@exaudeus/workrail 3.67.0 → 3.68.1

package/dist/coordinators/modes/implement-shared.js

@@ -15,7 +15,7 @@ async function runReviewAndVerdictCycle(deps, opts, prUrl, coordinatorStartMs, i
         ? `Review PR for merge: ${prUrl}`
         : `Re-review PR after fixes (iteration ${iteration}): ${prUrl}`;
     deps.stderr(`[review-cycle] Spawning review session (iteration=${iteration}): ${reviewGoal.slice(0, 80)}`);
-    const reviewSpawnResult = await deps.spawnSession('mr-review-workflow-agentic', reviewGoal, opts.workspace, { prUrl });
+    const reviewSpawnResult = await deps.spawnSession('wr.mr-review', reviewGoal, opts.workspace, { prUrl });
     if (reviewSpawnResult.kind === 'err') {
         return {
             kind: 'escalated',
@@ -86,7 +86,7 @@ async function runReviewAndVerdictCycle(deps, opts, prUrl, coordinatorStartMs, i
             if (fixCutoff)
                 return fixCutoff;
             const fixGoal = `Fix review findings: ${findings.findingSummaries.slice(0, 3).join('; ')}`;
-            const fixSpawnResult = await deps.spawnSession('coding-task-workflow-agentic', fixGoal, opts.workspace, { prUrl, findings: findings.findingSummaries });
+            const fixSpawnResult = await deps.spawnSession('wr.coding-task', fixGoal, opts.workspace, { prUrl, findings: findings.findingSummaries });
             if (fixSpawnResult.kind === 'err') {
                 return {
                     kind: 'escalated',
@@ -124,8 +124,8 @@ async function runAuditChain(deps, opts, prUrl, coordinatorStartMs, severity, fi
     if (auditCutoff)
         return auditCutoff;
     const auditWorkflow = findings?.some((f) => f.findingCategory === 'architecture')
-        ? 'architecture-scalability-audit'
-        : 'production-readiness-audit';
+        ? 'wr.architecture-scalability-audit'
+        : 'wr.production-readiness-audit';
     const auditSpawnResult = await deps.spawnSession(auditWorkflow, `Audit PR before merge: ${prUrl}`, opts.workspace, { prUrl, severity });
     if (auditSpawnResult.kind === 'err') {
         try {
@@ -171,7 +171,7 @@ async function runAuditChain(deps, opts, prUrl, coordinatorStartMs, severity, fi
     const reReviewCutoff = (0, adaptive_pipeline_js_1.checkSpawnCutoff)(coordinatorStartMs, deps.now(), 're-review-after-audit');
     if (reReviewCutoff)
         return reReviewCutoff;
-    const reReviewSpawnResult = await deps.spawnSession('mr-review-workflow-agentic', `Re-review after audit: ${prUrl}`, opts.workspace, { prUrl, auditComplete: true });
+    const reReviewSpawnResult = await deps.spawnSession('wr.mr-review', `Re-review after audit: ${prUrl}`, opts.workspace, { prUrl, auditComplete: true });
     if (reReviewSpawnResult.kind === 'err') {
         try {
             await deps.postToOutbox(`Adaptive pipeline escalated: re-review after audit failed to spawn`, { prUrl, phase: 're-review-after-audit', reason: reReviewSpawnResult.error });

package/dist/coordinators/modes/implement.js

@@ -35,11 +35,11 @@ async function runImplementPipeline(deps, opts, pitchPath, coordinatorStartMs) {
 }
 async function runImplementCore(deps, opts, pitchPath, coordinatorStartMs) {
     if (touchesUI(opts.goal)) {
-        deps.stderr(`[implement] UX signals detected in goal, dispatching ui-ux-design-workflow`);
+        deps.stderr(`[implement] UX signals detected in goal, dispatching wr.ui-ux-design`);
         const cutoffCheck = (0, adaptive_pipeline_js_1.checkSpawnCutoff)(coordinatorStartMs, deps.now(), 'ux-gate');
         if (cutoffCheck)
             return cutoffCheck;
-        const uxSpawnResult = await deps.spawnSession('ui-ux-design-workflow', opts.goal, opts.workspace, {
+        const uxSpawnResult = await deps.spawnSession('wr.ui-ux-design', opts.goal, opts.workspace, {
             pitchPath,
         });
         if (uxSpawnResult.kind === 'err') {
@@ -70,8 +70,8 @@ async function runImplementCore(deps, opts, pitchPath, coordinatorStartMs) {
     const cutoffCheck = (0, adaptive_pipeline_js_1.checkSpawnCutoff)(coordinatorStartMs, deps.now(), 'coding');
     if (cutoffCheck)
         return cutoffCheck;
-    deps.stderr(`[implement] Spawning coding-task-workflow-agentic`);
-    const codingSpawnResult = await deps.spawnSession('coding-task-workflow-agentic', opts.goal, opts.workspace, {
+    deps.stderr(`[implement] Spawning wr.coding-task`);
+    const codingSpawnResult = await deps.spawnSession('wr.coding-task', opts.goal, opts.workspace, {
         pitchPath,
     });
     if (codingSpawnResult.kind === 'err') {

