@rosthq/cli 0.6.7 → 0.6.8

package/dist/index.js

@@ -42157,7 +42157,7 @@ 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: "2026-06-30.1",
+    version: "2026-07-02.1",
     public: true,
     audiences: ["human", "cli", "mcp", "in_app_agent"],
     stages: ["staffing", "operating_rhythm"],
@@ -42255,7 +42255,7 @@ Beyond each seat's own manifest, the company can set one ceiling on how much an
 
 ## What humans should review
 
-The Agents page shows fleet health first: live state, work evidence, failed runs, open held actions, cost, and the next operator action. Work evidence distinguishes fresh real runs, stale runs, no completed run yet, queued or running work orders, and recent failures. A failure link opens the failed run itself; queued or stale rows route the operator to the seat's agent operations instead of pretending there is a hidden run to inspect. The page also shows configuration completeness for each staffed agent seat: Steward chain, lane or runtime substrate, vaulted credentials, granted tools, model config, sandbox dry run, and go-live state, each with a remediation link when incomplete. A seat's Trust Card drills into the same facts: run history, one-run detail, tool-call outcomes, product-visible errors, transcript references, loaded Skill versions, and held confirmations or escalations. Open confirmations stay visible until they are decided or expire, even when they are older than the default activity window. Approving or rejecting a held confirmation from the seat page is scoped to that seat; rejection can include a short reason. For a live agent, the seat page's agent operations panel can queue one immediate governed run through the same \`agent.run_now\` command path used by CLI and MCP; it does not expand authority or change the saved schedule.
+The Agents page shows fleet health first: live state, work evidence, failed runs, open held actions, cost, and the next operator action. Work evidence distinguishes fresh real runs, stale runs, no completed run yet, queued or running work orders, and recent failures. A failure link opens the failed run itself; queued or stale rows route the operator to the seat's agent operations instead of pretending there is a hidden run to inspect. The page also shows configuration completeness for each staffed agent seat: Steward chain, lane or runtime substrate, vaulted credentials, granted tools, model config, sandbox dry run, and go-live state, each with a remediation link when incomplete. A seat's Trust Card drills into the same facts: run history, one-run detail, tool-call outcomes, product-visible errors, transcript references, loaded Skill versions, and held confirmations or escalations. Open confirmations stay visible until they are decided or expire, even when they are older than the default activity window. Approving or rejecting a held confirmation from the seat page is scoped to that seat; rejection can include a short reason. For a live agent, the seat page's agent operations panel can queue one immediate governed run through the same \`agent.run_now\` command path used by CLI and MCP; it does not expand authority or change the saved schedule. Seat pages render legacy Charter manifest scope text with customer-safe labels when old setup data used internal placeholder wording.
 
 Review the first dry runs, fleet overview, tool-call audit rows, escalations, deliverables, and Signal impact. A seat's completed-work area combines explicit deliverables, work-log evidence, and successful run summaries into one operator-facing trail with safe links labelled as internal, Linear, GitHub, or external. The fleet view at \`/agents\` shows every staffed agent seat at a glance; the agent-native equivalents are \`{{cli}} command agent.list_fleet --json '{}'\` / \`rost_list_agent_fleet\` for the compact overview, and \`{{cli}} agent fleet-digest --json\` / \`agent.fleet_digest\` / \`rost_get_dogfood_fleet_health_digest\` for the daily dogfood evidence bundle. The digest returns live/idle state, 24h/7d turns, 7d/30d spend, recent failed runs, unresolved product errors, failed notifications, and a next action per seat.
 
