# What does this PR do?
- Fix issue w/ passthrough provider
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
llama stack run
[//]: # (## Documentation)
Summary:
This is not used anywhere.
closes#1421
Test Plan:
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 --record-responses
Summary:
1. adds option to not use bwrap for code execution
2. disable bwrap when running tests on macs
Test Plan:
```
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
```
Verify code_interpreter result in logs
INFO 2025-03-11 08:10:39,858
llama_stack.providers.inline.agents.meta_reference.agent_instance:1032
agents: tool
call code_interpreter completed with result:
content='completed\n\n541\n' error_message=None error_code=None
metadata=None
Summary:
Refactoring only.
Centralize logic to preprocess toolgroup to one place.
Test Plan:
LLAMA_STACK_CONFIG=fireworks pytest -s -v
tests/api/agents/test_agents.py --safety-shield
meta-llama/Llama-Guard-3-8B
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with
[ReviewStack](https://reviewstack.dev/meta-llama/llama-stack/pull/1381).
* #1384
* __->__ #1381
# 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 fixes the build error
## Test Plan
pre-commit run --all-files
check for merge
conflicts................................................Passed
trim trailing
whitespace.................................................Passed
check for added large
files..............................................Passed
fix end of
files.........................................................Passed
Insert license in
comments...............................................Passed
ruff.....................................................................Passed
ruff-format..............................................................Passed
blacken-docs.............................................................Passed
uv-lock..................................................................Passed
uv-export................................................................Passed
mypy.....................................................................Passed
Distribution Template
Codegen............................................Passed
# 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?
- fix precommit
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
CI
[//]: # (## Documentation)
## What does this PR do?
We noticed that the passthrough inference provider doesn't work agent
due to the type mis-match between client and server. We manually cast
the llama stack client type to llama stack server type to fix the issue.
## test
run `python -m examples.agents.hello localhost 8321` within
llama-stack-apps
<img width="1073" alt="Screenshot 2025-03-11 at 8 43 44 PM"
src="https://github.com/user-attachments/assets/bd1bdd31-606a-420c-a249-95f6184cc0b1"
/>
fix https://github.com/meta-llama/llama-stack/issues/1560
## What does this PR do?
As title, add codegen for open-benchmark template
## test
checked the new generated run.yaml file and it's identical before and
after the change
Also add small improvement to together template so that missing
TOGETHER_API_KEY won't crash the server which is the consistent user
experience as other remote providers
# What does this PR do?
uvicorn has a `log_level` arg in uvicorn.run, pass in the effective
level set by the logger.
Additionally, third party libraries like httpx are using our logging
format, but not honoring our log level.
This seems unintended, so loop through all items in the loggerDict and
apply the same log level as what we have set.
## Test Plan
before:
```
llama stack run --image-type venv ~/.llama/distributions/ollama/ollama-run.yaml
Environment variable LLAMA_STACK_LOGGING found: all=warn
Using virtual environment: /Users/charliedoern/projects/Documents/llama-stack/venv
+ python -m llama_stack.distribution.server.server --yaml-config /Users/charliedoern/.llama/distributions/ollama/ollama-run.yaml --port 8321
Environment variable LLAMA_STACK_LOGGING found: all=warn
WARNING 2025-03-10 16:05:49,706 root:71 uncategorized: Warning: `bwrap` is not available. Code interpreter tool will
not work correctly.
INFO 2025-03-10 16:05:49,916 datasets:54 uncategorized: PyTorch version 2.5.1 available.
INFO 2025-03-10 16:05:50,010 httpx:1740 uncategorized: HTTP Request: GET http://localhost:11434/api/ps "HTTP/1.1 200
OK"
INFO 2025-03-10 16:05:50,297 httpx:1740 uncategorized: HTTP Request: POST http://localhost:11434/api/pull "HTTP/1.1
200 OK"
INFO 2025-03-10 16:05:50,314 httpx:1740 uncategorized: HTTP Request: GET http://localhost:11434/api/tags "HTTP/1.1
200 OK"
INFO: Started server process [89663]
INFO: Waiting for application startup.
INFO: ASGI 'lifespan' protocol appears unsupported.
INFO: Application startup complete.
INFO: Uvicorn running on http://['::', '0.0.0.0']:8321 (Press CTRL+C to quit)
```
after:
```
llama stack run --image-type venv ~/.llama/distributions/ollama/ollama-run.yaml
Environment variable LLAMA_STACK_LOGGING found: all=warn
Using virtual environment: /Users/charliedoern/projects/Documents/llama-stack/venv
+ python -m llama_stack.distribution.server.server --yaml-config /Users/charliedoern/.llama/distributions/ollama/ollama-run.yaml --port 8321
Environment variable LLAMA_STACK_LOGGING found: all=warn
WARNING 2025-03-10 16:05:20,429 root:71 uncategorized: Warning: `bwrap` is not available. Code interpreter tool will
not work correctly.
INFO 2025-03-10 16:05:20,639 datasets:54 uncategorized: PyTorch version 2.5.1 available.
```
Signed-off-by: Charlie Doern <cdoern@redhat.com>
