litellm/tests/integration/observability
yucheng-berri 9f115be88d
fix(bedrock)!: scan Claude invoke-with-response-stream passthrough output with post_call guardrails (#46524)
* fix(bedrock): scan Claude invoke-with-response-stream passthrough frames with post_call guardrails (LIT-9618)

Invoke streams of Claude models now go through the same frame-by-frame relay as
converse-stream. Each chunk frame's Anthropic event is scanned by the /v1/messages
stream translation, a block ends the stream with an AWS exception frame, and a held
stream gets its masks written back into re-encoded chunk frames. Claude is told by
its model id or, behind an application inference profile, by the anthropic_version
its request body carries. Streams of other model families stay as they were

* test(bedrock): cover invoke stream vendor outage, upstream exception and release on scan (LIT-9618)

* fix(bedrock): hold Claude invoke streams for guardrails the relay cannot run and mark each scan as streaming (LIT-9618)

A guardrail released on scan or run in parallel left a Claude invoke-with-response-stream unscanned, while
converse-stream holds the whole stream and scans it once. Claude invoke streams now take the same buffered
path, with the rewrites written back into the chunk frames that carried each text.

Each invoke scan also sends stream true and the events relayed so far as responses, as /v1/messages does,
so a vendor can tie the scans of one streamed reply together.

* refactor(bedrock): mark the request dicts the buffered stream paths hand to post_call hooks (LIT-9618)

* fix(bedrock): scan a Claude invoke stream the upstream breaks off as a finished stream (LIT-9618)

An invoke stream that ended on an upstream exception, without a message_delta stop_reason, was scanned
as still in flight, so its tool input never reached the guardrail and a held stream released it unscanned.
The scan and its scan key now close such a stream the way converse-stream treats the end of its upstream.

* test(bedrock): pass the converse-stream endpoint where the tool call without input test frames its stream (LIT-9618)

* test(bedrock): expect the ValidationException main now returns when a guardrail blocks a Claude invoke stream before its first frame (LIT-9618)

* test(bedrock): type the Claude invoke event helpers in the passthrough guardrail tests

