Python: coalesce code interpreter history chunks

[he-yufeng]

Fixes #5793.

Summary

• Coalesce streamed code_interpreter_tool_call and code_interpreter_tool_result content by call_id during response finalization.
• When a later done event carries the full code, keep that full value instead of storing both chunk deltas and the complete script.
• Add a history-provider regression test for the Cosmos-style chunked code interpreter shape.

To verify

• uv run pytest packages\core\tests\core\test_sessions.py::TestHistoryProviderBase::test_after_run_stores_coalesced_code_interpreter_chunks -q --basetemp .tmp\pytest
• uv run pytest packages\core\tests\core\test_sessions.py -q --basetemp .tmp\pytest -p no:cacheprovider
• uv run pytest packages\core\tests\core\test_types.py -q --basetemp .tmp\pytest -p no:cacheprovider
• uv run pytest packages\openai\tests\openai\test_openai_chat_client.py -q -k "code_interpreter" --basetemp .tmp\pytest -p no:cacheprovider
• uv run ruff check packages\core\agent_framework_types.py packages\core\tests\core\test_sessions.py
• uv run ruff format --check packages\core\agent_framework_types.py packages\core\tests\core\test_sessions.py
• uv run mypy packages\core\agent_framework_types.py
• uv run python -m py_compile packages\core\agent_framework_types.py packages\core\tests\core\test_sessions.py
• git diff --check

[Copilot]

Pull request overview

This PR addresses streamed code-interpreter history bloat in the Python core by coalescing code_interpreter_tool_call / code_interpreter_tool_result content items with the same call_id (or item_id) during response finalization, ensuring history providers receive a single aggregated item per logical tool call.

Changes:

• Add response-finalization logic to coalesce code-interpreter tool call/result content by (type, call_id).
• Implement merge behavior that prefers a later “done” event carrying the full code over keeping both deltas and the complete script.
• Add a regression test ensuring history providers store the coalesced code-interpreter content shape.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated no comments.

File	Description
python/packages/core/agent_framework/_types.py	Adds code-interpreter coalescing/merge helpers and applies them during _finalize_response.
python/packages/core/tests/core/test_sessions.py	Adds a history-provider regression test verifying coalesced code-interpreter chunks are stored as a single content item.

[moonbox3]

Python Test Coverage Report •

File	Stmts	Miss	Cover	Missing
packages/core/agent_framework
_types.py	1187	97	91%	59, 68–69, 123, 128, 147, 149, 153, 157, 159, 161, 163, 181, 185, 211, 233, 238, 243, 247, 277, 690–691, 850–851, 1286, 1358, 1393, 1413, 1423, 1475, 1607–1609, 1791, 1894–1899, 1924, 1979, 1984, 1994, 2002, 2009–2013, 2031, 2104, 2112–2114, 2119, 2222, 2245, 2500, 2524, 2623, 2877, 3087, 3146, 3185, 3196, 3198–3202, 3204, 3207–3215, 3225, 3314, 3451, 3456, 3461, 3466, 3470, 3554–3556, 3585, 3673–3677
TOTAL	37460	4360	88%

Python Unit Test Overview

Tests	Skipped	Failures	Errors	Time
7452	34 💤	0 ❌	0 🔥	1m 58s ⏱️

[moonbox3]

@he-yufeng please have a look at the failing code quality failures. Thank you.

[he-yufeng]

Thanks for the heads up. I pushed a small follow-up that narrows the nested content list types before iteration/deepcopy, which addresses the pyright failures from the package check.

Validated locally:

• python -m py_compile agent_framework\_types.py tests\core\test_sessions.py
• python -m pytest tests\core\test_sessions.py::TestHistoryProviderBase::test_after_run_stores_coalesced_code_interpreter_chunks -q --basetemp .tmp\pytest -p no:cacheprovider
• python -m ruff check agent_framework\_types.py tests\core\test_sessions.py
• uv run pyright packages\core\agent_framework\_types.py
• git diff --check

[he-yufeng]

Thanks, I pushed a follow-up for the mypy redundant-cast failure in packages/core/agent_framework/_types.py.

Validated locally:

• uv run mypy packages\core\agent_framework\_types.py
• uv run python scripts\workspace_poe_tasks.py ci-mypy with UTF-8 console env on Windows
• uv run ruff check packages\core\agent_framework\_types.py packages\core\tests\core\test_sessions.py
• uv run ruff format --check packages\core\agent_framework\_types.py packages\core\tests\core\test_sessions.py
• uv run python -m py_compile packages\core\agent_framework\_types.py packages\core\tests\core\test_sessions.py
• uv run pytest packages\core\tests\core\test_sessions.py::TestHistoryProviderBase::test_after_run_stores_coalesced_code_interpreter_chunks -q --basetemp .tmp\pytest -p no:cacheprovider
• git diff --check

[he-yufeng]

I also rebased the branch onto current upstream/main after the mypy follow-up. The branch now carries only the three PR commits on top of main.

Revalidated after the rebase:

• uv run mypy packages\core\agent_framework\_types.py
• uv run ruff check packages\core\agent_framework\_types.py packages\core\tests\core\test_sessions.py
• uv run pytest packages\core\tests\core\test_sessions.py::TestHistoryProviderBase::test_after_run_stores_coalesced_code_interpreter_chunks -q --basetemp .tmp\pytest -p no:cacheprovider
• git diff --check

[he-yufeng]

Rebased onto current main and addressed the type-check failure from the previous run.

The fix only narrows the helper casts in _merge_content_item_lists() so Pyright/Mypy no longer infer unknown list elements.

Local validation:

uv run pyright packages\core\agent_framework\_types.py packages\core\tests\core\test_sessions.py
uv run mypy packages\core\agent_framework\_types.py
uv run pytest packages\core\tests\core\test_sessions.py::TestHistoryProviderBase::test_after_run_stores_coalesced_code_interpreter_chunks -q --basetemp .tmp\pytest -p no:cacheprovider
uv run ruff check packages\core\agent_framework\_types.py packages\core\tests\core\test_sessions.py
uv run ruff format --check packages\core\agent_framework\_types.py packages\core\tests\core\test_sessions.py
git diff --check

Result: pyright/mypy clean; targeted test passed; ruff and diff-check passed.