feat(yarn_client): SSL/TLS config for YARN REST connections

Add per-Connection ssl_verify / ssl_ca_bundle plus global defaults so
CDH 5 / on-prem clusters with self-signed certs or custom CA bundles can
be queried without patching code.

- Connection gets ssl_verify (bool|None) and ssl_ca_bundle (str|None)
- Settings gets ssl_verify_default and ssl_ca_bundle_default
- New YarnClientConfig dataclass carries the resolved verify= value
- _request passes verify= through to httpx.request
- All public yarn_client functions now take YarnClientConfig instead of
  a bare yarn_rm_url string; tool call sites resolve the Connection
- SaveConnectionRequest exposes the two new fields

Tests cover per-connection CA bundle, per-connection verify=False,
global default fallback, and connection-not-found error.
This commit is contained in:
Claude
2026-06-26 13:50:30 +08:00
parent 5566d55a7c
commit ad557b5984
16 changed files with 362 additions and 87 deletions
+41 -30
View File
@@ -4,17 +4,28 @@ from unittest.mock import patch
import pytest
from spark_executor.core import connection_store
from spark_executor.core.job_store import JobStore
from spark_executor.models import Job
from spark_executor.models import Connection, Job
from spark_executor.tools import result
from spark_executor.tools import connections
def test_result_returns_parsed_fields():
def _fresh_stores():
store = connection_store.ConnectionStore()
connection_store.store = store
connections.store = store
result.conn_store = store
result.store = JobStore()
def _seed(job_id="abc", app_id="application_1"):
_fresh_stores()
result.conn_store.save(Connection(name="prod", master="yarn", yarn_rm_url="http://rm:8088"))
result.store.put(
Job(
job_id="abc",
application_id="application_1",
job_id=job_id,
application_id=app_id,
script_path="/tmp/j.py",
queue="default",
submit_time=datetime(2026, 6, 24),
@@ -22,6 +33,10 @@ def test_result_returns_parsed_fields():
yarn_rm_url="http://rm:8088",
)
)
def test_result_returns_parsed_fields():
_seed()
raw = {
"app": {
"id": "application_1",
@@ -48,22 +63,13 @@ def test_result_returns_parsed_fields():
assert out.tracking_url == "http://nm:8088/proxy/application_1"
assert out.started_time == 1700000000000
assert out.finished_time == 1700000123000
assert m.call_args.args == ("application_1", "http://rm:8088")
args = m.call_args.args
assert args[0] == "application_1"
assert args[1].yarn_rm_url == "http://rm:8088"
def test_result_handles_running_job():
result.store = JobStore()
result.store.put(
Job(
job_id="running",
application_id="application_2",
script_path="/tmp/j.py",
queue="default",
submit_time=datetime(2026, 6, 24),
connection="prod",
yarn_rm_url="http://rm:8088",
)
)
_seed(job_id="running", app_id="application_2")
raw = {
"app": {
"id": "application_2",
@@ -87,18 +93,7 @@ def test_result_handles_running_job():
def test_result_handles_missing_optional_fields():
result.store = JobStore()
result.store.put(
Job(
job_id="accepted",
application_id="application_3",
script_path="/tmp/j.py",
queue="default",
submit_time=datetime(2026, 6, 24),
connection="prod",
yarn_rm_url="http://rm:8088",
)
)
_seed(job_id="accepted", app_id="application_3")
raw = {"app": {"id": "application_3", "state": "ACCEPTED"}}
import json
@@ -118,6 +113,22 @@ def test_result_handles_missing_optional_fields():
def test_result_raises_keyerror_for_unknown_job():
result.store = JobStore()
_fresh_stores()
with pytest.raises(KeyError, match="Unknown job_id"):
result.get_job_result("missing")
def test_result_raises_when_connection_missing():
_fresh_stores()
result.store.put(
Job(
job_id="abc",
application_id="application_1",
script_path="/tmp/j.py",
queue="default",
submit_time=datetime(2026, 6, 24),
connection="missing",
)
)
with pytest.raises(KeyError, match="Connection not found"):
result.get_job_result("abc")