@@ -42310,7 +42310,7 @@ Connecting a tool is a human-controlled step. The agent can recommend a tool, ex
 
 ## Generic REST connector
 
-For an API with no dedicated connector, the generic REST tool lets a seat read an HTTPS endpoint with a credential you paste through the vault \u2014 no {{brand}}-owned app. The agent-facing tool is GET-only. It is escalate-by-default: the agent may only call a host and explicit path prefix a steward has signed onto the allowlist; any other host or path is refused and escalated, with no request made. Mutating methods and request bodies fail before credential binding. A path prefix of \`/\` means the steward intentionally approved every path. The connector sets the Authorization header from the vaulted credential itself \u2014 the agent never sees the token, and the secret is redacted from the response before it reaches the agent, the audit row, or the logs. The token is only ever sent over HTTPS, only to the signed host and scoped path, and a redirect is never followed \u2014 so an allowlisted endpoint cannot bounce the call (and the token) to another host. A sandbox dry run of a REST tool makes no real request.
+For an API with no dedicated connector, the generic REST tool lets a seat read an HTTPS endpoint with a credential you paste through the vault \u2014 no {{brand}}-owned app. The agent-facing tool is GET-only. It is escalate-by-default: the agent may only call a host and explicit path prefix a steward has signed onto the allowlist; any other host or path is refused and escalated, with no request made. Mutating methods and request bodies fail before credential binding. A path prefix of \`/\` means the steward intentionally approved every path. The connector sets the Authorization header from the vaulted credential itself \u2014 the agent never sees the token, and the secret is redacted from the response before it reaches the agent, the audit row, or the logs. The token is only ever sent over HTTPS, only to the signed host and scoped path, and a redirect is never followed \u2014 so an allowlisted endpoint cannot bounce the call (and the token) to another host. Signal-source pulls also resolve the host at execution time, reject private or reserved addresses, and pin the outbound socket to the validated address so DNS rebinding cannot move the request after approval. A sandbox dry run of a REST tool makes no real request.
 
