phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

feat: support ClientTool output metadata (#1426)

Browse source 
# Summary:
Client side change in
https://github.com/meta-llama/llama-stack-client-python/pull/180
Changes the resume_turn API to accept `ToolResponse` instead of
`ToolResponseMessage`:
1. `ToolResponse` contains `metadata`
2. `ToolResponseMessage` is a concept for model inputs. Here we are just
submitting the outputs of tool execution.

# Test Plan:
Ran integration tests with newly added test using client tool with
metadata

LLAMA_STACK_CONFIG=fireworks pytest -s -v
tests/integration/agents/test_agents.py --safety-shield
meta-llama/Llama-Guard-3-8B --record-responses
This commit is contained in:
ehhuang 2025-03-05 14:30:27 -08:00 • committed by GitHub
parent ac717f38dc
commit 6cf79437b3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 3984 additions and 2172 deletions
Download patch file Download diff file Expand all files Collapse all files

20
docs/_static/llama-stack-spec.html vendored
View file

@ -9321,11 +9321,21 @@
"type": "object",
"properties": {
"tool_responses": {
"type": "array",
"items": {
"$ref": "#/components/schemas/ToolResponseMessage"
},
"description": "The tool call responses to resume the turn with."
"oneOf": [
{
"type": "array",
"items": {
"$ref": "#/components/schemas/ToolResponse"
}
},
{
"type": "array",
"items": {
"$ref": "#/components/schemas/ToolResponseMessage"
}
}
],
"description": "The tool call responses to resume the turn with. NOTE: ToolResponseMessage will be deprecated. Use ToolResponse."
},
"stream": {
"type": "boolean",