package/dist/coordinators/pr-review.js

@@ -383,7 +383,7 @@ async function runPrReviewCoordinator(deps, opts) {
     for (const pr of prs) {
         const goal = `Review PR #${pr.number} "${pr.title}" before merge`;
         if (opts.dryRun) {
-            log(`      PR #${pr.number} [dry-run] would spawn mr-review-workflow-agentic`);
+            log(`      PR #${pr.number} [dry-run] would spawn wr.mr-review`);
             continue;
         }
         let spawnContext;
@@ -405,7 +405,7 @@ async function runPrReviewCoordinator(deps, opts) {
                 deps.stderr(`[WARN coord:context prNumber=${pr.number}] priorSessionNotes failed: ${bundle.priorSessionNotes.error}`);
             }
         }
-        const spawnResult = await deps.spawnSession('mr-review-workflow-agentic', goal, opts.workspace, spawnContext);
+        const spawnResult = await deps.spawnSession('wr.mr-review', goal, opts.workspace, spawnContext);
         if (spawnResult.kind === 'err') {
             spawnErrors.set(pr.number, spawnResult.error);
             log(`      PR #${pr.number} spawn failed: ${spawnResult.error}`);
@@ -589,7 +589,7 @@ async function runFixAgentLoop(deps, opts, pr, initialFindings, initialOutcome,
             };
         }
         log(`      PR #${pr.number}  ->  spawning fix agent (pass ${passCount})...`);
-        const fixSpawnResult = await deps.spawnSession('coding-task-workflow-agentic', fixGoal, opts.workspace);
+        const fixSpawnResult = await deps.spawnSession('wr.coding-task', fixGoal, opts.workspace);
         if (fixSpawnResult.kind === 'err') {
             log(`      PR #${pr.number}  ->  fix agent spawn failed: ${fixSpawnResult.error}`);
             return {
@@ -636,7 +636,7 @@ async function runFixAgentLoop(deps, opts, pr, initialFindings, initialOutcome,
             };
         }
         const reReviewGoal = `Re-review PR #${pr.number} after fixes (pass ${passCount})`;
-        const reReviewSpawnResult = await deps.spawnSession('mr-review-workflow-agentic', reReviewGoal, opts.workspace, reviewSpawnContext);
+        const reReviewSpawnResult = await deps.spawnSession('wr.mr-review', reReviewGoal, opts.workspace, reviewSpawnContext);
         if (reReviewSpawnResult.kind === 'err') {
             log(`      PR #${pr.number}  ->  re-review spawn failed: ${reReviewSpawnResult.error}`);
             return {

package/dist/daemon/workflow-runner.d.ts

@@ -107,6 +107,7 @@ export declare function countOrphanStepAdvances(continueToken: string, ctx: V2To
 export declare function clearQueueIssueSidecars(sessionsDir: string): Promise<void>;
 export declare function stripFrontmatter(content: string): string;
 export declare function loadWorkspaceContext(workspacePath: string): Promise<string | null>;
+export declare function loadSessionNotes(continueToken: string, ctx: V2ToolContext): Promise<readonly string[]>;
 export declare function makeContinueWorkflowTool(sessionId: string, ctx: V2ToolContext, onAdvance: (nextStepText: string, continueToken: string) => void, onComplete: (notes: string | undefined, artifacts?: readonly unknown[]) => void, schemas: Record<string, any>, _executeContinueWorkflowFn?: typeof executeContinueWorkflow, emitter?: DaemonEventEmitter, workrailSessionId?: string | null): AgentTool;
 export declare function makeCompleteStepTool(sessionId: string, ctx: V2ToolContext, getCurrentToken: () => string, onAdvance: (nextStepText: string, continueToken: string) => void, onComplete: (notes: string | undefined, artifacts?: readonly unknown[]) => void, onTokenUpdate: (t: string) => void, schemas: Record<string, any>, _executeContinueWorkflowFn?: typeof executeContinueWorkflow, emitter?: DaemonEventEmitter, workrailSessionId?: string | null): AgentTool;
 export declare function makeBashTool(workspacePath: string, schemas: Record<string, any>, sessionId?: string, emitter?: DaemonEventEmitter, workrailSessionId?: string | null): AgentTool;

