare-test
-	TEST_DIR=$(abspath ./)/test-dir/ FIXTURES=$(abspath ./)/tests/fixtures CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models BACKENDS_PATH=$(abspath ./)/backends \
-	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="llama-gguf" --flake-attempts $(TEST_FLAKES) -v -r $(TEST_PATHS)
-
-test-tts: prepare-test
-	TEST_DIR=$(abspath ./)/test-dir/ FIXTURES=$(abspath ./)/tests/fixtures CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models BACKENDS_PATH=$(abspath ./)/backends \
-	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="tts" --flake-attempts $(TEST_FLAKES) -v -r $(TEST_PATHS)
-
-test-stablediffusion: prepare-test
-	TEST_DIR=$(abspath ./)/test-dir/ FIXTURES=$(abspath ./)/tests/fixtures CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models BACKENDS_PATH=$(abspath ./)/backends \
-	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="stablediffusion" --flake-attempts $(TEST_FLAKES) -v -r $(TEST_PATHS)
-
-test-stores:
-	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="stores" --flake-attempts $(TEST_FLAKES) -v -r tests/integration
+## Storage / vector-store integration. Requires the local-store backend to
+## be available — we build it on demand and pass its location via
+## BACKENDS_PATH (the model loader looks there for the gRPC binary).
+test-stores: backends/local-store
+	BACKENDS_PATH=$(abspath ./)/backends \
+	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --flake-attempts $(TEST_FLAKES) -v -r tests/integration
 
 test-opus:
 	@echo 'Running opus backend tests'
@@ -269,23 +254,13 @@ test-realtime: build-mock-backend
 	@echo 'Running realtime e2e tests (mock backend)'
 	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="Realtime && !real-models" --flake-attempts $(TEST_FLAKES) -v -r ./tests/e2e
 
-# Real-model realtime tests. Set REALTIME_TEST_MODEL to use your own pipeline,
-# or leave unset to auto-build one from the component env vars below.
+# Container-based real-model realtime testing. Build env vars / pipeline
+# definition kept here so test-realtime-models-docker can drive a fully wired
+# pipeline (VAD + STT + LLM + TTS) from inside a containerised runner.
 REALTIME_VAD?=silero-vad-ggml
 REALTIME_STT?=whisper-1
 REALTIME_LLM?=qwen3-0.6b
 REALTIME_TTS?=tts-1
-REALTIME_BACKENDS_PATH?=$(abspath ./)/backends
-
-test-realtime-models: build-mock-backend
-	@echo 'Running realtime e2e tests (real models)'
-	REALTIME_TEST_MODEL=$${REALTIME_TEST_MODEL:-realtime-test-pipeline} \
-	REALTIME_VAD=$(REALTIME_VAD) \
-	REALTIME_STT=$(REALTIME_STT) \
-	REALTIME_LLM=$(REALTIME_LLM) \
-	REALTIME_TTS=$(REALTIME_TTS) \
-	REALTIME_BACKENDS_PATH=$(REALTIME_BACKENDS_PATH) \
-	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="Realtime" --flake-attempts $(TEST_FLAKES) -v -r ./tests/e2e
 
 # --- Container-based real-model testing ---
 
@@ -528,7 +503,9 @@ test-extra-backend: protogen-go
 
 ## Convenience wrappers: build the image, then exercise it.
 test-extra-backend-llama-cpp: docker-build-llama-cpp
-	BACKEND_IMAGE=local-ai-backend:llama-cpp $(MAKE) test-extra-backend
+	BACKEND_IMAGE=local-ai-backend:llama-cpp \
+	BACKEND_TEST_CAPS=health,load,predict,stream,logprobs,logit_bias \
+	$(MAKE) test-extra-backend
 
 test-extra-backend-ik-llama-cpp: docker-build-ik-llama-cpp
 	BACKEND_IMAGE=local-ai-backend:ik-llama-cpp $(MAKE) test-extra-backend
diff --git a/core/http/app_test.go b/core/http/app_test.go
index 74220855c..31c6c5a55 100644
--- a/core/http/app_test.go
+++ b/core/http/app_test.go
@@ -9,7 +9,6 @@ import (
 	"net/http"
 	"os"
 	"path/filepath"
-	"runtime"
 	"time"
 
 	"github.com/mudler/LocalAI/core/application"
@@ -28,7 +27,6 @@ import (
 	"github.com/mudler/xlog"
 	openaigo "github.com/otiai10/openaigo"
 	"github.com/sashabaranov/go-openai"
-	"github.com/sashabaranov/go-openai/jsonschema"
 )
 
 const apiKey = "joshua"
@@ -322,7 +320,9 @@ var _ = Describe("API test", func() {
 			tmpdir, err = os.MkdirTemp("", "")
 			Expect(err).ToNot(HaveOccurred())
 
-			backendPath := os.Getenv("BACKENDS_PATH")
+			// No real backends needed — these specs cover gallery API, auth,
+			// routing, and file:// import. Use the suite-level empty backend dir.
+			backendPath := backendDir
 
 			modelDir = filepath.Join(tmpdir, "models")
 			err = os.Mkdir(modelDir, 0750)
@@ -671,258 +671,42 @@ parameters:
 		})
 	})
 
-	Context("Model gallery", func() {
+	Context("API query", func() {
 		BeforeEach(func() {
-			var err error
-			tmpdir, err = os.MkdirTemp("", "")
-
-			backendPath := os.Getenv("BACKENDS_PATH")
-
-			Expect(err).ToNot(HaveOccurred())
-			modelDir = filepath.Join(tmpdir, "models")
-			backendAssetsDir := filepath.Join(tmpdir, "backend-assets")
-			err = os.Mkdir(backendAssetsDir, 0750)
-			Expect(err).ToNot(HaveOccurred())
-
+			if mockBackendPath == "" {
+				Skip("mock-backend binary not built; run 'make build-mock-backend'")
+			}
 			c, cancel = context.WithCancel(context.Background())
 
-			galleries := []config.Gallery{
-				{
-					Name: "localai",
-					URL:  "https://raw.githubusercontent.com/mudler/LocalAI/refs/heads/master/gallery/index.yaml",
-				},
-			}
+			// Stand up an isolated model dir for this Context so the suite can
+			// register a mock-model config (read by /v1/models, /system, and the
+			// agent-jobs flow) without depending on real backend builds.
+			var err error
+			tmpdir, err = os.MkdirTemp("", "")
+			Expect(err).ToNot(HaveOccurred())
+			modelDir = filepath.Join(tmpdir, "models")
+			Expect(os.Mkdir(modelDir, 0750)).To(Succeed())
+
+			mockModelYAML := `name: mock-model
+backend: mock-backend
+parameters:
+  model: mock-model.bin
+`
+			Expect(os.WriteFile(filepath.Join(modelDir, "mock-model.yaml"), []byte(mockModelYAML), 0644)).To(Succeed())
 
 			systemState, err := system.GetSystemState(
-				system.WithBackendPath(backendPath),
+				system.WithBackendPath(backendDir),
 				system.WithModelPath(modelDir),
 			)
 			Expect(err).ToNot(HaveOccurred())
 
