@rosthq/cli 0.5.8 → 0.5.9

package/dist/index.js

@@ -41785,11 +41785,11 @@ Drafting can be assisted by agents. Activation is a human decision. When authori
     order: 40,
     title: "Agent staffing playbook",
     summary: "How to decide whether a seat should be human, agent, or hybrid, and how to go live safely.",
-    version: "2026-06-19.1",
+    version: "2026-06-19.2",
     public: true,
     audiences: ["human", "cli", "mcp", "in_app_agent"],
     stages: ["staffing"],
-    relatedCommandIds: ["staffing.assign_user", "staffing.assign_agent_dry_run", "agent.go_live", "agent.status", "agent.run_now", "agent.list_runs", "agent.list_tool_calls", "mcp_token.create", "agent_template.list", "agent.create_from_template", "agent_setup.start", "agent_setup.get", "agent_setup.update", "agent.update_schedule", "agent.decommission", "agent.create_custom", "agent.configure_tools", "agent.run_dry_run", "confirmation.approve"],
+    relatedCommandIds: ["staffing.assign_user", "staffing.assign_agent_dry_run", "agent.go_live", "agent.status", "agent.run_now", "agent.get_run", "agent.list_runs", "agent.list_tool_calls", "mcp_token.create", "agent_template.list", "agent.create_from_template", "agent_setup.start", "agent_setup.get", "agent_setup.update", "agent.update_schedule", "agent.decommission", "agent.create_custom", "agent.configure_tools", "agent.run_dry_run", "confirmation.approve"],
     legal: {
       publicRisk: "low",
       notes: [
@@ -41844,7 +41844,7 @@ Two creation paths, both draft-first. Read the stock-agents guide for templates
 - Custom: \`agent_setup.start\` / \`rost_start_agent_setup\` (returns a \`setup_id\`), iterate with \`agent_setup.get\` and \`agent_setup.update\`, then \`agent.create_custom\` / \`rost_create_custom_agent\`. Stage tools with \`agent.configure_tools\` (vault refs only) and sandbox with \`agent.run_dry_run\`.
 - Inspect runtime: \`agent.status\` / \`rost_get_agent_status\` with \`{"seat_id":"<seat-id>"}\` returns lane, live state, steward chain, dry-run result, and Runner availability.
 - Run on demand: \`{{cli}} agent run-now --seat-id <seat-id>\` / \`agent.run_now\` / \`rost_run_agent_now\` queues an immediate live run without changing the saved schedule. Cloud agents dispatch to the Inngest executor; runner agents queue work for the paired runner. The command is ungated but still requires a live staffed agent and the normal server-side tool guard.
-- Audit what an agent did (Trust Card): \`{{cli}} command agent.list_runs --json '{"seat_id":"<seat-id>"}'\` / \`rost_list_agent_runs\` returns the seat's run history with per-run tool-call and guard-held counts; \`{{cli}} command agent.list_tool_calls --json '{"seat_id":"<seat-id>"}'\` / \`rost_list_agent_tool_calls\` returns the tool-call ledger with each call's guard result. Both include a \`denied_tool_call_count\` rollup \u2014 the actions held because they exceeded the charter. Pass \`{"seat_id":"<seat-id>","held_only":true}\` to \`agent.list_tool_calls\` for only the held calls. The web seat page shows the same facts as a Trust Card.
+- Audit what an agent did (Trust Card): \`{{cli}} command agent.list_runs --json '{"seat_id":"<seat-id>"}'\` / \`rost_list_agent_runs\` returns the seat's run history with per-run tool-call and guard-held counts; \`{{cli}} agent get-run --seat-id <seat-id> --run-id <run-id>\` / \`agent.get_run\` / \`rost_get_agent_run_diagnostics\` reads one run's transcript reference, token/cost usage, outcome, and product-visible run errors; \`{{cli}} command agent.list_tool_calls --json '{"seat_id":"<seat-id>"}'\` / \`rost_list_agent_tool_calls\` returns the tool-call ledger with each call's guard result. Both list commands include a \`denied_tool_call_count\` rollup \u2014 the actions held because they exceeded the charter. Pass \`{"seat_id":"<seat-id>","held_only":true}\` to \`agent.list_tool_calls\` for only the held calls. The web seat page shows the same facts as a Trust Card.
 
