From f8b078b749f342a9e803a68af6d6e4b16e6c2ece Mon Sep 17 00:00:00 2001 From: Tai An Date: Sat, 9 May 2026 13:26:37 -0700 Subject: [PATCH] fix(bedrock/messages): preserve compact_20260112 context_management on /v1/messages (#27534) Squash-merged by litellm-agent from Anai-Guo's PR. --- .../anthropic_claude3_transformation.py | 51 +++++++++++- litellm/types/llms/bedrock.py | 7 ++ .../test_anthropic_claude3_transformation.py | 79 ++++++++++++++++++- 3 files changed, 132 insertions(+), 5 deletions(-) diff --git a/litellm/llms/bedrock/messages/invoke_transformations/anthropic_claude3_transformation.py b/litellm/llms/bedrock/messages/invoke_transformations/anthropic_claude3_transformation.py index aae2bc5e289..151e0e404a0 100644 --- a/litellm/llms/bedrock/messages/invoke_transformations/anthropic_claude3_transformation.py +++ b/litellm/llms/bedrock/messages/invoke_transformations/anthropic_claude3_transformation.py @@ -408,6 +408,47 @@ class AmazonAnthropicClaudeMessagesConfig( if self._supports_tool_search_on_bedrock(model): beta_set.add("tool-search-tool-2025-10-19") + @staticmethod + def _filter_context_management_for_bedrock_invoke( + anthropic_messages_request: Dict, + beta_set: set, + ) -> None: + """ + Bedrock InvokeModel accepts ``context_management`` only when it carries + ``compact_20260112`` edits paired with the ``compact-2026-01-12`` + anthropic-beta header. Other edit types (notably ``clear_thinking_20251015``, + which Claude Code sends on every request) are LiteLLM-internal and would + cause Bedrock to 400 with ``"context_management: Extra inputs are not + permitted"``. + + Filter the edits list to the supported subset, add the beta header when + compact edits remain, and drop ``context_management`` entirely when no + supported edits are left so the safety-net allowlist can pass it through. + + Ref: https://github.com/BerriAI/litellm/issues/27532 + """ + cm = anthropic_messages_request.get("context_management") + if not isinstance(cm, dict): + return + edits = cm.get("edits") + if not isinstance(edits, list): + anthropic_messages_request.pop("context_management", None) + return + + compact_edits = [ + e + for e in edits + if isinstance(e, dict) and e.get("type") == "compact_20260112" + ] + if compact_edits: + beta_set.add("compact-2026-01-12") + anthropic_messages_request["context_management"] = { + **cm, + "edits": compact_edits, + } + else: + anthropic_messages_request.pop("context_management", None) + def _convert_output_format_to_inline_schema( self, output_format: Dict, @@ -551,6 +592,11 @@ class AmazonAnthropicClaudeMessagesConfig( if injected_thinking_for_clear_thinking: beta_set.add("interleaved-thinking-2025-05-14") + self._filter_context_management_for_bedrock_invoke( + anthropic_messages_request=anthropic_messages_request, + beta_set=beta_set, + ) + self._get_tool_search_beta_header_for_bedrock( model=model, tool_search_used=tool_search_used, @@ -597,8 +643,9 @@ class AmazonAnthropicClaudeMessagesConfig( anthropic_messages_request.pop("output_config", None) # 7. Final safety net: filter top-level fields to the Bedrock Invoke allowlist. - # Catches Anthropic-only extensions (context_management, output_config, speed, - # mcp_servers, ...) and any future additions Claude Code may start sending. + # Catches Anthropic-only extensions (output_config, speed, mcp_servers, ...) + # and any future additions Claude Code may start sending. ``context_management`` + # has already been pre-filtered to its Bedrock-supported subset above. allowed = self.BEDROCK_INVOKE_ALLOWED_TOP_LEVEL_FIELDS stripped = sorted(k for k in anthropic_messages_request if k not in allowed) if stripped: diff --git a/litellm/types/llms/bedrock.py b/litellm/types/llms/bedrock.py index 64827db13f6..5db2a45054a 100644 --- a/litellm/types/llms/bedrock.py +++ b/litellm/types/llms/bedrock.py @@ -1042,3 +1042,10 @@ class BedrockInvokeAnthropicMessagesRequest(TypedDict, total=False): thinking: dict metadata: dict output_config: dict + + # `context_management` is allowed for Bedrock InvokeModel only when it + # carries `compact_20260112` edits paired with the `compact-2026-01-12` + # anthropic-beta