From 1cd31285229dfe32664ff09b347e1d4b43279add Mon Sep 17 00:00:00 2001
From: Claude <claude@anthropic.com>
Date: Wed, 24 Jun 2026 14:43:56 +0800
Subject: [PATCH] feat: add get_job_logs tool with tail

---
 spark_executor/tools/logs.py | 23 ++++++++++++++++++
 tests/unit/test_logs_tool.py | 47 ++++++++++++++++++++++++++++++++++++
 2 files changed, 70 insertions(+)
 create mode 100644 spark_executor/tools/logs.py
 create mode 100644 tests/unit/test_logs_tool.py

diff --git a/spark_executor/tools/logs.py b/spark_executor/tools/logs.py
new file mode 100644
index 0000000..ba0f8e0
--- /dev/null
+++ b/spark_executor/tools/logs.py
@@ -0,0 +1,23 @@
+# coding=utf-8
+"""
+@Time   :2026/6/24
+@Author :tao.chen
+"""
+from common.logging import logger
+from spark_executor.core.job_store import JobStore
+from spark_executor.core.yarn_client import get_application_logs
+
+store = JobStore()
+
+
+def get_job_logs(job_id: str, tail_chars: int = 5000) -> str:
+    job = store.get(job_id)
+    if job is None:
+        raise KeyError(f"Unknown job_id: {job_id}")
+    full = get_application_logs(job.application_id)
+    tailed = full[-tail_chars:] if len(full) > tail_chars else full
+    logger.info(
+        f"get_job_logs job_id={job_id} application_id={job.application_id} "
+        f"chars={len(tailed)}"
+    )
+    return tailed
diff --git a/tests/unit/test_logs_tool.py b/tests/unit/test_logs_tool.py
new file mode 100644
index 0000000..3c349de
--- /dev/null
+++ b/tests/unit/test_logs_tool.py
@@ -0,0 +1,47 @@
+# coding=utf-8
+from datetime import datetime
+from unittest.mock import patch
+
+from spark_executor.core.job_store import JobStore
+from spark_executor.models import Job
+from spark_executor.tools import logs
+
+
+def _seed(job_id="abc", app_id="application_1"):
+    logs.store = JobStore()
+    logs.store.put(
+        Job(
+            job_id=job_id,
+            application_id=app_id,
+            script_path="/tmp/j.py",
+            queue="default",
+            submit_time=datetime(2026, 6, 24),
+            connection="prod",
+        )
+    )
+
+
+def test_get_job_logs_tails_to_default_5000():
+    _seed()
+    big = "x" * 8000 + "\nEND"
+    with patch("spark_executor.tools.logs.get_application_logs", return_value=big):
+        out = logs.get_job_logs("abc")
+    assert out.endswith("END")
+    assert len(out) == 5000
+
+
+def test_get_job_logs_respects_custom_tail_chars():
+    _seed()
+    with patch(
+        "spark_executor.tools.logs.get_application_logs",
+        return_value="0123456789",
+    ):
+        out = logs.get_job_logs("abc", tail_chars=3)
+    assert out == "789"
+
+
+def test_get_job_logs_raises_for_unknown_job():
+    _seed()
+    import pytest
+    with pytest.raises(KeyError):
+        logs.get_job_logs("missing")