fix(cli): guide ssh argv usage

scripts/provider-runner-triage-contract-test.ts

@@ -1,4 +1,4 @@
-import { buildProviderTriageResult, type ProviderTriageSignal } from "./src/provider-triage";
+import { buildProviderTriageResult, providerTriageRecommendedCrossChecks, type ProviderTriageSignal } from "./src/provider-triage";
 import { codexTaskQuery } from "./src/code-queue";
 import { classifyRunnerError } from "../src/components/microservices/code-queue/src/runner-error-classifier";
 
@@ -58,6 +58,11 @@ export function runProviderRunnerTriageContract(): JsonRecord {
   assertCondition(result.decision === "retryable-transient", "single path provider offline should be retryable transient", result);
   assertCondition(result.retryable === true, "single path provider offline should be retryable", result);
   assertCondition(result.contract.singlePathProviderOfflineIsGlobalBlocker === false, "triage contract should reject single-path global blocker", result);
+  assertCondition(result.recommendedCrossChecks.includes("bun scripts/cli.ts ssh D601 argv true"), "provider triage result must recommend argv Host SSH cross-check", result.recommendedCrossChecks);
+
+  const crossChecks = providerTriageRecommendedCrossChecks("D601");
+  assertCondition(crossChecks.includes("bun scripts/cli.ts ssh D601 argv true"), "provider triage recommendedCrossChecks must keep ssh argv true", crossChecks);
+  assertCondition(crossChecks.includes("bun scripts/cli.ts debug dispatch D601 host.ssh --wait-ms 15000"), "provider triage recommendedCrossChecks must keep host.ssh dispatch probe", crossChecks);
 
   const rateLimitTriage = buildProviderTriageResult("D601", [
     signal("observed-runner-429", "external-provider", "failed", false),
@@ -102,6 +107,7 @@ export function runProviderRunnerTriageContract(): JsonRecord {
       "runner error classifier separates runner-local/provider-gateway/registry/k3s/scheduler/unknown",
       "each single runner error classification has globalBlocker=false",
       "provider triage keeps single provider is not online as retryable-transient, not global-blocker",
+      "provider triage recommendedCrossChecks keeps host.ssh dispatch and ssh argv true probes",
       "external OpenAI/model provider 429 is explicit retryable backoff evidence, not Code Queue infra outage",
       "codex task --detail preserves runnerErrorClassification in compact attempt output",
     ],

