chore: import upstream snapshot with attribution
CI (OpenClaw E2E) / openclaw test (push) Has been cancelled
CI / coverage-report (push) Has been cancelled
CI / test-kubernetes (push) Has been cancelled
CI / should-run-thorough (push) Has been cancelled
CI / test-thorough (cloudwatch-demo) (push) Has been cancelled
CI / test-thorough (flink-ecs) (push) Has been cancelled
CI / test-thorough (upstream-lambda) (push) Has been cancelled
CI / test-thorough (prefect-ecs-fargate) (push) Has been cancelled
Release / build-binaries (zip, opensre.exe, onefile, windows-latest, windows-x64) (push) Has been cancelled
Benchmark image — build + push to ECR (any adapter) / build + push (push) Has been cancelled
CI / quality (ubuntu-latest) (push) Has been cancelled
CI / test (tools-runtime) (push) Has been cancelled
CI / test (e2e-general) (push) Has been cancelled
CI / test (cli-runtime) (push) Has been cancelled
CI / test (e2e-provider-and-openclaw) (push) Has been cancelled
CI / test (integrations-and-misc) (push) Has been cancelled
Release / verify (push) Has been cancelled
Release / build-python-dist (push) Has been cancelled
Release / build-binaries (tar.gz, opensre, onedir, macos-15-intel, darwin-x64) (push) Has been cancelled
Release / build-binaries (tar.gz, opensre, onedir, macos-latest, darwin-arm64) (push) Has been cancelled
Release / build-binaries (tar.gz, opensre, onedir, ubuntu-22.04, linux-x64) (push) Has been cancelled
Release / publish-release (push) Has been cancelled
Release / publish-main-release (push) Has been cancelled
Interactive Shell Live (PR + post-merge) / turn-checks (no-LLM) (push) Has been cancelled
CodeQL / Analyze (python) (push) Has been cancelled
Interactive Shell Live (PR + post-merge) / turn-live shard ${{ matrix.shard_index }} (push) Has been cancelled
Release / prepare (push) Has been cancelled
Release / build-binaries (tar.gz, opensre, onedir, ubuntu-22.04-arm, linux-arm64) (push) Has been cancelled
Synthetic Deterministic Tests / Synthetic offline (deterministic) (push) Has been cancelled

This commit is contained in:
wehub-resource-sync
2026-07-13 13:10:45 +08:00
commit 4b6817381b
3933 changed files with 525247 additions and 0 deletions
+33
View File
@@ -0,0 +1,33 @@
"""Splunk integration classifier."""
from __future__ import annotations
import logging
from typing import Any
from integrations._validation_helpers import report_classify_failure
from integrations.config_models import SplunkIntegrationConfig
logger = logging.getLogger(__name__)
def classify(
credentials: dict[str, Any], record_id: str
) -> tuple[SplunkIntegrationConfig | None, str | None]:
try:
cfg = SplunkIntegrationConfig.model_validate(
{
"base_url": credentials.get("base_url", ""),
"token": credentials.get("token", ""),
"index": credentials.get("index", "main"),
"verify_ssl": credentials.get("verify_ssl", True),
"ca_bundle": credentials.get("ca_bundle", ""),
"integration_id": record_id,
}
)
except Exception as exc:
report_classify_failure(exc, logger=logger, integration="splunk", record_id=record_id)
return None, None
if cfg.base_url and cfg.token:
return cfg, "splunk"
return None, None
+32
View File
@@ -0,0 +1,32 @@
"""Splunk client factory for the SplunkSearchTool."""
from __future__ import annotations
from typing import Any
from integrations.splunk.client import SplunkClient, SplunkConfig
def make_client(
base_url: str | None,
token: str | None = None,
index: str = "main",
verify_ssl: bool = True,
ca_bundle: str = "",
) -> SplunkClient | None:
if not base_url or not token:
return None
return SplunkClient(
SplunkConfig(
base_url=base_url,
token=token,
index=index,
verify_ssl=verify_ssl,
ca_bundle=ca_bundle,
)
)
def unavailable(source: str, empty_key: str, error: str, **extra: Any) -> dict[str, Any]:
"""Standardised unavailable response."""
return {"source": source, "available": False, "error": error, empty_key: [], **extra}
+203
View File
@@ -0,0 +1,203 @@
"""Splunk REST API client for RCA log searches."""
from __future__ import annotations
import json
import logging
from datetime import UTC, datetime, timedelta
from typing import Any
import httpx
from integrations.config_models import SplunkIntegrationConfig
from integrations.probes import ProbeResult
from platform.observability.errors.service import capture_service_error
from platform.observability.streaming import StreamingParseStats
logger = logging.getLogger(__name__)
_DEFAULT_TIMEOUT_SECONDS = 30.0
def build_splunk_spl_query(
*,
raw_query: str = "",
index: str = "main",
error_message: str = "",
alert_name: str = "",
trace_id: str = "",
limit: int = 50,
) -> str:
"""Build an SPL query for RCA investigation.
Priority:
1. raw_query — operator supplied a verbatim SPL (from annotations.query)
2. Construct from available signals (index + keyword filters)
"""
if raw_query.strip():
# Ensure a head clause to prevent runaway queries
spl = raw_query.strip()
if "| head " not in spl.lower():
spl = f"{spl} | head {limit}"
return spl
# Build keyword filter from alert signals
keyword = (error_message or alert_name or "").strip()
if trace_id:
keyword_clause = f'index={index} trace_id="{trace_id}"'
elif keyword:
# Escape double-quotes inside keyword
safe_keyword = keyword.replace('"', '\\"')
keyword_clause = f'index={index} "{safe_keyword}"'
else:
keyword_clause = f"index={index}"
return f"search {keyword_clause} | head {limit}"
SplunkConfig = SplunkIntegrationConfig
class SplunkClient:
"""Synchronous Splunk REST API client using the export (streaming) endpoint."""
def __init__(self, config: SplunkConfig) -> None:
self.config = config
def _headers(self) -> dict[str, str]:
return {
"Authorization": f"Bearer {self.config.token}",
"Content-Type": "application/x-www-form-urlencoded",
}
def _export_url(self) -> str:
return f"{self.config.base_url}/services/search/jobs/export"
def search_logs(
self,
query: str,
*,
time_range_minutes: int = 60,
limit: int = 50,
) -> dict[str, Any]:
"""Run a blocking SPL search via the export endpoint.
Returns normalized log rows. The export endpoint streams results
immediately — no job polling needed, making it ideal for RCA.
"""
now = datetime.now(UTC)
earliest = now - timedelta(minutes=max(int(time_range_minutes), 1))
params = {
"search": query if query.startswith("search ") else f"search {query}",
"earliest_time": earliest.strftime("%Y-%m-%dT%H:%M:%S"),
"latest_time": now.strftime("%Y-%m-%dT%H:%M:%S"),
"output_mode": "json",
"count": str(limit),
}
try:
response = httpx.post(
self._export_url(),
headers=self._headers(),
data=params,
timeout=_DEFAULT_TIMEOUT_SECONDS,
verify=self.config.ssl_verify,
)
response.raise_for_status()
except httpx.HTTPStatusError as exc:
capture_service_error(exc, logger=logger, integration="splunk", method="search_logs")
return {
"success": False,
"error": f"HTTP {exc.response.status_code}: {exc.response.text[:200]}",
}
except Exception as exc:
capture_service_error(exc, logger=logger, integration="splunk", method="search_logs")
return {"success": False, "error": str(exc)}
logs = self._parse_export_response(response.text)
return {
"success": True,
"logs": logs,
"total": len(logs),
"query": query,
}
def _parse_export_response(self, response_text: str) -> list[dict[str, Any]]:
"""Parse the NDJSON export stream into normalized log dicts."""
logs: list[dict[str, Any]] = []
stats = StreamingParseStats()
for line in response_text.splitlines():
stripped = line.strip()
if not stripped:
continue
try:
payload = json.loads(stripped)
except json.JSONDecodeError as exc:
stats.record_error(exc)
continue
stats.record_parsed()
if not isinstance(payload, dict):
continue
result_type = payload.get("result")
if isinstance(result_type, dict):
logs.append(self._normalize_row(result_type))
stats.report_if_unhealthy(logger=logger, integration="splunk", source="search/jobs/export")
return logs
def _normalize_row(self, row: dict[str, Any]) -> dict[str, Any]:
"""Normalize a Splunk result row to a common log shape."""
return {
"timestamp": str(row.get("_time", "")),
"message": str(row.get("_raw", row.get("message", ""))),
"level": str(row.get("log_level", row.get("severity", ""))),
"source": str(row.get("source", "")),
"host": str(row.get("host", "")),
"sourcetype": str(row.get("sourcetype", "")),
"index": str(row.get("index", "")),
"raw": row,
}
def validate_access(self) -> dict[str, Any]:
"""Validate Splunk credentials by hitting the server info endpoint."""
info_url = f"{self.config.base_url}/services/server/info"
try:
response = httpx.get(
info_url,
headers={"Authorization": f"Bearer {self.config.token}"},
params={"output_mode": "json"},
timeout=10.0,
verify=self.config.ssl_verify,
)
response.raise_for_status()
data = response.json()
version = data.get("entry", [{}])[0].get("content", {}).get("version", "unknown")
return {
"success": True,
"detail": f"Connected to Splunk {version}",
}
except httpx.HTTPStatusError as exc:
capture_service_error(
exc, logger=logger, integration="splunk", method="validate_access"
)
return {
"success": False,
"error": f"HTTP {exc.response.status_code}: {exc.response.text[:200]}",
}
except Exception as exc:
capture_service_error(
exc, logger=logger, integration="splunk", method="validate_access"
)
return {"success": False, "error": str(exc)}
def probe_access(self) -> ProbeResult:
"""Validate Splunk connectivity by calling the server info endpoint."""
if not (self.config.base_url and self.config.token):
return ProbeResult.missing("Missing base_url or token.")
result = self.validate_access()
if not result.get("success"):
return ProbeResult.failed(
f"Server info check failed: {result.get('error', 'unknown error')}"
)
return ProbeResult.passed(result.get("detail", "Connected."))
