Merge pull request 'fix(arguments): validate claim_ids + per-row savepoint in argument_aggregator (#156)' (#330) from worktree-fix-argument-aggregator-savepoint into main

mcp-server/src/legal_mcp/services/argument_aggregator.py

@@ -230,6 +230,15 @@ async def aggregate_claims_to_arguments(
             party = "unknown"
         by_party.setdefault(party, []).append(dict(r))
 
+    # Valid claim_ids for this case == the ids of the claims we just fetched.
+    # The LLM is asked to echo back supporting claim_ids, but it may hallucinate
+    # a syntactically-valid-but-nonexistent UUID (malformed ones are already
+    # dropped in ``_normalize_argument``). Validating against this known set at
+    # source keeps a doomed INSERT — which would poison the surrounding asyncpg
+    # transaction (FK violation -> "current transaction is aborted") — out of
+    # the transaction entirely (G1: fix at source, not symptom).
+    valid_claim_ids: set[UUID] = {r["id"] for r in rows}
+
     party_counts: dict[str, int] = {}
     inserted = 0
     errors: list[str] = []
@@ -275,7 +284,22 @@ async def aggregate_claims_to_arguments(
                         arg["priority"],
                     )
                     for cid in arg["claim_ids"]:
+                        if cid not in valid_claim_ids:
+                            # Hallucinated claim_id that doesn't belong to this
+                            # case. Skip it rather than letting the FK violation
+                            # abort the whole transaction.
+                            logger.warning(
+                                "argument_aggregator: skipped unknown claim_id %s for arg %s",
+                                cid, arg_id,
+                            )
+                            continue
                         try:
+                            # Per-row savepoint: even after the validation above,
+                            # wrap the INSERT so any unexpected constraint failure
+                            # rolls back to the savepoint instead of poisoning the
+                            # surrounding transaction (asyncpg nests transaction()
+                            # as SAVEPOINT when already inside one).
+                            async with conn.transaction():
                                 await conn.execute(
                                     """INSERT INTO legal_argument_propositions
                                         (argument_id, claim_id)
@@ -284,8 +308,6 @@ async def aggregate_claims_to_arguments(
                                     arg_id, cid,
                                 )
                         except Exception as e:  # noqa: BLE001
-                            # Likely FK violation if the LLM hallucinated
-                            # a claim_id. Log and continue.
                             logger.warning(
                                 "argument_aggregator: skipped bad claim_id %s for arg %s: %s",
                                 cid, arg_id, e,