Phase 5 Batch 2: 4 RM Tool + rm 客户端 + 日志降级链

- internal/rm/client.go: YARN RM 客户端 - ListApps / GetApp / KillApp / GetLogs - GetLogs 降级链数据驱动 (amContainerLogs → aggregated-logs → logs) - 跨主机 redirect 保留 Authorization (URLAllowlist 兜底) - 4 Tool: list_applications / get_application_status / get_application_logs / kill_application - mcp.WithEnum(state) 约束 YARN app 状态 - tool handler 永远 (result, nil), 业务错误用 NewToolResultError - deps.go: +HTTPClient + MaxResponseBytes - main.go: 注入 httpclient.Client - 端到端实测: mock RM 验证 4 Tool + 降级链 + 错误路径 Co-Authored-By: Claude <noreply@anthropic.com>
2026-07-10 16:50:27 +08:00
parent 705665745e
commit c4ac3cc354
9 changed files with 885 additions and 0 deletions
@@ -0,0 +1,93 @@
+package tools
+
+import (
+	"context"
+
+	"github.com/mark3labs/mcp-go/mcp"
+
+	"spark-mcp-go/internal/rm"
+)
+
+const GetApplicationLogsName = "get_application_logs"
+
+const defaultTailBytes = 1 << 20
+
+// NewGetApplicationLogsTool returns the schema for the get_application_logs MCP Tool.
+func NewGetApplicationLogsTool() mcp.Tool {
+	return mcp.NewTool(GetApplicationLogsName,
+		mcp.WithDescription("Fetch YARN application logs. Tries amContainerLogs first, then aggregated-logs, then the legacy /logs endpoint. Returns {source, text}."),
+		mcp.WithString("cluster_id",
+			mcp.Required(),
+			mcp.Description("ID of the configured cluster (from list_clusters)"),
+		),
+		mcp.WithString("app_id",
+			mcp.Required(),
+			mcp.Description("YARN application ID, e.g. application_1234567890_0001"),
+		),
+		mcp.WithString("container",
+			mcp.Description("Container ID used for the aggregated-logs fallback, e.g. container_1234567890_0001_01_000001."),
+		),
+		mcp.WithNumber("tail_bytes",
+			mcp.Description("Maximum bytes to return. 0 means use the server-wide response byte limit."),
+		),
+	)
+}
+
+// GetApplicationLogsHandler retrieves logs using the RM fallback chain.
+func (d *Deps) GetApplicationLogsHandler(ctx context.Context, req mcp.CallToolRequest) (*mcp.CallToolResult, error) {
+	clusterID, err := req.RequireString("cluster_id")
+	if err != nil {
+		return errResult("get_application_logs: " + err.Error()), nil
+	}
+	appID, err := req.RequireString("app_id")
+	if err != nil {
+		return errResult("get_application_logs: " + err.Error()), nil
+	}
+
+	args := req.GetArguments()
+	container := ""
+	if v, ok := args["container"].(string); ok {
+		container = v
+	}
+
+	tailBytes := defaultTailBytes
+	if v, ok := args["tail_bytes"].(float64); ok {
+		tailBytes = int(v)
+	}
+	if tailBytes == 0 {
+		tailBytes = int(d.MaxResponseBytes)
+	}
+
+	callLog := startToolCall(ctx, d.Logger, GetApplicationLogsName, map[string]any{
+		"cluster_id": clusterID,
+		"app_id":     appID,
+		"container":  container,
+		"tail_bytes": tailBytes,
+	})
+	defer callLog.End()
+
+	cl, err := d.ClusterRepo.Get(ctx, clusterID)
+	if err != nil {
+		callLog.WithError(err)
+		return errResult("get_application_logs: cluster " + clusterID + ": " + err.Error()), nil
+	}
+
+	rmc := rm.New(d.HTTPClient, cl)
+	body, source, err := rmc.GetLogs(ctx, appID, container)
+	if err != nil {
+		callLog.WithError(err)
+		return errResult("get_application_logs: " + err.Error()), nil
+	}
+
+	text := string(body)
+	if len(text) > tailBytes {
+		text = truncateMiddle(text, tailBytes)
+	}
+
+	result := map[string]any{
+		"source": source,
+		"text":   text,
+	}
+	callLog.WithResult(map[string]any{"source": source, "bytes": len(body), "returned_bytes": len(text)})
+	return textResult(encodeJSON(result)), nil
+}