tao.chenandClaude
2537976722
P0 (Python parity 缺口):
- rm.Client.ListApps 新增 queue + limit 查询参数
- list_applications MCP tool schema 暴露 queue (string) 和 limit
(number, default 100), handler 透传给 RM client
- 限流原因: 生产 RM 上无 limit 会拉回 N MB JSON 撞 MaxResponseBytes
- limit <= 0 不发送 query 参数, 跟 RM 默认行为一致; 老的调用方
(TestListApplications_EndToEnd 等) 不传参时行为不变
- 4 个旧 ListApps 测试调用点跟着更新, 加 3 个新测试:
TestListApps_WithLimit, TestListApps_WithQueue,
TestListApps_LimitZeroNoParam
P1.3 (Python fallback 行为补全):
- rm.Client.GetLogs 加第 4 步 fallback: 当前 3 步
(amContainerLogs/aggregated-logs/logs) 全失败时, 调 GetApp
解析 app.amContainerLogs 字段, GET 该 URL 直连 NodeManager
- 新 source 名 'amContainerLogs-direct' 区分 RM-level endpoint
- 提取 doBytesWithHosts(extraHosts...) 支持 per-call host 白名单,
NM host 动态加进 allowedHosts, SSRF 保护不破 (URL 是 RM 响应里
回来的, 不是 LLM 任意填的)
- 新增 TestGetLogs_FallbackToAMDirect (成功路径) 和
TestGetLogs_FallbackFailsWhenAMFieldMissing (amContainerLogs
字段为空时正常返回 error)
P1.4 (零代码改动 + 文档化):
- get_application_logs / get_application_status 工具 description
更新, 提示 LLM raw RM JSON 里包含 amContainerLogs 字段, 可在
aggregated-logs 全部失败时自己用 fetch_url 直连 NM
- get_application_status 函数体不变 (本就是透传 raw JSON)
验证:
- go build / go vet / go test 全部通过
- 5 个新测试全 PASS, 老的 TestListApplications_EndToEnd 仍 PASS
- 单 ListApps 调用点 (list_applications.go:81) 编译过
未提交: spark-mcp-linux-amd64 (本地 build 产物, 当前 .gitignore
没拦, 需另行决定)
Co-Authored-By: Claude <noreply@anthropic.com>
90 lines
2.5 KiB
Go
90 lines
2.5 KiB
Go
package tools
|
|
|
|
import (
|
|
"context"
|
|
|
|
"github.com/mark3labs/mcp-go/mcp"
|
|
|
|
"spark-mcp-go/internal/rm"
|
|
)
|
|
|
|
const ListApplicationsName = "list_applications"
|
|
|
|
// NewListApplicationsTool returns the schema for the list_applications MCP Tool.
|
|
func NewListApplicationsTool() mcp.Tool {
|
|
return mcp.NewTool(ListApplicationsName,
|
|
mcp.WithDescription("List YARN applications from a cluster's ResourceManager. Returns the raw RM JSON response so the agent can inspect app IDs, states, and owners."),
|
|
mcp.WithString("cluster_id",
|
|
mcp.Required(),
|
|
mcp.Description("ID of the configured cluster (from list_clusters)"),
|
|
),
|
|
mcp.WithString("state",
|
|
mcp.Description("Filter by application state. YARN accepts comma-separated states; common values: NEW, NEW_SAVING, SUBMITTED, ACCEPTED, RUNNING, FINISHED, FAILED, KILLED."),
|
|
),
|
|
mcp.WithString("user",
|
|
mcp.Description("Filter by submitting user."),
|
|
),
|
|
mcp.WithString("queue",
|
|
mcp.Description("Filter by YARN queue name. Matches the YARN RM ?queue= parameter."),
|
|
),
|
|
mcp.WithNumber("limit",
|
|
mcp.Description("Maximum number of applications to return. Defaults to 100 if not provided; set to 0 to request the RM default (no limit)."),
|
|
mcp.DefaultNumber(100),
|
|
),
|
|
)
|
|
}
|
|
|
|
// ListApplicationsHandler queries the ResourceManager for applications.
|
|
func (d *Deps) ListApplicationsHandler(ctx context.Context, req mcp.CallToolRequest) (*mcp.CallToolResult, error) {
|
|
clusterID, err := req.RequireString("cluster_id")
|
|
if err != nil {
|
|
return errResult("list_applications: " + err.Error()), nil
|
|
}
|
|
|
|
args := req.GetArguments()
|
|
state := ""
|
|
if v, ok := args["state"].(string); ok {
|
|
state = v
|
|
}
|
|
user := ""
|
|
if v, ok := args["user"].(string); ok {
|
|
user = v
|
|
}
|
|
queue := ""
|
|
if v, ok := args["queue"].(string); ok {
|
|
queue = v
|
|
}
|
|
limit := 0
|
|
if v, ok := args["limit"].(float64); ok {
|
|
limit = int(v)
|
|
}
|
|
if limit < 0 {
|
|
limit = 0
|
|
}
|
|
|
|
callLog := startToolCall(ctx, d.Logger, ListApplicationsName, map[string]any{
|
|
"cluster_id": clusterID,
|
|
"state": state,
|
|
"user": user,
|
|
"queue": queue,
|
|
"limit": limit,
|
|
})
|
|
defer callLog.End()
|
|
|
|
cl, err := d.ClusterRepo.Get(ctx, clusterID)
|
|
if err != nil {
|
|
callLog.WithError(err)
|
|
return errResult("list_applications: cluster " + clusterID + ": " + err.Error()), nil
|
|
}
|
|
|
|
rmc := rm.New(d.HTTPClient, cl)
|
|
raw, err := rmc.ListApps(ctx, state, user, queue, limit)
|
|
if err != nil {
|
|
callLog.WithError(err)
|
|
return errResult("list_applications: " + err.Error()), nil
|
|
}
|
|
|
|
callLog.WithResult(map[string]any{"bytes": len(raw)})
|
|
return textResult(string(raw)), nil
|
|
}
|