# What does this PR do?
This allows llama-stack users of the Docker image to use OpenTelemetry
like previous versions.
#4127 migrated to automatic instrumentation, but unless we add those
libraries to the image, everyone needs to build a custom image to enable
otel. Also, unless we establish a convention for enabling it, users who
formerly just set config now need to override the entrypoint.
This PR bootstraps OTEL packages, so they are available (only +10MB). It
also prefixes `llama stack run` with `opentelemetry-instrument` when any
`OTEL_*` environment variable is set.
The result is implicit tracing like before, where you don't need a
custom image to use traces or metrics.
## Test Plan
```bash
# Build image
docker build -f containers/Containerfile \
--build-arg DISTRO_NAME=starter \
--build-arg INSTALL_MODE=editable \
--tag llamastack/distribution-starter:otel-test .
# Run with OTEL env to implicitly use `opentelemetry-instrument`. The
# Settings below ensure inbound traces are honored, but no
# "junk traces" like SQL connects are created.
docker run -p 8321:8321 \
-e OTEL_EXPORTER_OTLP_ENDPOINT=http://host.docker.internal:4318 \
-e OTEL_SERVICE_NAME=llama-stack \
-e OTEL_TRACES_SAMPLER=parentbased_traceidratio \
-e OTEL_TRACES_SAMPLER_ARG=0.0 \
llamastack/distribution-starter:otel-test
```
Ran a sample flight search agent which is instrumented on the client
side. This and llama-stack target
[otel-tui](https://github.com/ymtdzzz/otel-tui) I verified no root
database spans, yet database spans are attached to incoming traces.
<img width="1608" height="742" alt="screenshot"
src="https://github.com/user-attachments/assets/69f59b74-3054-42cd-947d-a6c0d9472a7c"
/>
Signed-off-by: Adrian Cole <adrian@tetrate.io>
Fixes container builds failing with UV index strategy errors when build
args are passed with empty values.
Docker ARGs declared with empty defaults (ARG UV_INDEX_STRATEGY="")
become environment variables with empty string values in RUN commands.
UV interprets these as if --index-strategy "" was passed on the command
line, causing build failures with "error: a value is required for
'--index-strategy <UV_INDEX_STRATEGY>'".
This is a footgun because empty string ≠ unset variable, and ARGs
silently propagate to all RUN commands, only failing when declared with
empty defaults.
The fix unsets UV_EXTRA_INDEX_URL and UV_INDEX_STRATEGY at the start of
RUN blocks, saves the values early, and only restores them for editable
installs with RC dependencies. All other install modes (PyPI, test-pypi,
client) now run with a clean environment.
Backports UV index configuration fixes from `release-0.3.x` (PR #4002).
The main issue: when we created the release branch infrastructure, we
configured UV to use `test.pypi` as the PRIMARY index to resolve RC
dependencies. This caused UV to look for ALL packages there first, which
led to problems - some packages don't have binary wheels on `test.pypi`,
so UV tried building from source and failed (like the `psycopg2-binary`
issue we hit).
The fix is simple: use PyPI as primary (default) and `test.pypi` as an
EXTRA index. UV will check PyPI first for everything, and only fall back
to `test.pypi` for packages not found there (like our RC client
versions).
This PR includes:
- Fixed `install-llama-stack-client` action to output
`UV_EXTRA_INDEX_URL` instead of `UV_INDEX_URL`
- New `uv-run-with-index.sh` wrapper that auto-detects release branches
and sets UV env vars
- Updated pre-commit hooks (`uv-lock`, codegen, etc.) to use the wrapper
- Pass UV env vars as Docker build args in all locations
- Scope UV env vars properly in Containerfile (inline for llama-stack
install, explicitly unset before distribution deps)
- Export UV env vars to `GITHUB_ENV` in setup-runner for cross-step
persistence
The wrapper detects release branches automatically in both CI and local
environments, so this "just works" without manual configuration. On main
(non-release branch), the wrapper becomes a no-op.
Tested and validated on `release-0.3.x` where all CI checks pass.
# What does this PR do?
mirrors build_container.sh
trying to resolve:
0.105 + [ editable = editable ]
0.105 + [ ! -d /workspace/llama-stack ]
0.105 + uv pip install --no-cache-dir -e /workspace/llama-stack
0.261 Using Python 3.12.12 environment at: /usr/local
0.479 × No solution found when resolving dependencies:
0.479 ╰─▶ Because only llama-stack-client<=0.2.23 is available and
0.479 llama-stack==0.3.0rc4 depends on llama-stack-client>=0.3.0rc4, we
can
0.479 conclude that llama-stack==0.3.0rc4 cannot be used.
0.479 And because only llama-stack==0.3.0rc4 is available and you
require
0.479 llama-stack, we can conclude that your requirements are
unsatisfiable.
------
## Test Plan
# What does this PR do?
relates to #2878
We introduce a Containerfile which is used to replaced the `llama stack
build` command (removal in a separate PR).
```
llama stack build --distro starter --image-type venv --run
```
is replaced by
```
llama stack list-deps starter | xargs -L1 uv pip install
llama stack run starter
```
- See the updated workflow files for e2e workflow.
## Test Plan
CI
```
❯ docker build . -f docker/Dockerfile --build-arg DISTRO_NAME=starter --build-arg INSTALL_MODE=editable --tag test_starter
❯ docker run -p 8321:8321 test_starter
❯ curl http://localhost:8321/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-4o-mini",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'
```
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with
[ReviewStack](https://reviewstack.dev/llamastack/llama-stack/pull/3839).
* #3855
* __->__ #3839
