fix(aggregator): צד שלם נמחק בשקט — chunking לפי גודל + כשל שמדווח (#233) #430
@@ -147,6 +147,38 @@ def _normalize_argument(raw: dict, fallback_topic: str = "") -> dict | None:
|
||||
}
|
||||
|
||||
|
||||
class AggregationFailed(RuntimeError):
|
||||
"""One side's aggregation call failed. Never swallowed — see #233."""
|
||||
|
||||
|
||||
#: Largest number of propositions sent to Claude in a single aggregation call.
|
||||
#:
|
||||
#: Above roughly this size the model stops returning a JSON array and the whole
|
||||
#: side is lost. The per-brief split added for the respondent side (#224) hid
|
||||
#: this by accident — it kept those calls small — but appellant and committee
|
||||
#: speak with a single voice and are never split by brief, so a big appeal goes
|
||||
#: out in one oversized call. 1069-04-26 sent 310 propositions and got nothing
|
||||
#: back (#233).
|
||||
#:
|
||||
#: Chunking is a real trade-off, not a free win: each chunk is grouped in
|
||||
#: isolation, so a side split across chunks can end up with more (and slightly
|
||||
#: overlapping) arguments than a single pass would have produced. Losing an
|
||||
#: entire litigant is worse, and the alternative — a smaller prompt per
|
||||
#: proposition — would degrade every case to fix the large ones.
|
||||
MAX_PROPS_PER_CALL = 80
|
||||
|
||||
|
||||
def _chunk(propositions: list[dict], size: int) -> list[list[dict]]:
|
||||
"""Split propositions into calls of at most ``size``, keeping claim order.
|
||||
|
||||
Order matters: claims arrive sorted by ``claim_index``, so neighbouring
|
||||
propositions usually belong to the same head of argument. Slicing in order
|
||||
keeps related material together instead of scattering one argument across
|
||||
chunks.
|
||||
"""
|
||||
return [propositions[i:i + size] for i in range(0, len(propositions), size)]
|
||||
|
||||
|
||||
async def _aggregate_party(
|
||||
party: str, propositions: list[dict], party_name: str = "",
|
||||
) -> list[dict]:
|
||||
@@ -155,9 +187,27 @@ async def _aggregate_party(
|
||||
``party_name`` names the specific pleading when this is a split side
|
||||
(respondent / permit_applicant brief), so the prompt scopes to that
|
||||
litigant's position only (#224).
|
||||
|
||||
Sides larger than ``MAX_PROPS_PER_CALL`` are aggregated in several calls and
|
||||
concatenated; a failure in any chunk raises rather than returning a partial
|
||||
side quietly.
|
||||
"""
|
||||
if not propositions:
|
||||
return []
|
||||
|
||||
if len(propositions) > MAX_PROPS_PER_CALL:
|
||||
chunks = _chunk(propositions, MAX_PROPS_PER_CALL)
|
||||
logger.info(
|
||||
"argument_aggregator: party '%s'%s has %d propositions — "
|
||||
"aggregating in %d calls of up to %d",
|
||||
party, f" ({party_name})" if party_name else "",
|
||||
len(propositions), len(chunks), MAX_PROPS_PER_CALL,
|
||||
)
|
||||
out: list[dict] = []
|
||||
for chunk in chunks:
|
||||
out.extend(await _aggregate_party(party, chunk, party_name=party_name))
|
||||
return out
|
||||
|
||||
prompt = _build_prompt(party, propositions, party_name=party_name)
|
||||
|
||||
try:
|
||||
@@ -171,11 +221,18 @@ async def _aggregate_party(
|
||||
) from e
|
||||
|
||||
if not isinstance(raw_result, list):