+145
View File
@@ -0,0 +1,145 @@
# ======== from tools/splunk_search_tool/ ========
"""Splunk log search tool for RCA investigation."""
from __future__ import annotations
from typing import Any
from core.tool_framework.base import BaseTool
from integrations.splunk._client import make_client, unavailable
from platform.common.evidence_compaction import compact_logs, summarize_counts
_ERROR_KEYWORDS = (
"error",
"fail",
"exception",
"traceback",
"critical",
"killed",
"crash",
"panic",
"timeout",
)
class SplunkSearchTool(BaseTool):
"""Search Splunk logs using SPL for errors, exceptions, and application events."""
name = "query_splunk_logs"
source = "splunk"
description = (
"Search Splunk using SPL (Search Processing Language) for application errors, "
"exceptions, and operational events. Returns time-bounded log evidence."
)
use_cases = [
"Investigating application errors stored in Splunk",
"Searching Splunk indexes for error patterns during incident window",
"Fetching recent error logs for a service identified in an alert",
"Correlating trace IDs with Splunk log entries",
]
surfaces = ("investigation", "chat")
requires = [] # connection_verified check is in is_available()
outputs = {
"splunk_logs": "All log events returned from Splunk search",
"splunk_error_logs": "Subset of logs matching error/exception keywords",
}
input_schema = {
"type": "object",
"properties": {
"query": {
"type": "string",
"description": (
"SPL search string (e.g. 'index=main error | head 50'). "
"Do not include the leading 'search' keyword."
),
},
"time_range_minutes": {
"type": "integer",
"default": 60,
"description": "Look-back window in minutes from now.",
},
"limit": {
"type": "integer",
"default": 50,
"description": "Maximum number of events to return.",
},
"index": {
"type": "string",
"description": "Splunk index to search (overrides integration default).",
},
},
"required": ["query"],
}
def is_available(self, sources: dict) -> bool:
return bool(sources.get("splunk", {}).get("connection_verified"))
def extract_params(self, sources: dict) -> dict:
splunk = sources.get("splunk", {})
return {
"query": splunk.get("default_query", f"index={splunk.get('index', 'main')} | head 50"),
"time_range_minutes": splunk.get("time_range_minutes", 60),
"limit": 50,
"index": splunk.get("index", "main"),
"base_url": splunk.get("base_url"),
"token": splunk.get("token"),
"verify_ssl": splunk.get("verify_ssl", True),
"ca_bundle": splunk.get("ca_bundle", ""),
}
def run(
self,
query: str,
time_range_minutes: int = 60,
limit: int = 50,
index: str = "main",
base_url: str | None = None,
token: str | None = None,
verify_ssl: bool = True,
ca_bundle: str = "",
**_kwargs: Any,
) -> dict:
client = make_client(base_url, token, index, verify_ssl, ca_bundle)
if client is None:
return unavailable(
"splunk_logs",
"logs",
"Splunk integration not configured (missing base_url or token)",
)
result = client.search_logs(
query=query,
time_range_minutes=time_range_minutes,
limit=limit,
)
if not result.get("success"):
return unavailable("splunk_logs", "logs", result.get("error", "Unknown error"))
logs = result.get("logs", [])
error_logs = [
log
for log in logs
if any(kw in log.get("message", "").lower() for kw in _ERROR_KEYWORDS)
]
compacted_logs = compact_logs(logs, limit=limit)
compacted_error_logs = compact_logs(error_logs, limit=limit)
result_data: dict[str, Any] = {
"source": "splunk_logs",
"available": True,
"logs": compacted_logs,
"error_logs": compacted_error_logs,
"total": result.get("total", 0),
"query": query,
}
summary = summarize_counts(result.get("total", 0), len(compacted_logs), "logs")
if summary:
result_data["truncation_note"] = summary
return result_data
# Module-level alias for direct invocation
query_splunk_logs = SplunkSearchTool()
+12
View File
@@ -0,0 +1,12 @@
"""Splunk integration verifier."""
from __future__ import annotations
from integrations.splunk.client import SplunkClient, SplunkConfig
from integrations.verification import register_probe_verifier
verify_splunk = register_probe_verifier(
"splunk",
config=SplunkConfig.model_validate,
client=SplunkClient,
)