PR #25765: fix: handle Anthropic-format tool_use/tool_result content blocks in message sanitization

• Repository: BerriAI/litellm
• Author: aayushbaluni
• State: open | merged: False
• Link: https://github.com/BerriAI/litellm/pull/25765

Description (problem / solution / changelog)

Summary

When clients send multi-turn conversations using Anthropic content block format (tool_use in assistant content list, tool_result in user content list), _is_orphaned_tool_result() only checks the OpenAI-style tool_calls array for matching tool IDs. Every tool_result is incorrectly flagged as orphaned and stripped, destroying conversation history.

Root Cause

1. _is_orphaned_tool_result() in factory.py only checks prev_msg.get("tool_calls") (OpenAI format). It never checks content blocks for type=tool_use, so Anthropic-format tool calls are invisible to the orphan detection logic.

2. ValidUserMessageContentTypes in openai.py does not include "tool_result", causing validate_chat_completion_user_messages() to reject Anthropic-format user messages before they reach the provider.

Fix

• _is_orphaned_tool_result(): After checking tool_calls, also iterate over assistant message content blocks looking for type=tool_use with a matching id.
• ValidUserMessageContentTypes and ValidUserMessageContentTypesLiteral: Add "tool_result" so Anthropic-format user messages pass validation.

Reproduction

import openai
client = openai.OpenAI(base_url="http://localhost:4000", api_key="sk-xxx")
client.chat.completions.create(
    model="anthropic/claude-sonnet-4-6",
    messages=[
        {"role": "user", "content": "run ls"},
        {"role": "assistant", "content": [
            {"type": "text", "text": "Running ls"},
            {"type": "tool_use", "id": "toolu_01xxx", "name": "Shell", "input": {"command": "ls"}}
        ]},
        {"role": "user", "content": [
            {"type": "tool_result", "tool_use_id": "toolu_01xxx", "content": [{"type": "text", "text": "file.txt"}]}
        ]}
    ],
    tools=[{"type": "function", "function": {"name": "Shell", "description": "run shell", "parameters": {"type": "object", "properties": {"command": {"type": "string"}}}}}]
)

Fixes #25669

Made with Cursor

Changed files

• litellm/litellm_core_utils/prompt_templates/factory.py (modified, +11/-0)
• litellm/types/llms/openai.py (modified, +5/-2)
• tests/test_litellm/llms/anthropic/test_anthropic_tool_content.py (added, +110/-0)

PR #25853: fix(bedrock): handle orphaned tool blocks caused by conversation compaction

• Repository: BerriAI/litellm
• Author: AlmogBaku
• State: open | merged: False
• Link: https://github.com/BerriAI/litellm/pull/25853

Description (problem / solution / changelog)

Summary

Fixes Bedrock Converse API failures when clients like OpenAI Codex CLI compact long conversations. Compaction truncates history, leaving behind orphaned toolUse/toolResult blocks that Bedrock rejects.

Errors fixed:

• "tool_use ids were found without tool_result blocks"
• "The toolConfig field must be defined when using toolUse and toolResult content blocks."
• "tool_choice.type: Field required" (follow-on from injected toolConfig missing toolChoice)

Related issues: #25669, #24361

Changes

All fixes are gated on modify_params=True and follow existing LiteLLM patterns.

1. litellm/utils.py — has_tool_call_blocks()

Extended to detect Anthropic-format content blocks (type="tool_use" / type="tool_result") and role="tool" messages, in addition to the existing OpenAI tool_calls array check. Previously, when a Responses API request arrived with Anthropic-format tool content, the function returned False and _transform_request_helper skipped injecting toolConfig.

2. litellm/litellm_core_utils/prompt_templates/factory.py

Applied to both _bedrock_converse_messages_pt (sync) and _bedrock_converse_messages_pt_async (async):

a. Sort assistant content blocks (inside loop, after deduplication): Ensures order reasoningContent → text → toolUse within each assistant message. Bedrock rejects requests where text blocks appear after toolUse blocks, as it interprets them as breaking the toolUse→toolResult pairing.

b. Tool pairing sanitization (post-loop):

• Pass 1: For each assistant message with orphaned toolUse blocks (no matching toolResult), collect all orphaned IDs in order, then inject dummy toolResult blocks as a single batch into the next user message (or a newly inserted user message). Batch injection is important — injecting one at a time via prepend reverses the order, and Bedrock requires toolResult order to match toolUse order.
• Pass 2: Remove toolResult blocks whose toolUseId has no matching toolUse in any assistant message. If a user message becomes empty, replace its content with [BedrockContentBlock(text=" ")] (single space — Bedrock rejects empty strings).

3. litellm/llms/bedrock/chat/converse_transformation.py

Applied to both _transform_request (sync) and _async_transform_request (async):

After building bedrock_messages, if tool blocks are now present (injected by fix #2) but toolConfig is absent (because the original OpenAI messages had no tool blocks, so _transform_request_helper never added it), inject a dummy toolConfig with:

• A single ToolBlock(toolSpec=...) with empty input schema
• toolChoice=ToolChoiceValuesBlock(auto={}) — required by Bedrock/Claude; omitting it causes "tool_choice.type: Field required"

Test plan

• Verify no regression on normal tool-calling requests (tools present in original messages)
• Verify compacted conversations with orphaned toolUse no longer hit "tool_use ids were found without tool_result blocks"
• Verify compacted conversations with orphaned toolResult have them silently removed
• Verify toolConfig is injected when tool blocks exist after compaction sanitization
• Verify assistant messages with multiple parallel tool calls inject toolResult blocks in correct order

🤖 Generated with Claude Code

Changed files

• litellm/litellm_core_utils/prompt_templates/factory.py (modified, +457/-814)
• litellm/llms/bedrock/chat/converse_transformation.py (modified, +60/-0)
• litellm/utils.py (modified, +15/-0)
• tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py (modified, +260/-0)