 ## Slack post connector
 
@@ -42359,7 +42359,7 @@ There is exactly one way to give a connected tool its credential, and it is the
     order: 47,
     title: "Available tools guide",
     summary: "How to think about tool categories available to seats and what each category should be used for.",
-    version: "2026-07-02.1",
+    version: "2026-06-30.1",
     public: true,
     audiences: ["human", "cli", "mcp", "in_app_agent"],
     stages: ["staffing"],
@@ -42412,7 +42412,7 @@ External connectors are being rolled out provider by provider, conservatively (r
     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: "2026-07-02.3",
+    version: "2026-07-02.5",
     public: true,
     audiences: ["human", "cli", "mcp", "in_app_agent"],
     stages: ["company_setup", "staffing"],
@@ -42874,7 +42874,7 @@ The signed-in app exposes the same Skill command surface under **Skills** in the
 | \`{{cli}} system health\` | \`system.health\` | Read the scoped system-health snapshot across agent runs, unresolved errors, Signals, Cascade setup, work loop, integrations, runners, notifications, and Sync Brief readiness. | Tenant, member, or seat token | \`{{cli}} system health --json\`; \`{{cli}} system health --seat <id> --json\` |
 | \`{{cli}} command usage.report|usage.snapshot\` | \`usage.report\`, \`usage.snapshot\` | Read the AI-workforce ROI report (per-period agent turns, token/run cost, human-accepted value, exceptions, approvals) from immutable usage snapshots, and freeze a period's totals into a new snapshot (insert-only, idempotent). | Tenant | \`{{cli}} command usage.report --json\`; \`{{cli}} command usage.snapshot --json\` |
 | \`{{cli}} settings get|update|product-learning|agent-policy|rename\` | \`settings.get\`, \`settings.update\`, \`settings.product_learning.get\`, \`settings.product_learning.update\`, \`settings.agent_policy.get\`, \`settings.agent_policy.update\`, \`tenant.rename\` | Read tenant settings, update budget caps, read or update product-learning participation, read or set the company autonomy ceiling, and rename the company. Budget, product-learning, and policy updates stop at human confirmation in non-interactive CLI/MCP sessions; company rename is owner-only and human-gated. | Tenant / Tenant-admin for updates | \`{{cli}} settings product-learning get --json\`; \`{{cli}} settings agent-policy get --json\`; \`{{cli}} settings rename --company "Acme Operations"\` |
-| \`{{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}} member invite|update|remove\` | \`member.invite\`, \`member.update\`, \`member.remove\` | Manage tenant members; execution requires an owner or admin membership. | Tenant | \`{{cli}} member invite --email ops@example.com --role member\` |
 | \`{{cli}} agent templates|create|setup|tools|dry-run|go-live|status|run-now|fleet-digest|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.fleet_digest\`, \`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, capture the fleet-health digest, read one run's transcript/error diagnostics, and show a markdown readout. Human CLI dry-runs print the rehearsal transcript and, when present, the per-tool preview labels (\`Would run\`, \`Blocked\`, \`Escalated\`) before go-live. 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 fleet-digest --json\` |
 | \`{{cli}} tools list\` | \`tool.catalog\` | List the discoverable tool catalog the builder reads (id, scope tiers, credential requirement, access policy, and execution-boundary guidance). | Tenant | \`{{cli}} tools list --json\` |
 | \`{{cli}} skills list|get|file|assigned|check-dependencies\` | \`skill.list\`, \`skill.get\`, \`skill.file.get\`, \`skill.assigned.list\`, \`skill.check_dependencies\` | Discover reusable Skills, read descriptors and stored package files, list approved Seat assignments, and compare required/optional tool dependencies with a Seat's signed Charter manifest. Skills are instructions, not authority. | Tenant-admin; seat-scoped reads for assigned Skills | \`{{cli}} skills list --json\`; \`{{cli}} skills file --slug invoice-review --path SKILL.md\` |
@@ -43046,9 +43046,9 @@ Several rows here are seat-operating commands (\`task.create\`, the \`signal.*\`
 | \`rost_check_integration_readiness\` | \`integration.readiness\` | Return the connector setup checklist: OAuth env/callback, tenant connection, scopes, latest test state, external verification/CASA, handler availability, and DER-coded next actions. | Tenant | Call with \`{"provider":"google"}\`; metadata only, no secrets or vault refs. |
 | \`rost_get_integration_status\` | \`integration.status\` | Read one integration's metadata by provider or integration id. | Tenant | Call with \`{"provider":"google"}\` or \`{"integration_id":"<id>"}\`. |
 | \`rost_test_integration_connection\` | \`integration.test\` | Run the provider-specific connection test and update integration health. | Tenant | Call with \`{"provider":"google"}\`; result is bounded metadata only. |
-| \`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. |
+| \`rost_invite_member\` | \`member.invite\` | Create a pending tenant invite for a human teammate. | Tenant | Owner/admin only; call with \`email\` and \`role\`. |
+| \`rost_update_member_role\` | \`member.update\` | Change a tenant member's role. | Tenant | Owner/admin only; call with \`member_id\` and \`role\`; expect human confirmation. |
+| \`rost_remove_member\` | \`member.remove\` | Remove a tenant member. | Tenant | Owner/admin only; call with \`member_id\`; blocked if it would orphan an agent steward chain. |
 | \`rost_get_tenant_settings\` | \`settings.get\` | Read tenant operating settings and integration status. | Tenant | Call with \`{}\`; metadata only. |
 | \`rost_update_tenant_settings\` | \`settings.update\` | Update tenant AI budget caps. | Tenant | Call with \`soft_cap_usd\` or \`hard_cap_usd\`; expect human confirmation. |
 | \`rost_rename_company\` | \`tenant.rename\` | Rename the current company. | Tenant-admin | Call with \`company_name\`; expect human confirmation. |
@@ -43700,7 +43700,7 @@ Agents can suggest commitments and report progress. They should not create a new
     order: 61,
     title: "Signal guide",
     summary: "How to define and read measurables so the company runs on evidence instead of status theater.",
-    version: "2026-07-02.3",
+    version: "2026-07-02.4",
     public: true,
     audiences: ["human", "cli", "mcp", "in_app_agent"],
     stages: ["operating_rhythm"],
@@ -43784,12 +43784,14 @@ Once a measurable's number lives in a connected system, you can teach {{brand}}
 - \`signal.bind\` persists the validated recipe as an inert \`draft\` binding. It requires the \`preview_token\` from a preview of the same recipe, so nothing is bound that was not first seen working.
 - \`signal.bind_confirm\` is human-only. It activates the binding (\`draft -> active\`); an agent that calls it produces a pending confirmation instead. Only after a human confirms does the scheduled pull begin writing confirmed readings.
 
