From e47bebacaf27725e9ecdc5b7d8265a416a3c62d8 Mon Sep 17 00:00:00 2001 From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com> Date: Sat, 12 Sep 2026 13:16:43 +0000 Subject: [PATCH 01/11] Initial plan From 304a06f97c1228a2dee15ebcddee85da53507ab8 Mon Sep 17 00:00:00 2001 From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com> Date: Sat, 12 Sep 2026 13:17:22 +0000 Subject: [PATCH 02/11] Initial plan From 45a5e4157deb7f2e708793b44802aff034ab820e Mon Sep 17 00:00:00 2001 From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com> Date: Sat, 12 Sep 2026 13:22:40 +0000 Subject: [PATCH 03/11] fix: preserve multi-cause reconcile warnings and align slot blocking Co-authored-by: genichin <4282227+genichin@users.noreply.github.com> --- .../portfolio/test_reconcile_warning_store.py | 42 ++++++++++ .../test_reconcile_notification.py | 2 +- .../test_reconcile_warning_blocking.py | 4 + .../test_reconcile_warning_store.py | 19 ++++- .../test_slots_handler_quantity_mismatch.py | 47 ++++++++++- tests/application/test_sync.py | 16 ++++ tests/application/test_verify.py | 38 ++++++++- tests/runtime/test_cli_operator.py | 2 +- .../sql/016_create_slot_reconcile_warning.sql | 4 +- .../028_preserve_reconcile_warning_cases.sql | 7 ++ .../portfolio/reconcile_warning_store.py | 51 +++++++----- trex_core/application/messaging_handlers.py | 83 ++++++++++++------- trex_core/application/portfolio.py | 72 ++++++++++++---- trex_core/application/reconciliation.py | 34 +++++--- trex_core/runtime/cli.py | 10 ++- trex_core/runtime/daemon.py | 2 +- 16 files changed, 337 insertions(+), 96 deletions(-) create mode 100644 tests/adapters/portfolio/test_reconcile_warning_store.py create mode 100644 trex_core/adapters/persistence/sql/028_preserve_reconcile_warning_cases.sql diff --git a/tests/adapters/portfolio/test_reconcile_warning_store.py b/tests/adapters/portfolio/test_reconcile_warning_store.py new file mode 100644 index 0000000..05cc113 --- /dev/null +++ b/tests/adapters/portfolio/test_reconcile_warning_store.py @@ -0,0 +1,42 @@ +"""PostgreSQLReconcileWarningStore integration tests.""" +from __future__ import annotations + +from trex_core.adapters.portfolio.reconcile_warning_store import ( + PostgreSQLReconcileWarningStore, +) + + +def test_warning_store_preserves_multiple_cases_for_same_slot(pg_clean): + store = PostgreSQLReconcileWarningStore(pg_clean) + store.set_warned("slot-1", portfolio_id="pf-A", case_code="B", reason="b") + store.set_warned("slot-1", portfolio_id="pf-A", case_code="C", reason="c") + + assert store.is_warned("slot-1") is True + info = store.get_warning_info("slot-1") + assert info is not None + assert info["case_codes"] == ["B", "C"] + + +def test_warning_store_case_specific_clear_and_full_clear(pg_clean): + store = PostgreSQLReconcileWarningStore(pg_clean) + store.set_warned("slot-2", portfolio_id="pf-A", case_code="B") + store.set_warned("slot-2", portfolio_id="pf-A", case_code="C") + + store.clear_warned("slot-2", case_code="C") + info = store.get_warning_info("slot-2") + assert info is not None + assert info["case_codes"] == ["B"] + + store.clear_warned("slot-2") + assert store.is_warned("slot-2") is False + + +def test_warning_store_is_durable_across_reinstantiation(pg_clean): + a = PostgreSQLReconcileWarningStore(pg_clean) + a.set_warned("slot-restart", portfolio_id="pf-A", case_code="B") + a.set_warned("slot-restart", portfolio_id="pf-A", case_code="C") + + b = PostgreSQLReconcileWarningStore(pg_clean) + info = b.get_warning_info("slot-restart") + assert info is not None + assert info["case_codes"] == ["B", "C"] diff --git a/tests/application/test_reconcile_notification.py b/tests/application/test_reconcile_notification.py index 1c1de0d..b95044d 100644 --- a/tests/application/test_reconcile_notification.py +++ b/tests/application/test_reconcile_notification.py @@ -896,7 +896,7 @@ def test_b_sync_does_not_publish_resolved_when_clear_warned_fails(): from trex_core.application.reconciliation import sync_slot_to_broker class FailingWarnStore(InMemoryReconcileWarningStore): - def clear_warned(self, slot_id): + def clear_warned(self, slot_id, *, case_code=None): raise RuntimeError("DB unavailable") ns = InMemoryReconcileNotificationStore() diff --git a/tests/application/test_reconcile_warning_blocking.py b/tests/application/test_reconcile_warning_blocking.py index 73487b7..8acff52 100644 --- a/tests/application/test_reconcile_warning_blocking.py +++ b/tests/application/test_reconcile_warning_blocking.py @@ -892,6 +892,8 @@ def test_slot_to_dict_reconcile_warned_false_when_no_warn_store(): row = slot_to_dict(slot, warn_store=None) assert "reconcile_warned" in row assert row["reconcile_warned"] is False + assert row["trade_eligible"] is True + assert row["reconcile_warning_cases"] == [] def test_slot_to_dict_reconcile_warned_true_when_warned(): @@ -902,6 +904,8 @@ def test_slot_to_dict_reconcile_warned_true_when_warned(): warn_store.set_warned(str(slot.slot_id), portfolio_id="pf-A", case_code="B") row = slot_to_dict(slot, warn_store=warn_store) assert row["reconcile_warned"] is True + assert row["trade_eligible"] is False + assert row["reconcile_warning_cases"] == ["B"] def test_slot_to_dict_paused_and_warned_independent(): diff --git a/tests/application/test_reconcile_warning_store.py b/tests/application/test_reconcile_warning_store.py index 97f329e..7224aa9 100644 --- a/tests/application/test_reconcile_warning_store.py +++ b/tests/application/test_reconcile_warning_store.py @@ -33,14 +33,27 @@ def test_clear_warned_returns_false(): assert store.is_warned("slot-1") is False -# AC-3 (REQ-102): duplicate set_warned on same slot_id => upsert (single entry). -def test_set_warned_upsert_same_slot(): +# AC-3 (REQ-123): same slot can carry multiple active warning causes. +def test_set_warned_preserves_multiple_cases_on_same_slot(): store = _store() store.set_warned("slot-1", portfolio_id="pf-A", case_code="B", reason="first") store.set_warned("slot-1", portfolio_id="pf-A", case_code="C", reason="second") - # After second set, is_warned still True — single entry (no duplicate row). assert store.is_warned("slot-1") is True assert store.list_warned() == {"slot-1"} + info = store.get_warning_info("slot-1") + assert info is not None + assert info["case_codes"] == ["B", "C"] + + +def test_clear_warned_single_case_preserves_other_case(): + store = _store() + store.set_warned("slot-1", portfolio_id="pf-A", case_code="B") + store.set_warned("slot-1", portfolio_id="pf-A", case_code="C") + store.clear_warned("slot-1", case_code="C") + info = store.get_warning_info("slot-1") + assert info is not None + assert info["case_codes"] == ["B"] + assert store.is_warned("slot-1") is True # AC-5 (REQ-102): list_warned returns set of warned slot_ids. diff --git a/tests/application/test_slots_handler_quantity_mismatch.py b/tests/application/test_slots_handler_quantity_mismatch.py index 124a495..d181765 100644 --- a/tests/application/test_slots_handler_quantity_mismatch.py +++ b/tests/application/test_slots_handler_quantity_mismatch.py @@ -128,6 +128,44 @@ def test_ac1_single_portfolio_c_case_excluded(): assert resp.payload["slots"] == [] assert resp.payload["excluded_slots"]["reconcile_quantity_mismatch"] == 1 + assert resp.payload["excluded_slots"]["reconcile_warning_cases"] == {"C": 1} + + +def test_holding_slot_with_b_case_is_excluded_for_strategy(): + repo = InMemorySlotRepository() + svc = SlotService(repo) + warn_store = InMemoryReconcileWarningStore() + + slot = _make_holding_slot(repo, svc, portfolio_id="pf-A", symbol=SYM_A, qty=10) + warn_store.set_warned(str(slot.slot_id), portfolio_id="pf-A", case_code="B") + + handler = _make_handler(repo, warn_store) + resp = handler(_req(filter="holding")) + + assert resp.payload["slots"] == [] + assert resp.payload["excluded_slots"]["reconcile_quantity_mismatch"] == 1 + assert resp.payload["excluded_slots"]["reconcile_warning_cases"] == {"B": 1} + + +def test_holding_slot_with_b_and_c_cases_keeps_both_and_reports_both(): + repo = InMemorySlotRepository() + svc = SlotService(repo) + warn_store = InMemoryReconcileWarningStore() + + slot = _make_holding_slot(repo, svc, portfolio_id="pf-A", symbol=SYM_A, qty=10) + slot_id = str(slot.slot_id) + warn_store.set_warned(slot_id, portfolio_id="pf-A", case_code="B") + warn_store.set_warned(slot_id, portfolio_id="pf-A", case_code="C") + + handler = _make_handler(repo, warn_store) + resp = handler(_req(filter="holding")) + + assert resp.payload["slots"] == [] + assert resp.payload["excluded_slots"]["reconcile_quantity_mismatch"] == 1 + assert resp.payload["excluded_slots"]["reconcile_warning_cases"] == {"B": 1, "C": 1} + info = warn_store.get_warning_info(slot_id) + assert info is not None + assert info["case_codes"] == ["B", "C"] # --------------------------------------------------------------------------- @@ -286,7 +324,8 @@ def test_ac5_excluded_slots_count_zero_when_no_warnings(): resp = handler(_req(filter="holding")) assert "excluded_slots" in resp.payload - assert resp.payload["excluded_slots"] == {"reconcile_quantity_mismatch": 0} + assert resp.payload["excluded_slots"]["reconcile_quantity_mismatch"] == 0 + assert resp.payload["excluded_slots"]["reconcile_warning_cases"] == {} # --------------------------------------------------------------------------- @@ -312,8 +351,8 @@ def test_ac6_no_warn_store_no_filtering_no_excluded_slots_key(): # --------------------------------------------------------------------------- class BrokenWarnStore(InMemoryReconcileWarningStore): - """Simulates a warn_store that fails on list_c_case_warned.""" - def list_c_case_warned(self): + """Simulates a warn_store that fails on warning reads.""" + def list_warned(self): raise RuntimeError("db connection lost") @@ -356,7 +395,7 @@ def test_ac23_exclusion_precedes_broker_and_strategy_state_readers(): ) response = handler(_req(filter="holding")).payload assert response["slots"] == [] - assert response["excluded_slots"] == {"reconcile_quantity_mismatch": 1} + assert response["excluded_slots"]["reconcile_quantity_mismatch"] == 1 # --------------------------------------------------------------------------- diff --git a/tests/application/test_sync.py b/tests/application/test_sync.py index c09d08f..4079789 100644 --- a/tests/application/test_sync.py +++ b/tests/application/test_sync.py @@ -199,6 +199,22 @@ def test_sync_holding_qty_mismatch_updated(): assert not ws_out.is_warned(str(slot.slot_id)) +def test_sync_clears_only_b_case_when_slot_has_multiple_warning_causes(): + slot = _make_slot(SlotState.HOLDING, qty=5.0) + ws = InMemoryReconcileWarningStore() + slot_id = str(slot.slot_id) + ws.set_warned(slot_id, portfolio_id="pf-005930", case_code="B") + ws.set_warned(slot_id, portfolio_id="pf-005930", case_code="C") + + result, _repo, ws_out = _setup(slot, {"005930": 10}, warn_store=ws) + + assert result["warning_cleared"] is True + assert ws_out.is_warned(slot_id) is True + info = ws_out.get_warning_info(slot_id) + assert info is not None + assert info["case_codes"] == ["C"] + + # --------------------------------------------------------------------------- # AC-4: WAC seed from cost_basis_port when available # --------------------------------------------------------------------------- diff --git a/tests/application/test_verify.py b/tests/application/test_verify.py index 5adc88d..61f94cf 100644 --- a/tests/application/test_verify.py +++ b/tests/application/test_verify.py @@ -313,6 +313,40 @@ def test_verify_c_case_clear_preserves_b_case_warning(): assert b_info is not None and b_info["case_code"] == "B" +def test_verify_c_case_clear_on_slot_with_b_and_c_keeps_b(): + sym = "005930" + slot = _make_slot(status=SlotState.HOLDING, symbol=sym, pid="pf-c") + + repo = InMemorySlotRepository() + repo.add_slot(slot) + + ws = InMemoryReconcileWarningStore() + slot_id = str(slot.slot_id) + ws.set_warned(slot_id, portfolio_id="pf-c", case_code="B") + ws.set_warned(slot_id, portfolio_id="pf-c", case_code="C") + + store = SnapshotStore() + store.swap([ + PortfolioItem(portfolio_id="pf-c", symbol=sym, cash_balance=0.0, asset_quantity=10.0), + ]) + broker = FakeBroker({sym: 10}) + + result = verify_slot_reconcile( + portfolio_id="pf-c", + store=store, + broker=broker, + slot_repo=repo, + instance_key=INSTANCE, + warn_store=ws, + ) + + assert result["result"] == "cleared" + assert ws.is_warned(slot_id) is True + info = ws.get_warning_info(slot_id) + assert info is not None + assert info["case_codes"] == ["B"] + + def test_verify_c_case_clear_non_holding_slot(): """A non-HOLDING slot with C-case warning for the same symbol must also be cleared.""" sym = "005930" @@ -360,11 +394,11 @@ class _FailAfterNStore(InMemoryReconcileWarningStore): self._calls = 0 self._fail_after = fail_after - def clear_warned(self, slot_id: str) -> None: + def clear_warned(self, slot_id: str, *, case_code: str | None = None) -> None: self._calls += 1 if self._calls > self._fail_after: raise RuntimeError("simulated DB error") - super().clear_warned(slot_id) + super().clear_warned(slot_id, case_code=case_code) def test_verify_partial_clear_failure_returns_clear_failed(): diff --git a/tests/runtime/test_cli_operator.py b/tests/runtime/test_cli_operator.py index f110464..91f6d1e 100644 --- a/tests/runtime/test_cli_operator.py +++ b/tests/runtime/test_cli_operator.py @@ -418,7 +418,7 @@ def test_sync_fail_closed_skipped_error_exits_nonzero_without_writes( return SimpleNamespace(get_balance=lambda: []), None class _WarningStore: - def clear_warned(self, *_args): + def clear_warned(self, *_args, **_kwargs): raise AssertionError("warning clear must not be called") class _Connection: diff --git a/trex_core/adapters/persistence/sql/016_create_slot_reconcile_warning.sql b/trex_core/adapters/persistence/sql/016_create_slot_reconcile_warning.sql index e663962..98664c3 100644 --- a/trex_core/adapters/persistence/sql/016_create_slot_reconcile_warning.sql +++ b/trex_core/adapters/persistence/sql/016_create_slot_reconcile_warning.sql @@ -1,6 +1,6 @@ -- BAT-050 / REQ-102: reconcile-warning durable store (dcy-034). --- PK: slot_id (TEXT, UUID string). pause_store 동형 설계. --- ON CONFLICT DO UPDATE: 동일 slot_id 재삽입 시 최신 값으로 갱신. +-- Initial schema; migration 028 upgrades PK to (slot_id, case_code) +-- so B/C causes can coexist for the same slot. CREATE TABLE IF NOT EXISTS slot_reconcile_warning ( slot_id TEXT PRIMARY KEY, portfolio_id TEXT NOT NULL, diff --git a/trex_core/adapters/persistence/sql/028_preserve_reconcile_warning_cases.sql b/trex_core/adapters/persistence/sql/028_preserve_reconcile_warning_cases.sql new file mode 100644 index 0000000..11e967d --- /dev/null +++ b/trex_core/adapters/persistence/sql/028_preserve_reconcile_warning_cases.sql @@ -0,0 +1,7 @@ +-- REQ-123 / issue #83: +-- Preserve simultaneous warning causes by keying warnings per (slot_id, case_code). +ALTER TABLE slot_reconcile_warning + DROP CONSTRAINT IF EXISTS slot_reconcile_warning_pkey; + +ALTER TABLE slot_reconcile_warning + ADD CONSTRAINT slot_reconcile_warning_pkey PRIMARY KEY (slot_id, case_code); diff --git a/trex_core/adapters/portfolio/reconcile_warning_store.py b/trex_core/adapters/portfolio/reconcile_warning_store.py index 731b565..91f8c7a 100644 --- a/trex_core/adapters/portfolio/reconcile_warning_store.py +++ b/trex_core/adapters/portfolio/reconcile_warning_store.py @@ -1,8 +1,4 @@ -"""PostgreSQL-backed durable reconcile-warning store (REQ-102, BAT-050). - -pause_store.py와 동형 설계. PK: slot_id. case_code: 'B' | 'C'. -Survives daemon restart (dcy-034 NFR-1). -""" +"""PostgreSQL-backed durable reconcile-warning store (REQ-102, BAT-050).""" from __future__ import annotations from datetime import datetime, timezone @@ -12,7 +8,7 @@ from trex_core.adapters.persistence.postgresql import _require_psycopg class PostgreSQLReconcileWarningStore: - """`slot_reconcile_warning` table CRUD. slot_id PK is the gate (REQ-102).""" + """`slot_reconcile_warning` table CRUD keyed by (slot_id, case_code).""" def __init__(self, dsn: str, *, psycopg_module: Any = None) -> None: self._psycopg = _require_psycopg(psycopg_module) @@ -34,9 +30,8 @@ class PostgreSQLReconcileWarningStore: "INSERT INTO slot_reconcile_warning " "(slot_id, portfolio_id, case_code, actor, reason, created_at, updated_at) " "VALUES (%s, %s, %s, %s, %s, %s, %s) " - "ON CONFLICT (slot_id) DO UPDATE " + "ON CONFLICT (slot_id, case_code) DO UPDATE " "SET portfolio_id = EXCLUDED.portfolio_id, " - " case_code = EXCLUDED.case_code, " " actor = EXCLUDED.actor, " " reason = EXCLUDED.reason, " " updated_at = EXCLUDED.updated_at", @@ -44,13 +39,19 @@ class PostgreSQLReconcileWarningStore: ) conn.commit() - def clear_warned(self, slot_id: str) -> None: + def clear_warned(self, slot_id: str, *, case_code: str | None = None) -> None: with self._psycopg.connect(self._dsn, autocommit=False) as conn: with conn.cursor() as cur: - cur.execute( - "DELETE FROM slot_reconcile_warning WHERE slot_id = %s", - (slot_id,), - ) + if case_code is None: + cur.execute( + "DELETE FROM slot_reconcile_warning WHERE slot_id = %s", + (slot_id,), + ) + else: + cur.execute( + "DELETE FROM slot_reconcile_warning WHERE slot_id = %s AND case_code = %s", + (slot_id, case_code), + ) conn.commit() def is_warned(self, slot_id: str) -> bool: @@ -65,7 +66,7 @@ class PostgreSQLReconcileWarningStore: def list_warned(self) -> set[str]: with self._psycopg.connect(self._dsn) as conn: with conn.cursor() as cur: - cur.execute("SELECT slot_id FROM slot_reconcile_warning") + cur.execute("SELECT DISTINCT slot_id FROM slot_reconcile_warning") return {row[0] for row in cur.fetchall()} def list_c_case_warned(self) -> set[str]: @@ -73,26 +74,30 @@ class PostgreSQLReconcileWarningStore: with self._psycopg.connect(self._dsn) as conn: with conn.cursor() as cur: cur.execute( - "SELECT slot_id FROM slot_reconcile_warning WHERE case_code = %s", + "SELECT DISTINCT slot_id FROM slot_reconcile_warning WHERE case_code = %s", ("C",), ) return {row[0] for row in cur.fetchall()} def get_warning_info(self, slot_id: str) -> dict | None: - """Return {"portfolio_id", "case_code", "actor", "reason"} or None (REQ-105/106).""" + """Return warning info with full active case set, or None.""" with self._psycopg.connect(self._dsn) as