8 Commits
Author SHA1 Message Date
Hermes Agent 6017bde744 chore(release): bump version to 0.6.0 2026-09-02 18:24:06 +09:00
genichin 869664aa4a Merge pull request #82 from fourblocks2020/copilot/fix-cancel-sql-error-and-pending-issue
fix(execution): cancel SQL IndeterminateDatatype, KIS child cancel detection, worker exception visibility
2026-09-01 23:21:01 +09:00
copilot-swe-agent[bot]andgenichin f3fbc179b0 fix(kis): collect all parent candidates before child evaluation; boundary case tests
Co-authored-by: genichin <4282227+genichin@users.noreply.github.com>
2026-09-01 13:35:12 +00:00
copilot-swe-agent[bot]andgenichin 584e08eb36 fix(execution): bind parent row to request identity before child evaluation; add parent mismatch and race tests
Co-authored-by: genichin <4282227+genichin@users.noreply.github.com>
2026-09-01 13:21:20 +00:00
copilot-swe-agent[bot]andgenichin 65df10542b fix(execution): KIS child cancel identity binding, sanitized logging, PG cancel SQL tests
Co-authored-by: genichin <4282227+genichin@users.noreply.github.com>
2026-09-01 12:06:45 +00:00
copilot-swe-agent[bot]andgenichin f0ac909958 fix(execution): cancel SQL nullable type error, KIS child cancel detection, worker exception logging
Co-authored-by: genichin <4282227+genichin@users.noreply.github.com>
2026-09-01 03:33:38 +00:00
copilot-swe-agent[bot] 2b412fd786 Initial plan 2026-09-01 03:27:51 +00:00
Hermes Agent 16257e65a6 chore(release): restore Dockerfile and bump version to 0.5.1 2026-08-30 16:42:13 +09:00
10 changed files with 983 additions and 26 deletions
+27
View File
@@ -0,0 +1,27 @@
FROM python:3.12-slim
ARG SOURCE_COMMIT
LABEL org.opencontainers.image.source="https://github.com/fourblocks2020/trex-core" \
org.opencontainers.image.revision="${SOURCE_COMMIT}"
WORKDIR /opt/trex-core
RUN test "${#SOURCE_COMMIT}" -eq 40 \
&& case "${SOURCE_COMMIT}" in \
*[!0-9a-f]*) false ;; \
*) true ;; \
esac \
|| { echo "SOURCE_COMMIT must be a 40-character lowercase commit" >&2; exit 1; }
COPY pyproject.toml uv.lock ./
COPY trex_core/ ./trex_core/
RUN python -m pip install --no-cache-dir "uv==0.11.14" \
&& uv sync --locked --no-dev --no-editable \
&& useradd --create-home --uid 10001 trex
ENV PATH="/opt/trex-core/.venv/bin:${PATH}"
USER 10001:10001
ENTRYPOINT ["trex-core-daemon"]
+1 -1
View File
@@ -1,6 +1,6 @@
[project]
name = "trex-core"
version = "0.5.0"
version = "0.6.0"
description = "Shared core for the trex product family; first domain: slot lifecycle (storage-agnostic pure domain)"
requires-python = ">=3.12"
dependencies = [
+519 -2
View File
@@ -7,7 +7,7 @@ pre-seeded, httpx.get faked) and assert the FillStatus mapping.
from __future__ import annotations
from datetime import datetime, timedelta, timezone
from datetime import UTC, datetime, timedelta
from trex_core.adapters.broker import kis as kis_mod
from trex_core.adapters.broker.kis import KISBroker
@@ -23,7 +23,7 @@ def _broker():
base_url="https://openapivts.koreainvestment.com:29443", # mock endpoint
)
b._token = "tok"
b._token_exp = datetime.now(tz=timezone.utc) + timedelta(hours=1)
b._token_exp = datetime.now(tz=UTC) + timedelta(hours=1)
return b
@@ -52,6 +52,7 @@ def _row(**kw):
"rjct_qty": "0",
"ord_dt": "20260608",
"ord_gno_brno": "06010",
"pdno": "005930",
}
base.update(kw)
return {"rt_cd": "0", "output1": [base]}
@@ -130,3 +131,519 @@ def test_full_fill_unaffected_by_cancel_flag(monkeypatch):
f"06010:{ODNO}", side="sell", symbol="005930", order_date="20260608"
)
assert fs.is_filled and fs.filled_qty == 10 and not fs.is_partial_cancel
# ── Regression: KIS child cancel row (orgn_odno) ─────────────────────────────
def _payload_with_child_cancel(parent_odno: str, child_odno: str, ord_qty: str = "89", symbol: str = "225190"):
"""Simulate KIS returning original row (cncl_yn='') + separate cancel child."""
parent = {
"odno": parent_odno,
"orgn_odno": "",
"ord_qty": ord_qty,
"tot_ccld_qty": "0",
"avg_prvs": "0",
"cncl_yn": "",
"rjct_qty": "0",
"rmn_qty": "0",
"ord_dt": "20260901",
"ord_gno_brno": "06010",
"pdno": symbol,
}
child = {
"odno": child_odno,
"orgn_odno": parent_odno,
"ord_qty": ord_qty,
"tot_ccld_qty": "0",
"avg_prvs": "0",
"cncl_yn": "Y",
"rjct_qty": "0",
"rmn_qty": "0",
"ord_dt": "20260901",
"ord_gno_brno": "06010",
"pdno": symbol,
}
return {"rt_cd": "0", "output1": [parent, child]}
def test_child_cancel_row_orgn_odno_maps_to_cancelled(monkeypatch):
"""KIS child row with orgn_odno=<original> + cncl_yn=Y → full cancel."""