 			application, err := application.New(
 				append(commonOpts,
-					config.WithContext(c),
-					config.WithGeneratedContentDir(tmpdir),
-					config.WithSystemState(systemState),
-					config.WithGalleries(galleries),
-				)...,
-			)
-			Expect(err).ToNot(HaveOccurred())
-			app, err = API(application)
-			Expect(err).ToNot(HaveOccurred())
-
-			go func() {
-				if err := app.Start("127.0.0.1:9090"); err != nil && err != http.ErrServerClosed {
-					xlog.Error("server error", "error", err)
-				}
-			}()
-
-			defaultConfig := openai.DefaultConfig("")
-			defaultConfig.BaseURL = "http://127.0.0.1:9090/v1"
-
-			client2 = openaigo.NewClient("")
-			client2.BaseURL = defaultConfig.BaseURL
-
-			// Wait for API to be ready
-			client = openai.NewClientWithConfig(defaultConfig)
-			Eventually(func() error {
-				_, err := client.ListModels(context.TODO())
-				return err
-			}, "2m").ShouldNot(HaveOccurred())
-		})
-
-		AfterEach(func() {
-			cancel()
-			if app != nil {
-				ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
-				defer cancel()
-				err := app.Shutdown(ctx)
-				Expect(err).ToNot(HaveOccurred())
-			}
-			err := os.RemoveAll(tmpdir)
-			Expect(err).ToNot(HaveOccurred())
-			_, err = os.ReadDir(tmpdir)
-			Expect(err).To(HaveOccurred())
-		})
-
-		It("runs gguf models (chat)", Label("llama-gguf"), func() {
-			if runtime.GOOS != "linux" {
-				Skip("test supported only on linux")
-			}
-
-			modelName := "qwen3-1.7b"
-			response := postModelApplyRequest("http://127.0.0.1:9090/models/apply", modelApplyRequest{
-				ID: "localai@" + modelName,
-			})
-
-			Expect(response["uuid"]).ToNot(BeEmpty(), fmt.Sprint(response))
-
-			uuid := response["uuid"].(string)
-
-			Eventually(func() bool {
-				response := getModelStatus("http://127.0.0.1:9090/models/jobs/" + uuid)
-				return response["processed"].(bool)
-			}, "900s", "10s").Should(Equal(true))
-
-			By("testing chat")
-			resp, err := client.CreateChatCompletion(context.TODO(), openai.ChatCompletionRequest{Model: modelName, Messages: []openai.ChatCompletionMessage{
-				{
-					Role:    "user",
-					Content: "How much is 2+2?",
-				},
-			}})
-			Expect(err).ToNot(HaveOccurred())
-			Expect(len(resp.Choices)).To(Equal(1))
-			Expect(resp.Choices[0].Message.Content).To(Or(ContainSubstring("4"), ContainSubstring("four")))
-
-			By("testing functions")
-			resp2, err := client.CreateChatCompletion(
-				context.TODO(),
-				openai.ChatCompletionRequest{
-					Model: modelName,
-					Messages: []openai.ChatCompletionMessage{
-						{
-							Role:    "user",
-							Content: "What is the weather like in San Francisco (celsius)?",
-						},
-					},
-					Functions: []openai.FunctionDefinition{
-						openai.FunctionDefinition{
-							Name:        "get_current_weather",
-							Description: "Get the current weather",
-							Parameters: jsonschema.Definition{
-								Type: jsonschema.Object,
-								Properties: map[string]jsonschema.Definition{
-									"location": {
-										Type:        jsonschema.String,
-										Description: "The city and state, e.g. San Francisco, CA",
-									},
-									"unit": {
-										Type: jsonschema.String,
-										Enum: []string{"celcius", "fahrenheit"},
-									},
-								},
-								Required: []string{"location"},
-							},
-						},
-					},
-				})
-			Expect(err).ToNot(HaveOccurred())
-			Expect(len(resp2.Choices)).To(Equal(1))
-			Expect(resp2.Choices[0].Message.FunctionCall).ToNot(BeNil())
-			Expect(resp2.Choices[0].Message.FunctionCall.Name).To(Equal("get_current_weather"), resp2.Choices[0].Message.FunctionCall.Name)
-
-			var res map[string]string
-			err = json.Unmarshal([]byte(resp2.Choices[0].Message.FunctionCall.Arguments), &res)
-			Expect(err).ToNot(HaveOccurred())
-			Expect(res["location"]).To(ContainSubstring("San Francisco"), fmt.Sprint(res))
-			Expect(res["unit"]).To(Equal("celcius"), fmt.Sprint(res))
-			Expect(string(resp2.Choices[0].FinishReason)).To(Equal("function_call"), fmt.Sprint(resp2.Choices[0].FinishReason))
-		})
-
-		It("installs and is capable to run tts", Label("tts"), func() {
-			if runtime.GOOS != "linux" {
-				Skip("test supported only on linux")
-			}
-
-			response := postModelApplyRequest("http://127.0.0.1:9090/models/apply", modelApplyRequest{
-				ID: "localai@voice-en-us-kathleen-low",
-			})
-
-			Expect(response["uuid"]).ToNot(BeEmpty(), fmt.Sprint(response))
-
-			uuid := response["uuid"].(string)
-
-			Eventually(func() bool {
-				response := getModelStatus("http://127.0.0.1:9090/models/jobs/" + uuid)
-				fmt.Println(response)
-				return response["processed"].(bool)
-			}, "360s", "10s").Should(Equal(true))
-
-			// An HTTP Post to the /tts endpoint should return a wav audio file
-			resp, err := http.Post("http://127.0.0.1:9090/tts", "application/json", bytes.NewBuffer([]byte(`{"input": "Hello world", "model": "voice-en-us-kathleen-low"}`)))
-			Expect(err).ToNot(HaveOccurred(), fmt.Sprint(resp))
-			dat, err := io.ReadAll(resp.Body)
-			Expect(err).ToNot(HaveOccurred(), fmt.Sprint(resp))
-
-			Expect(resp.StatusCode).To(Equal(200), fmt.Sprint(string(dat)))
-			Expect(resp.Header.Get("Content-Type")).To(Or(Equal("audio/x-wav"), Equal("audio/wav"), Equal("audio/vnd.wave")))
-		})
-		It("installs and is capable to generate images", Label("stablediffusion"), func() {
-			if runtime.GOOS != "linux" {
-				Skip("test supported only on linux")
-			}
-
-			response := postModelApplyRequest("http://127.0.0.1:9090/models/apply", modelApplyRequest{
-				ID:   "localai@sd-1.5-ggml",
-				Name: "stablediffusion",
-			})
-
-			Expect(response["uuid"]).ToNot(BeEmpty(), fmt.Sprint(response))
-
-			uuid := response["uuid"].(string)
-
-			Eventually(func() bool {
-				response := getModelStatus("http://127.0.0.1:9090/models/jobs/" + uuid)
-				fmt.Println(response)
-				return response["processed"].(bool)
-			}, "1200s", "10s").Should(Equal(true))
-
-			resp, err := http.Post(
-				"http://127.0.0.1:9090/v1/images/generations",
-				"application/json",
-				bytes.NewBuffer([]byte(`{
-					 			"prompt": "a lovely cat",
-								"step": 1,  "seed":9000,
-					 			"size": "256x256", "n":2}`)))
-			// The response should contain an URL
-			Expect(err).ToNot(HaveOccurred(), fmt.Sprint(resp))
-			dat, err := io.ReadAll(resp.Body)
-			Expect(err).ToNot(HaveOccurred(), "error reading /image/generations response")
-
-			imgUrlResp := &schema.OpenAIResponse{}
-			err = json.Unmarshal(dat, imgUrlResp)
-			Expect(err).ToNot(HaveOccurred(), fmt.Sprint(dat))
-			Expect(imgUrlResp.Data).ToNot(Or(BeNil(), BeZero()))
-			imgUrl := imgUrlResp.Data[0].URL
-			Expect(imgUrl).To(ContainSubstring("http://127.0.0.1:9090/"), imgUrl)
-			Expect(imgUrl).To(ContainSubstring(".png"), imgUrl)
-
-			imgResp, err := http.Get(imgUrl)
-			Expect(err).To(BeNil())
-			Expect(imgResp).ToNot(BeNil())
-			Expect(imgResp.StatusCode).To(Equal(200))
-			Expect(imgResp.ContentLength).To(BeNumerically(">", 0))
-			imgData := make([]byte, 512)
-			count, err := io.ReadFull(imgResp.Body, imgData)
-			Expect(err).To(Or(BeNil(), MatchError(io.EOF)))
-			Expect(count).To(BeNumerically(">", 0))
-			Expect(count).To(BeNumerically("<=", 512))