conn: with conn.cursor() as cur: cur.execute( "SELECT portfolio_id, case_code, actor, reason " - "FROM slot_reconcile_warning WHERE slot_id = %s LIMIT 1", + "FROM slot_reconcile_warning WHERE slot_id = %s " + "ORDER BY CASE WHEN case_code = 'C' THEN 0 ELSE 1 END, updated_at DESC", (slot_id,), ) - row = cur.fetchone() - if row is None: + rows = cur.fetchall() + if not rows: return None + case_codes = sorted({str(row[1]) for row in rows if row[1]}) + preferred = rows[0] return { - "portfolio_id": row[0], - "case_code": row[1], - "actor": row[2], - "reason": row[3], + "portfolio_id": preferred[0], + "case_code": preferred[1], + "case_codes": case_codes, + "actor": preferred[2], + "reason": preferred[3], } diff --git a/trex_core/application/messaging_handlers.py b/trex_core/application/messaging_handlers.py index 9e5f291..f50c04a 100644 --- a/trex_core/application/messaging_handlers.py +++ b/trex_core/application/messaging_handlers.py @@ -263,28 +263,24 @@ def make_slots_rpc_handler( for s in holding_slots: watchdog_store.update(str(s.slot_id)) - # Build merged slot rows (REQ-074) - # BAT-050 / REQ-104: warn_store passed to slot_to_dict for reconcile_warned field. - slot_rows = [ - slot_to_dict( - s, - snapshot_store=snapshot_store, - watchdog_store=watchdog_store, - pause_store=pause_store, - warn_store=warn_store, - watchdog_timeout_sec=watchdog_timeout_sec, - ) - for s in slots - ] - - # AC-0023 exclusion must precede all optional data readers so excluded - # slots cannot expose state or make an otherwise valid response fail. - excluded_count = 0 + warning_cases_by_slot: dict[str, set[str]] = {} if warn_store is not None: try: - c_warned_ids = warn_store.list_c_case_warned() + warned_slot_ids = warn_store.list_warned() + for sid in warned_slot_ids: + info = warn_store.get_warning_info(sid) + if info is None: + continue + raw_codes = info.get("case_codes") + if isinstance(raw_codes, list): + codes = {str(code) for code in raw_codes if code} + else: + case_code = str(info.get("case_code", "")) + codes = {case_code} if case_code else set() + if codes: + warning_cases_by_slot[str(sid)] = codes except Exception: # noqa: BLE001 - _log.exception("warn_store.list_c_case_warned() failed — fail-closed") + _log.exception("warn_store warning query failed — fail-closed") return RpcResponse(payload={ "slots": [], "available_slots": None, @@ -296,18 +292,42 @@ def make_slots_rpc_handler( ), "excluded_slots": {"reconcile_quantity_mismatch": 0}, }) - if c_warned_ids: - included = [ - (slot, row) - for slot, row in zip(slots, slot_rows, strict=True) - if not ( - slot.status.value == "holding" - and str(slot.slot_id) in c_warned_ids - ) - ] - excluded_count = len(slots) - len(included) + + # Build merged slot rows (REQ-074) + slot_rows = [ + slot_to_dict( + s, + snapshot_store=snapshot_store, + watchdog_store=watchdog_store, + pause_store=pause_store, + warning_cases_by_slot=warning_cases_by_slot, + watchdog_timeout_sec=watchdog_timeout_sec, + ) + for s in slots + ] + + # Exclusion must precede all optional data readers so blocked slots cannot + # expose state or make an otherwise valid response fail. + excluded_count = 0 + excluded_case_counts: dict[str, int] = {} + if warn_store is not None: + included: list[tuple[object, dict]] = [] + for slot, row in zip(slots, slot_rows, strict=True): + blocked_holding = ( + slot.status.value == "holding" and bool(row.get("reconcile_warned")) + ) + if blocked_holding: + excluded_count += 1 + for code in row.get("reconcile_warning_cases", []): + excluded_case_counts[code] = excluded_case_counts.get(code, 0) + 1 + continue + included.append((slot, row)) + if included: slots = [slot for slot, _ in included] slot_rows = [row for _, row in included] + else: + slots = [] + slot_rows = [] broker_qty_by_symbol: dict[str, int] = {} broker_qty_available = False @@ -410,7 +430,10 @@ def make_slots_rpc_handler( "message": message, } if warn_store is not None: - base_payload["excluded_slots"] = {"reconcile_quantity_mismatch": excluded_count} + base_payload["excluded_slots"] = { + "reconcile_quantity_mismatch": excluded_count, + "reconcile_warning_cases": excluded_case_counts, + } return RpcResponse(payload=base_payload) return handler diff --git a/trex_core/application/portfolio.py b/trex_core/application/portfolio.py index abe519b..ad2b7c0 100644 --- a/trex_core/application/portfolio.py +++ b/trex_core/application/portfolio.py @@ -359,7 +359,7 @@ class InMemoryKillSwitchStore: class ReconcileWarningStore(Protocol): - """Durable reconcile-warning overlay — slot_id PK (REQ-102, dcy-034).""" + """Durable reconcile-warning overlay keyed by (slot_id, case_code).""" def set_warned( self, @@ -372,7 +372,7 @@ class ReconcileWarningStore(Protocol): ) -> None: ... - def clear_warned(self, slot_id: str) -> None: + def clear_warned(self, slot_id: str, *, case_code: str | None = None) -> None: ... def is_warned(self, slot_id: str) -> bool: @@ -382,10 +382,14 @@ class ReconcileWarningStore(Protocol): ... def get_warning_info(self, slot_id: str) -> dict | None: - """Return {"portfolio_id", "case_code", "actor", "reason"} or None. + """Return warning info dict or None. - Used by verify to determine whether the warning is case_code='C' - (verify's responsibility) vs 'B' (sync's responsibility, REQ-106 OQ-C). + Returned dict includes: + {"portfolio_id", "case_code", "case_codes", "actor", "reason"} + where case_code is a backward-compatible preferred case and case_codes is + the full active case set for the slot. + + Used by verify to determine whether C-case is active (REQ-106 OQ-C). Returns None when the slot has no active warning. """ ... @@ -403,8 +407,8 @@ class InMemoryReconcileWarningStore: def __init__(self) -> None: self._lock = threading.Lock() - # slot_id -> {"portfolio_id", "case_code", "actor", "reason"} - self._warned: dict[str, dict] = {} + # slot_id -> case_code -> {"portfolio_id", "actor", "reason"} + self._warned: dict[str, dict[str, dict]] = {} def set_warned( self, @@ -416,16 +420,24 @@ class InMemoryReconcileWarningStore: reason: str = "", ) -> None: with self._lock: - self._warned[slot_id] = { + per_case = self._warned.setdefault(slot_id, {}) + per_case[case_code] = { "portfolio_id": portfolio_id, - "case_code": case_code, "actor": actor, "reason": reason, } - def clear_warned(self, slot_id: str) -> None: + def clear_warned(self, slot_id: str, *, case_code: str | None = None) -> None: with self._lock: - self._warned.pop(slot_id, None) + if case_code is None: + self._warned.pop(slot_id, None) + return + per_case = self._warned.get(slot_id) + if not per_case: + return + per_case.pop(case_code, None) + if not per_case: + self._warned.pop(slot_id, None) def is_warned(self, slot_id: str) -> bool: with self._lock: @@ -437,12 +449,23 @@ class InMemoryReconcileWarningStore: def get_warning_info(self, slot_id: str) -> dict | None: with self._lock: - info = self._warned.get(slot_id) - return dict(info) if info is not None else None + per_case = self._warned.get(slot_id) + if not per_case: + return None + case_codes = sorted(per_case.keys()) + preferred_case = "C" if "C" in per_case else case_codes[0] + preferred = per_case[preferred_case] + return { + "portfolio_id": preferred.get("portfolio_id", ""), + "case_code": preferred_case, + "case_codes": case_codes, + "actor": preferred.get("actor", ""), + "reason": preferred.get("reason", ""), + } def list_c_case_warned(self) -> set[str]: with self._lock: - return {sid for sid, info in self._warned.items() if info.get("case_code") == "C"} + return {sid for sid, per_case in self._warned.items() if "C" in per_case} class ReconcileNotificationStore(Protocol): @@ -544,6 +567,7 @@ def slot_to_dict( watchdog_store=None, pause_store: PauseStore | None = None, warn_store: ReconcileWarningStore | None = None, + warning_cases_by_slot: dict[str, set[str]] | None = None, watchdog_timeout_sec: int = 120, ) -> dict: """Merged slot row for trex.slots.req (REQ-073/074). @@ -618,10 +642,23 @@ def slot_to_dict( # BAT-050 / REQ-104: reconcile_warned overlay (ReconcileWarningStore) — additive field. # Bulk list_warned() called once per RPC (caller pre-fetches; see make_slots_rpc_handler). # warn_store=None → reconcile_warned=False (backward compatible, NFR-4). - reconcile_warned = False - if warn_store is not None: - reconcile_warned = str(s.slot_id) in warn_store.list_warned() + warning_cases: set[str] = set() + if warning_cases_by_slot is not None: + warning_cases = set(warning_cases_by_slot.get(str(s.slot_id), set())) + elif warn_store is not None: + info = warn_store.get_warning_info(str(s.slot_id)) + if info is not None: + raw_cases = info.get("case_codes") + if isinstance(raw_cases, list): + warning_cases = {str(c) for c in raw_cases if c} + else: + case_code = str(info.get("case_code", "")) + if case_code: + warning_cases = {case_code} + reconcile_warned = bool(warning_cases) d["reconcile_warned"] = reconcile_warned + d["reconcile_warning_cases"] = sorted(warning_cases) + d["trade_eligible"] = not reconcile_warned return d @@ -637,4 +674,3 @@ def _sanitize(message: str) -> str: out = out[:idx] + "" break return out[:200] - diff --git a/trex_core/application/reconciliation.py b/trex_core/application/reconciliation.py index aca2c5d..bf326c1 100644 --- a/trex_core/application/reconciliation.py +++ b/trex_core/application/reconciliation.py @@ -629,7 +629,7 @@ def sync_slot_to_broker( Broker qty == 0 for slot → skipped with WARN (slot-side A-case guard). Broker-only (no slot) → NOT handled here; caller filters (FR-3). - After update, if slot.qty == broker_qty: clear_warned(slot_id). + After update, if slot.qty == broker_qty: clear_warned(slot_id, case_code="B"). """ from uuid import UUID @@ -870,14 +870,15 @@ def sync_slot_to_broker( after_avg = float(refreshed.avg_price) if (refreshed and refreshed.avg_price is not None) else None after = {"qty": after_qty, "status": after_status, "avg_price": after_avg} - # Clear warning when qty now matches broker + # Clear B-case warning when qty now matches broker warning_cleared = False if after_qty is not None and int(after_qty) == broker_qty: try: - warn_store.clear_warned(slot_id) + warn_store.clear_warned(slot_id, case_code="B") warning_cleared = True _log.info( - "sync: reconcile-warning cleared slot=%s symbol=%s broker_qty=%d actor=sync", + "sync: reconcile-warning cleared slot=%s symbol=%s case_code=B " + "broker_qty=%d actor=sync", slot_id, sym, broker_qty, ) except Exception: # noqa: BLE001 @@ -962,7 +963,7 @@ def verify_slot_reconcile( "reason": "no active reconcile-warning (already cleared or never set)", } - # Check case_code — verify is C-only (REQ-106 OQ-C). + # Check case set — verify is C-only (REQ-106 OQ-C). info = warn_store.get_warning_info(slot_id_str) if info is None: return { @@ -974,8 +975,13 @@ def verify_slot_reconcile( "reason": "warning exists but get_warning_info returned None (unexpected)", } - case_code = info.get("case_code", "") - if case_code != "C": + case_codes_raw = info.get("case_codes") + if isinstance(case_codes_raw, list): + case_codes = {str(code) for code in case_codes_raw if code} + else: + case_code = str(info.get("case_code", "")) + case_codes = {case_code} if case_code else set() + if "C" not in case_codes: return { "portfolio_id": portfolio_id, "slot_id": slot_id_str, @@ -983,7 +989,7 @@ def verify_slot_reconcile( "hub_qty": None, "broker_qty": None, "reason": ( - f"warning case_code='{case_code}' is not 'C' — " + f"warning case_codes={sorted(case_codes)} do not include 'C' — " "use 'trex-core sync' to resolve B-case (slot↔broker qty mismatch)" ), } @@ -1014,9 +1020,17 @@ def verify_slot_reconcile( continue sid_str = str(s.slot_id) warn_info = warn_store.get_warning_info(sid_str) - if warn_info is None or warn_info.get("case_code") != "C": + if warn_info is None: continue - warn_store.clear_warned(sid_str) + warned_codes_raw = warn_info.get("case_codes") + if isinstance(warned_codes_raw, list): + warned_codes = {str(code) for code in warned_codes_raw if code} + else: + case_code = str(warn_info.get("case_code", "")) + warned_codes = {case_code} if case_code else set() + if "C" not in warned_codes: + continue + warn_store.clear_warned(sid_str, case_code="C") store.set_warning(s.portfolio_id, False) cleared_slots.append(sid_str) _log.info( diff --git a/trex_core/runtime/cli.py b/trex_core/runtime/cli.py index 128ef21..d985ad0 100644 --- a/trex_core/runtime/cli.py +++ b/trex_core/runtime/cli.py @@ -912,7 +912,15 @@ def _cmd_verify(args, cfg) -> int: c_slots: list[str] = [] for sid in warn_store.list_warned(): info = warn_store.get_warning_info(sid) - if info and info.get("case_code") == "C": + if not info: + continue + raw_codes = info.get("case_codes") + if isinstance(raw_codes, list): + case_codes = {str(code) for code in raw_codes if code} + else: + case_code = str(info.get("case_code", "")) + case_codes = {case_code} if case_code else set() + if "C" in case_codes: c_slots.append(info.get("portfolio_id", "")) target_pids = [p for p in c_slots if p] diff --git a/trex_core/runtime/daemon.py b/trex_core/runtime/daemon.py index d232973..8af08bb 100644 --- a/trex_core/runtime/daemon.py +++ b/trex_core/runtime/daemon.py @@ -198,7 +198,7 @@ class Daemon: # BAT-010/011: per-slot watchdog (snapshot RPC writer, safety-sell reader). self.watchdog = WatchdogStore() self.pause_store = PostgreSQLPauseStore(config.dsn) - # BAT-050 / REQ-102: durable reconcile-warning store (slot_id PK). + # BAT-050 / REQ-102: durable reconcile-warning store ((slot_id, case_code) PK). self.warn_store = PostgreSQLReconcileWarningStore(config.dsn) # req-0007 / ac-0024: durable reconcile notification deduplication store. self.notification_store = PostgreSQLReconcileNotificationStore(config.dsn) From 09b1b4f4c3d78c985796d3275e2b04815ee984f9 Mon Sep 17 00:00:00 2001 From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com> Date: Sat, 12 Sep 2026 13:24:58 +0000 Subject: [PATCH 04/11] fix: isolate ledger outbox delivery by instance Co-authored-by: genichin <4282227+genichin@users.noreply.github.com> --- .../persistence/test_migration_and_drift.py | 112 +++++++++------ .../test_postgresql_ledger_outbox.py | 128 +++++++++++++++--- tests/application/test_ledger_outbox.py | 27 ++++ tests/runtime/test_cli_ledger_backfill.py | 18 ++- trex_core/adapters/persistence/postgresql.py | 91 +++++++++++-- .../sql/028_ledger_outbox_instance_claims.sql | 22 +++ trex_core/application/ledger_outbox.py | 108 ++++++++++++++- trex_core/runtime/cli.py | 2 +- trex_core/runtime/daemon.py | 2 +- 9 files changed, 429 insertions(+), 81 deletions(-) create mode 100644 trex_core/adapters/persistence/sql/028_ledger_outbox_instance_claims.sql diff --git a/tests/adapters/persistence/test_migration_and_drift.py b/tests/adapters/persistence/test_migration_and_drift.py index 3a35cd3..592cc60 100644 --- a/tests/adapters/persistence/test_migration_and_drift.py +++ b/tests/adapters/persistence/test_migration_and_drift.py @@ -6,9 +6,10 @@ iteration: EXPECTED_SLOT_FIELDS (code contract) vs daily_slot actual columns """ from __future__ import annotations +from datetime import UTC, datetime + import psycopg import pytest -from datetime import datetime, timezone from trex_core.adapters.persistence.migrate import apply_migrations, migration_files from trex_core.adapters.persistence.postgresql import ( @@ -33,24 +34,22 @@ _EXPECTED_TABLES = { def _columns(dsn: str, table: str) -> set[str]: - with psycopg.connect(dsn) as conn: - with conn.cursor() as cur: - cur.execute( - "SELECT column_name FROM information_schema.columns " - "WHERE table_schema = 'public' AND table_name = %s", - (table,), - ) - return {r[0] for r in cur.fetchall()} + with psycopg.connect(dsn) as conn, conn.cursor() as cur: + cur.execute( + "SELECT column_name FROM information_schema.columns " + "WHERE table_schema = 'public' AND table_name = %s", + (table,), + ) + return {r[0] for r in cur.fetchall()} def test_migrations_create_expected_tables(pg_clean): assert migration_files(), "no migration files found" - with psycopg.connect(pg_clean) as conn: - with conn.cursor() as cur: - cur.execute( - "SELECT table_name FROM information_schema.tables WHERE table_schema='public'" - ) - tables = {r[0] for r in cur.fetchall()} + with psycopg.connect(pg_clean) as conn, conn.cursor() as cur: + cur.execute( + "SELECT table_name FROM information_schema.tables WHERE table_schema='public'" + ) + tables = {r[0] for r in cur.fetchall()} assert _EXPECTED_TABLES <= tables @@ -61,20 +60,19 @@ def test_daily_slot_columns_match_expected_contract(pg_clean): def test_strategy_state_schema_matches_instance_map_contract(pg_clean): - with psycopg.connect(pg_clean) as conn: - with conn.cursor() as cur: - cur.execute( - "SELECT column_name, data_type, udt_name " - "FROM information_schema.columns " - "WHERE table_schema = 'public' AND table_name = 'slot_strategy_state'" - ) - columns = {row[0]: (row[1], row[2]) for row in cur.fetchall()} - cur.execute( - "SELECT a.attname FROM pg_index i " - "JOIN pg_attribute a ON a.attrelid = i.indrelid AND a.attnum = ANY(i.indkey) " - "WHERE i.indrelid = 'slot_strategy_state'::regclass AND i.indisprimary" - ) - primary_key = {row[0] for row in cur.fetchall()} + with psycopg.connect(pg_clean) as conn, conn.cursor() as cur: + cur.execute( + "SELECT column_name, data_type, udt_name " + "FROM information_schema.columns " + "WHERE table_schema = 'public' AND table_name = 'slot_strategy_state'" + ) + columns = {row[0]: (row[1], row[2]) for row in cur.fetchall()} + cur.execute( + "SELECT a.attname FROM pg_index i " + "JOIN pg_attribute a ON a.attrelid = i.indrelid AND a.attnum = ANY(i.indkey) " + "WHERE i.indrelid = 'slot_strategy_state'::regclass AND i.indisprimary" + ) + primary_key = {row[0] for row in cur.fetchall()} assert columns == {"slot_id": ("uuid", "uuid"), "data": ("jsonb", "jsonb")} assert primary_key == {"slot_id"} @@ -111,13 +109,12 @@ def test_migration_replay_converts_existing_auto_venue_row_to_sor(pg_clean): apply_migrations(pg_clean) assert repo.fetch_slot(slot.slot_id).venue == "SOR" - with psycopg.connect(pg_clean) as conn: - with conn.cursor() as cur: - with pytest.raises(psycopg.errors.CheckViolation): - cur.execute( - "UPDATE