feat(cron): add run history tracking for cron jobs
Record run_at_ms, status, duration_ms and error for each execution, keeping the last 20 entries per job in jobs.json. Adds CronRunRecord dataclass, get_job() lookup, and four regression tests covering success, error, trimming and persistence. Closes #1837 Made-with: Cursor
This commit is contained in:
@@ -10,7 +10,7 @@ from typing import Any, Callable, Coroutine
|
|||||||
|
|
||||||
from loguru import logger
|
from loguru import logger
|
||||||
|
|
||||||
from nanobot.cron.types import CronJob, CronJobState, CronPayload, CronSchedule, CronStore
|
from nanobot.cron.types import CronJob, CronJobState, CronPayload, CronRunRecord, CronSchedule, CronStore
|
||||||
|
|
||||||
|
|
||||||
def _now_ms() -> int:
|
def _now_ms() -> int:
|
||||||
@@ -63,10 +63,12 @@ def _validate_schedule_for_add(schedule: CronSchedule) -> None:
|
|||||||
class CronService:
|
class CronService:
|
||||||
"""Service for managing and executing scheduled jobs."""
|
"""Service for managing and executing scheduled jobs."""
|
||||||
|
|
||||||
|
_MAX_RUN_HISTORY = 20
|
||||||
|
|
||||||
def __init__(
|
def __init__(
|
||||||
self,
|
self,
|
||||||
store_path: Path,
|
store_path: Path,
|
||||||
on_job: Callable[[CronJob], Coroutine[Any, Any, str | None]] | None = None
|
on_job: Callable[[CronJob], Coroutine[Any, Any, str | None]] | None = None,
|
||||||
):
|
):
|
||||||
self.store_path = store_path
|
self.store_path = store_path
|
||||||
self.on_job = on_job
|
self.on_job = on_job
|
||||||
@@ -113,6 +115,15 @@ class CronService:
|
|||||||
last_run_at_ms=j.get("state", {}).get("lastRunAtMs"),
|
last_run_at_ms=j.get("state", {}).get("lastRunAtMs"),
|
||||||
last_status=j.get("state", {}).get("lastStatus"),
|
last_status=j.get("state", {}).get("lastStatus"),
|
||||||
last_error=j.get("state", {}).get("lastError"),
|
last_error=j.get("state", {}).get("lastError"),
|
||||||
|
run_history=[
|
||||||
|
CronRunRecord(
|
||||||
|
run_at_ms=r["runAtMs"],
|
||||||
|
status=r["status"],
|
||||||
|
duration_ms=r.get("durationMs", 0),
|
||||||
|
error=r.get("error"),
|
||||||
|
)
|
||||||
|
for r in j.get("state", {}).get("runHistory", [])
|
||||||
|
],
|
||||||
),
|
),
|
||||||
created_at_ms=j.get("createdAtMs", 0),
|
created_at_ms=j.get("createdAtMs", 0),
|
||||||
updated_at_ms=j.get("updatedAtMs", 0),
|
updated_at_ms=j.get("updatedAtMs", 0),
|
||||||
@@ -160,6 +171,15 @@ class CronService:
|
|||||||
"lastRunAtMs": j.state.last_run_at_ms,
|
"lastRunAtMs": j.state.last_run_at_ms,
|
||||||
"lastStatus": j.state.last_status,
|
"lastStatus": j.state.last_status,
|
||||||
"lastError": j.state.last_error,
|
"lastError": j.state.last_error,
|
||||||
|
"runHistory": [
|
||||||
|
{
|
||||||
|
"runAtMs": r.run_at_ms,
|
||||||
|
"status": r.status,
|
||||||
|
"durationMs": r.duration_ms,
