build: add missing dev dependencies for unit tests (#1004)

# What does this PR do?
Added necessary dependencies to ensure successful execution of unit
tests. Without these, the following command would fail due to missing
imports:

```
uv run pytest -v -k "ollama" \
     --inference-model=llama3.2:3b-instruct-fp16
     llama_stack/providers/tests/inference/test_model_registration.py
```

Signed-off-by: Sébastien Han <seb@redhat.com>

[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])

## Test Plan
Run:

```
ollama run llama3.2:3b-instruct-fp16 --keepalive 2m &
uv run pytest -v -k "ollama" --inference-model=llama3.2:3b-instruct-fp16 llama_stack/providers/tests/inference/test_model_registration.py

```

You can observe that some tests pass while others fail, but the test
runs successfully.

[//]: # (## Documentation)
[//]: # (- [ ] Added a Changelog entry if the change is significant)

Signed-off-by: Sébastien Han <seb@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>

llama_stack/providers/tests/README.md

@@ -12,6 +12,20 @@ We use `pytest` and all of its dynamism to enable the features needed. Specifica
 
 - We use `pytest_collection_modifyitems` to filter tests based on the test config (if specified).
 
+## Pre-requisites
+
+Your development environment should have been configured as per the instructions in the
+[CONTRIBUTING.md](../../../CONTRIBUTING.md) file. In particular, make sure to install the test extra
+dependencies. Below is the full configuration:
+
+
+```bash
+$ cd llama-stack
+$ uv sync --extra dev --extra test
+$ uv pip install -e .
+$ source .venv/bin/activate
+```
+
 ## Common options
 
 All tests support a `--providers` option which can be a string of the form `api1=provider_fixture1,api2=provider_fixture2`. So, when testing safety (which need inference and safety APIs) you can use `--providers inference=together,safety=meta_reference` to use these fixtures in concert.
@@ -50,6 +64,9 @@ pytest -s -v llama_stack/providers/tests/inference/test_text_inference.py \
   --env FIREWORKS_API_KEY=<...>
 ```
 
+> [!TIP]
+> If you’re using `uv`, you can isolate test executions by prefixing all commands with `uv run pytest...`.
+
 ## Agents
 
 The Agents API composes three other APIs underneath:

pyproject.toml

@@ -41,6 +41,7 @@ dependencies = [
 dev = [
     "pytest",
     "pytest-asyncio",
+    "pytest-html",
     "nbval",            # For notebook testing
     "black",
     "ruff",
@@ -49,7 +50,19 @@ dev = [
     "pre-commit",
     "uvicorn",
     "fastapi",
-    "ruamel.yaml",      # needed for openai generator
+    "ruamel.yaml",      # needed for openapi generator
+]
+test = [
+    "openai",
+    "aiosqlite",
+    "ollama",
+    "torch>=2.6.0",
+    "fairscale>=0.4.13",
+    "torchvision>=0.21.0",
+    "lm-format-enforcer>=0.10.9",
+    "groq",
+    "opentelemetry-sdk",
+    "opentelemetry-exporter-otlp-proto-http",
 ]
 docs = [
     "sphinx-autobuild",
@@ -79,6 +92,10 @@ name = "pytorch-cpu"
 url = "https://download.pytorch.org/whl/cpu"
 explicit = true
 
+[tool.uv.sources]
+torch = [{ index = "pytorch-cpu" }]
+torchvision = [{ index = "pytorch-cpu" }]
+
 [tool.ruff]
 line-length = 120
 exclude = [

requirements.txt

@@ -12,7 +12,7 @@ distro==1.9.0
 exceptiongroup==1.2.2 ; python_full_version < '3.11'
 filelock==3.17.0
 fire==0.7.0
-fsspec==2024.12.0
+fsspec==2025.2.0
 h11==0.14.0
 httpcore==1.0.7
 httpx==0.28.1
@@ -23,11 +23,11 @@ jsonschema==4.23.0
 jsonschema-specifications==2024.10.1
 llama-models==0.1.3
 llama-stack-client==0.1.3
-lxml==5.3.0
+lxml==5.3.1
 markdown-it-py==3.0.0
 markupsafe==3.0.2
 mdurl==0.1.2
-numpy==2.2.2
+numpy==2.2.3
 packaging==24.2
 pandas==2.2.3
 pillow==11.1.0
@@ -50,7 +50,7 @@ setuptools==75.8.0
 six==1.17.0
 sniffio==1.3.1
 termcolor==2.5.0
-tiktoken==0.8.0
+tiktoken==0.9.0
 tqdm==4.67.1
 typing-extensions==4.12.2
 tzdata==2025.1