 ## When to stop for confirmation
 
@@ -42084,7 +42084,7 @@ Decisions should be recorded as human decisions. Handoffs should attach to seats
     order: 45,
     title: "How agents work",
     summary: "How {{brand}} agents operate inside seats, use Charters, report work, and escalate beyond authority.",
-    version: "2026-06-19.4",
+    version: "2026-06-19.6",
     public: true,
     audiences: ["human", "cli", "mcp", "in_app_agent"],
     stages: ["staffing", "operating_rhythm"],
@@ -42167,11 +42167,13 @@ The model is only ever offered the tools the seat's manifest grants \u2014 a den
 3. The action runs bound to the seat's vaulted credential. The secret stays inside the call and never reaches the result, the audit row, the logs, or the model.
 4. Every call \u2014 allowed, denied, escalated, or invalid \u2014 writes a tool-call audit row you can review.
 
+Provider requests carry only the model payload the runtime needs; run attribution, tenant attribution, usage, and cost are recorded in {{brand}} audit tables after the call, not sent as custom provider metadata.
+
 Before an agent goes live, the sandbox dry run rehearses this against fake data and returns a per-tool preview: for each tool the agent would touch, whether it would run it, would be blocked, or would escalate \u2014 no external side effect. Review that preview before you approve go-live.
 
