test support: add function_call cassettes for vLLM response mode #60
Merged
franciscojavierarceo merged 3 commits intoJun 17, 2026
Merged
Conversation
Signed-off-by: maral <maralbahari.98@gmail.com>
maralbahari
requested review from
bbrowning,
franciscojavierarceo,
jiahuei,
leseb,
noobHappylife,
qandrew and
tjtanaa
as code owners
maralbahari
changed the title
function_call cassettes for vLLM response mode
Signed-off-by: maral <maralbahari.98@gmail.com>
Collaborator
Author
|
@ashwing I added a readme file, a guide how to use the python cassettes recoder and how it works. @franciscojavierarceo I believe this could help you to collect cassettes for ogx |
franciscojavierarceo
approved these changes
Jun 17, 2026
ashwing
added a commit
to ashwing/agentic-api
that referenced
this pull request
Jun 17, 2026
…lator Add 10 new cassette tests covering: - All tool_choice modes streaming (auto, required, named, none) - All tool_choice modes non-streaming (validates from_json path) - Reasoning streaming (Qwen3 and GPT-oss) Validates the accumulator correctly handles real multi-tool streaming responses and non-streaming JSON responses from multiple model families. Signed-off-by: Ashwin Giridharan <girida@amazon.com>
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
--toolsand--tool-choiceoptions torecord_cassette.pyto inject tool definitions and tool_choice into requeststool_calls/tools.jsonwith 8 tool definitions (get_weather, get_time, get_stock_price, search_web, translate_text, calculate, send_email, read_file)record_tool_call_cassettes.shto record 8 cassettes covering all four tool_choice modes (auto, none, required, named) × streaming and non-streamingThis recorded cassettes in this PR assist to test #59
How to Record
1. Start vLLM with tool-call support:
vllm serve Qwen/Qwen3-30B-A3B-FP8 \ --tool-call-parser hermes \ --enable-auto-tool-choice \ --port 50502. Run the cassette recorder: