quietjules 5a392b9e5f fix(bedrock)!: keep Claude's thinking when response_format json_schema is set (#49696) ... * fix(anthropic): stop forcing the response_format json tool when Claude will think A forced tool call skips Claude's thinking. The json_schema emulation forced json_tool_call unless thinking.type was enabled, so adaptive thinking and the models that think by default (Opus 5, Sonnet 5, Haiku 5.5, and the always-on families) lost their thinking on every structured-output request. AnthropicModelInfo.response_format_tool_can_be_forced is now the one check the Anthropic, Bedrock Converse (including the native output fallback) and Databricks paths use. It leaves the tool unforced when thinking is requested in any form or the model thinks by default, and keeps forcing it when the request turns thinking off (thinking disabled or reasoning_effort none) on a model that accepts forced tools. The new thinking_on_by_default cost map key marks Opus 5, Sonnet 5 and Haiku 5.5 on the providers that reach these paths, and a miss-only fallback rule covers unmapped Claude 5 and later ids. * fix(bedrock): route native output and thinking token counts by whether Claude will think Bedrock's native output opt-in now uses the same will-think check as the json tool, so Claude 5 models that think by default with no thinking param go native. Converse also asks for /usage/output_tokens_details on those models, so reasoning tokens are reported for them. * fix(anthropic): tell Claude to answer through the unforced response_format tool Moves the integration tests that check the forced JSON tool from Claude 5 models to Opus 4.8, since Claude 5 models now keep their default thinking and take the unforced tool or native output * fix(anthropic): keep open-object schemas on the json tool when Claude will think Native output closes every object, so an open object came back empty. Also declare thinking_on_by_default in the Rust model catalog and expect the Converse thinking-token field in test_main * fix(anthropic): hold streamed prose until the JSON tool decides the answer In json mode with the unforced JSON tool, Claude can write its working before it calls the tool. The stream now holds that text, drops it when the JSON tool answers, and sends it when Claude calls a caller tool or skips the JSON tool, matching the non-streamed reply. * test(anthropic): build the stream test events without nested comprehensions * fix(anthropic): keep always-on thinking models unforced, open objects native when thinking, and the tool instruction Claude-only * test(anthropic): keep main's open-object integration cases and cover the unforced tool on a default-thinking model * fix(anthropic): treat thinking False as thinking off so the JSON tool stays forced Cover thinking False on the Anthropic and Converse forcing tests, and pin that a Converse json_schema stream with the unforced JSON tool never sends Claude's working text as content * fix(anthropic): drop the thinking False forcing case that completion never reaches litellm.completion turns thinking False into no thinking param before any route sees it, so the case was dead on the request path and False keeps meaning the model's default * test(bedrock): collect the Converse json_schema stream chunks in one assignment --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>		2026-11-05 04:07:11 +00:00
..
audio_utils	feat(realtime)!: support latest OpenAI audio models (#35600)	2026-11-03 07:27:52 +00:00
llm_cost_calc	chore(cost-map): openai context fixes, azure gpt-6 flex pricing, bedrock govcloud and gmi rows (#50082)	2026-11-04 13:23:26 -08:00
llm_response_utils	feat(hosted_vllm)!: keep vLLM's stop_reason and token_ids on chat choices and stream chunks (#48393)	2026-11-02 13:26:29 -08:00
prompt_templates	test: make three flaky unit tests deterministic (#50114)	2026-11-04 14:38:44 -08:00
specialty_caches	test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)	2026-09-25 17:10:13 -07:00
__init__.py
attribute_forwarder.py	refactor(typing): clear 1181 basedpyright Any errors across 431 files (#47789)	2026-10-24 11:31:09 -07:00