 ## What humans should review
 
-Review the first dry runs, fleet overview, tool-call audit rows, escalations, and Signal impact. The fleet view at \`/agents\` shows every staffed agent seat at a glance; the agent-native equivalent is \`{{cli}} command agent.list_fleet --json '{}'\` / \`rost_list_agent_fleet\`, which returns lane, live state, last real turn, 24h/7d real turns, top measurable status, open escalations, and 7-day spend. Sandbox dry runs do not count as real turns. If the agent is repeatedly blocked, revise the Charter or split the seat. If the agent is taking too much judgment, narrow its autonomous scope.`
+Review the first dry runs, fleet overview, tool-call audit rows, escalations, and Signal impact. The fleet view at \`/agents\` shows every staffed agent seat at a glance; the agent-native equivalent is \`{{cli}} command agent.list_fleet --json '{}'\` / \`rost_list_agent_fleet\`, which returns lane, live state, last real turn, 24h/7d real turns, top measurable status, open escalations, and 7-day spend. Scheduled agents are checked in rounded five-minute buckets, so a minute-level cron inside the bucket queues one work order for that bucket rather than one order per minute. Sandbox dry runs do not count as real turns. If the agent is repeatedly blocked, revise the Charter or split the seat. If the agent is taking too much judgment, narrow its autonomous scope.`
   },
   {
     slug: "tool-access-and-vault",
@@ -42299,7 +42301,7 @@ External connectors (such as email, drive, or a generic API) are being rolled ou
     order: 48,
     title: "CLI and MCP installation guide",
     summary: "Install the public CLI, register remote token-backed MCP clients, and find the full command and tool catalog.",
-    version: "2026-06-19.3",
+    version: "2026-06-19.4",
     public: true,
     audiences: ["human", "cli", "mcp", "in_app_agent"],
     stages: ["company_setup", "staffing"],
@@ -42335,6 +42337,7 @@ External connectors (such as email, drive, or a generic API) are being rolled ou
       "agent.go_live",
       "agent.status",
       "agent.list_fleet",
+      "agent.get_run",
       "agent.list_runs",
       "agent.list_tool_calls"
     ],
@@ -42709,10 +42712,10 @@ These ergonomic wrappers (including the \`{{cli}} agent\` group) require **{{cli
 | \`{{cli}} escalation list|get|resolve|reject\` | \`escalation.list\`, \`escalation.get\`, \`escalation.resolve\`, \`escalation.reject\` | Work the steward escalation queue. | Steward | \`{{cli}} escalation list --json\` |
 | \`{{cli}} sync brief|compile|complete\` | \`sync.brief.get\`, \`sync.brief.compile\`, \`sync.run.complete\` | Compile, read, and complete a weekly Sync. | Tenant | \`{{cli}} sync brief --json\` |
 | \`{{cli}} runner list|status|work-orders|revoke\` | \`runner.list\`, \`runner.status\`, \`work_order.list\`, \`runner.revoke\` | Inspect runners and work orders; revoke a runner. | Tenant | \`{{cli}} runner list --json\` |
-| \`{{cli}} notification settings|test\` | \`notification.settings.get\`, \`notification.test\` | Read notification settings; send a test. | Tenant | \`{{cli}} notification settings --json\` |
+| \`{{cli}} notification settings|test|errors\` | \`notification.settings.get\`, \`notification.test\`, \`notification.list_errors\` | Read notification settings, send a test, and list failed deliveries with linked product error source, seat id, and run id when available. | Tenant | \`{{cli}} notification errors --limit 10 --json\` |
 | \`{{cli}} settings get|update\` | \`settings.get\`, \`settings.update\` | Read tenant settings; update budget caps. | Tenant | \`{{cli}} settings get --json\` |
 | \`{{cli}} member invite|update|remove\` | \`member.invite\`, \`member.update\`, \`member.remove\` | Manage tenant members. | Tenant | \`{{cli}} member invite --email ops@example.com --role member\` |
-| \`{{cli}} agent templates|create|setup|tools|dry-run|go-live|status|run-now|show\` | \`agent_template.list\`, \`agent.create_from_template\`, \`agent.create_custom\`, \`agent_setup.get\`, \`agent_setup.update\`, \`agent.configure_tools\`, \`agent.run_dry_run\`, \`agent.go_live\`, \`agent.status\`, \`agent.run_now\`, \`agent.show_markdown\` | Run the full agent setup and operation flow: list templates, create a draft from a template or guided custom answers (with \`--model\` and \`--effort\`), read or answer setup state, connect or decline tools, dry-run, go live, run on demand, and show a markdown readout. Create and go-live stop at human gates; the dry-run is ungated by human approval but requires a signed manifest first. | Tenant and seat | \`{{cli}} agent templates --json\` |
+| \`{{cli}} agent templates|create|setup|tools|dry-run|go-live|status|run-now|get-run|show\` | \`agent_template.list\`, \`agent.create_from_template\`, \`agent.create_custom\`, \`agent_setup.get\`, \`agent_setup.update\`, \`agent.configure_tools\`, \`agent.run_dry_run\`, \`agent.go_live\`, \`agent.status\`, \`agent.run_now\`, \`agent.get_run\`, \`agent.show_markdown\` | Run the full agent setup and operation flow: list templates, create a draft from a template or guided custom answers (with \`--model\` and \`--effort\`), read or answer setup state, connect or decline tools, dry-run, go live, run on demand, read one run's transcript/error diagnostics, and show a markdown readout. Create and go-live stop at human gates; the dry-run is ungated by human approval but requires a signed manifest first. | Tenant and seat | \`{{cli}} agent get-run --seat-id <seat-id> --run-id <run-id> --json\` |