daily_slot SET venue = 'AUTO' WHERE slot_id = %s", - (slot.slot_id,), - ) + with psycopg.connect(pg_clean) as conn, conn.cursor() as cur: + with pytest.raises(psycopg.errors.CheckViolation): + cur.execute( + "UPDATE daily_slot SET venue = 'AUTO' WHERE slot_id = %s", + (slot.slot_id,), + ) def test_migration_024_separates_legacy_sor_and_is_replay_safe(pg_clean): @@ -129,7 +126,7 @@ def test_migration_024_separates_legacy_sor_and_is_replay_safe(pg_clean): side="buy", qty=1, price=1000, - executed_at=datetime(2026, 8, 19, tzinfo=timezone.utc), + executed_at=datetime(2026, 8, 19, tzinfo=UTC), venue="NXT", order_venue="KRX", ) @@ -140,7 +137,7 @@ def test_migration_024_separates_legacy_sor_and_is_replay_safe(pg_clean): side="buy", qty=1, price=1000, - executed_at=datetime(2026, 8, 19, tzinfo=timezone.utc), + executed_at=datetime(2026, 8, 19, tzinfo=UTC), venue="KRX", order_venue="SOR", ) @@ -172,10 +169,39 @@ def test_migration_024_separates_legacy_sor_and_is_replay_safe(pg_clean): assert legacy_row.trade.venue is None assert legacy_row.trade.order_venue == "SOR" + with psycopg.connect(pg_clean) as conn, conn.cursor() as cur: + with pytest.raises(psycopg.errors.CheckViolation): + cur.execute( + "UPDATE ledger_outbox SET venue='SOR' WHERE correlation_id=%s", + (normal.correlation_id,), + ) + + +def test_migration_028_fail_closes_unowned_legacy_outbox_rows(pg_clean): + outbox = PostgreSQLLedgerOutbox(pg_clean, instance_key="inst-a") + trade = LedgerTrade( + asset_id="PF-LEGACY", + order_id="O-LEGACY", + execution_id="E-LEGACY", + side="buy", + qty=1, + price=1000, + executed_at=datetime(2026, 9, 12, tzinfo=UTC), + ) + outbox.enqueue(trade) + with psycopg.connect(pg_clean) as conn: with conn.cursor() as cur: - with pytest.raises(psycopg.errors.CheckViolation): - cur.execute( - "UPDATE ledger_outbox SET venue='SOR' WHERE correlation_id=%s", - (normal.correlation_id,), - ) + cur.execute("ALTER TABLE ledger_outbox ALTER COLUMN instance_key DROP NOT NULL") + cur.execute("ALTER TABLE ledger_outbox ALTER COLUMN instance_key DROP DEFAULT") + cur.execute( + "UPDATE ledger_outbox SET instance_key=NULL WHERE correlation_id=%s", + (trade.correlation_id,), + ) + conn.commit() + + apply_migrations(pg_clean) + stored = outbox.get(trade.correlation_id) + assert stored is not None + assert stored.instance_key == "__unowned__" + assert outbox.list_pending() == [] diff --git a/tests/adapters/persistence/test_postgresql_ledger_outbox.py b/tests/adapters/persistence/test_postgresql_ledger_outbox.py index ef65a3c..6f51388 100644 --- a/tests/adapters/persistence/test_postgresql_ledger_outbox.py +++ b/tests/adapters/persistence/test_postgresql_ledger_outbox.py @@ -4,7 +4,7 @@ Skipped without TREX_POSTGRESQL_TEST_DSN (same gate as other PG suites). """ from __future__ import annotations -from datetime import datetime, timezone +from datetime import UTC, datetime from trex_core.adapters.ledger.in_memory import InMemoryLedger from trex_core.adapters.persistence.postgresql import PostgreSQLLedgerOutbox @@ -13,34 +13,40 @@ from trex_core.application.ledger_outbox import ( OutboxOutcome, WorkItemStatus, ) -from trex_core.application.ledger_port import LedgerTrade +from trex_core.application.ledger_port import ( + LedgerRetryableError, + LedgerTrade, + LedgerWriteOutcome, + LedgerWriteResult, +) def _trade(execution_id="paper:1:10") -> LedgerTrade: return LedgerTrade( asset_id="PF-1", order_id="ORD-1", execution_id=execution_id, side="buy", qty=10, price=1000.0, fee=1.5, tax=0.0, - executed_at=datetime(2026, 6, 4, tzinfo=timezone.utc), + executed_at=datetime(2026, 6, 4, tzinfo=UTC), venue="NXT", order_venue="SOR", ) def test_enqueue_persists_and_is_idempotent(pg_clean): - outbox = PostgreSQLLedgerOutbox(pg_clean) + outbox = PostgreSQLLedgerOutbox(pg_clean, instance_key="inst-a") a = outbox.enqueue(_trade()) b = outbox.enqueue(_trade()) assert a.correlation_id == b.correlation_id pending = outbox.list_pending() assert len(pending) == 1 assert pending[0].status is WorkItemStatus.PENDING + assert pending[0].instance_key == "inst-a" assert pending[0].trade.venue == "NXT" assert pending[0].trade.order_venue == "SOR" def test_writer_completes_persisted_item(pg_clean): - outbox = PostgreSQLLedgerOutbox(pg_clean) + outbox = PostgreSQLLedgerOutbox(pg_clean, instance_key="inst-a") ledger = InMemoryLedger() - writer = LedgerWriter(outbox, ledger) + writer = LedgerWriter(outbox, ledger, instance_key="inst-a") outbox.enqueue(_trade(execution_id="pg-1")) stats = writer.run_once() assert stats.completed == 1 and ledger.count() == 1 @@ -50,9 +56,9 @@ def test_writer_completes_persisted_item(pg_clean): def test_writer_marks_conflict_blocked_on_pg(pg_clean): - outbox = PostgreSQLLedgerOutbox(pg_clean) + outbox = PostgreSQLLedgerOutbox(pg_clean, instance_key="inst-a") ledger = InMemoryLedger(conflict_executions={"pg-x"}) - writer = LedgerWriter(outbox, ledger) + writer = LedgerWriter(outbox, ledger, instance_key="inst-a") outbox.enqueue(_trade(execution_id="pg-x")) writer.run_once() row = outbox.get("PF-1:ORD-1:pg-x") @@ -61,10 +67,10 @@ def test_writer_marks_conflict_blocked_on_pg(pg_clean): def test_writer_retries_on_pg(pg_clean): - outbox = PostgreSQLLedgerOutbox(pg_clean) + outbox = PostgreSQLLedgerOutbox(pg_clean, instance_key="inst-a") ledger = InMemoryLedger(fail_n_then_succeed=1) # dcy-015: base 0 => next_retry_at == now, so the row is immediately due again. - writer = LedgerWriter(outbox, ledger, retry_base_sec=0.0) + writer = LedgerWriter(outbox, ledger, retry_base_sec=0.0, instance_key="inst-a") outbox.enqueue(_trade(execution_id="pg-r")) writer.run_once() row1 = outbox.get("PF-1:ORD-1:pg-r") @@ -79,9 +85,9 @@ def test_writer_retries_on_pg(pg_clean): def test_writer_marks_delivery_failed_permanent_on_pg(pg_clean): """dcy-015 / REQ-019: 404/permanent → terminal delivery_failed persisted (migration 007 status enum + last_outcome). No retry.""" - outbox = PostgreSQLLedgerOutbox(pg_clean) + outbox = PostgreSQLLedgerOutbox(pg_clean, instance_key="inst-a") ledger = InMemoryLedger(permanent_executions={"pg-perm"}) - writer = LedgerWriter(outbox, ledger) + writer = LedgerWriter(outbox, ledger, instance_key="inst-a") outbox.enqueue(_trade(execution_id="pg-perm")) s = writer.run_once() assert s.delivery_failed == 1 @@ -94,22 +100,112 @@ def test_writer_marks_delivery_failed_permanent_on_pg(pg_clean): def test_pending_cash_delta_on_pg(pg_clean): """dcy-018 / REQ-029: estimated cash delta of pending rows summed by asset (SQL).""" - outbox = PostgreSQLLedgerOutbox(pg_clean) + outbox = PostgreSQLLedgerOutbox(pg_clean, instance_key="inst-a") outbox.enqueue(LedgerTrade(asset_id="PF-1", order_id="O-1", execution_id="cd-buy", side="buy", qty=10, price=1000.0, fee=1.0, tax=0.0, - executed_at=datetime(2026, 6, 4, tzinfo=timezone.utc))) + executed_at=datetime(2026, 6, 4, tzinfo=UTC))) deltas = outbox.pending_cash_delta() assert deltas["PF-1"] == -(10 * 1000.0 + 1.0) # buy => cash down by notional+fee def test_backoff_row_skipped_by_pending_scan_on_pg(pg_clean): """dcy-015 / REQ-019: a future next_retry_at excludes the row from list_pending.""" - outbox = PostgreSQLLedgerOutbox(pg_clean) + outbox = PostgreSQLLedgerOutbox(pg_clean, instance_key="inst-a") ledger = InMemoryLedger(fail_n_then_succeed=99) # large base => next_retry_at well in the future - writer = LedgerWriter(outbox, ledger, retry_base_sec=600.0, max_attempts=99) + writer = LedgerWriter( + outbox, ledger, retry_base_sec=600.0, max_attempts=99, instance_key="inst-a" + ) outbox.enqueue(_trade(execution_id="pg-bo")) writer.run_once() # -> retryable, next_retry_at ~ now + 600s row = outbox.get("PF-1:ORD-1:pg-bo") assert row.status is WorkItemStatus.PENDING and row.next_retry_at is not None assert outbox.list_pending() == [] # still backing off -> skipped + + +def test_pending_claims_are_isolated_per_instance(pg_clean): + ledger = InMemoryLedger() + outbox_a = PostgreSQLLedgerOutbox(pg_clean, instance_key="inst-a") + outbox_b = PostgreSQLLedgerOutbox(pg_clean, instance_key="inst-b") + writer_a = LedgerWriter(outbox_a, ledger, instance_key="inst-a") + writer_b = LedgerWriter(outbox_b, ledger, instance_key="inst-b") + row_a = outbox_a.enqueue(_trade(execution_id="pg-a")) + row_b = outbox_b.enqueue(_trade(execution_id="pg-b")) + + stats_a = writer_a.run_once() + assert stats_a.completed == 1 and ledger.count() == 1 + assert outbox_a.get(row_a.correlation_id).status is WorkItemStatus.COMPLETED + assert outbox_b.get(row_b.correlation_id).status is WorkItemStatus.PENDING + + stats_b = writer_b.run_once() + assert stats_b.completed == 1 and ledger.count() == 2 + assert outbox_b.get(row_b.correlation_id).status is WorkItemStatus.COMPLETED + + +def test_claim_expiry_allows_safe_recovery_after_worker_crash(pg_clean): + now = {"t": datetime(2026, 6, 4, tzinfo=UTC)} + outbox_a = PostgreSQLLedgerOutbox( + pg_clean, + instance_key="inst-a", + claim_ttl_sec=5.0, + worker_id="worker-a", + clock=lambda: now["t"], + ) + outbox_b = PostgreSQLLedgerOutbox( + pg_clean, + instance_key="inst-a", + claim_ttl_sec=5.0, + worker_id="worker-b", + clock=lambda: now["t"], + ) + row = outbox_a.enqueue(_trade(execution_id="pg-crash")) + + claimed_a = outbox_a.claim_pending() + assert [item.correlation_id for item in claimed_a] == [row.correlation_id] + assert outbox_b.claim_pending() == [] + + now["t"] = datetime(2026, 6, 4, 0, 0, 6, tzinfo=UTC) + claimed_b = outbox_b.claim_pending() + assert [item.correlation_id for item in claimed_b] == [row.correlation_id] + + +def test_writer_records_retryable_403_without_cross_instance_delivery(pg_clean): + class _ForbiddenLedger: + def __init__(self): + self.calls: list[str] = [] + + def record_trade(self, trade): + self.calls.append(trade.execution_id) + raise LedgerRetryableError("portfolio-hub 403 Forbidden") + + outbox_a = PostgreSQLLedgerOutbox(pg_clean, instance_key="inst-a") + outbox_b = PostgreSQLLedgerOutbox(pg_clean, instance_key="inst-b") + writer_b = LedgerWriter( + outbox_b, _ForbiddenLedger(), retry_base_sec=0.0, instance_key="inst-b" + ) + row_a = outbox_a.enqueue(_trade(execution_id="pg-403-a")) + row_b = outbox_b.enqueue(_trade(execution_id="pg-403-b")) + + stats_b = writer_b.run_once() + + assert stats_b.retryable == 1 + assert outbox_b.get(row_b.correlation_id).last_outcome is OutboxOutcome.RETRYABLE_FAILURE + assert outbox_a.get(row_a.correlation_id).status is WorkItemStatus.PENDING + + +def test_writer_marks_duplicate_completed_from_adapter_response_on_pg(pg_clean): + class _DuplicateLedger: + def record_trade(self, _trade): + return LedgerWriteOutcome(LedgerWriteResult.DUPLICATE_OK) + + outbox = PostgreSQLLedgerOutbox(pg_clean, instance_key="inst-a") + writer = LedgerWriter(outbox, _DuplicateLedger(), instance_key="inst-a") + row = outbox.enqueue(_trade(execution_id="pg-dup")) + + outcome = writer.process_correlation_id(row.correlation_id) + + assert outcome is OutboxOutcome.DUPLICATE_COMPLETED + stored = outbox.get(row.correlation_id) + assert stored is not None + assert stored.status is WorkItemStatus.COMPLETED + assert stored.last_outcome is OutboxOutcome.DUPLICATE_COMPLETED diff --git a/tests/application/test_ledger_outbox.py b/tests/application/test_ledger_outbox.py index 5ce7f71..e085f30 100644 --- a/tests/application/test_ledger_outbox.py +++ b/tests/application/test_ledger_outbox.py @@ -83,3 +83,30 @@ def test_process_correlation_id_only_drains_requested_row(): assert ledger.count() == 1 assert outbox.get(first.correlation_id).status is WorkItemStatus.COMPLETED assert outbox.get(second.correlation_id).status is WorkItemStatus.PENDING + + +def test_process_correlation_id_skips_foreign_instance_row(): + outbox = InMemoryLedgerOutbox(instance_key="inst-a") + ledger = InMemoryLedger() + writer = LedgerWriter(outbox, ledger, instance_key="inst-b") + item = outbox.enqueue(_trade(execution_id="e-foreign")) + + outcome = writer.process_correlation_id(item.correlation_id) + + assert outcome is None + assert ledger.count() == 0 + assert writer.counters["claim:foreign_instance"] == 1 + assert outbox.get(item.correlation_id).status is WorkItemStatus.PENDING + + +def test_writer_exposes_claim_and_outcome_counters(): + outbox = InMemoryLedgerOutbox(instance_key="inst-a") + ledger = InMemoryLedger() + writer = LedgerWriter(outbox, ledger, instance_key="inst-a") + outbox.enqueue(_trade(execution_id="e-count")) + + stats = writer.run_once() + + assert stats.completed == 1 + assert writer.counters["claim:claimed"] == 1 + assert writer.counters["outcome:completed"] == 1 diff --git a/tests/runtime/test_cli_ledger_backfill.py b/tests/runtime/test_cli_ledger_backfill.py index e09282f..17455ff 100644 --- a/tests/runtime/test_cli_ledger_backfill.py +++ b/tests/runtime/test_cli_ledger_backfill.py @@ -187,7 +187,11 @@ def test_ledger_backfill_existing_completed_row_is_idempotent(monkeypatch, tmp_p import trex_core.adapters.ledger.portfolio_hub as hub_mod import trex_core.adapters.persistence.postgresql as pg_mod - monkeypatch.setattr(pg_mod, "PostgreSQLLedgerOutbox", lambda dsn: _Outbox()) + monkeypatch.setattr( + pg_mod, + "PostgreSQLLedgerOutbox", + lambda dsn, *, instance_key: _Outbox(), + ) monkeypatch.setattr(hub_mod, "PortfolioHubLedger", lambda *args, **kwargs: object()) monkeypatch.setattr(cli, "LedgerWriter", _Writer) monkeypatch.setattr( @@ -246,7 +250,11 @@ def test_ledger_backfill_live_enqueue_and_processes_exact_trade(monkeypatch, tmp import trex_core.adapters.ledger.portfolio_hub as hub_mod import trex_core.adapters.persistence.postgresql as pg_mod - monkeypatch.setattr(pg_mod, "PostgreSQLLedgerOutbox", lambda dsn: outbox) + monkeypatch.setattr( + pg_mod, + "PostgreSQLLedgerOutbox", + lambda dsn, *, instance_key: outbox, + ) monkeypatch.setattr(hub_mod, "PortfolioHubLedger", lambda *args, **kwargs: object()) monkeypatch.setattr(cli, "LedgerWriter", _Writer) monkeypatch.setattr( @@ -310,7 +318,11 @@ def test_ledger_backfill_resolves_matching_skip(monkeypatch, tmp_path, capsys): import trex_core.adapters.ledger.portfolio_hub as hub_mod import trex_core.adapters.persistence.postgresql as pg_mod - monkeypatch.setattr(pg_mod, "PostgreSQLLedgerOutbox", lambda dsn: _Outbox()) + monkeypatch.setattr( + pg_mod, + "PostgreSQLLedgerOutbox", + lambda dsn, *, instance_key: _Outbox(), + ) monkeypatch.setattr(hub_mod, "PortfolioHubLedger", lambda *args, **kwargs: object()) monkeypatch.setattr(cli, "LedgerWriter", _Writer) monkeypatch.setattr( diff --git a/trex_core/adapters/persistence/postgresql.py b/trex_core/adapters/persistence/postgresql.py index 6a52b3d..64cabc7 100644 --- a/trex_core/adapters/persistence/postgresql.py +++ b/trex_core/adapters/persistence/postgresql.py @@ -13,9 +13,10 @@ domain layer (NFR-1). from __future__ import annotations import json +from collections.abc import Iterator from contextlib import contextmanager from datetime import datetime, timedelta, timezone -from typing import Any, Iterator, Optional +from typing import Any, Optional from uuid import UUID, uuid4 from trex_core.application.ledger_outbox import ( @@ -26,9 +27,9 @@ from trex_core.application.ledger_outbox import ( from trex_core.application.ledger_port import LedgerTrade from trex_core.application.ports import IntentRecord from trex_core.application.strategy_state import ( + _STATE_CAP_BYTES, SetResult, StrategyStateEntry, - _STATE_CAP_BYTES, ) from trex_core.domain.slot import Slot, SlotNotFoundError, SlotState, SlotTransitionRecord @@ -565,16 +566,32 @@ class _PgIntentRecord: _OUTBOX_COLUMNS = ( "correlation_id, asset_id, order_id, execution_id, side, qty, price, " "fee, tax, executed_at, status, attempts, last_outcome, last_error, " - "created_at, updated_at, next_retry_at, venue, order_venue" + "created_at, updated_at, next_retry_at, venue, order_venue, instance_key" ) class PostgreSQLLedgerOutbox: """ledger_outbox-backed LedgerOutbox. correlation_id PK is the dedup gate.""" - def __init__(self, dsn: str, *, psycopg_module: Any = None) -> None: + def __init__( + self, + dsn: str, + *, + instance_key: str = "default", + claim_ttl_sec: float = 60.0, + worker_id: str | None = None, + clock=None, + psycopg_module: Any = None, + ) -> None: self._psycopg = _require_psycopg(psycopg_module) self._dsn = dsn + self._instance_key = instance_key + self._claim_ttl_sec = claim_ttl_sec + self._worker_id = worker_id or f"ledger-writer-{uuid4().hex}" + self._clock = clock or (lambda: datetime.now(tz=timezone.utc)) + + def _now(self) -> datetime: + return self._clock() def enqueue(self, trade: LedgerTrade) -> LedgerWorkItem: with self._psycopg.connect(self._dsn, autocommit=False) as conn: @@ -582,8 +599,8 @@ class PostgreSQLLedgerOutbox: cur.execute( "INSERT INTO ledger_outbox " "(correlation_id, asset_id, order_id, execution_id, side, " - " qty, price, fee, tax, executed_at, venue, order_venue) " - "VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s) " + " qty, price, fee, tax, executed_at, venue, order_venue, instance_key) " + "VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s) " "ON CONFLICT (correlation_id) DO NOTHING", ( trade.correlation_id, @@ -598,6 +615,7 @@ class PostgreSQLLedgerOutbox: trade.executed_at, trade.venue, trade.order_venue, + self._instance_key, ), ) conn.commit() @@ -611,12 +629,53 @@ class PostgreSQLLedgerOutbox: cur.execute( f"SELECT {_OUTBOX_COLUMNS} FROM ledger_outbox " "WHERE status = 'pending' " + "AND instance_key = %s " "AND (next_retry_at IS NULL OR next_retry_at <= now()) " - "ORDER BY created_at LIMIT %s", - (limit,), + "AND (claim_expires_at IS NULL OR claim_expires_at <= now()) " + "ORDER BY created_at, correlation_id LIMIT %s", + (self._instance_key, limit), ) return [self._row_to_item(r) for r in cur.fetchall()] + def claim_pending( + self, + limit: int = 32, + *, + correlation_id: str | None = None, + ) -> list[LedgerWorkItem]: + now = self._now() + lease_until = now + timedelta(seconds=self._claim_ttl_sec) + correlation_sql = "" + params: list[Any] = [self._instance_key] + if correlation_id is not None: + correlation_sql = "AND correlation_id = %s " + params.append(correlation_id) + params.extend([limit, self._worker_id, lease_until, now]) + with self._psycopg.connect(self._dsn, autocommit=False) as