package/dist/daemon/workflow-runner.js

@@ -44,6 +44,7 @@ exports.countOrphanStepAdvances = countOrphanStepAdvances;
 exports.clearQueueIssueSidecars = clearQueueIssueSidecars;
 exports.stripFrontmatter = stripFrontmatter;
 exports.loadWorkspaceContext = loadWorkspaceContext;
+exports.loadSessionNotes = loadSessionNotes;
 exports.makeContinueWorkflowTool = makeContinueWorkflowTool;
 exports.makeCompleteStepTool = makeCompleteStepTool;
 exports.makeBashTool = makeBashTool;

package/dist/manifest.json

@@ -86,8 +86,8 @@
       "bytes": 1168
     },
     "application/services/compiler/template-registry.js": {
-      "sha256": "92f824723e8d137533f8c752f2f753bb2a88e5812631de0a6428e3c6ff44543a",
-      "bytes": 5283
+      "sha256": "6df7c3b29f7eb62459e86bbafc7d279e19e95d363e820ca46ddb3e4daba6951b",
+      "bytes": 5453
     },
     "application/services/enhanced-error-service.d.ts": {
       "sha256": "b6fe8fad92717f0962f87aa9c0f88277bf28fe2b5e3cfd7875612ee57eb8c684",
@@ -358,8 +358,8 @@
       "bytes": 1041
     },
     "cli/commands/worktrain-init.js": {
-      "sha256": "179afa86b7bb235ede92693ce45249cd30f0056841bdede6583f86a2124eb0dd",
-      "bytes": 12528
+      "sha256": "726d5b3a6252bf25d99fa53445ec543ea7e8c3d020a845c0b13c08182876fdb9",
+      "bytes": 12514
     },
     "cli/commands/worktrain-overview.d.ts": {
       "sha256": "d9cb907b57aaa19ee5654c1726a33cdc6b7a54e3bd24dd8f2900d18491dd94a3",
@@ -477,12 +477,12 @@
       "sha256": "40290b50e21ee7e82433efe13b1aa31c1ea608bd057a5c4e324982f284bc928b",
       "bytes": 60673
     },
-    "console-ui/assets/index-tOl8Vowf.js": {
-      "sha256": "f598d8869c96cf01f1adc245ac289f9614d7616ce1d8f0a86a0bb9665a26fe5d",
+    "console-ui/assets/index-DPdRJHMX.js": {
+      "sha256": "5d77b82c529f8adaf1ce398dbab3a2c9a74d4f3e0cb59318f13967d2b659aa5f",
       "bytes": 767983
     },
     "console-ui/index.html": {
-      "sha256": "908a96c5cb785772a69156cc4c8abaa821f37104d8b7ed0ce0f8db077d7d62e3",
+      "sha256": "e9b7fc1c2488485be8d965ba96d0ce2e29c1b59b7fdd09d194625341120ec404",
       "bytes": 417
     },
     "console/standalone-console.d.ts": {
@@ -538,24 +538,24 @@
       "bytes": 462
     },
     "coordinators/modes/full-pipeline.js": {
-      "sha256": "945d726d728235f8f31f03f33fbde8f6614472b38921a44fba42da959875f37d",
-      "bytes": 13201
+      "sha256": "040b412e33ecb46dcc27c9968c9c0cc5d416880a03dab6f93ed09b8f447c21aa",
+      "bytes": 13161
     },
     "coordinators/modes/implement-shared.d.ts": {
       "sha256": "fbad9d91d84d2112b273175618686489a7f106385e0e62d6cab80804d6d0f2d7",
       "bytes": 708
     },
     "coordinators/modes/implement-shared.js": {
-      "sha256": "117eec98c38826e62150e4ca1ece6ac1cad91b2d0d7128dc34acb609151e4619",
-      "bytes": 13672
+      "sha256": "96f95d9fca1c511eb1b12247148d0e0de3dd3add5aacd72e2a8bba4b36f5995b",
+      "bytes": 13636
     },
     "coordinators/modes/implement.d.ts": {
