litellm/tests/unit/llms/bedrock
simonp9 61da6fcb4d
fix(mcp)!: answer 400 for a hosted MCP tool a translated route cannot run, drop it under drop_params (#48931)
* fix(bedrock, gemini, deepseek, databricks, gigachat, anthropic): answer 400 for a hosted MCP tool a route cannot run, drop it under drop_params

A `type: "mcp"` tool sent to a route that rebuilds tools for its provider
(Bedrock Converse and Nova, Bedrock Invoke Claude, Vertex AI Claude, Vertex AI
and Google AI Studio Gemini, DeepSeek, Databricks Claude, GigaChat) was dropped
silently and the request still answered 200. These routes now answer
UnsupportedParamsError (400) naming the model, route and server, and pointing
to the LiteLLM MCP gateway. Under drop_params the tool is dropped with a
warning, other tools are kept, and no empty tools field is sent.

Anthropic, Azure AI Claude and Claude Platform on AWS keep mapping the tool to
the MCP connector. Native Responses providers and raw OpenAI-compatible
forwarders are unchanged.

* fix(mcp): check hosted MCP tools once per request and keep base tool_choice handling

Each route now runs one request-level step before its param mapping. When the drop leaves no tools,
the request sends no tools, tool_choice or parallel_tool_calls. Converse and GigaChat go back to their
base tool_choice and empty-tools handling.

* refactor(deepseek): hold the sent tools in a tuple

* fix(mcp): keep tool_choice for legacy functions when every hosted MCP tool drops

* fix(mcp): answer 400 for MCP servers a route cannot run on Messages, Ollama and the Responses playground

/v1/messages requests with mcp_servers on a chat-adapter or Responses-bridge
route now answer 400 naming each server, or drop it with a warning under
drop_params, instead of being forwarded or silently ignored. Ollama generate
no longer pastes a hosted MCP tool (headers included) into the prompt, and
ollama_chat filters hosted MCP tools the same way. The Admin UI Responses
playground now sends litellm_proxy/mcp references like the other endpoints.

* fix(ollama): leave JSON mode off when drop_params drops every hosted MCP tool

Ollama generate set format json for any request with tools, even after the
hosted MCP check dropped all of them, so a plain answer came back as JSON or
as a call to a tool the model never had. The check now runs before the JSON
mode switch, which stays on only while a tool is left for the prompt.

* fix(messages): honor additional_drop_params for mcp_servers and read the beta map only for hosted MCP tools

* fix(mcp_security): accept gateway server names and toolsets the gateway resolves

The guardrail compared litellm_proxy/mcp/<name> refs against registry keys, which are server ids, so a saved server referenced by name, alias, or toolset name was blocked although the gateway routes it. It now resolves each ref the way the gateway does and still blocks unknown names.

* fix(tool_fields): keep MCP drop warnings on one log line

Server labels, model names, and routes come from the caller, so a line break in one could forge extra log lines. The drop warnings now strip CR and LF from each value.

---------

Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
2026-11-02 13:13:03 -08:00
..
batches fix(bedrock): send batch jobs to a configured control-plane endpoint (#47260) 2026-10-20 12:30:16 -07:00
chat 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
count_tokens fix(proxy): count the context_management edits /v1/messages applies on every bridged provider (#49234) 2026-11-02 10:38:35 -08:00
embed fix(bedrock)!: route region-prefixed embedding models to that region and bill its price (#49072) 2026-10-29 06:24:04 -07:00
files fix(anthropic): answer 400 naming a non-string role or tool call id instead of 500 (#49237) 2026-10-31 21:13:24 +00:00
image test: move 81 legacy live tests in pass-through, spend, batches, audio, search, guardrails, image and ocr dirs offline (#45288) 2026-10-08 02:38:12 -07:00
image_edit refactor(types): replace Any with proven types in 137 files (#44478) 2026-10-05 11:01:45 -07:00
image_generation test: move the unit half of 126 mixed legacy files into tests/unit (#45090) 2026-10-07 14:07:43 -07:00
invoke_agent refactor(llms): expose public names for private provider helpers (#45037) 2026-10-07 08:49:25 -07:00
messages fix(anthropic): retry /v1/messages without strict when Claude rejects strict tools under drop_params (#49102) 2026-10-29 17:18:59 -07:00
passthrough fix(streaming): keep merged think tags balanced and split SSE lines only on CR/LF (#48755) 2026-10-28 17:00:29 -07:00
realtime test(bedrock): detect Vault reads on the event-loop thread (#47597) 2026-10-20 10:45:04 -07:00
rerank refactor(types): replace Any with proven types in 137 files (#44478) 2026-10-05 11:01:45 -07:00
responses fix(openai): warn when the GPT-5 reasoning effort gate drops a level under drop_params (#47761) 2026-10-29 04:46:29 -07:00
search fix(streaming): keep merged think tags balanced and split SSE lines only on CR/LF (#48755) 2026-10-28 17:00:29 -07:00
vector_stores 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
__init__.py test(unit): make every tests/unit directory a package so pytest collection is unique 2026-09-20 11:50:59 +00:00
event_loop_probe.py test(bedrock): detect Vault reads on the event-loop thread (#47597) 2026-10-20 10:45:04 -07:00
slow_upstream.py fix(router)!: bound fake-streamed calls by the request timeout, not stream_timeout (#47162) 2026-10-17 22:08:02 +00:00
test_anthropic_beta_support.py refactor(llms): rename model-version transformation files to family names (#48509) 2026-10-26 18:53:16 -07:00
test_base_aws_llm.py refactor(llms): rename model-version transformation files to family names (#48509) 2026-10-26 18:53:16 -07:00
test_bedrock_common_utils.py fix(decisions)!: honor a deployment's own supports_audio_input and supports_video_input flags (#49207) 2026-10-31 01:09:46 -07:00
test_bedrock_model_listing.py fix(bedrock): list the account's invocable models behind bedrock/* when check_provider_endpoint is on (#43981) 2026-10-09 14:14:17 -07:00
test_bedrock_ssl_verify.py test: move tests/test_litellm/llms into tests/unit/llms (#43191) 2026-09-25 12:43:23 -07:00
test_claude_platform_provider.py fix(anthropic)!: drop beta-gated body fields under drop_params (#48793) 2026-10-29 06:25:31 -07:00
test_converse_context_management.py test: move tests/test_litellm/llms into tests/unit/llms (#43191) 2026-09-25 12:43:23 -07:00
test_cost_calculation.py fix(bedrock): price claude_platform calls from their own cost map rows (#48150) 2026-10-24 13:54:18 -07:00
test_cross_region_inference_profile_mapping.py feat(bedrock): serve gpt-5.6+ chat completions natively by default, with chat_completions/ opt-in for gpt-oss and grok (#44307) 2026-10-02 19:55:54 -07:00
test_guardrail_attachments.py fix(guardrails): scan or refuse attachments in the bedrock guardrail (#43383) 2026-10-10 16:48:37 -07:00
test_mantle.py fix(bedrock): send the anthropic-workspace-id header to Bedrock Mantle (#44173) 2026-10-02 21:12:33 -07:00
test_nova_imported_models.py fix(bedrock): route a Bedrock model id with no Invoke provider to Converse (#43290) 2026-10-30 06:27:59 -07:00
test_request_metadata.py refactor(llms): rename model-version transformation files to family names (#48509) 2026-10-26 18:53:16 -07:00
test_web_identity_session_policy.py fix(bedrock): grant sts:GetWebIdentityToken and sts:TagGetWebIdentityToken in web identity session policy for claude_platform (#46670) 2026-10-16 06:37:49 +00:00