@rosthq/cli 0.6.1 → 0.6.2

package/dist/generated/command-manifest.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"command-manifest.d.ts","sourceRoot":"","sources":["../../src/generated/command-manifest.ts"],"names":[],"mappings":"AAIA,OAAO,KAAK,EAAE,oBAAoB,EAAE,MAAM,gCAAgC,CAAC;AAE3E,eAAO,MAAM,gBAAgB,EAAE,SAAS,oBAAoB,EA+K3D,CAAC"}
+{"version":3,"file":"command-manifest.d.ts","sourceRoot":"","sources":["../../src/generated/command-manifest.ts"],"names":[],"mappings":"AAIA,OAAO,KAAK,EAAE,oBAAoB,EAAE,MAAM,gCAAgC,CAAC;AAE3E,eAAO,MAAM,gBAAgB,EAAE,SAAS,oBAAoB,EAmL3D,CAAC"}

package/dist/index.js

@@ -42403,7 +42403,7 @@ 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: "2026-06-30.7",
+    version: "2026-07-01.1",
     public: true,
     audiences: ["human", "cli", "mcp", "in_app_agent"],
     stages: ["company_setup", "staffing"],
@@ -43056,6 +43056,10 @@ Several rows here are seat-operating commands (\`task.create\`, the \`signal.*\`
 | \`rost_correct_signal_reading\` | \`signal.correct_reading\` | Overwrite a reading with a human-confirmed value. | Seat or tenant-admin | Manual correction; expect confirmation. |
 | \`rost_add_a_measurable\` | \`measurable.create\` | Add a measurable a seat owns (name, unit, direction, target, cadence). | Seat or tenant-admin | Call with \`{"seat_id":"<id>","name":"...","unit":"...","direction":"up_good","target":0,"cadence":"weekly"}\`. |
 | \`rost_import_signals_from_csv\` | \`signal.import\` | Bulk-import measurable definitions + trailing historical readings from a parsed scorecard export (e.g. a ninety CSV). Owners resolve to seats; readings are human-confirmed; re-import upserts by (measurable, period, cadence); a cross-cadence row is reported and skipped, not overwritten. | Tenant | Call with the parsed \`measurables\` array. |
+| \`rost_discover_a_connection_for_signals\` | \`integration.discover\` | Read-only introspection of a connected source: returns non-secret metadata and a recipe skeleton to author a signal pull against. | Tenant | No network; call with \`{"integration_id":"<id>"}\`. |
+| \`rost_preview_a_signal_source\` | \`signal.preview\` | Run a candidate recipe live but read-only against an allowlisted HTTPS source; returns the extracted value and a short-lived \`preview_token\`. Never mutates; the credential is resolved from the connection at execution and never stored in the recipe. | Tenant | Call with \`{"measurable_id":"<id>","integration_id":"<id>","recipe":{...}}\`. |
+| \`rost_bind_a_signal_source_draft\` | \`signal.bind\` | Persist the validated recipe as an inert \`draft\` binding; requires the \`preview_token\` from a preview of the same recipe, so nothing is bound that was not first seen working. | Tenant | Call with \`{"measurable_id":"<id>","integration_id":"<id>","recipe":{...},"cadence":"weekly","preview_token":"<token>"}\`. |
+| \`rost_confirm_and_activate_a_signal_binding\` | \`signal.bind_confirm\` | Human-only: activates a draft binding (\`draft -> active\`) so scheduled pulls begin writing confirmed readings. An agent that calls it produces a pending confirmation instead. | Tenant | Human confirms; call with \`{"binding_id":"<id>"}\`. |
 | \`rost_import_friction_issues_from_a_ninety_issues_list\` | \`friction.import\` | Bulk-import issues as Friction items for the named owner seat (from a ninety Issues List export). Owners resolve to seats; idempotent re-import skips an open issue already imported for the same seat + summary; whole-file re-import is skipped by content hash. | Tenant | Call with the parsed \`issues\` array. |
 | \`rost_import_tasks_from_a_ninety_to_dos_export\` | \`task.import\` | Bulk-import To-Dos as tasks the named owner seat owns (from a ninety To-Dos export), provenance origin_kind:manual. Owners resolve to seats; idempotent re-import skips a non-terminal task already imported for the same seat + title. | Tenant | Call with the parsed \`todos\` array. |
 | \`rost_import_rocks_from_a_ninety_rocks_export\` | \`cascade.import\` | Bulk-import Rocks as Cascade cycle goals under a company objective in the active cycle (from a ninety Rocks export). Owners resolve to seats; idempotent re-import skips a cycle goal already imported for the same objective + seat + title. | Tenant | Call with the parsed \`rocks\` array. |
@@ -43570,7 +43574,7 @@ Retrieve the narrowest relevant guide before making a setup recommendation. Pref
     order: 60,
     title: "Cascade guide",
     summary: "How to connect company goals to seat-level work without turning {{brand}} into a project-management tool.",
-    version: "2026-06-30.1",
+    version: "2026-06-30.2",
     public: true,
     audiences: ["human", "cli", "mcp", "in_app_agent"],
     stages: ["operating_rhythm"],
@@ -43606,12 +43610,21 @@ Retrieve the narrowest relevant guide before making a setup recommendation. Pref
 