* test(bedrock): type the remaining parameters of the Claude invoke stream tests

* refactor(bedrock): bind the buffered invoke rewrite in its condition

---------

Co-authored-by: yucheng-berri <293926326+yucheng-berri@users.noreply.github.com>
2026-10-17 01:17:19 -07:00
..
_azure_storage_support.py fix(azure_storage): name Data Lake objects without base64 padding or slashes (#43914) 2026-09-30 18:17:13 -07:00
_logging_only_scope_support.py feat(guardrails): split logging_only_scope direction from input-failure policy (#45709) 2026-10-10 01:46:39 -07:00
_openinference_support.py fix(cache): keep cache hits free of unset fields, and follow intentional behavior changes in CircleCI suites (#46359) 2026-10-14 08:56:05 -07:00
_s3_v2_support.py fix(s3_v2): upload fresh events first, drop terminal failures and hour-old retries by default, opt-in adaptive concurrency (#43022) 2026-09-26 14:58:28 -07:00
_ternary_support.py feat(focus): add ternary destination for FOCUS export (#46106) 2026-10-12 22:52:40 -07:00
azure_dispatch_support.py fix(guardrails): restore Azure guardrail get_user_prompt dispatch and allow logging (#44067) 2026-10-01 23:30:32 -07:00
conftest.py fix(ci): isolate integration workers and repair test fixtures (#45863) 2026-10-11 01:56:02 -07:00
logging_worker_drain_canary.py test: migrate SDK and proxy-booting legacy CircleCI tests to their tiers (#45758) 2026-10-11 00:17:21 -07:00
test_akto_logging_only.py feat(guardrails): support logging_only mode for the Akto guardrail (#45461) 2026-10-08 17:28:08 -07:00
test_apply_guardrail_endpoint.py fix(cache): keep cache hits free of unset fields, and follow intentional behavior changes in CircleCI suites (#46359) 2026-10-14 08:56:05 -07:00
test_arize_otel_v2_openinference_chaos.py test(integration): give chaos and timing tests a harness API and gate raw signals (#46031) 2026-10-12 05:27:33 -07:00
test_arize_otel_v2_openinference_family.py fix(otel): emit OpenInference tool calls and metadata on Arize OTel v2 spans (#43698) 2026-10-08 15:53:07 -07:00
test_arize_otel_v2_openinference_modes.py fix(ci): isolate integration workers and repair test fixtures (#45863) 2026-10-11 01:56:02 -07:00
test_arize_otel_v2_openinference_sad_edge.py fix(otel): emit OpenInference tool calls and metadata on Arize OTel v2 spans (#43698) 2026-10-08 15:53:07 -07:00
test_arize_otel_v2_openinference_spans.py fix(proxy): classify /v1/messages pass-through streams as Anthropic on any host (#45602) 2026-10-09 11:57:03 -07:00
test_azure_content_safety_audit.py test(integration): give chaos and timing tests a harness API and gate raw signals (#46031) 2026-10-12 05:27:33 -07:00
test_azure_content_safety_dispatch.py fix(guardrails): restore Azure guardrail get_user_prompt dispatch and allow logging (#44067) 2026-10-01 23:30:32 -07:00
test_azure_content_safety_dispatch_resilience.py test(integration): hand every harness server a port from one per-worker block (#46761) 2026-10-15 16:56:40 -07:00
test_azure_content_safety_endpoints.py fix(guardrails): scan Responses API input in Azure Prompt Shield (#43786) 2026-09-30 22:48:20 -07:00
test_azure_storage_chaos.py test(integration): give chaos and timing tests a harness API and gate raw signals (#46031) 2026-10-12 05:27:33 -07:00
test_azure_storage_client_ttl.py fix(azure_storage): keep the DataLakeServiceClient alive until its TTL elapses (#43082) 2026-09-30 18:50:15 -07:00
test_azure_storage_file_names.py fix(azure_storage): keep client call ids from sharing one Data Lake file (#44099) 2026-10-01 23:23:37 -07:00
test_batch_line_items_cold_storage.py test(integration): fix seven CircleCI integration tests that race or assume a worker spread (#47001) 2026-10-16 22:45:29 +00:00
test_bedrock_converse_stream_post_call_guardrail.py fix(bedrock)!: stream Converse passthrough frames through post_call guardrails instead of buffering (#46307) 2026-10-17 00:53:53 -07:00
test_bedrock_error_request_id.py fix(responses): preserve provider request IDs in streaming failure logs (#45453) 2026-10-16 00:29:11 -07:00
test_bedrock_guardrail_attachments.py fix(ci): isolate integration workers and repair test fixtures (#45863) 2026-10-11 01:56:02 -07:00
test_bedrock_invoke_stream_post_call_guardrail.py fix(bedrock)!: scan Claude invoke-with-response-stream passthrough output with post_call guardrails (#46524) 2026-10-17 01:17:19 -07:00
test_cache_hit_guardrail_metrics.py test(integration): remove BUG skip for 1 test that passes on main (#46937) 2026-10-16 12:39:35 -07:00
test_cache_hit_guardrail_metrics_chaos.py test(integration): give chaos and timing tests a harness API and gate raw signals (#46031) 2026-10-12 05:27:33 -07:00
test_callback_delivery.py fix(openai_like)!: surface provider response headers on non-streaming chat completions (#46928) 2026-10-16 17:25:50 -07:00
test_content_filter_logging_only.py fix(guardrails): record every content filter match in logging_only and offer the mode in the UI (#46673) 2026-10-16 00:37:03 -07:00
test_custom_logger_redaction.py fix(logging): redact nested callback input and provider response fields (#45923) 2026-10-13 12:25:56 -07:00
test_datadog_logging_delivery.py test: migrate legacy unit dirs and unrun folders into tests/unit, tests/integration and tests/e2e (#45940) 2026-10-11 06:24:57 -07:00
test_file_usage_counter_span.py feat(proxy): cap batch file records, daily batch uploads, and per-file downloads (#43632) 2026-10-06 03:06:36 +00:00
test_generic_guardrail_api_wire.py fix(guardrails): accept Gemini tools in generic_guardrail_api, add opt-in forward_messages_as_sent, name the error type on fail-open (#46338) 2026-10-16 14:52:35 -07:00
test_grayswan_wire.py fix(grayswan): send request conversation and tool calls to post-call monitor (#43770) 2026-09-30 17:52:53 -07:00
test_grayswan_wire_chaos.py test(integration): give chaos and timing tests a harness API and gate raw signals (#46031) 2026-10-12 05:27:33 -07:00