-Discovery always returns a \`recipe_presets\` array; it is empty when {{brand}} does not recognize a safe source type. Today those presets cover Baserow row fields and the generic REST JSON fallback. Google Sheets uses OAuth JSON credentials and is withheld from REST presets until the pull executor extracts and refreshes the Google access token instead of treating the stored credential blob as a bearer token. A preset includes a label, cadence, required metadata, a draft \`rest_for_signals\` recipe, and the host allowlist to preview with. The human still fills in the real Baserow table/row/field or exact REST URL and value path before running \`signal.preview\`; presets are starter recipes, not secret stores.
+Discovery always returns a \`recipe_presets\` array; it is empty when {{brand}} does not recognize a safe source type. Today the proven self-filling path is Baserow REST through \`integration.connect_rest\`: a tenant admin creates or rotates the Baserow connection through the command/vault path, then Signal runs \`integration.discover -> signal.preview -> signal.bind -> signal.bind_confirm\` against that connected source. Baserow row-field recipes and custom filtered-count recipes are supported when the human supplies the real table, field, filter, host, and value path. A first-class filtered-count preset is still a follow-up; do not imply every filtered count appears as a one-click preset. Google Sheets Signal pulls are not live yet: Google uses OAuth JSON credentials and remains withheld from REST presets until the pull executor extracts and refreshes the Google access token instead of treating the stored credential blob as a bearer token. A preset includes a label, cadence, required metadata, a draft \`rest_for_signals\` recipe, and the host allowlist to preview with. The human still fills in the real Baserow table/row/field or exact REST URL and value path before running \`signal.preview\`; presets are starter recipes, not secret stores.
 
 Recipes are validated data, never code: a read-only GET, a closed set of non-secret headers, and a restricted scalar path to the value. Every fetch passes one SSRF guard (HTTPS only, a steward-confirmed host allowlist set at bind, and a runtime check that the host does not resolve to a private address). The preset output never contains \`nango://\` handles, vault refs, tokens, or static credential headers. Deterministic pulls write \`integration\`-sourced readings on the measurable's cadence.
 
 In the web app, the same workflow lives on \`/signal\` in the "Connect a self-filling source" panel. It shows each measurable's setup state \u2014 manual, agent draft, source draft, or auto-filled \u2014 plus the latest safe pull outcome when one exists. Choose a connected source, discover its non-secret metadata, preview a GET URL and value path, bind the working preview as a draft, then confirm the draft before scheduled pulls can write readings. The UI never displays credential material, vault refs, raw response bodies, or recipe secrets; if no connected source exists, connect one from Settings first.
 
+A source binding can inform a measurable without automatically changing a Cascade goal. The proven Leiluna Baserow binding uses \`informs\`. Use \`drives_status\` only after a second business anchor confirms that this exact measurable should compute a childless goal's status; otherwise the Signal should stay visible as evidence and exception context, not an automatic goal-status driver.
+
 ## Collect a Signal by judgment (the Signal agent)
 
 Some measurables cannot be a deterministic pull \u2014 the number lives in a PDF, in messy records that need reconciling, or is a judgment estimate of progress. For those, mark the measurable \`agent\`-sourced and let a per-seat Signal agent read it. The agent proposes each reading with \`signal.report\` (scope: seat): one draft reading for one of its OWN seat's agent-sourced measurables, with a \`value\` and a short \`note\` citing the source. The reading lands unconfirmed, exactly like a deterministic draft \u2014 a human clears it with \`signal.confirm_reading\`. \`signal.report\` refuses any measurable not owned by the acting seat and any measurable whose source is not \`agent\`, and it never confirms its own reading. Deliver it as the \`stock/signal-collector\` template (a read-only agent whose only durable grant is \`signal.report\`) or run the \`collect-seat-signals\` how-to from an occupant agent. When the agent cannot read a number confidently \u2014 ambiguous or conflicting sources \u2014 it escalates instead of guessing.
@@ -44115,7 +44117,7 @@ Do not claim that a live charge happened unless Stripe test/live evidence proves
     order: 72,
     title: "Settings guide",
     summary: "How to use Settings as the control plane for company access, channels, providers, tokens, and operating defaults.",
-    version: "2026-07-02.2",
+    version: "2026-07-02.3",
     public: true,
     audiences: ["human", "cli", "mcp", "in_app_agent"],
     stages: ["company_setup", "staffing"],
@@ -44201,6 +44203,7 @@ The company autonomy ceiling is a single tenant-wide dial that caps how much ANY
 