scripts/src/check.ts

@@ -45,6 +45,7 @@ const syntaxFiles = [
   "scripts/microservice-health-output-contract-test.ts",
   "scripts/code-queue-supervisor-disclosure-contract-test.ts",
   "scripts/code-queue-commander-view-contract-test.ts",
+  "scripts/ssh-argv-guidance-contract-test.ts",
   "src/components/frontend/src/index.ts",
   "src/components/frontend/src/app.tsx",
   "src/components/frontend/src/decision-center.tsx",
@@ -334,6 +335,7 @@ export function runChecks(config: UniDeskConfig, options: CheckOptions = default
       fileItem("scripts/host-codex-commander-skeleton-contract-test.ts"),
       fileItem("scripts/host-codex-commander-no-daemon-smoke-contract-test.ts"),
       fileItem("scripts/provider-runner-triage-contract-test.ts"),
+      fileItem("scripts/ssh-argv-guidance-contract-test.ts"),
       fileItem("scripts/src/provider-triage.ts"),
       fileItem("src/components/microservices/code-queue/src/runner-error-classifier.ts"),
       fileItem("scripts/src/ci.ts"),
@@ -384,6 +386,7 @@ export function runChecks(config: UniDeskConfig, options: CheckOptions = default
     items.push(commandItem("host-codex-commander:skeleton-contract", ["bun", "scripts/host-codex-commander-skeleton-contract-test.ts"], 30_000));
     items.push(commandItem("host-codex-commander:no-daemon-smoke-contract", ["bun", "scripts/host-codex-commander-no-daemon-smoke-contract-test.ts"], 30_000));
     items.push(commandItem("provider:runner-triage-contract", ["bun", "scripts/provider-runner-triage-contract-test.ts"], 30_000));
+    items.push(commandItem("ssh:argv-guidance-contract", ["bun", "scripts/ssh-argv-guidance-contract-test.ts"], 30_000));
     items.push(commandItem("deploy:artifact-matrix-contract", ["bun", "scripts/deploy-artifact-matrix-contract-test.ts"], 30_000));
     items.push(commandItem("decision-center:desired-state-contract", ["bun", "scripts/decision-center-desired-state-contract-test.ts"], 30_000));
     items.push(commandItem("code-queue:active-run-heartbeat-visible", ["bun", "scripts/code-queue-liveness-diagnostics-test.ts", "--only", "code-queue:active-run-heartbeat-visible"], 30_000));
@@ -423,6 +426,7 @@ export function runChecks(config: UniDeskConfig, options: CheckOptions = default
     items.push(skippedItem("host-codex-commander:skeleton-contract", "host Codex commander skeleton contract is opt-in with script checks", "--scripts-typecheck or --full"));
     items.push(skippedItem("host-codex-commander:no-daemon-smoke-contract", "host Codex commander no-daemon smoke contract is opt-in with script checks", "--scripts-typecheck or --full"));
     items.push(skippedItem("provider:runner-triage-contract", "Provider runner triage contract is opt-in with script checks", "--scripts-typecheck or --full"));
+    items.push(skippedItem("ssh:argv-guidance-contract", "SSH argv guidance and failure hint contract is opt-in with script checks", "--scripts-typecheck or --full"));
     items.push(skippedItem("deploy:artifact-matrix-contract", "deploy artifact matrix contract is opt-in with script checks", "--scripts-typecheck or --full"));
     items.push(skippedItem("decision-center:desired-state-contract", "Decision Center desired-state drift contract is opt-in with script checks", "--scripts-typecheck or --full"));
     items.push(skippedItem("code-queue:liveness-diagnostics-fixtures", "Code Queue liveness diagnostics fixtures are opt-in with script checks", "--scripts-typecheck or --full"));