conftest.py	test(ci): repair stale tests and flaky CI infrastructure (#43983)	2026-10-01 17:46:43 +00:00
event_loop_lag.py	test: repair stale and polluting tests red on scheduled main CI (#44229)	2026-10-02 21:32:17 +00:00
fake_secret_vault.py	test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)	2026-09-25 17:10:13 -07:00
messages_with_counts.py	test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)	2026-09-25 17:10:13 -07:00
test_agentic_followup_kwargs.py	test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)	2026-09-25 17:10:13 -07:00
test_allowed_tools_tool_choice.py	fix(tool_choice): accept OpenAI allowed_tools on chat completions and flatten it for the Responses bridge (#49043)	2026-11-02 18:51:58 -08:00
test_anthropic_dedup_factory.py	test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)	2026-09-25 17:10:13 -07:00
test_api_route_to_call_types.py	fix(proxy): serve /a2a/{agent_id}/message/stream routes (#49471)	2026-10-31 16:11:51 -07:00
test_app_crypto.py	test: move offline logging, secret manager and provider tests from legacy dirs into tests/unit (#45554)	2026-10-09 09:48:10 -07:00
test_audio_utils.py	fix(proxy): account for media in combined TPM reservations (#48865)	2026-10-28 12:39:41 -07:00
test_aws_partition.py	perf(ci): isolate and shard integration suites (#44146)	2026-10-10 11:15:19 -07:00
test_batch_utils.py	fix(proxy): charge a video's provider-reported cost once, on the first poll that sees it completed (#49824)	2026-11-04 20:22:06 +00:00
test_bedrock_converse_dedup_factory.py	test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)	2026-09-25 17:10:13 -07:00
test_bug_report.py	fix(proxy): cooldown errors carry 429, Sentry starts at boot without request bodies, tracing failures log at ERROR, exporter counters exported (#46344)	2026-10-16 00:53:52 +00:00
test_chat_completion_agentic_loop.py	fix(agentic)!: surface a failed agentic follow-up call instead of the pre-loop tool call (#49227)	2026-11-04 02:00:33 +00:00
test_classifier_logging.py	test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)	2026-09-25 17:10:13 -07:00
test_cli_token_utils.py	test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)	2026-09-25 17:10:13 -07:00
test_cloud_storage_security.py	fix(proxy)!: let proxy admin keys read raw cloud storage file ids on GET /files/{id}/content (#40621)	2026-10-20 10:58:42 +00:00
test_codestral_provider_routing.py	test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)	2026-09-25 17:10:13 -07:00
test_core_helpers.py	fix(cohere): emit streamed tool calls from v2 tool-call-start and tool-call-delta chunks (#47794)	2026-10-31 21:14:53 +00:00
test_coroutine_checker.py	test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)	2026-09-25 17:10:13 -07:00
test_cost_discount.py	feat(cost): support provider/model-pattern keys in cost_discount_config (#43335)	2026-10-12 14:59:18 -07:00
test_custom_logger_registry.py	test: move whole-unit legacy test files into tests/unit and delete dead skips (#44807)	2026-10-07 05:02:28 +00:00
test_dd_tracing.py	refactor: expose core private helpers under public names (#44871)	2026-10-07 00:05:27 +00:00
test_decisions_pricing.py	feat(decisions): add Parallel AI web-grounded decisions (#49188)	2026-11-03 04:47:02 +00:00
test_decode_special_tokens.py	test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)	2026-09-25 17:10:13 -07:00
test_default_encoding.py	test: move 76 live top-level tests to offline unit and integration coverage (#45352)	2026-10-08 10:33:35 -07:00
test_dot_notation_indexing.py	refactor(typing): widen delete_nested_value to Mapping and drop two unused Span aliases (#48001)	2026-10-24 19:39:27 +00:00
test_duration_parser.py	feat(proxy): report when each per-model budget window resets (#45797)	2026-10-15 10:56:45 -07:00
test_env_utils.py	fix(router): cap the default OTPM reservation and reconcile token counters after each call (#49054)	2026-10-29 20:32:04 -07:00
test_error_normalization.py	fix(anthropic): answer an upstream Anthropic 529 as 529 overloaded_error on /v1/messages (#46063)	2026-11-03 17:37:09 -08:00
