Python: re-role trailing assistant message to user for Anthropic compatibility (fixes #5008)

[hanhan761]

Summary

When two agents backed by Anthropic are connected via WorkflowBuilder, the first agent's output (assistant-role messages) is passed as context to the second agent. Anthropic's API rejects this with:

\
This model does not support assistant message prefill. The conversation must end with a user message.
\\

Changes

Modified _prepare_messages_for_anthropic\ in the Anthropic chat client:

• After preparing all messages, check if the last message has role "assistant"
• If so, re-role it as "user" so the conversation ends with a valid user message
• Single-agent usage is unaffected (conversation already ends with user message in that flow)

Related

Fixes #5008

[Copilot]

Pull request overview

Note

Copilot was unable to run its full agentic suite in this review.

Updates tool invocation argument handling to preserve None values, adds regression coverage, and adjusts Anthropic message preparation to satisfy its “last message must be user” constraint.

Changes:

• Preserve explicit None tool arguments by disabling exclude_none during Pydantic dumps.
• Add a regression test for tool invocation with explicit None.
• Ensure Anthropic message lists end with a user message by re-labeling a trailing assistant message.

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 4 comments.

File	Description
python/packages/core/tests/core/test_tools.py	Adds a regression test around invoke() handling of explicit None arguments.
python/packages/core/agent_framework/_tools.py	Changes Pydantic serialization to keep None values when building invocation kwargs.
python/packages/anthropic/agent_framework_anthropic/_chat_client.py	Adjusts message preparation to ensure the final message role is user for Anthropic.

[eavanvalkenburg]

please address the comments @hanhan761

[github-actions]

Python Test Coverage Report •

File	Stmts	Miss	Cover	Missing
packages/anthropic/agent_framework_anthropic
_chat_client.py	450	35	92%	461, 464, 545, 638, 640, 798, 834–835, 913, 915, 945–946, 991, 1007–1008, 1015–1017, 1021–1023, 1027–1030, 1144, 1154, 1206, 1354–1355, 1372, 1385, 1398, 1423–1424
packages/core/agent_framework
_tools.py	1014	78	92%	219–220, 395, 397, 410, 435–437, 445, 463, 477, 484, 491, 514, 516, 523, 531, 650, 685–687, 690–692, 694, 700, 752–754, 779, 805, 809, 847–849, 853, 875, 1018–1019, 1023, 1059, 1071, 1078–1081, 1102, 1106, 1110, 1124–1126, 1473, 1559, 1587, 1609, 1613, 1743, 1747, 1793, 1854–1855, 1958, 2011, 2031, 2033, 2089, 2152, 2324–2325, 2345, 2401–2402, 2540–2541, 2608, 2613, 2620
TOTAL	37785	4407	88%

Python Unit Test Overview

Tests	Skipped	Failures	Errors	Time
7509	34 💤	0 ❌	0 🔥	1m 58s ⏱️

[hanhan761]

All Copilot review comments have been addressed and resolved:

1. exclude_none → exclude_unset=True, exclude_none=False — applied to both invoke() and _auto_invoke_function() in _tools.py
2. Test distinguishes omission from explicit None — test now uses a non-None default and verifies different outputs
3. Re-role → append synthetic user turn — _chat_client.py now appends {"role": "user", "content": "Continue"} instead of rewriting the assistant message. Docstring updated accordingly.

@eavanvalkenburg This is ready for re-review.

[eavanvalkenburg]

There are changes unrelated to the stated goal of this PR in here, touching the core package, please remove