-			Expect(http.DetectContentType(imgData)).To(Equal("image/png"))
-		})
-	})
-
-	Context("API query", func() {
-		BeforeEach(func() {
-			modelPath := os.Getenv("MODELS_PATH")
-			backendPath := os.Getenv("BACKENDS_PATH")
-			c, cancel = context.WithCancel(context.Background())
-
-			var err error
-
-			systemState, err := system.GetSystemState(
-				system.WithBackendPath(backendPath),
-				system.WithModelPath(modelPath),
-			)
-			Expect(err).ToNot(HaveOccurred())
-
-			application, err := application.New(
-				append(commonOpts,
-					config.WithExternalBackend("transformers", os.Getenv("TRANSFORMER_BACKEND")),
 					config.WithContext(c),
 					config.WithSystemState(systemState),
 				)...)
 			Expect(err).ToNot(HaveOccurred())
+			application.ModelLoader().SetExternalBackend("mock-backend", mockBackendPath)
 			app, err = API(application)
 			Expect(err).ToNot(HaveOccurred())
 			go func() {
@@ -952,149 +736,12 @@ parameters:
 				err := app.Shutdown(ctx)
 				Expect(err).ToNot(HaveOccurred())
 			}
+			Expect(os.RemoveAll(tmpdir)).To(Succeed())
 		})
 		It("returns the models list", func() {
 			models, err := client.ListModels(context.TODO())
 			Expect(err).ToNot(HaveOccurred())
-			Expect(len(models.Models)).To(BeNumerically(">=", 7))
-		})
-		It("can generate completions via ggml", func() {
-			if runtime.GOOS != "linux" {
-				Skip("test supported only on linux")
-			}
-			resp, err := client.CreateCompletion(context.TODO(), openai.CompletionRequest{Model: "testmodel.ggml", Prompt: testPrompt})
-			Expect(err).ToNot(HaveOccurred())
-			Expect(len(resp.Choices)).To(Equal(1))
-			Expect(resp.Choices[0].Text).ToNot(BeEmpty())
-		})
-
-		It("can generate chat completions via ggml", func() {
-			if runtime.GOOS != "linux" {
-				Skip("test supported only on linux")
-			}
-			resp, err := client.CreateChatCompletion(context.TODO(), openai.ChatCompletionRequest{Model: "testmodel.ggml", Messages: []openai.ChatCompletionMessage{openai.ChatCompletionMessage{Role: "user", Content: testPrompt}}})
-			Expect(err).ToNot(HaveOccurred())
-			Expect(len(resp.Choices)).To(Equal(1))
-			Expect(resp.Choices[0].Message.Content).ToNot(BeEmpty())
-		})
-
-		It("does not duplicate the first content token in streaming chat completions", Label("llama-gguf", "llama-gguf-stream"), func() {
-			if runtime.GOOS != "linux" {
-				Skip("test supported only on linux")
-			}
-			stream, err := client.CreateChatCompletionStream(context.TODO(), openai.ChatCompletionRequest{
-				Model:    "testmodel.ggml",
-				Messages: []openai.ChatCompletionMessage{{Role: "user", Content: testPrompt}},
-			})
-			Expect(err).ToNot(HaveOccurred())
-			defer stream.Close()
-
-			var contentParts []string
-			for {
-				chunk, err := stream.Recv()
-				if err == io.EOF {
-					break
-				}
-				Expect(err).ToNot(HaveOccurred())
-				if len(chunk.Choices) > 0 {
-					delta := chunk.Choices[0].Delta.Content
-					if delta != "" {
-						contentParts = append(contentParts, delta)
-					}
-				}
-			}
-
-			Expect(contentParts).ToNot(BeEmpty(), "Expected streaming content tokens")
-			// The first content token should appear exactly once.
-			// A bug in grpc-server.cpp caused the role-init array element
-			// to get the same ChatDelta stamped, duplicating the first token.
-			if len(contentParts) >= 2 {
-				Expect(contentParts[0]).ToNot(Equal(contentParts[1]),
-					"First content token was duplicated: %v", contentParts[:2])
-			}
-		})
-
-		It("returns logprobs in chat completions when requested", func() {
-			if runtime.GOOS != "linux" {
-				Skip("test only on linux")
-			}
-			topLogprobsVal := 3
-			response, err := client.CreateChatCompletion(context.TODO(), openai.ChatCompletionRequest{
-				Model:       "testmodel.ggml",
-				LogProbs:    true,
-				TopLogProbs: topLogprobsVal,
-				Messages:    []openai.ChatCompletionMessage{{Role: "user", Content: testPrompt}}})
-			Expect(err).ToNot(HaveOccurred())
-
-			Expect(len(response.Choices)).To(Equal(1))
-			Expect(response.Choices[0].Message).ToNot(BeNil())
-			Expect(response.Choices[0].Message.Content).ToNot(BeEmpty())
-
-			// Verify logprobs are present and have correct structure
-			Expect(response.Choices[0].LogProbs).ToNot(BeNil())
-			Expect(response.Choices[0].LogProbs.Content).ToNot(BeEmpty())
-
-			Expect(len(response.Choices[0].LogProbs.Content)).To(BeNumerically(">", 1))
-
-			foundatLeastToken := ""
-			foundAtLeastBytes := []byte{}
-			foundAtLeastTopLogprobBytes := []byte{}
-			foundatLeastTopLogprob := ""
-			// Verify logprobs content structure matches OpenAI format
-			for _, logprobContent := range response.Choices[0].LogProbs.Content {
-				// Bytes can be empty for certain tokens (special tokens, etc.), so we don't require it
-				if len(logprobContent.Bytes) > 0 {
-					foundAtLeastBytes = logprobContent.Bytes
-				}
-				if len(logprobContent.Token) > 0 {
-					foundatLeastToken = logprobContent.Token
-				}
-				Expect(logprobContent.LogProb).To(BeNumerically("<=", 0)) // Logprobs are always <= 0
-				Expect(len(logprobContent.TopLogProbs)).To(BeNumerically(">", 1))
-
-				// If top_logprobs is requested, verify top_logprobs array respects the limit
-				if len(logprobContent.TopLogProbs) > 0 {
-					// Should respect top_logprobs limit (3 in this test)
-					Expect(len(logprobContent.TopLogProbs)).To(BeNumerically("<=", topLogprobsVal))
-					for _, topLogprob := range logprobContent.TopLogProbs {
-						if len(topLogprob.Bytes) > 0 {
-							foundAtLeastTopLogprobBytes = topLogprob.Bytes
-						}
-						if len(topLogprob.Token) > 0 {
-							foundatLeastTopLogprob = topLogprob.Token
-						}
-						Expect(topLogprob.LogProb).To(BeNumerically("<=", 0))
-					}
-				}
-			}
-
-			Expect(foundAtLeastBytes).ToNot(BeEmpty())
-			Expect(foundAtLeastTopLogprobBytes).ToNot(BeEmpty())
-			Expect(foundatLeastToken).ToNot(BeEmpty())
-			Expect(foundatLeastTopLogprob).ToNot(BeEmpty())
-		})
-
-		It("applies logit_bias to chat completions when requested", func() {
-			if runtime.GOOS != "linux" {
-				Skip("test only on linux")
-			}
-			// logit_bias is a map of token IDs (as strings) to bias values (-100 to 100)
-			// According to OpenAI API: modifies the likelihood of specified tokens appearing in the completion
-			logitBias := map[string]int{
-				"15043": 1, // Bias token ID 15043 (example token ID) with bias value 1
-			}
-			response, err := client.CreateChatCompletion(context.TODO(), openai.ChatCompletionRequest{
-				Model:     "testmodel.ggml",
-				Messages:  []openai.ChatCompletionMessage{{Role: "user", Content: testPrompt}},
-				LogitBias: logitBias,
-			})
-			Expect(err).ToNot(HaveOccurred())
-			Expect(len(response.Choices)).To(Equal(1))
-			Expect(response.Choices[0].Message).ToNot(BeNil())
-			Expect(response.Choices[0].Message.Content).ToNot(BeEmpty())
-			// If logit_bias is applied, the response should be generated successfully
-			// We can't easily verify the bias effect without knowing the actual token IDs for the model,
-			// but the fact that the request succeeds confirms the API accepts and processes logit_bias
+			Expect(len(models.Models)).To(BeNumerically(">=", 1))
 		})
 