 Cascade connects company direction to seat-level commitments. It is a goal tree, not a ticket tracker. Work belongs in Cascade when it explains how a seat contributes to a larger outcome.
 
+## The four goal kinds
+
+Cascade has four goal kinds that form one chain from vision to sub-step:
+
+- **Horizon** goals (10-year, 3-year, 1-year) live in the Compass document, not in the goal tree. They change by supersession, roughly yearly.
+- **Company objective** \u2014 the quarter's company-level rocks. Each is a cascade root that ties back to the active Compass's 1-year horizon, is materialized from the Compass, and renders as a read-only header tier on \`/cascade\` (edited through the Compass or by leadership, not inline). Re-versioning the Compass keeps the in-flight quarter's objectives intact \u2014 it never orphans them.
+- **Seat goal** \u2014 a seat's quarterly rocks. A seat goal connects under a company objective, and seat goals may still nest (a function seat goal above an agent execution seat goal) for the accountable-human layer.
+- **Milestone** \u2014 optional sub-steps of a seat goal. Completing milestones automatically rolls into the parent seat goal's progress, so a rock's percentage reflects real sub-step completion.
+
 ## Good Cascade structure
 
-- Company goals connect back to the Compass.
-- Team or function goals connect to company goals. This is the accountable human layer for most agent work.
-- Agent execution goals connect below the human or function goal they advance, unless the agent seat is intentionally accountable for that outcome.
-- Seat commitments connect to the goal they advance.
+- Company objectives connect back to the Compass 1-year horizon.
+- Team or function seat goals connect to company objectives. This is the accountable human layer for most agent work.
+- Agent execution seat goals connect below the human or function goal they advance, unless the agent seat is intentionally accountable for that outcome.
+- Milestones connect below the seat goal they break down.
 - Each commitment has one owning seat.
 - Status is evidence-based where possible.
 
@@ -43630,7 +43643,7 @@ On \`/cascade\`, the screen renders the full goal depth, not just one or two lev
 