payload = _payload_with_child_cancel(ODNO, "0000123457")
monkeypatch.setattr(kis_mod.httpx, "get", _fake_get(payload))
fs = _broker().poll_fill(
f"06010:{ODNO}", side="buy", symbol="225190", order_date="20260901"
)
assert fs.state == "cancelled", f"expected cancelled, got {fs.state}"
assert fs.is_terminal_reject
def test_correction_child_row_not_misclassified_as_cancel(monkeypatch):
"""Correction child (cncl_yn!='Y') must not be treated as a cancel.
Issue #81 AC: a correction/replacement child means the order is superseded
but we cannot safely determine terminal status without the replacement
identity → fail-closed as 'unknown' (not 'accepted/open_confirmed').
"""
parent = {
"odno": ODNO,
"orgn_odno": "",
"ord_qty": "10",
"tot_ccld_qty": "0",
"avg_prvs": "0",
"cncl_yn": "",
"rjct_qty": "0",
"ord_dt": "20260901",
"ord_gno_brno": "06010",
"pdno": "225190",
}
correction_child = {
"odno": "0000123458",
"orgn_odno": ODNO,
"ord_qty": "10",
"tot_ccld_qty": "0",
"avg_prvs": "0",
"cncl_yn": "N", # correction, not cancel
"rjct_qty": "0",
"ord_dt": "20260901",
"ord_gno_brno": "06010",
"pdno": "225190",
}
monkeypatch.setattr(
kis_mod.httpx, "get", _fake_get({"rt_cd": "0", "output1": [parent, correction_child]})
)
fs = _broker().poll_fill(
f"06010:{ODNO}", side="buy", symbol="225190", order_date="20260901"
)
# Correction child means replacement identity is unresolved → fail-closed
assert fs.state == "unknown", f"expected unknown, got {fs.state}"
raw = fs.raw if isinstance(fs.raw, dict) else {}
assert raw.get("reason") == "correction_child_present_unresolved"
# Must NOT be open_confirmed — that would allow new orders on the same slot
assert not raw.get("order_open_confirmed", False)
def test_partial_fill_with_child_cancel_row(monkeypatch):
"""Partial fill on parent + cancel child → partial_cancel."""
parent = {
"odno": ODNO,
"orgn_odno": "",
"ord_qty": "10",
"tot_ccld_qty": "4",
"avg_prvs": "70000",
"cncl_yn": "",
"rjct_qty": "0",
"ord_dt": "20260901",
"ord_gno_brno": "06010",
"pdno": "225190",
}
child = {
"odno": "0000123459",
"orgn_odno": ODNO,
"ord_qty": "6",
"tot_ccld_qty": "0",
"avg_prvs": "0",
"cncl_yn": "Y",
"rjct_qty": "0",
"ord_dt": "20260901",
"ord_gno_brno": "06010",
"pdno": "225190",
}
monkeypatch.setattr(
kis_mod.httpx, "get", _fake_get({"rt_cd": "0", "output1": [parent, child]})
)
fs = _broker().poll_fill(
f"06010:{ODNO}", side="sell", symbol="225190", order_date="20260901"
)
assert fs.state == "partially_filled"
assert fs.cancelled and fs.is_partial_cancel
assert fs.filled_qty == 4
# ── Regression: identity mismatch / ambiguous child rows ─────────────────────
def test_child_cancel_mismatched_branch_is_ignored(monkeypatch):
"""Cancel child from a different branch (ord_gno_brno) must not affect parent."""
parent = {
"odno": ODNO,
"orgn_odno": "",
"ord_qty": "10",
"tot_ccld_qty": "0",
"avg_prvs": "0",
"cncl_yn": "",
"rjct_qty": "0",
"ord_dt": "20260901",
"ord_gno_brno": "06010",
"pdno": "225190",
}
child_wrong_branch = {
"odno": "0000199999",
"orgn_odno": ODNO,
"ord_qty": "10",
"tot_ccld_qty": "0",
"avg_prvs": "0",
"cncl_yn": "Y",
"rjct_qty": "0",
"ord_dt": "20260901",
"ord_gno_brno": "99999", # different branch
"pdno": "225190",
}
monkeypatch.setattr(
kis_mod.httpx, "get", _fake_get({"rt_cd": "0", "output1": [parent, child_wrong_branch]})
)
fs = _broker().poll_fill(
f"06010:{ODNO}", side="buy", symbol="225190", order_date="20260901"
)
# Child has wrong branch → not a matching cancel → parent stays accepted
assert fs.state == "accepted", f"expected accepted (mismatch branch), got {fs.state}"
def test_child_cancel_mismatched_symbol_is_ignored(monkeypatch):
"""Cancel child with different symbol (pdno) must not affect parent."""
