mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-22 08:17:18 +00:00
2c43285e22
**This PR changes configurations in a backward incompatible way.**
Run configs today repeat full SQLite/Postgres snippets everywhere a
store is needed, which means duplicated credentials, extra connection
pools, and lots of drift between files. This PR introduces named storage
backends so the stack and providers can share a single catalog and
reference those backends by name.
## Key Changes
- Add `storage.backends` to `StackRunConfig`, register each KV/SQL
backend once at startup, and validate that references point to the right
family.
- Move server stores under `storage.stores` with lightweight references
(backend + namespace/table) instead of full configs.
- Update every provider/config/doc to use the new reference style;
docs/codegen now surface the simplified YAML.
## Migration
Before:
```yaml
metadata_store:
type: sqlite
db_path: ~/.llama/distributions/foo/registry.db
inference_store:
type: postgres
host: ${env.POSTGRES_HOST}
port: ${env.POSTGRES_PORT}
db: ${env.POSTGRES_DB}
user: ${env.POSTGRES_USER}
password: ${env.POSTGRES_PASSWORD}
conversations_store:
type: postgres
host: ${env.POSTGRES_HOST}
port: ${env.POSTGRES_PORT}
db: ${env.POSTGRES_DB}
user: ${env.POSTGRES_USER}
password: ${env.POSTGRES_PASSWORD}
```
After:
```yaml
storage:
backends:
kv_default:
type: kv_sqlite
db_path: ~/.llama/distributions/foo/kvstore.db
sql_default:
type: sql_postgres
host: ${env.POSTGRES_HOST}
port: ${env.POSTGRES_PORT}
db: ${env.POSTGRES_DB}
user: ${env.POSTGRES_USER}
password: ${env.POSTGRES_PASSWORD}
stores:
metadata:
backend: kv_default
namespace: registry
inference:
backend: sql_default
table_name: inference_store
max_write_queue_size: 10000
num_writers: 4
conversations:
backend: sql_default
table_name: openai_conversations
```
Provider configs follow the same pattern—for example, a Chroma vector
adapter switches from:
```yaml
providers:
vector_io:
- provider_id: chromadb
provider_type: remote::chromadb
config:
url: ${env.CHROMADB_URL}
kvstore:
type: sqlite
db_path: ~/.llama/distributions/foo/chroma.db
```
to:
```yaml
providers:
vector_io:
- provider_id: chromadb
provider_type: remote::chromadb
config:
url: ${env.CHROMADB_URL}
persistence:
backend: kv_default
namespace: vector_io::chroma_remote
```
Once the backends are declared, everything else just points at them, so
rotating credentials or swapping to Postgres happens in one place and
the stack reuses a single connection pool.
101 lines
3.4 KiB
YAML
101 lines
3.4 KiB
YAML
name: 'Run and Record Tests'
|
|
description: 'Run integration tests and handle recording/artifact upload'
|
|
|
|
inputs:
|
|
stack-config:
|
|
description: 'Stack configuration to use'
|
|
required: true
|
|
setup:
|
|
description: 'Setup to use for tests (e.g., ollama, gpt, vllm)'
|
|
required: false
|
|
default: ''
|
|
inference-mode:
|
|
description: 'Inference mode (record or replay)'
|
|
required: true
|
|
suite:
|
|
description: 'Test suite to use: base, responses, vision, etc.'
|
|
required: false
|
|
default: ''
|
|
subdirs:
|
|
description: 'Comma-separated list of test subdirectories to run; overrides suite'
|
|
required: false
|
|
default: ''
|
|
pattern:
|
|
description: 'Regex pattern to pass to pytest -k'
|
|
required: false
|
|
default: ''
|
|
|
|
runs:
|
|
using: 'composite'
|
|
steps:
|
|
- name: Check Storage and Memory Available Before Tests
|
|
if: ${{ always() }}
|
|
shell: bash
|
|
run: |
|
|
free -h
|
|
df -h
|
|
|
|
- name: Run Integration Tests
|
|
shell: bash
|
|
run: |
|
|
SCRIPT_ARGS="--stack-config ${{ inputs.stack-config }} --inference-mode ${{ inputs.inference-mode }}"
|
|
|
|
# Add optional arguments only if they are provided
|
|
if [ -n '${{ inputs.setup }}' ]; then
|
|
SCRIPT_ARGS="$SCRIPT_ARGS --setup ${{ inputs.setup }}"
|
|
fi
|
|
if [ -n '${{ inputs.suite }}' ]; then
|
|
SCRIPT_ARGS="$SCRIPT_ARGS --suite ${{ inputs.suite }}"
|
|
fi
|
|
if [ -n '${{ inputs.subdirs }}' ]; then
|
|
SCRIPT_ARGS="$SCRIPT_ARGS --subdirs ${{ inputs.subdirs }}"
|
|
fi
|
|
if [ -n '${{ inputs.pattern }}' ]; then
|
|
SCRIPT_ARGS="$SCRIPT_ARGS --pattern ${{ inputs.pattern }}"
|
|
fi
|
|
|
|
echo "=== Running command ==="
|
|
echo "uv run --no-sync ./scripts/integration-tests.sh $SCRIPT_ARGS"
|
|
echo ""
|
|
|
|
uv run --no-sync ./scripts/integration-tests.sh $SCRIPT_ARGS | tee pytest-${{ inputs.inference-mode }}.log
|
|
|
|
|
|
- name: Commit and push recordings
|
|
if: ${{ inputs.inference-mode == 'record' }}
|
|
shell: bash
|
|
run: |
|
|
echo "Checking for recording changes"
|
|
git status --porcelain tests/integration/
|
|
|
|
if [[ -n $(git status --porcelain tests/integration/) ]]; then
|
|
echo "New recordings detected, committing and pushing"
|
|
git add tests/integration/
|
|
|
|
git commit -m "Recordings update from CI (suite: ${{ inputs.suite }})"
|
|
git fetch origin ${{ github.ref_name }}
|
|
git rebase origin/${{ github.ref_name }}
|
|
echo "Rebased successfully"
|
|
git push origin HEAD:${{ github.ref_name }}
|
|
echo "Pushed successfully"
|
|
else
|
|
echo "No recording changes"
|
|
fi
|
|
|
|
- name: Write docker logs to file
|
|
if: ${{ always() }}
|
|
shell: bash
|
|
run: |
|
|
sudo docker logs ollama > ollama-${{ inputs.inference-mode }}.log || true
|
|
distro_name=$(echo "${{ inputs.stack-config }}" | sed 's/^docker://' | sed 's/^server://')
|
|
stack_container_name="llama-stack-test-$distro_name"
|
|
sudo docker logs $stack_container_name > docker-${distro_name}-${{ inputs.inference-mode }}.log || true
|
|
|
|
- name: Upload logs
|
|
if: ${{ always() }}
|
|
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
|
|
with:
|
|
name: logs-${{ github.run_id }}-${{ github.run_attempt || '' }}-${{ strategy.job-index }}
|
|
path: |
|
|
*.log
|
|
retention-days: 1
|