 - Read it with \`settings.agent_policy.get\` (CLI: \`{{cli}} settings agent-policy get\`).
 - Set it with \`settings.agent_policy.update\` (CLI: \`{{cli}} settings agent-policy set --profile locked_down\`). Owner-only and human-gated.
+- In the signed-in app, tenant owners manage the same policy from **Settings \u2192 Company guardrails**. Non-owners can see the current posture but cannot change it.
 - Profiles are named ceilings: \`locked_down\` (agents autonomously read/draft only; every write/send escalates), \`balanced\` (the default; read/draft autonomous, writes escalate), \`high_autonomy\` (approval-marked write tools may run autonomously; only full-access escalates), and \`custom\` + \`max_autonomous_risk\` (\`low\`, \`medium\`, \`high\`, \`critical\`).
 - An explicitly set ceiling is ENFORCED by default. Enforcement has two modes: \`enforce\` blocks an over-ceiling autonomous call and routes it to the steward (it is never a dead-end deny \u2014 a human can still approve), and \`observe\` allows the call but logs it. The platform default for a company that never set a policy is balanced + observe, so existing live agents are never retro-bricked.
 - When enforcement is on, signing a manifest or taking an agent live is REFUSED if the manifest grants always_allow to a tool whose risk exceeds the ceiling; the error names the exact ceiling, tool, and risk in its \`details\`. Lower that tool to always_ask, or raise the ceiling, then retry.
@@ -44214,7 +44217,7 @@ Agents may explain which setting is needed and why. They should not ask users to
     order: 73,
     title: "Members and invites guide",
     summary: "How to invite humans into the company without confusing user access with seat accountability.",
-    version: "2026-06-13.1",
+    version: "2026-07-02.1",
     public: true,
     audiences: ["human", "cli", "mcp", "in_app_agent"],
     stages: ["company_setup", "staffing"],
@@ -44239,6 +44242,8 @@ Invite the person as a tenant member. Then assign them to one or more seats only
 
 Tenant roles control app access. Seats control operating accountability. Do not attach goals, tasks, or measurables directly to a user when the work belongs to a seat.
 
+Owners and admins can invite people and manage member roles. Use \`external_implementer\` plus setup-limited access for a temporary implementation partner helping configure onboarding, Responsibility Graph, Compass, Charters, and agent setup. Do not grant external implementers sensitive run history, hidden tool arguments, credentials, Memory, or company-operating data unless an owner explicitly expands their profile.
+
 ## Agent guidance
 
