mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-14 09:03:16 +00:00
dc1284d3d2
* fix(otel): distinguish unknown timeout usage from prompt estimates * fix(otel): handle expected tokenizer failures and cover parent spans * fix(otel): validate failure usage inputs at typed boundaries * fix(otel): type Logging.messages for the failed prompt token estimate Declare Logging.messages as Sequence[object] | None at its single __init__ assignment and drop the list TypeAdapter, so the failure estimate reads a typed value without new unknown-type diagnostics. * fix(otel): skip the failure prompt estimate for prompts with attachments Only estimate the failed prompt when every message is plain text, so files, documents and images never reach PDF parsing or media decoding on the failure path. Those requests still report unknown provider usage without an estimate. * fix(otel): count the failed prompt off the event loop for async requests Async failure logging now awaits the existing offload_token_count limiter for the optional prompt estimate, and the sync half of an async request no longer counts inline, so a slow tokenizer load cannot stall other requests. * fix(otel): only count the failed prompt for loggers that receive failures The estimate check now reads general callbacks, the global failure lists through a typed get_failure_callbacks accessor, and the dynamic failure lists, so a logger registered only for success never triggers failure token counting. * fix(otel): return an immutable failure callback snapshot * fix(otel): keep malformed content blocks from breaking failure logging Only compare string block types against the text block table, and run the text-only check inside the estimate's narrow try, so a malformed prompt leaves usage unknown without an estimate instead of interrupting failure callbacks. * fix(otel): stop the token counter from debug-logging raw prompts The failure estimate counts the original prompt, so the counter's debug line could write prompt text to application logs while message logging was off. Drop that line and assert the prompt stays out of debug logs on both routes. * test(otel): pin text-only eligibility and failure callback categories Cover the public has_only_text_content contract for malformed and non-text messages, and check get_callbacks_by_type puts sync and async failure registrations in the failure categories through the public manager APIs. * fix(otel): keep failure logging when the prompt estimate cannot run Return no estimate when the offloaded count hits a worker or tokenizer RuntimeError or OSError, so failure callbacks still run, while cancellation still propagates. Treat SDK Message objects like their dict form when checking whether a prompt is text only. --------- Co-authored-by: Joshua Valluru <326636767+joshua-berri@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| arize | ||
| azure_storage | ||
| bitbucket | ||
| clickhouse | ||
| cloudzero | ||
| code_interpreter_interception | ||
| compression_interception | ||
| datadog | ||
| dotprompt | ||
| email_alerting | ||
| focus | ||
| gcs_bucket | ||
| gcs_pubsub | ||
| generic_api | ||
| gitlab | ||
| helicone | ||
| langfuse | ||
| levo | ||
| litellm_agent | ||
| mavvrik_focus | ||
| newrelic | ||
| open_telemetry | ||
| opik | ||
| otel | ||
| pointfive | ||
| SlackAlerting | ||
| ternary | ||
| vantage | ||
| vector_store_integrations | ||
| websearch_interception | ||
| zerobus | ||
| __init__.py | ||
| conftest.py | ||
| rubrik_test_helpers.py | ||
| test_adaptive_concurrency.py | ||
| test_agentops.py | ||
| test_anthropic_cache_control_hook.py | ||
| test_argilla.py | ||
| test_athina.py | ||
| test_azure_sentinel.py | ||
| test_braintrust_logging.py | ||
| test_braintrust_span_name.py | ||
| test_custom_callback_input.py | ||
| test_custom_guardrail.py | ||
| test_custom_guardrail_post_call_once.py | ||
| test_custom_guardrail_recursion.py | ||
| test_custom_logger.py | ||
| test_custom_prompt_management.py | ||
| test_deepeval.py | ||
| test_dynamodb.py | ||
| test_email_alerting.py | ||
| test_galileo.py | ||
| test_guardrail_logging_sync.py | ||
| test_helicone.py | ||
| test_humanloop.py | ||
| test_lago.py | ||
| test_langfuse.py | ||
| test_langfuse_otel.py | ||
| test_langsmith.py | ||
| test_langsmith_init.py | ||
| test_langtrace.py | ||
| test_lunary.py | ||
| test_mlflow.py | ||
| test_openmeter.py | ||
| test_opentelemetry.py | ||
| test_opentelemetry_dynamic_imports.py | ||
| test_opentelemetry_request_spans.py | ||
| test_opik_utils.py | ||
| test_otel_guardrail_violation_spans.py | ||
| test_otel_team_attributes_matrix.py | ||
| test_performance_alert_notifications.py | ||
| test_posthog.py | ||
| test_prometheus_api_promql_escape.py | ||
| test_prometheus_budget_metric_guard.py | ||
| test_prometheus_budget_metrics_db_lookups.py | ||
| test_prometheus_budget_metrics_timeout.py | ||
| test_prometheus_cache_metrics.py | ||
| test_prometheus_caller_identity.py | ||
| test_prometheus_carried_budget_state.py | ||
| test_prometheus_client_ip_user_agent.py | ||
| test_prometheus_custom_metadata_label_counts.py | ||
| test_prometheus_deployment_state_proxy_rejects.py | ||
| test_prometheus_end_user_cardinality.py | ||
| test_prometheus_input_sequence_length_label.py | ||
| test_prometheus_invalid_key_filtering.py | ||
| test_prometheus_labels.py | ||
| test_prometheus_mcp_tool_metrics.py | ||
| test_prometheus_media_generation_metrics.py | ||
| test_prometheus_metric_name_consistency.py | ||
| test_prometheus_metrics_endpoint.py | ||
| test_prometheus_missing_metrics.py | ||
| test_prometheus_none_metadata.py | ||
| test_prometheus_overhead_with_guardrails.py | ||
| test_prometheus_queue_guardrail_metrics.py | ||
| test_prometheus_rate_limit_labels.py | ||
| test_prometheus_remaining_tokens_router_fallback.py | ||
| test_prometheus_requested_model_cardinality.py | ||
| test_prometheus_series_cardinality.py | ||
| test_prometheus_service_tier_label.py | ||
| test_prometheus_services.py | ||
| test_prometheus_spend_capture_rate.py | ||
| test_prometheus_spend_logs_metadata.py | ||
| test_prometheus_stream_label.py | ||
| test_prometheus_token_detail_metrics.py | ||
| test_prometheus_user_team_metrics.py | ||
| test_prometheus_zero_cost_metric.py | ||
| test_prompt_layer.py | ||
| test_prompt_manager_ssti.py | ||
| test_responses_background_cost.py | ||
| test_rubrik.py | ||
| test_s3.py | ||
| test_s3_v2.py | ||
| test_shadow_eval_logger.py | ||
| test_sqs.py | ||
| test_wandb.py | ||
| test_weave_otel.py | ||