fix(llm): stream_options.include_usage so cost tracking actually fires#119
Merged
Conversation
call_model_stream_raw now defaults stream_options to
{"include_usage": True}. Without it, vLLM (and any OpenAI-compatible
server) never emits a terminal usage chunk on streaming responses,
which means StreamMetrics.prompt_tokens / completion_tokens stay None
and OpenAIChatServer._persist_cost_data returns early -- cost_data
accumulators stayed empty in production despite full unit-test green.
Surfaced during the cluster smoke for #116. setdefault semantics so
callers can opt out by passing stream_options={include_usage: False}.
Bumps fipsagents to 0.14.1.
Closes #118.
Assisted-by: Claude Code (Opus 4.7)
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
LLMClient.call_model_stream_rawwas never asking vLLM for the terminal usage chunk, soOpenAIChatServer._persist_cost_data(added in #117) returned early on every real call andcost_dataaccumulators stayed empty in deployed agents. Setsstream_options={\"include_usage\": True}by default.setdefaultsemantics so callers can opt out.Surfaced during the cluster smoke for #116. Closes #118.
Test plan
test_llm.py— default-on and caller-overrideBumps fipsagents to 0.14.1.
Closes #118.
Assisted-by: Claude Code (Opus 4.7)