ClaudeandClaude Fable 5
6cf68439a2
Add 3 new MCP tools for inspecting YARN applications NOT submitted through this service: get_external_job_logs, get_external_job_status, get_external_job_result. Each takes application_id + connection_name and queries YARN directly, bypassing the local JobStore. - spark_executor/tools/external_jobs.py: 3 tool functions - spark_executor/tools/requests.py: 3 new Pydantic body models (ExternalJobLogsRequest, ExternalJobStatusRequest, ExternalJobResultRequest) - spark_executor/server.py: 3 new POST routes with explicit operation_id - tests/unit/test_external_jobs.py: 7 unit tests - tests/integration/test_mcp_routes.py: assert 20 tool routes - README.md: list the 3 new tools To make the LLM pick the right tool and not guess at field values, also: - Add Pydantic field descriptions for 22 fields across 8 request models (SaveConnectionRequest, UpdatePendingJobRequest, GetJobLogsRequest, JobIdRequest, PendingIdRequest, ConnectionNameRequest, plus the new ExternalJob*Request models). - Update 12 route descriptions with cross-references, prerequisite context, and 400 behavior notes. - Refactor _unknown_job_error: an input that looks like a YARN application_id (starts with 'application_') now returns HTTP 400 (ValueError) with a hint message naming the right external tool; other not-found cases still return 404 (KeyError). This catches the common LLM mistake of passing application_id to the internal get_job_* / kill_job tools. - 4 new unit tests for the 400 behavior. Tests: 356 passed (up from 242). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
66 lines
3.0 KiB
Python
66 lines
3.0 KiB
Python
# coding=utf-8
|
|
"""
|
|
@Time :2026/7/8
|
|
@Author :tao.chen
|
|
|
|
Tools for inspecting YARN applications NOT submitted through this service.
|
|
These bypass the local JobStore and require the caller to supply both the
|
|
YARN application_id and the name of a saved Connection.
|
|
"""
|
|
import json
|
|
|
|
from common.logging import logger
|
|
from spark_executor.core.yarn_client import YarnClientConfig, get_application_status, get_application_logs
|
|
from spark_executor.models import JobStatus, JobResult
|
|
from spark_executor.tools.connections import store as conn_store
|
|
|
|
|
|
def get_external_job_logs(application_id: str, connection_name: str, tail_chars: int = 5000) -> str:
|
|
"""Fetch aggregated container logs for a YARN application by ID."""
|
|
logger.debug(f"get_external_job_logs enter application_id={application_id} connection_name={connection_name} tail_chars={tail_chars}")
|
|
conn = conn_store.get(connection_name)
|
|
if conn is None:
|
|
raise KeyError(f"Connection not found: {connection_name}")
|
|
config = YarnClientConfig.from_connection(conn)
|
|
full = get_application_logs(application_id, config)
|
|
tailed = full[-tail_chars:] if len(full) > tail_chars else full
|
|
logger.info(
|
|
f"get_external_job_logs ok application_id={application_id} connection_name={connection_name} "
|
|
f"full_chars={len(full)} returned_chars={len(tailed)}"
|
|
)
|
|
return tailed
|
|
|
|
|
|
def get_external_job_status(application_id: str, connection_name: str) -> JobStatus:
|
|
"""Query YARN for an external application's current status."""
|
|
logger.debug(f"get_external_job_status enter application_id={application_id} connection_name={connection_name}")
|
|
conn = conn_store.get(connection_name)
|
|
if conn is None:
|
|
raise KeyError(f"Connection not found: {connection_name}")
|
|
config = YarnClientConfig.from_connection(conn)
|
|
state, raw = get_application_status(application_id, config)
|
|
logger.info(f"get_external_job_status ok application_id={application_id} connection_name={connection_name} state={state}")
|
|
return JobStatus(application_id=application_id, state=state, raw=raw)
|
|
|
|
|
|
def get_external_job_result(application_id: str, connection_name: str) -> JobResult:
|
|
"""Query YARN for an external application's terminal result view."""
|
|
logger.debug(f"get_external_job_result enter application_id={application_id} connection_name={connection_name}")
|
|
conn = conn_store.get(connection_name)
|
|
if conn is None:
|
|
raise KeyError(f"Connection not found: {connection_name}")
|
|
config = YarnClientConfig.from_connection(conn)
|
|
state, raw = get_application_status(application_id, config)
|
|
app = json.loads(raw).get("app", {})
|
|
result = JobResult(
|
|
application_id=application_id,
|
|
state=state,
|
|
final_status=app.get("finalStatus"),
|
|
diagnostics=app.get("diagnostics"),
|
|
tracking_url=app.get("trackingUrl"),
|
|
started_time=app.get("startedTime"),
|
|
finished_time=app.get("finishedTime"),
|
|
)
|
|
logger.info(f"get_external_job_result ok application_id={application_id} connection_name={connection_name} state={state}")
|
|
return result
|