🐛 Bug Report: Gemini streaming raises TypeError after the last chunk when usage metadata has no candidates_token_count

Aperta
#4,711 0 commenti 0 reazioni 0 assegnatari Vedi su GitHub

I maintainer di solito rispondono entro 1 giorno

@prassu017 ci sta già lavorando.

Dal 17/11/2026.

  • #4712 di @prassu017 — aperta

Valutazione

Difficoltà
3/5
Tempo stimato
1-2 giorni
Idoneità per principianti
35/100
Tipo di issue
Bug
Chiarezza
Specificata chiaramente
Stato di attività
Ferma
Stack tecnologico
python

Direzione di ricerca

Start with the usage calculation and histogram recording in packages/opentelemetry-instrumentation-google-generativeai/opentelemetry/instrumentation/google_generativeai/span_utils.py and the sync and async stream finalization in __init__.py. Reproduce the issue with the synthetic response described here, then check the Google Generative AI instrumentation tests for coverage of both wrappers. Done means streams finish normally and spans end when candidate token counts are absent; linked PR #4712 is already open.

Scritto dal modello di indicizzazione a partire dal testo della issue.

Descrizione

Hullo folks,

I’m doing some research for Tessl Code Review and we ran it against your repo. It flagged a potential issue, and I figured it made sense to share it with you:

Which component is this bug for?

Google Generative AI Instrumentation

📜 Description

With metrics enabled, a Gemini stream whose last chunk has usage metadata but no candidates_token_count raises TypeError when the caller tries to finish iterating.

The last chunk has already been yielded. The failure occurs while recording the output-token histogram, and span.end() is not reached. Both sync and async stream wrappers reproduce this.

👟 Reproduction steps

This uses real SDK response objects and a real OpenTelemetry histogram, with a synthetic stream and no Gemini API call:

from google.genai.types import (
    GenerateContentResponse, GenerateContentResponseUsageMetadata,
)
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.metrics import MeterProvider
from opentelemetry.instrumentation.google_generativeai import (
    _build_from_streaming_response,
)

tracer = TracerProvider().get_tracer("repro")
meter = MeterProvider().get_meter("repro")
histogram = meter.create_histogram("gen_ai.client.token.usage")
chunk = GenerateContentResponse(
    usage_metadata=GenerateContentResponseUsageMetadata(
        prompt_token_count=2, total_token_count=2,
    )
)
span = tracer.start_span("repro")
stream = _build_from_streaming_response(
    span, iter([chunk]), "gemini-test", None, histogram,
)
assert next(stream) is chunk
try:
    next(stream)  # Expected: StopIteration
finally:
    print("span still recording:", span.is_recording())
    span.end()
👍 Expected behavior

The stream ends normally, the span ends, and missing token counts do not become non-numeric histogram measurements.

👎 Actual Behavior
span still recording: True
TypeError: must be real number, not NoneType

Controls tested:

Final usage / metrics Result
Missing candidate count, no thoughts, metrics on TypeError
Candidate count 0, metrics on Clean end
Missing candidate count, thoughts count 3, metrics on Clean end
Missing candidate count, metrics off Clean end

The async wrapper produced the same TypeError after yielding its final chunk.

🤖 Python Version

3.13.11 on macOS arm64.

📃 Additional context

Tested installed versions:

  • opentelemetry-instrumentation-google-generativeai==0.63.1
  • google-genai==3.4.0
  • opentelemetry-sdk==1.45.2

The current source at 864f8591081251a40a40e0bb06a4d8084c3664d2 retains the same path:

This is a local wrapper reproduction with synthetic response data, not a live provider reproduction. #4603 handles thinking tokens, but when both candidate and thinking counts are absent, output_tokens still stays None. Skipping absent metrics or normalizing them according to the intended usage semantics would avoid the exception.

👀 Duplicate check
  • Checked existing issues and related token-usage PRs; did not find this exact report.

I’m with Tessl. Tessl reviews code using repository-level context and specific review lenses that improve over time through feedback. That’s how this finding surfaced. We’re just getting started and want to offer the tool free to open-source projects. If this is useful, happy to give you access.

Baptiste

Lingua principale
Python
Stelle
7.5k
Fork
1.2k
Merge medio
1g 23h
PR unite (30g)
3

Preparare l'ambiente

Come iniziare

  1. Leggi tutta la issue e poi la guida ai contributi del progetto.
  2. Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
  3. Fai un fork del repository e lavora su un branch.
  4. Apri una pull request che faccia riferimento al numero della issue.

Altre issue di traceloop/openllmetry

Tutte le issue di traceloop/openllmetry

Issue simili

Altre issue su Python

Ricevi le nuove issue nella tua casella

Un breve riepilogo di issue GitHub adatte ai principianti.