@getmarrow/mcp 3.9.70 → 3.9.72

package/README.md

@@ -104,14 +104,20 @@ npx -y --package=@getmarrow/mcp@latest marrow-mcp ping
 
 Detection and notification are automatic. After explicit installer activation, the local controller may restore only Marrow-managed hooks/configuration. Package upgrades, owner policy, credentials, and unrelated configuration remain explicit and subject to the operator's normal change policy.
 
-## What's New in v3.9.70
+## What's New in v3.9.72
 
-v3.9.70 finishes the control-path honesty work for every MCP host:
+v3.9.72 requires SDK `3.7.61` so MCP installations cannot resolve to an SDK that recursively intercepts its own Marrow control-plane traffic. The MCP tool contract is unchanged; this release aligns the tested package chain.
 
-- `marrow_status` does not return a 4-minute last-known snapshot when a live read is still possible;
-- explicit `drain-spool` continues past the first failed event and dead-letters leftover current-namespace receipts instead of leaving a pending queue;
-- quarantine removes leftover `.json.lock` files for moved namespaces;
-- idle nudge tries up to 10 current-namespace events instead of stopping after one failure.
+## Previous: v3.9.71
+
+v3.9.71 makes the advertised Grok control loop true:
+
+- default tools include `marrow_think` so the official loop can create a `decision_id` without `MARROW_TOOL_PROFILE=full`;
+- process identity prefers `MARROW_KEY_<ROLE>` when it matches `MARROW_AGENT_ID`, so a leaked fleet env cannot 403 every status call;
+- Grok native hooks are installed under `~/.grok/hooks/marrow.json` and hook parsers accept Grok camelCase envelopes;
+- idle spool nudge drains up to 40 current-namespace events so the queue does not sit as a nag;
+- if `risk_gate.enforced` is false, the gate is advisory — do not describe it as a live block;
+- `marrow_commit.decision_id` may come from `marrow_think`, `marrow_auto`, or `marrow_agent_runtime.runtime_authorization.id`.
 
 ## Previous: v3.9.69
 
@@ -178,7 +184,7 @@ v3.9.62 integrates four model-neutral reliability and capability contracts:
 - `spool-status` and `drain-spool` report the active credential namespace separately from isolated legacy debt, and a clear active namespace exits successfully without replaying, merging, editing, or deleting old-key files;
 - initialize, prompt, setup, and tool responses qualify coverage by `host_capability`: MCP tools are on demand, while native hooks, an owned SDK process, a governed runner, or a custom event adapter cover only the scope proved by observed Marrow receipts.
 
-The default surface remains six tools and the prompt remains named `marrow-always-on`. Host and model labels are display-only and never change auth, tenant, plan, policy, proof, schema, or API behavior.
+The default surface is seven tools (runtime, think, commit, ask, status, auto, handoff status) and the prompt remains named `marrow-always-on`. Host and model labels are display-only and never change auth, tenant, plan, policy, proof, schema, or API behavior. Grok always-on coverage is native hooks plus MCP; it is verified only from observed receipts.
 
 ## Previous: v3.9.61
 
@@ -232,7 +238,7 @@ The compact agent control path introduced in v3.9.57 remains the default:
 - `marrow_status`, `marrow_ask`, and `marrow_agent_runtime` use authenticated routes with bounded retries and typed failures;
 - transient read failures return an owner-only last-known brief when available, while cached guidance can never authorize high-risk work;
 - normal tool errors return structured `ok`, `error_code`, `exact_fix`, `stale_brief`, and `client_update` data instead of raw MCP `fetch failed` errors;
-- the default agent surface is six tools: runtime, commit, ask, status, auto, and handoff status; set `MARROW_TOOL_PROFILE=full` only for legacy or advanced integrations;
+- the default agent surface is seven tools: runtime, think, commit, ask, status, auto, and handoff status; set `MARROW_TOOL_PROFILE=full` only for legacy or advanced integrations;
 - risky `marrow_auto` calls obtain a fresh runtime gate automatically and cannot self-close as successful without required proof;
 - `marrow_run` requires an explicit outcome and never invents proof or a successful result;
 - the package includes an exact-version control-path canary covering every route reported in the production incident.
@@ -332,7 +338,7 @@ With installed native hooks, protected tool calls follow this automatically. For
 
 1. Call `marrow_agent_runtime` or `marrow_decision_brief`.
 2. Stop when the returned decision is `block` or `review_required`; otherwise follow its prior lesson and proof contract.
-3. Call `marrow_think` to record intent and obtain the `decision_id` that will be closed.
+3. Call `marrow_think` or `marrow_auto` to record intent and obtain the `decision_id` that will be closed. `marrow_agent_runtime.runtime_authorization.id` is also accepted.
 4. Perform the action only when its gate allows it. For a hard external choke point, run the command through `npx @getmarrow/install run`; it verifies the signed action permit immediately before execution.
 5. Call `marrow_commit` with that `decision_id`, the outcome, gate receipt, and required proof.
 

