Add an initial test for chat_with_ai #3793
Conversation
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
kinance
changed the title
kinance
changed the title
Codecov ReportPatch coverage has no change and project coverage change:
Additional details and impacted files@@ Coverage Diff @@
## master #3793 +/- ##
==========================================
- Coverage 69.65% 67.72% -1.94%
==========================================
Files 72 72
Lines 3523 3535 +12
Branches 562 559 -3
==========================================
- Hits 2454 2394 -60
- Misses 881 956 +75
+ Partials 188 185 -3 ☔ View full report in Codecov by Sentry. |
|
This is a mass message from the AutoGPT core team. For more details (and for infor on joining our Discord), please refer to: |
|
This is going to be even more important once there's support for dynamic prompting #3937 |
| token_limit = 4000 | ||
| mocker.patch( | ||
| "autogpt.llm.chat.create_chat_completion", | ||
| return_value="I'm doing well, thank you for asking.", |
There was a problem hiding this comment.
im still learning more about mocker so excuse me if im incorrect, but by doing this return value and then asserting it arent we always going to get a passing test because the way you are asserting it is just going to return this? please feel free to correct me if im wrong
There was a problem hiding this comment.
Since the patched module is create_chat_completion it might be a correct implementation, so let me know if I'm missing something
| from autogpt.llm.chat import chat_with_ai | ||
|
|
||
|
|
||
| @pytest.fixture |
There was a problem hiding this comment.
should this fixture live in the conftest.py? there might be a agent fixture already defined therem, if so lets just use that other fixture
tests/test_chat.py
Outdated
| token_limit = 4000 | ||
| mocker.patch( | ||
| "autogpt.llm.chat.create_chat_completion", | ||
| return_value="I'm doing well, thank you for asking.", |
There was a problem hiding this comment.
same as above, by patching the function arent we just testing that the patch works, rather than the implementation of the actual function
There was a problem hiding this comment.
i might be wrong though as we are patching create_chat_completion
|
Deployment failed with the following error: |
|
Deployment failed with the following error: |
Background
The core function, chat_with_ai, is very important to auto-gpt, but missing a test. It'd be great to have some testcases to verify some basic behaviors and increase code coverage.
Changes
Just to get started: added a basic test for chat.py to cover the chat_with_ai function, and verify the output message, full_message_history and new summary_memory. More testcases to come later.
Test Plan
Ran the test itself.
PR Quality Checklist