test_guardrail_attachment.py test: replace 61 live logging and otel tests with offline unit and integration coverage (#45362) 2026-10-08 15:55:57 -07:00
test_guardrail_effects.py test(integration): hand every harness server a port from one per-worker block (#46761) 2026-10-15 16:56:40 -07:00
test_guardrail_load_balancing.py test: migrate SDK and proxy-booting legacy CircleCI tests to their tiers (#45758) 2026-10-11 00:17:21 -07:00
test_guardrail_stream_scope.py feat(guardrails): per-mode stream_scope with bedrock stream and pass-through fixes (#43801) 2026-10-08 13:46:53 -07:00
test_guardrail_stream_scope_chaos.py test(integration): hand every harness server a port from one per-worker block (#46761) 2026-10-15 16:56:40 -07:00
test_guardrail_stream_scope_matrix.py test(integration): update stale CircleCI integration expectations (#46570) 2026-10-14 18:21:59 -07:00
test_guardrail_timeout_all_providers.py feat(guardrails): add Wingback guardrail integration (#46136) 2026-10-12 22:18:10 -07:00
test_langfuse_delivery.py test(integration): isolate shared proxy state behind six order-dependent flakes (#46172) 2026-10-13 09:55:11 -07:00
test_langsmith_logging_delivery.py test: migrate legacy unit dirs and unrun folders into tests/unit, tests/integration and tests/e2e (#45940) 2026-10-11 06:24:57 -07:00
test_langtrace_delivery.py test(integration): hand every harness server a port from one per-worker block (#46761) 2026-10-15 16:56:40 -07:00
test_logging_only_scope_chaos.py test(integration): hand every harness server a port from one per-worker block (#46761) 2026-10-15 16:56:40 -07:00
test_logging_only_scope_config.py fix(guardrails): record every content filter match in logging_only and offer the mode in the UI (#46673) 2026-10-16 00:37:03 -07:00
test_logging_only_scope_runtime.py feat(guardrails): split logging_only_scope direction from input-failure policy (#45709) 2026-10-10 01:46:39 -07:00
test_logging_worker_drain.py test: migrate SDK and proxy-booting legacy CircleCI tests to their tiers (#45758) 2026-10-11 00:17:21 -07:00
test_otel_conversation_id.py test(integration): give chaos and timing tests a harness API and gate raw signals (#46031) 2026-10-12 05:27:33 -07:00
test_otel_excluded_services.py test(integration): isolate shared proxy state behind six order-dependent flakes (#46172) 2026-10-13 09:55:11 -07:00
test_otel_excluded_services_matrix.py test(integration): wait for the gen-AI span before reading the excluded-services operator trace (#46846) 2026-10-15 22:35:23 -07:00
test_otel_team_capture_message_content.py feat(otel)!: let a team capture_message_content override the global setting for its OTel v2 destination (#44264) 2026-10-10 13:52:32 -07:00
test_otel_text_completion_choices.py fix(otel): keep text completion choice fields beside the synthesized message (#42537) 2026-09-22 14:24:32 -07:00
test_otel_trace_response_header.py feat(proxy): return the W3C traceresponse header on traced responses (#42079) 2026-10-14 18:12:34 -07:00
test_otel_v1_request_trace.py fix(caching): key response cache by router model group in litellm_metadata (#44542) 2026-10-05 17:06:21 +00:00
test_passthrough_upstream_error_chaos.py test(integration): hand every harness server a port from one per-worker block (#46761) 2026-10-15 16:56:40 -07:00
test_passthrough_upstream_error_visibility.py test(integration): cover pass_through endpoint contracts (#44690) 2026-10-14 07:38:17 +00:00
test_presidio_entity_masking.py test(integration): cover guardrails_policies endpoint contracts (#44722) 2026-10-14 04:07:26 +00:00
test_presidio_streaming_output.py test(integration): give chaos and timing tests a harness API and gate raw signals (#46031) 2026-10-12 05:27:33 -07:00
test_prometheus_project_alias_label.py fix(prometheus): skip custom metadata labels a metric already carries (#46267) 2026-10-13 18:20:52 -07:00
test_prometheus_request_metrics.py test: replace 61 live logging and otel tests with offline unit and integration coverage (#45362) 2026-10-08 15:55:57 -07:00
test_prometheus_series_cap.py feat(prometheus): cap series per metric for every labeled metric (#44420) 2026-10-06 01:28:44 +00:00
test_prometheus_series_cap_chaos.py test(integration): give chaos and timing tests a harness API and gate raw signals (#46031) 2026-10-12 05:27:33 -07:00
test_prometheus_shared_custom_labels.py test(integration): wait on the right signal in five flaky integration contracts (#46737) 2026-10-15 13:48:51 -07:00
test_realtime_guardrail_translation.py test: migrate tests/llm_translation into unit, integration and e2e tiers (#45759) 2026-10-11 07:58:53 +00:00
test_s3_v2_flush_surfaces.py fix(s3_v2): upload fresh events first, drop terminal failures and hour-old retries by default, opt-in adaptive concurrency (#43022) 2026-09-26 14:58:28 -07:00
test_s3_v2_partition_granularity.py test(integration): give chaos and timing tests a harness API and gate raw signals (#46031) 2026-10-12 05:27:33 -07:00
test_s3_v2_streaming_failure_dedupe.py test(integration): cut CircleCI proxy boot time with concurrent worker stacks and single-worker test proxies (#46037) 2026-10-12 09:48:42 -07:00
test_s3_v2_upload_fanout.py test(integration): fix seven CircleCI integration tests that race or assume a worker spread (#47001) 2026-10-16 22:45:29 +00:00
test_signoz_delivery.py test(integration): remove BUG skips for 3 tests that pass on main (#46725) 2026-10-15 18:50:26 +00:00
test_straiker_v3_platform.py test(integration): hand every harness server a port from one per-worker block (#46761) 2026-10-15 16:56:40 -07:00
test_ternary_focus_export.py feat(focus): add ternary destination for FOCUS export (#46106) 2026-10-12 22:52:40 -07:00
test_wingback_guardrail.py feat(guardrails): add Wingback guardrail integration (#46136) 2026-10-12 22:18:10 -07:00
test_xecguard_wire.py refactor(types): replace Any with proven types in 7 files (#43704) 2026-09-29 06:12:58 -07:00