scripts/src/help.ts

@@ -18,13 +18,13 @@ export function rootHelp(): unknown {
       { command: "server cleanup plan [--min-age-hours N] [--limit N]", description: "Dry-run Docker image cleanup plan only: list active/protected images, stale candidates older than the default 24h threshold, risk, estimated reclaim, and manual review commands without deleting anything." },
       { command: "server rebuild <backend-core|frontend|dev-frontend-proxy|provider-gateway|todo-note|code-queue-mgr|project-manager|baidu-netdisk|oa-event-flow>", description: "Maintenance-only local Compose rebuild for reviewed main-server services; frontend standard release must use CI artifact plus deploy apply dev/prod artifact consumers." },
       { command: "provider attach <providerId> [--master-server URL] [--up] [--force] | provider triage <providerId> [--observed-error text] [--observed-scope scope] [--microservice id ...] [--full|--raw]", description: "Generate the minimal external provider-gateway env/compose bundle or run the low-noise read-only provider health triage contract." },
-      { command: "ssh <providerId> [ssh-like args...]", description: "Open a Host SSH / WSL SSH maintenance session through the provider-gateway bridge with built-in remote helper tools in PATH." },
+      { command: "ssh <providerId> [ssh-like args...]", description: "Open a Host SSH / WSL SSH maintenance session through the provider-gateway bridge; prefer `ssh <providerId> argv ...` for non-interactive remote commands." },
       { command: "ssh <providerId> apply-patch [tool args...] < patch.diff", description: "Invoke the injected remote apply_patch helper directly over SSH passthrough and stream the patch from local stdin." },
       { command: "ssh <providerId> py [script-args...] < script.py", description: "Run remote Python from local stdin through SSH passthrough without nested shell quoting; extra args become script argv." },
       { command: "ssh <providerId> skills [--scope all|wsl|windows] [--limit N]", description: "Discover WSL/Linux and, for WSL providers, Windows skill directories in one SSH passthrough call." },
       { command: "ssh <providerId> find <path...> [--max-depth N] [--type d|f|l] [--contains TEXT] [--iname PATTERN] [--limit N] [--sort]", description: "Run a structured remote find command without nested shell quoting or parentheses." },
       { command: "ssh <providerId> glob [--root DIR] [--pattern PATTERN] [--contains TEXT] [--type any|f|d] [--limit N] [--sort]", description: "Run remote glob matching through the injected helper without shell glob expansion." },
-      { command: "ssh <providerId> argv <command> [args...]", description: "Run a remote command with each argv token shell-quoted by UniDesk before SSH passthrough." },
+      { command: "ssh <providerId> argv <command> [args...]", description: "Run a non-interactive remote command with each argv token shell-quoted by UniDesk before SSH passthrough; use `argv bash -lc '<command>'` when shell features are required." },
       { command: "microservice list", description: "List UniDesk-managed user services and their provider/runtime mapping." },
       { command: "microservice status <id>", description: "Show one user service config, repository reference, backend mapping, and runtime status." },
       { command: "microservice health <id> [--compact|--raw|--full]", description: "Probe one user service through backend-core -> provider-gateway HTTP proxy; default output is compact, and code-queue uses a commander-safe liveness summary unless raw/full is requested." },
@@ -142,6 +142,7 @@ export function sshHelp(): unknown {
     usage: [
       "bun scripts/cli.ts ssh <providerId>",
       "bun scripts/cli.ts ssh <providerId> argv <command> [args...]",
+      "bun scripts/cli.ts ssh D601 argv bash -lc '<command>'",
       "bun scripts/cli.ts ssh <providerId> apply-patch < patch.diff",
       "bun scripts/cli.ts ssh <providerId> py [script-args...] < script.py",
       "bun scripts/cli.ts ssh <providerId> skills [--scope all|wsl|windows] [--limit N]",
@@ -150,7 +151,8 @@ export function sshHelp(): unknown {
     ],
     notes: [
       "ssh --help and ssh <providerId> --help print this JSON help and never open an interactive session.",
-      "Use argv when nested shell quoting would be fragile.",
+      "For non-interactive remote commands, prefer argv: bun scripts/cli.ts ssh D601 argv bash -lc '<command>'.",
+      "If an ssh-like remote command fails with timeout/kex/exit-255 friction, stderr includes one low-noise UNIDESK_SSH_HINT JSON line with the argv retry command.",
       "Use -- before a remote command that intentionally starts with a dash.",
     ],
   };

scripts/src/remote.ts

@@ -3,7 +3,7 @@ import { type UniDeskConfig } from "./config";
 import { type DebugDispatchCommand, isDebugDispatchCommand } from "./debug";
 import { summarizeMicroserviceHealthResponse, summarizeMicroserviceObservation, summarizeMicroserviceProxyResponse } from "./microservices";
 import { parseNetworkPerfOptions, runNetworkPerf } from "./network-perf";
-import { isSshSkillDiscoveryArgs, parseSshArgs } from "./ssh";
+import { formatSshFailureHint, isSshSkillDiscoveryArgs, parseSshArgs, sshFailureHint } from "./ssh";
 import { codexJudgeQueryAsync, codexOutputQueryAsync, codexPrPreflightQueryAsync, codexQueuesQueryAsync, codexTaskQueryAsync, codexTasksQueryAsync, codexUnreadTriageAsync } from "./code-queue";
 import { runDecisionCenterCommandAsync } from "./decision-center";
 import {
@@ -862,7 +862,10 @@ async function runRemoteSshOverFrontend(session: FrontendSession, providerId: st
   if (stderr.length > 0) process.stderr.write(stderr);
   if (task?.status !== "succeeded") {
     if (stdout.length === 0 && stderr.length === 0) process.stderr.write(`${JSON.stringify({ taskId, task }, null, 2)}\n`);
-    return typeof result.exitCode === "number" ? result.exitCode : 255;
+    const exitCode = typeof result.exitCode === "number" ? result.exitCode : 255;
+    const hint = sshFailureHint(providerId, parsed, exitCode, stderr.length > 0 ? stderr : String(task?.message ?? ""));
+    if (hint !== null) process.stderr.write(formatSshFailureHint(hint));
+    return exitCode;
   }
   return typeof result.exitCode === "number" ? result.exitCode : 0;
 }