parent = {
"odno": ODNO,
"orgn_odno": "",
"ord_qty": "10",
"tot_ccld_qty": "0",
"avg_prvs": "0",
"cncl_yn": "",
"rjct_qty": "0",
"ord_dt": "20260901",
"ord_gno_brno": "06010",
"pdno": "225190",
}
child_wrong_symbol = {
"odno": "0000199998",
"orgn_odno": ODNO,
"ord_qty": "10",
"tot_ccld_qty": "0",
"avg_prvs": "0",
"cncl_yn": "Y",
"rjct_qty": "0",
"ord_dt": "20260901",
"ord_gno_brno": "06010",
"pdno": "000660", # different symbol
}
monkeypatch.setattr(
kis_mod.httpx, "get", _fake_get({"rt_cd": "0", "output1": [parent, child_wrong_symbol]})
)
fs = _broker().poll_fill(
f"06010:{ODNO}", side="buy", symbol="225190", order_date="20260901"
)
assert fs.state == "accepted", f"expected accepted (mismatch symbol), got {fs.state}"
def test_child_cancel_mismatched_date_is_ignored(monkeypatch):
"""Cancel child with different ord_dt must not affect parent."""
parent = {
"odno": ODNO,
"orgn_odno": "",
"ord_qty": "10",
"tot_ccld_qty": "0",
"avg_prvs": "0",
"cncl_yn": "",
"rjct_qty": "0",
"ord_dt": "20260901",
"ord_gno_brno": "06010",
"pdno": "225190",
}
child_wrong_date = {
"odno": "0000199997",
"orgn_odno": ODNO,
"ord_qty": "10",
"tot_ccld_qty": "0",
"avg_prvs": "0",
"cncl_yn": "Y",
"rjct_qty": "0",
"ord_dt": "20260831", # different date
"ord_gno_brno": "06010",
"pdno": "225190",
}
monkeypatch.setattr(
kis_mod.httpx, "get", _fake_get({"rt_cd": "0", "output1": [parent, child_wrong_date]})
)
fs = _broker().poll_fill(
f"06010:{ODNO}", side="buy", symbol="225190", order_date="20260901"
)
assert fs.state == "accepted", f"expected accepted (mismatch date), got {fs.state}"
def test_ambiguous_multiple_child_cancel_rows_return_unknown(monkeypatch):
"""Two matching cancel children → ambiguous identity → fail-closed as unknown."""
parent = {
"odno": ODNO,
"orgn_odno": "",
"ord_qty": "10",
"tot_ccld_qty": "0",
"avg_prvs": "0",
"cncl_yn": "",
"rjct_qty": "0",
"ord_dt": "20260901",
"ord_gno_brno": "06010",
"pdno": "225190",
}
child1 = {**parent, "odno": "0000123460", "orgn_odno": ODNO, "cncl_yn": "Y", "ord_qty": "10"}
child2 = {**parent, "odno": "0000123461", "orgn_odno": ODNO, "cncl_yn": "Y", "ord_qty": "10"}
monkeypatch.setattr(
kis_mod.httpx, "get", _fake_get({"rt_cd": "0", "output1": [parent, child1, child2]})
)
fs = _broker().poll_fill(
f"06010:{ODNO}", side="buy", symbol="225190", order_date="20260901"
)
assert fs.state == "unknown", f"expected unknown (ambiguous children), got {fs.state}"
raw = fs.raw if isinstance(fs.raw, dict) else {}
assert raw.get("reason") == "child_cancel_ambiguous"
# ── Regression: parent row identity mismatch with request ────────────────────
def test_parent_row_wrong_branch_returns_unknown(monkeypatch):
"""Parent row with wrong ord_gno_brno (branch) relative to broker_order_id → unknown."""
parent = {
"odno": ODNO,
"orgn_odno": "",
"ord_qty": "10",
"tot_ccld_qty": "0",
"avg_prvs": "0",
"cncl_yn": "",
"rjct_qty": "0",
"ord_dt": "20260901",
"ord_gno_brno": "99999", # wrong branch — request has 06010
"pdno": "225190",
}
monkeypatch.setattr(
kis_mod.httpx, "get", _fake_get({"rt_cd": "0", "output1": [parent]})
)
# broker_order_id encodes branch 06010, but row has 99999
fs = _broker().poll_fill(
f"06010:{ODNO}", side="buy", symbol="225190", order_date="20260901"
)
assert fs.state == "unknown", f"expected unknown (wrong parent branch), got {fs.state}"
raw = fs.raw if isinstance(fs.raw, dict) else {}
assert "mismatch" in raw.get("reason", "")
def test_parent_row_wrong_date_returns_unknown(monkeypatch):
"""Parent row with wrong ord_dt relative to order_date arg → unknown."""
parent = {
"odno": ODNO,
"orgn_odno": "",
"ord_qty": "10",
"tot_ccld_qty": "0",
"avg_prvs": "0",
"cncl_yn": "",
"rjct_qty": "0",
"ord_dt": "20260831", # wrong date — request has 20260901
"ord_gno_brno": "06010",
"pdno": "225190",
}
monkeypatch.setattr(
kis_mod.httpx, "get", _fake_get({"rt_cd": "0", "output1": [parent]})
)
fs = _broker().poll_fill(
f"06010:{ODNO}", side="buy", symbol="225190", order_date="20260901"
)
assert fs.state == "unknown", f"expected unknown (wrong parent date), got {fs.state}"
raw = fs.raw if isinstance(fs.raw, dict) else {}
assert "mismatch" in raw.get("reason", "")
def test_parent_row_wrong_symbol_returns_unknown(monkeypatch):
"""Parent row with wrong pdno (symbol) relative to symbol arg → unknown."""