conn: + with conn.cursor() as cur: + cur.execute( + "WITH candidates AS (" + "SELECT correlation_id FROM ledger_outbox " + "WHERE status = 'pending' " + "AND instance_key = %s " + "AND (next_retry_at IS NULL OR next_retry_at <= now()) " + "AND (claim_expires_at IS NULL OR claim_expires_at <= now()) " + f"{correlation_sql}" + "ORDER BY created_at, correlation_id " + "LIMIT %s " + "FOR UPDATE SKIP LOCKED" + ") " + "UPDATE ledger_outbox o " + "SET claim_owner = %s, claim_expires_at = %s, updated_at = %s " + "FROM candidates " + "WHERE o.correlation_id = candidates.correlation_id " + f"RETURNING {_OUTBOX_COLUMNS}", + params, + ) + rows = [self._row_to_item(r) for r in cur.fetchall()] + conn.commit() + return rows + def pending_cash_delta(self) -> dict[str, float]: # dcy-018 / REQ-029 (OQ-4): estimated cash delta of all pending rows by # asset_id. SUM in SQL: sell → +(qty*price - fee - tax), buy → negative. @@ -627,7 +686,10 @@ class PostgreSQLLedgerOutbox: "SUM(CASE WHEN side='sell' " " THEN (qty*price - fee - tax) " " ELSE -(qty*price + fee + tax) END) " - "FROM ledger_outbox WHERE status='pending' GROUP BY asset_id" + "FROM ledger_outbox " + "WHERE status='pending' AND instance_key=%s " + "GROUP BY asset_id", + (self._instance_key,), ) return {r[0]: float(r[1]) for r in cur.fetchall() if r[1] is not None} @@ -671,16 +733,20 @@ class PostgreSQLLedgerOutbox: nra = next_retry_at if outcome is OutboxOutcome.RETRYABLE_FAILURE else None cur.execute( "UPDATE ledger_outbox SET status=%s, attempts=attempts+%s, " - "last_outcome=%s, last_error=%s, next_retry_at=%s, updated_at=%s " - "WHERE correlation_id=%s", + "last_outcome=%s, last_error=%s, next_retry_at=%s, updated_at=%s, " + "claim_owner=NULL, claim_expires_at=NULL " + "WHERE correlation_id=%s AND instance_key=%s " + "AND (claim_owner=%s OR claim_owner IS NULL)", ( status_value, attempts_delta, outcome.value, error, nra, - datetime.now(tz=timezone.utc), + self._now(), correlation_id, + self._instance_key, + self._worker_id, ), ) conn.commit() @@ -714,6 +780,7 @@ class PostgreSQLLedgerOutbox: created_at=row[14], updated_at=row[15], next_retry_at=row[16], + instance_key=row[19], ) diff --git a/trex_core/adapters/persistence/sql/028_ledger_outbox_instance_claims.sql b/trex_core/adapters/persistence/sql/028_ledger_outbox_instance_claims.sql new file mode 100644 index 0000000..186c809 --- /dev/null +++ b/trex_core/adapters/persistence/sql/028_ledger_outbox_instance_claims.sql @@ -0,0 +1,22 @@ +-- GitHub #84: persist outbox owner instance and add claim/lease fields so +-- shared-DB daemon writers only deliver their own rows and can safely recover +-- abandoned work after lease expiry. Existing rows remain fail-closed when the +-- owner instance cannot be inferred. +ALTER TABLE ledger_outbox ADD COLUMN IF NOT EXISTS instance_key TEXT; +ALTER TABLE ledger_outbox ADD COLUMN IF NOT EXISTS claim_owner TEXT; +ALTER TABLE ledger_outbox ADD COLUMN IF NOT EXISTS claim_expires_at TIMESTAMPTZ; + +UPDATE ledger_outbox +SET instance_key='__unowned__' +WHERE instance_key IS NULL; + +ALTER TABLE ledger_outbox ALTER COLUMN instance_key SET DEFAULT '__unowned__'; +ALTER TABLE ledger_outbox ALTER COLUMN instance_key SET NOT NULL; + +CREATE INDEX IF NOT EXISTS idx_ledger_outbox_instance_pending + ON ledger_outbox (instance_key, status, created_at) + WHERE status = 'pending'; + +CREATE INDEX IF NOT EXISTS idx_ledger_outbox_instance_claim_expires + ON ledger_outbox (instance_key, claim_expires_at) + WHERE status = 'pending'; diff --git a/trex_core/application/ledger_outbox.py b/trex_core/application/ledger_outbox.py index 574fe87..79e7b32 100644 --- a/trex_core/application/ledger_outbox.py +++ b/trex_core/application/ledger_outbox.py @@ -104,6 +104,7 @@ class LedgerWorkItem: next_retry_at: Optional[datetime] = None created_at: Optional[datetime] = None updated_at: Optional[datetime] = None + instance_key: Optional[str] = None class LedgerOutbox(Protocol): @@ -118,6 +119,15 @@ class LedgerOutbox(Protocol): """Return pending work items in FIFO order, up to `limit`.""" ... + def claim_pending( + self, + limit: int = 32, + *, + correlation_id: str | None = None, + ) -> list[LedgerWorkItem]: + """Atomically claim pending items for delivery.""" + ... + def pending_cash_delta(self) -> dict[str, float]: """Sum the estimated cash delta of ALL not-yet-settled (pending) rows, grouped by asset_id (dcy-018 / REQ-029, OQ-4 estimate overlay). @@ -191,13 +201,27 @@ class LedgerWriter: self._alarm_emitter = alarm_emitter self._ledger_skip_store = ledger_skip_store self._instance_key = instance_key + self.counters: dict[str, int] = {} + + def _count(self, key: str) -> None: + self.counters[key] = self.counters.get(key, 0) + 1 def enqueue_fill(self, trade: LedgerTrade) -> LedgerWorkItem: return self._outbox.enqueue(trade) def run_once(self, limit: int = 32) -> WriterStats: stats = WriterStats() - for item in self._outbox.list_pending(limit): + items = self._outbox.claim_pending(limit) + claim_result = "claimed" if items else "empty" + self._count(f"claim:{claim_result}") + _log.info( + "ledger outbox claim: instance_key=%s claim_result=%s count=%d limit=%d", + self._instance_key, + claim_result, + len(items), + limit, + ) + for item in items: outcome = self._process(item) if outcome is OutboxOutcome.COMPLETED: stats.completed += 1 @@ -216,6 +240,32 @@ class LedgerWriter: item = self._outbox.get(correlation_id) if item is None: return None + if ( + self._instance_key is not None + and item.instance_key is not None + and item.instance_key != self._instance_key + ): + self._count("claim:foreign_instance") + _log.info( + "ledger outbox claim: instance_key=%s claim_result=foreign_instance " + "correlation_id=%s owner_instance_key=%s", + self._instance_key, + correlation_id, + item.instance_key, + ) + return None + if item.status is WorkItemStatus.PENDING: + claimed = self._outbox.claim_pending(1, correlation_id=correlation_id) + if not claimed: + self._count("claim:unavailable") + _log.info( + "ledger outbox claim: instance_key=%s claim_result=unavailable " + "correlation_id=%s", + self._instance_key, + correlation_id, + ) + return None + item = claimed[0] return self._process(item) def _backoff_delay(self, attempts: int) -> float: @@ -229,6 +279,7 @@ class LedgerWriter: existing = self._outbox.get(item.correlation_id) if existing is not None and existing.status is WorkItemStatus.COMPLETED: self._outbox.mark_outcome(item.correlation_id, OutboxOutcome.DUPLICATE_COMPLETED) + self._log_outcome(item, OutboxOutcome.DUPLICATE_COMPLETED) return OutboxOutcome.DUPLICATE_COMPLETED try: outcome = self._ledger.record_trade(item.trade) @@ -236,6 +287,7 @@ class LedgerWriter: self._outbox.mark_outcome( item.correlation_id, OutboxOutcome.CONFLICT_BLOCKED, error=str(exc) ) + self._log_outcome(item, OutboxOutcome.CONFLICT_BLOCKED, error=str(exc)) # dcy-033 / REQ-100: CRITICAL alarm — 409 conflict, operator resolution needed. if self._alarm_emitter is not None: self._alarm_emitter.publish_alarm( @@ -252,8 +304,10 @@ class LedgerWriter: self._outbox.mark_outcome( item.correlation_id, OutboxOutcome.PERMANENT_FAILURE, error=str(exc) ) + self._log_outcome(item, OutboxOutcome.PERMANENT_FAILURE, error=str(exc)) _log.warning( - "ledger delivery_failed (permanent): correlation_id=%s reason=%s", + "ledger delivery_failed (permanent): instance_key=%s correlation_id=%s reason=%s", + item.instance_key or self._instance_key, item.correlation_id, exc, ) # dcy-033 / REQ-100: CRITICAL alarm — permanent failure, no retry. @@ -273,10 +327,14 @@ class LedgerWriter: self._outbox.mark_outcome( item.correlation_id, OutboxOutcome.DEAD_LETTERED, error=str(exc) ) + self._log_outcome(item, OutboxOutcome.DEAD_LETTERED, error=str(exc)) _log.warning( "ledger delivery_failed (dead-letter, attempts=%d): " - "correlation_id=%s reason=%s", - new_attempts, item.correlation_id, exc, + "instance_key=%s correlation_id=%s reason=%s", + new_attempts, + item.instance_key or self._instance_key, + item.correlation_id, + exc, ) # dcy-033 / REQ-100: CRITICAL alarm — dead-lettered after max retries. if self._alarm_emitter is not None: @@ -296,6 +354,7 @@ class LedgerWriter: item.correlation_id, OutboxOutcome.RETRYABLE_FAILURE, error=str(exc), next_retry_at=next_retry_at, ) + self._log_outcome(item, OutboxOutcome.RETRYABLE_FAILURE, error=str(exc)) return OutboxOutcome.RETRYABLE_FAILURE # dcy-018 / REQ-019/030 (option D): write back portfolio-hub authoritative # cash/quantity to the snapshot store on new+duplicate (OQ-2 b). *_after @@ -308,11 +367,32 @@ class LedgerWriter: if outcome.result is LedgerWriteResult.DUPLICATE_OK: self._outbox.mark_outcome(item.correlation_id, OutboxOutcome.DUPLICATE_COMPLETED) self._resolve_ledger_skip(item.trade) + self._log_outcome(item, OutboxOutcome.DUPLICATE_COMPLETED) return OutboxOutcome.DUPLICATE_COMPLETED self._outbox.mark_outcome(item.correlation_id, OutboxOutcome.COMPLETED) self._resolve_ledger_skip(item.trade) + self._log_outcome(item, OutboxOutcome.COMPLETED) return OutboxOutcome.COMPLETED + def _log_outcome( + self, + item: LedgerWorkItem, + outcome: OutboxOutcome, + *, + error: str | None = None, + ) -> None: + self._count(f"outcome:{outcome.value}") + msg = "ledger outbox outcome: instance_key=%s correlation_id=%s outcome=%s" + args: tuple[object, ...] = ( + item.instance_key or self._instance_key, + item.correlation_id, + outcome.value, + ) + if error is not None: + msg += " error=%s" + args = (*args, error) + _log.info(msg, *args) + def _resolve_ledger_skip(self, trade: LedgerTrade) -> None: if ( self._ledger_skip_store is None @@ -358,7 +438,12 @@ class LedgerWriter: class InMemoryLedgerOutbox: """Process-local outbox. Thread-safe; idempotent on correlation_id.""" - def __init__(self, *, clock: Optional[Callable[[], datetime]] = None) -> None: + def __init__( + self, + *, + clock: Optional[Callable[[], datetime]] = None, + instance_key: str = "default", + ) -> None: import threading self._rows: dict[str, LedgerWorkItem] = {} @@ -367,6 +452,7 @@ class InMemoryLedgerOutbox: # dcy-015: shared clock lets tests align backoff (next_retry_at) with # list_pending's "now" deterministically. self._clock = clock or (lambda: datetime.now(tz=timezone.utc)) + self._instance_key = instance_key def _now(self) -> datetime: return self._clock() @@ -383,6 +469,7 @@ class InMemoryLedgerOutbox: status=WorkItemStatus.PENDING, created_at=self._now(), updated_at=self._now(), + instance_key=self._instance_key, ) self._rows[cid] = row self._order.append(cid) @@ -404,6 +491,17 @@ class InMemoryLedgerOutbox: break return out + def claim_pending( + self, + limit: int = 32, + *, + correlation_id: str | None = None, + ) -> list[LedgerWorkItem]: + pending = self.list_pending(limit if correlation_id is None else max(limit, 1)) + if correlation_id is None: + return pending[:limit] + return [row for row in pending if row.correlation_id == correlation_id][:1] + def pending_cash_delta(self) -> dict[str, float]: with self._lock: out: dict[str, float] = {} diff --git a/trex_core/runtime/cli.py b/trex_core/runtime/cli.py index 128ef21..182eeea 100644 --- a/trex_core/runtime/cli.py +++ b/trex_core/runtime/cli.py @@ -1333,7 +1333,7 @@ def _cmd_ledger_backfill(args, cfg, confirm) -> int: _emit_pretty_json(report) return 1 - outbox = PostgreSQLLedgerOutbox(cfg.dsn) + outbox = PostgreSQLLedgerOutbox(cfg.dsn, instance_key=instance) if not cfg.portfolio_hub or not cfg.portfolio_hub.base_url: report["result"] = {"status": "rejected", "reason": "portfolio-hub ledger adapter is not configured"} report["audit_path"] = _write_ledger_backfill_audit(args, report) diff --git a/trex_core/runtime/daemon.py b/trex_core/runtime/daemon.py index d232973..95bcd66 100644 --- a/trex_core/runtime/daemon.py +++ b/trex_core/runtime/daemon.py @@ -190,7 +190,7 @@ class Daemon: instance_key=config.instance_key, ) - self.outbox = PostgreSQLLedgerOutbox(config.dsn) + self.outbox = PostgreSQLLedgerOutbox(config.dsn, instance_key=config.instance_key) self.ledger_skip_store = PostgreSQLLedgerSkipStore(config.dsn) # BAT-008: portfolio-hub read + snapshot store + durable pause + scheduler. # (Created before the ledger writer so option-D write-back can target it.) From 31d6e5c02b50799b01ed5ff950d53c8b3c70354b Mon Sep 17 00:00:00 2001 From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com> Date: Sat, 12 Sep 2026 13:27:27 +0000 Subject: [PATCH 05/11] test: cover stale ledger outbox lease updates Co-authored-by: genichin <4282227+genichin@users.noreply.github.com> --- .../test_postgresql_ledger_outbox.py | 39 +++++++++++++++++++ tests/application/test_ledger_outbox.py | 6 ++- trex_core/adapters/persistence/postgresql.py | 37 +++++++++++------- .../sql/028_ledger_outbox_instance_claims.sql | 3 +- trex_core/application/ledger_outbox.py | 36 ++++++++++++++--- 5 files changed, 99 insertions(+), 22 deletions(-) diff --git a/tests/adapters/persistence/test_postgresql_ledger_outbox.py b/tests/adapters/persistence/test_postgresql_ledger_outbox.py index 6f51388..d553846 100644 --- a/tests/adapters/persistence/test_postgresql_ledger_outbox.py +++ b/tests/adapters/persistence/test_postgresql_ledger_outbox.py @@ -169,6 +169,45 @@ def test_claim_expiry_allows_safe_recovery_after_worker_crash(pg_clean): assert [item.correlation_id for item in claimed_b] == [row.correlation_id] +def test_stale_claim_cannot_overwrite_new_owner_outcome(pg_clean): + now = {"t": datetime(2026, 6, 4, tzinfo=UTC)} + outbox_a = PostgreSQLLedgerOutbox( + pg_clean, + instance_key="inst-a", + claim_ttl_sec=5.0, + worker_id="worker-a", + clock=lambda: now["t"], + ) + outbox_b = PostgreSQLLedgerOutbox( + pg_clean, + instance_key="inst-a", + claim_ttl_sec=5.0, + worker_id="worker-b", + clock=lambda: now["t"], + ) + row = outbox_a.enqueue(_trade(execution_id="pg-stale")) + + [claim_a] = outbox_a.claim_pending() + now["t"] = datetime(2026, 6, 4, 0, 0, 6, tzinfo=UTC) + [claim_b] = outbox_b.claim_pending() + outbox_b.mark_outcome( + row.correlation_id, + OutboxOutcome.COMPLETED, + expected_claim_expires_at=claim_b.claim_expires_at, + ) + + stored = outbox_a.mark_outcome( + row.correlation_id, + OutboxOutcome.RETRYABLE_FAILURE, + error="stale owner", + next_retry_at=now["t"], + expected_claim_expires_at=claim_a.claim_expires_at, + ) + + assert stored.status is WorkItemStatus.COMPLETED + assert stored.last_outcome is OutboxOutcome.COMPLETED + + def test_writer_records_retryable_403_without_cross_instance_delivery(pg_clean): class _ForbiddenLedger: def __init__(self): diff --git a/tests/application/test_ledger_outbox.py b/tests/application/test_ledger_outbox.py index e085f30..25e747d 100644 --- a/tests/application/test_ledger_outbox.py +++ b/tests/application/test_ledger_outbox.py @@ -71,9 +71,9 @@ def test_writer_retries_until_success(): def test_process_correlation_id_only_drains_requested_row(): - outbox = InMemoryLedgerOutbox() + outbox = InMemoryLedgerOutbox(instance_key="inst-a") ledger = InMemoryLedger() - writer = LedgerWriter(outbox, ledger) + writer = LedgerWriter(outbox, ledger, instance_key="inst-a") first = outbox.enqueue(_trade(execution_id="e-1")) second = outbox.enqueue(_trade(execution_id="e-2")) @@ -81,6 +81,8 @@ def test_process_correlation_id_only_drains_requested_row(): assert outcome is OutboxOutcome.COMPLETED assert ledger.count() == 1 + assert writer.counters["claim:claimed"] == 1 + assert writer.counters["outcome:completed"] == 1 assert outbox.get(first.correlation_id).status is WorkItemStatus.COMPLETED assert outbox.get(second.correlation_id).status is WorkItemStatus.PENDING diff --git a/trex_core/adapters/persistence/postgresql.py b/trex_core/adapters/persistence/postgresql.py index 64cabc7..aa5b0f0 100644 --- a/trex_core/adapters/persistence/postgresql.py +++ b/trex_core/adapters/persistence/postgresql.py @@ -566,7 +566,8 @@ class _PgIntentRecord: _OUTBOX_COLUMNS = ( "correlation_id, asset_id, order_id, execution_id, side, qty, price, " "fee, tax, executed_at, status, attempts, last_outcome, last_error, " - "created_at, updated_at, next_retry_at, venue, order_venue, instance_key" + "created_at, updated_at, next_retry_at, venue, order_venue, instance_key, " + "claim_expires_at" ) @@ -710,6 +711,7 @@ class PostgreSQLLedgerOutbox: *, error: Optional[str] = None, next_retry_at: Optional[datetime] = None, + expected_claim_expires_at: datetime | None = None, ) -> LedgerWorkItem: with self._psycopg.connect(self._dsn, autocommit=False) as conn: with conn.cursor() as cur: @@ -731,23 +733,29 @@ class PostgreSQLLedgerOutbox: attempts_delta = 1 # next_retry_at only persists for a retryable backoff; cleared otherwise. nra = next_retry_at if outcome is OutboxOutcome.RETRYABLE_FAILURE else None + params: list[Any] = [ + status_value, + attempts_delta, + outcome.value, + error, + nra, + self._now(), + correlation_id, + self._instance_key, + ] + where = "WHERE correlation_id=%s AND instance_key=%s " + if expected_claim_expires_at is None: + where += "AND status=%s AND claim_owner IS NULL AND claim_expires_at IS NULL" + params.append(WorkItemStatus.COMPLETED.value) + else: + where += "AND claim_owner=%s AND claim_expires_at=%s" + params.extend([self._worker_id, expected_claim_expires_at]) cur.execute( "UPDATE ledger_outbox SET status=%s, attempts=attempts+%s, " "last_outcome=%s, last_error=%s, next_retry_at=%s, updated_at=%s, " "claim_owner=NULL, claim_expires_at=NULL " - "WHERE correlation_id=%s AND instance_key=%s " - "AND (claim_owner=%s OR claim_owner IS NULL)", - ( - status_value, - attempts_delta, - outcome.value, - error, - nra, - self._now(), - correlation_id, - self._instance_key, - self._worker_id, - ), + f"{where}", + params, ) conn.commit() row = self.get(correlation_id) @@ -781,6 +789,7 @@ class PostgreSQLLedgerOutbox: updated_at=row[15], next_retry_at=row[16], instance_key=row[19], + claim_expires_at=row[20], ) diff --git a/trex_core/adapters/persistence/sql/028_ledger_outbox_instance_claims.sql b/trex_core/adapters/persistence/sql/028_ledger_outbox_instance_claims.sql index 186c809..1c037c7 100644 --- a/trex_core/adapters/persistence/sql/028_ledger_outbox_instance_claims.sql +++ b/trex_core/adapters/persistence/sql/028_ledger_outbox_instance_claims.sql @@ -13,8 +13,9 @@ WHERE instance_key IS NULL; ALTER TABLE ledger_outbox ALTER COLUMN instance_key SET DEFAULT '__unowned__'; ALTER TABLE ledger_outbox ALTER COLUMN instance_key SET NOT NULL; +DROP INDEX IF EXISTS idx_ledger_outbox_instance_pending; CREATE INDEX IF NOT EXISTS idx_ledger_outbox_instance_pending - ON ledger_outbox (instance_key, status, created_at) + ON ledger_outbox (instance_key, status, created_at, correlation_id) WHERE status = 'pending'; CREATE INDEX IF NOT EXISTS idx_ledger_outbox_instance_claim_expires diff --git a/trex_core/application/ledger_outbox.py b/trex_core/application/ledger_outbox.py index 79e7b32..e0bdd5c 100644 --- a/trex_core/application/ledger_outbox.py +++ b/trex_core/application/ledger_outbox.py @@ -105,6 +105,7 @@ class LedgerWorkItem: created_at: Optional[datetime] = None updated_at: Optional[datetime] = None instance_key: Optional[str] = None + claim_expires_at: Optional[datetime] = None class LedgerOutbox(Protocol): @@ -146,6 +147,7 @@ class LedgerOutbox(Protocol): *, error: Optional[str] = None, next_retry_at: Optional[datetime] = None, + expected_claim_expires_at: Optional[datetime] = None, ) -> LedgerWorkItem: """Record the outcome of a writer attempt and advance status. @@ -266,6 +268,14 @@ class LedgerWriter: ) return None item = claimed[0] + self._count("claim:claimed") + _log.info( + "ledger outbox claim: instance_key=%s claim_result=claimed " + "count=%d correlation_id=%s", + self._instance_key, + len(claimed), + correlation_id, + ) return self._process(item) def _backoff_delay(self, attempts: int) -> float: @@ -285,7 +295,10 @@ class LedgerWriter: outcome = self._ledger.record_trade(item.trade) except LedgerConflictError as exc: self._outbox.mark_outcome( - item.correlation_id, OutboxOutcome.CONFLICT_BLOCKED, error=str(exc) + item.correlation_id, + OutboxOutcome.CONFLICT_BLOCKED, + error=str(exc), + expected_claim_expires_at=item.claim_expires_at, ) self._log_outcome(item, OutboxOutcome.CONFLICT_BLOCKED, error=str(exc)) # dcy-033 / REQ-100: CRITICAL alarm — 409 conflict, operator resolution needed. @@ -302,7 +315,10 @@ class LedgerWriter: # dcy-015 / REQ-017/018 (issue #13): non-retryable client error → # terminal delivery_failed immediately (no retry spam). Surface for ops. self._outbox.mark_outcome( - item.correlation_id, OutboxOutcome.PERMANENT_FAILURE, error=str(exc) + item.correlation_id, + OutboxOutcome.PERMANENT_FAILURE, + error=str(exc), + expected_claim_expires_at=item.claim_expires_at, ) self._log_outcome(item, OutboxOutcome.PERMANENT_FAILURE, error=str(exc)) _log.warning( @@ -325,7 +341,10 @@ class LedgerWriter: new_attempts = item.attempts + 1 if new_attempts >= self._max_attempts: self._outbox.mark_outcome( - item.correlation_id, OutboxOutcome.DEAD_LETTERED, error=str(exc) + item.correlation_id, + OutboxOutcome.DEAD_LETTERED, + error=str(exc), + expected_claim_expires_at=item.claim_expires_at, ) self._log_outcome(item, OutboxOutcome.DEAD_LETTERED, error=str(exc)) _log.warning( @@ -352,7 +371,9 @@ class LedgerWriter: ) self._outbox.mark_outcome( item.correlation_id, OutboxOutcome.RETRYABLE_FAILURE, - error=str(exc), next_retry_at=next_retry_at, + error=str(exc), + next_retry_at=next_retry_at, + expected_claim_expires_at=item.claim_expires_at, ) self._log_outcome(item, OutboxOutcome.RETRYABLE_FAILURE, error=str(exc)) return OutboxOutcome.RETRYABLE_FAILURE @@ -369,7 +390,11 @@ class LedgerWriter: self._resolve_ledger_skip(item.trade) self._log_outcome(item, OutboxOutcome.DUPLICATE_COMPLETED) return OutboxOutcome.DUPLICATE_COMPLETED - self._outbox.mark_outcome(item.correlation_id, OutboxOutcome.COMPLETED) + self._outbox.mark_outcome( + item.correlation_id, + OutboxOutcome.COMPLETED, + expected_claim_expires_at=item.claim_expires_at, + ) self._resolve_ledger_skip(item.trade) self._log_outcome(item, OutboxOutcome.COMPLETED) return OutboxOutcome.COMPLETED @@ -522,6 +547,7 @@ class InMemoryLedgerOutbox: *, error: Optional[str] = None, next_retry_at: Optional[datetime] = None, + expected_claim_expires_at: Optional[datetime] = None, ) -> LedgerWorkItem: with self._lock: row = self._rows[correlation_id] From 310b6f6dec34236679508da85bcd1a3dd288cd34 Mon Sep 17 00:00:00 2001 From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com> Date: Sat, 12 Sep 2026 13:28:40 +0000 Subject: [PATCH 06/11] fix: align warning-case blocking semantics across reconcile paths Co-authored-by: genichin <4282227+genichin@users.noreply.github.com> --- .../test_slots_handler_quantity_mismatch.py | 8 +++---- .../028_preserve_reconcile_warning_cases.sql | 23 +++++++++++++++++++ trex_core/application/intents.py | 23 +++++++++++++++++-- trex_core/application/messaging_handlers.py | 18 ++++++++++----- trex_core/application/portfolio.py | 4 +++- 5 files changed, 63 insertions(+), 13 deletions(-) diff --git a/tests/application/test_slots_handler_quantity_mismatch.py b/tests/application/test_slots_handler_quantity_mismatch.py index d181765..c374ced 100644 --- a/tests/application/test_slots_handler_quantity_mismatch.py +++ b/tests/application/test_slots_handler_quantity_mismatch.py @@ -128,7 +128,7 @@ def test_ac1_single_portfolio_c_case_excluded(): assert resp.payload["slots"] == [] assert resp.payload["excluded_slots"]["reconcile_quantity_mismatch"] == 1 - assert resp.payload["excluded_slots"]["reconcile_warning_cases"] == {"C": 1} + assert resp.payload["excluded_slots"]["active_reconcile_warning_cases"] == {"C": 1} def test_holding_slot_with_b_case_is_excluded_for_strategy(): @@ -144,7 +144,7 @@ def test_holding_slot_with_b_case_is_excluded_for_strategy(): assert resp.payload["slots"] == [] assert resp.payload["excluded_slots"]["reconcile_quantity_mismatch"] == 1 - assert resp.payload["excluded_slots"]["reconcile_warning_cases"] == {"B": 1} + assert resp.payload["excluded_slots"]["active_reconcile_warning_cases"] == {"B": 1} def test_holding_slot_with_b_and_c_cases_keeps_both_and_reports_both(): @@ -162,7 +162,7 @@ def test_holding_slot_with_b_and_c_cases_keeps_both_and_reports_both(): assert resp.payload["slots"] == [] assert resp.payload["excluded_slots"]["reconcile_quantity_mismatch"] == 1 - assert resp.payload["excluded_slots"]["reconcile_warning_cases"] == {"B": 1, "C": 1} + assert resp.payload["excluded_slots"]["active_reconcile_warning_cases"] == {"B": 1, "C": 1} info = warn_store.get_warning_info(slot_id) assert info is not None assert info["case_codes"] == ["B", "C"] @@ -325,7 +325,7 @@ def test_ac5_excluded_slots_count_zero_when_no_warnings(): assert "excluded_slots" in resp.payload assert resp.payload["excluded_slots"]["reconcile_quantity_mismatch"] == 0 - assert resp.payload["excluded_slots"]["reconcile_warning_cases"] == {} + assert resp.payload["excluded_slots"]["active_reconcile_warning_cases"] == {} # --------------------------------------------------------------------------- diff --git a/trex_core/adapters/persistence/sql/028_preserve_reconcile_warning_cases.sql b/trex_core/adapters/persistence/sql/028_preserve_reconcile_warning_cases.sql index 11e967d..40771bf 100644 --- a/trex_core/adapters/persistence/sql/028_preserve_reconcile_warning_cases.sql +++ b/trex_core/adapters/persistence/sql/028_preserve_reconcile_warning_cases.sql @@ -1,7 +1,30 @@ -- REQ-123 / issue #83: -- Preserve simultaneous warning causes by keying warnings per (slot_id, case_code). +-- NOTE: historical overwritten causes cannot be reconstructed from the prior +-- slot_id-only schema; this migration enables forward preservation only. +UPDATE slot_reconcile_warning +SET case_code = 'B' +WHERE case_code IS NULL OR case_code = ''; + +ALTER TABLE slot_reconcile_warning + ALTER COLUMN case_code SET NOT NULL; + +DELETE FROM slot_reconcile_warning w +USING ( + SELECT ctid, ROW_NUMBER() OVER ( + PARTITION BY slot_id, case_code + ORDER BY updated_at DESC, created_at DESC, ctid DESC + ) AS rn + FROM slot_reconcile_warning +) ranked +WHERE w.ctid = ranked.ctid + AND ranked.rn > 1; + ALTER TABLE slot_reconcile_warning DROP CONSTRAINT IF EXISTS slot_reconcile_warning_pkey; ALTER TABLE slot_reconcile_warning ADD CONSTRAINT slot_reconcile_warning_pkey PRIMARY KEY (slot_id, case_code); + +CREATE INDEX IF NOT EXISTS idx_slot_reconcile_warning_slot_id + ON slot_reconcile_warning (slot_id); diff --git a/trex_core/application/intents.py b/trex_core/application/intents.py index 1f4bf2e..26afb70 100644 --- a/trex_core/application/intents.py +++ b/trex_core/application/intents.py @@ -29,6 +29,7 @@ from typing import Any, Callable, Optional from uuid import UUID from trex_core.application.alarm_emitter import AlarmEmitter +from trex_core.application.portfolio import BLOCKING_RECONCILE_CASES from trex_core.application.ports import IntentStore from trex_core.domain.slot import ( SlotAdmissionRejectedError, @@ -270,6 +271,24 @@ class IntentService: except Exception: # noqa: BLE001 - alarm path must not affect intent decision pass + def _is_reconcile_trade_blocked(self, slot_id: str) -> bool: + if self._warn_store is None: + return False + if not self._warn_store.is_warned(slot_id): + return False + info = self._warn_store.get_warning_info(slot_id) + if info is None: + return True + raw_codes = info.get("case_codes") + if isinstance(raw_codes, list): + case_codes = {str(code) for code in raw_codes if code} + else: + case_code = str(info.get("case_code", "")) + case_codes = {case_code} if case_code else set() + if not case_codes: + return True + return bool(case_codes & BLOCKING_RECONCILE_CASES) + # ------------------------------------------------------------ def _dedup(self, intent_id: str, intent_type: str, payload: dict) -> Optional[IntentDecision]: """Return prior decision if intent_id already seen; else None (and reserve it).""" @@ -339,7 +358,7 @@ class IntentService: # those paths call SlotService.sell() directly. if self._warn_store is not None: try: - if self._warn_store.is_warned(str(slot.slot_id)): + if self._is_reconcile_trade_blocked(str(slot.slot_id)): return IntentDecision( intent.intent_id, "rejected", None, "reconcile_warned" ) @@ -432,7 +451,7 @@ class IntentService: # SlotService.sell() / transit_slot() directly without IntentService (OQ-B). if self._warn_store is not None: try: - if self._warn_store.is_warned(str(slot.slot_id)): + if self._is_reconcile_trade_blocked(str(slot.slot_id)): return IntentDecision( intent.intent_id, "rejected", None, "reconcile_warned" ) diff --git a/trex_core/application/messaging_handlers.py b/trex_core/application/messaging_handlers.py index f50c04a..527dbb1 100644 --- a/trex_core/application/messaging_handlers.py +++ b/trex_core/application/messaging_handlers.py @@ -17,6 +17,7 @@ from trex_core.application.account_snapshot import AccountSnapshotUnavailable from trex_core.application.broker_port import BalanceItem from trex_core.application.messaging import RpcRequest, RpcResponse from trex_core.application.portfolio import ( + BLOCKING_RECONCILE_CASES, PauseStore, ReconcileWarningStore, SnapshotStore, @@ -270,15 +271,16 @@ def make_slots_rpc_handler( for sid in warned_slot_ids: info = warn_store.get_warning_info(sid) if info is None: - continue + raise RuntimeError(f"missing warning info for slot_id={sid}") raw_codes = info.get("case_codes") if isinstance(raw_codes, list): codes = {str(code) for code in raw_codes if code} else: case_code = str(info.get("case_code", "")) codes = {case_code} if case_code else set() - if codes: - warning_cases_by_slot[str(sid)] = codes + if not codes: + raise RuntimeError(f"empty warning cases for slot_id={sid}") + warning_cases_by_slot[str(sid)] = codes except Exception: # noqa: BLE001 _log.exception("warn_store warning query failed — fail-closed") return RpcResponse(payload={ @@ -290,7 +292,10 @@ def make_slots_rpc_handler( "reconcile warning store unavailable; " "returning no slots (fail-closed)" ), - "excluded_slots": {"reconcile_quantity_mismatch": 0}, + "excluded_slots": { + "reconcile_quantity_mismatch": 0, + "active_reconcile_warning_cases": {}, + }, }) # Build merged slot rows (REQ-074) @@ -314,7 +319,8 @@ def make_slots_rpc_handler( included: list[tuple[object, dict]] = [] for slot, row in zip(slots, slot_rows, strict=True): blocked_holding = ( - slot.status.value == "holding" and bool(row.get("reconcile_warned")) + slot.status.value == "holding" + and bool(set(row.get("reconcile_warning_cases", [])) & BLOCKING_RECONCILE_CASES) ) if blocked_holding: excluded_count += 1 @@ -432,7 +438,7 @@ def make_slots_rpc_handler( if warn_store is not None: base_payload["excluded_slots"] = { "reconcile_quantity_mismatch": excluded_count, - "reconcile_warning_cases": excluded_case_counts, + "active_reconcile_warning_cases": excluded_case_counts, } return RpcResponse(payload=base_payload) diff --git a/trex_core/application/portfolio.py b/trex_core/application/portfolio.py index ad2b7c0..ba11a89 100644 --- a/trex_core/application/portfolio.py +++ b/trex_core/application/portfolio.py @@ -21,6 +21,8 @@ from datetime import UTC, datetime from enum import Enum from typing import Protocol +BLOCKING_RECONCILE_CASES = frozenset({"B", "C"}) + # ---------------------------------------------------------------- portfolio-hub @dataclass(frozen=True) @@ -658,7 +660,7 @@ def slot_to_dict( reconcile_warned = bool(warning_cases) d["reconcile_warned"] = reconcile_warned d["reconcile_warning_cases"] = sorted(warning_cases) - d["trade_eligible"] = not reconcile_warned + d["trade_eligible"] = not bool(warning_cases & BLOCKING_RECONCILE_CASES) return d From 0b5b4660e57c17a0f584973fd850234b171b6bdd Mon Sep 17 00:00:00 2001 From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com> Date: Sat, 12 Sep 2026 13:29:05 +0000 Subject: [PATCH 07/11] fix: guard ledger outbox outcomes by lease Co-authored-by: genichin <4282227+genichin@users.noreply.github.com> --- trex_core/adapters/persistence/postgresql.py | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/trex_core/adapters/persistence/postgresql.py b/trex_core/adapters/persistence/postgresql.py index aa5b0f0..5864957 100644 --- a/trex_core/adapters/persistence/postgresql.py +++ b/trex_core/adapters/persistence/postgresql.py @@ -745,8 +745,7 @@ class PostgreSQLLedgerOutbox: ] where = "WHERE correlation_id=%s AND instance_key=%s " if expected_claim_expires_at is None: - where += "AND status=%s AND claim_owner IS NULL AND claim_expires_at IS NULL" - params.append(WorkItemStatus.COMPLETED.value) + where += "AND claim_owner IS NULL AND claim_expires_at IS NULL" else: where += "AND claim_owner=%s AND claim_expires_at=%s" params.extend([self._worker_id, expected_claim_expires_at]) From f801c53e0c30edb31250e536e6ac0e8d8d5c861e Mon Sep 17 00:00:00 2001 From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com> Date: Sat, 12 Sep 2026 13:30:50 +0000 Subject: [PATCH 08/11] test: cover targeted and expired ledger claims Co-authored-by: genichin <4282227+genichin@users.noreply.github.com> --- .../test_postgresql_ledger_outbox.py | 23 +++++++++++++++++++ tests/application/test_ledger_outbox.py | 6 ++--- trex_core/adapters/persistence/postgresql.py | 7 ++++-- trex_core/application/ledger_outbox.py | 12 +++++++--- 4 files changed, 40 insertions(+), 8 deletions(-) diff --git a/tests/adapters/persistence/test_postgresql_ledger_outbox.py b/tests/adapters/persistence/test_postgresql_ledger_outbox.py index d553846..d9d465d 100644 --- a/tests/adapters/persistence/test_postgresql_ledger_outbox.py +++ b/tests/adapters/persistence/test_postgresql_ledger_outbox.py @@ -208,6 +208,29 @@ def test_stale_claim_cannot_overwrite_new_owner_outcome(pg_clean): assert stored.last_outcome is OutboxOutcome.COMPLETED +def test_original_owner_can_finalize_expired_unreclaimed_claim(pg_clean): + now = {"t": datetime(2026, 6, 4, tzinfo=UTC)} + outbox = PostgreSQLLedgerOutbox( + pg_clean, + instance_key="inst-a", + claim_ttl_sec=5.0, + worker_id="worker-a", + clock=lambda: now["t"], + ) + row = outbox.enqueue(_trade(execution_id="pg-expired")) + + [claim] = outbox.claim_pending() + now["t"] = datetime(2026, 6, 4, 0, 0, 6, tzinfo=UTC) + stored = outbox.mark_outcome( + row.correlation_id, + OutboxOutcome.COMPLETED, + expected_claim_expires_at=claim.claim_expires_at, + ) + + assert stored.status is WorkItemStatus.COMPLETED + assert stored.last_outcome is OutboxOutcome.COMPLETED + + def test_writer_records_retryable_403_without_cross_instance_delivery(pg_clean): class _ForbiddenLedger: def __init__(self): diff --git a/tests/application/test_ledger_outbox.py b/tests/application/test_ledger_outbox.py index 25e747d..651efc6 100644 --- a/tests/application/test_ledger_outbox.py +++ b/tests/application/test_ledger_outbox.py @@ -77,14 +77,14 @@ def test_process_correlation_id_only_drains_requested_row(): first = outbox.enqueue(_trade(execution_id="e-1")) second = outbox.enqueue(_trade(execution_id="e-2")) - outcome = writer.process_correlation_id(first.correlation_id) + outcome = writer.process_correlation_id(second.correlation_id) assert outcome is OutboxOutcome.COMPLETED assert ledger.count() == 1 assert writer.counters["claim:claimed"] == 1 assert writer.counters["outcome:completed"] == 1 - assert outbox.get(first.correlation_id).status is WorkItemStatus.COMPLETED - assert outbox.get(second.correlation_id).status is WorkItemStatus.PENDING + assert outbox.get(first.correlation_id).status is WorkItemStatus.PENDING + assert outbox.get(second.correlation_id).status is WorkItemStatus.COMPLETED def test_process_correlation_id_skips_foreign_instance_row(): diff --git a/trex_core/adapters/persistence/postgresql.py b/trex_core/adapters/persistence/postgresql.py index 5864957..3812448 100644 --- a/trex_core/adapters/persistence/postgresql.py +++ b/trex_core/adapters/persistence/postgresql.py @@ -747,8 +747,11 @@ class PostgreSQLLedgerOutbox: if expected_claim_expires_at is None: where += "AND claim_owner IS NULL AND claim_expires_at IS NULL" else: - where += "AND claim_owner=%s AND claim_expires_at=%s" - params.extend([self._worker_id, expected_claim_expires_at]) + where += ( + "AND claim_owner=%s " + "AND (claim_expires_at=%s OR (status='pending' AND claim_expires_at<=%s))" + ) + params.extend([self._worker_id, expected_claim_expires_at, self._now()]) cur.execute( "UPDATE ledger_outbox SET status=%s, attempts=attempts+%s, " "last_outcome=%s, last_error=%s, next_retry_at=%s, updated_at=%s, " diff --git a/trex_core/application/ledger_outbox.py b/trex_core/application/ledger_outbox.py index e0bdd5c..2dc7eac 100644 --- a/trex_core/application/ledger_outbox.py +++ b/trex_core/application/ledger_outbox.py @@ -522,10 +522,16 @@ class InMemoryLedgerOutbox: *, correlation_id: str | None = None, ) -> list[LedgerWorkItem]: - pending = self.list_pending(limit if correlation_id is None else max(limit, 1)) if correlation_id is None: - return pending[:limit] - return [row for row in pending if row.correlation_id == correlation_id][:1] + return self.list_pending(limit) + now = self._now() + with self._lock: + row = self._rows.get(correlation_id) + if row is None or row.status is not WorkItemStatus.PENDING: + return [] + if row.next_retry_at is not None and row.next_retry_at > now: + return [] + return [row] def pending_cash_delta(self) -> dict[str, float]: with self._lock: From 853943f6763e2d4b90903c72fb5df8c02e1acfad Mon Sep 17 00:00:00 2001 From: Hermes Agent Date: Sat, 12 Sep 2026 22:58:11 +0900 Subject: [PATCH 09/11] fix: fail closed on unknown reconcile warnings --- .proofline/criteria/ac-0023.md | 12 +++-- docs/interface-contract.md | 12 ++++- .../test_reconcile_warning_blocking.py | 46 +++++++++++++++++++ .../test_slots_handler_quantity_mismatch.py | 18 ++++++++ trex_core/application/intents.py | 5 ++ trex_core/application/messaging_handlers.py | 2 + trex_core/application/portfolio.py | 4 +- 7 files changed, 92 insertions(+), 7 deletions(-) diff --git a/.proofline/criteria/ac-0023.md b/.proofline/criteria/ac-0023.md index e0e01d7..b4fe994 100644 --- a/.proofline/criteria/ac-0023.md +++ b/.proofline/criteria/ac-0023.md @@ -3,20 +3,22 @@ id: "ac-0023" status: active --- -# C-case quantity mismatch — strategy RPC exclusion and intent blocking +# B/C reconcile warning — strategy RPC exclusion and intent blocking ## Criterion -KIS 계좌 잔고(`hldg_qty`)와 같은 instance가 관리하는 동일 symbol의 portfolio-hub `asset_quantity` 합계가 일치하지 않으면(`case_code=C` reconcile-warning 활성), 해당 symbol의 모든 `holding` slot을 `trex.slots.req.