scripts/src/ssh.ts

@@ -4,6 +4,20 @@ import { type UniDeskConfig, repoRoot } from "./config";
 export interface ParsedSshArgs {
   remoteCommand: string | null;
   requiresStdin: boolean;
+  invocationKind: SshInvocationKind;
+}
+
+export type SshInvocationKind = "interactive" | "argv" | "helper" | "ssh-like";
+
+export interface SshFailureHint {
+  code: "ssh-like-command-friction";
+  providerId: string;
+  trigger: "timeout-or-kex" | "exit-255";
+  exitCode: number;
+  message: string;
+  try: string;
+  triage: string;
+  note: string;
 }
 
 const argvQuotedSshSubcommands = new Set(["rg", "grep", "sed", "nl", "stat", "du", "ls", "cat", "head", "tail", "wc", "pwd"]);
@@ -479,28 +493,28 @@ export function parseSshArgs(args: string[]): ParsedSshArgs {
   const subcommand = args[0] ?? "";
   if (isSshSkillDiscoveryArgs(args)) {
     const toolArgs = subcommand === "skill" ? ["skill-discover", ...args.slice(2)] : ["skill-discover", ...args.slice(1)];
-    return { remoteCommand: shellArgv(toolArgs), requiresStdin: false };
+    return { remoteCommand: shellArgv(toolArgs), requiresStdin: false, invocationKind: "helper" };
   }
   if (subcommand === "apply-patch" || subcommand === "patch") {
     const toolArgs = ["apply_patch", ...args.slice(1)];
-    return { remoteCommand: shellArgv(toolArgs), requiresStdin: true };
+    return { remoteCommand: shellArgv(toolArgs), requiresStdin: true, invocationKind: "helper" };
   }
   if (subcommand === "py") {
-    return { remoteCommand: buildPythonStdinCommand(args.slice(1)), requiresStdin: true };
+    return { remoteCommand: buildPythonStdinCommand(args.slice(1)), requiresStdin: true, invocationKind: "helper" };
   }
   if (subcommand === "argv" || subcommand === "exec") {
     const toolArgs = args.slice(1);
     if (toolArgs.length === 0) throw new Error(`ssh ${subcommand} requires a command`);
-    return { remoteCommand: shellArgv(toolArgs), requiresStdin: false };
+    return { remoteCommand: shellArgv(toolArgs), requiresStdin: false, invocationKind: "argv" };
   }
   if (subcommand === "find") {
-    return { remoteCommand: buildFindCommand(args.slice(1)), requiresStdin: false };
+    return { remoteCommand: buildFindCommand(args.slice(1)), requiresStdin: false, invocationKind: "helper" };
   }
   if (subcommand === "glob") {
-    return { remoteCommand: shellArgv(["glob", ...args.slice(1)]), requiresStdin: false };
+    return { remoteCommand: shellArgv(["glob", ...args.slice(1)]), requiresStdin: false, invocationKind: "helper" };
   }
   if (argvQuotedSshSubcommands.has(subcommand)) {
-    return { remoteCommand: shellArgv(args), requiresStdin: false };
+    return { remoteCommand: shellArgv(args), requiresStdin: false, invocationKind: "argv" };
   }
   const remote: string[] = [];
   let remoteStarted = false;
@@ -521,7 +535,11 @@ export function parseSshArgs(args: string[]): ParsedSshArgs {
     remoteStarted = true;
     remote.push(arg);
   }
-  return { remoteCommand: remote.length === 0 ? null : remote.join(" "), requiresStdin: false };
+  return {
+    remoteCommand: remote.length === 0 ? null : remote.join(" "),
+    requiresStdin: false,
+    invocationKind: remote.length === 0 ? "interactive" : "ssh-like",
+  };
 }
 
 function shellArgv(args: string[]): string {
@@ -658,6 +676,48 @@ export function wrapSshRemoteCommand(command: string | null): string {
   return `${bootstrap}; stty -echo 2>/dev/null || true; ${command}`;
 }
 
