mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-14 23:21:35 +00:00
342d8897b6
* fix(guardrails): walk Responses-API text taxonomy in shared content helpers
Every guardrail sharing litellm/proxy/guardrails/_content_utils.py silently
drops all text on the /v1/responses path. AIM turns it into a loud 422 (
{"error":"No messages in the request"}); every other guardrail (Lakera v2,
Cato, Lasso, Repello, IBM, Azure Content Safety, enterprise secret
detection) scans an empty payload and lets the request through unscanned.
Three defects, all in _content_utils.py:
1. _iter_text_parts_in_content recognised only part.type == "text", but the
Responses API uses input_text (request) and output_text (assistant).
2. _coerce_input_to_messages gated on "every item has a role key"; any
Responses input list containing a function_call or function_call_output
item failed the check and was wrapped as one opaque blob.
3. build_inspection_messages forwarded any role through, including a bare
tool role missing tool_call_id, which validators like AIM's /fw/v1/analyze
reject with a schema error.
Fix walks the actual Responses item taxonomy (message, function_call,
function_call_output, bare content parts and strings), recognises
{text, input_text, output_text} everywhere, and coerces any role outside
{system, user, assistant} to user in the outbound inspection payload.
* style: ruff-format changed guardrail files
* test(guardrails): cover function_call_output string form; drop em-dash in new docstring
* fix(guardrails): map function_call_output straight to user role
Avoids ever materialising a schema-invalid bare tool message. The
downstream role-safety coercion in build_inspection_messages still
guards genuinely caller-supplied non-standard roles (developer,
function, custom values); add a regression test covering that path
so the coercion has real coverage after this simplification.
* test(guardrails): pin chat-completions tool-role coercion in build_inspection_messages
* docs(test): soften AIM-specific claims in LIT-4294 test docstrings
Ryan's review flagged that several test docstrings assert AIM's
/fw/v1/analyze validates + rejects specific schema violations. That
behavior is customer-reported in the LIT-4294 writeup, not directly
verified by us. Rephrase to attribute the AIM 422 to the customer's
writeup and describe the underlying constraint as the OpenAI chat
schema; any downstream API that validates against that schema rejects
the same shape.
* refactor(guardrails): move unsupported-role coercion into AIM only
The generic coercion in build_inspection_messages collapsed any role
outside {system, user, assistant} to user for every caller of the
helper. Combined with the pre-existing apply_redacted_messages_back
write-back behavior in Lakera/AIM/Cato, that turned a loud OpenAI 400
on chat-completions tool-message masking into a silent semantic
corruption of the outbound request (role tool with tool_call_id got
rewritten to bare role user, dropping the assistant + tool_calls
sibling).
AIM specifically requires the coercion because its /fw/v1/analyze
validates the payload against the OpenAI chat schema; other guardrails
either do not validate roles or do their own reconstruction. Move the
coercion to AimGuardrail._build_aim_inspection_messages so the shared
helper keeps caller roles intact and no new cross-guardrail role
corruption is introduced. The pre-existing apply_redacted_messages_back
structural flatten remains as separate follow-up work.
function_call_output items still synthesise role user in the shared
helper because they have no natural role field, which is a different
concern from coercing a caller-supplied role.
* refactor(guardrails): preserve role fidelity in shared _content_utils
Shared inspection helpers should extract text and preserve semantic
role signals; role coercion for third-party schema safety stays inside
the guardrail that needs it (AIM).
Three shared-helper changes:
- Bare content-part dicts (input_text/output_text) with an explicit role
keep it; only role-less parts default to user.
- Responses message items already had their role preserved; the
behavior is now covered by an explicit test.
- function_call_output items default to role tool (semantic equivalent
of the chat-completions tool message shape) instead of role user, so
Responses and chat completions produce symmetric inspection payloads.
A caller-supplied role on the item is still preserved.
AIM's schema-safe coercion in _build_aim_inspection_messages already
handles the resulting role tool: it collapses to user before the POST
to /fw/v1/analyze so AIM's OpenAI-schema validator does not reject the
bare tool message (no tool_call_id can survive the flatten). Added a
regression test in test_aim.py covering that path.