` 응답에서 제외해야 한다. 수량 대조는 **instance_key + symbol 단위 합계**로 수행하며, 개별 portfolio 수량을 KIS 종목 합계와 직접 비교해서는 안 된다. 응답에는 `excluded_slots.reconcile_quantity_mismatch` 필드로 제외된 slot 수를 포함한다. warn-store를 읽지 못하면 경고 유무를 모르는 상태로 slot 목록을 반환하지 않고 `degraded=true` / `reason="warn_store_unavailable"`으로 응답해야 한다(fail-closed). 신규 buy/sell intent는 durable warning을 재확인하여 `reconcile_warned` 사유로 거부한다. C-case 경고 해제는 symbol 단위 합계가 다시 일치한 경우에만 수행하며, 해당 symbol에 걸린 모든 C-case 경고를 함께 해제한다. 이 경로는 주문 submit/cancel, ledger write, slot lifecycle mutation을 유발하지 않아야 한다. +`case_code=B`(core slot↔KIS 수량 불일치) 또는 `case_code=C`(portfolio-hub↔KIS 수량 불일치) reconcile-warning이 활성인 `holding` slot은 `trex.slots.req.` 응답에서 제외해야 한다. 동일 slot의 B/C 원인은 서로 덮어쓰지 않고 동시에 보존하며, 응답에는 제외된 slot 수와 활성 case별 count를 포함한다. 신규 buy/sell intent는 같은 durable warning 원인 집합을 재확인하여 `reconcile_warned` 사유로 거부한다. warn-store를 읽지 못하거나 warning metadata가 비어 있거나 지원하지 않는 case를 포함하면 안전한 eligibility를 입증할 수 없으므로 slots RPC는 `degraded=true` / `reason="warn_store_unavailable"`, intent는 `reconcile_warning_unavailable`(조회 실패) 또는 `reconcile_warned`(empty/unsupported metadata)로 fail-closed 처리해야 한다. `sync`는 수량 일치 확인 후 B-case만 해제하고, `verify`는 instance+symbol 단위 KIS와 portfolio-hub 합계가 다시 일치한 경우 C-case만 해제하여 다른 활성 원인을 보존한다. C-case 수량 대조는 **instance_key + symbol 단위 합계**로 수행하며, 개별 portfolio 수량을 KIS 종목 합계와 직접 비교해서는 안 된다. 이 경로는 주문 submit/cancel, ledger write, slot lifecycle mutation을 유발하지 않아야 한다. ## Verification - 성공 조건: KIS 440주, hub portfolio A 200주 + B 240주(합계 440) → A·B 모두 반환되고 `excluded_slots.reconcile_quantity_mismatch=0`. -- 불일치 조건: KIS 440주, hub A 200주 + B 235주(합계 435) → A·B 모두 제외되고 `excluded_slots.reconcile_quantity_mismatch=2`. 다른 symbol 정상 slot은 같은 응답에 포함된다. +- 불일치 조건: KIS 440주, hub A 200주 + B 235주(합계 435) → A·B 모두 제외되고 `excluded_slots.reconcile_quantity_mismatch=2`, `active_reconcile_warning_cases.C=2`. 다른 symbol 정상 slot은 같은 응답에 포함된다. +- 복합 원인: 동일 slot에 B와 C가 동시에 활성일 때 두 원인이 모두 조회·차단되며, B 또는 C 하나를 해제해도 다른 원인은 보존된다. +- B-case: B warning이 활성인 holding slot은 slots RPC에서 제외되고 신규 buy/sell intent도 거부된다. - 단일 portfolio 불일치: hub 단일 portfolio qty != KIS → 해당 symbol 전체 slot 제외. -- fail-closed (slots RPC): warn-store가 `list_c_case_warned()` 중 예외를 throw하면 `slots=[], degraded=true, reason="warn_store_unavailable"` 반환. +- fail-closed (slots RPC): warn-store 조회가 실패하거나 empty/unknown case metadata를 반환하면 `slots=[], degraded=true, reason="warn_store_unavailable"` 반환. - fail-closed (intent): intent 처리 시 `warn_store.is_warned()` 호출이 실패하면 `reconcile_warning_unavailable` 사유로 거부해야 한다 — fail-open 허용 불가. -- intent race: 마지막 slots RPC 이후 경고가 설정된 경우에도 intent 처리 시점의 durable warning을 재확인해 `reconcile_warned`로 거부. +- intent race: 마지막 slots RPC 이후 경고가 설정된 경우에도 intent 처리 시점의 durable warning을 재확인해 `reconcile_warned`로 거부. unknown case도 거래 허용 근거로 사용하지 않는다. - 해제: symbol 합계가 다시 일치하면 해당 symbol의 모든 **C-case 경고만** 함께 해제. 같은 symbol의 B-case 등 다른 case 경고는 보존해야 한다. - 해제 대상: HOLDING 뿐 아니라 모든 상태의 slot에 걸린 C-case 경고를 포함한다. - 해제 실패: 해제 도중 예외가 발생하면 `result='clear_failed'`를 반환하고 완전 성공으로 보고하지 않아야 한다(부분 성공 = 실패). diff --git a/docs/interface-contract.md b/docs/interface-contract.md index 05b00df..7f020b2 100644 --- a/docs/interface-contract.md +++ b/docs/interface-contract.md @@ -110,13 +110,20 @@ "last_seen": "ISO-8601 | null" }, "paused": "bool", + "reconcile_warned": "bool", // durable B/C warning 또는 unknown case 존재 + "reconcile_warning_cases": ["B", "C"], // 활성 case code 목록 + "trade_eligible": "bool", // known blocking/unknown case가 없을 때만 true "strategy_name": "str | null", // REQ-116 additive (BAT-055) — portfolio-hub PortfolioItem 출처 "strategy_params": "dict", // REQ-116 additive (BAT-055) — portfolio-hub opaque dict; {} if absent "markets": ["str"] // REQ-116 additive (BAT-055) — portfolio-hub markets list; [] if absent } ], + "excluded_slots": { + "reconcile_quantity_mismatch": "int", + "active_reconcile_warning_cases": {"B": "int", "C": "int"} + }, "degraded": "bool", - "reason": "portfolio_hub_unavailable | snapshot_fetch_failed | cash_position_stale | null", + "reason": "portfolio_hub_unavailable | snapshot_fetch_failed | cash_position_stale | warn_store_unavailable | null", "message": "str | null" // sanitized — no credentials/raw exceptions } ``` @@ -138,11 +145,14 @@ | `warned` | 파생 | `slot_quantity != asset_quantity` (REQ-074 AC-2) | | `watchdog` | WatchdogStore | 만료 여부 + last_seen; null=store 미연결 | | `paused` | PauseStore | durable pause overlay (REQ-032) | +| `reconcile_warned`, `reconcile_warning_cases` | ReconcileWarningStore | 동일 slot의 durable B/C 원인을 동시에 보존·노출 | +| `trade_eligible` | 파생(safety gate) | 활성 B/C 또는 지원하지 않는 warning case가 있으면 false | | `strategy_name` | hub (PortfolioItem via SnapshotStore) | REQ-116 additive. portfolio-hub 정본. hub 미제공 시 null | | `strategy_params` | hub (PortfolioItem via SnapshotStore) | REQ-116 additive. opaque dict; hub 미제공 시 {} | | `markets` | hub (PortfolioItem via SnapshotStore) | REQ-116 additive. list[str]; hub 미제공 시 [] | - **slot-origin strategy 필드 없음** (REQ-074 AC-5, REQ-116 additive 재도입 후에도 유지): `strategy_id`, `sell_strategy_id`, `active_strategy_id` 는 응답에 포함되지 않는다. `strategy_name`/`strategy_params`/`markets` 는 PortfolioItem(hub) 출처이므로 AC-5 제외 대상과 구분된다 — REQ-116 Notes 참조. +- **Reconcile warning fail-closed**: B/C warning이 활성인 holding slot은 응답에서 제외된다. warning store 조회 실패, empty metadata, unknown case는 `slots=[]`, `degraded=true`, `reason="warn_store_unavailable"`로 처리한다. intent admission도 동일 durable source를 재확인하며 unknown case를 거래 허용 근거로 사용하지 않는다. - **Breaking change (holding `qty`) rollout**: 기존 전략 클라이언트가 `qty=slot mirror`로 가정했다면 `slot_quantity`를 읽도록 전환해야 한다. 권장 경로는 (1) 클라이언트에 `qty_source`/`broker_quantity_available` 체크 추가 → (2) fail-closed (`qty is null`) 처리 배포 → (3) `qty`를 broker 정본으로 사용하도록 cutover 순서다. - `spy=false`(기본): holding 슬롯 응답 후 `WatchdogStore.update(slot_id)` 호출 — 전략 폴링 = 생존 신호. - `spy=true`: watchdog 갱신 건너뜀 — 운영자 CLI(`universe`/`slots`) 가 항상 사용. diff --git a/tests/application/test_reconcile_warning_blocking.py b/tests/application/test_reconcile_warning_blocking.py index 8acff52..ed9f761 100644 --- a/tests/application/test_reconcile_warning_blocking.py +++ b/tests/application/test_reconcile_warning_blocking.py @@ -340,6 +340,52 @@ def test_intent_service_sell_rejected_when_reconcile_warned(): assert d.reason == "reconcile_warned" +def test_unknown_warning_case_blocks_buy_and_sell_intents(): + repo = InMemorySlotRepository() + svc = SlotService(repo) + warn_store = InMemoryReconcileWarningStore() + slot = _make_holding_slot(repo, svc, qty=10) + warn_store.set_warned(str(slot.slot_id), portfolio_id="pf-A", case_code="X") + + intent_svc = IntentService( + svc, + repo, + InMemoryIntentStore(), + instance_key="default", + warn_store=warn_store, + ) + + buy = intent_svc.submit_buy(BuyIntent( + intent_id="b-unknown-case", + slot_id=slot.slot_id, + entry_price=100.0, + qty=1.0, + )) + sell = intent_svc.submit_sell(SellIntent( + intent_id="s-unknown-case", + slot_id=slot.slot_id, + reason="strategy_exit", + )) + + assert buy.status == "rejected" + assert buy.reason == "reconcile_warned" + assert sell.status == "rejected" + assert sell.reason == "reconcile_warned" + + +def test_slot_to_dict_marks_unknown_warning_case_ineligible(): + repo = InMemorySlotRepository() + svc = SlotService(repo) + warn_store = InMemoryReconcileWarningStore() + slot = _make_holding_slot(repo, svc, qty=10) + warn_store.set_warned(str(slot.slot_id), portfolio_id="pf-A", case_code="X") + + row = slot_to_dict(slot, warn_store=warn_store) + + assert row["reconcile_warning_cases"] == ["X"] + assert row["trade_eligible"] is False + + def test_reconcile_warned_buy_emits_alarm_with_allowlisted_fields_after_finalize(): repo = InMemorySlotRepository() svc = SlotService(repo) diff --git a/tests/application/test_slots_handler_quantity_mismatch.py b/tests/application/test_slots_handler_quantity_mismatch.py index c374ced..333574b 100644 --- a/tests/application/test_slots_handler_quantity_mismatch.py +++ b/tests/application/test_slots_handler_quantity_mismatch.py @@ -371,6 +371,24 @@ def test_ac7_warn_store_failure_fail_closed(): assert "excluded_slots" in resp.payload +def test_unknown_warning_case_fails_closed(): + repo = InMemorySlotRepository() + svc = SlotService(repo) + warn_store = InMemoryReconcileWarningStore() + slot = _make_holding_slot(repo, svc, portfolio_id="pf-A", symbol=SYM_A, qty=10) + warn_store.set_warned(str(slot.slot_id), portfolio_id="pf-A", case_code="X") + + resp = _make_handler(repo, warn_store)(_req()) + + assert resp.payload["slots"] == [] + assert resp.payload["degraded"] is True + assert resp.payload["reason"] == "warn_store_unavailable" + assert resp.payload["excluded_slots"] == { + "reconcile_quantity_mismatch": 0, + "active_reconcile_warning_cases": {}, + } + + def test_ac23_exclusion_precedes_broker_and_strategy_state_readers(): repo = InMemorySlotRepository() svc = SlotService(repo) diff --git a/trex_core/application/intents.py b/trex_core/application/intents.py index 26afb70..7297d06 100644 --- a/trex_core/application/intents.py +++ b/trex_core/application/intents.py @@ -287,6 +287,11 @@ class IntentService: case_codes = {case_code} if case_code else set() if not case_codes: return True + # The warning row is authoritative. Unknown cases are not evidence + # that trading is safe: they may come from corrupt data or a newer + # producer that this core version cannot interpret. + if not case_codes.issubset(BLOCKING_RECONCILE_CASES): + return True return bool(case_codes & BLOCKING_RECONCILE_CASES) # ------------------------------------------------------------ diff --git a/trex_core/application/messaging_handlers.py b/trex_core/application/messaging_handlers.py index 527dbb1..f525d95 100644 --- a/trex_core/application/messaging_handlers.py +++ b/trex_core/application/messaging_handlers.py @@ -280,6 +280,8 @@ def make_slots_rpc_handler( codes = {case_code} if case_code else set() if not codes: raise RuntimeError(f"empty warning cases for slot_id={sid}") + if not codes.issubset(BLOCKING_RECONCILE_CASES): + raise RuntimeError(f"unsupported warning cases for slot_id={sid}") warning_cases_by_slot[str(sid)] = codes except Exception: # noqa: BLE001 _log.exception("warn_store warning query failed — fail-closed") diff --git a/trex_core/application/portfolio.py b/trex_core/application/portfolio.py index ba11a89..5e9e9ea 100644 --- a/trex_core/application/portfolio.py +++ b/trex_core/application/portfolio.py @@ -660,7 +660,9 @@ def slot_to_dict( reconcile_warned = bool(warning_cases) d["reconcile_warned"] = reconcile_warned d["reconcile_warning_cases"] = sorted(warning_cases) - d["trade_eligible"] = not bool(warning_cases & BLOCKING_RECONCILE_CASES) + known_blocking = bool(warning_cases & BLOCKING_RECONCILE_CASES) + unknown_cases = bool(warning_cases - BLOCKING_RECONCILE_CASES) + d["trade_eligible"] = not (known_blocking or unknown_cases) return d From f1e718e46835c8e898f1b57e691d7d5a696f41b4 Mon Sep 17 00:00:00 2001 From: Hermes Agent Date: Sat, 12 Sep 2026 23:06:29 +0900 Subject: [PATCH 10/11] docs: align reconcile warning acceptance criteria --- .proofline/criteria/ac-0022.md | 4 ++-- .proofline/criteria/ac-0023.md | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/.proofline/criteria/ac-0022.md b/.proofline/criteria/ac-0022.md index 54d5f67..d08ea22 100644 --- a/.proofline/criteria/ac-0022.md +++ b/.proofline/criteria/ac-0022.md @@ -7,9 +7,9 @@ status: active ## Criterion -`trex.slots.req.`의 **전략용 slots 응답에 포함되는** `holding` 슬롯(AC-0023에 따라 C-case 수량 불일치로 제외된 slot 제외)의 `qty`는 요청한 instance에 결합된 KIS account broker holdings(`hldg_qty`)를 authoritative source로 사용해야 한다. `daily_slot.qty`와 portfolio-hub 집계값은 각각 `slot_quantity`, `asset_quantity` 진단 필드로 분리 유지한다. broker 수량을 확보하지 못했거나 freshness 허용시간을 초과하면 core/hub mirror fallback 없이 `qty=null`, `qty_source="unavailable"`, `broker_quantity_available=false`, `broker_quantity_captured_at=null`을 반환해 전략이 fail-closed하도록 해야 한다. confirmed broker zero는 `qty=0`, `qty_source="broker"`로 unavailable과 구분되어야 한다. 이 read path는 주문 submit/cancel, ledger write, slot lifecycle mutation을 유발하지 않아야 한다. +`trex.slots.req.`의 **전략용 slots 응답에 포함되는** `holding` 슬롯(AC-0023에 따라 B 또는 C reconcile warning으로 제외된 slot 제외)의 `qty`는 요청한 instance에 결합된 KIS account broker holdings(`hldg_qty`)를 authoritative source로 사용해야 한다. `daily_slot.qty`와 portfolio-hub 집계값은 각각 `slot_quantity`, `asset_quantity` 진단 필드로 분리 유지한다. broker 수량을 확보하지 못했거나 freshness 허용시간을 초과하면 core/hub mirror fallback 없이 `qty=null`, `qty_source="unavailable"`, `broker_quantity_available=false`, `broker_quantity_captured_at=null`을 반환해 전략이 fail-closed하도록 해야 한다. confirmed broker zero는 `qty=0`, `qty_source="broker"`로 unavailable과 구분되어야 한다. 이 read path는 주문 submit/cancel, ledger write, slot lifecycle mutation을 유발하지 않아야 한다. -**Scope note:** AC-0023에 따라 C-case(`case_code=C`) 수량 불일치로 전략용 slots RPC에서 제외된 slot에는 이 AC의 broker-authoritative `qty` 응답 형식을 적용하지 않는다. AC-0023 제외가 AC-0022 broker-qty 형식보다 우선한다. +**Scope note:** AC-0023에 따라 B 또는 C reconcile warning(`case_code=B` 또는 `case_code=C`)으로 전략용 slots RPC에서 제외된 slot에는 이 AC의 broker-authoritative `qty` 응답 형식을 적용하지 않는다. AC-0023 제외가 AC-0022 broker-qty 형식보다 우선한다. ## Verification diff --git a/.proofline/criteria/ac-0023.md b/.proofline/criteria/ac-0023.md index b4fe994..1ab13c4 100644 --- a/.proofline/criteria/ac-0023.md +++ b/.proofline/criteria/ac-0023.md @@ -24,4 +24,4 @@ status: active - 해제 실패: 해제 도중 예외가 발생하면 `result='clear_failed'`를 반환하고 완전 성공으로 보고하지 않아야 한다(부분 성공 = 실패). - 시간이 지났다는 이유만으로 자동 해제하지 않음. - 비침습 조건: slots RPC 호출 전후로 slot 상태 전이, broker mutation, ledger write side effect가 없어야 한다. -- AC-0022 우선순위: C-case로 제외된 slot에는 broker-authoritative `qty` 응답 형식(AC-0022)을 적용하지 않는다. +- AC-0022 우선순위: B 또는 C reconcile warning으로 제외된 slot에는 broker-authoritative `qty` 응답 형식(AC-0022)을 적용하지 않는다. From 762a953c95574c8a2cd5e1a7665bd1a91655321d Mon Sep 17 00:00:00 2001 From: Hermes Agent Date: Sun, 13 Sep 2026 09:41:51 +0900 Subject: [PATCH 11/11] fix: fence ledger outbox claims by instance --- .proofline/criteria/ac-0029.md | 21 +++ .proofline/identities.json | 2 +- scripts/virtual_execution_final_state.py | 2 +- .../persistence/test_migration_and_drift.py | 4 +- .../test_postgresql_ledger_outbox.py | 43 ++++- tests/application/test_execution_cancel.py | 2 +- .../test_execution_fill_price_backfill.py | 4 +- tests/application/test_execution_ledger.py | 8 +- tests/application/test_ledger_option_d.py | 16 +- tests/application/test_ledger_outbox.py | 116 ++++++++++++-- .../application/test_ledger_outbox_backoff.py | 2 +- .../test_messaging_event_publisher.py | 4 +- trex_core/adapters/persistence/postgresql.py | 31 +++- ... => 029_ledger_outbox_instance_claims.sql} | 0 trex_core/application/ledger_outbox.py | 149 +++++++++++++----- 15 files changed, 316 insertions(+), 88 deletions(-) create mode 100644 .proofline/criteria/ac-0029.md rename trex_core/adapters/persistence/sql/{028_ledger_outbox_instance_claims.sql => 029_ledger_outbox_instance_claims.sql} (100%) diff --git a/.proofline/criteria/ac-0029.md b/.proofline/criteria/ac-0029.md new file mode 100644 index 0000000..04b4574 --- /dev/null +++ b/.proofline/criteria/ac-0029.md @@ -0,0 +1,21 @@ +--- +id: "ac-0029" +status: active +--- + +# Ledger outbox instance ownership and lease fencing + +## Criterion + +`trex-core`의 durable ledger outbox row는 enqueue 시점의 required non-empty `instance_key`를 immutable owner로 저장해야 하며, daemon·operator backfill·targeted processing을 포함한 모든 delivery 경로는 자기 instance의 row만 claim하고 처리해야 한다. Shared PostgreSQL에서 claim은 pending·retry-due·unclaimed 또는 lease-expired row를 원자적으로 선택해 worker별 bounded lease를 설정해야 하고, 성공·중복·retryable·conflict·permanent·dead-letter outcome은 해당 claim의 fencing 정보가 일치할 때만 반영해야 한다. 