 | \`{{cli}} tools list\` | \`tool.catalog\` | List the discoverable tool catalog the builder reads (id, scope tiers, credential requirement, access policy). Configuration only; the tools do not execute yet. | Tenant | \`{{cli}} tools list --json\` |
 | \`{{cli}} compass show\` | \`compass.show_markdown\` | Render the current Compass as a clean markdown card for review. | Tenant | \`{{cli}} compass show --markdown\` |
 | \`{{cli}} charter show\` | \`charter.show_markdown\` | Render a seat's Charter as a clean markdown card for review. | Tenant | \`{{cli}} charter show --seat-id <id> --markdown\` |
@@ -42812,6 +42815,7 @@ Several rows here are seat-operating commands (\`task.create\`, the \`signal.*\`
 | \`rost_list_agent_fleet\` | \`agent.list_fleet\` | Read every staffed agent seat at once: lane, live state, last real turn, 24h/7d real turns, measurable status, escalations, and 7-day spend. | Tenant | Call with \`{}\`; sandbox dry runs are excluded from real turns. |
 | \`rost_run_agent_now\` | \`agent.run_now\` | Queue an immediate run for a live staffed agent without changing its saved schedule; cloud lane dispatches to the executor and runner lane queues for the paired runner. | Tenant | Call with \`{"seat_id":"<seat-id>"}\`. |
 | \`rost_list_agent_runs\` | \`agent.list_runs\` | Read a seat's agent run history (status, lane, model, cost, per-run tool-call and guard-held counts) plus the seat's run/tool-call rollup including held-action count. | Seat or tenant-admin | Call with \`{"seat_id":"<seat-id>"}\`; pass \`limit\` for a deeper window. |
+| \`rost_get_agent_run_diagnostics\` | \`agent.get_run\` | Read one run's diagnostic record: transcript reference, token/cost usage, outcome, and linked product-visible run errors. | Seat or tenant-admin | Call with \`{"seat_id":"<seat-id>","run_id":"<run-id>"}\`. |
 | \`rost_list_agent_tool_calls\` | \`agent.list_tool_calls\` | Read a seat's tool-call ledger (tool name, guard result, manifest clause, outcome) with the held-action count as the hero metric. Never returns argument summaries or secret material. | Seat or tenant-admin | Call with \`{"seat_id":"<seat-id>"}\`; pass \`held_only: true\` for only guard-held calls. |
 | \`rost_list_agent_templates\` | \`agent_template.list\` | List stock agent templates and metadata. | Tenant | Call with \`{}\`. |
 | \`rost_create_agent_from_template\` | \`agent.create_from_template\` | Create a draft stock agent and draft Charter from a template (draft-only; occupancy needs a human steward). | Tenant | Call with \`seat_id\` and \`template_slug\`; expect human confirmation. |
@@ -42836,7 +42840,7 @@ Several rows here are seat-operating commands (\`task.create\`, the \`signal.*\`
 | \`rost_get_notification_settings\` | \`notification.settings.get\` | Read tenant notification preferences. | Tenant | Call with \`{}\`. |
 | \`rost_update_notification_settings\` | \`notification.settings.update\` | Update tenant notification preferences. | Tenant | Call with the fields to change. |
 | \`rost_send_test_notification\` | \`notification.test\` | Emit an in-app test notification to the acting human. | Tenant | Call with \`{}\`. |
-| \`rost_list_notification_errors\` | \`notification.list_errors\` | List recent failed notification deliveries. | Tenant | Call with optional \`limit\`. |
+| \`rost_list_notification_errors\` | \`notification.list_errors\` | List recent failed notification deliveries with linked \`error_log_id\`, source, seat id, and run id when available. | Tenant | Call with optional \`limit\`; \`source=run\` rows can be followed with \`agent.get_run\`. |
 | \`rost_invite_member\` | \`member.invite\` | Create a pending tenant invite for a human teammate. | Tenant | Call with \`email\` and \`role\`. |
 | \`rost_update_member_role\` | \`member.update\` | Change a tenant member's role. | Tenant | Call with \`member_id\` and \`role\`; expect human confirmation. |
 | \`rost_remove_member\` | \`member.remove\` | Remove a tenant member. | Tenant | Call with \`member_id\`; blocked if it would orphan an agent steward chain. |
@@ -43453,7 +43457,7 @@ When a user asks to add a person, clarify whether they mean app access, seat occ
     order: 74,
     title: "Notifications guide",
     summary: "How {{brand}} should notify humans about decisions, escalations, stale work, and agent boundaries.",
-    version: "2026-06-13.1",
+    version: "2026-06-19.1",
     public: true,
     audiences: ["human", "cli", "mcp", "in_app_agent"],
     stages: ["operating_rhythm"],
@@ -43478,6 +43482,10 @@ Notifications should move decisions to the right human without turning {{brand}}
 - A Friction item needs a decision.
 - A Sync decision creates a handoff.
 