 		It("returns errors", func() {
@@ -1103,331 +750,193 @@ parameters:
 			Expect(err.Error()).To(ContainSubstring("error, status code: 404, status: 404 Not Found"))
 		})
 
-		It("shows the external backend", func() {
-			// Only run on linux
-			if runtime.GOOS != "linux" {
-				Skip("test supported only on linux")
-			}
-			// do an http request to the /system endpoint
+		It("shows the external backend on /system", func() {
+			// /system reports the backends available to the application.
+			// Mock-backend is registered via SetExternalBackend so it appears
+			// alongside any built-in entries; verifying that string proves the
+			// endpoint is wired up regardless of which real backends exist.
 			resp, err := http.Get("http://127.0.0.1:9090/system")
 			Expect(err).ToNot(HaveOccurred())
 			Expect(resp.StatusCode).To(Equal(200))
 			dat, err := io.ReadAll(resp.Body)
 			Expect(err).ToNot(HaveOccurred())
-			Expect(string(dat)).To(ContainSubstring("llama-cpp"))
+			Expect(string(dat)).To(ContainSubstring("mock-backend"))
 		})
 
-		It("transcribes audio", func() {
-			if runtime.GOOS != "linux" {
-				Skip("test supported only on linux")
-			}
-			resp, err := client.CreateTranscription(
-				context.Background(),
-				openai.AudioRequest{
-					Model:    openai.Whisper1,
-					FilePath: filepath.Join(os.Getenv("TEST_DIR"), "audio.wav"),
-				},
-			)
-			Expect(err).ToNot(HaveOccurred())
-			Expect(resp.Text).To(ContainSubstring("This is the Micro Machine Man presenting"))
-		})
-
-		It("calculate embeddings", func() {
-			if runtime.GOOS != "linux" {
-				Skip("test supported only on linux")
-			}
-			embeddingModel := openai.AdaEmbeddingV2
-			resp, err := client.CreateEmbeddings(
-				context.Background(),
-				openai.EmbeddingRequest{
-					Model: embeddingModel,
-					Input: []string{"sun", "cat"},
-				},
-			)
-			Expect(err).ToNot(HaveOccurred(), err)
-			Expect(len(resp.Data[0].Embedding)).To(BeNumerically("==", 4096))
-			Expect(len(resp.Data[1].Embedding)).To(BeNumerically("==", 4096))
-
-			sunEmbedding := resp.Data[0].Embedding
-			resp2, err := client.CreateEmbeddings(
-				context.Background(),
-				openai.EmbeddingRequest{
-					Model: embeddingModel,
-					Input: []string{"sun"},
-				},
-			)
-			Expect(err).ToNot(HaveOccurred())
-			Expect(resp2.Data[0].Embedding).To(Equal(sunEmbedding))
-			Expect(resp2.Data[0].Embedding).ToNot(Equal(resp.Data[1].Embedding))
-
-			resp3, err := client.CreateEmbeddings(
-				context.Background(),
-				openai.EmbeddingRequest{
-					Model: embeddingModel,
-					Input: []string{"cat"},
-				},
-			)
-			Expect(err).ToNot(HaveOccurred())
-			Expect(resp3.Data[0].Embedding).To(Equal(resp.Data[1].Embedding))
-			Expect(resp3.Data[0].Embedding).ToNot(Equal(sunEmbedding))
-		})
-
-		Context("External gRPC calls", func() {
-			It("calculate embeddings with sentencetransformers", func() {
-				if runtime.GOOS != "linux" {
-					Skip("test supported only on linux")
+		// Agent Jobs: HTTP API for task/job scheduling. The underlying AgentPool
+		// service is exercised in core/services/agentpool/agent_jobs_test.go;
+		// these specs cover the /api/agent/* HTTP plumbing on top.
+		Context("Agent Jobs", func() {
+			It("creates and manages tasks", func() {
+				// Create a task
+				taskBody := map[string]any{
+					"name":        "Test Task",
+					"description": "Test Description",
+					"model":       "mock-model",
+					"prompt":      "Hello {{.name}}",
+					"enabled":     true,
 				}
-				resp, err := client.CreateEmbeddings(
-					context.Background(),
-					openai.EmbeddingRequest{
-						Model: openai.AdaCodeSearchCode,
-						Input: []string{"sun", "cat"},
-					},
-				)
+
+				var createResp map[string]any
+				err := postRequestResponseJSON("http://127.0.0.1:9090/api/agent/tasks", &taskBody, &createResp)
 				Expect(err).ToNot(HaveOccurred())
-				Expect(len(resp.Data[0].Embedding)).To(BeNumerically("==", 384))
-				Expect(len(resp.Data[1].Embedding)).To(BeNumerically("==", 384))
+				Expect(createResp["id"]).ToNot(BeEmpty())
+				taskID := createResp["id"].(string)
 
-				sunEmbedding := resp.Data[0].Embedding
-				resp2, err := client.CreateEmbeddings(
-					context.Background(),
-					openai.EmbeddingRequest{
-						Model: openai.AdaCodeSearchCode,
-						Input: []string{"sun"},
-					},
-				)
+				// Get the task
+				var task schema.Task
+				resp, err := http.Get("http://127.0.0.1:9090/api/agent/tasks/" + taskID)
 				Expect(err).ToNot(HaveOccurred())
-				Expect(resp2.Data[0].Embedding).To(Equal(sunEmbedding))
-				Expect(resp2.Data[0].Embedding).ToNot(Equal(resp.Data[1].Embedding))
-			})
-		})
+				Expect(resp.StatusCode).To(Equal(200))
+				body, _ := io.ReadAll(resp.Body)
+				json.Unmarshal(body, &task)
+				Expect(task.Name).To(Equal("Test Task"))
 