parent = {
"odno": ODNO,
"orgn_odno": "",
"ord_qty": "10",
"tot_ccld_qty": "0",
"avg_prvs": "0",
"cncl_yn": "",
"rjct_qty": "0",
"ord_dt": "20260901",
"ord_gno_brno": "06010",
"pdno": "000660", # wrong symbol — request has 225190
}
monkeypatch.setattr(
kis_mod.httpx, "get", _fake_get({"rt_cd": "0", "output1": [parent]})
)
fs = _broker().poll_fill(
f"06010:{ODNO}", side="buy", symbol="225190", order_date="20260901"
)
assert fs.state == "unknown", f"expected unknown (wrong parent symbol), got {fs.state}"
raw = fs.raw if isinstance(fs.raw, dict) else {}
assert "mismatch" in raw.get("reason", "")
def test_correction_child_wrong_identity_is_not_treated_as_correction(monkeypatch):
"""Correction child with wrong branch/date/symbol must not trigger correction_child_present_unresolved."""
parent = {
"odno": ODNO,
"orgn_odno": "",
"ord_qty": "10",
"tot_ccld_qty": "0",
"avg_prvs": "0",
"cncl_yn": "",
"rjct_qty": "0",
"ord_dt": "20260901",
"ord_gno_brno": "06010",
"pdno": "225190",
}
unrelated_correction = {
"odno": "0000199990",
"orgn_odno": ODNO,
"ord_qty": "10",
"tot_ccld_qty": "0",
"avg_prvs": "0",
"cncl_yn": "N",
"rjct_qty": "0",
"ord_dt": "20260831", # different date → not related to our request
"ord_gno_brno": "99999", # different branch
"pdno": "000660", # different symbol
}
monkeypatch.setattr(
kis_mod.httpx,
"get",
_fake_get({"rt_cd": "0", "output1": [parent, unrelated_correction]}),
)
fs = _broker().poll_fill(
f"06010:{ODNO}", side="buy", symbol="225190", order_date="20260901"
)
# Unrelated correction must not cause correction_child_present_unresolved
assert fs.state == "accepted", f"expected accepted (unrelated correction), got {fs.state}"
raw = fs.raw if isinstance(fs.raw, dict) else {}
assert raw.get("reason") != "correction_child_present_unresolved"
# ── Regression: parent identity boundary cases (missing / wrong-first / ambiguous) ─
def test_parent_missing_identity_fields_returns_unknown(monkeypatch):
"""Parent row with missing pdno and ord_dt → treated as identity mismatch (fail-closed)."""
parent_no_identity = {
"odno": ODNO,
"orgn_odno": "",
"ord_qty": "10",
"tot_ccld_qty": "0",
"avg_prvs": "0",
"cncl_yn": "Y", # would be cancelled if accepted
"rjct_qty": "0",
# ord_dt, ord_gno_brno, pdno intentionally absent
}
monkeypatch.setattr(
kis_mod.httpx, "get", _fake_get({"rt_cd": "0", "output1": [parent_no_identity]})
)
fs = _broker().poll_fill(
f"06010:{ODNO}", side="buy", symbol="225190", order_date="20260901"
)
# Missing identity → fail-closed, not terminal
assert fs.state == "unknown", f"expected unknown (missing identity), got {fs.state}"
assert not fs.is_terminal_reject
def test_child_cancel_missing_identity_fields_not_accepted_as_cancel(monkeypatch):
"""Cancel child with missing identity fields must NOT be accepted as matching child."""
parent = {
"odno": ODNO,
"orgn_odno": "",
"ord_qty": "10",
"tot_ccld_qty": "0",
"avg_prvs": "0",
"cncl_yn": "",
"rjct_qty": "0",
"ord_dt": "20260901",
"ord_gno_brno": "06010",
"pdno": "225190",
}
child_no_identity = {
"odno": "0000123461",
"orgn_odno": ODNO,
"ord_qty": "10",
"tot_ccld_qty": "0",
"avg_prvs": "0",
"cncl_yn": "Y",
"rjct_qty": "0",
# ord_dt, ord_gno_brno, pdno intentionally absent
}
monkeypatch.setattr(
kis_mod.httpx,
"get",
_fake_get({"rt_cd": "0", "output1": [parent, child_no_identity]}),
)
fs = _broker().poll_fill(
f"06010:{ODNO}", side="buy", symbol="225190", order_date="20260901"
)
# Child has missing identity → not a matching cancel; parent has no fill → accepted
assert fs.state == "accepted", f"expected accepted (child missing identity), got {fs.state}"
def test_wrong_parent_first_exact_parent_later_finds_cancel(monkeypatch):
"""When the wrong-branch parent comes first, the exact parent+cancel child later must win."""