 ## Goal progress and at-risk goals
 
-A goal can carry a quantified progress (0-100) distinct from its on/off/done status. Report it with \`goal.set_progress\`; when an agent reports progress it lands as a proposal a human approves before the goal moves. \`goal.list_at_risk\` projects which goals are off pace by comparing progress against the elapsed fraction of the cycle window (deterministic date math, no forecast model). Off-pace goals surface on \`/cascade\`, on the owner home, in the weekly Sync Brief, and as a weekly owner alert. Status-only goals (no progress recorded) are excluded from the projection and render as pending measurement, not as proven on track.
+A goal can carry a quantified progress (0-100) distinct from its on/off/done status. Report it with \`goal.set_progress\`; when an agent reports progress it lands as a proposal a human approves before the goal moves. A seat goal that has milestones takes its progress from milestone completion instead \u2014 the percentage is the share of its non-dropped milestones marked done, recomputed automatically as milestones complete, drop, or re-open. \`goal.list_at_risk\` projects which goals are off pace by comparing progress against the elapsed fraction of the cycle window (deterministic date math, no forecast model). Off-pace goals surface on \`/cascade\`, on the owner home, in the weekly Sync Brief, and as a weekly owner alert. Status-only goals (no progress recorded) are excluded from the projection and render as pending measurement, not as proven on track.
 
 On human and function seat pages, goal visibility includes both direct goals and descendant seat goals from the Responsibility Graph subtree, so a manager can review team progress without double-owning the agent's work.
 
@@ -43658,7 +43671,7 @@ 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: "2026-06-30.1",
+    version: "2026-07-01.1",
     public: true,
     audiences: ["human", "cli", "mcp", "in_app_agent"],
     stages: ["operating_rhythm"],
@@ -43671,7 +43684,11 @@ Agents can suggest commitments and report progress. They should not create a new
       "signal.confirm_reading",
       "signal.correct_reading",
       "measurable.create",
-      "signal.import"
+      "signal.import",
+      "integration.discover",
+      "signal.preview",
+      "signal.bind",
+      "signal.bind_confirm"
     ],
     legal: {
       publicRisk: "low",
@@ -43717,6 +43734,17 @@ A human can run the whole loop from the Signal page. Each measurable has a "Log
 
 To move off a spreadsheet or another operating tool, upload a scorecard export from the Signal page "Import from CSV" panel (the \`signal.import\` command, also available on CLI/MCP). Each row becomes a measurable owned by the seat whose name matches the row's owner, with its target, unit, direction, cadence, and trailing readings. Import is idempotent \u2014 re-importing upserts by period \u2014 and a row whose cadence conflicts with an existing measurable is reported and skipped, not overwritten.
 
+## Auto-fill Signal from a connected source
+
+Once a measurable's number lives in a connected system, you can teach {{brand}} the exact deterministic pull once and let it keep the measurable current. The flow is \`discover -> preview -> bind -> bind_confirm\`:
+
+- \`integration.discover\` returns non-secret metadata for a connected source and a recipe skeleton to author against.
+- \`signal.preview\` runs a candidate recipe live but read-only against an allowlisted HTTPS source, returns the extracted value, and issues a short-lived \`preview_token\`. It never mutates and never stores a secret in the recipe \u2014 the credential is resolved from the connection at execution.
+- \`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.
+
+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). Deterministic pulls write \`integration\`-sourced readings on the measurable's cadence.
+
 ## When to stop for confirmation
 