|
||||||
|
"error": r.error,
|
||||||
|
}
|
||||||
|
for r in j.state.run_history
|
||||||
|
],
|
||||||
},
|
},
|
||||||
"createdAtMs": j.created_at_ms,
|
"createdAtMs": j.created_at_ms,
|
||||||
"updatedAtMs": j.updated_at_ms,
|
"updatedAtMs": j.updated_at_ms,
|
||||||
@@ -248,9 +268,8 @@ class CronService:
|
|||||||
logger.info("Cron: executing job '{}' ({})", job.name, job.id)
|
logger.info("Cron: executing job '{}' ({})", job.name, job.id)
|
||||||
|
|
||||||
try:
|
try:
|
||||||
response = None
|
|
||||||
if self.on_job:
|
if self.on_job:
|
||||||
response = await self.on_job(job)
|
await self.on_job(job)
|
||||||
|
|
||||||
job.state.last_status = "ok"
|
job.state.last_status = "ok"
|
||||||
job.state.last_error = None
|
job.state.last_error = None
|
||||||
@@ -261,8 +280,17 @@ class CronService:
|
|||||||
job.state.last_error = str(e)
|
job.state.last_error = str(e)
|
||||||
logger.error("Cron: job '{}' failed: {}", job.name, e)
|
logger.error("Cron: job '{}' failed: {}", job.name, e)
|
||||||
|
|
||||||
|
end_ms = _now_ms()
|
||||||
job.state.last_run_at_ms = start_ms
|
job.state.last_run_at_ms = start_ms
|
||||||
job.updated_at_ms = _now_ms()
|
job.updated_at_ms = end_ms
|
||||||
|
|
||||||
|
job.state.run_history.append(CronRunRecord(
|
||||||
|
run_at_ms=start_ms,
|
||||||
|
status=job.state.last_status,
|
||||||
|
duration_ms=end_ms - start_ms,
|
||||||
|
error=job.state.last_error,
|
||||||
|
))
|
||||||
|
job.state.run_history = job.state.run_history[-self._MAX_RUN_HISTORY:]
|
||||||
|
|
||||||
# Handle one-shot jobs
|
# Handle one-shot jobs
|
||||||
if job.schedule.kind == "at":
|
if job.schedule.kind == "at":
|
||||||
@@ -366,6 +394,11 @@ class CronService:
|
|||||||
return True
|
return True
|
||||||
return False
|
return False
|
||||||
|
|
||||||
|
def get_job(self, job_id: str) -> CronJob | None:
|
||||||
|
"""Get a job by ID."""
|
||||||
|
store = self._load_store()
|
||||||
|
return next((j for j in store.jobs if j.id == job_id), None)
|
||||||
|
|
||||||
def status(self) -> dict:
|
def status(self) -> dict:
|
||||||
"""Get service status."""
|
"""Get service status."""
|
||||||
store = self._load_store()
|
store = self._load_store()
|
||||||
|
|||||||
@@ -29,6 +29,15 @@ class CronPayload:
|
|||||||
to: str | None = None # e.g. phone number
|
to: str | None = None # e.g. phone number
|
||||||
|
|
||||||
|
|
||||||
|
@dataclass
|
||||||
|
class CronRunRecord:
|
||||||
|
"""A single execution record for a cron job."""
|
||||||
|
run_at_ms: int
|
||||||
|
status: Literal["ok", "error", "skipped"]
|
||||||
|
duration_ms: int = 0
|
||||||
|
error: str | None = None
|
||||||
|
|
||||||
|
|
||||||
@dataclass
|
@dataclass
|
||||||
class CronJobState:
|
class CronJobState:
|
||||||
"""Runtime state of a job."""
|
"""Runtime state of a job."""