wrong_parent = {
"odno": ODNO,
"orgn_odno": "",
"ord_qty": "10",
"tot_ccld_qty": "0",
"avg_prvs": "0",
"cncl_yn": "",
"rjct_qty": "0",
"ord_dt": "20260901",
"ord_gno_brno": "99999", # wrong branch — comes first in list
"pdno": "225190",
}
exact_parent = {
"odno": ODNO,
"orgn_odno": "",
"ord_qty": "10",
"tot_ccld_qty": "0",
"avg_prvs": "0",
"cncl_yn": "",
"rjct_qty": "0",
"ord_dt": "20260901",
"ord_gno_brno": "06010", # correct branch — comes second
"pdno": "225190",
}
child = {
"odno": "0000123462",
"orgn_odno": ODNO,
"ord_qty": "10",
"tot_ccld_qty": "0",
"avg_prvs": "0",
"cncl_yn": "Y",
"rjct_qty": "0",
"ord_dt": "20260901",
"ord_gno_brno": "06010",
"pdno": "225190",
}
monkeypatch.setattr(
kis_mod.httpx,
"get",
_fake_get({"rt_cd": "0", "output1": [wrong_parent, exact_parent, child]}),
)
fs = _broker().poll_fill(
f"06010:{ODNO}", side="buy", symbol="225190", order_date="20260901"
)
# Must find the exact parent + cancel child even though wrong parent comes first
assert fs.state == "cancelled", f"expected cancelled (exact parent later), got {fs.state}"
def test_ambiguous_exact_parents_returns_unknown(monkeypatch):
"""Two rows with identical exact identity → ambiguous parent → unknown."""
parent1 = {
"odno": ODNO,
"orgn_odno": "",
"ord_qty": "10",
"tot_ccld_qty": "0",
"avg_prvs": "0",
"cncl_yn": "",
"rjct_qty": "0",
"ord_dt": "20260901",
"ord_gno_brno": "06010",
"pdno": "225190",
}
parent2 = {**parent1} # exact duplicate
monkeypatch.setattr(
kis_mod.httpx, "get", _fake_get({"rt_cd": "0", "output1": [parent1, parent2]})
)
fs = _broker().poll_fill(
f"06010:{ODNO}", side="buy", symbol="225190", order_date="20260901"
)
assert fs.state == "unknown", f"expected unknown (ambiguous parents), got {fs.state}"
raw = fs.raw if isinstance(fs.raw, dict) else {}
assert raw.get("reason") == "parent_identity_ambiguous"
@@ -2,6 +2,8 @@
Skipped without TREX_POSTGRESQL_TEST_DSN."""
from __future__ import annotations
from datetime import UTC, datetime, timedelta
from trex_core.adapters.persistence.in_memory_intent_store import InMemoryIntentStore # noqa: F401
from trex_core.adapters.persistence.postgresql import (
PostgreSQLIntentStore,
@@ -244,3 +246,80 @@ def test_strategy_state_write_cannot_follow_close(pg_clean):
result = store.set(slot.slot_id, "instance", expected_version=1, data="after", slot_active=True)
assert not result.ok and result.reason == "slot_inactive"
assert store.get_for_slots([slot.slot_id])[slot.slot_id]["instance"].data == "before"
# ── Regression: reserve_cancel_attempt() SQL paths (issue #81 Fix A) ─────────
# These tests exercise the real PostgreSQL code path that previously failed with
# IndeterminateDatatype when retry_before=None was bound to %s IS NOT NULL.
def test_reserve_cancel_first_attempt_retry_before_none_pg(pg_clean):
"""First reservation with retry_before=None must succeed exactly once."""
repo, _, intents = _wire(pg_clean)
repo.reconcile_universe(INST, {"PF-1": "005930"})
d = intents.submit_buy(BuyIntent(intent_id="pg-can-first", qty=1, portfolio_id="PF-1"))
repo.mark_dispatched(d.slot_id, "ord-first")
# First reservation: retry_before=None — must not raise IndeterminateDatatype
assert repo.reserve_cancel_attempt(d.slot_id, "ord-first") is True
slot = repo.fetch_slot(d.slot_id)
assert slot.cancel_state == "unknown"
assert slot.cancel_attempts == 1
assert slot.cancel_requested_at is not None
# Duplicate CAS must be rejected (cancel_state is no longer NULL)
assert repo.reserve_cancel_attempt(d.slot_id, "ord-first") is False
assert repo.fetch_slot(d.slot_id).cancel_attempts == 1 # not incremented
def test_reserve_cancel_retry_backoff_gated_pg(pg_clean):
"""Retry path with retry_before is accepted when backoff window passes."""
import psycopg
repo, _, intents = _wire(pg_clean)
repo.reconcile_universe(INST, {"PF-1": "005930"})
d = intents.submit_buy(BuyIntent(intent_id="pg-can-retry", qty=1, portfolio_id="PF-1"))
repo.mark_dispatched(d.slot_id, "ord-retry")
# Simulate a previous cancel attempt that left state=rejected a while ago
past = datetime.now(tz=UTC) - timedelta(seconds=60)
with psycopg.connect(pg_clean, autocommit=False) as conn:
with conn.cursor() as cur:
cur.execute(
"UPDATE daily_slot SET cancel_state='rejected', cancel_requested_at=%s, "
"cancel_attempts=1 WHERE slot_id=%s",
(past, d.slot_id),
)
conn.commit()
# retry_before = now means backoff window has elapsed
retry_before = datetime.now(tz=UTC)
assert repo.reserve_cancel_attempt(d.slot_id, "ord-retry", retry_before=retry_before) is True
slot = repo.fetch_slot(d.slot_id)
assert slot.cancel_state == "unknown"
assert slot.cancel_attempts == 2
def test_reserve_cancel_retry_max_attempts_blocked_pg(pg_clean):
"""Retry is rejected when cancel_attempts >= 4."""