 \`signal.correct_reading\` is \`human_required\`; overwriting a recorded measurable is a human judgment. \`signal.confirm_reading\` is \`none\`, so a seat can confirm its own readings directly. \`measurable.create\` is \`none\` \u2014 defining a measurable is not gated. An agent records readings with evidence; a human corrects when a value is wrong.
@@ -45955,6 +45983,7 @@ var COMMAND_MANIFEST = [
   { "id": "goal.set_status", "namespace": "goal", "action": "set_status", "title": "Set Cascade goal status", "description": "Set a goal's status (on/off/done). Seat-scoped callers may set status only for their own goals.", "requiredScope": "seat", "confirmation": "none", "exposeOverMcp": true, "fields": [{ "name": "goal_id", "flag": "goal-id", "type": "string", "required": true }, { "name": "status", "flag": "status", "type": "enum", "required": true, "enumValues": ["on", "off", "done"] }], "hasComplexInput": false, "help": "Set a goal's status; seat tokens may only set status for their own goals." },
   { "id": "goal.update", "namespace": "goal", "action": "update", "title": "Update Cascade goal", "description": "Update a goal's title or definition of done. Topology (parent/seat) and status have dedicated commands.", "requiredScope": "tenant_admin", "confirmation": "none", "exposeOverMcp": true, "fields": [{ "name": "goal_id", "flag": "goal-id", "type": "string", "required": true }, { "name": "title", "flag": "title", "type": "string", "required": false }, { "name": "definition_of_done", "flag": "definition-of-done", "type": "string", "required": false }], "hasComplexInput": false, "help": "Update a goal's title or definition of done; topology and status have dedicated commands." },
   { "id": "graph.get", "namespace": "graph", "action": "get", "title": "Get Responsibility Graph", "description": "Return the tenant's Responsibility Graph: seats, edges, root, occupants, and status rollups.", "requiredScope": "tenant", "confirmation": "none", "exposeOverMcp": true, "fields": [], "hasComplexInput": false, "help": "Read the Responsibility Graph to discover seat ids, parentage, occupants, and status before mutating or routing work." },
+  { "id": "integration.discover", "namespace": "integration", "action": "discover", "title": "Discover a connection for signals", "description": "Read-only introspection of a connected source for signal binding. Returns non-secret adapter metadata and a rest-for-signals recipe skeleton to author against signal.preview. Exposes no secrets.", "requiredScope": "tenant", "confirmation": "none", "exposeOverMcp": true, "fields": [{ "name": "integration_id", "flag": "integration-id", "type": "string", "required": true }], "hasComplexInput": false, "help": "Read-only introspection of a connected source: returns non-secret metadata + a recipe skeleton to author a signal pull against. No network." },
   { "id": "integration.list", "namespace": "integration", "action": "list", "title": "List integrations", "description": "List tenant integration metadata and health status. Returns account/scopes/capabilities only; never secrets or vault refs.", "requiredScope": "tenant", "confirmation": "none", "exposeOverMcp": true, "fields": [{ "name": "provider", "flag": "provider", "type": "string", "required": false }], "hasComplexInput": false, "help": "List connected integrations and their metadata-only health state before enabling a connector-backed tool." },
   { "id": "integration.readiness", "namespace": "integration", "action": "readiness", "title": "Check integration readiness", "description": "Return a safe connector setup checklist for operators and agents. Starts with Google and exposes no secrets.", "requiredScope": "tenant", "confirmation": "none", "exposeOverMcp": true, "fields": [{ "name": "provider", "flag": "provider", "type": "enum", "required": false, "enumValues": ["google"] }], "hasComplexInput": false, "help": "Read the connector setup checklist before relying on Google-backed agent work; the checklist names missing config, connection, scopes, external verification, and handler blockers." },
   { "id": "integration.status", "namespace": "integration", "action": "status", "title": "Get integration status", "description": "Read one integration's metadata and latest health status. Returns no secret material.", "requiredScope": "tenant", "confirmation": "none", "exposeOverMcp": true, "fields": [{ "name": "provider", "flag": "provider", "type": "string", "required": false }, { "name": "integration_id", "flag": "integration-id", "type": "string", "required": false }], "hasComplexInput": false, "help": "Read one integration's metadata-only status by provider or integration id." },
