@getmarrow/mcp 3.9.78 → 3.9.80

package/README.md

@@ -116,7 +116,15 @@ 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 v3.9.78
+## What's New in v3.9.80
+
+v3.9.80 is a reliability patch for direct `marrow_think` and `marrow_commit` calls. Each invocation now carries one stable bounded idempotency key. Only the backend's documented pending-persistence states are reconciled, using the byte-identical request and key after a fixed one-second delay for at most three total attempts. A 202 response is never reported as successful completion; unknown, malformed, correlation-drifted, or exhausted pending responses fail closed with a structured error. Explicit caller-supplied idempotency keys remain unchanged, and durable `observed_unverified` outcomes retain their terminal, non-authorizing semantics.
+
+### Previous release: v3.9.79
+
+v3.9.79 aligns `marrow_replay_compare` with the production replay contract. Its public MCP schema now exposes two exclusive modes: fetch an existing comparison with `comparison_id`, or create one with `source_decision_id`, `baseline.decision_id`, and `candidate.decision_id`. Empty, incomplete, mixed-mode, blank-ID, unsafe-ID, same-decision, and undeclared content-bearing fields fail locally before any request, while comparison fetches and valid distinct-decision comparisons keep their existing behavior. Outbound baseline and candidate references contain only validated decision IDs and optional privacy-safe identifier labels. Replay comparison still uses only already-recorded durable evidence and never runs a model or replays customer content. This release requires SDK `^3.7.62`, keeping the active MCP dependency floor aligned with the current SDK release.
+
+## Previous: v3.9.78
 
 v3.9.78 separates durable post-action observation from action authorization. For outcome closure only, `marrow_commit` sends the existing `decision_id` to runtime and can use the backend's exact `outcome_observation_only` response to submit the already-completed result without forwarding its non-durable correlation ID as receipt evidence. That response never permits an action: it has `allow: false`, `durable: false`, and no authorization. The accepted result remains `committed: false`, `outcome_state: "observed_unverified"`, `authorization_granted: false`, and `trusted_learning_applied: false`; it is terminal delivery and is not retried from the local queue. Trusted promotion requires an explicit new commit attempt with the backend-required authorization and proof for the exact observed payload. Missing, malformed, conflicting, or cross-scope runtime truth still fails closed, and privacy-unsafe `instruction_ref` values such as dates and long numeric IDs now fail locally before any network call.
 

package/dist/cli.js

@@ -1398,10 +1398,17 @@ if (process.argv[2] !== 'keys') {
                     'This does not run a model or replay customer content; it returns complete or insufficient_evidence.',
                 inputSchema: {
                     type: 'object',
+                    additionalProperties: false,
                     properties: {
-                        comparison_id: { type: 'string', description: 'Fetch a prior replay comparison by id.' },
-                        source_decision_id: { type: 'string', description: 'Original task decision used to bind the comparison.' },
-                        workspace_binding_id: { type: 'string', description: 'Optional privacy-safe workspace binding from runtime.' },
+                        comparison_id: { type: 'string', minLength: 1, description: 'Fetch a prior replay comparison by id.' },
+                        source_decision_id: {
+                            type: 'string', minLength: 1, maxLength: 128, pattern: '^[A-Za-z0-9._:-]{1,128}$',
+                            description: 'Original task decision used to bind the comparison.',
+                        },
+                        workspace_binding_id: {
+                            type: 'string', minLength: 34, maxLength: 34, pattern: '^workspace_[a-f0-9]{24}$',
+                            description: 'Optional privacy-safe workspace binding from runtime.',
+                        },
                         constraints: {
                             type: 'object',
                             additionalProperties: false,
@@ -1419,16 +1426,43 @@ if (process.argv[2] !== 'keys') {
                         },
                         baseline: {
                             type: 'object',
-                            properties: { label: { type: 'string' }, decision_id: { type: 'string' } },
+                            additionalProperties: false,
+                            maxProperties: 2,
+                            properties: {
+                                label: { type: 'string', minLength: 1, maxLength: 80, pattern: '^[A-Za-z0-9._:-]{1,80}$' },
+                                decision_id: { type: 'string', minLength: 1, maxLength: 128, pattern: '^[A-Za-z0-9._:-]{1,128}$' },
+                            },
                             required: ['decision_id'],
                         },
                         candidate: {
                             type: 'object',
-                            properties: { label: { type: 'string' }, decision_id: { type: 'string' } },
+                            additionalProperties: false,
+                            maxProperties: 2,
+                            properties: {
+                                label: { type: 'string', minLength: 1, maxLength: 80, pattern: '^[A-Za-z0-9._:-]{1,80}$' },
+                                decision_id: { type: 'string', minLength: 1, maxLength: 128, pattern: '^[A-Za-z0-9._:-]{1,128}$' },
+                            },
                             required: ['decision_id'],
                         },
                     },
-                    required: [],
+                    oneOf: [
+                        {
+                            required: ['comparison_id'],
+                            not: {
+                                anyOf: [
+                                    { required: ['source_decision_id'] },
+                                    { required: ['workspace_binding_id'] },
+                                    { required: ['constraints'] },
+                                    { required: ['baseline'] },
+                                    { required: ['candidate'] },
+                                ],
+                            },
+                        },
+                        {
+                            required: ['source_decision_id', 'baseline', 'candidate'],
+                            not: { required: ['comparison_id'] },
+                        },
+                    ],
                 },
             },
             {