+## Diagnose failed deliveries
+
+\`{{cli}} notification errors --limit 10\` / \`notification.list_errors\` / \`rost_list_notification_errors\` returns recent failed deliveries. When a failed notification links to a product error, it includes \`error_log_id\`, \`source\`, and any linked \`seat_id\` / \`run_id\`; \`source=run\` means the notification is tied to an agent run and can be followed with \`agent.get_run\` for the transcript reference and run errors.
+
 ## Keep notifications useful
 
 Every notification should include the seat, cause, evidence, and requested decision. Avoid status-only messages when no action is needed.`
@@ -45004,6 +45012,17 @@ function optionalValue(parsed, key) {
   const value = parsed.values.get(key);
   return value === void 0 || value.length === 0 ? void 0 : value;
 }
+function optionalNumber(parsed, key) {
+  const raw = optionalValue(parsed, key);
+  if (raw === void 0) {
+    return void 0;
+  }
+  const parsedNumber = Number(raw);
+  if (!Number.isSafeInteger(parsedNumber)) {
+    throw new UsageError(`--${key} must be an integer.`);
+  }
+  return parsedNumber;
+}
 function parseNumber(parsed, key, options) {
   const raw = parsed.values.get(key);
   if (raw === void 0 || raw.length === 0) {
@@ -45606,12 +45625,27 @@ var notificationWrapper = (context, args) => dispatch(context, "notification", a
       const record2 = asRecord(output);
       return `Test notification ${field(record2, "notification_id")} (delivered=${field(record2, "delivered")}).`;
     });
+  },
+  errors: (ctx, rest) => {
+    const parsed = parseFlags(rest);
+    const body = withOptional({}, { limit: optionalNumber(parsed, "limit") });
+    return execute(ctx, parsed, "notification.list_errors", body, (output) => {
+      const errors = asArray(asRecord(output).errors);
+      if (errors.length === 0) {
+        return "No failed notification deliveries.";
+      }
+      return errors.map((entry) => {
+        const record2 = asRecord(entry);
+        return `${field(record2, "created_at")}  ${field(record2, "channel")}  source=${field(record2, "source")}  seat=${field(record2, "seat_id")}  run=${field(record2, "run_id")}  ${field(record2, "error_message")}`;
+      }).join("\n");
+    });
   }
 }, notificationUsage(context.binName));
 function notificationUsage(bin) {
-  return `Usage: ${bin} notification settings|test [--json]
+  return `Usage: ${bin} notification settings|test|errors [--json]
   ${bin} notification settings
-  ${bin} notification test`;
+  ${bin} notification test
+  ${bin} notification errors [--limit <n>]`;
 }
 var settingsWrapper = (context, args) => dispatch(context, "settings", args, {
   get: (ctx, rest) => {
@@ -45812,6 +45846,21 @@ ${field(record2, "summary")}`;
       return `queued ${field(workOrder, "lane")} work order ${field(workOrder, "id")} for agent ${field(workOrder, "agent_id")} (${field(workOrder, "status")})`;
     });
   },
+  "get-run": (ctx, rest) => {
+    const parsed = parseFlags(rest);
+    const body = {
+      seat_id: requireValue2(parsed, "seat-id"),
+      run_id: requireValue2(parsed, "run-id")
+    };
+    return execute(ctx, parsed, "agent.get_run", body, (output) => {
+      const run2 = asRecord(asRecord(output).run);
+      const errors = asArray(run2.error_logs);
+      const errorLine = errors.length === 0 ? "errors=0" : `errors=${errors.length} first=${field(asRecord(errors[0]), "message")}`;
+      return `run ${field(run2, "run_id")}  status=${field(run2, "status")}  lane=${field(run2, "lane")}  cost=$${field(run2, "cost_usd")}
+transcript=${field(run2, "transcript_ref")}
+${errorLine}`;
+    });
+  },
   // DER-787 (H8): markdown readout for a seat's agent setup. `--markdown` (or
   // default) prints the composed card; `--json` returns the { markdown } object.
   show: (ctx, rest) => {
@@ -45838,7 +45887,7 @@ function agentConfigureTools(ctx, rest, decision) {
   });
 }
 function agentUsage(bin) {
-  return `Usage: ${bin} agent templates|create|setup|tools|dry-run|go-live|status|run-now|show [--json]
+  return `Usage: ${bin} agent templates|create|setup|tools|dry-run|go-live|status|run-now|get-run|show [--json]
   ${bin} agent templates
   ${bin} agent create --seat-id <id> --template <slug> [--expected-version <v>]
   ${bin} agent create --seat-id <id> --custom [--steward-seat-id <id>] [--lane cloud|mcp_session|runner] [--model triage|balanced|complex|hardest|<id>] [--effort low|medium|high|xhigh|max] [--owns <text>] [--success <text>] [--never-alone <text>]
@@ -45849,6 +45898,7 @@ function agentUsage(bin) {
   ${bin} agent go-live --seat-id <id> --charter-version-id <id>
   ${bin} agent status --seat-id <id>
   ${bin} agent run-now --seat-id <id> [--task-id <id>]
+  ${bin} agent get-run --seat-id <id> --run-id <id>
   ${bin} agent show --seat-id <id> [--markdown]`;
 }
 function agentSetupUsage(bin) {
@@ -45987,10 +46037,10 @@ function operationUsageLines(bin) {
     `${bin} escalation list|get|resolve|reject`,
     `${bin} sync brief|compile|complete`,
     `${bin} runner list|status|work-orders|revoke`,
-    `${bin} notification settings|test`,
+    `${bin} notification settings|test|errors`,
     `${bin} settings get|update`,
     `${bin} member invite|update|remove`,
-    `${bin} agent templates|create|setup|tools|dry-run|go-live|status|run-now|show`,
+    `${bin} agent templates|create|setup|tools|dry-run|go-live|status|run-now|get-run|show`,
     `${bin} tools list`,
     `${bin} compass show`,
     `${bin} charter show`