# What does this PR do?
This change adds a compact type to include metrics in response as
opposed to the full MetricEvent which is relevant for internal logging
purposes.
## Test Plan
```
LLAMA_STACK_CONFIG=~/.llama/distributions/fireworks/fireworks-run.yaml pytest -s -v agents/test_agents.py --safety-shield meta-llama/Llama-Guard-3-8B --text-model meta-llama/Llama-3.1-8B-Instruct
llama stack run ~/.llama/distributions/fireworks/fireworks-run.yaml
curl --request POST \
--url http://localhost:8321/v1/inference/chat-completion \
--header 'content-type: application/json' \
--data '{
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"messages": [
{
"role": "user",
"content": {
"type": "text",
"text": "where do humans live"
}
}
],
"stream": false
}'
{
"metrics": [
{
"metric": "prompt_tokens",
"value": 10,
"unit": null
},
{
"metric": "completion_tokens",
"value": 522,
"unit": null
},
{
"metric": "total_tokens",
"value": 532,
"unit": null
}
],
"completion_message": {
"role": "assistant",
"content": "Humans live in various parts of the world...............",
"stop_reason": "out_of_tokens",
"tool_calls": []
},
"logprobs": null
}
```
# What does this PR do?
This PR adds back the changes in #1300 which were reverted in #1476 .
It also adds logic to preserve context variables across asyncio
boundary. this is needed with the library client since the async
generator logic yields control to code outside the event loop, and on
resuming, does not have the same context as before and this requires
preserving the context vars.
address #1477
## Test Plan
```
curl --request POST \
--url http://localhost:8321/v1/inference/chat-completion \
--header 'content-type: application/json' \
--data '{
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"messages": [
{
"role": "user",
"content": {
"type": "text",
"text": "where do humans live"
}
}
],
"stream": false
}' | jq .
{
"metrics": [
{
"trace_id": "kCZwO3tyQC-FuAGb",
"span_id": "bsP_5a5O",
"timestamp": "2025-03-11T16:47:38.549084Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "prompt_tokens",
"value": 10,
"unit": "tokens"
},
{
"trace_id": "kCZwO3tyQC-FuAGb",
"span_id": "bsP_5a5O",
"timestamp": "2025-03-11T16:47:38.549449Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "completion_tokens",
"value": 369,
"unit": "tokens"
},
{
"trace_id": "kCZwO3tyQC-FuAGb",
"span_id": "bsP_5a5O",
"timestamp": "2025-03-11T16:47:38.549457Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "total_tokens",
"value": 379,
"unit": "tokens"
}
],
"completion_message": {
"role": "assistant",
"content": "Humans live on the planet Earth, specifically on its landmasses and in its oceans. Here's a breakdown of where humans live:\n\n1. **Continents:** Humans inhabit all seven continents:\n\t* Africa\n\t* Antarctica ( temporary residents, mostly scientists and researchers)\n\t* Asia\n\t* Australia\n\t* Europe\n\t* North America\n\t* South America\n2. **Countries:** There are 196 countries recognized by the United Nations, and humans live in almost all of them.\n3. **Cities and towns:** Many humans live in urban areas, such as cities and towns, which are often located near coastlines, rivers, or other bodies of water.\n4. **Rural areas:** Some humans live in rural areas, such as villages, farms, and countryside.\n5. **Islands:** Humans inhabit many islands around the world, including those in the Pacific, Indian, and Atlantic Oceans.\n6. **Mountains and highlands:** Humans live in mountainous regions, such as the Himalayas, the Andes, and the Rocky Mountains.\n7. **Deserts:** Some humans live in desert regions, such as the Sahara, the Mojave, and the Atacama.\n8. **Coastal areas:** Many humans live in coastal areas, such as beaches, ports, and coastal cities.\n9. **Underwater habitats:** A few humans live in underwater habitats, such as research stations and submarines.\n10. **Space:** A small number of humans have lived in space, including astronauts on the International Space Station and those who have visited the Moon.\n\nOverall, humans can be found living in almost every environment on Earth, from the frozen tundra to the hottest deserts, and from the highest mountains to the deepest oceans.",
"stop_reason": "end_of_turn",
"tool_calls": []
},
"logprobs": null
}
```
Orignal repro no longer showing any error:
```
LLAMA_STACK_DISABLE_VERSION_CHECK=true llama stack run ~/.llama/distributions/fireworks/fireworks-run.yaml
python -m examples.agents.e2e_loop_with_client_tools localhost 8321
```
client logs:
https://gist.github.com/dineshyv/047c7e87b18a5792aa660e311ea53166
server logs:
https://gist.github.com/dineshyv/97a2174099619e9916c7c490be26e559
# What does this PR do?
Add support for listing agents, describing an agent, and retrieving
session IDs for a given agent. This is only the API definition, the
implementations will come separately.
Closes: https://github.com/meta-llama/llama-stack/issues/1294
Signed-off-by: Sébastien Han <seb@redhat.com>
# What does this PR do?
The commit addresses the Ruff warning B008 by refactoring the code to
avoid calling SamplingParams() directly in function argument defaults.
Instead, it either uses Field(default_factory=SamplingParams) for
Pydantic models or sets the default to None and instantiates
SamplingParams inside the function body when the argument is None.
Signed-off-by: Sébastien Han <seb@redhat.com>
# 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
# What does this PR do?
Inference router computes the token usage related metrics for all
providers and returns the metrics as part of response and also logs to
telemetry.
