agents to use tools api (#673)

# What does this PR do?

PR #639 introduced the notion of Tools API and ability to invoke tools
through API just as any resource. This PR changes the Agents to start
using the Tools API to invoke tools. Major changes include:
1) Ability to specify tool groups with AgentConfig
2) Agent gets the corresponding tool definitions for the specified tools
and pass along to the model
3) Attachements are now named as Documents and their behavior is mostly
unchanged from user perspective
4) You can specify args that can be injected to a tool call through
Agent config. This is especially useful in case of memory tool, where
you want the tool to operate on a specific memory bank.
5) You can also register tool groups with args, which lets the agent
inject these as well into the tool call.
6) All tests have been migrated to use new tools API and fixtures
including client SDK tests
7) Telemetry just works with tools API because of our trace protocol
decorator


## Test Plan
```
pytest -s -v -k fireworks llama_stack/providers/tests/agents/test_agents.py  \
   --safety-shield=meta-llama/Llama-Guard-3-8B \
   --inference-model=meta-llama/Llama-3.1-8B-Instruct

pytest -s -v -k together  llama_stack/providers/tests/tools/test_tools.py \
   --safety-shield=meta-llama/Llama-Guard-3-8B \
   --inference-model=meta-llama/Llama-3.1-8B-Instruct

LLAMA_STACK_CONFIG="/Users/dineshyv/.llama/distributions/llamastack-together/together-run.yaml" pytest -v tests/client-sdk/agents/test_agents.py
```
run.yaml:
https://gist.github.com/dineshyv/0365845ad325e1c2cab755788ccc5994

Notebook:
https://colab.research.google.com/drive/1ck7hXQxRl6UvT-ijNRZ-gMZxH1G3cN2d?usp=sharing

llama_stack/providers/remote/tool_runtime/wolfram_alpha/__init__.py

@@ -0,0 +1,22 @@
+# 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.
+
+from pydantic import BaseModel
+
+from .config import WolframAlphaToolConfig
+from .wolfram_alpha import WolframAlphaToolRuntimeImpl
+
+__all__ = ["WolframAlphaToolConfig", "WolframAlphaToolRuntimeImpl"]
+
+
+class WolframAlphaToolProviderDataValidator(BaseModel):
+    api_key: str
+
+
+async def get_adapter_impl(config: WolframAlphaToolConfig, _deps):
+    impl = WolframAlphaToolRuntimeImpl(config)
+    await impl.initialize()
+    return impl

llama_stack/providers/remote/tool_runtime/wolfram_alpha/config.py

@@ -0,0 +1,15 @@
+# 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.
+
+from typing import Optional
+
+from pydantic import BaseModel
+
+
+class WolframAlphaToolConfig(BaseModel):
+    """Configuration for WolframAlpha Tool Runtime"""
+
+    api_key: Optional[str] = None

llama_stack/providers/remote/tool_runtime/wolfram_alpha/wolfram_alpha.py

@@ -0,0 +1,146 @@
+# 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 json
+from typing import Any, Dict, List, Optional
+
+import requests
+
+from llama_stack.apis.common.content_types import URL
+from llama_stack.apis.tools import (
+    Tool,
+    ToolDef,
+    ToolInvocationResult,
+    ToolParameter,
+    ToolRuntime,
+)
+from llama_stack.distribution.request_headers import NeedsRequestProviderData
+from llama_stack.providers.datatypes import ToolsProtocolPrivate
+
+from .config import WolframAlphaToolConfig
+
+
+class WolframAlphaToolRuntimeImpl(
+    ToolsProtocolPrivate, ToolRuntime, NeedsRequestProviderData
+):
+    def __init__(self, config: WolframAlphaToolConfig):
+        self.config = config
+        self.url = "https://api.wolframalpha.com/v2/query"
+
+    async def initialize(self):
+        pass
+
+    async def register_tool(self, tool: Tool):
+        pass
+
+    async def unregister_tool(self, tool_id: str) -> None:
+        return
+
+    def _get_api_key(self) -> str:
+        if self.config.api_key:
+            return self.config.api_key
+
+        provider_data = self.get_request_provider_data()
+        if provider_data is None or not provider_data.api_key:
+            raise ValueError(
+                'Pass WolframAlpha API Key in the header X-LlamaStack-ProviderData as { "api_key": <your api key>}'
+            )
+        return provider_data.api_key
+
+    async def list_runtime_tools(
+        self, tool_group_id: Optional[str] = None, mcp_endpoint: Optional[URL] = None
+    ) -> List[ToolDef]:
+        return [
+            ToolDef(
+                name="wolfram_alpha",
+                description="Query WolframAlpha for computational knowledge",
+                parameters=[
+                    ToolParameter(
+                        name="query",
+                        description="The query to compute",
+                        parameter_type="string",
+                    )
+                ],
+            )
+        ]
+
+    async def invoke_tool(
+        self, tool_name: str, args: Dict[str, Any]
+    ) -> ToolInvocationResult:
+        api_key = self._get_api_key()
+        params = {
+            "input": args["query"],
+            "appid": api_key,
+            "format": "plaintext",
+            "output": "json",
+        }
+        response = requests.get(
+            self.url,
+            params=params,
+        )
+
+        return ToolInvocationResult(
+            content=json.dumps(self._clean_wolfram_alpha_response(response.json()))
+        )
+
+    def _clean_wolfram_alpha_response(self, wa_response):
+        remove = {
+            "queryresult": [
+                "datatypes",
+                "error",
+                "timedout",
+                "timedoutpods",
+                "numpods",
+                "timing",
+                "parsetiming",
+                "parsetimedout",
+                "recalculate",
+                "id",
+                "host",
+                "server",
+                "related",
+                "version",
+                {
+                    "pods": [
+                        "scanner",
+                        "id",
+                        "error",
+                        "expressiontypes",
+                        "states",
+                        "infos",
+                        "position",
+                        "numsubpods",
+                    ]
+                },
+                "assumptions",
+            ],
+        }
+        for main_key in remove:
+            for key_to_remove in remove[main_key]:
+                try:
+                    if key_to_remove == "assumptions":
+                        if "assumptions" in wa_response[main_key]:
+                            del wa_response[main_key][key_to_remove]
+                    if isinstance(key_to_remove, dict):
+                        for sub_key in key_to_remove:
+                            if sub_key == "pods":
+                                for i in range(len(wa_response[main_key][sub_key])):
+                                    if (
+                                        wa_response[main_key][sub_key][i]["title"]
+                                        == "Result"
+                                    ):
+                                        del wa_response[main_key][sub_key][i + 1 :]
+                                        break
+                            sub_items = wa_response[main_key][sub_key]
+                            for i in range(len(sub_items)):
+                                for sub_key_to_remove in key_to_remove[sub_key]:
+                                    if sub_key_to_remove in sub_items[i]:
+                                        del sub_items[i][sub_key_to_remove]
+                    elif key_to_remove in wa_response[main_key]:
+                        del wa_response[main_key][key_to_remove]
+                except KeyError:
+                    pass
+        return wa_response