fix(langchain): neutralize write_todos tool message

[Nick Hollon (nick-hollon-lc)]

Replaces the write_todos tool message payload from the verbose "Updated todo list to [...]" dump to a neutral "Todo list updated." acknowledgment.

The actual todo state still flows through the todos field of the Command update — only the text content returned to the model changes. No behavior change for downstream consumers reading state.

Why

Inlining the full todo list into the tool message — especially with status: completed entries on the final call — was priming some models (notably Anthropic Sonnet 4.6) to read the tool result as "everything done, wrap up briefly" and emit a content-free recap in the next turn instead of continuing with the substantive answer the user asked for. Reducing the tool message to a plain ack removes that prime.

This is one half of a paired change. The companion prompt updates to WRITE_TODOS_SYSTEM_PROMPT and WRITE_TODOS_TOOL_DESCRIPTION are in #37643 and can land in either order.

Notes for review

• write_todos and _write_todos both produce the new ack; behavior parity preserved.
• test_todo_middleware_write_todos_tool_execution no longer asserts on the inline-dump format; it now asserts on the neutral ack string.

---

[codspeed-hq]

Merging this PR will not alter performance

✅ 2 untouched benchmarks
⏩ 13 skipped benchmarks¹

---

_{Comparing nh/neutralize-write-todos-tool-message (dc13974) with master (d08245f)²}

Footnotes

1. 13 benchmarks were skipped, so the baseline results were used instead. If they were deleted from the codebase, click here and archive them to remove them from the performance reports. ↩

2. No successful run was found on master (c7858c4) during the generation of this report, so d08245f was used instead as the comparison base. There might be some changes unrelated to this pull request in this report. ↩

[Kevin Kakolla (torontodeveloper)]

LGTM!!!

[era (avinashkamat48)]

This makes the tool result neutral, but the tests still call write_todos.invoke(...) directly. The duplicated/priming behavior this fixes happens when the middleware returns the Command into an agent state update. Could you add one middleware-level test that verifies the visible tool message is the neutral text while the actual todo state is still preserved in result.update["todos"]?