mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-14 23:21:35 +00:00
2eab9ee2c0
* perf: reduce per-request and per-chunk overhead across Anthropic streaming hot paths
- Introduce pure-text fast-path in `_build_complete_streaming_response` that collapses O(N) `content_block_delta` events into a single equivalent SSE event before conversion, eliminating per-output-token Pydantic `ModelResponseStream` construction; non-text streams (tool_use, thinking, citations) fall back to the unchanged legacy path
- Skip agentic streaming wrapper entirely when no callback overrides `async_should_run_agentic_loop`; the wrapper buffered every chunk and rebuilt the SSE response only to call hooks that all return `(False, {})` — a pure no-op for the default config
- Serialize request body once (`json.dumps`) for both the pre-call log input and the wire, instead of twice; avoids a full O(payload) scan per request, significant for long-context Claude Code histories
- Add fast path in `async_streaming_data_generator` that bypasses the per-chunk `async_post_call_streaming_hook` coroutine await, response-string materialization, and cost-injection call when no callback/guardrail/cost-injection is active (the default config)
- Resolve `_DD_STREAMING_TRACE_ENABLED` once at import time; eliminate per-chunk `NullSpan` context manager allocation when Datadog tracing is disabled (the default)
- Memoize `get_type_hints(AnthropicMessagesRequestOptionalParams)` with `@lru_cache(maxsize=1)` — resolves once per process instead of once per `/v1/messages` request (~80µs each)
- Hoist `cost_injection_active` out of the per-chunk loop in `chunk_processor`; eliminates repeated `getattr` + endpoint-type checks on every streamed byte chunk
- Extract `_build_passthrough_logging_result` from `_route_streaming_logging_to_handler` as a standalone static method to facilitate future off-loop dispatch
- Convert `async_sse_data_generator` from an `async for: yield` trampoline to a direct return of the underlying generator, removing one async-generator layer per streamed chunk
- Skip redundant `strip_empty_text_blocks_from_anthropic_messages` scan in `anthropic_messages_handler` when the async wrapper already sanitized (signalled via `_litellm_messages_presanitized` sentinel, popped before reaching provider params)
- Gate debug log `f-string` evaluation behind `isEnabledFor(DEBUG)` in both the streaming generator and the transformation layer to avoid serializing entire message payloads on every request at non-debug log levels
- Add benchmark script (`scripts/benchmark_anthropic_messages_perf.py`) with a local mock Anthropic SSE provider for reproducible TTFT and TPM measurement across commits/branches
- Add parity tests asserting fast-path and legacy-path produce byte-identical logged/billed payloads, plus unit tests for agentic hook detection, pre-serialized body reuse, and memoized key resolution
* perf: address greptile review for anthropic streaming hot path
- Bail to legacy in `_collapse_pure_text_chunks` when content_block_delta
events from different block indexes are observed without an intervening
flush. Anthropic sends blocks strictly sequentially, but defensive bail
prevents silent text-merging if the protocol ever interleaves.
- Replace leaf-class `__dict__` check for `async_post_call_streaming_hook`
in `_callback_capabilities` with a function-identity comparison that
walks the MRO. A vendor base class can carry the override and the
registered class can add nothing else; before this PR the hook was
unconditionally invoked, so an inherited-override miss would silently
drop the hook on the streaming path.
- Add unit tests for both behaviors.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(mypy): narrow model_name to str in cost-injection branch
The hoisted cost_injection_active flag in chunk_processor encodes the
`bool(model_name)` requirement but mypy can't track that invariant
through the local, so the per-chunk `_process_chunk_with_cost_injection(
chunk, model_name)` calls flagged Optional[str] vs str. Pin a typed
non-None local inside the cost-injection branch so mypy narrows
correctly without changing runtime behavior.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Yassin Kortam <yassinkortam@g.ucla.edu>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|---|---|---|
| .. | ||
| _experimental/mcp_server | ||
| agent_endpoints | ||
| anthropic_endpoints | ||
| auth | ||
| client | ||
| common_utils | ||
| db | ||
| discovery_endpoints | ||
| experimental/mcp_server | ||
| google_endpoints | ||
| guardrails | ||
| health_endpoints | ||
| hooks | ||
| image_endpoints | ||
| management_endpoints | ||
| management_helpers | ||
| memory | ||
| middleware | ||
| openai_files_endpoint | ||
| pass_through_endpoints | ||
| policy_engine | ||
| prompts | ||
| public_endpoints | ||
| rag_endpoints | ||
| realtime_endpoints | ||
| response_api_endpoints | ||
| spend_tracking | ||
| test_configs | ||
| types_utils | ||
| ui_crud_endpoints | ||
| vector_store_endpoints | ||
| __init__.py | ||
| conftest.py | ||
| test_aiohttp_cleanup_closed.py | ||
| test_aiohttp_session_recovery.py | ||
| test_api_key_masking_in_errors.py | ||
| test_audio_speech_prometheus_hooks.py | ||
| test_batch_expiry.py | ||
| test_batch_metadata_none_fix.py | ||
| test_batch_retrieve_bedrock.py | ||
| test_budget_reservation.py | ||
| test_caching_routes.py | ||
| test_chat_completion_metadata.py | ||
| test_common_request_processing.py | ||
| test_component_allowlists.py | ||
| test_cors_config.py | ||
| test_custom_proxy.py | ||
| test_dynamic_mcp_route.py | ||
| test_empty_model_list.py | ||
| test_enforce_user_param.py | ||
| test_fallback_management_endpoints.py | ||
| test_fastapi_offline_routes.py | ||
| test_filter_models_by_team_access_group.py | ||
| test_health_check_functions.py | ||
| test_health_check_max_tokens.py | ||
| test_langfuse_passthrough_security.py | ||
| test_lazy_openapi_snapshot.py | ||
| test_litellm_pre_call_utils.py | ||
| test_max_budget_env_var.py | ||
| test_mcp_asgi_response.py | ||
| test_model_dump_with_preserved_fields.py | ||
| test_model_id_header_propagation.py | ||
| test_model_info_default_limits.py | ||
| test_model_level_guardrails.py | ||
| test_openapi_schema_validation.py | ||
| test_pricing_field_strip.py | ||
| test_prometheus_cleanup.py | ||
| test_provider_url_destination_guard.py | ||
| test_proxy_cli.py | ||
| test_proxy_logging_hook_detection.py | ||
| test_proxy_server.py | ||
| test_proxy_types.py | ||
| test_proxy_utils.py | ||
| test_pyroscope.py | ||
| test_redis_auth_cache_flag.py | ||
| test_response_model_sanitization.py | ||
| test_route_a2a_models.py | ||
| test_route_llm_request.py | ||
| test_sensitive_route_auth.py | ||
| test_shared_health_check.py | ||
| test_spend_log_cleanup.py | ||
| test_swagger_chat_completions.py | ||
| test_team_member_update.py | ||
| test_team_org_move.py | ||
| test_tools_allowlist_enforcement.py | ||
| test_update_llm_router_resilience.py | ||
| test_utils.py | ||