-		// See tests/integration/stores_test
-		Context("Stores", Label("stores"), func() {
+				// List tasks
+				resp, err = http.Get("http://127.0.0.1:9090/api/agent/tasks")
+				Expect(err).ToNot(HaveOccurred())
+				Expect(resp.StatusCode).To(Equal(200))
+				var tasks []schema.Task
+				body, _ = io.ReadAll(resp.Body)
+				json.Unmarshal(body, &tasks)
+				Expect(len(tasks)).To(BeNumerically(">=", 1))
 
-			BeforeEach(func() {
-				// Only run on linux
-				if runtime.GOOS != "linux" {
-					Skip("test supported only on linux")
-				}
+				// Update task
+				taskBody["name"] = "Updated Task"
+				err = putRequestJSON("http://127.0.0.1:9090/api/agent/tasks/"+taskID, &taskBody)
+				Expect(err).ToNot(HaveOccurred())
+
+				// Verify update
+				resp, err = http.Get("http://127.0.0.1:9090/api/agent/tasks/" + taskID)
+				Expect(err).ToNot(HaveOccurred())
+				body, _ = io.ReadAll(resp.Body)
+				json.Unmarshal(body, &task)
+				Expect(task.Name).To(Equal("Updated Task"))
+
+				// Delete task
+				req, _ := http.NewRequest("DELETE", "http://127.0.0.1:9090/api/agent/tasks/"+taskID, nil)
+				req.Header.Set("Authorization", bearerKey)
+				resp, err = http.DefaultClient.Do(req)
+				Expect(err).ToNot(HaveOccurred())
+				Expect(resp.StatusCode).To(Equal(200))
 			})
 
-			It("sets, gets, finds and deletes entries", func() {
-				ks := [][]float32{
-					{0.1, 0.2, 0.3},
-					{0.4, 0.5, 0.6},
-					{0.7, 0.8, 0.9},
-				}
-				vs := []string{
-					"test1",
-					"test2",
-					"test3",
-				}
-				setBody := schema.StoresSet{
-					Keys:   ks,
-					Values: vs,
+			It("executes and monitors jobs", func() {
+				// Create a task first
+				taskBody := map[string]any{
+					"name":    "Job Test Task",
+					"model":   "mock-model",
+					"prompt":  "Say hello",
+					"enabled": true,
 				}
 
-				url := "http://127.0.0.1:9090/stores/"
-				err := postRequestJSON(url+"set", &setBody)
+				var createResp map[string]any
+				err := postRequestResponseJSON("http://127.0.0.1:9090/api/agent/tasks", &taskBody, &createResp)
 				Expect(err).ToNot(HaveOccurred())
+				taskID := createResp["id"].(string)
 
-				getBody := schema.StoresGet{
-					Keys: ks,
+				// Execute a job
+				jobBody := map[string]any{
+					"task_id":    taskID,
+					"parameters": map[string]string{},
 				}
-				var getRespBody schema.StoresGetResponse
-				err = postRequestResponseJSON(url+"get", &getBody, &getRespBody)
+
+				var jobResp schema.JobExecutionResponse
+				err = postRequestResponseJSON("http://127.0.0.1:9090/api/agent/jobs/execute", &jobBody, &jobResp)
 				Expect(err).ToNot(HaveOccurred())
-				Expect(len(getRespBody.Keys)).To(Equal(len(ks)))
+				Expect(jobResp.JobID).ToNot(BeEmpty())
+				jobID := jobResp.JobID
 
-				for i, v := range getRespBody.Keys {
-					if v[0] == 0.1 {
-						Expect(getRespBody.Values[i]).To(Equal("test1"))
-					} else if v[0] == 0.4 {
-						Expect(getRespBody.Values[i]).To(Equal("test2"))
-					} else {
-						Expect(getRespBody.Values[i]).To(Equal("test3"))
-					}
-				}
-
-				deleteBody := schema.StoresDelete{
-					Keys: [][]float32{
-						{0.1, 0.2, 0.3},
-					},
-				}
-				err = postRequestJSON(url+"delete", &deleteBody)
+				// Get job status
+				var job schema.Job
+				resp, err := http.Get("http://127.0.0.1:9090/api/agent/jobs/" + jobID)
 				Expect(err).ToNot(HaveOccurred())
+				Expect(resp.StatusCode).To(Equal(200))
+				body, _ := io.ReadAll(resp.Body)
+				json.Unmarshal(body, &job)
+				Expect(job.ID).To(Equal(jobID))
+				Expect(job.TaskID).To(Equal(taskID))
 
-				findBody := schema.StoresFind{
-					Key:  []float32{0.1, 0.3, 0.7},
-					Topk: 10,
-				}
-
-				var findRespBody schema.StoresFindResponse
-				err = postRequestResponseJSON(url+"find", &findBody, &findRespBody)
+				// List jobs
+				resp, err = http.Get("http://127.0.0.1:9090/api/agent/jobs")
 				Expect(err).ToNot(HaveOccurred())
-				Expect(len(findRespBody.Keys)).To(Equal(2))
+				Expect(resp.StatusCode).To(Equal(200))
+				var jobs []schema.Job
+				body, _ = io.ReadAll(resp.Body)
+				json.Unmarshal(body, &jobs)
+				Expect(len(jobs)).To(BeNumerically(">=", 1))
 
-				for i, v := range findRespBody.Keys {
-					if v[0] == 0.4 {
-						Expect(findRespBody.Values[i]).To(Equal("test2"))
-					} else {
-						Expect(findRespBody.Values[i]).To(Equal("test3"))
-					}
-
-					Expect(findRespBody.Similarities[i]).To(BeNumerically(">=", -1))
-					Expect(findRespBody.Similarities[i]).To(BeNumerically("<=", 1))
-				}
-			})
-
-			Context("Agent Jobs", Label("agent-jobs"), func() {
-				It("creates and manages tasks", func() {
-					// Create a task
-					taskBody := map[string]any{
-						"name":        "Test Task",
-						"description": "Test Description",
-						"model":       "testmodel.ggml",
-						"prompt":      "Hello {{.name}}",
-						"enabled":     true,
-					}
-
-					var createResp map[string]any
-					err := postRequestResponseJSON("http://127.0.0.1:9090/api/agent/tasks", &taskBody, &createResp)
-					Expect(err).ToNot(HaveOccurred())
-					Expect(createResp["id"]).ToNot(BeEmpty())
-					taskID := createResp["id"].(string)
-
-					// Get the task
-					var task schema.Task
-					resp, err := http.Get("http://127.0.0.1:9090/api/agent/tasks/" + taskID)
-					Expect(err).ToNot(HaveOccurred())
-					Expect(resp.StatusCode).To(Equal(200))
-					body, _ := io.ReadAll(resp.Body)
-					json.Unmarshal(body, &task)
-					Expect(task.Name).To(Equal("Test Task"))
-
-					// List tasks
-					resp, err = http.Get("http://127.0.0.1:9090/api/agent/tasks")
-					Expect(err).ToNot(HaveOccurred())
-					Expect(resp.StatusCode).To(Equal(200))
-					var tasks []schema.Task
-					body, _ = io.ReadAll(resp.Body)
-					json.Unmarshal(body, &tasks)
-					Expect(len(tasks)).To(BeNumerically(">=", 1))
-
-					// Update task
-					taskBody["name"] = "Updated Task"
-					err = putRequestJSON("http://127.0.0.1:9090/api/agent/tasks/"+taskID, &taskBody)
-					Expect(err).ToNot(HaveOccurred())
-
-					// Verify update
-					resp, err = http.Get("http://127.0.0.1:9090/api/agent/tasks/" + taskID)
-					Expect(err).ToNot(HaveOccurred())
-					body, _ = io.ReadAll(resp.Body)
-					json.Unmarshal(body, &task)
-					Expect(task.Name).To(Equal("Updated Task"))
-
-					// Delete task
-					req, _ := http.NewRequest("DELETE", "http://127.0.0.1:9090/api/agent/tasks/"+taskID, nil)
+				// Cancel job (if still pending/running)
+				if job.Status == schema.JobStatusPending || job.Status == schema.JobStatusRunning {
+					req, _ := http.NewRequest("POST", "http://127.0.0.1:9090/api/agent/jobs/"+jobID+"/cancel", nil)
 					req.Header.Set("Authorization", bearerKey)
 					resp, err = http.DefaultClient.Do(req)
 					Expect(err).ToNot(HaveOccurred())
 					Expect(resp.StatusCode).To(Equal(200))
-				})
+				}
+			})
 