다른 instance, legacy `instance_key IS NULL`, 아직 유효한 foreign lease 또는 이미 새 worker가 reclaim한 row는 처리·상태 변경·성공 통계·ledger-skip resolution 없이 fail closed 해야 한다. + +Claim owner가 crash하면 lease 만료 후 같은 instance의 다른 worker가 row를 reclaim할 수 있어야 한다. Outcome CAS가 0건이면 claim 상실로 명시적으로 처리하고 성공 outcome으로 보고해서는 안 된다. InMemory와 PostgreSQL outbox는 instance filtering, active lease exclusion, expiry recovery와 stale-claim rejection에서 같은 의미를 가져야 한다. Claim·outcome 관측 정보에는 `instance_key`, sanitized result/reason과 correlation identity만 허용하며 credential, account identifier, token, password, DSN, provider payload 또는 exception 원문을 로그·metric·alert에 포함해서는 안 된다. + +## Verification + +- 격리 조건: 서로 다른 `instance_key`의 daemon/writer 두 개가 한 PostgreSQL을 공유할 때 각 writer는 자기 row만 claim·전송·집계한다. `list_pending`, `pending_cash_delta`, batch claim과 correlation-targeted claim 모두 foreign row와 `instance_key IS NULL` legacy row를 제외한다. 누락·빈 instance key로 outbox 또는 writer를 생성하면 외부 연결이나 row 생성 전에 거부된다. +- lease 조건: worker A가 claim한 row는 lease 동안 worker B가 claim하지 못한다. A가 outcome을 기록하면 lease가 해제되고 terminal 또는 retry 상태가 정확히 저장된다. A가 crash한 경우 expiry 전에는 B가 claim하지 못하고 expiry 뒤에는 B가 reclaim할 수 있다. Reclaim 뒤 A의 stale outcome은 typed claim-lost 결과로 거부되며 B의 row 상태, outcome, attempt count, next retry와 lease를 변경하지 않는다. +- outcome 조건: adapter의 신규 성공과 `DUPLICATE_OK`, retryable, conflict, permanent 및 dead-letter 모든 분기는 claim fencing을 전달한다. CAS 실패 시 completion/retry counter, 성공 로그, snapshot write-back 이후의 ledger-skip resolution을 실행하지 않는다. Adapter duplicate는 row를 `completed/duplicate_completed`로 만들고 lease를 즉시 해제하여 재전송되지 않는다. +- InMemory parity: 두 번의 동시 claim에서 첫 claim만 성공하고 active lease row는 pending scan에서 제외된다. clock을 이동하면 expiry recovery가 가능하며 이전 claim token으로 outcome을 기록할 수 없다. Instance filter와 targeted processing의 fail-closed 동작이 PostgreSQL과 같다. +- 보안 조건: exception에 credential·account·token·password·DSN·provider payload를 식별하는 sentinel을 넣어 claim 실패, retry, permanent, dead-letter와 write-back 오류를 실행해도 rendered log, metric key/value와 alert에 sentinel 또는 exception 원문이 나타나지 않는다. +- migration 및 회귀: migration 번호는 저장소에서 유일하고 기존 row를 자동 귀속시키지 않으며 `instance_key IS NULL`로 격리한다. 빈 DB와 기존 schema 모두에서 migration apply/replay, PostgreSQL claim round-trip, restart/expiry 회수, daemon·CLI wiring을 검증한다. 전체 repository test, Ruff, compileall, ProofLine validation과 `git diff --check`를 실행한다. diff --git a/.proofline/identities.json b/.proofline/identities.json index 34f4cf3..e90cfd1 100644 --- a/.proofline/identities.json +++ b/.proofline/identities.json @@ -1,5 +1,5 @@ { "schema_version": 1, "next_line_number": 10, - "next_ac_number": 29 + "next_ac_number": 30 } diff --git a/scripts/virtual_execution_final_state.py b/scripts/virtual_execution_final_state.py index 80eba0f..f05ea30 100644 --- a/scripts/virtual_execution_final_state.py +++ b/scripts/virtual_execution_final_state.py @@ -32,7 +32,7 @@ def main() -> int: ) repo.reconcile_universe(instance, {portfolio_id: symbol}) broker = PaperBroker(fill_after_polls=0) - outbox = InMemoryLedgerOutbox() + outbox = InMemoryLedgerOutbox(instance_key="test-instance") ledger = InMemoryLedger() execution = ExecutionService( slots, diff --git a/tests/adapters/persistence/test_migration_and_drift.py b/tests/adapters/persistence/test_migration_and_drift.py index 592cc60..71c5c21 100644 --- a/tests/adapters/persistence/test_migration_and_drift.py +++ b/tests/adapters/persistence/test_migration_and_drift.py @@ -118,7 +118,7 @@ def test_migration_replay_converts_existing_auto_venue_row_to_sor(pg_clean): def test_migration_024_separates_legacy_sor_and_is_replay_safe(pg_clean): - outbox = PostgreSQLLedgerOutbox(pg_clean) + outbox = PostgreSQLLedgerOutbox(pg_clean, instance_key="test-instance") normal = LedgerTrade( asset_id="PF-NORMAL", order_id="O-NORMAL", @@ -177,7 +177,7 @@ def test_migration_024_separates_legacy_sor_and_is_replay_safe(pg_clean): ) -def test_migration_028_fail_closes_unowned_legacy_outbox_rows(pg_clean): +def test_migration_029_fail_closes_unowned_legacy_outbox_rows(pg_clean): outbox = PostgreSQLLedgerOutbox(pg_clean, instance_key="inst-a") trade = LedgerTrade( asset_id="PF-LEGACY", diff --git a/tests/adapters/persistence/test_postgresql_ledger_outbox.py b/tests/adapters/persistence/test_postgresql_ledger_outbox.py index d9d465d..eef6e87 100644 --- a/tests/adapters/persistence/test_postgresql_ledger_outbox.py +++ b/tests/adapters/persistence/test_postgresql_ledger_outbox.py @@ -4,12 +4,16 @@ Skipped without TREX_POSTGRESQL_TEST_DSN (same gate as other PG suites). """ from __future__ import annotations +from concurrent.futures import ThreadPoolExecutor from datetime import UTC, datetime +import pytest + from trex_core.adapters.ledger.in_memory import InMemoryLedger from trex_core.adapters.persistence.postgresql import PostgreSQLLedgerOutbox from trex_core.application.ledger_outbox import ( LedgerWriter, + OutboxClaimLostError, OutboxOutcome, WorkItemStatus, ) @@ -196,18 +200,27 @@ def test_stale_claim_cannot_overwrite_new_owner_outcome(pg_clean): expected_claim_expires_at=claim_b.claim_expires_at, ) - stored = outbox_a.mark_outcome( - row.correlation_id, - OutboxOutcome.RETRYABLE_FAILURE, - error="stale owner", - next_retry_at=now["t"], - expected_claim_expires_at=claim_a.claim_expires_at, - ) + with pytest.raises(OutboxClaimLostError): + outbox_a.mark_outcome( + row.correlation_id, + OutboxOutcome.RETRYABLE_FAILURE, + error="stale owner", + next_retry_at=now["t"], + expected_claim_expires_at=claim_a.claim_expires_at, + ) + stored = outbox_a.get(row.correlation_id) + assert stored is not None assert stored.status is WorkItemStatus.COMPLETED assert stored.last_outcome is OutboxOutcome.COMPLETED +@pytest.mark.parametrize("instance_key", ["", " "]) +def test_postgresql_outbox_rejects_empty_instance_before_connect(pg_clean, instance_key): + with pytest.raises(ValueError, match="non-empty"): + PostgreSQLLedgerOutbox(pg_clean, instance_key=instance_key) + + def test_original_owner_can_finalize_expired_unreclaimed_claim(pg_clean): now = {"t": datetime(2026, 6, 4, tzinfo=UTC)} outbox = PostgreSQLLedgerOutbox( @@ -255,6 +268,22 @@ def test_writer_records_retryable_403_without_cross_instance_delivery(pg_clean): assert outbox_a.get(row_a.correlation_id).status is WorkItemStatus.PENDING +def test_concurrent_workers_claim_each_row_at_most_once(pg_clean): + outbox_a = PostgreSQLLedgerOutbox( + pg_clean, instance_key="inst-a", worker_id="worker-a" + ) + outbox_b = PostgreSQLLedgerOutbox( + pg_clean, instance_key="inst-a", worker_id="worker-b" + ) + row = outbox_a.enqueue(_trade(execution_id="pg-concurrent")) + + with ThreadPoolExecutor(max_workers=2) as pool: + claims = list(pool.map(lambda box: box.claim_pending(), (outbox_a, outbox_b))) + + claimed_ids = [item.correlation_id for batch in claims for item in batch] + assert claimed_ids == [row.correlation_id] + + def test_writer_marks_duplicate_completed_from_adapter_response_on_pg(pg_clean): class _DuplicateLedger: def record_trade(self, _trade): diff --git a/tests/application/test_execution_cancel.py b/tests/application/test_execution_cancel.py index a88fd8c..3fa65f9 100644 --- a/tests/application/test_execution_cancel.py +++ b/tests/application/test_execution_cancel.py @@ -70,7 +70,7 @@ def _wire(broker, *, stale_sec=None): svc = SlotService(repo) intents = IntentService(svc, repo, InMemoryIntentStore(), resolve_symbol=lambda pid: "005930") - outbox = InMemoryLedgerOutbox() + outbox = InMemoryLedgerOutbox(instance_key="test-instance") ledger = InMemoryLedger() execution = ExecutionService( svc, repo, broker, ledger_outbox=outbox, diff --git a/tests/application/test_execution_fill_price_backfill.py b/tests/application/test_execution_fill_price_backfill.py index 6bb6ac7..2baf2d2 100644 --- a/tests/application/test_execution_fill_price_backfill.py +++ b/tests/application/test_execution_fill_price_backfill.py @@ -120,7 +120,7 @@ def _wire(broker): resolve_symbol=lambda pid: "005930", instance_key=INST, ) - outbox = InMemoryLedgerOutbox() + outbox = InMemoryLedgerOutbox(instance_key="test-instance") execution = ExecutionService(svc, repo, broker, ledger_outbox=outbox, instance_key=INST) repo.reconcile_universe(INST, {"PF-1": "005930"}) return repo, svc, intents, execution, outbox @@ -966,7 +966,7 @@ class TestPaperBrokerRegression: resolve_symbol=lambda pid: "005930", instance_key=INST, ) - outbox2 = InMemoryLedgerOutbox() + outbox2 = InMemoryLedgerOutbox(instance_key="test-instance") execution2 = ExecutionService(svc2, repo2, paper, ledger_outbox=outbox2, instance_key=INST) repo2.reconcile_universe(INST, {"PF-1": "005930"}) diff --git a/tests/application/test_execution_ledger.py b/tests/application/test_execution_ledger.py index d993c2c..e1aa009 100644 --- a/tests/application/test_execution_ledger.py +++ b/tests/application/test_execution_ledger.py @@ -119,7 +119,11 @@ def _wire(broker, *, ledger=None, clock=None, alarm_emitter=None, ledger_skip_st svc = SlotService(repo) intents = IntentService(svc, repo, InMemoryIntentStore(), resolve_symbol=lambda pid: "005930") - outbox = InMemoryLedgerOutbox(clock=clock) if clock else InMemoryLedgerOutbox() + outbox = ( + InMemoryLedgerOutbox(clock=clock, instance_key="default") + if clock + else InMemoryLedgerOutbox(instance_key="default") + ) execution = ExecutionService( svc, repo, @@ -430,7 +434,7 @@ def test_duplicate_execution_id_results_in_zero_duplicate_in_ledger(): # And even if the writer somehow re-processes (simulated by a fresh outbox # row for the same execution_id, e.g. after a manual replay), the ledger # adapter dedup'd it server-side and the outcome is duplicate_completed. - replay_outbox = InMemoryLedgerOutbox() + replay_outbox = InMemoryLedgerOutbox(instance_key="test-instance") replay_writer = LedgerWriter(replay_outbox, ledger) replay_outbox.enqueue(first.trade) stats = replay_writer.run_once() diff --git a/tests/application/test_ledger_option_d.py b/tests/application/test_ledger_option_d.py index 8685773..e0e8769 100644 --- a/tests/application/test_ledger_option_d.py +++ b/tests/application/test_ledger_option_d.py @@ -39,7 +39,7 @@ def _store_with(pid="PF-1", cash=1_000_000.0, qty=0.0): # --- write-back (REQ-019/030) ---------------------------------------------- def test_writeback_updates_snapshot_on_new(): store = _store_with() - outbox = InMemoryLedgerOutbox() + outbox = InMemoryLedgerOutbox(instance_key="test-instance") ledger = InMemoryLedger(cash_after=300_000.0, quantity_after=10.0) writer = LedgerWriter(outbox, ledger, snapshot_store=store) outbox.enqueue(_trade()) @@ -50,7 +50,7 @@ def test_writeback_updates_snapshot_on_new(): def test_writeback_applies_on_duplicate_too(): store = _store_with(cash=1_000_000.0) - outbox = InMemoryLedgerOutbox() + outbox = InMemoryLedgerOutbox(instance_key="test-instance") # execution already recorded once → second write is duplicate, *_after still authoritative ledger = InMemoryLedger(cash_after=300_000.0, quantity_after=10.0) ledger.record_trade(_trade(execution_id="dup")) # pre-record → next is duplicate @@ -62,7 +62,7 @@ def test_writeback_applies_on_duplicate_too(): def test_writeback_skipped_when_after_missing(): store = _store_with(cash=1_000_000.0) - outbox = InMemoryLedgerOutbox() + outbox = InMemoryLedgerOutbox(instance_key="test-instance") ledger = InMemoryLedger() # no cash_after/quantity_after → None writer = LedgerWriter(outbox, ledger, snapshot_store=store) outbox.enqueue(_trade()) @@ -74,7 +74,7 @@ def test_writeback_best_effort_does_not_block_completion(): class _BoomStore: def update_cash_position(self, *a, **k): raise RuntimeError("boom") - outbox = InMemoryLedgerOutbox() + outbox = InMemoryLedgerOutbox(instance_key="test-instance") ledger = InMemoryLedger(cash_after=1.0, quantity_after=1.0) writer = LedgerWriter(outbox, ledger, snapshot_store=_BoomStore()) outbox.enqueue(_trade()) @@ -83,7 +83,7 @@ def test_writeback_best_effort_does_not_block_completion(): def test_no_writeback_without_store(): - outbox = InMemoryLedgerOutbox() + outbox = InMemoryLedgerOutbox(instance_key="test-instance") ledger = InMemoryLedger(cash_after=1.0, quantity_after=1.0) writer = LedgerWriter(outbox, ledger) # no snapshot_store outbox.enqueue(_trade()) @@ -92,7 +92,7 @@ def test_no_writeback_without_store(): # --- estimate overlay (REQ-029 / OQ-4) — via make_slots_rpc_handler ---------- def test_pending_cash_delta_sums_by_asset(): - outbox = InMemoryLedgerOutbox() + outbox = InMemoryLedgerOutbox(instance_key="test-instance") outbox.enqueue(_trade(execution_id="b", side="buy", qty=10, price=1000.0, fee=1.0)) deltas = outbox.pending_cash_delta() assert deltas["PF-1"] == trade_cash_delta(_trade(side="buy", qty=10, price=1000.0, fee=1.0)) @@ -101,7 +101,7 @@ def test_pending_cash_delta_sums_by_asset(): def test_apply_cash_estimate_overlays_pending_delta(): """Cash-estimated overlay applied through slots handler (REQ-029 OQ-4).""" - outbox = InMemoryLedgerOutbox() + outbox = InMemoryLedgerOutbox(instance_key="test-instance") outbox.enqueue(_trade(execution_id="b", side="buy", qty=10, price=1000.0, fee=1.0)) store = _store_with(pid="PF-1", cash=1_000_000.0, qty=0.0) repo = InMemorySlotRepository() @@ -117,7 +117,7 @@ def test_apply_cash_estimate_overlays_pending_delta(): def test_estimate_clears_after_writeback(): """Once the ledger write completes (no longer pending), the estimate is gone.""" store = _store_with(cash=1_000_000.0) - outbox = InMemoryLedgerOutbox() + outbox = InMemoryLedgerOutbox(instance_key="test-instance") ledger = InMemoryLedger(cash_after=989_999.0, quantity_after=10.0) writer = LedgerWriter(outbox, ledger, snapshot_store=store) outbox.enqueue(_trade(side="buy", qty=10, price=1000.0, fee=1.0)) diff --git a/tests/application/test_ledger_outbox.py b/tests/application/test_ledger_outbox.py index 651efc6..64fc05c 100644 --- a/tests/application/test_ledger_outbox.py +++ b/tests/application/test_ledger_outbox.py @@ -1,16 +1,20 @@ """LedgerOutbox + LedgerWriter direct unit tests (REQ-019).""" from __future__ import annotations +from dataclasses import replace from datetime import UTC, datetime, timedelta +import pytest + from trex_core.adapters.ledger.in_memory import InMemoryLedger from trex_core.application.ledger_outbox import ( InMemoryLedgerOutbox, LedgerWriter, + OutboxClaimLostError, OutboxOutcome, WorkItemStatus, ) -from trex_core.application.ledger_port import LedgerTrade +from trex_core.application.ledger_port import LedgerPermanentError, LedgerTrade def _trade(execution_id="paper:PAPER-1:10") -> LedgerTrade: @@ -22,7 +26,7 @@ def _trade(execution_id="paper:PAPER-1:10") -> LedgerTrade: def test_enqueue_is_idempotent_on_correlation_id(): - outbox = InMemoryLedgerOutbox() + outbox = InMemoryLedgerOutbox(instance_key="test-instance") a = outbox.enqueue(_trade()) b = outbox.enqueue(_trade()) assert a.correlation_id == b.correlation_id @@ -30,7 +34,7 @@ def test_enqueue_is_idempotent_on_correlation_id(): def test_writer_run_once_drains_pending_and_marks_completed(): - outbox = InMemoryLedgerOutbox() + outbox = InMemoryLedgerOutbox(instance_key="test-instance") ledger = InMemoryLedger() writer = LedgerWriter(outbox, ledger) outbox.enqueue(_trade(execution_id="e-1")) @@ -42,7 +46,7 @@ def test_writer_run_once_drains_pending_and_marks_completed(): def test_writer_marks_conflict_blocked_and_does_not_retry(): - outbox = InMemoryLedgerOutbox() + outbox = InMemoryLedgerOutbox(instance_key="test-instance") ledger = InMemoryLedger(conflict_executions={"e-x"}) writer = LedgerWriter(outbox, ledger) outbox.enqueue(_trade(execution_id="e-x")) @@ -58,7 +62,9 @@ def test_writer_retries_until_success(): # dcy-015: retryable rows now back off; share an injected clock between the # outbox (list_pending "now") and the writer (next_retry_at) to advance past it. now = {"t": datetime(2026, 6, 4, tzinfo=UTC)} - outbox = InMemoryLedgerOutbox(clock=lambda: now["t"]) + outbox = InMemoryLedgerOutbox( + clock=lambda: now["t"], instance_key="test-instance" + ) ledger = InMemoryLedger(fail_n_then_succeed=1) writer = LedgerWriter(outbox, ledger, clock=lambda: now["t"]) outbox.enqueue(_trade(execution_id="e-r")) @@ -90,17 +96,29 @@ def test_process_correlation_id_only_drains_requested_row(): def test_process_correlation_id_skips_foreign_instance_row(): outbox = InMemoryLedgerOutbox(instance_key="inst-a") ledger = InMemoryLedger() - writer = LedgerWriter(outbox, ledger, instance_key="inst-b") item = outbox.enqueue(_trade(execution_id="e-foreign")) - outcome = writer.process_correlation_id(item.correlation_id) - - assert outcome is None + with pytest.raises(ValueError, match="must match"): + LedgerWriter(outbox, ledger, instance_key="inst-b") assert ledger.count() == 0 - assert writer.counters["claim:foreign_instance"] == 1 assert outbox.get(item.correlation_id).status is WorkItemStatus.PENDING +def test_process_correlation_id_rejects_legacy_row_without_instance_owner(): + class _LegacyOutbox(InMemoryLedgerOutbox): + def get(self, correlation_id): + item = super().get(correlation_id) + return replace(item, instance_key=None) if item is not None else None + + outbox = _LegacyOutbox(instance_key="inst-a") + ledger = InMemoryLedger() + writer = LedgerWriter(outbox, ledger, instance_key="inst-a") + item = outbox.enqueue(_trade()) + + assert writer.process_correlation_id(item.correlation_id) is None + assert ledger.count() == 0 + + def test_writer_exposes_claim_and_outcome_counters(): outbox = InMemoryLedgerOutbox(instance_key="inst-a") ledger = InMemoryLedger() @@ -112,3 +130,81 @@ def test_writer_exposes_claim_and_outcome_counters(): assert stats.completed == 1 assert writer.counters["claim:claimed"] == 1 assert writer.counters["outcome:completed"] == 1 + + +@pytest.mark.parametrize("instance_key", ["", " "]) +def test_writer_rejects_explicit_empty_instance_key(instance_key): + outbox = InMemoryLedgerOutbox(instance_key="inst-a") + with pytest.raises(ValueError, match="non-empty"): + LedgerWriter(outbox, InMemoryLedger(), instance_key=instance_key) + + +@pytest.mark.parametrize("instance_key", ["", " "]) +def test_outbox_rejects_empty_instance_key(instance_key): + with pytest.raises(ValueError, match="non-empty"): + InMemoryLedgerOutbox(instance_key=instance_key) + + +def test_in_memory_claim_is_exclusive_and_stale_lease_is_fenced(): + now = {"t": datetime(2026, 6, 4, tzinfo=UTC)} + outbox = InMemoryLedgerOutbox( + instance_key="inst-a", + claim_ttl_sec=5.0, + clock=lambda: now["t"], + ) + item = outbox.enqueue(_trade(execution_id="e-lease")) + + [claim_a] = outbox.claim_pending() + assert outbox.claim_pending() == [] + assert