llama-stack-mirror/llama_stack
Ben Browning 8e316c9b1e
feat: function tools in OpenAI Responses (#2094)
# What does this PR do?

This is a combination of what was previously 3 separate PRs - #2069,
#2075, and #2083. It turns out all 3 of those are needed to land a
working function calling Responses implementation. The web search
builtin tool was already working, but this wires in support for custom
function calling.

I ended up combining all three into one PR because they all had lots of
merge conflicts, both with each other but also with #1806 that just
landed. And, because landing any of them individually would have only
left a partially working implementation merged.

The new things added here are:
* Storing of input items from previous responses and restoring of those
input items when adding previous responses to the conversation state
* Handling of multiple input item messages roles, not just "user"
messages.
* Support for custom tools passed into the Responses API to enable
function calling outside of just the builtin websearch tool.

Closes #2074
Closes #2080

## Test Plan

### Unit Tests

Several new unit tests were added, and they all pass. Ran via:

```
python -m pytest -s -v tests/unit/providers/agents/meta_reference/test_openai_responses.py
```

### Responses API Verification Tests

I ran our verification run.yaml against multiple providers to ensure we
were getting a decent pass rate. Specifically, I ensured the new custom
tool verification test passed across multiple providers and that the
multi-turn examples passed across at least some of the providers (some
providers struggle with the multi-turn workflows still).

Running the stack setup for verification testing:

```
llama stack run --image-type venv tests/verifications/openai-api-verification-run.yaml
```

Together, passing 100% as an example:

```
pytest -s -v 'tests/verifications/openai_api/test_responses.py' --provider=together-llama-stack
```

## Documentation

We will need to start documenting the OpenAI APIs, but for now the
Responses stuff is still rapidly evolving so delaying that.

---------

Signed-off-by: Derek Higgins <derekh@redhat.com>
Signed-off-by: Ben Browning <bbrownin@redhat.com>
Co-authored-by: Derek Higgins <derekh@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
2025-05-13 11:29:15 -07:00
..
apis feat: function tools in OpenAI Responses (#2094) 2025-05-13 11:29:15 -07:00
cli chore(refact)!: simplify config management (#1105) 2025-05-07 09:18:12 -07:00
distribution feat: function tools in OpenAI Responses (#2094) 2025-05-13 11:29:15 -07:00
models fix: llama4 tool use prompt fix (#2103) 2025-05-06 22:18:31 -07:00
providers feat: function tools in OpenAI Responses (#2094) 2025-05-13 11:29:15 -07:00
strong_typing chore: enable pyupgrade fixes (#1806) 2025-05-01 14:23:50 -07:00
templates fix: Adding Embedding model to watsonx inference (#2118) 2025-05-12 10:58:22 -07:00
__init__.py export LibraryClient 2024-12-13 12:08:00 -08:00
env.py refactor(test): move tools, evals, datasetio, scoring and post training tests (#1401) 2025-03-04 14:53:47 -08:00
log.py chore: enable pyupgrade fixes (#1806) 2025-05-01 14:23:50 -07:00
schema_utils.py chore: enable pyupgrade fixes (#1806) 2025-05-01 14:23:50 -07:00