 When a user asks to add a person, clarify whether they mean app access, seat occupancy, or both. Use invites for access and staffing commands for occupancies.`
@@ -46168,9 +46173,9 @@ var COMMAND_MANIFEST = [
   { "id": "measurable_template.adopt", "namespace": "measurable_template", "action": "adopt", "title": "Adopt a measurable template", "description": "Create a seat measurable from a catalog template (unit/direction/cadence from the template; target optionally overridden). The seat owns it; readings attach afterward.", "requiredScope": "seat", "confirmation": "none", "exposeOverMcp": true, "fields": [{ "name": "template_id", "flag": "template-id", "type": "string", "required": true }, { "name": "seat_id", "flag": "seat-id", "type": "string", "required": true }, { "name": "target", "flag": "target", "type": "number", "required": false }], "hasComplexInput": false, "help": "Create a seat measurable from a catalog template (unit/direction/cadence from the template; target optionally overridden). Adoption is a human act \u2014 source is human." },
   { "id": "measurable_template.list", "namespace": "measurable_template", "action": "list", "title": "List measurable templates", "description": "List the measurable template catalog (Sales/Finance/Ops/Marketing/HR) with unit, direction, cadence, and a suggested target. Adopt one with measurable_template.adopt.", "requiredScope": "tenant", "confirmation": "none", "exposeOverMcp": true, "fields": [{ "name": "function", "flag": "function", "type": "enum", "required": false, "enumValues": ["sales", "finance", "operations", "marketing", "hr"] }], "hasComplexInput": false, "help": "List the measurable template catalog by function (Sales/Finance/Ops/Marketing/HR); adopt one with measurable_template.adopt to create a seat measurable." },
   { "id": "measurable.create", "namespace": "measurable", "action": "create", "title": "Add a measurable", "description": "Create a measurable (a Signal a seat owns) with its target, unit, direction, and cadence. The seat owns it; readings attach to the measurable. Source is 'human' \u2014 a human-defined measurable a human logs.", "requiredScope": "seat", "confirmation": "none", "exposeOverMcp": true, "fields": [{ "name": "seat_id", "flag": "seat-id", "type": "string", "required": true }, { "name": "name", "flag": "name", "type": "string", "required": true }, { "name": "unit", "flag": "unit", "type": "string", "required": true }, { "name": "direction", "flag": "direction", "type": "enum", "required": true, "enumValues": ["up_good", "down_good"] }, { "name": "target", "flag": "target", "type": "number", "required": true }, { "name": "cadence", "flag": "cadence", "type": "enum", "required": true, "enumValues": ["daily", "weekly", "monthly", "quarterly", "annual"] }], "hasComplexInput": false, "help": "Add a measurable a seat owns (name, unit, direction, target, cadence) before recording readings against it." },
-  { "id": "member.invite", "namespace": "member", "action": "invite", "title": "Invite member", "description": "Create a pending tenant invite for a human teammate. The acceptance link is delivered out of band, not in the command result.", "requiredScope": "tenant", "confirmation": "none", "exposeOverMcp": true, "fields": [{ "name": "email", "flag": "email", "type": "string", "required": true }, { "name": "role", "flag": "role", "type": "enum", "required": true, "enumValues": ["owner", "steward", "member"] }, { "name": "byo_key", "flag": "byo-key", "type": "boolean", "required": false }], "hasComplexInput": false, "help": "Invite humans to the company by seat-aware role; the invite token is never returned over CLI or MCP." },
+  { "id": "member.invite", "namespace": "member", "action": "invite", "title": "Invite member", "description": "Create a pending tenant invite for a human teammate. The acceptance link is delivered out of band, not in the command result.", "requiredScope": "tenant", "confirmation": "none", "exposeOverMcp": true, "fields": [{ "name": "email", "flag": "email", "type": "string", "required": true }, { "name": "role", "flag": "role", "type": "enum", "required": true, "enumValues": ["owner", "admin", "steward", "member"] }, { "name": "member_type", "flag": "member-type", "type": "enum", "required": false, "enumValues": ["internal", "external_implementer"] }, { "name": "access_profile", "flag": "access-profile", "type": "enum", "required": false, "enumValues": ["full_setup", "setup_limited", "seat_scoped", "custom"] }, { "name": "aicos_access_scope", "flag": "aicos-access-scope", "type": "enum", "required": false, "enumValues": ["none", "own_scope", "setup", "company_read", "company_operate"] }, { "name": "byo_key", "flag": "byo-key", "type": "boolean", "required": false }], "hasComplexInput": false, "help": "Invite humans to the company by seat-aware role; the invite token is never returned over CLI or MCP." },
