llama-stack-mirror/src/llama_stack
Ken Dreyer dabebdd230
Some checks failed
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 1s
Integration Tests (Replay) / generate-matrix (push) Successful in 3s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Python Package Build Test / build (3.13) (push) Failing after 4s
Python Package Build Test / build (3.12) (push) Failing after 6s
API Conformance Tests / check-schema-compatibility (push) Successful in 10s
Test External API and Providers / test-external (venv) (push) Failing after 27s
Vector IO Integration Tests / test-matrix (push) Failing after 36s
UI Tests / ui-tests (22) (push) Successful in 44s
Unit Tests / unit-tests (3.13) (push) Failing after 1m21s
Unit Tests / unit-tests (3.12) (push) Failing after 1m59s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 2m33s
Pre-commit / pre-commit (push) Successful in 3m0s
fix: update hard-coded google model names (#4212)
# What does this PR do?
When we send the model names to Google's openai API, we must use the
"google" name prefix. Google does not recognize the "vertexai" model
names.

Closes #4211

## Test Plan
```bash
uv venv --python python312
. .venv/bin/activate
llama stack list-deps starter | xargs -L1 uv pip install
llama stack run starter
```

Test that this shows the gemini models with their correct names:
```bash
curl http://127.0.0.1:8321/v1/models | jq '.data | map(select(.custom_metadata.provider_id == "vertexai"))'
```

Test that this chat completion works:
```bash
curl -X POST   -H "Content-Type: application/json"   "http://127.0.0.1:8321/v1/chat/completions"   -d '{
        "model": "vertexai/google/gemini-2.5-flash",
        "messages": [
          {
            "role": "system",
            "content": "You are a helpful assistant."
          },
          {
            "role": "user",
            "content": "Hello! Can you tell me a joke?"
          }
        ],
        "temperature": 1.0,
        "max_tokens": 256
      }'
```
2025-11-21 13:12:01 -08:00
..
cli fix: rename llama_stack_api dir (#4155) 2025-11-13 15:04:36 -08:00
core chore: add storage sane defaults (#4182) 2025-11-18 15:22:26 -08:00
distributions feat!: change bedrock bearer token env variable to match AWS docs & boto3 convention (#4152) 2025-11-21 09:48:05 -05:00
models refactor: remove dead inference API code and clean up imports (#4093) 2025-11-10 15:29:24 -08:00
providers fix: update hard-coded google model names (#4212) 2025-11-21 13:12:01 -08:00
testing fix: MCP authorization parameter implementation (#4052) 2025-11-14 08:54:42 -08:00
__init__.py chore: Stack server no longer depends on llama-stack-client (#4094) 2025-11-07 09:54:09 -08:00
env.py chore(package): migrate to src/ layout (#3920) 2025-10-27 12:02:21 -07:00
log.py chore(package): migrate to src/ layout (#3920) 2025-10-27 12:02:21 -07:00