-				It("executes and monitors jobs", func() {
-					// Create a task first
-					taskBody := map[string]any{
-						"name":    "Job Test Task",
-						"model":   "testmodel.ggml",
-						"prompt":  "Say hello",
-						"enabled": true,
-					}
+			It("executes task by name", func() {
+				// Create a task with a specific name
+				taskBody := map[string]any{
+					"name":    "Named Task",
+					"model":   "mock-model",
+					"prompt":  "Hello",
+					"enabled": true,
+				}
 
-					var createResp map[string]any
-					err := postRequestResponseJSON("http://127.0.0.1:9090/api/agent/tasks", &taskBody, &createResp)
-					Expect(err).ToNot(HaveOccurred())
-					taskID := createResp["id"].(string)
+				var createResp map[string]any
+				err := postRequestResponseJSON("http://127.0.0.1:9090/api/agent/tasks", &taskBody, &createResp)
+				Expect(err).ToNot(HaveOccurred())
 
-					// Execute a job
-					jobBody := map[string]any{
-						"task_id":    taskID,
-						"parameters": map[string]string{},
-					}
-
-					var jobResp schema.JobExecutionResponse
-					err = postRequestResponseJSON("http://127.0.0.1:9090/api/agent/jobs/execute", &jobBody, &jobResp)
-					Expect(err).ToNot(HaveOccurred())
-					Expect(jobResp.JobID).ToNot(BeEmpty())
-					jobID := jobResp.JobID
-
-					// Get job status
-					var job schema.Job
-					resp, err := http.Get("http://127.0.0.1:9090/api/agent/jobs/" + jobID)
-					Expect(err).ToNot(HaveOccurred())
-					Expect(resp.StatusCode).To(Equal(200))
-					body, _ := io.ReadAll(resp.Body)
-					json.Unmarshal(body, &job)
-					Expect(job.ID).To(Equal(jobID))
-					Expect(job.TaskID).To(Equal(taskID))
-
-					// List jobs
-					resp, err = http.Get("http://127.0.0.1:9090/api/agent/jobs")
-					Expect(err).ToNot(HaveOccurred())
-					Expect(resp.StatusCode).To(Equal(200))
-					var jobs []schema.Job
-					body, _ = io.ReadAll(resp.Body)
-					json.Unmarshal(body, &jobs)
-					Expect(len(jobs)).To(BeNumerically(">=", 1))
-
-					// Cancel job (if still pending/running)
-					if job.Status == schema.JobStatusPending || job.Status == schema.JobStatusRunning {
-						req, _ := http.NewRequest("POST", "http://127.0.0.1:9090/api/agent/jobs/"+jobID+"/cancel", nil)
-						req.Header.Set("Authorization", bearerKey)
-						resp, err = http.DefaultClient.Do(req)
-						Expect(err).ToNot(HaveOccurred())
-						Expect(resp.StatusCode).To(Equal(200))
-					}
-				})
-
-				It("executes task by name", func() {
-					// Create a task with a specific name
-					taskBody := map[string]any{
-						"name":    "Named Task",
-						"model":   "testmodel.ggml",
-						"prompt":  "Hello",
-						"enabled": true,
-					}
-
-					var createResp map[string]any
-					err := postRequestResponseJSON("http://127.0.0.1:9090/api/agent/tasks", &taskBody, &createResp)
-					Expect(err).ToNot(HaveOccurred())
-
-					// Execute by name
-					paramsBody := map[string]string{"param1": "value1"}
-					var jobResp schema.JobExecutionResponse
-					err = postRequestResponseJSON("http://127.0.0.1:9090/api/agent/tasks/Named Task/execute", &paramsBody, &jobResp)
-					Expect(err).ToNot(HaveOccurred())
-					Expect(jobResp.JobID).ToNot(BeEmpty())
-				})
+				// Execute by name
+				paramsBody := map[string]string{"param1": "value1"}
+				var jobResp schema.JobExecutionResponse
+				err = postRequestResponseJSON("http://127.0.0.1:9090/api/agent/tasks/Named Task/execute", &paramsBody, &jobResp)
+				Expect(err).ToNot(HaveOccurred())
+				Expect(jobResp.JobID).ToNot(BeEmpty())
 			})
 		})
 	})
 
+	// Config file Context: exercises the path where models are loaded from a
+	// single multi-entry YAML (config_file option) rather than per-model YAMLs
+	// in the model dir. The fixtures point at mock-backend so this is a
+	// plumbing test for config-file loading and routing, not a real-inference
+	// test.
 	Context("Config file", func() {
 		BeforeEach(func() {
-			if runtime.GOOS != "linux" {
-				Skip("run this test only on linux")
+			if mockBackendPath == "" {
+				Skip("mock-backend binary not built; run 'make build-mock-backend'")
 			}
-			modelPath := os.Getenv("MODELS_PATH")
-			backendPath := os.Getenv("BACKENDS_PATH")
 			c, cancel = context.WithCancel(context.Background())
 
 			var err error
+			tmpdir, err = os.MkdirTemp("", "")
+			Expect(err).ToNot(HaveOccurred())
+			modelDir = filepath.Join(tmpdir, "models")
+			Expect(os.Mkdir(modelDir, 0750)).To(Succeed())
+
+			// Inline config file with two list entries that both resolve to mock-backend.
+			// Mirrors the legacy testmodel.ggml shape so the test still proves that
+			// config-file loading registers each entry as a routable model.
+			configContent := `- name: list1
+  parameters:
+    model: mock-model.bin
+  backend: mock-backend
+  context_size: 200
+- name: list2
+  parameters:
+    model: mock-model.bin
+  backend: mock-backend
+  context_size: 200
+`
+			configFile := filepath.Join(tmpdir, "config.yaml")
+			Expect(os.WriteFile(configFile, []byte(configContent), 0644)).To(Succeed())
 
 			systemState, err := system.GetSystemState(
-				system.WithBackendPath(backendPath),
-				system.WithModelPath(modelPath),
+				system.WithBackendPath(backendDir),
+				system.WithModelPath(modelDir),
 			)
 			Expect(err).ToNot(HaveOccurred())
 