   { "id": "member.remove", "namespace": "member", "action": "remove", "title": "Remove member", "description": "Remove a tenant member. Blocked when it would orphan an agent steward chain.", "requiredScope": "tenant", "confirmation": "human_required", "exposeOverMcp": true, "fields": [{ "name": "member_id", "flag": "member-id", "type": "string", "required": true }], "hasComplexInput": false, "help": "Remove a member; the no-orphan-agent guard blocks removing the only steward in an agent chain." },
-  { "id": "member.update", "namespace": "member", "action": "update", "title": "Update member role", "description": "Change a tenant member's role.", "requiredScope": "tenant", "confirmation": "human_required", "exposeOverMcp": true, "fields": [{ "name": "member_id", "flag": "member-id", "type": "string", "required": true }, { "name": "role", "flag": "role", "type": "enum", "required": true, "enumValues": ["owner", "steward", "member"] }], "hasComplexInput": false, "help": "Change a member's role; role changes are human-gated." },
+  { "id": "member.update", "namespace": "member", "action": "update", "title": "Update member role", "description": "Change a tenant member's role.", "requiredScope": "tenant", "confirmation": "human_required", "exposeOverMcp": true, "fields": [{ "name": "member_id", "flag": "member-id", "type": "string", "required": true }, { "name": "role", "flag": "role", "type": "enum", "required": true, "enumValues": ["owner", "admin", "steward", "member"] }], "hasComplexInput": false, "help": "Change a member's role; role changes are human-gated." },
   { "id": "model.catalog", "namespace": "model", "action": "catalog", "title": "List model catalog", "description": "List the guided model tiers the agent builder reads \u2014 recommendation, token prices, cost band, effort, model id, and when to choose or avoid each tier.", "requiredScope": "tenant", "confirmation": "none", "exposeOverMcp": true, "fields": [], "hasComplexInput": false, "help": "List guided model tiers with recommendations, token prices, cost bands, best-fit work, and model ids before choosing --model for an agent." },
   { "id": "notification.list_errors", "namespace": "notification", "action": "list_errors", "title": "List notification errors", "description": "List recent failed notification deliveries for the tenant.", "requiredScope": "tenant", "confirmation": "none", "exposeOverMcp": true, "fields": [{ "name": "limit", "flag": "limit", "type": "integer", "required": false }], "hasComplexInput": false, "help": "List recent failed notification deliveries when diagnosing missed escalations or briefs." },
   { "id": "notification.settings.get", "namespace": "notification", "action": "settings.get", "title": "Get notification settings", "description": "Read tenant notification preferences (escalations, Sync brief, default channel).", "requiredScope": "tenant", "confirmation": "none", "exposeOverMcp": true, "fields": [], "hasComplexInput": false, "help": "Read notification preferences before changing escalation or Sync brief delivery." },
@@ -46178,7 +46183,7 @@ var COMMAND_MANIFEST = [
   { "id": "notification.test", "namespace": "notification", "action": "test", "title": "Send test notification", "description": "Emit an in-app test notification to the acting human to verify delivery is wired.", "requiredScope": "tenant", "confirmation": "none", "exposeOverMcp": true, "fields": [], "hasComplexInput": false, "help": "Send an in-app test notification to confirm the delivery path is wired." },
   { "id": "onboarding.advance_step", "namespace": "onboarding", "action": "advance_step", "title": "Advance onboarding step", "description": "Persist the current onboarding step after server-side validation.", "requiredScope": "tenant", "confirmation": "none", "exposeOverMcp": true, "fields": [{ "name": "step", "flag": "step", "type": "string", "required": true }, { "name": "completed", "flag": "completed", "type": "boolean", "required": false }], "hasComplexInput": true, "help": "Advance onboarding only after the current setup step is represented in the tenant state." },