import psycopg
repo, _, intents = _wire(pg_clean)
repo.reconcile_universe(INST, {"PF-1": "005930"})
d = intents.submit_buy(BuyIntent(intent_id="pg-can-max", qty=1, portfolio_id="PF-1"))
repo.mark_dispatched(d.slot_id, "ord-max")
past = datetime.now(tz=UTC) - timedelta(seconds=120)
with psycopg.connect(pg_clean, autocommit=False) as conn:
with conn.cursor() as cur:
cur.execute(
"UPDATE daily_slot SET cancel_state='rejected', cancel_requested_at=%s, "
"cancel_attempts=4 WHERE slot_id=%s",
(past, d.slot_id),
)
conn.commit()
retry_before = datetime.now(tz=UTC)
assert repo.reserve_cancel_attempt(d.slot_id, "ord-max", retry_before=retry_before) is False
assert repo.fetch_slot(d.slot_id).cancel_attempts == 4 # unchanged
+112
View File
@@ -179,3 +179,115 @@ def test_operator_cancel_is_sent_once_across_repeat_and_restart():
assert restarted.cancel_pending_slot(sid) == "cancel_already_recorded"
assert broker.cancel_calls == 1
assert repo.fetch_slot(sid).cancel_state == CancelState.REQUESTED.value
# ── Regression: first-cancel reservation (retry_before=None) ─────────────────
def test_first_cancel_reservation_with_no_retry_before_succeeds():
"""First cancel reservation with retry_before=None must reserve exactly once (fix for
PostgreSQL IndeterminateDatatype; the in-memory repo mirrors the corrected SQL path)."""
broker = ProgrammableBroker()
repo, svc, intents, execution, _, _ = _wire(broker)
sid = _buy_to_holding(intents, execution)
intents.submit_sell(SellIntent(intent_id="s1", slot_id=sid))
broker.responder = lambda side: FillStatus(state="accepted")
execution.run_once() # dispatch
# First operator cancel — retry_before=None path
result = execution.cancel_pending_slot(sid)
assert result == "ok", f"expected ok, got {result}"
assert broker.cancel_calls == 1
# Second call must be idempotent (cancel_state already set)
result2 = execution.cancel_pending_slot(sid)
assert result2 == "cancel_already_recorded"
assert broker.cancel_calls == 1 # no second broker call
def test_timeout_cancel_first_attempt_with_retry_before_none():
"""Timeout cancel's first attempt passes retry_before=None; must call broker once."""
broker = ProgrammableBroker()
repo, svc, intents, execution, _, _ = _wire(broker)
sid = _buy_to_holding(intents, execution)
intents.submit_sell(SellIntent(intent_id="s1", slot_id=sid))
broker.responder = lambda side: FillStatus(
state="accepted",
raw={"order_open_confirmed": True},
)
execution.run_once() # dispatch
# Simulate timeout: set order_submitted_at well in the past
s = repo.fetch_slot(sid)
repo._slots[sid] = replace(
s,
order_submitted_at=datetime.now(tz=timezone.utc) - timedelta(seconds=120),
order_date="20260901",
timeout_sec=30,
)
execution.run_once() # should trigger timeout cancel
assert broker.cancel_calls == 1
# ── Regression: concurrent timeout/operator cancel race — broker call count 1 ─
def test_timeout_operator_race_broker_called_exactly_once():
"""Timeout cancel loop and operator cancel_pending_slot race to the same first
reservation. The repository CAS guarantees exactly one winner; broker must
receive cancel_order exactly once regardless of scheduling order.
Uses a threading barrier so both paths enter reserve_cancel_attempt
simultaneously, making the race deterministic.
"""
import threading
broker = ProgrammableBroker()
repo, _, intents, execution, _, _ = _wire(broker)
sid = _buy_to_holding(intents, execution)
intents.submit_sell(SellIntent(intent_id="s1", slot_id=sid))
broker.responder = lambda side: FillStatus(
state="accepted",
raw={"order_open_confirmed": True},
)
execution.run_once() # dispatch sell
# Backdate so timeout_cancel fires in the next run_once()
s = repo.fetch_slot(sid)
repo._slots[sid] = replace(
s,
order_submitted_at=datetime.now(tz=timezone.utc) - timedelta(seconds=120),
order_date="20260901",
timeout_sec=30,
)
barrier = threading.Barrier(2)
original_reserve = repo.reserve_cancel_attempt
def _barrier_reserve(slot_id, broker_order_id, *, retry_before=None):
barrier.wait(timeout=5)
return original_reserve(slot_id, broker_order_id, retry_before=retry_before)
repo.reserve_cancel_attempt = _barrier_reserve
errors = []
def _operator():
try:
execution.cancel_pending_slot(sid)
except Exception as exc: # noqa: BLE001
errors.append(exc)
t = threading.Thread(target=_operator)
t.start()
# Execution loop's timeout cancel is the second concurrent caller.
try:
execution.run_once()
except Exception as exc: # noqa: BLE001
errors.append(exc)
t.join(timeout=5)
assert not errors, f"thread errors: {errors}"
# CAS ensures exactly one winner — broker cancel must be called once.
assert broker.cancel_calls == 1, (
f"expected exactly 1 broker cancel call, got {broker.cancel_calls}"
)
@@ -0,0 +1,70 @@
"""Regression: execution loop exceptions must be logged without leaking secrets.
dcy-031 / issue #81 (Fix C):
- Exceptions from execution.run_once() were silently ignored via bare `continue`.
- Sanitized logging requirement: only type(exc).__name__ is emitted; the
exception message, traceback, and exc_info must NOT appear in the log record
so adapter exceptions containing credentials/DSN/raw payload are never exposed.
