Commit graph

12 commits

Author SHA1 Message Date
ehhuang
42788a9d50
test: re record responses after client sync (#1615)
Summary:

Test Plan:
LLAMA_STACK_CONFIG=fireworks pytest -s -v
tests/integration/agents/test_agents.py --safety-shield
meta-llama/Llama-Guard-3-8B --text-model
meta-llama/Llama-3.1-8B-Instruct --record-responses
2025-03-13 11:21:10 -07:00
ehhuang
a505bf45a3
feat(api): remove tool_name from ToolResponseMessage (#1599)
Summary:
This is not used anywhere.

closes #1421 

Test Plan:
LLAMA_STACK_CONFIG=fireworks pytest -s -v
tests/integration/agents/test_agents.py --safety-shield
meta-llama/Llama-Guard-3-8B --text-model
meta-llama/Llama-3.1-8B-Instruct --record-responses
2025-03-12 19:41:48 -07:00
ehhuang
6bfcb65343
test: code exec on mac (#1549)
Summary:
1. adds option to not use bwrap for code execution
2. disable bwrap when running tests on macs

Test Plan:
```
LLAMA_STACK_CONFIG=fireworks pytest -s -v tests/integration/agents/test_agents.py --safety-shield meta-llama/Llama-Guard-3-8B --text-model meta-llama/Llama-3.1-8B-Instruct
```

Verify code_interpreter result in logs

INFO 2025-03-11 08:10:39,858
llama_stack.providers.inline.agents.meta_reference.agent_instance:1032
agents: tool
call code_interpreter completed with result:
content='completed\n\n541\n' error_message=None error_code=None
         metadata=None
2025-03-12 19:21:53 -07:00
ehhuang
3b4f3a6b15
test: update recorded fixtures (#1493)
Summary:

Test Plan:
2025-03-07 13:58:38 -08:00
ehhuang
fbd47bb4b6
feat(agent): plain function as client tool (#1479)
Summary:
support added in
https://github.com/meta-llama/llama-stack-client-python/pull/187

Test Plan:

LLAMA_STACK_CONFIG=fireworks pytest -s -v
tests/integration/agents/test_agents.py --safety-shield
meta-llama/Llama-Guard-3-8B --text-model
meta-llama/Llama-3.1-8B-Instruct
2025-03-07 11:10:07 -08:00
Xi Yan
1e3be1e4d7
fix: fix agent test recorded responses (#1462)
# What does this PR do?

- re-gen to fix agents test
- update test_custom_tool

[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])

## Test Plan
```
LLAMA_STACK_CONFIG=fireworks pytest -v tests/integration/agents/test_agents.py --text-model meta-llama/Llama-3.3-70B-Instruct
```

<img width="1294" alt="image"
src="https://github.com/user-attachments/assets/63521532-b989-4cf2-8fe5-c7f057f1c4dc"
/>


[//]: # (## Documentation)
2025-03-06 19:37:52 -08:00
ehhuang
3d71e5a036
test: recordable mocks use json only (#1443)
# Summary:
removes the use of pickle

# Test Plan:
Run the following with `--record-responses` first, then another time
without.

LLAMA_STACK_CONFIG=fireworks pytest -s -v
tests/integration/agents/test_agents.py --safety-shield
meta-llama/Llama-Guard-3-8B --text-model
meta-llama/Llama-3.1-8B-Instruct
2025-03-06 14:46:29 -08:00
ehhuang
6cf79437b3
feat: support ClientTool output metadata (#1426)
# Summary:
Client side change in
https://github.com/meta-llama/llama-stack-client-python/pull/180
Changes the resume_turn API to accept `ToolResponse` instead of
`ToolResponseMessage`:
1. `ToolResponse` contains `metadata`
2. `ToolResponseMessage` is a concept for model inputs. Here we are just
submitting the outputs of tool execution.

# Test Plan:
Ran integration tests with newly added test using client tool with
metadata

LLAMA_STACK_CONFIG=fireworks pytest -s -v
tests/integration/agents/test_agents.py --safety-shield
meta-llama/Llama-Guard-3-8B --record-responses
2025-03-05 14:30:27 -08:00
Xi Yan
78962be996
chore: refactor create_and_execute_turn and resume_turn (#1399)
# What does this PR do?
- Closes https://github.com/meta-llama/llama-stack/issues/1212

[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])

## Test Plan
```
LLAMA_STACK_BASE_URL=http://localhost:8321 pytest -v tests/integration/agents/test_agents.py --inference-model "meta-llama/Llama-3.3-70B-Instruct"
```
<img width="1203" alt="image"
src="https://github.com/user-attachments/assets/35b60017-b3f2-4e98-87f2-2868730261bd"
/>

```
LLAMA_STACK_CONFIG=fireworks pytest -v tests/integration/agents/test_agents.py::test_rag_and_code_agent --inference-model "meta-llama/Llama-3.3-70B-Instruct"
```

[//]: # (## Documentation)
2025-03-04 16:07:30 -08:00
ehhuang
fd8c991393
fix: rag as attachment bug (#1392)
Summary:

Test Plan:
added new test
LLAMA_STACK_CONFIG=fireworks pytest -s -v
tests/api/agents/test_agents.py --safety-shield
meta-llama/Llama-Guard-3-8B
2025-03-04 13:08:16 -08:00
Xi Yan
158b6dc404
chore: deprecate allow_turn_resume (#1377)
# What does this PR do?

- Deprecate allow_turn_resume flag as this is used for staying backward
compat.
- Closes https://github.com/meta-llama/llama-stack/issues/1363

[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])

## Test Plan
```
LLAMA_STACK_CONFIG=fireworks pytest -v tests/api/agents/test_agents.py --inference-model "meta-llama/Llama-3.3-70B-Instruct" --record-responses
```

<img width="1054" alt="image"
src="https://github.com/user-attachments/assets/d31de2d4-0953-41e1-a71a-7e1579fa351a"
/>


[//]: # (## Documentation)
2025-03-04 12:22:11 -08:00
Ashwin Bharambe
4ca58eb987 refactor: tests/unittests -> tests/unit; tests/api -> tests/integration 2025-03-04 09:57:00 -08:00