+function safeProviderId(providerId: string): string {
+  return /^[A-Za-z0-9_.-]{1,64}$/u.test(providerId) ? providerId : "<provider>";
+}
+
+function classifySshLikeFailure(exitCode: number, stderrText: string): SshFailureHint["trigger"] | null {
+  const normalized = stderrText.toLowerCase();
+  if (
+    normalized.includes("kex_exchange_identification")
+    || normalized.includes("ssh_exchange_identification")
+    || normalized.includes("connection closed by remote host")
+    || normalized.includes("connection reset by peer")
+    || normalized.includes("connection timed out")
+    || normalized.includes("operation timed out")
+    || normalized.includes("timed out waiting for provider session")
+    || normalized.includes("the operation was aborted")
+  ) {
+    return "timeout-or-kex";
+  }
+  return exitCode === 255 ? "exit-255" : null;
+}
+
+export function sshFailureHint(providerId: string, parsed: ParsedSshArgs, exitCode: number, stderrText: string): SshFailureHint | null {
+  if (parsed.invocationKind !== "ssh-like") return null;
+  const trigger = classifySshLikeFailure(exitCode, stderrText);
+  if (trigger === null) return null;
+  const shownProviderId = safeProviderId(providerId);
+  return {
+    code: "ssh-like-command-friction",
+    providerId: shownProviderId,
+    trigger,
+    exitCode,
+    message: "ssh-like remote command failed before proving Host SSH is globally unavailable; prefer argv form for non-interactive commands.",
+    try: `bun scripts/cli.ts ssh ${shownProviderId} argv bash -lc '<command>'`,
+    triage: `bun scripts/cli.ts provider triage ${shownProviderId} --observed-scope ssh --observed-error '<ssh-like timeout or kex failure>'`,
+    note: "This hint intentionally does not echo the original remote command.",
+  };
+}
+
+export function formatSshFailureHint(hint: SshFailureHint): string {
+  return `UNIDESK_SSH_HINT ${JSON.stringify(hint)}\n`;
+}
+
 function brokerSource(): string {
   return String.raw`
 const open = JSON.parse(process.argv[2] || process.argv[1] || "{}");
@@ -831,8 +891,16 @@ export async function runSsh(config: UniDeskConfig, providerId: string, args: st
   if (rawMode) process.stdin.setRawMode(true);
   process.stdin.resume();
   process.stdin.pipe(child.stdin);
+  let stderrTail = "";
+  const appendStderrTail = (chunk: Buffer | string): void => {
+    const text = Buffer.isBuffer(chunk) ? chunk.toString("utf8") : chunk;
+    stderrTail = (stderrTail + text).slice(-16_384);
+  };
   child.stdout.pipe(process.stdout);
-  child.stderr.pipe(process.stderr);
+  child.stderr.on("data", (chunk: Buffer) => {
+    appendStderrTail(chunk);
+    process.stderr.write(chunk);
+  });
 
   return await new Promise<number>((resolve) => {
     const restore = (): void => {
@@ -841,12 +909,19 @@ export async function runSsh(config: UniDeskConfig, providerId: string, args: st
     };
     child.on("error", (error) => {
       restore();
-      process.stderr.write(`unidesk ssh failed to start broker: ${error.message}\n`);
+      const message = `unidesk ssh failed to start broker: ${error.message}\n`;
+      appendStderrTail(message);
+      process.stderr.write(message);
+      const hint = sshFailureHint(providerId, parsed, 255, stderrTail);
+      if (hint !== null) process.stderr.write(formatSshFailureHint(hint));
       resolve(255);
     });
     child.on("close", (code) => {
       restore();
-      resolve(code ?? 255);
+      const exitCode = code ?? 255;
+      const hint = sshFailureHint(providerId, parsed, exitCode, stderrTail);
+      if (hint !== null) process.stderr.write(formatSshFailureHint(hint));
+      resolve(exitCode);
     });
   });
 }

