Python: Fix AG-UI tool history replay sanitization

[moonbox3]

Motivation & Context

AG-UI replay can reconstruct assistant/tool histories that violate provider message contracts, causing OpenAI/Azure OpenAI requests to fail when assistant tool_calls are not followed by matching tool result messages.

This change keeps replayed AG-UI history provider-valid for interrupted or incomplete tool-call sequences, and adds coverage for approved HITL tool results being persisted into MESSAGES_SNAPSHOT so the next replay does not re-send raw approval payloads.

Description & Review Guide

• What are the major changes?

  • Harden AG-UI tool-history sanitization so pending assistant tool calls are closed with deterministic synthetic tool results before a later assistant message, non-tool continuation, or end of history.
  • Preserve tool-call order when injecting synthetic results.
  • Add regression coverage for consecutive assistant tool-call messages and histories ending with unresolved tool calls.
  • Add HITL approval replay coverage proving approved tool results replace approval payloads in MESSAGES_SNAPSHOT.

• What is the impact of these changes?

  • AG-UI replay is less likely to produce provider-invalid message sequences.
  • Approved HITL tool calls replay as completed tool results instead of stale approval payloads.
  • Existing synthetic repair behavior is extended without introducing a new public API or breaking behavior.

• What do you want reviewers to focus on?

  • Whether the synthetic repair points match the existing AG-UI replay behavior.
  • Whether the regression tests cover the Python: [Bug]: AG-UI history replay can send invalid assistant/tool sequence to OpenAI (tool_calls without matching tool messages) #5855 and Python: [Bug]: HITL approval (approval_mode="always_require") result not persisted into AG-UI snapshot → provider 400 ("tool_call_ids did not have response messages") on next run #6513 failure modes clearly.

Related Issue

Fixes #5855
Fixes #6513

No other open PR was found for these issues.

Contribution Checklist

• The code builds clean without any errors or warnings
• All unit tests pass, and I have added new tests where possible
• The PR follows the Contribution Guidelines
• This PR is linked to an issue and there is no other open PR for this issue (see Related Issue above).
• This is not a breaking change. If it is a breaking change, add the breaking change label (or add "[BREAKING]" to the title prefix, before or after any language prefix) — a workflow keeps the label and title prefix in sync automatically.

[github-actions]

Python Test Coverage Report •

File	Stmts	Miss	Cover	Missing
packages/ag-ui/agent_framework_ag_ui
_message_adapters.py	608	48	92%	148–149, 158–160, 163, 166–170, 172–177, 180, 189–191, 194–197, 232, 397, 518–520, 574, 577, 579, 582, 585, 601, 618, 640, 740, 756–757, 828, 850, 920, 955–956, 1024, 1067
TOTAL	39875	4497	88%

Python Unit Test Overview

Tests	Skipped	Failures	Errors	Time
7990	34 💤	0 ❌	0 🔥	2m 9s ⏱️

[github-actions]

Automated Code Review

Reviewers: 5 | Confidence: 90% | Result: All clear

Reviewed: Correctness, Security Reliability, Test Coverage, Failure Modes, Design Approach

---

Automated review by moonbox3's agents

[Copilot]

Pull request overview

This PR hardens the Python AG-UI message replay path so outbound provider messages remain contract-valid when tool-call sequences are interrupted, incomplete, or interleaved, and adds regression coverage for HITL approval replay so approved tool outputs are persisted for subsequent replays.

Changes:

• Extend _sanitize_tool_history to deterministically close pending assistant tool calls by injecting synthetic tool results before later assistant messages, non-standard roles, or end-of-history.
• Preserve tool-call ordering when injecting synthetic results by tracking pending tool call ids in-order.
• Add tests covering consecutive assistant tool-call messages, histories ending with unresolved tool calls, and HITL approval snapshots replaying as tool results (not raw approval payloads).

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 2 comments.

File	Description
python/packages/ag-ui/agent_framework_ag_ui/_message_adapters.py	Refactors and extends tool-history sanitization to inject synthetic tool results at more replay boundary points, using ordered pending call tracking.
python/packages/ag-ui/tests/ag_ui/test_message_adapters.py	Adds regression tests for consecutive assistant tool-call messages, end-of-history pending tool calls, and updated behavior for non-standard roles.
python/packages/ag-ui/tests/ag_ui/test_approval_result_event.py	Adds coverage ensuring approved HITL tool executions are persisted into MESSAGES_SNAPSHOT for replay, and that replay normalizes to provider-valid function_result content.