phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-28 02:53:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
llama-stack-mirror/llama_stack
History
Xi Yan 0fe071764f
feat(1/n): api: unify agents for handling server & client tools (#1178) 
# Problem

Our current Agent framework has discrepancies in definition on how we
handle server side and client side tools.

1. Server Tools: a single Turn is returned including `ToolExecutionStep`
in agenst
2. Client Tools: `create_agent_turn` is called in loop with client agent
lib yielding the agent chunk

ad6ffc63df/src/llama_stack_client/lib/agents/agent.py (L186-L211)

This makes it inconsistent to work with server & client tools. It also
complicates the logs to telemetry to get information about agents turn /
history for observability.

#### Principle
The same `turn_id` should be used to represent the steps required to
complete a user message including client tools.

## Solution

1. `AgentTurnResponseEventType.turn_awaiting_input` status to indicate
that the current turn is not completed, and awaiting tool input
2. `continue_agent_turn` endpoint to update agent turn with client's
tool response.


# What does this PR do?
- Skeleton API as example

## Test Plan
[Describe the tests you ran to verify your changes with result
summaries. *Provide clear instructions so the plan can be easily
re-executed.*]

- Just API update, no functionality change
```
llama stack run + client-sdk test
```

<img width="842" alt="image"
src="https://github.com/user-attachments/assets/7ac56b5f-f424-4632-9476-7e0f57555bc3"
/>


[//]: # (## Documentation)
2025-02-21 11:48:27 -08:00
..
apis feat(1/n): api: unify agents for handling server & client tools (#1178) 2025-02-21 11:48:27 -08:00
cli chore: move embedding deps to RAG tool where they are needed (#1210) 2025-02-21 11:33:41 -08:00
distribution fix: Updating images so that they are able to run without root access (#1208) 2025-02-21 11:32:56 -05:00
models/llama chore: move all Llama Stack types from llama-models to llama-stack (#1098) 2025-02-14 09:10:59 -08:00
providers feat(1/n): api: unify agents for handling server & client tools (#1178) 2025-02-21 11:48:27 -08:00
scripts precommit again 2025-02-19 22:40:45 -08:00
strong_typing Ensure that deprecations for fields follow through to OpenAPI 2025-02-19 13:54:04 -08:00
templates chore: move embedding deps to RAG tool where they are needed (#1210) 2025-02-21 11:33:41 -08:00
__init__.py export LibraryClient 2024-12-13 12:08:00 -08:00
schema_utils.py feat: adding endpoints for files and uploads (#1070) 2025-02-20 13:09:00 -08:00