Commit graph

3 commits

Author SHA1 Message Date
Charlie Doern
9df073450f
feat: remove core.telemetry as a dependency of llama_stack.apis (#4064)
Some checks failed
Integration Tests (Replay) / generate-matrix (push) Successful in 3s
Test External API and Providers / test-external (venv) (push) Failing after 4s
UI Tests / ui-tests (22) (push) Successful in 55s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 1s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Python Package Build Test / build (3.12) (push) Failing after 1s
Pre-commit / pre-commit (push) Failing after 2s
Python Package Build Test / build (3.13) (push) Failing after 1s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 5s
Vector IO Integration Tests / test-matrix (push) Failing after 5s
API Conformance Tests / check-schema-compatibility (push) Successful in 11s
Unit Tests / unit-tests (3.12) (push) Failing after 4s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 4s
Unit Tests / unit-tests (3.13) (push) Failing after 5s
# What does this PR do?

Remove circular dependency by moving tracing from API protocol
definitions
 to router implementation layer.

This gets us closer to having a self contained API package with no other
cross-cutting dependencies to other parts of the llama stack codebase.
To the best of our ability, the llama_stack.api should only be type and
protocol definitions.

  Changes:
- Create apis/common/tracing.py with marker decorator (zero core
dependencies)
- Add the _new_ `@telemetry_traceable` marker decorator to 11 protocol
classes
- Apply actual tracing in core/resolver.py in `instantiate_provider`
based on protocol marker
- Move MetricResponseMixin from core to apis (it's an API response type)
  - APIs package is now self-contained with zero core dependencies

The tracing functionality remains identical - actual trace_protocol from
core
is applied to router implementations at runtime when both telemetry is
enabled
  and the protocol has the `__marked_for_tracing__` marker.

  ## Test Plan

  Manual integration test confirms identical behavior to main branch:

  ```bash
  llama stack list-deps --format uv starter | sh
  export OLLAMA_URL=http://localhost:11434
  llama stack run starter

  curl -X POST http://localhost:8321/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{"model": "ollama/gpt-oss:20b",
         "messages": [{"role": "user", "content": "Say hello"}],
         "max_tokens": 10}'
         
```

  Verified identical between main and this branch:
  - trace_id present in response
  - metrics array with prompt_tokens, completion_tokens, total_tokens
  - Server logs show trace_protocol applied to all routers

  Existing telemetry integration tests (tests/integration/telemetry/) validate
  trace context propagation and span attributes.


relates to #3895

---------

Signed-off-by: Charlie Doern <cdoern@redhat.com>
2025-11-06 10:58:30 -08:00
Sébastien Han
fd1603beef
chore: remove unused classes (#4077)
# What does this PR do?

These were maybe be included in the webmethod?
The unit test was pointless too since the request was never used
anywhere?

This shouldn't be in the API definition, if we never consume it.

## Test Plan

CI with pre-commit on OpenAPI spec generation.

Signed-off-by: Sébastien Han <seb@redhat.com>
2025-11-05 16:45:23 +01:00
Ashwin Bharambe
471b1b248b
chore(package): migrate to src/ layout (#3920)
Migrates package structure to src/ layout following Python packaging
best practices.

All code moved from `llama_stack/` to `src/llama_stack/`. Public API
unchanged - imports remain `import llama_stack.*`.

Updated build configs, pre-commit hooks, scripts, and GitHub workflows
accordingly. All hooks pass, package builds cleanly.

**Developer note**: Reinstall after pulling: `pip install -e .`
2025-10-27 12:02:21 -07:00