mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-16 04:29:31 +00:00
c5ac1845b0
* fix(langfuse): log token usage for /v1/responses calls ResponseAPIUsage exposes input_tokens/output_tokens, so the Langfuse generation logger read prompt_tokens/completion_tokens as 0 while cost was still correct. Normalize the usage with ResponseAPILoggingUtils._transform_response_api_usage_to_chat_usage before extracting usage_details. Resolves LIT-8238 Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(langfuse): adapt responses-api usage regression test to langfuse v4 spans The v4 migration exports usage_details as an OTEL span attribute via an in-memory exporter instead of a mocked generation() call. Assert on the exported span's langfuse.observation.usage_details with the same token counts. Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(langfuse): log token usage for streamed /v1/responses calls An assembled /v1/responses stream reaches the logger with its usage stored as a plain dict of chat fields, which the attribute reads saw as zero. Route both ResponseAPIUsage and that dict through one normalizer. * fix(langfuse): keep generations whose usage dict fails validation; cover streaming in the e2e A usage dict whose token counts are not integers falls back to the raw object, so the generation is still logged with zero usage instead of being dropped. The live e2e now runs streamed and non-streamed /v1/responses. * ci: re-run the e2e gate * test(langfuse): run the real prompt helper and label the responses usage e2e cases Drop the _add_prompt_to_generation_params pass-through patch from the Responses usage unit tests so the real helper runs with the empty metadata they already pass. Declare a Subject on both e2e parametrizations (observability, /v1/responses, openai, stream and nonstream). --------- Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: yucheng-berri <293926326+yucheng-berri@users.noreply.github.com>
31 lines
8.2 KiB
YAML
31 lines
8.2 KiB
YAML
# Logging integration delivery (behavior features). Grounded in litellm/integrations/.
|
|
- {id: logging.s3.success.writes_object, module: logging, tier: P0, event: success, assertions: [writes_object], exercised_on: [chat_completions, messages, embeddings], source: "integrations/s3_v2.py", rationale: "Primary audit trail; batch flush no-drop"}
|
|
- {id: logging.s3.failure.writes_object, module: logging, tier: P0, event: failure, assertions: [writes_object], exercised_on: [chat_completions, messages], source: "integrations/s3_v2.py", rationale: "Failed calls persisted for compliance"}
|
|
- {id: logging.s3.success.partition_layout, module: logging, tier: P1, event: success, assertions: [object_key_layout], exercised_on: [chat_completions], source: "integrations/s3_v2.py / LIT-8985", rationale: "s3_partition_granularity picks the date or date/hour folder every downstream query and lifecycle rule reads"}
|
|
- {id: logging.gcs_bucket.success.writes_object, module: logging, tier: P0, event: success, assertions: [writes_object], exercised_on: [chat_completions, messages, embeddings], source: "integrations/gcs_bucket/gcs_bucket.py", rationale: "GCS parallel to S3"}
|
|
- {id: logging.datadog.success.exports_metric, module: logging, tier: P0, event: success, assertions: [exports_metric], exercised_on: [chat_completions, messages, responses, embeddings], source: "integrations/datadog/datadog.py", rationale: "Powers dashboards/alerts; cardinality regressions common"}
|
|
- {id: logging.datadog.stream.exports_metric, module: logging, tier: P0, event: stream, assertions: [exports_metric], exercised_on: [chat_completions, messages, responses], source: "integrations/datadog/datadog.py", rationale: "Streaming aggregates usage after the last chunk; delivery and cost must survive that path"}
|
|
- {id: logging.datadog.failure.exports_metric, module: logging, tier: P0, event: failure, assertions: [exports_metric], exercised_on: [chat_completions], source: "integrations/datadog/datadog.py", rationale: "Failure metrics for alerting/SLO"}
|
|
- {id: logging.datadog.stream_failure.exports_metric, module: logging, tier: P0, event: failure, assertions: [exports_metric], exercised_on: [chat_completions], source: "litellm_core_utils/litellm_logging.py", rationale: "Streamed failures re-enter the failure handler once per retry on the same logging object; dedup must hold on the stream path too (#42988)"}
|
|
- {id: logging.prometheus.success.exports_metric, module: logging, tier: P0, event: success, assertions: [exports_metric], exercised_on: [chat_completions, messages, embeddings], source: "integrations/prometheus.py", rationale: "Standard OSS metrics; per-key cardinality (existing e2e)"}
|
|
- {id: logging.prometheus.success.records_queue_time, module: logging, tier: P1, event: success, assertions: [records_queue_time], exercised_on: [chat_completions], source: "integrations/prometheus.py / LIT-2034", fail_before_fix: proven, rationale: "Queue time feeds saturation alerting; the family stayed registered while no observation was ever recorded, so presence alone is not the contract"}
|
|
