Python: Fix Foundry reasoning MCP compaction

[godququ5-code]

Summary

• Preserve Foundry reasoning output as text_reasoning with the provider reasoning id when reconstructing response history.
• Treat mcp_server_tool_call as a tool-call assistant item during compaction so reasoning + MCP call pairs stay atomic.
• Add focused regressions for both Foundry reasoning reconstruction paths and sliding-window MCP compaction.

Fixes #6883

Root cause

Foundry response reconstruction converted reasoning summaries into ordinary text content, dropping the reasoning id. Core compaction also only recognized function_call assistant messages as tool-call items, so an MCP call following a reasoning item could be grouped separately and survive after its reasoning prefix was excluded.

Test plan

• uv run pytest packages/core/tests/core/test_compaction.py packages/foundry_hosting/tests/test_responses.py -q
• uv run prek run --files packages/core/agent_framework/_compaction.py packages/core/tests/core/test_compaction.py packages/foundry_hosting/agent_framework_foundry_hosting/_responses.py packages/foundry_hosting/tests/test_responses.py

Note: the pytest command exits 0, but the local environment emits unrelated OpenTelemetry exporter shutdown noise against 127.0.0.1:7897 after the tests finish.

[Copilot]

Pull request overview

Fixes Python response-history reconstruction and core compaction behavior so Foundry reasoning items and subsequent MCP tool calls remain correctly paired and valid for downstream APIs (avoiding “orphaned mcp_call” 400s in multi-turn reasoning flows).

Changes:

• Preserve Foundry reasoning summaries as text_reasoning content (instead of plain text) while retaining the provider reasoning id.
• Treat mcp_server_tool_call assistant messages as tool-call items during compaction grouping so reasoning + MCP call pairs stay atomic.
• Add targeted regression tests covering both Foundry reasoning reconstruction paths and sliding-window MCP compaction grouping.

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated no comments.

File	Description
python/packages/foundry_hosting/agent_framework_foundry_hosting/_responses.py	Reconstruct reasoning summaries as text_reasoning while preserving reasoning IDs.
python/packages/foundry_hosting/tests/test_responses.py	Adds assertions ensuring reconstructed reasoning content type and ID are preserved.
python/packages/core/agent_framework/_compaction.py	Expands tool-call detection to include MCP server tool calls for proper grouping/compaction.
python/packages/core/tests/core/test_compaction.py	Adds regression ensuring sliding-window compaction keeps reasoning + MCP calls in the same group.

[godququ5-code]

@microsoft-github-policy-service agree

[github-actions]

Python Test Coverage Report •

File	Stmts	Miss	Cover	Missing
packages/anthropic/agent_framework_anthropic
_chat_client.py	517	37	92%	467, 470, 551, 668, 680, 768, 802, 892, 931–932, 1010, 1012, 1042–1043, 1088, 1104–1105, 1112–1114, 1118–1120, 1124–1127, 1244, 1254, 1306, 1454–1455, 1472, 1485, 1498, 1523–1524
packages/core/agent_framework
_compaction.py	702	60	91%	117–118, 126, 193–194, 212–213, 230, 264, 278, 285, 300–301, 355, 362, 378, 428, 452, 483, 530, 536, 538, 557, 601–606, 618, 690, 692, 707, 751, 813, 939, 945–949, 952–954, 962, 1037, 1039, 1055, 1062, 1067, 1082, 1090, 1184, 1187, 1205, 1221, 1317, 1344, 1349, 1428
packages/foundry_hosting/agent_framework_foundry_hosting
_responses.py	816	90	88%	186–189, 276, 281, 305, 360–361, 375, 378–379, 427–428, 438, 483, 515–517, 520–521, 532, 575, 589, 664, 667, 673, 675, 747, 834–835, 1146, 1159, 1656–1658, 1660, 1707–1708, 1710–1711, 1713–1714, 1716–1717, 1722, 1731, 1734–1736, 1738, 1748, 1752, 1765, 1810–1811, 1813, 1818–1822, 1824, 1831–1832, 1834–1835, 1841, 1843–1847, 1854, 1860, 1882, 1888, 1894, 1896, 1898–1901, 1909, 1911, 1962–1964, 1974–1975
packages/openai/agent_framework_openai
_chat_client.py	1277	127	90%	307, 320, 670–674, 682–685, 691–695, 745–752, 754–756, 763–765, 823, 831, 854, 972, 1071, 1130, 1132, 1134, 1136, 1202, 1216, 1296, 1306, 1311, 1354, 1465–1466, 1481, 1705, 1710, 1714–1716, 1720–1721, 1804, 1814, 1841, 1847, 1857, 1863, 1868, 1874, 1879–1880, 1960, 2004, 2007–2010, 2024, 2026, 2034–2035, 2047, 2089, 2154, 2171, 2174, 2201–2203, 2242, 2259, 2262, 2324, 2331, 2355–2356, 2391, 2429–2430, 2448–2449, 2492, 2619–2620, 2638, 2721–2729, 2759, 2904, 2919, 2968–2971, 2981–2983, 3010–3012, 3022–3023, 3029, 3044, 3166–3167
_chat_completion_client.py	373	18	95%	440, 536–537, 541, 782, 784, 789, 792, 883, 885, 902, 923, 931, 955, 968, 992, 1012, 1327
TOTAL	45087	5418	87%

Python Unit Test Overview

Tests	Skipped	Failures	Errors	Time
8912	33 💤	0 ❌	0 🔥	2m 23s ⏱️