(cherry picked from commit
|
||
|---|---|---|
| .. | ||
| a2a_protocol | ||
| anthropic_interface/exceptions | ||
| caching | ||
| completion_extras | ||
| containers | ||
| enterprise | ||
| expected_fine_tuning_api | ||
| expected_responses_api_request | ||
| experimental_mcp_client | ||
| google_genai | ||
| images | ||
| integrations | ||
| interactions | ||
| litellm_core_utils | ||
| llms | ||
| models | ||
| ocr | ||
| passthrough | ||
| proxy | ||
| repositories | ||
| responses | ||
| router_strategy | ||
| router_utils | ||
| sandbox | ||
| secret_managers | ||
| test_router | ||
| types | ||
| vector_stores | ||
| __init__.py | ||
| conftest.py | ||
| log.txt | ||
| readme.md | ||
| test__types.py | ||
| test_a2a_registry_lookup.py | ||
| test_acompletion_session_reuse_e2e.py | ||
| test_add_deployment_no_master_key.py | ||
| test_aembedding_session_reuse_e2e.py | ||
| test_anthropic_beta_headers_filtering.py | ||
| test_anthropic_skills_transformation.py | ||
| test_anthropic_sonnet_1hr_cache_pricing.py | ||
| test_azure_ad_token_credential_resolution.py | ||
| test_azure_video_router.py | ||
| test_batch_completion_models_all_responses.py | ||
| test_bedrock_anthropic_1hr_cache_pricing.py | ||
| test_bedrock_usgov_haiku_1hr_cache.py | ||
| test_bedrock_usgov_pricing.py | ||
| test_budget_ratchet_check.py | ||
| test_chat_ui_responses_session.py | ||
| test_check_licenses.py | ||
| test_check_type_discipline.py | ||
| test_claude_fable_5_config.py | ||
| test_claude_haiku_4_5_config.py | ||
| test_claude_opus_4_6_config.py | ||
| test_claude_opus_4_8_config.py | ||
| test_claude_sonnet_4_6_config.py | ||
| test_command_r7b_pricing.py | ||
| test_completion_timeout_resolution.py | ||
| test_compression.py | ||
| test_constants.py | ||
| test_container_router.py | ||
| test_cost_calculation_log_level.py | ||
| test_cost_calculator.py | ||
| test_count_tokens_public_api.py | ||
| test_dashscope_image_generation.py | ||
| test_deepseek_model_metadata.py | ||
| test_dockerfile_non_root.py | ||
| test_eager_tiktoken_load.py | ||
| test_exception_exports.py | ||
| test_exception_header_preservation.py | ||
| test_exception_mapping_request_attribute.py | ||
| test_filter_out_litellm_params.py | ||
| test_get_blog_posts.py | ||
| test_git_hooks.py | ||
| test_github_close_low_quality_prs.py | ||
| test_github_review_gate.py | ||
| test_github_triage_with_llm.py | ||
| test_github_triage_workflows.py | ||
| test_gpt_5_5_model_metadata.py | ||
| test_gpt_image_cost_calculator.py | ||
| test_groq_streaming_encoding.py | ||
| test_guardrail_exception_status_codes.py | ||
| test_lazy_imports.py | ||
| test_litellm_params_reserved_keys.py | ||
| test_logging.py | ||
| test_lowest_latency_zero_tokens.py | ||
| test_main.py | ||
| test_main_module_header.py | ||
| test_mistral_medium_3_5_model_metadata.py | ||
| test_model_block_unblock.py | ||
| test_model_cost_aliases.py | ||
| test_model_param_helper.py | ||
| test_model_response_normalization.py | ||
| test_nested_drop_params.py | ||
| test_openai_embedding_encoding_format_default.py | ||
| test_project_alias_tracking.py | ||
| test_project_tags_pydantic.py | ||
| test_rag_openai_ingestion.py | ||
| test_rate_limit_error_unification.py | ||
| test_redact_string_in_error_paths.py | ||
| test_redis.py | ||
| test_register_model_custom_pricing.py | ||
| test_register_model_zero_cost_persistence.py | ||
| test_responses_api_bridge_non_stream.py | ||
| test_responses_id_security.py | ||
| test_responses_streaming_container_ownership.py | ||
| test_retrieve_batch_bedrock_dispatch.py | ||
| test_router.py | ||
| test_router_block_helpers.py | ||
| test_router_exception_redaction.py | ||
| test_router_google_genai.py | ||
| test_router_model_cost_isolation.py | ||
| test_router_order_fallback.py | ||
| test_router_per_deployment_num_retries.py | ||
| test_router_redis_init.py | ||
| test_router_retry_non_retryable_errors.py | ||
| test_router_silent_experiment.py | ||
| test_router_weighted_failover.py | ||
| test_ruff_strict_gate.py | ||
| test_secret_redaction.py | ||
| test_service_logger.py | ||
| test_setup_wizard.py | ||
| test_shared_session_integration.py | ||
| test_ssl_verify_unit.py | ||
| test_stream_chunk_builder_annotations.py | ||
| test_streaming_connection_cleanup.py | ||
| test_system_message_format_bug.py | ||
| test_thinking_enabled.py | ||
| test_triage_rollout_heads_up.py | ||
| test_type_check_gate.py | ||
| test_type_discipline_gate.py | ||
| test_utils.py | ||
| test_utils_module_docstring.py | ||
| test_uuid_helper.py | ||
| test_vcr_safe_body_matcher.py | ||
| test_video_generation.py | ||
| test_xai_grok_4_3_model_metadata.py | ||
| test_xai_responses_auto_routing.py | ||
Testing for litellm/
This directory 1:1 maps the the litellm/ directory, and can only contain mocked tests.
The point of this is to:
- Increase test coverage of
litellm/ - Make it easy for contributors to add tests for the
litellm/package and easily run tests without needing LLM API keys.
File name conventions
litellm/proxy/test_caching_routes.pymaps tolitellm/proxy/caching_routes.pytest_<filename>.pymaps tolitellm/<filename>.py