|
||||
logger.warning(
|
||||
"argument_aggregator: Claude returned non-list (%s) for party '%s'",
|
||||
type(raw_result).__name__, party,
|
||||
# NOT a silent []: returning empty here is indistinguishable from "this
|
||||
# side genuinely has no arguments", and the caller would then report
|
||||
# status=completed while a whole litigant vanished. That is exactly what
|
||||
# happened to the appellant side of 1069-04-26 — 310 claims in, 0
|
||||
# arguments out, "completed" (#233). Raise so the caller records it in
|
||||
# ``errors`` and the status degrades to completed_with_errors (§6).
|
||||
raise AggregationFailed(
|
||||
f"Claude returned {type(raw_result).__name__}, not a list, for party "
|
||||
f"'{party}'{f' ({party_name})' if party_name else ''} with "
|
||||
f"{len(propositions)} propositions — the side would otherwise be "
|
||||
f"dropped without trace",
|
||||
)
|
||||
return []
|
||||
|
||||
out: list[dict] = []
|
||||
for entry in raw_result:
|
||||
@@ -276,6 +333,12 @@ async def aggregate_claims_to_arguments(
|
||||
group_key = f"{party}·{party_name}" if party_name else party
|
||||
try:
|
||||
arguments = await _aggregate_party(party, props, party_name=party_name)
|
||||
except AggregationFailed as e:
|
||||
# A side that failed is NOT a side with no arguments. Record it so
|
||||
# the status degrades and the caller can see which litigant is
|
||||
# missing (#233).
|
||||
errors.append(f"{group_key}: {e}")
|
||||
continue
|
||||
except RuntimeError as e:
|
||||
# Most likely cause: Claude CLI not installed (running from
|
||||
# the container). Don't crash — record the gap and continue.
|
||||
|
||||
54
mcp-server/tests/test_argument_aggregator.py
Normal file
54
mcp-server/tests/test_argument_aggregator.py
Normal file
@@ -0,0 +1,54 @@
|
||||
"""Regression tests for argument aggregation (#233).
|
||||
|
||||
Both tests cover the same 2026-08-05 incident from different angles: the
|
||||
appellant side of 1069-04-26 sent 310 propositions in one Claude call, the call
|
||||
came back as something other than a JSON array, and the code logged a warning
|
||||
and returned ``[]``. The caller could not tell that apart from "this side has no
|
||||
arguments", so ``aggregate_claims_to_arguments`` reported ``completed`` with the
|
||||
central litigant of the appeal missing entirely.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import pytest
|
||||
|
||||
from legal_mcp.services.argument_aggregator import (
|
||||
MAX_PROPS_PER_CALL,
|
||||
AggregationFailed,
|
||||
_aggregate_party,
|
||||
_chunk,
|
||||
)
|
||||
|
||||
|
||||
def test_chunk_preserves_every_proposition_and_their_order():
|
||||
"""Chunking must not drop or reorder — losing claims here is invisible."""
|
||||
props = [{"i": i} for i in range(310)]
|
||||
|
||||
chunks = _chunk(props, MAX_PROPS_PER_CALL)
|
||||
|
||||
assert sum(len(c) for c in chunks) == 310, "propositions were lost"
|
||||
assert [p for c in chunks for p in c] == props, "order changed"
|
||||
assert all(len(c) <= MAX_PROPS_PER_CALL for c in chunks)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_non_list_reply_raises_instead_of_dropping_the_side(monkeypatch):
|
||||
"""A malformed reply must surface, never look like an empty side.
|
||||
|
||||
This is the exact 1069-04-26 failure. If this test ever goes back to
|
||||
asserting ``== []``, the silent-drop bug has been reintroduced.
|
||||
"""
|
||||
async def _query_json(prompt, tools=""): # noqa: ARG001
|
||||
return {"error": "not a list"}
|
||||
|
||||
monkeypatch.setattr(
|
||||
"legal_mcp.services.argument_aggregator.claude_session.query_json",
|
||||
_query_json,
|
||||
)
|
||||
|
||||
with pytest.raises(AggregationFailed) as excinfo:
|
||||
await _aggregate_party("appellant", [{"id": "x", "claim_text": "t"}])
|
||||
|
||||
# The message has to name the side, or an operator reading
|
||||
# completed_with_errors cannot tell which litigant went missing.
|
||||
assert "appellant" in str(excinfo.value)
|
||||
Reference in New Issue
Block a user