scripts/ssh-argv-guidance-contract-test.ts

@@ -0,0 +1,54 @@
+import { sshHelp } from "./src/help";
+import { providerTriageRecommendedCrossChecks } from "./src/provider-triage";
+import { formatSshFailureHint, parseSshArgs, sshFailureHint } from "./src/ssh";
+
+type JsonRecord = Record<string, unknown>;
+
+function assertCondition(condition: unknown, message: string, detail: unknown = {}): void {
+  if (!condition) throw new Error(`${message}: ${JSON.stringify(detail)}`);
+}
+
+export function runSshArgvGuidanceContract(): JsonRecord {
+  const argv = parseSshArgs(["argv", "bash", "-lc", "echo ok"]);
+  assertCondition(argv.invocationKind === "argv", "argv subcommand must be classified as argv", argv);
+  assertCondition(argv.remoteCommand === "'bash' '-lc' 'echo ok'", "argv command must shell-quote each token", argv);
+  assertCondition(argv.requiresStdin === false, "argv command must not require stdin", argv);
+  assertCondition(sshFailureHint("D601", argv, 255, "kex_exchange_identification: Connection closed by remote host") === null, "argv failures must not produce ssh-like friction hint", argv);
+
+  const shortcut = parseSshArgs(["pwd"]);
+  assertCondition(shortcut.invocationKind === "argv", "safe command shortcuts must use argv quoting", shortcut);
+  assertCondition(shortcut.remoteCommand === "'pwd'", "safe command shortcut should be shell-quoted", shortcut);
+
+  const sshLike = parseSshArgs(["echo hello"]);
+  const hint = sshFailureHint("D601", sshLike, 255, "kex_exchange_identification: Connection closed by remote host");
+  assertCondition(hint !== null, "ssh-like kex failure must produce a hint", sshLike);
+  assertCondition(hint?.try === "bun scripts/cli.ts ssh D601 argv bash -lc '<command>'", "hint must provide canonical argv retry", hint);
+  assertCondition(hint?.triage.includes("provider triage D601"), "hint must provide provider triage command", hint);
+  const formatted = formatSshFailureHint(hint!);
+  assertCondition(formatted.startsWith("UNIDESK_SSH_HINT "), "formatted hint must have structured prefix", formatted);
+  assertCondition(!formatted.includes("echo hello"), "formatted hint must not echo the original remote command", formatted);
+
+  const timeoutHint = sshFailureHint("D601", sshLike, 255, "unidesk ssh bridge timed out waiting for provider session");
+  assertCondition(timeoutHint?.trigger === "timeout-or-kex", "provider session timeout must map to timeout-or-kex", timeoutHint);
+
+  const helpText = JSON.stringify(sshHelp());
+  assertCondition(helpText.includes("ssh D601 argv bash -lc '<command>'"), "ssh help must recommend argv bash -lc for non-interactive commands", helpText);
+  assertCondition(helpText.includes("UNIDESK_SSH_HINT"), "ssh help must document structured failure hint", helpText);
+
+  const crossChecks = providerTriageRecommendedCrossChecks("D601");
+  assertCondition(crossChecks.includes("bun scripts/cli.ts ssh D601 argv true"), "provider triage cross-checks must keep argv true", crossChecks);
+
+  return {
+    ok: true,
+    checks: [
+      "argv form is classified and quoted as the success path for non-interactive commands",
+      "ssh-like timeout/kex failures emit one structured argv retry hint",
+      "help text documents argv bash -lc and UNIDESK_SSH_HINT",
+      "provider triage recommendedCrossChecks keeps ssh D601 argv true",
+    ],
+  };
+}
+
+if (import.meta.main) {
+  process.stdout.write(`${JSON.stringify(runSshArgvGuidanceContract(), null, 2)}\n`);
+}