@@ -45962,7 +45991,7 @@ var COMMAND_MANIFEST = [
   { "id": "mcp_token.create", "namespace": "mcp_token", "action": "create", "title": "Create MCP token", "description": "Mint a tenant-admin or seat-scoped MCP token.", "requiredScope": "tenant", "confirmation": "human_required", "exposeOverMcp": true, "fields": [{ "name": "scope", "flag": "scope", "type": "enum", "required": true, "enumValues": ["tenant_admin", "seat"] }, { "name": "seat_id", "flag": "seat-id", "type": "string", "required": false }, { "name": "expires_at", "flag": "expires-at", "type": "string", "required": false }, { "name": "expires_in_days", "flag": "expires-in-days", "type": "integer", "required": false }], "hasComplexInput": false, "help": "Create MCP tokens with the narrowest scope needed, and tell agents where to retrieve reference docs." },
   { "id": "mcp_token.list", "namespace": "mcp_token", "action": "list", "title": "List MCP tokens", "description": "List MCP token metadata (id, scope, seat, created/last-used/revoked). Never returns token material.", "requiredScope": "tenant", "confirmation": "none", "exposeOverMcp": true, "fields": [{ "name": "include_revoked", "flag": "include-revoked", "type": "boolean", "required": false }, { "name": "seat_id", "flag": "seat-id", "type": "string", "required": false }], "hasComplexInput": false, "help": "List MCP token metadata (never token material) to audit which seats hold active sessions." },
   { "id": "mcp_token.revoke", "namespace": "mcp_token", "action": "revoke", "title": "Revoke MCP token", "description": "Revoke an MCP token immediately.", "requiredScope": "tenant", "confirmation": "human_required", "exposeOverMcp": true, "fields": [{ "name": "token_id", "flag": "token-id", "type": "string", "required": true }, { "name": "seat_id", "flag": "seat-id", "type": "string", "required": false }], "hasComplexInput": false, "help": "Revoke MCP access when a local session ends or seat authority changes." },
-  { "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"] }], "hasComplexInput": false, "help": "Add a measurable a seat owns (name, unit, direction, target, cadence) before recording readings against it." },
+  { "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.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." },
@@ -45998,11 +46027,14 @@ var COMMAND_MANIFEST = [
   { "id": "settings.sync_brief_scope.get", "namespace": "settings", "action": "sync_brief_scope.get", "title": "Get Sync Brief scope", "description": "Read the tenant's Sync Brief scope: company_wide (one weekly brief) or per_cluster (one brief per cluster).", "requiredScope": "tenant", "confirmation": "none", "exposeOverMcp": true, "fields": [], "hasComplexInput": false, "help": "Read whether weekly Sync Briefs compile company-wide (one brief) or per cluster (one brief per cluster)." },
   { "id": "settings.sync_brief_scope.update", "namespace": "settings", "action": "sync_brief_scope.update", "title": "Update Sync Brief scope", "description": "Set the tenant's Sync Brief scope (company_wide or per_cluster). Per_cluster falls back to company-wide when the tenant has no clusters.", "requiredScope": "tenant_admin", "confirmation": "none", "exposeOverMcp": true, "fields": [{ "name": "sync_brief_scope", "flag": "sync-brief-scope", "type": "enum", "required": true, "enumValues": ["company_wide", "per_cluster"] }], "hasComplexInput": false, "help": "Set Sync Brief scope to company_wide or per_cluster; per_cluster falls back to company-wide when no clusters exist." },
   { "id": "settings.update", "namespace": "settings", "action": "update", "title": "Update tenant settings", "description": "Update tenant AI budget caps (soft/hard, USD). Budget changes are dangerous and gated.", "requiredScope": "tenant", "confirmation": "dangerous", "exposeOverMcp": true, "fields": [{ "name": "soft_cap_usd", "flag": "soft-cap-usd", "type": "string", "required": false }, { "name": "hard_cap_usd", "flag": "hard-cap-usd", "type": "string", "required": false }], "hasComplexInput": false, "help": "Update tenant AI budget caps; budget changes are dangerous and require human confirmation." },