header. The Invoke transformation filters edits to the + # supported subset and strips the field entirely when nothing remains, so + # other edit types (e.g. `clear_thinking_20251015`) never reach Bedrock. + context_management: dict diff --git a/tests/test_litellm/llms/bedrock/messages/invoke_transformations/test_anthropic_claude3_transformation.py b/tests/test_litellm/llms/bedrock/messages/invoke_transformations/test_anthropic_claude3_transformation.py index c98f7840343..9ecdad1fcff 100644 --- a/tests/test_litellm/llms/bedrock/messages/invoke_transformations/test_anthropic_claude3_transformation.py +++ b/tests/test_litellm/llms/bedrock/messages/invoke_transformations/test_anthropic_claude3_transformation.py @@ -867,10 +867,12 @@ def test_bedrock_messages_explicit_output_config_wins_over_reasoning_effort(): def test_bedrock_messages_strips_context_management(): """ Ensure context_management is stripped from the request before sending to - Bedrock Invoke, which doesn't support this Anthropic-specific parameter. + Bedrock Invoke when it carries only LiteLLM-internal edits (e.g. + clear_thinking_20251015, which is consumed via thinking injection). - Claude Code sends context_management on every request; leaving it in the body - causes a 400 "context_management: Extra inputs are not permitted" from Bedrock. + Claude Code sends context_management on every request; leaving such edits + in the body causes a 400 "context_management: Extra inputs are not + permitted" from Bedrock. """ from litellm.types.router import GenericLiteLLMParams @@ -897,6 +899,77 @@ def test_bedrock_messages_strips_context_management(): assert result.get("max_tokens") == 4096 +def test_bedrock_messages_preserves_compact_context_management_and_adds_beta(): + """ + Bedrock InvokeModel supports compaction when paired with the + ``compact-2026-01-12`` anthropic-beta header, even though the Converse API + does not. The transformation should: + 1. Keep ``context_management`` with compact_20260112 edits in the body + (Bedrock rejects unknown top-level fields, but accepts this one with + the right beta). + 2. Auto-inject ``compact-2026-01-12`` into ``anthropic_beta``. + + Ref: https://github.com/BerriAI/litellm/issues/27532 + """ + from litellm.types.router import GenericLiteLLMParams + + cfg = AmazonAnthropicClaudeMessagesConfig() + messages = [{"role": "user", "content": [{"type": "text", "text": "Hi"}]}] + optional_params = { + "max_tokens": 4096, + "context_management": { + "edits": [{"type": "compact_20260112"}] + }, + } + + result = cfg.transform_anthropic_messages_request( + model="anthropic.claude-sonnet-4-6-20250929-v1:0", + messages=messages, + anthropic_messages_optional_request_params=optional_params, + litellm_params=GenericLiteLLMParams(), + headers={}, + ) + + assert result.get("context_management") == { + "edits": [{"type": "compact_20260112"}] + } + assert "compact-2026-01-12" in result.get("anthropic_beta", []) + assert result["max_tokens"] == 4096 + + +def test_bedrock_messages_filters_unsupported_context_management_edits(): + """ + Mixed edit lists must drop the LiteLLM-internal ``clear_thinking_20251015`` + entries while keeping ``compact_20260112`` and adding the compact beta. + """ + from litellm.types.router import GenericLiteLLMParams + + cfg = AmazonAnthropicClaudeMessagesConfig() + messages = [{"role": "user", "content": [{"type": "text", "text": "Hi"}]}] + optional_params = { + "max_tokens": 4096, + "context_management": { + "edits": [ + {"type": "clear_thinking_20251015", "keep": "all"}, + {"type": "compact_20260112"}, + ] + }, + } + + result = cfg.transform_anthropic_messages_request( + model="anthropic.claude-sonnet-4-6-20250929-v1:0", + messages=messages, + anthropic_messages_optional_request_params=optional_params, + litellm_params=GenericLiteLLMParams(), + headers={}, + ) + + assert result.get("context_management") == { + "edits": [{"type": "compact_20260112"}] + } + assert "compact-2026-01-12" in result.get("anthropic_beta", []) + + def test_bedrock_messages_allowlist_filters_anthropic_only_fields(): """ Bedrock Invoke rejects any top-level body field it doesn't recognize with