refactor(tests): delete inference, safety and agents tests from providers/tests/ (#1393)

Continues the refactor of tests. 

Tests from `providers/tests` should be considered deprecated. For this
PR, I deleted most of the tests in
 - inference
 - safety
 - agents
since much more comprehensive tests exist in
`tests/integration/{inference,safety,agents}` already.

I moved `test_persistence.py` from agents, but disabled all the tests
since that test needs to be properly migrated.

## Test Plan

```
LLAMA_STACK_CONFIG=fireworks pytest -s -v agents --vision-inference-model=''
/Users/ashwin/homebrew/Caskroom/miniconda/base/envs/toolchain/lib/python3.10/site-packages/pytest_asyncio/plugin.py:208: PytestDeprecationWarning: The configuration option "asyncio_default_fixture_loop_scope" is unset.
The event loop scope for asynchronous fixtures will default to the fixture caching scope. Future versions of pytest-asyncio will default the loop scope for asynchronous fixtures to function scope. Set the default fixture loop scope explicitly in order to avoid unexpected behavior in the future. Valid fixture loop scopes are: "function", "class", "module", "package", "session"

  warnings.warn(PytestDeprecationWarning(_DEFAULT_FIXTURE_LOOP_SCOPE_UNSET))
======================================================================================================= test session starts ========================================================================================================
platform darwin -- Python 3.10.16, pytest-8.3.3, pluggy-1.5.0 -- /Users/ashwin/homebrew/Caskroom/miniconda/base/envs/toolchain/bin/python
cachedir: .pytest_cache
metadata: {'Python': '3.10.16', 'Platform': 'macOS-15.3.1-arm64-arm-64bit', 'Packages': {'pytest': '8.3.3', 'pluggy': '1.5.0'}, 'Plugins': {'asyncio': '0.24.0', 'html': '4.1.1', 'metadata': '3.1.1', 'anyio': '4.8.0', 'nbval': '0.11.0'}}
rootdir: /Users/ashwin/local/llama-stack
configfile: pyproject.toml
plugins: asyncio-0.24.0, html-4.1.1, metadata-3.1.1, anyio-4.8.0, nbval-0.11.0
asyncio: mode=strict, default_loop_scope=None
collected 15 items

agents/test_agents.py::test_agent_simple[txt=8B] PASSED
agents/test_agents.py::test_tool_config[txt=8B] PASSED
agents/test_agents.py::test_builtin_tool_web_search[txt=8B] PASSED
agents/test_agents.py::test_builtin_tool_code_execution[txt=8B] PASSED
agents/test_agents.py::test_code_interpreter_for_attachments[txt=8B] PASSED
agents/test_agents.py::test_custom_tool[txt=8B] PASSED
agents/test_agents.py::test_custom_tool_infinite_loop[txt=8B] PASSED
agents/test_agents.py::test_tool_choice[txt=8B] PASSED
agents/test_agents.py::test_rag_agent[txt=8B-builtin::rag/knowledge_search] PASSED
agents/test_agents.py::test_rag_agent[txt=8B-builtin::rag] PASSED
agents/test_agents.py::test_rag_agent_with_attachments[txt=8B] PASSED
agents/test_agents.py::test_rag_and_code_agent[txt=8B] PASSED
agents/test_agents.py::test_create_turn_response[txt=8B] PASSED
agents/test_persistence.py::test_delete_agents_and_sessions SKIPPED (This test needs to be migrated to api / client-sdk world)
agents/test_persistence.py::test_get_agent_turns_and_steps SKIPPED (This test needs to be migrated to api / client-sdk world)

```

llama_stack/providers/tests/safety/conftest.py

@@ -1,96 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the terms described in the LICENSE file in
-# the root directory of this source tree.
-
-import pytest
-
-from ..conftest import get_provider_fixture_overrides
-from ..inference.fixtures import INFERENCE_FIXTURES
-from .fixtures import SAFETY_FIXTURES
-
-DEFAULT_PROVIDER_COMBINATIONS = [
-    pytest.param(
-        {
-            "inference": "meta_reference",
-            "safety": "llama_guard",
-        },
-        id="meta_reference",
-        marks=pytest.mark.meta_reference,
-    ),
-    pytest.param(
-        {
-            "inference": "ollama",
-            "safety": "llama_guard",
-        },
-        id="ollama",
-        marks=pytest.mark.ollama,
-    ),
-    pytest.param(
-        {
-            "inference": "together",
-            "safety": "llama_guard",
-        },
-        id="together",
-        marks=pytest.mark.together,
-    ),
-    pytest.param(
-        {
-            "inference": "bedrock",
-            "safety": "bedrock",
-        },
-        id="bedrock",
-        marks=pytest.mark.bedrock,
-    ),
-    pytest.param(
-        {
-            "inference": "remote",
-            "safety": "remote",
-        },
-        id="remote",
-        marks=pytest.mark.remote,
-    ),
-]
-
-
-def pytest_configure(config):
-    for mark in ["meta_reference", "ollama", "together", "remote", "bedrock"]:
-        config.addinivalue_line(
-            "markers",
-            f"{mark}: marks tests as {mark} specific",
-        )
-
-
-SAFETY_SHIELD_PARAMS = [
-    pytest.param("meta-llama/Llama-Guard-3-1B", marks=pytest.mark.guard_1b, id="guard_1b"),
-]
-
-
-def pytest_generate_tests(metafunc):
-    # We use this method to make sure we have built-in simple combos for safety tests
-    # But a user can also pass in a custom combination via the CLI by doing
-    #  `--providers inference=together,safety=meta_reference`
-
-    if "safety_shield" in metafunc.fixturenames:
-        shield_id = metafunc.config.getoption("--safety-shield")
-        if shield_id:
-            params = [pytest.param(shield_id, id="")]
-        else:
-            params = SAFETY_SHIELD_PARAMS
-        for fixture in ["inference_model", "safety_shield"]:
-            metafunc.parametrize(
-                fixture,
-                params,
-                indirect=True,
-            )
-
-    if "safety_stack" in metafunc.fixturenames:
-        available_fixtures = {
-            "inference": INFERENCE_FIXTURES,
-            "safety": SAFETY_FIXTURES,
-        }
-        combinations = (
-            get_provider_fixture_overrides(metafunc.config, available_fixtures) or DEFAULT_PROVIDER_COMBINATIONS
-        )
-        metafunc.parametrize("safety_stack", combinations, indirect=True)