chore: Change create_tool endpoint on v1 routes to error instead of upsert (#2102)
This commit is contained in:
104
.github/workflows/test_groq.yml
vendored
104
.github/workflows/test_groq.yml
vendored
@@ -1,104 +0,0 @@
|
||||
name: Groq Llama 3.1 70b Capabilities Test
|
||||
|
||||
env:
|
||||
GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [ main ]
|
||||
pull_request:
|
||||
branches: [ main ]
|
||||
|
||||
jobs:
|
||||
test:
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 15
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: "Setup Python, Poetry and Dependencies"
|
||||
uses: packetcoders/action-setup-cache-python-poetry@main
|
||||
with:
|
||||
python-version: "3.12"
|
||||
poetry-version: "1.8.2"
|
||||
install-args: "-E dev -E external-tools"
|
||||
|
||||
- name: Test first message contains expected function call and inner monologue
|
||||
id: test_first_message
|
||||
env:
|
||||
GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
|
||||
run: |
|
||||
poetry run pytest -s -vv tests/test_model_letta_perfomance.py::test_groq_llama31_70b_returns_valid_first_message
|
||||
echo "TEST_FIRST_MESSAGE_EXIT_CODE=$?" >> $GITHUB_ENV
|
||||
continue-on-error: true
|
||||
|
||||
- name: Test model sends message with keyword
|
||||
id: test_keyword_message
|
||||
env:
|
||||
GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
|
||||
run: |
|
||||
poetry run pytest -s -vv tests/test_model_letta_perfomance.py::test_groq_llama31_70b_returns_keyword
|
||||
echo "TEST_KEYWORD_MESSAGE_EXIT_CODE=$?" >> $GITHUB_ENV
|
||||
continue-on-error: true
|
||||
|
||||
- name: Test model uses external tool correctly
|
||||
id: test_external_tool
|
||||
env:
|
||||
GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
|
||||
run: |
|
||||
poetry run pytest -s -vv tests/test_model_letta_perfomance.py::test_groq_llama31_70b_uses_external_tool
|
||||
echo "TEST_EXTERNAL_TOOL_EXIT_CODE=$?" >> $GITHUB_ENV
|
||||
continue-on-error: true
|
||||
|
||||
- name: Test model recalls chat memory
|
||||
id: test_chat_memory
|
||||
env:
|
||||
GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
|
||||
run: |
|
||||
poetry run pytest -s -vv tests/test_model_letta_perfomance.py::test_groq_llama31_70b_recall_chat_memory
|
||||
echo "TEST_CHAT_MEMORY_EXIT_CODE=$?" >> $GITHUB_ENV
|
||||
continue-on-error: true
|
||||
|
||||
- name: Test model uses 'archival_memory_search' to find secret
|
||||
id: test_archival_memory
|
||||
env:
|
||||
GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
|
||||
run: |
|
||||
poetry run pytest -s -vv tests/test_model_letta_perfomance.py::test_groq_llama31_70b_archival_memory_retrieval
|
||||
echo "TEST_ARCHIVAL_MEMORY_EXIT_CODE=$?" >> $GITHUB_ENV
|
||||
continue-on-error: true
|
||||
|
||||
- name: Test model can edit core memories
|
||||
id: test_core_memory
|
||||
env:
|
||||
GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
|
||||
run: |
|
||||
poetry run pytest -s -vv tests/test_model_letta_perfomance.py::test_groq_llama31_70b_edit_core_memory
|
||||
echo "TEST_CORE_MEMORY_EXIT_CODE=$?" >> $GITHUB_ENV
|
||||
continue-on-error: true
|
||||
|
||||
- name: Summarize test results
|
||||
if: always()
|
||||
run: |
|
||||
echo "Test Results Summary:"
|
||||
|
||||
# If the exit code is empty, treat it as a failure (❌)
|
||||
echo "Test first message: $([[ -z $TEST_FIRST_MESSAGE_EXIT_CODE || $TEST_FIRST_MESSAGE_EXIT_CODE -ne 0 ]] && echo ❌ || echo ✅)"
|
||||
echo "Test model sends message with keyword: $([[ -z $TEST_KEYWORD_MESSAGE_EXIT_CODE || $TEST_KEYWORD_MESSAGE_EXIT_CODE -ne 0 ]] && echo ❌ || echo ✅)"
|
||||
echo "Test model uses external tool: $([[ -z $TEST_EXTERNAL_TOOL_EXIT_CODE || $TEST_EXTERNAL_TOOL_EXIT_CODE -ne 0 ]] && echo ❌ || echo ✅)"
|
||||
echo "Test model recalls chat memory: $([[ -z $TEST_CHAT_MEMORY_EXIT_CODE || $TEST_CHAT_MEMORY_EXIT_CODE -ne 0 ]] && echo ❌ || echo ✅)"
|
||||
echo "Test model uses 'archival_memory_search' to find secret: $([[ -z $TEST_ARCHIVAL_MEMORY_EXIT_CODE || $TEST_ARCHIVAL_MEMORY_EXIT_CODE -ne 0 ]] && echo ❌ || echo ✅)"
|
||||
echo "Test model can edit core memories: $([[ -z $TEST_CORE_MEMORY_EXIT_CODE || $TEST_CORE_MEMORY_EXIT_CODE -ne 0 ]] && echo ❌ || echo ✅)"
|
||||
|
||||
# Check if any test failed (either non-zero or unset exit code)
|
||||
if [[ -z $TEST_FIRST_MESSAGE_EXIT_CODE || $TEST_FIRST_MESSAGE_EXIT_CODE -ne 0 || \
|
||||
-z $TEST_KEYWORD_MESSAGE_EXIT_CODE || $TEST_KEYWORD_MESSAGE_EXIT_CODE -ne 0 || \
|
||||
-z $TEST_EXTERNAL_TOOL_EXIT_CODE || $TEST_EXTERNAL_TOOL_EXIT_CODE -ne 0 || \
|
||||
-z $TEST_CHAT_MEMORY_EXIT_CODE || $TEST_CHAT_MEMORY_EXIT_CODE -ne 0 || \
|
||||
-z $TEST_ARCHIVAL_MEMORY_EXIT_CODE || $TEST_ARCHIVAL_MEMORY_EXIT_CODE -ne 0 || \
|
||||
-z $TEST_CORE_MEMORY_EXIT_CODE || $TEST_CORE_MEMORY_EXIT_CODE -ne 0 ]]; then
|
||||
echo "Some tests failed."
|
||||
exit 78
|
||||
fi
|
||||
continue-on-error: true
|
||||
Reference in New Issue
Block a user