- Worker must continue after the error (loop survives).
"""
from __future__ import annotations
import logging
import threading
_SENTINEL = "SECRET-DSN-CREDENTIAL-RAWPAYLOAD-DO-NOT-LOG"
def test_execution_loop_logs_exception_without_leaking_secrets(caplog):
"""Exception type is logged; secret sentinel in exc message is NOT logged."""
import trex_core.runtime.daemon as daemon_mod
call_count = 0
stop_event = threading.Event()
class _FakeExecution:
def run_once(self):
nonlocal call_count
call_count += 1
if call_count == 1:
raise RuntimeError(f"dsn=postgresql://user:{_SENTINEL}@host/db")
# Stop after second successful tick
stop_event.set()
class _FakePublisher:
def keepalive_tick(self):
pass
class _FakeConfig:
execution_interval_sec = 0.001
daemon = object.__new__(daemon_mod.Daemon)
daemon.stop = stop_event
daemon.config = _FakeConfig()
daemon.event_publisher = _FakePublisher()
daemon.execution = _FakeExecution()
with caplog.at_level(logging.ERROR, logger="trex_core.runtime.daemon"):
t = threading.Thread(target=daemon._execution_loop, daemon=True)
t.start()
t.join(timeout=2.0)
assert not t.is_alive(), "execution loop did not exit cleanly"
error_records = [r for r in caplog.records if "execution loop error" in r.message]
assert error_records, (
f"expected 'execution loop error' log record, got: {[r.message for r in caplog.records]}"
)
# Secret sentinel must NOT appear in any log record (message or exc_info output)
for rec in caplog.records:
assert _SENTINEL not in rec.getMessage(), (
f"secret sentinel leaked into log: {rec.getMessage()}"
)
# exc_info must not be attached
assert rec.exc_info is None or rec.exc_info == (None, None, None), (
"exc_info must not be set on execution loop error record"
)
# The loop continued: second call_count tick was reached
assert call_count >= 2, "loop did not continue after exception"
+137 -8
View File
@@ -413,15 +413,56 @@ class KISBroker:
self._fill_poll_not_before[broker_order_id] = monotonic() + _FILL_POLL_MIN_INTERVAL_SECONDS
rows = payload.get("output1") or []
normalized_odno = odno.lstrip("0") or "0"
row = next(
(
r
for r in rows
if (str(r.get("odno") or "").strip().lstrip("0") or "0") == normalized_odno
),
None,
# Canonical request identity from the caller — these are authoritative
# and must not be overridden by whatever the response row contains.
request_brno = broker_order_id.split(":")[0] if ":" in broker_order_id else ""
request_date = inquiry_date # == order_date
request_symbol = symbol
def _row_odno_normalized(r: dict) -> str:
return str(r.get("odno") or "").strip().lstrip("0") or "0"
def _row_matches_request_identity(r: dict) -> bool:
"""True when a row's identity fields are present and agree with the
authoritative request identity. An absent field in the row is
treated as a mismatch (fail-closed), not as a wildcard."""
row_brno = str(r.get("ord_gno_brno") or "").strip()
row_dt = str(r.get("ord_dt") or "").strip()
row_pdno = str(r.get("pdno") or "").strip()
# brno: required only when request carries one; if request has no
# brno (legacy odno-only format) skip the check to preserve
# backwards compatibility.
if request_brno and (not row_brno or row_brno != request_brno):
return False
# date and symbol: always required — these never legitimately vary
# for the same order on the same inquiry date.
if not row_dt or row_dt != request_date:
return False
return bool(row_pdno) and row_pdno == request_symbol
# Collect ALL rows whose odno matches. We must then require exactly
# one that also passes the full identity check. Using next() here
# would accept the first odno-match regardless of identity and stop
# the search, missing authoritative rows that come later and ignoring
# the ambiguous-parent edge case.
odno_matches = [
r for r in rows if _row_odno_normalized(r) == normalized_odno
]
exact_parent_matches = [r for r in odno_matches if _row_matches_request_identity(r)]
if len(exact_parent_matches) == 0:
# No row with the exact request identity. If there are odno
# matches they all failed identity validation → unknown (not grace).
if odno_matches:
return FillStatus(
state="unknown",
raw={
"reason": "parent_identity_mismatch",
"order_visible": True,
"inquiry_date": inquiry_date,
},
)
if row is None:
# Truly invisible — apply the submission visibility grace window.
visible_grace = (
submitted_at is None
or (self._clock().astimezone(UTC) - submitted_at.astimezone(UTC))
@@ -440,6 +481,94 @@ class KISBroker:
"inquiry_date": inquiry_date,
},
)
if len(exact_parent_matches) > 1:
# More than one row claims the same exact identity — ambiguous.
return FillStatus(
state="unknown",
raw={
"reason": "parent_identity_ambiguous",
"order_visible": True,
"inquiry_date": inquiry_date,
},
)
row = exact_parent_matches[0]
# dcy-013 ext: KIS sometimes records an external cancel as a separate
# child row with orgn_odno=<original> and cncl_yn="Y" rather than
# setting cncl_yn on the original row. Scan sibling rows to detect
# this case.
#
# Safety requirements:
# - Child must share the AUTHORITATIVE request identity (branch, date,
# symbol from the caller). All identity fields must be present and
# equal — absent fields are NOT treated as wildcards (fail-closed).
# - Ambiguous (> 1 matching cancel) → fail-closed "unknown".
# - Correction (정정) children (cncl_yn != "Y") that match the same
# request identity are also fail-closed → "unknown".
# - Unrelated rows whose identity fields differ from the request are
# excluded from both candidate lists.
def _child_matches_request(r: dict) -> bool:
"""True when a child row's identity fields are all present and
equal to the authoritative request identity. Missing = mismatch."""