outbox.list_pending() == [] + + now["t"] += timedelta(seconds=6) + [claim_b] = outbox.claim_pending() + assert claim_b.claim_expires_at != claim_a.claim_expires_at + with pytest.raises(OutboxClaimLostError): + outbox.mark_outcome( + item.correlation_id, + OutboxOutcome.COMPLETED, + expected_claim_expires_at=claim_a.claim_expires_at, + ) + + stored = outbox.mark_outcome( + item.correlation_id, + OutboxOutcome.COMPLETED, + expected_claim_expires_at=claim_b.claim_expires_at, + ) + assert stored.status is WorkItemStatus.COMPLETED + assert stored.claim_expires_at is None + + +def test_outcome_logs_do_not_render_exception_text(caplog): + sentinel = "TOKEN_SENTINEL_ACCOUNT_DSN_PAYLOAD" + + class _FailingLedger: + def record_trade(self, _trade): + raise LedgerPermanentError(sentinel) + + outbox = InMemoryLedgerOutbox(instance_key="inst-a") + writer = LedgerWriter(outbox, _FailingLedger(), instance_key="inst-a") + outbox.enqueue(_trade(execution_id="e-sensitive")) + + with caplog.at_level("INFO"): + stats = writer.run_once() + + assert stats.delivery_failed == 1 + assert sentinel not in caplog.text + + +def test_lost_claim_is_counted_without_false_completion(): + class _ClaimLosingOutbox(InMemoryLedgerOutbox): + def mark_outcome(self, correlation_id, outcome, **kwargs): + raise OutboxClaimLostError(correlation_id) + + outbox = _ClaimLosingOutbox(instance_key="inst-a") + outbox.enqueue(_trade()) + writer = LedgerWriter(outbox, InMemoryLedger(), instance_key="inst-a") + + stats = writer.run_once() + + assert stats.claim_lost == 1 + assert stats.completed == 0 diff --git a/tests/application/test_ledger_outbox_backoff.py b/tests/application/test_ledger_outbox_backoff.py index 5c5cd5d..577c2bd 100644 --- a/tests/application/test_ledger_outbox_backoff.py +++ b/tests/application/test_ledger_outbox_backoff.py @@ -47,7 +47,7 @@ class _ProgrammableLedger: def _wire(behavior, *, clock, **writer_kw): - outbox = InMemoryLedgerOutbox(clock=clock) + outbox = InMemoryLedgerOutbox(clock=clock, instance_key="test-instance") ledger = _ProgrammableLedger(behavior) writer = LedgerWriter(outbox, ledger, clock=clock, rng=lambda: 0.0, **writer_kw) return outbox, ledger, writer diff --git a/tests/application/test_messaging_event_publisher.py b/tests/application/test_messaging_event_publisher.py index 03a3bd5..e612a1c 100644 --- a/tests/application/test_messaging_event_publisher.py +++ b/tests/application/test_messaging_event_publisher.py @@ -22,7 +22,7 @@ def _wire(transport): svc = SlotService(repo) intents = IntentService(svc, repo, InMemoryIntentStore(), resolve_symbol=lambda pid: "005930") - outbox = InMemoryLedgerOutbox() + outbox = InMemoryLedgerOutbox(instance_key="test-instance") ledger = InMemoryLedger() writer = LedgerWriter(outbox, ledger) repo.reconcile_universe("default", {"PF-1": "SYM"}) @@ -203,7 +203,7 @@ def test_sell_fill_dlq_sentinel_absent_when_strategy_id_set(): intents = IntentService(svc, repo, InMemoryIntentStore(), resolve_symbol=lambda pid: "005930") from trex_core.application.ledger_outbox import InMemoryLedgerOutbox - outbox = InMemoryLedgerOutbox() + outbox = InMemoryLedgerOutbox(instance_key="test-instance") execution = ExecutionService(svc, repo, PaperBroker(fill_after_polls=0), ledger_outbox=outbox, event_emitter=emitter) repo.reconcile_universe("default", {"PF-1": "SYM"}) diff --git a/trex_core/adapters/persistence/postgresql.py b/trex_core/adapters/persistence/postgresql.py index 3812448..8439926 100644 --- a/trex_core/adapters/persistence/postgresql.py +++ b/trex_core/adapters/persistence/postgresql.py @@ -21,6 +21,7 @@ from uuid import UUID, uuid4 from trex_core.application.ledger_outbox import ( LedgerWorkItem, + OutboxClaimLostError, OutboxOutcome, WorkItemStatus, ) @@ -569,6 +570,9 @@ _OUTBOX_COLUMNS = ( "created_at, updated_at, next_retry_at, venue, order_venue, instance_key, " "claim_expires_at" ) +_OUTBOX_RETURN_COLUMNS = ", ".join( + f"o.{column.strip()}" for column in _OUTBOX_COLUMNS.split(",") +) class PostgreSQLLedgerOutbox: @@ -578,12 +582,16 @@ class PostgreSQLLedgerOutbox: self, dsn: str, *, - instance_key: str = "default", + instance_key: str, claim_ttl_sec: float = 60.0, worker_id: str | None = None, clock=None, psycopg_module: Any = None, ) -> None: + if not isinstance(instance_key, str) or not instance_key.strip(): + raise ValueError("instance_key must be a non-empty string") + if claim_ttl_sec <= 0: + raise ValueError("claim_ttl_sec must be positive") self._psycopg = _require_psycopg(psycopg_module) self._dsn = dsn self._instance_key = instance_key @@ -594,6 +602,10 @@ class PostgreSQLLedgerOutbox: def _now(self) -> datetime: return self._clock() + @property + def instance_key(self) -> str: + return self._instance_key + def enqueue(self, trade: LedgerTrade) -> LedgerWorkItem: with self._psycopg.connect(self._dsn, autocommit=False) as conn: with conn.cursor() as cur: @@ -625,16 +637,17 @@ class PostgreSQLLedgerOutbox: return existing def list_pending(self, limit: int = 32) -> list[LedgerWorkItem]: + now = self._now() with self._psycopg.connect(self._dsn) as conn: with conn.cursor() as cur: cur.execute( f"SELECT {_OUTBOX_COLUMNS} FROM ledger_outbox " "WHERE status = 'pending' " "AND instance_key = %s " - "AND (next_retry_at IS NULL OR next_retry_at <= now()) " - "AND (claim_expires_at IS NULL OR claim_expires_at <= now()) " + "AND (next_retry_at IS NULL OR next_retry_at <= %s) " + "AND (claim_expires_at IS NULL OR claim_expires_at <= %s) " "ORDER BY created_at, correlation_id LIMIT %s", - (self._instance_key, limit), + (self._instance_key, now, now, limit), ) return [self._row_to_item(r) for r in cur.fetchall()] @@ -647,7 +660,7 @@ class PostgreSQLLedgerOutbox: now = self._now() lease_until = now + timedelta(seconds=self._claim_ttl_sec) correlation_sql = "" - params: list[Any] = [self._instance_key] + params: list[Any] = [self._instance_key, now, now] if correlation_id is not None: correlation_sql = "AND correlation_id = %s " params.append(correlation_id) @@ -659,8 +672,8 @@ class PostgreSQLLedgerOutbox: "SELECT correlation_id FROM ledger_outbox " "WHERE status = 'pending' " "AND instance_key = %s " - "AND (next_retry_at IS NULL OR next_retry_at <= now()) " - "AND (claim_expires_at IS NULL OR claim_expires_at <= now()) " + "AND (next_retry_at IS NULL OR next_retry_at <= %s) " + "AND (claim_expires_at IS NULL OR claim_expires_at <= %s) " f"{correlation_sql}" "ORDER BY created_at, correlation_id " "LIMIT %s " @@ -670,7 +683,7 @@ class PostgreSQLLedgerOutbox: "SET claim_owner = %s, claim_expires_at = %s, updated_at = %s " "FROM candidates " "WHERE o.correlation_id = candidates.correlation_id " - f"RETURNING {_OUTBOX_COLUMNS}", + f"RETURNING {_OUTBOX_RETURN_COLUMNS}", params, ) rows = [self._row_to_item(r) for r in cur.fetchall()] @@ -759,6 +772,8 @@ class PostgreSQLLedgerOutbox: f"{where}", params, ) + if cur.rowcount != 1: + raise OutboxClaimLostError(correlation_id) conn.commit() row = self.get(correlation_id) assert row is not None diff --git a/trex_core/adapters/persistence/sql/028_ledger_outbox_instance_claims.sql b/trex_core/adapters/persistence/sql/029_ledger_outbox_instance_claims.sql similarity index 100% rename from trex_core/adapters/persistence/sql/028_ledger_outbox_instance_claims.sql rename to trex_core/adapters/persistence/sql/029_ledger_outbox_instance_claims.sql diff --git a/trex_core/application/ledger_outbox.py b/trex_core/application/ledger_outbox.py index 2dc7eac..cf043ed 100644 --- a/trex_core/application/ledger_outbox.py +++ b/trex_core/application/ledger_outbox.py @@ -66,6 +66,10 @@ class WorkItemStatus(str, Enum): DELIVERY_FAILED = "delivery_failed" # dcy-015 — permanent or dead-lettered (terminal) +class OutboxClaimLostError(RuntimeError): + """The caller no longer owns the lease required for an outcome update.""" + + # Outcomes that move a row to the terminal delivery_failed state. _DELIVERY_FAILED_OUTCOMES = frozenset( {OutboxOutcome.PERMANENT_FAILURE, OutboxOutcome.DEAD_LETTERED} @@ -111,6 +115,11 @@ class LedgerWorkItem: class LedgerOutbox(Protocol): """Durable work-item store backing the ledger writer.""" + @property + def instance_key(self) -> str: + """Immutable owner partition for rows handled by this outbox.""" + ... + def enqueue(self, trade: LedgerTrade) -> LedgerWorkItem: """Enqueue a trade. Idempotent on correlation_id (returns the existing row unchanged if it is already present).""" @@ -163,6 +172,7 @@ class WriterStats: retryable: int = 0 conflicts: int = 0 delivery_failed: int = 0 # dcy-015: permanent + dead-lettered terminals + claim_lost: int = 0 class LedgerWriter: @@ -202,7 +212,12 @@ class LedgerWriter: # dcy-033 / REQ-100: best-effort alarm emitter. self._alarm_emitter = alarm_emitter self._ledger_skip_store = ledger_skip_store - self._instance_key = instance_key + resolved_instance_key = outbox.instance_key if instance_key is None else instance_key + if not isinstance(resolved_instance_key, str) or not resolved_instance_key.strip(): + raise ValueError("instance_key must be a non-empty string") + if resolved_instance_key != outbox.instance_key: + raise ValueError("writer instance_key must match outbox instance_key") + self._instance_key = resolved_instance_key self.counters: dict[str, int] = {} def _count(self, key: str) -> None: @@ -224,7 +239,19 @@ class LedgerWriter: limit, ) for item in items: - outcome = self._process(item) + if not self._validate_instance(item): + continue + try: + outcome = self._process(item) + except OutboxClaimLostError: + self._count("claim:lost") + stats.claim_lost += 1 + _log.warning( + "ledger outbox claim lost: instance_key=%s correlation_id=%s", + self._instance_key, + item.correlation_id, + ) + continue if outcome is OutboxOutcome.COMPLETED: stats.completed += 1 elif outcome is OutboxOutcome.DUPLICATE_COMPLETED: @@ -242,19 +269,7 @@ class LedgerWriter: item = self._outbox.get(correlation_id) if item is None: return None - if ( - self._instance_key is not None - and item.instance_key is not None - and item.instance_key != self._instance_key - ): - self._count("claim:foreign_instance") - _log.info( - "ledger outbox claim: instance_key=%s claim_result=foreign_instance " - "correlation_id=%s owner_instance_key=%s", - self._instance_key, - correlation_id, - item.instance_key, - ) + if not self._validate_instance(item): return None if item.status is WorkItemStatus.PENDING: claimed = self._outbox.claim_pending(1, correlation_id=correlation_id) @@ -276,7 +291,28 @@ class LedgerWriter: len(claimed), correlation_id, ) - return self._process(item) + try: + return self._process(item) + except OutboxClaimLostError: + self._count("claim:lost") + _log.warning( + "ledger outbox claim lost: instance_key=%s correlation_id=%s", + self._instance_key, + correlation_id, + ) + return None + + def _validate_instance(self, item: LedgerWorkItem) -> bool: + if item.instance_key == self._instance_key: + return True + self._count("claim:foreign_instance") + _log.warning( + "ledger outbox claim rejected: instance_key=%s " + "claim_result=foreign_or_unowned correlation_id=%s", + self._instance_key, + item.correlation_id, + ) + return False def _backoff_delay(self, attempts: int) -> float: """Exponential backoff with jitter: min(base*2^(n-1), cap) + up to 25%.""" @@ -288,7 +324,6 @@ class LedgerWriter: # outbox row. Skip the adapter call. existing = self._outbox.get(item.correlation_id) if existing is not None and existing.status is WorkItemStatus.COMPLETED: - self._outbox.mark_outcome(item.correlation_id, OutboxOutcome.DUPLICATE_COMPLETED) self._log_outcome(item, OutboxOutcome.DUPLICATE_COMPLETED) return OutboxOutcome.DUPLICATE_COMPLETED try: @@ -300,7 +335,7 @@ class LedgerWriter: error=str(exc), expected_claim_expires_at=item.claim_expires_at, ) - self._log_outcome(item, OutboxOutcome.CONFLICT_BLOCKED, error=str(exc)) + self._log_outcome(item, OutboxOutcome.CONFLICT_BLOCKED) # dcy-033 / REQ-100: CRITICAL alarm — 409 conflict, operator resolution needed. if self._alarm_emitter is not None: self._alarm_emitter.publish_alarm( @@ -320,11 +355,11 @@ class LedgerWriter: error=str(exc), expected_claim_expires_at=item.claim_expires_at, ) - self._log_outcome(item, OutboxOutcome.PERMANENT_FAILURE, error=str(exc)) + self._log_outcome(item, OutboxOutcome.PERMANENT_FAILURE) _log.warning( - "ledger delivery_failed (permanent): instance_key=%s correlation_id=%s reason=%s", + "ledger delivery_failed (permanent): instance_key=%s correlation_id=%s", item.instance_key or self._instance_key, - item.correlation_id, exc, + item.correlation_id, ) # dcy-033 / REQ-100: CRITICAL alarm — permanent failure, no retry. if self._alarm_emitter is not None: @@ -346,14 +381,13 @@ class LedgerWriter: error=str(exc), expected_claim_expires_at=item.claim_expires_at, ) - self._log_outcome(item, OutboxOutcome.DEAD_LETTERED, error=str(exc)) + self._log_outcome(item, OutboxOutcome.DEAD_LETTERED) _log.warning( "ledger delivery_failed (dead-letter, attempts=%d): " - "instance_key=%s correlation_id=%s reason=%s", + "instance_key=%s correlation_id=%s", new_attempts, item.instance_key or self._instance_key, item.correlation_id, - exc, ) # dcy-033 / REQ-100: CRITICAL alarm — dead-lettered after max retries. if self._alarm_emitter is not None: @@ -375,7 +409,7 @@ class LedgerWriter: next_retry_at=next_retry_at, expected_claim_expires_at=item.claim_expires_at, ) - self._log_outcome(item, OutboxOutcome.RETRYABLE_FAILURE, error=str(exc)) + self._log_outcome(item, OutboxOutcome.RETRYABLE_FAILURE) return OutboxOutcome.RETRYABLE_FAILURE # dcy-018 / REQ-019/030 (option D): write back portfolio-hub authoritative # cash/quantity to the snapshot store on new+duplicate (OQ-2 b). *_after @@ -386,7 +420,11 @@ class LedgerWriter: # duplicate_completed; the ledger has exactly one entry for this # execution_id either way (REQ-019 AC-1, AC-4). if outcome.result is LedgerWriteResult.DUPLICATE_OK: - self._outbox.mark_outcome(item.correlation_id, OutboxOutcome.DUPLICATE_COMPLETED) + self._outbox.mark_outcome( + item.correlation_id, + OutboxOutcome.DUPLICATE_COMPLETED, + expected_claim_expires_at=item.claim_expires_at, + ) self._resolve_ledger_skip(item.trade) self._log_outcome(item, OutboxOutcome.DUPLICATE_COMPLETED) return OutboxOutcome.DUPLICATE_COMPLETED @@ -403,8 +441,6 @@ class LedgerWriter: self, item: LedgerWorkItem, outcome: OutboxOutcome, - *, - error: str | None = None, ) -> None: self._count(f"outcome:{outcome.value}") msg = "ledger outbox outcome: instance_key=%s correlation_id=%s outcome=%s" @@ -413,9 +449,6 @@ class LedgerWriter: item.correlation_id, outcome.value, ) - if error is not None: - msg += " error=%s" - args = (*args, error) _log.info(msg, *args) def _resolve_ledger_skip(self, trade: LedgerTrade) -> None: @@ -454,7 +487,7 @@ class LedgerWriter: except Exception: # noqa: BLE001 - write-back must not block the ledger path _log.warning( "snapshot cash/position write-back failed: asset_id=%s", - trade.asset_id, exc_info=True, + trade.asset_id, ) @@ -467,7 +500,8 @@ class InMemoryLedgerOutbox: self, *, clock: Optional[Callable[[], datetime]] = None, - instance_key: str = "default", + instance_key: str, + claim_ttl_sec: float = 60.0, ) -> None: import threading @@ -477,7 +511,16 @@ class InMemoryLedgerOutbox: # dcy-015: shared clock lets tests align backoff (next_retry_at) with # list_pending's "now" deterministically. self._clock = clock or (lambda: datetime.now(tz=timezone.utc)) + if not isinstance(instance_key, str) or not instance_key.strip(): + raise ValueError("instance_key must be a non-empty string") + if claim_ttl_sec <= 0: + raise ValueError("claim_ttl_sec must be positive") self._instance_key = instance_key + self._claim_ttl_sec = claim_ttl_sec + + @property + def instance_key(self) -> str: + return self._instance_key def _now(self) -> datetime: return self._clock() @@ -508,8 +551,11 @@ class InMemoryLedgerOutbox: row = self._rows[cid] # dcy-015 / REQ-019: skip rows still in backoff so they don't # occupy the FIFO batch (head-of-line protection, NFR-3). - if row.status is WorkItemStatus.PENDING and ( - row.next_retry_at is None or row.next_retry_at <= now + if ( + row.status is WorkItemStatus.PENDING + and row.instance_key == self._instance_key + and (row.next_retry_at is None or row.next_retry_at <= now) + and (row.claim_expires_at is None or row.claim_expires_at <= now) ): out.append(row) if len(out) >= limit: @@ -522,16 +568,27 @@ class InMemoryLedgerOutbox: *, correlation_id: str | None = None, ) -> list[LedgerWorkItem]: - if correlation_id is None: - return self.list_pending(limit) now = self._now() + lease_until = now + timedelta(seconds=self._claim_ttl_sec) with self._lock: - row = self._rows.get(correlation_id) - if row is None or row.status is not WorkItemStatus.PENDING: - return [] - if row.next_retry_at is not None and row.next_retry_at > now: - return [] - return [row] + claimed: list[LedgerWorkItem] = [] + candidates = [correlation_id] if correlation_id is not None else self._order + for cid in candidates: + row = self._rows.get(cid) + if row is None or row.status is not WorkItemStatus.PENDING: + continue + if row.instance_key != self._instance_key: + continue + if row.next_retry_at is not None and row.next_retry_at > now: + continue + if row.claim_expires_at is not None and row.claim_expires_at > now: + continue + updated = replace(row, claim_expires_at=lease_until, updated_at=now) + self._rows[cid] = updated + claimed.append(updated) + if len(claimed) >= limit: + break + return claimed def pending_cash_delta(self) -> dict[str, float]: with self._lock: @@ -557,6 +614,11 @@ class InMemoryLedgerOutbox: ) -> LedgerWorkItem: with self._lock: row = self._rows[correlation_id] + if expected_claim_expires_at is None: + if row.claim_expires_at is not None: + raise OutboxClaimLostError(correlation_id) + elif row.claim_expires_at != expected_claim_expires_at: + raise OutboxClaimLostError(correlation_id) if outcome is OutboxOutcome.COMPLETED: new_status = WorkItemStatus.COMPLETED elif outcome is OutboxOutcome.CONFLICT_BLOCKED: @@ -578,6 +640,7 @@ class InMemoryLedgerOutbox: next_retry_at if outcome is OutboxOutcome.RETRYABLE_FAILURE else None ), updated_at=self._now(), + claim_expires_at=None, ) self._rows[correlation_id] = updated return updated