|
||||||
@@ -36,6 +45,7 @@ class CronJobState:
|
|||||||
last_run_at_ms: int | None = None
|
last_run_at_ms: int | None = None
|
||||||
last_status: Literal["ok", "error", "skipped"] | None = None
|
last_status: Literal["ok", "error", "skipped"] | None = None
|
||||||
last_error: str | None = None
|
last_error: str | None = None
|
||||||
|
run_history: list[CronRunRecord] = field(default_factory=list)
|
||||||
|
|
||||||
|
|
||||||
@dataclass
|
@dataclass
|
||||||
|
|||||||
@@ -1,4 +1,5 @@
|
|||||||
import asyncio
|
import asyncio
|
||||||
|
import json
|
||||||
|
|
||||||
import pytest
|
import pytest
|
||||||
|
|
||||||
@@ -32,6 +33,87 @@ def test_add_job_accepts_valid_timezone(tmp_path) -> None:
|
|||||||
assert job.state.next_run_at_ms is not None
|
assert job.state.next_run_at_ms is not None
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.asyncio
|
||||||
|
async def test_execute_job_records_run_history(tmp_path) -> None:
|
||||||
|
store_path = tmp_path / "cron" / "jobs.json"
|
||||||
|
service = CronService(store_path, on_job=lambda _: asyncio.sleep(0))
|
||||||
|
job = service.add_job(
|
||||||
|
name="hist",
|
||||||
|
schedule=CronSchedule(kind="every", every_ms=60_000),
|
||||||
|
message="hello",
|
||||||
|
)
|
||||||
|
await service.run_job(job.id)
|
||||||
|
|
||||||
|
loaded = service.get_job(job.id)
|
||||||
|
assert loaded is not None
|
||||||
|
assert len(loaded.state.run_history) == 1
|
||||||
|
rec = loaded.state.run_history[0]
|
||||||
|
assert rec.status == "ok"
|
||||||
|
assert rec.duration_ms >= 0
|
||||||
|
assert rec.error is None
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.asyncio
|
||||||
|
async def test_run_history_records_errors(tmp_path) -> None:
|
||||||
|
store_path = tmp_path / "cron" / "jobs.json"
|
||||||
|
|
||||||
|
async def fail(_):
|
||||||
|
raise RuntimeError("boom")
|
||||||
|
|
||||||
|
service = CronService(store_path, on_job=fail)
|
||||||
|
job = service.add_job(
|
||||||
|
name="fail",
|
||||||
|
schedule=CronSchedule(kind="every", every_ms=60_000),
|
||||||
|
message="hello",
|
||||||
|
)
|
||||||
|
await service.run_job(job.id)
|
||||||
|
|
||||||
|
loaded = service.get_job(job.id)
|
||||||
|
assert len(loaded.state.run_history) == 1
|
||||||
|
assert loaded.state.run_history[0].status == "error"
|
||||||
|
assert loaded.state.run_history[0].error == "boom"
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.asyncio
|
||||||
|
async def test_run_history_trimmed_to_max(tmp_path) -> None:
|
||||||
|
store_path = tmp_path / "cron" / "jobs.json"
|
||||||
|
service = CronService(store_path, on_job=lambda _: asyncio.sleep(0))
|
||||||
|
job = service.add_job(
|
||||||
|
name="trim",
|
||||||
|
schedule=CronSchedule(kind="every", every_ms=60_000),
|
||||||
|
message="hello",
|
||||||
|
)
|
||||||
|
for _ in range(25):
|
||||||
|
await service.run_job(job.id)
|
||||||
|
|
||||||
|
loaded = service.get_job(job.id)
|
||||||
|
assert len(loaded.state.run_history) == CronService._MAX_RUN_HISTORY
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.asyncio
|
||||||
|
async def test_run_history_persisted_to_disk(tmp_path) -> None:
|
||||||
|
store_path = tmp_path / "cron" / "jobs.json"
|
||||||
|
service = CronService(store_path, on_job=lambda _: asyncio.sleep(0))
|
||||||
|
job = service.add_job(
|
||||||
|
name="persist",
|
||||||
|
schedule=CronSchedule(kind="every", every_ms=60_000),
|
||||||
|
message="hello",
|
||||||
|
)
|
||||||
|
await service.run_job(job.id)
|
||||||
|
|
||||||
|
raw = json.loads(store_path.read_text())
|
||||||
|
history = raw["jobs"][0]["state"]["runHistory"]
|
||||||
|
assert len(history) == 1
|
||||||
|
assert history[0]["status"] == "ok"
|
||||||
|
assert "runAtMs" in history[0]
|
||||||
|
assert "durationMs" in history[0]
|
||||||
|
|
||||||
|
fresh = CronService(store_path)
|
||||||
|
loaded = fresh.get_job(job.id)
|
||||||
|
assert len(loaded.state.run_history) == 1
|
||||||
|
assert loaded.state.run_history[0].status == "ok"
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.asyncio
|
@pytest.mark.asyncio
|
||||||
async def test_running_service_honors_external_disable(tmp_path) -> None:
|
async def test_running_service_honors_external_disable(tmp_path) -> None:
|
||||||
store_path = tmp_path / "cron" / "jobs.json"
|
store_path = tmp_path / "cron" / "jobs.json"
|
||||||
|
|||||||
Reference in New Issue
Block a user