child_brno = str(r.get("ord_gno_brno") or "").strip()
child_dt = str(r.get("ord_dt") or "").strip()
child_pdno = str(r.get("pdno") or "").strip()
if request_brno and (not child_brno or child_brno != request_brno):
return False
if not child_dt or child_dt != request_date:
return False
return bool(child_pdno) and child_pdno == request_symbol
child_cancel_candidates = [
r
for r in rows
if (str(r.get("orgn_odno") or "").strip().lstrip("0") or "0") == normalized_odno
and str(r.get("cncl_yn") or "").strip().upper() == "Y"
and _child_matches_request(r)
]
# Correction children: same orgn_odno + matching identity but cncl_yn != "Y".
correction_candidates = [
r
for r in rows
if (str(r.get("orgn_odno") or "").strip().lstrip("0") or "0") == normalized_odno
and str(r.get("cncl_yn") or "").strip().upper() != "Y"
and _child_matches_request(r)
]
if len(child_cancel_candidates) > 1:
# More than one matching cancel child — identity is ambiguous.
return FillStatus(
state="unknown",
raw={
"reason": "child_cancel_ambiguous",
"order_visible": True,
"inquiry_date": inquiry_date,
},
)
if correction_candidates:
# A correction/replacement child is present; the original order is
# superseded but we cannot safely infer terminal status without
# explicit broker confirmation of the replacement identity.
return FillStatus(
state="unknown",
raw={
"reason": "correction_child_present_unresolved",
"order_visible": True,
"inquiry_date": inquiry_date,
},
)
if child_cancel_candidates and str(row.get("cncl_yn") or "").strip().upper() != "Y":
child_cancel_row = child_cancel_candidates[0]
# Inject the cancel signal from the child row into the parent row so
# _fill_status_from_row can treat it as cancelled, while keeping
# the original row's fill quantities authoritative.
row = {**row, "cncl_yn": "Y", "_child_cancel_odno": str(child_cancel_row.get("odno") or "")}
status = self._fill_status_from_row(
row, side=side, today=inquiry_date, fallback_odno=odno
)
+22 -5
View File
@@ -385,19 +385,36 @@ class PostgreSQLSlotRepository:
*,
retry_before: Optional[datetime] = None,
) -> bool:
"""Atomically reserve first cancel or an authoritative backoff-gated retry."""
"""Atomically reserve first cancel or an authoritative backoff-gated retry.
Two separate SQL paths avoid nullable-placeholder type-inference errors
(PostgreSQL IndeterminateDatatype when binding None to %s IS NOT NULL).
"""
now = datetime.now(tz=timezone.utc)
with self._psycopg.connect(self._dsn, autocommit=False) as conn:
with conn.cursor() as cur:
if retry_before is None:
# First reservation: only match when no cancel has been
# attempted yet (cancel_state IS NULL).
cur.execute(
"UPDATE daily_slot SET cancel_state='unknown', cancel_requested_at=%s, "
"cancel_attempts=cancel_attempts+1, updated_at=%s "
"WHERE slot_id=%s AND broker_order_id=%s "
"AND status IN ('pending_buy','pending_sell') "
"AND (cancel_state IS NULL OR "
"(%s IS NOT NULL AND cancel_state IN ('rejected','unknown') "
"AND cancel_attempts < 4 AND cancel_requested_at <= %s))",
(now, now, slot_id, broker_order_id, retry_before, retry_before),
"AND cancel_state IS NULL",
(now, now, slot_id, broker_order_id),
)
else:
# Retry: backoff-gated, only match retryable states.
cur.execute(
"UPDATE daily_slot SET cancel_state='unknown', cancel_requested_at=%s, "
"cancel_attempts=cancel_attempts+1, updated_at=%s "
"WHERE slot_id=%s AND broker_order_id=%s "
"AND status IN ('pending_buy','pending_sell') "
"AND cancel_state IN ('rejected','unknown') "
"AND cancel_attempts < 4 "
"AND cancel_requested_at <= %s",
(now, now, slot_id, broker_order_id, retry_before),
)
ok = cur.rowcount == 1
conn.commit()
+8 -2
View File
@@ -408,8 +408,14 @@ class Daemon:
self.event_publisher.keepalive_tick()
try:
self.execution.run_once()
except Exception: # noqa: BLE001 - loop must survive transient errors
continue
except Exception as exc: # noqa: BLE001 - loop must survive transient errors
# Sanitized: emit only the exception type, not the message or
# traceback, so credentials / DSN / raw payloads in adapter
# exceptions are never written to the log stream.
_log.error(
"execution loop error — worker continues: exc_type=%s",
type(exc).__name__,
)
def _ledger_loop(self) -> None:
while not self.stop.wait(self.config.ledger_interval_sec):
Generated
+1 -1
View File
@@ -289,7 +289,7 @@ wheels = [
[[package]]
name = "trex-core"
version = "0.5.0"
version = "0.6.0"
source = { editable = "." }
dependencies = [
{ name = "httpx" },