- {id: logging.otel.success.exports_metric, module: logging, tier: P0, event: success, assertions: [exports_metric], exercised_on: [chat_completions, messages, responses, embeddings], source: "integrations/otel/logger.py", rationale: "OTEL spans on every call path"}
|
|
- {id: logging.otel.stream.exports_metric, module: logging, tier: P0, event: stream, assertions: [exports_metric], exercised_on: [chat_completions, messages, responses], source: "integrations/otel/logger.py", rationale: "Streaming closes the LLM span from the stream path; historically prone to duplicate/orphaned spans"}
|
|
- {id: logging.otel.stream.records_ttft, module: logging, tier: P1, event: stream, assertions: [records_ttft], exercised_on: [chat_completions, messages, responses], source: "integrations/otel/mappers/genai.py", rationale: "TTFT is the streaming latency SLI; a zero or span-length value silently corrupts dashboards"}
|
|
- {id: logging.otel.failure.exports_metric, module: logging, tier: P0, event: failure, assertions: [exports_metric], exercised_on: [chat_completions, messages], source: "integrations/otel/logger.py", rationale: "Error spans for observability continuity"}
|
|
- {id: logging.braintrust.success.logs_spend, module: logging, tier: P1, event: success, assertions: [logs_spend], exercised_on: [chat_completions, messages], source: "integrations/braintrust_logging.py", rationale: "Evals platform spend"}
|
|
- {id: logging.langsmith.success.logs_spend, module: logging, tier: P1, event: success, assertions: [logs_spend], exercised_on: [chat_completions, messages], source: "integrations/langsmith.py", rationale: "LangChain ecosystem"}
|
|
- {id: logging.langsmith.success.serializes_non_native_metadata, module: logging, tier: P1, event: success, assertions: [serializes_non_native_metadata], exercised_on: [sdk], source: "integrations/langsmith.py", rationale: "datetime/Decimal/UUID metadata used to TypeError in json.dumps and drop the whole batch (LIT-8310)"}
|
|
- {id: logging.arize.success.logs_spend, module: logging, tier: P1, event: success, assertions: [logs_spend], exercised_on: [chat_completions, embeddings], source: "integrations/arize/arize.py", rationale: "ML-ops observability"}
|
|
- {id: logging.mlflow.success.logs_spend, module: logging, tier: P1, event: success, assertions: [logs_spend], exercised_on: [chat_completions], source: "integrations/mlflow.py", rationale: "Experiment tracking cost/run"}
|
|
- {id: logging.opik.success.logs_spend, module: logging, tier: P1, event: success, assertions: [logs_spend], exercised_on: [chat_completions], source: "integrations/opik/opik.py", rationale: "Eval platform spend/case"}
|
|
- {id: logging.openmeter.success.exports_metric, module: logging, tier: P1, event: success, assertions: [exports_metric], exercised_on: [chat_completions, messages, embeddings], source: "integrations/openmeter.py", rationale: "Usage metering for billing"}
|
|
- {id: logging.literal_ai.success.logs_spend, module: logging, tier: P1, event: success, assertions: [logs_spend], exercised_on: [chat_completions, messages], source: "integrations/literal_ai.py", rationale: "Tracing platform spend"}
|
|
- {id: logging.posthog.success.exports_metric, module: logging, tier: P1, event: success, assertions: [exports_metric], exercised_on: [chat_completions, messages], source: "integrations/posthog.py", rationale: "Product analytics batching"}
|
|
- {id: logging.azure_storage.success.writes_object, module: logging, tier: P1, event: success, assertions: [writes_object], exercised_on: [chat_completions, messages], source: "integrations/azure_storage/azure_storage.py", rationale: "Azure blob for enterprise"}
|
|
- {id: logging.cloudzero.success.logs_spend, module: logging, tier: P1, event: success, assertions: [logs_spend], exercised_on: [chat_completions], source: "integrations/cloudzero/cloudzero.py", rationale: "Cost ops correlation"}
|
|
- {id: logging.focus.success.writes_object, module: logging, tier: P1, event: success, assertions: [writes_object], exercised_on: [chat_completions, messages], source: "integrations/focus/focus_logger.py", rationale: "Cost mgmt multi-destination export"}
|
|
- {id: logging.niche_integrations.success.logs_spend, module: logging, tier: P2, event: success, assertions: [logs_spend], exercised_on: [chat_completions], source: grammar, rationale: "SMOKE cohort: athina/galileo/deepeval/langtrace/weave/lunary/humanloop/traceloop/helicone/argilla/newrelic/sqs/supabase/dynamodb/agentops/lago/etc"}
|
|
- {id: logging.niche_integrations.failure.logs_spend, module: logging, tier: P2, event: failure, assertions: [logs_spend], exercised_on: [chat_completions], source: grammar, rationale: "SMOKE niche failure path"}
|
|
- {id: logging.langfuse.success.logs_spend, module: logging, tier: P1, event: success, assertions: [logs_spend], exercised_on: [chat_completions], source: "integrations/langfuse/langfuse_otel.py", rationale: "Team-scoped Langfuse delivery via /team/callback; LangChain-ecosystem evals spend"}
|
|
- {id: logging.langfuse.success.logs_usage, module: logging, tier: P1, event: success, assertions: [logs_usage], exercised_on: [responses], source: "integrations/langfuse/langfuse.py", rationale: "Classic Langfuse SDK generations must carry token usage on the /v1/responses path; ResponseAPIUsage read as chat Usage logs all zeros (LIT-8238)"}
|