   { "id": "onboarding.attach_reference", "namespace": "onboarding", "action": "attach_reference", "title": "Attach reference document", "description": "Attach a company reference document (text/markdown) so Compass and Charters can cite it. Reference-only \u2014 it does not build a Compass; convert each meaningful doc to markdown and attach it with a title, kind, and source.", "requiredScope": "tenant", "confirmation": "none", "exposeOverMcp": true, "fields": [{ "name": "text", "flag": "text", "type": "string", "required": true }, { "name": "filename", "flag": "filename", "type": "string", "required": false }, { "name": "mime_type", "flag": "mime-type", "type": "enum", "required": false, "enumValues": ["text/plain", "text/markdown", "text/csv"] }, { "name": "title", "flag": "title", "type": "string", "required": false }, { "name": "kind", "flag": "kind", "type": "enum", "required": false, "enumValues": ["plan", "financial", "org_chart", "process"] }, { "name": "source", "flag": "source", "type": "string", "required": false }], "hasComplexInput": false, "help": "Convert each meaningful company doc to markdown and attach it as a reference (title, kind, source) so Compass and Charters can cite it; this attaches a reference, it does not build a Compass \u2014 author Compass directly.", "example": { "text": "# Company handbook\n\nWe build precision components for the aerospace supply chain.", "filename": "handbook.md", "mime_type": "text/markdown", "title": "Company handbook", "kind": "plan", "source": "handbook/overview.md" } },
-  { "id": "onboarding.create_invite", "namespace": "onboarding", "action": "create_invite", "title": "Create onboarding invite", "description": "Create a pending invite for an onboarding team member.", "requiredScope": "tenant", "confirmation": "none", "exposeOverMcp": true, "fields": [{ "name": "email", "flag": "email", "type": "string", "required": true }, { "name": "role", "flag": "role", "type": "enum", "required": false, "enumValues": ["owner", "steward", "member"] }], "hasComplexInput": true, "help": "Invites should give humans access to the company without assigning work directly to people instead of seats." },
+  { "id": "onboarding.create_invite", "namespace": "onboarding", "action": "create_invite", "title": "Create onboarding invite", "description": "Create a pending invite for an onboarding team member.", "requiredScope": "tenant", "confirmation": "none", "exposeOverMcp": true, "fields": [{ "name": "email", "flag": "email", "type": "string", "required": true }, { "name": "role", "flag": "role", "type": "enum", "required": false, "enumValues": ["owner", "admin", "steward", "member"] }], "hasComplexInput": true, "help": "Invites should give humans access to the company without assigning work directly to people instead of seats." },
   { "id": "onboarding.finish", "namespace": "onboarding", "action": "finish", "title": "Finish onboarding", "description": "Mark onboarding complete after the existing onboarding requirements pass.", "requiredScope": "tenant", "confirmation": "human_required", "exposeOverMcp": true, "fields": [], "hasComplexInput": false, "help": "Finish onboarding when the graph, at least one Charter, and the first operating rhythm are clear." },
   { "id": "onboarding.status", "namespace": "onboarding", "action": "status", "title": "Onboard status", "description": "Return current onboarding progress, graph summary, and the next recommended actions.", "requiredScope": "tenant", "confirmation": "none", "exposeOverMcp": true, "fields": [], "hasComplexInput": false, "help": "Start by checking onboarding status, then use the implementation method guide to choose the next setup step." },
   { "id": "onboarding.upload_context", "namespace": "onboarding", "action": "upload_context", "title": "Upload org context", "description": "Compatibility alias for onboarding.attach_reference: attach a company reference document (text/markdown) that Compass and Charters can cite. Reference-only \u2014 it does not build a Compass.", "requiredScope": "tenant", "confirmation": "none", "exposeOverMcp": true, "fields": [{ "name": "text", "flag": "text", "type": "string", "required": true }, { "name": "filename", "flag": "filename", "type": "string", "required": false }, { "name": "mime_type", "flag": "mime-type", "type": "enum", "required": false, "enumValues": ["text/plain", "text/markdown", "text/csv"] }, { "name": "title", "flag": "title", "type": "string", "required": false }, { "name": "kind", "flag": "kind", "type": "enum", "required": false, "enumValues": ["plan", "financial", "org_chart", "process"] }, { "name": "source", "flag": "source", "type": "string", "required": false }], "hasComplexInput": false, "help": "Compatibility alias for onboarding.attach_reference: attach a company reference document so Compass and Charters can cite it. It does not build a Compass.", "example": { "text": "# Company handbook\n\nWe build precision components for the aerospace supply chain.", "filename": "handbook.md", "mime_type": "text/markdown", "title": "Company handbook", "kind": "plan", "source": "handbook/overview.md" } },