## Test Plan
LLAMA_STACK_DISABLE_VERSION_CHECK=true llama stack run
~/.llama/distributions/fireworks/fireworks-run.yaml
```
curl --request POST \
--url http://localhost:8321/v1/inference/chat-completion \
--header 'content-type: application/json' \
--data '{
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"messages": [
{
"role": "user",
"content": {
"type": "text",
"text": "where do humans live"
}
}
],
"stream": false
}' | jq .
{
"metrics": [
{
"trace_id": "yjv1tf0jS1evOyPm",
"span_id": "WqYKvg0_",
"timestamp": "2025-02-27T18:55:10.770903Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "prompt_tokens",
"value": 10,
"unit": "tokens"
},
{
"trace_id": "yjv1tf0jS1evOyPm",
"span_id": "WqYKvg0_",
"timestamp": "2025-02-27T18:55:10.770916Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "completion_tokens",
"value": 411,
"unit": "tokens"
},
{
"trace_id": "yjv1tf0jS1evOyPm",
"span_id": "WqYKvg0_",
"timestamp": "2025-02-27T18:55:10.770919Z",
"attributes": {
"model_id": "meta-llama/Llama-3.1-70B-Instruct",
"provider_id": "fireworks"
},
"type": "metric",
"metric": "total_tokens",
"value": 421,
"unit": "tokens"
}
],
"completion_message": {
"role": "assistant",
"content": "Humans live in various parts of the world, inhabiting almost every continent, country, and region. Here's a breakdown of where humans live:\n\n1. **Continents:** Humans inhabit all seven continents:\n\t* Africa\n\t* Antarctica (research stations only)\n\t* Asia\n\t* Australia\n\t* Europe\n\t* North America\n\t* South America\n2. **Countries:** There are 196 countries recognized by the United Nations, and humans live in almost all of them.\n3. **Regions:** Humans live in diverse regions, including:\n\t* Deserts (e.g., Sahara, Mojave)\n\t* Forests (e.g., Amazon, Congo)\n\t* Grasslands (e.g., Prairies, Steppes)\n\t* Mountains (e.g., Himalayas, Andes)\n\t* Oceans (e.g., coastal areas, islands)\n\t* Tundras (e.g., Arctic, sub-Arctic)\n4. **Cities and towns:** Many humans live in urban areas, such as cities and towns, which are often located near:\n\t* Coastlines\n\t* Rivers\n\t* Lakes\n\t* Mountains\n5. **Rural areas:** Some humans live in rural areas, such as:\n\t* Villages\n\t* Farms\n\t* Countryside\n6. **Islands:** Humans inhabit many islands, including:\n\t* Tropical islands (e.g., Hawaii, Maldives)\n\t* Arctic islands (e.g., Greenland, Iceland)\n\t* Continental islands (e.g., Great Britain, Ireland)\n7. **Extreme environments:** Humans also live in extreme environments, such as:\n\t* High-altitude areas (e.g., Tibet, Andes)\n\t* Low-altitude areas (e.g., Death Valley, Dead Sea)\n\t* Areas with extreme temperatures (e.g., Arctic, Sahara)\n\nOverall, humans have adapted to live in a wide range of environments and ecosystems around the world.",
"stop_reason": "end_of_turn",
"tool_calls": []
},
"logprobs": null
}
```
```
LLAMA_STACK_CONFIG=fireworks pytest -s -v tests/integration/inference
======================================================================== short test summary info =========================================================================
FAILED tests/integration/inference/test_text_inference.py::test_text_chat_completion_tool_calling_tools_not_in_request[txt=8B:vis=11B-inference:chat_completion:tool_calling_tools_absent-True] - ValueError: Unsupported tool prompt format: ToolPromptFormat.json
FAILED tests/integration/inference/test_text_inference.py::test_text_chat_completion_tool_calling_tools_not_in_request[txt=8B:vis=11B-inference:chat_completion:tool_calling_tools_absent-False] - ValueError: Unsupported tool prompt format: ToolPromptFormat.json
FAILED tests/integration/inference/test_vision_inference.py::test_image_chat_completion_non_streaming[txt=8B:vis=11B] - fireworks.client.error.InvalidRequestError: {'error': {'object': 'error', 'type': 'invalid_request_error', 'message': 'Failed to decode image cannot identify image f...
FAILED tests/integration/inference/test_vision_inference.py::test_image_chat_completion_streaming[txt=8B:vis=11B] - fireworks.client.error.InvalidRequestError: {'error': {'object': 'error', 'type': 'invalid_request_error', 'message': 'Failed to decode image cannot identify image f...
========================================================= 4 failed, 16 passed, 23 xfailed, 17 warnings in 44.36s =========================================================
```
# What does this PR do?
- add some docs to OpenAPI for agents/eval/scoring/datasetio
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
- read
[//]: # (## Documentation)
# What does this PR do?
- This was missed from previous deprecation:
https://github.com/meta-llama/llama-stack/pull/1186
- Part of https://github.com/meta-llama/llama-stack/issues/1396
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
```
pytest -v -s --nbval-lax ./llama-stack/docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb
```
[//]: # (## Documentation)
# What does this PR do?
- Deprecate allow_turn_resume flag as this is used for staying backward
compat.
- Closes https://github.com/meta-llama/llama-stack/issues/1363
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
```
LLAMA_STACK_CONFIG=fireworks pytest -v tests/api/agents/test_agents.py --inference-model "meta-llama/Llama-3.3-70B-Instruct" --record-responses
```
<img width="1054" alt="image"
src="https://github.com/user-attachments/assets/d31de2d4-0953-41e1-a71a-7e1579fa351a"
/>
[//]: # (## Documentation)
