fix: add job cancel and tune artifact download

scripts/src/artifact-registry.ts

@@ -1677,6 +1677,8 @@ function downloadRemoteFile(options: ArtifactRegistryOptions, remotePath: string
     "ssh",
     options.providerId,
     "download",
+    "--chunk-bytes",
+    "64000",
     remotePath,
     localPath,
   ], repoRoot, { timeoutMs });

scripts/src/help.ts

@@ -84,6 +84,7 @@ export function rootHelp(): unknown {
       { command: "codex (queues [--full|--all] | queue create <queueId> | queue merge <sourceQueueId> --into <targetQueueId> | move <taskId> --queue <queueId>)", description: "List low-noise queue summaries by default, including effective activity counts that distinguish scheduler-local queues, DB running tasks, and heartbeat-fresh runners; full queue rows require --full/--all." },
       { command: "job list [--limit N] [--include-command]", description: "List async jobs from .state/jobs with a bounded default page and progress summaries." },
       { command: "job status <jobId|latest> [--tail-bytes N]", description: "Show job state with a structured progress summary and bounded stdout/stderr tails." },
+      { command: "job cancel <jobId>", description: "Cancel a queued/running async job through the .state/jobs control entry and keep a terminal canceled record." },
       { command: "debug health", description: "Probe internal core, nodes, system/Docker status, frontend, provider ingress, and public boundary." },
       { command: "debug dispatch [providerId] [docker.ps|provider.upgrade|host.ssh|microservice.http|echo] [--wait-ms N]", description: "Submit a real internal-core dispatch request for CLI debugging." },
       { command: "debug task <taskId|latest>", description: "Read a dispatched task record from internal core for CLI debugging." },
@@ -480,13 +481,14 @@ function codexHelp(): unknown {
 
 function jobHelp(): unknown {
   return {
-    command: "job list|status",
+    command: "job list|status|cancel",
     output: "json",
     usage: [
       "bun scripts/cli.ts job list [--limit N] [--include-command]",
       "bun scripts/cli.ts job status <jobId|latest> [--tail-bytes N]",
+      "bun scripts/cli.ts job cancel <jobId>",
     ],
-    description: "Inspect fire-and-forget job state from .state/jobs with structured progress summaries and bounded log tails.",
+    description: "Inspect or cancel fire-and-forget job state from .state/jobs with structured progress summaries and bounded log tails.",
   };
 }
 

scripts/src/jobs.ts

@@ -4,7 +4,7 @@ import { join } from "node:path";
 import { repoRoot, rootPath } from "./config";
 import { runCommandToFiles, tailFile } from "./command";
 
-export type JobStatus = "queued" | "running" | "succeeded" | "failed";
+export type JobStatus = "queued" | "running" | "succeeded" | "failed" | "canceled";
 
 export interface JobRecord {
   id: string;
@@ -68,6 +68,34 @@ export function readJob(id: string): JobRecord {
   return JSON.parse(readFileSync(path, "utf8")) as JobRecord;
 }
 
+export function cancelJob(id: string): unknown {
+  const job = readJob(id);
+  if (job.status !== "queued" && job.status !== "running") {
+    return { ok: true, action: "cancel-job", id, alreadyTerminal: true, job };
+  }
+  const actions: Array<Record<string, unknown>> = [];
+  if (job.runnerPid !== null && job.runnerPid !== undefined) {
+    try {
+      process.kill(-job.runnerPid, "SIGTERM");
+      actions.push({ signal: "SIGTERM", target: "process-group", pid: job.runnerPid, ok: true });
+    } catch (error) {
+      actions.push({ signal: "SIGTERM", target: "process-group", pid: job.runnerPid, ok: false, error: error instanceof Error ? error.message : String(error) });
+      try {
+        process.kill(job.runnerPid, "SIGTERM");
+        actions.push({ signal: "SIGTERM", target: "process", pid: job.runnerPid, ok: true });
+      } catch (innerError) {
+        actions.push({ signal: "SIGTERM", target: "process", pid: job.runnerPid, ok: false, error: innerError instanceof Error ? innerError.message : String(innerError) });
+      }
+    }
+  }
+  job.status = "canceled";
+  job.finishedAt = new Date().toISOString();
+  job.exitCode = 130;
+  writeFileSync(job.stderrFile, `${tailFile(job.stderrFile, 512_000)}${JSON.stringify({ event: "unidesk.job.cancel", at: job.finishedAt, jobId: id, actions })}\n`, "utf8");
+  writeJob(job);
+  return { ok: true, action: "cancel-job", id, actions, job };
+}
+
 export function listJobs(): JobRecord[] {
   return readdirSync(jobsDir())
     .filter((name) => name.endsWith(".json"))
@@ -323,32 +351,40 @@ function summarizeGitMirrorJobProgress(job: JobRecord, stdoutTail: string, stder
 
 function genericJobProgress(job: JobRecord): JobProgressSummary {
   const nowMs = Date.now();
+  const stderrTail = tailFile(job.stderrFile, 96_000);
+  const downloadEvents = parseJsonLineEvents(stderrTail, "unidesk.ssh.download.progress");
+  const lastDownload = downloadEvents.at(-1) ?? null;
+  const lastDownloadAt = stringField(lastDownload?.at);
+  const lastEventAgeSeconds = lastDownloadAt === null ? null : secondsSince(lastDownloadAt, job.finishedAt ?? nowMs);
   const elapsedSeconds = jobElapsedSeconds(job, nowMs);
   const warnings = jobProgressWarnings({
     job,
-    eventsObserved: 0,
+    eventsObserved: downloadEvents.length,
     elapsedSeconds,
-    stage: null,
-    stageStatus: null,
+    stage: lastDownload === null ? null : "ssh-download",
+    stageStatus: lastDownload === null ? null : "running",
     stageElapsedSeconds: null,
-    lastEventAgeSeconds: null,
+    lastEventAgeSeconds,
   });
+  const downloadSummary = lastDownload === null
+    ? null
+    : ` ssh-download ${Number(lastDownload.actualBytes ?? 0)}/${Number(lastDownload.expectedBytes ?? 0)} bytes chunks=${Number(lastDownload.chunks ?? 0)}`;
   return {
     kind: "generic",
-    stage: null,
-    stageStatus: null,
+    stage: lastDownload === null ? null : "ssh-download",
+    stageStatus: lastDownload === null ? null : "running",
     sourceCommit: null,
     pipelineRun: null,
     pipelineCreated: null,
     elapsedSeconds,
     stageElapsedSeconds: null,
-    lastEventAt: null,
-    lastEventAgeSeconds: null,
-    eventsObserved: 0,
+    lastEventAt: lastDownloadAt,
+    lastEventAgeSeconds,
+    eventsObserved: downloadEvents.length,
     slow: warnings.length > 0,
     warnings,
     timings: {},
-    summary: `${job.status}${job.exitCode === null ? "" : ` exit=${job.exitCode}`}`,
+    summary: `${job.status}${job.exitCode === null ? "" : ` exit=${job.exitCode}`}${downloadSummary ?? ""}`,
     nextCommand: job.status === "running" ? `bun scripts/cli.ts job status ${job.id} --tail-bytes 12000` : null,
   };
 }