+  { "id": "signal.bind", "namespace": "signal", "action": "bind", "title": "Bind a signal source (draft)", "description": "Persist a validated recipe + connection + cadence as an INERT draft binding for a measurable. Requires a valid preview_token from signal.preview of the same recipe. Never activates \u2014 a human signal.bind_confirm does that.", "requiredScope": "tenant", "confirmation": "none", "exposeOverMcp": true, "fields": [{ "name": "measurable_id", "flag": "measurable-id", "type": "string", "required": true }, { "name": "integration_id", "flag": "integration-id", "type": "string", "required": true }, { "name": "cadence", "flag": "cadence", "type": "enum", "required": true, "enumValues": ["daily", "weekly", "monthly", "quarterly", "annual"] }, { "name": "host_allowlist", "flag": "host-allowlist", "type": "array", "required": true, "itemType": "string" }, { "name": "preview_token", "flag": "preview-token", "type": "string", "required": true }, { "name": "role", "flag": "role", "type": "enum", "required": false, "enumValues": ["informs", "drives_status"] }], "hasComplexInput": true, "help": "Persist a validated recipe as an inert draft binding; requires the preview_token from a preview of the same recipe." },
+  { "id": "signal.bind_confirm", "namespace": "signal", "action": "bind_confirm", "title": "Confirm and activate a signal binding", "description": "Human-only activation of a draft signal binding (draft \u2192 active). Agents can never self-activate \u2014 an agent caller produces a pending confirmation. A drives_status binding requires a second-anchor confirmation. Once active, the scheduled pull auto-fills the measurable.", "requiredScope": "tenant", "confirmation": "human_required", "exposeOverMcp": true, "fields": [{ "name": "binding_id", "flag": "binding-id", "type": "string", "required": true }], "hasComplexInput": true, "help": "Human-only: activate a draft signal binding (draft -> active) so scheduled pulls begin; an agent that calls it produces a pending confirmation." },
   { "id": "signal.confirm_reading", "namespace": "signal", "action": "confirm_reading", "title": "Confirm Signal reading", "description": "Confirm an unconfirmed reading as human-verified. Humans confirm; agents cannot. Idempotent on an already-confirmed reading.", "requiredScope": "seat", "confirmation": "none", "exposeOverMcp": true, "fields": [{ "name": "reading_id", "flag": "reading-id", "type": "string", "required": true }], "hasComplexInput": false, "help": "Confirm an unconfirmed reading as human-verified; confirmation is a human act, not an agent one." },
   { "id": "signal.correct_reading", "namespace": "signal", "action": "correct_reading", "title": "Correct Signal reading", "description": "Overwrite a reading for a period with a human-confirmed value. A manual correction is a human decision and is gated behind confirmation.", "requiredScope": "seat", "confirmation": "human_required", "exposeOverMcp": true, "fields": [{ "name": "measurable_id", "flag": "measurable-id", "type": "string", "required": true }, { "name": "period_start", "flag": "period-start", "type": "string", "required": true }, { "name": "value", "flag": "value", "type": "number", "required": true }], "hasComplexInput": false, "help": "Correct a reading only as a human; manual corrections that change confirmed data require confirmation." },
   { "id": "signal.get", "namespace": "signal", "action": "get", "title": "Get Signal", "description": "Return a measurable definition with its full reading history (confirmed and unconfirmed).", "requiredScope": "tenant", "confirmation": "none", "exposeOverMcp": true, "fields": [{ "name": "measurable_id", "flag": "measurable-id", "type": "string", "required": true }], "hasComplexInput": false, "help": "Read a measurable's full reading history before confirming or correcting a value." },
   { "id": "signal.import", "namespace": "signal", "action": "import", "title": "Import Signals from CSV", "description": "Bulk-import measurable definitions and their historical readings from a parsed scorecard export (e.g. a ninety CSV). Owners are seat names resolved to seats; readings are human-confirmed. Idempotent \u2014 re-import upserts by (measurable, period, cadence). Re-importing a measurable at a different cadence is rejected, not overwritten.", "requiredScope": "tenant", "confirmation": "none", "exposeOverMcp": true, "fields": [{ "name": "dry_run", "flag": "dry-run", "type": "boolean", "required": false }], "hasComplexInput": true, "help": "Bulk-import measurables + historical readings from a parsed scorecard export (owners resolve to seats); idempotent, human-confirmed, re-import upserts by period." },
