Commit graph

5 commits

Author SHA1 Message Date
Eric Huang
7027b537e0 feat: RFC: tools API rework
# What does this PR do?
This PR proposes updates to the tools API in Inference and Agent.

Goals:
1. Agent's tool specification should be consistent with Inference's tool spec, but with add-ons.
2. Formal types should be defined for built in tools. Currently Agent tools args are untyped, e.g. how does one know that `builtin::rag_tool` takes a `vector_db_ids` param or even how to know 'builtin::rag_tool' is even available (in code, outside of docs)?

Inference:
1. BuiltinTool is to be removed and replaced by a formal `type` parameter.
2. 'brave_search' is replaced by 'web_search' to be more generic. It will still be translated back to brave_search when the prompt is constructed to be consistent with model training.
3. I'm not sure what `photogen` is. Maybe it can be removed?

Agent:
1. Uses the same format as in Inference for builtin tools.
2. New tools types are added, i.e. knowledge_sesarch (currently rag_tool), and MCP tool.
3. Toolgroup as a concept will be removed since it's really only used for MCP.
4. Instead MCPTool is its own type and available tools provided by the server will be expanded by default. Users can specify a subset of tool names if desired.

Example snippet:
```

agent = Agent(
    client,
    model=model_id,
    instructions="You are a helpful assistant. Use the tools you have access to for providing relevant answers.",
    tools=[
        KnowledgeSearchTool(vector_store_id="1234"),
        KnowledgeSearchTool(vector_store_id="5678", name="paper_search", description="Search research papers"),
        KnowledgeSearchTool(vector_store_id="1357", name="wiki_search", description="Search wiki pages"),
        # no need to register toolgroup, just pass in the server uri
        # all available tools will be used
        MCPTool(server_uri="http://localhost:8000/sse"),
        # can specify a subset of available tools
        MCPTool(server_uri="http://localhost:8000/sse", tool_names=["list_directory"]),
        MCPTool(server_uri="http://localhost:8000/sse", tool_names=["list_directory"]),
        # custom tool
        my_custom_tool,
    ]
)
```

## Test Plan
# What does this PR do?


## Test Plan
# What does this PR do?


## Test Plan
2025-03-26 11:14:41 -07:00
ehhuang
af8b4484a3
fix: update default tool call system prompt (#1712)
# What does this PR do?
closes #1584 

This should be a rather innocuous change. 

## Test Plan

Verify that there's no more tool call parsing error for example in issue
<img width="1216" alt="image"
src="https://github.com/user-attachments/assets/a5a6f4e8-2093-4ca2-bc06-794b707a0429"
/>

LLAMA_STACK_CONFIG=fireworks pytest -s -v
tests/integration/agents/test_agents.py --safety-shield
meta-llama/Llama-Guard-3-8B --text-model
meta-llama/Llama-3.1-8B-Instruct
2025-03-19 22:49:24 -07:00
Hardik Shah
65ca85ba6b
fix: Updating ToolCall.arguments to allow for json strings that can be decoded on client side (#1685)
### What does this PR do?

Currently, `ToolCall.arguments` is a `Dict[str, RecursiveType]`.
However, on the client SDK side -- the `RecursiveType` gets deserialized
into a number ( both int and float get collapsed ) and hence when params
are `int` they get converted to float which might break client side
tools that might be doing type checking.

Closes: https://github.com/meta-llama/llama-stack/issues/1683

### Test Plan
Stainless changes --
https://github.com/meta-llama/llama-stack-client-python/pull/204
```
pytest -s -v --stack-config=fireworks tests/integration/agents/test_agents.py  --text-model meta-llama/Llama-3.1-8B-Instruct
```
2025-03-19 10:36:19 -07:00
Ihar Hrachyshka
a64021bb47
fix: Disable async loop warning messages during test run (#1526)
# What does this PR do?

The test class by default enables debug mode, which produces some
unexpected warnings like:

```
tests/unit/models/test_prompt_adapter.py::PrepareMessagesTests::test_completion_message_encoding
WARNING  2025-03-10 20:41:48,577 asyncio:1904 uncategorized: Executing <Task pending name='Task-1'
  coro=<IsolatedAsyncioTestCase._asyncioLoopRunner() running at
  /home/ec2-user/.local/share/uv/python/cpython-3.10.16-linux-x86_64-gnu/lib/python3.10/unittest/async_case.py:95
  > wait_for=<Future pending cb=[Task.task_wakeup()] created at
  /home/ec2-user/.local/share/uv/python/cpython-3.10.16-linux-x86_64-gnu/lib/python3.10/asyncio/base_events.py:42
  9> created at
  /home/ec2-user/.local/share/uv/python/cpython-3.10.16-linux-x86_64-gnu/lib/python3.10/unittest/async_case.py:11
  7> took 0.231 seconds
PASSED
```

I suggest we disable these since they are not very useful and can
confuse other developers.

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

## Test Plan

Run tests. The warnings are no longer seen.

[//]: # (## Documentation)

Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
2025-03-10 15:29:08 -07:00
Ashwin Bharambe
4ca58eb987 refactor: tests/unittests -> tests/unit; tests/api -> tests/integration 2025-03-04 09:57:00 -08:00