test_exception_mapping_utils.py	fix(anthropic): answer an upstream Anthropic 529 as 529 overloaded_error on /v1/messages (#46063)	2026-11-03 17:37:09 -08:00
test_extract_base64_image.py	test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)	2026-09-25 17:10:13 -07:00
test_fallback_generalizations.py	fix(bedrock)!: keep Claude's thinking when response_format json_schema is set (#49696)	2026-11-05 04:07:11 +00:00
test_fallback_utils.py	fix(cache_control): pick the chat-path dialect from the deployment's provider prefix (#45295)	2026-10-30 05:11:42 -07:00
test_get_litellm_params.py	feat(openai): bill gov.api.openai.com FedRAMP endpoint with 1.1x uplift (#49951)	2026-11-04 08:57:42 -08:00
test_get_llm_provider_endpoint_match.py	test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)	2026-09-25 17:10:13 -07:00
test_get_llm_provider_logic.py	fix(proxy): let typesafe/* allowlists cover /typesafe Jev calls and list Jev in the model picker (#47697)	2026-10-28 20:19:58 -07:00
test_get_model_cost_map.py	feat(proxy): add LITELLM_OFFLINE_MODE, one switch for the fetches LiteLLM makes on its own (#48096)	2026-10-23 16:54:19 -07:00
test_get_supported_openai_params.py	fix(bedrock): backfill published regional service tier prices (#49113)	2026-10-29 19:46:57 -07:00
test_health_check_helpers.py	fix(health): probe only models a partial wildcard serves (#49060)	2026-10-29 23:34:57 -07:00
test_hidden_params.py	perf(streaming): stop raising caught AttributeErrors inside pydantic on every streamed chunk (#49166)	2026-10-30 10:01:44 -07:00
test_image_handling.py	fix(anthropic): send an https PDF image_url to Claude as a document (#49708)	2026-11-03 07:05:15 +00:00
test_initialize_dynamic_callback_params.py	test: move whole-unit legacy test files into tests/unit and delete dead skips (#44807)	2026-10-07 05:02:28 +00:00
test_internal_call_metadata.py	fix(responses): resume background response streams with stream and starting_after (#48819)	2026-10-29 02:31:22 -07:00
test_json_fragment_accumulator.py	test: deflake the json accumulator drain test and the armed routing prefetch test (#49505)	2026-10-31 15:14:33 -07:00
test_json_schema_validation.py	test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)	2026-09-25 17:10:13 -07:00
test_litellm_logging.py	fix(cost_calculator): keep regional and speed multipliers for per-call custom prices and log the billed per-call entry (#50063)	2026-11-04 15:47:57 -08:00
test_llm_judge.py	fix(guardrails): resolve decision models in caller team scope (#46085)	2026-10-15 11:43:36 -07:00
test_llm_request_utils.py	fix(aiand)!: show ai&'s name and logo, and sync ai&'s model list (#49158)	2026-10-30 10:55:26 -07:00
test_logging_callback_manager.py	fix(router): unregister strategy selectors from global callbacks on discard (#45795)	2026-10-21 02:39:36 +00:00
test_logging_utils.py	perf(logging): skip the base64 regex on plain text and copy a few large strings inline (#49228)	2026-10-31 01:03:04 -07:00
test_logging_worker.py	fix(proxy): persist tag spend and drain success callbacks within the shutdown budget (#48988)	2026-10-29 09:32:18 -07:00
test_max_streaming_duration.py	fix(router): log each dropped /v1/messages attempt through its own logging copy and open the retry without its usage (#45194)	2026-10-20 21:46:45 -07:00
test_model_param_helper.py	feat(realtime)!: support latest OpenAI audio models (#35600)	2026-11-03 07:27:52 +00:00
test_model_response_utils.py	test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)	2026-09-25 17:10:13 -07:00
test_moderation_standard_logging.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_oauth_token_exchange.py	feat(microsoft_365_copilot): add Microsoft 365 Copilot chat provider with OAuth token exchange (#45158)	2026-10-09 15:19:07 -07:00
test_offline_mode.py	feat(proxy): add LITELLM_OFFLINE_MODE, one switch for the fetches LiteLLM makes on its own (#48096)	2026-10-23 16:54:19 -07:00
test_optional_imports.py	refactor(sdk): separate core AWS and tokenizer dependencies (#44447)	2026-10-08 19:07:57 -07:00