@@ -1435,9 +944,10 @@ parameters:
 				append(commonOpts,
 					config.WithContext(c),
 					config.WithSystemState(systemState),
-					config.WithConfigFile(os.Getenv("CONFIG_FILE")))...,
+					config.WithConfigFile(configFile))...,
 			)
 			Expect(err).ToNot(HaveOccurred())
+			application.ModelLoader().SetExternalBackend("mock-backend", mockBackendPath)
 			app, err = API(application)
 			Expect(err).ToNot(HaveOccurred())
 
@@ -1466,6 +976,7 @@ parameters:
 				err := app.Shutdown(ctx)
 				Expect(err).ToNot(HaveOccurred())
 			}
+			Expect(os.RemoveAll(tmpdir)).To(Succeed())
 		})
 		It("can generate chat completions from config file (list1)", func() {
 			resp, err := client.CreateChatCompletion(context.TODO(), openai.ChatCompletionRequest{Model: "list1", Messages: []openai.ChatCompletionMessage{{Role: "user", Content: testPrompt}}})
diff --git a/core/http/http_suite_test.go b/core/http/http_suite_test.go
index 805eb5b52..744c2c252 100644
--- a/core/http/http_suite_test.go
+++ b/core/http/http_suite_test.go
@@ -12,8 +12,41 @@ import (
 var (
 	tmpdir   string
 	modelDir string
+
+	// Backend directory and the mock-backend binary path. Resolved by
+	// findMockBackendBinary() from the same prebuilt artifact that
+	// tests/e2e uses, so the suite no longer needs llama-cpp / transformers
+	// / whisper / piper / stablediffusion-ggml builds.
+	backendDir      string
+	mockBackendPath string
 )
 
+// findMockBackendBinary locates the mock-backend binary built by
+// `make build-mock-backend`. Mirrors the lookup used by
+// tests/e2e/e2e_suite_test.go so both suites consume the same artifact.
+func findMockBackendBinary() (string, bool) {
+	candidates := []string{
+		filepath.Join("..", "..", "tests", "e2e", "mock-backend", "mock-backend"),
+		filepath.Join("tests", "e2e", "mock-backend", "mock-backend"),
+		filepath.Join("..", "e2e", "mock-backend", "mock-backend"),
+	}
+	if wd, err := os.Getwd(); err == nil {
+		candidates = append(candidates,
+			filepath.Join(wd, "..", "..", "tests", "e2e", "mock-backend", "mock-backend"),
+		)
+	}
+	for _, p := range candidates {
+		if info, err := os.Stat(p); err == nil && !info.IsDir() {
+			abs, absErr := filepath.Abs(p)
+			if absErr == nil {
+				return abs, true
+			}
+			return p, true
+		}
+	}
+	return "", false
+}
+
 func TestLocalAI(t *testing.T) {
 	RegisterFailHandler(Fail)
 
@@ -24,6 +57,15 @@ func TestLocalAI(t *testing.T) {
 	err = os.Mkdir(modelDir, 0750)
 	Expect(err).ToNot(HaveOccurred())
 
+	backendDir = filepath.Join(tmpdir, "backends")
+	Expect(os.Mkdir(backendDir, 0750)).To(Succeed())
+
+	if p, ok := findMockBackendBinary(); ok {
+		mockBackendPath = p
+		// Make sure it's executable for the path the suite owns.
+		_ = os.Chmod(mockBackendPath, 0755)
+	}
+
 	AfterSuite(func() {
 		err := os.RemoveAll(tmpdir)
 		Expect(err).ToNot(HaveOccurred())
diff --git a/tests/e2e-aio/e2e_test.go b/tests/e2e-aio/e2e_test.go
index cf6573f85..19b310460 100644
--- a/tests/e2e-aio/e2e_test.go
+++ b/tests/e2e-aio/e2e_test.go
@@ -41,6 +41,34 @@ var _ = Describe("E2E test", func() {
 				Expect(len(resp.Choices)).To(Equal(1), fmt.Sprint(resp))
 				Expect(resp.Choices[0].Message.Content).To(Or(ContainSubstring("4"), ContainSubstring("four")), fmt.Sprint(resp.Choices[0].Message.Content))
 			})
+
+			// Smoke: verifies the AIO container streams chat completions end-to-end.
+			// Catches packaging/proxy regressions where the streaming path breaks
+			// even though non-streaming works.
+			It("streams correctly", func() {
+				model := "gpt-4"
+				stream := client.Chat.Completions.NewStreaming(context.TODO(),
+					openai.ChatCompletionNewParams{
+						Model: model,
+						Messages: []openai.ChatCompletionMessageParamUnion{
+							openai.UserMessage("Count to three."),
+						},
+					})
+				defer stream.Close()
+
+				var chunks int
+				var combined string
+				for stream.Next() {
+					chunk := stream.Current()
+					if len(chunk.Choices) > 0 && chunk.Choices[0].Delta.Content != "" {
+						chunks++
+						combined += chunk.Choices[0].Delta.Content
+					}
+				}
+				Expect(stream.Err()).ToNot(HaveOccurred())
+				Expect(chunks).To(BeNumerically(">", 1), "expected multi-chunk stream, got %d", chunks)
+				Expect(combined).ToNot(BeEmpty(), "stream produced no content")
+			})
 		})
 
 		Context("function calls", func() {
diff --git a/tests/e2e-backends/backend_test.go b/tests/e2e-backends/backend_test.go
index 1820fceb5..cdcf1b74f 100644
--- a/tests/e2e-backends/backend_test.go
+++ b/tests/e2e-backends/backend_test.go
@@ -102,6 +102,8 @@ const (
 	capVoiceEmbed    = "voice_embed"
 	capVoiceVerify   = "voice_verify"
 	capVoiceAnalyze  = "voice_analyze"
+	capLogprobs      = "logprobs"
+	capLogitBias     = "logit_bias"
 
 	defaultPrompt             = "The capital of France is"
 	streamPrompt              = "Once upon a time"
@@ -422,6 +424,7 @@ var _ = Describe("Backend container", Ordered, func() {
 
 		var chunks int
 		var combined string
+		var firstChunks []string
 		for {
 			msg, err := stream.Recv()
 			if err == io.EOF {
@@ -431,12 +434,71 @@ var _ = Describe("Backend container", Ordered, func() {
 			if len(msg.GetMessage()) > 0 {
 				chunks++
 				combined += string(msg.GetMessage())
+				if len(firstChunks) < 2 {
+					firstChunks = append(firstChunks, string(msg.GetMessage()))
+				}
 			}
 		}
 		Expect(chunks).To(BeNumerically(">", 0), "no stream chunks received")
+		// Regression guard: a bug in llama-cpp's grpc-server.cpp caused the
+		// role-init array element to get the same ChatDelta stamped, duplicating
+		// the first content token. Applies to any streaming backend.
+		if len(firstChunks) >= 2 {
+			Expect(firstChunks[0]).NotTo(Equal(firstChunks[1]),
+				"first content token was duplicated: %v", firstChunks)
+		}
 		GinkgoWriter.Printf("Stream: %d chunks, combined=%q\n", chunks, combined)
 	})
 
