Repository navigation
test: cover LiteLLM response parsing and tool-call handling with mocked tests - #37
Open
devin-ai-integration[bot] wants to merge 1 commit into
Open
devin-ai-integration[bot] wants to merge 1 commit into
devin-ai-integration[bot] wants to merge 1 commit into
Conversation
Author
🤖 Devin AI EngineerI'll be helping with this pull request! Here's what you should know: ✅ I will automatically:
Note: I can only respond to comments from users who have write access to this repository. ⚙️ Control Options:
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Closes a code-scan coverage gap:
LiteLLMModel._parse_response, its extraction helpers, andLiteLLMAPIMessageBuilder.handle_tool_callwere only exercised by livepricyprovider tests, so every response-shape branch was unverified in CI. This adds 19 network-free tests totests/llm/test_litellm_api.pybuilt on aFakeMessage/SimpleNamespacestand-in for a litellm chat completion.Fake response shape used throughout:
Behaviours now pinned:
<think>...</think>\n(plus customwrap_tag) and concatenation orderreasoning + text + contentToolCalls;Nonewhen the message has notool_calls; malformed arguments surface asjson.JSONDecodeErroruse_only_first_toolcall=Truetruncates extraction to the first callget_weather(location='Paris'), multiple -> newline-joined, empty/None->None_extract_env_actions_from_text_responsereturnsNone(the degenerate non-tool action space)handle_tool_callemits the raw assistant message followed by{"name", "role", "tool_call_id", "content"}dicts, truncatesraw_call.tool_callsto one underuse_only_first_toolcall, rejects image tool responses, and raises withoutresponded_tool_callsNo production code changed.
Devin-Org: engineering
Link to Devin session: https://app.devin.ai/sessions/be1f1fd646a74dfb9f2988ee920ac028
Open in Devin Desktop: https://app.devin.ai/desktop/session/be1f1fd646a74dfb9f2988ee920ac028?variant=devin