llama-stack/llama_stack/distribution/utils/context.py
Dinesh Yeduguru 58d08d100e
feat: Add back inference metrics and preserve context variables across asyncio boundary (#1552)
# 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
2025-03-12 12:01:03 -07:00

33 lines
1.1 KiB
Python

# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from contextvars import ContextVar
from typing import AsyncGenerator, List, TypeVar
T = TypeVar("T")
def preserve_contexts_async_generator(
gen: AsyncGenerator[T, None], context_vars: List[ContextVar]
) -> AsyncGenerator[T, None]:
"""
Wraps an async generator to preserve context variables across iterations.
This is needed because we start a new asyncio event loop for each streaming request,
and we need to preserve the context across the event loop boundary.
"""
async def wrapper():
while True:
try:
item = await gen.__anext__()
context_values = {context_var.name: context_var.get() for context_var in context_vars}
yield item
for context_var in context_vars:
_ = context_var.set(context_values[context_var.name])
except StopAsyncIteration:
break
return wrapper()