+	// Logprobs: backends that wire OpenAI-compatible logprobs return a
+	// JSON-encoded payload in Reply.logprobs (see backend.proto). The exact
+	// shape is backend-specific; we only assert that the field is populated
+	// when requested. Gated by capLogprobs because not every backend
+	// implements it.
+	It("returns logprobs when requested", func() {
+		if !caps[capLogprobs] {
+			Skip("logprobs capability not enabled")
+		}
+		ctx, cancel := context.WithTimeout(context.Background(), 120*time.Second)
+		defer cancel()
+		res, err := client.Predict(ctx, &pb.PredictOptions{
+			Prompt:      prompt,
+			Tokens:      10,
+			Temperature: 0.1,
+			TopK:        40,
+			TopP:        0.9,
+			Logprobs:    1,
+			TopLogprobs: 1,
+		})
+		Expect(err).NotTo(HaveOccurred())
+		Expect(res.GetMessage()).NotTo(BeEmpty(), "Predict produced empty output")
+		Expect(res.GetLogprobs()).NotTo(BeEmpty(), "Reply.logprobs was empty when requested")
+		GinkgoWriter.Printf("Logprobs: %d bytes\n", len(res.GetLogprobs()))
+	})
+
+	// Logit bias: encoded as a JSON string keyed by token id. We don't
+	// know the model's tokenizer, so we exercise the API path with a
+	// nonsense bias map that any backend should accept and ignore for
+	// unknown ids. The assertion is that the request succeeds — proving
+	// the LogitBias plumbing is wired end-to-end.
+	It("accepts logit_bias when supplied", func() {
+		if !caps[capLogitBias] {
+			Skip("logit_bias capability not enabled")
+		}
+		ctx, cancel := context.WithTimeout(context.Background(), 120*time.Second)
+		defer cancel()
+		res, err := client.Predict(ctx, &pb.PredictOptions{
+			Prompt:      prompt,
+			Tokens:      10,
+			Temperature: 0.1,
+			TopK:        40,
+			TopP:        0.9,
+			LogitBias:   `{"1":-100}`,
+		})
+		Expect(err).NotTo(HaveOccurred())
+		Expect(res.GetMessage()).NotTo(BeEmpty(), "Predict produced empty output with logit_bias")
+	})
+
 	It("computes embeddings via Embedding", func() {
 		if !caps[capEmbeddings] {
 			Skip("embeddings capability not enabled")
diff --git a/tests/models_fixtures/completion.tmpl b/tests/models_fixtures/completion.tmpl
deleted file mode 100644
index 9867cfcd3..000000000
--- a/tests/models_fixtures/completion.tmpl
+++ /dev/null
@@ -1 +0,0 @@
-{{.Input}}
\ No newline at end of file
diff --git a/tests/models_fixtures/config.yaml b/tests/models_fixtures/config.yaml
deleted file mode 100644
index f61c2a7c0..000000000
--- a/tests/models_fixtures/config.yaml
+++ /dev/null
@@ -1,32 +0,0 @@
-- name: list1
-  parameters:
-    model: testmodel.ggml
-    top_p: 80
-    top_k: 0.9
-    temperature: 0.1
-  context_size: 200
-  stopwords:
-  - "HUMAN:"
-  - "### Response:"
-  roles:
-    user: "HUMAN:"
-    system: "GPT:"
-  template:
-    completion: completion
-    chat: ggml-gpt4all-j
-- name: list2
-  parameters:
-    top_p: 80
-    top_k: 0.9
-    temperature: 0.1
-    model: testmodel.ggml
-  context_size: 200
-  stopwords:
-  - "HUMAN:"
-  - "### Response:"
-  roles:
-    user: "HUMAN:"
-    system: "GPT:"
-  template:
-    completion: completion
-    chat: ggml-gpt4all-j
\ No newline at end of file
diff --git a/tests/models_fixtures/embeddings.yaml b/tests/models_fixtures/embeddings.yaml
deleted file mode 100644
index 76c4a56ad..000000000
--- a/tests/models_fixtures/embeddings.yaml
+++ /dev/null
@@ -1,4 +0,0 @@
-name: text-embedding-ada-002
-embeddings: true
-parameters:
-  model: huggingface://hugging-quants/Llama-3.2-1B-Instruct-Q4_K_M-GGUF/llama-3.2-1b-instruct-q4_k_m.gguf
\ No newline at end of file
diff --git a/tests/models_fixtures/ggml-gpt4all-j.tmpl b/tests/models_fixtures/ggml-gpt4all-j.tmpl
deleted file mode 100644
index f76b080ab..000000000
--- a/tests/models_fixtures/ggml-gpt4all-j.tmpl
+++ /dev/null
@@ -1,4 +0,0 @@
-The prompt below is a question to answer, a task to complete, or a conversation to respond to; decide which and write an appropriate response.
-### Prompt:
-{{.Input}}
-### Response:
diff --git a/tests/models_fixtures/gpt4.yaml b/tests/models_fixtures/gpt4.yaml
deleted file mode 100644
index 43e77586d..000000000
--- a/tests/models_fixtures/gpt4.yaml
+++ /dev/null
@@ -1,16 +0,0 @@
-name: gpt4all
-parameters:
-  model: testmodel.ggml
-  top_p: 80
-  top_k: 0.9
-  temperature: 0.1
-context_size: 200
-stopwords:
-- "HUMAN:"
-- "### Response:"
-roles:
-  user: "HUMAN:"
-  system: "GPT:"
-template:
-  completion: completion
-  chat: ggml-gpt4all-j
\ No newline at end of file
diff --git a/tests/models_fixtures/gpt4_2.yaml b/tests/models_fixtures/gpt4_2.yaml
deleted file mode 100644
index 8a2111530..000000000
--- a/tests/models_fixtures/gpt4_2.yaml
+++ /dev/null
@@ -1,16 +0,0 @@
-name: gpt4all-2
-parameters:
-  model: testmodel.ggml
-  top_p: 80
-  top_k: 0.9
-  temperature: 0.1
-context_size: 200
-stopwords:
-- "HUMAN:"
-- "### Response:"
-roles:
-  user: "HUMAN:"
-  system: "GPT:"
-template:
-  completion: completion
-  chat: ggml-gpt4all-j
\ No newline at end of file
diff --git a/tests/models_fixtures/grpc.yaml b/tests/models_fixtures/grpc.yaml
deleted file mode 100644
index 8c5199205..000000000
--- a/tests/models_fixtures/grpc.yaml
+++ /dev/null
@@ -1,5 +0,0 @@
-name: code-search-ada-code-001
-backend: sentencetransformers
-embeddings: true
-parameters:
-  model: all-MiniLM-L6-v2
\ No newline at end of file
diff --git a/tests/models_fixtures/rwkv.yaml b/tests/models_fixtures/rwkv.yaml
deleted file mode 100644
index f66cfe211..000000000
--- a/tests/models_fixtures/rwkv.yaml
+++ /dev/null
@@ -1,24 +0,0 @@
-name: rwkv_test
-parameters:
-  model: huggingface://bartowski/rwkv-6-world-7b-GGUF/rwkv-6-world-7b-Q4_K_M.gguf
-  top_k: 80
-  temperature: 0.9
-  max_tokens: 4098
-  top_p: 0.8
-context_size: 4098
-
-roles:
-  user: "User: "
-  system: "System: "
-  assistant: "Assistant: "
-
-stopwords:
-- 'Assistant:'
-- '<s>'
-
-template:
-  chat: |
-    {{.Input}}
-    Assistant: 
-  completion: |
-    {{.Input}}
\ No newline at end of file
diff --git a/tests/models_fixtures/whisper.yaml b/tests/models_fixtures/whisper.yaml
deleted file mode 100644
index 4ea99efce..000000000
--- a/tests/models_fixtures/whisper.yaml
+++ /dev/null
@@ -1,4 +0,0 @@
-name: whisper-1
-backend: whisper
-parameters:
-  model: whisper-en
\ No newline at end of file