package/dist/cli.js

@@ -12,6 +12,7 @@
 Object.defineProperty(exports, "__esModule", { value: true });
 const index_1 = require("./index");
 const hook_1 = require("./hook");
+const hook_contract_1 = require("./hook-contract");
 const hook_context_1 = require("./hook-context");
 const hook_session_1 = require("./hook-session");
 const hook_pre_action_1 = require("./hook-pre-action");
@@ -20,7 +21,7 @@ const lifecycle_spool_1 = require("./lifecycle-spool");
 const spool_command_1 = require("./spool-command");
 const guidance_cache_1 = require("./guidance-cache");
 const request_reliability_1 = require("./request-reliability");
-const hook_contract_1 = require("./hook-contract");
+const hook_contract_2 = require("./hook-contract");
 const ping_state_1 = require("./ping-state");
 const control_path_state_1 = require("./control-path-state");
 const redact_1 = require("./redact");
@@ -243,6 +244,13 @@ ${MARROW_BLOCK_END}`;
     else {
         process.stdout.write('Stop hook configuration is present. Session-end coverage remains unverified until Marrow observes session-end receipts.\n');
     }
+    const grokHookInstall = (0, hook_contract_1.installGrokNativeHooks)();
+    if (grokHookInstall.installed) {
+        process.stdout.write(`Configured Grok native hooks at ${grokHookInstall.settingsPath}. Coverage remains unverified until Marrow observes Grok lifecycle receipts.\n`);
+    }
+    else {
+        process.stdout.write(`Grok native hook configuration is present at ${grokHookInstall.settingsPath}. Coverage remains unverified until Marrow observes Grok lifecycle receipts.\n`);
+    }
     process.stdout.write(`Hook settings: ${hookInstall.settingsPath}\n`);
     process.stdout.write('Set MARROW_AUTO_HOOK=false to disable passive hooks.\n');
     process.stdout.write('Set MARROW_PASSIVE_BRIEF=false to disable automatic decision briefs, or MARROW_PASSIVE_BRIEF=always to brief every prompt.\n');
@@ -840,12 +848,13 @@ if (process.argv[2] !== 'keys') {
             {
                 name: 'marrow_commit',
                 description: 'Close a recorded action with success/failure, a specific outcome, and required proof. ' +
-                    'Use the decision_id from marrow_think and the gate receipt from marrow_agent_runtime for consequential work. ' +
+                    'decision_id may come from marrow_think, marrow_auto, or marrow_agent_runtime.runtime_authorization.id. ' +
+                    'Use the gate receipt from marrow_agent_runtime for consequential work. ' +
                     'Outcome closure is required for accountable fleet learning.',
                 inputSchema: {
                     type: 'object',
                     properties: {
-                        decision_id: { type: 'string', description: 'decision_id from the marrow_think call' },
+                        decision_id: { type: 'string', description: 'decision_id from marrow_think, marrow_auto, or marrow_agent_runtime.runtime_authorization.id' },
                         success: { type: 'boolean', description: 'Did the action succeed?' },
                         outcome: { type: 'string', description: 'What happened — be specific, this trains the hive' },
                         caused_by: { type: 'string', description: 'Optional: what caused this action' },
@@ -1695,6 +1704,7 @@ if (process.argv[2] !== 'keys') {
         ];
         const CORE_TOOL_NAMES = new Set([
             'marrow_agent_runtime',
+            'marrow_think',
             'marrow_commit',
             'marrow_ask',
             'marrow_status',
@@ -1726,9 +1736,9 @@ if (process.argv[2] !== 'keys') {
                     success(id, {
                         protocolVersion: '2024-11-05',
                         capabilities: { tools: {}, prompts: {} },
-                        serverInfo: { name: 'marrow', version: hook_contract_1.MCP_ADAPTER_VERSION },
+                        serverInfo: { name: 'marrow', version: hook_contract_2.MCP_ADAPTER_VERSION },
                         ...(AUTO_ENROLL ? {
-                            instructions: `Use marrow_agent_runtime before consequential actions, obey fresh allow/warn/review_required/block results, use marrow_ask for relevant prior lessons, and close meaningful outcomes with marrow_commit. Infrastructure failures are not policy denials; continue only low-risk reversible work from the returned outage-safe brief, and require a fresh gate for high-risk work. ${(0, host_capability_1.hostCapabilityInstructions)(hostCapability)}`,
+                            instructions: `Call marrow_think before meaningful work to create the decision_id. Use marrow_agent_runtime before consequential actions and obey fresh allow/warn/review_required/block only when risk_gate.enforced is true; if enforced is false the gate is advisory, not a live block. Use marrow_ask for relevant prior lessons, and close outcomes with marrow_commit using that decision_id. Infrastructure failures are not policy denials; continue only low-risk reversible work from the returned outage-safe brief, and require a fresh gate for high-risk work. ${(0, host_capability_1.hostCapabilityInstructions)(hostCapability)}`,
                         } : {}),
                         _meta: { host_capability: hostCapability },
                     });
@@ -2057,7 +2067,7 @@ Marrow is not a replacement agent or a standalone memory app. Context and prior
                                 action,
                                 outcome_state: delivered?.committed ? 'closed' : 'pending',
                                 success: delivered?.committed ? acceptedSuccess : highRisk ? undefined : acceptedSuccess,
-                                adapter_version: hook_contract_1.MCP_ADAPTER_VERSION,
+                                adapter_version: hook_contract_2.MCP_ADAPTER_VERSION,
                                 capability_level: 'mcp',
                             },
                         });