   { "id": "signal.list", "namespace": "signal", "action": "list", "title": "List Signals", "description": "List measurable definitions with their latest reading and on/off-track state. Seat-scoped callers see only their own seat.", "requiredScope": "tenant", "confirmation": "none", "exposeOverMcp": true, "fields": [{ "name": "seat_id", "flag": "seat-id", "type": "string", "required": false }], "hasComplexInput": false, "help": "List Signals to find measurable ids and current on/off-track state before recording or correcting readings." },
+  { "id": "signal.preview", "namespace": "signal", "action": "preview", "title": "Preview a signal source", "description": "Execute a candidate rest-for-signals recipe LIVE and read-only against an allowlisted HTTPS source, returning the extracted scalar and a short-lived preview_token required by signal.bind. Guarded (SSRF + restricted JSONPath); writes a signal_pull_log row. Never mutates.", "requiredScope": "tenant", "confirmation": "none", "exposeOverMcp": true, "fields": [{ "name": "measurable_id", "flag": "measurable-id", "type": "string", "required": true }, { "name": "integration_id", "flag": "integration-id", "type": "string", "required": true }, { "name": "cadence", "flag": "cadence", "type": "enum", "required": true, "enumValues": ["daily", "weekly", "monthly", "quarterly", "annual"] }, { "name": "host_allowlist", "flag": "host-allowlist", "type": "array", "required": true, "itemType": "string" }], "hasComplexInput": true, "help": "Run a candidate recipe live but read-only against an allowlisted HTTPS source; returns the extracted value + a short-lived preview_token. Never mutates; the credential is resolved from the connection at execution." },
   { "id": "signup.provision_tenant", "namespace": "signup", "action": "provision_tenant", "title": "Create company", "description": "Provision a new company (tenant) for the authenticated CLI user with no web step.", "requiredScope": "user", "confirmation": "none", "exposeOverMcp": false, "fields": [{ "name": "company_name", "flag": "company-name", "type": "string", "required": true }], "hasComplexInput": false, "help": "Create the company headlessly when the CLI session has no tenant yet; it becomes the user's active tenant so the rest of setup runs with no web step." },
   { "id": "skill.assign_to_seat", "namespace": "skill", "action": "assign_to_seat", "title": "Assign skill to seat", "description": "Propose or human-approve a published immutable skill version for a Seat after checking required and optional tool dependencies.", "requiredScope": "seat", "confirmation": "human_required", "exposeOverMcp": true, "fields": [{ "name": "seat_id", "flag": "seat-id", "type": "string", "required": true }, { "name": "slug", "flag": "slug", "type": "string", "required": false }, { "name": "skill_version_id", "flag": "skill-version-id", "type": "string", "required": false }, { "name": "status", "flag": "status", "type": "enum", "required": false, "enumValues": ["proposed", "approved"] }, { "name": "rationale", "flag": "rationale", "type": "string", "required": true }, { "name": "allow_blocked_proposal", "flag": "allow-blocked-proposal", "type": "boolean", "required": false }], "hasComplexInput": false, "help": "Propose or human-approve a published Skill for a Seat after dependency checks. Missing required tools block approval; optional tools are warnings only." },
   { "id": "skill.assigned.list", "namespace": "skill", "action": "assigned.list", "title": "List assigned skills", "description": "List approved skill assignments for a Seat, including immutable version, dependency status, rationale, and approval time. Seat-scoped callers can only read their own assignments.", "requiredScope": "tenant", "confirmation": "none", "exposeOverMcp": true, "fields": [{ "name": "seat_id", "flag": "seat-id", "type": "string", "required": false }], "hasComplexInput": false, "help": "List approved Skills assigned to a Seat before loading instructions into a run. A seat-scoped token can only read its own assigned Skills." },