test_path_utils.py	refactor(core): move path_utils from proxy common_utils to litellm_core_utils (#45775)	2026-10-10 19:07:22 +00:00
test_private_json.py	test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)	2026-09-25 17:10:13 -07:00
test_provider_affinity.py	fix(headroom): forward tenant-scoped session affinity (#49255)	2026-10-30 12:32:03 -07:00
test_provider_specific_headers.py	test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)	2026-09-25 17:10:13 -07:00
test_ptu_pricing.py	feat(proxy): split Azure PTU deployments across teams with per-team PTU ceilings and PTU-hour reporting (#43043)	2026-10-15 18:44:30 +00:00
test_realtime_errors.py	test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)	2026-09-25 17:10:13 -07:00
test_realtime_streaming.py	feat(realtime)!: support latest OpenAI audio models (#35600)	2026-11-03 07:27:52 +00:00
test_redact_messages.py	fix(logging): don't leak redacted reasoning via provider_specific_fields (#47398)	2026-11-04 18:31:09 +00:00
test_request_timeout_resolver.py	test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)	2026-09-25 17:10:13 -07:00
test_retry_after_headers.py	test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)	2026-09-25 17:10:13 -07:00
test_safe_divide_seconds.py	test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)	2026-09-25 17:10:13 -07:00
test_safe_json_dumps.py	fix(spend): keep a NaN or infinite cost from wedging daily spend writes (#48829)	2026-10-30 08:27:35 -07:00
test_sensitive_data_masker.py	refactor: expose core private helpers under public names (#44871)	2026-10-07 00:05:27 +00:00
test_sentry_scrubbing.py	fix(proxy): cooldown errors carry 429, Sentry starts at boot without request bodies, tracing failures log at ERROR, exporter counters exported (#46344)	2026-10-16 00:53:52 +00:00
test_served_output_texts.py	fix(guardrails): scan and rewrite streamed /v1/completions under post_call guardrails (#49035)	2026-10-29 08:46:49 -07:00
test_stream_usage_logging.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_streaming_chunk_builder_cursor.py	test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)	2026-09-25 17:10:13 -07:00
test_streaming_chunk_builder_server_tool_use.py	test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)	2026-09-25 17:10:13 -07:00
test_streaming_chunk_builder_utils.py	feat(hosted_vllm)!: keep vLLM's stop_reason and token_ids on chat choices and stream chunks (#48393)	2026-11-02 13:26:29 -08:00
test_streaming_handler.py	feat(hosted_vllm)!: keep vLLM's stop_reason and token_ids on chat choices and stream chunks (#48393)	2026-11-02 13:26:29 -08:00
test_streaming_overhead.py	refactor: expose core private helpers under public names (#44871)	2026-10-07 00:05:27 +00:00
test_text_completion_conversion.py	refactor(types): replace Any with proven types in 14 files (#48928)	2026-10-29 07:26:07 -07:00
test_thread_pool_executor.py	test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)	2026-09-25 17:10:13 -07:00
test_token_counter.py	chore(cost-map): remove the 52 rows whose provider retired them before 2026 (#49974)	2026-11-03 16:23:06 -08:00
test_token_counter_tool.py	test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)	2026-09-25 17:10:13 -07:00
test_token_counter_tool_data.py	test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)	2026-09-25 17:10:13 -07:00
test_tokenizer.py	fix(token_counter)!: keep a loaded Hugging Face tokenizer when a slower download fails (#48916)	2026-10-29 03:50:58 -07:00
test_tool_fields.py	fix(mcp)!: answer 400 for a hosted MCP tool a translated route cannot run, drop it under drop_params (#48931)	2026-11-02 13:13:03 -08:00
test_tool_search_spend_logging.py	test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)	2026-09-25 17:10:13 -07:00
test_url_utils.py	feat(proxy): authenticate billing metrics with a cognito bearer token (#49852)	2026-11-04 14:08:40 -08:00
test_xai_oauth_routing.py	test: move tests/test_litellm core utils, routing, responses, caching and rust_bridge into tests/unit (#43199)	2026-09-25 17:10:13 -07:00