       "sha256": "23919c24d62a0bf15296a52fbc594cca8b1b34e6f8d98dcf7dede8d97ad4cabb",
       "bytes": 347
     },
     "coordinators/modes/implement.js": {
-      "sha256": "e05ad7330c00db7b2ad8baf27e224616eae1b5cce460a0394a80633fca8827bf",
-      "bytes": 5522
+      "sha256": "59b0dddf00587db1d565c1e460cdad1f75b4ca32687e3649452b0f4de90a3061",
+      "bytes": 5482
     },
     "coordinators/modes/quick-review.d.ts": {
       "sha256": "03a4f29a07047b0bf788d84f8e0ebab63d64c8eb98aa57087943a8fb84563998",
@@ -578,8 +578,8 @@
       "bytes": 3947
     },
     "coordinators/pr-review.js": {
-      "sha256": "870d8baaaec89ebd1bf789a8c03e217c9866b5d89b828ef6efe3bdf3814155f4",
-      "bytes": 32475
+      "sha256": "385baa9e6252dbd84060bb423ce219884d519752f4a6e9f8f04e5f503fa38b67",
+      "bytes": 32419
     },
     "coordinators/routing/route-task.d.ts": {
       "sha256": "6661d21e5cfbc9dffbfd8c2f9aaaf0e30a3251997a2c69c6a1b09929343e30e3",
@@ -654,12 +654,12 @@
       "bytes": 5921
     },
     "daemon/workflow-runner.d.ts": {
-      "sha256": "784dea8d1b86c162bd025706273e07e622cef8bfeeee5c465e09b92f1552dfbd",
-      "bytes": 8114
+      "sha256": "eba5089ec9210f27a06dc1c3fc89804de4d77208fad7678df2ad824c4511636f",
+      "bytes": 8227
     },
     "daemon/workflow-runner.js": {
-      "sha256": "2718b3dcf42846c3aec5ae6533c377bf58c0dc1c9f450d0cc016649296ae39af",
-      "bytes": 101417
+      "sha256": "b11fb90d06e7d2f45b76e05640475615295de4eadb89c0c3d1c18ed48d6d0cb4",
+      "bytes": 101462
     },
     "di/container.d.ts": {
       "sha256": "003bb7fb7478d627524b9b1e76bd0a963a243794a687ff233b96dc0e33a06d9f",
@@ -1106,8 +1106,8 @@
       "bytes": 674
     },
     "mcp/handlers/v2-context-budget.js": {
-      "sha256": "5450c08d25900fd639090ba0090fc4c866e02295ee11aa52c187447424fdc4c2",
-      "bytes": 7199
+      "sha256": "e27121c84449f8bdcbcd37a242db54c1afda4a14bc6bc50e148aaf96fecd45b3",
+      "bytes": 8181
     },
     "mcp/handlers/v2-error-mapping.d.ts": {
       "sha256": "4522217a754afc6a2ee3834368decb7fb22ebf9d4c72fc0de9890903d652d76c",
@@ -1234,8 +1234,8 @@
       "bytes": 4343
     },
     "mcp/handlers/v2-workflow.js": {
-      "sha256": "ed2594e771344c5c3fed99e92b196f72dcfdf1d34ef8dc911bf6e9a12669ef0d",
-      "bytes": 28075
+      "sha256": "4b12fcb52c80bf2b141c99921d2ddae92da2f543ae65abc5035c0b794bd777b6",
+      "bytes": 28078
     },
     "mcp/handlers/v2-workspace-resolution.d.ts": {
       "sha256": "dd4de57b4918ebe749cf8c1df70c02bf1effc50932634bae60db53c9a157e872",
@@ -1514,8 +1514,8 @@
       "bytes": 1863
     },
     "mcp/workflow-protocol-contracts.js": {
-      "sha256": "d57a075134f5e7ff7d6ce78f64572ef0322c16943f67a6c974795c5dad241277",
-      "bytes": 14372
+      "sha256": "bcd0a058385ab23d2ff550267bfc88ac06b5d89ed2d773086a3cf83431a86c4f",
+      "bytes": 14344
     },
     "mcp/workflow-tool-edition-selector.d.ts": {
       "sha256": "75194908a89aaf7dc48fb661aea099827e7032ec76daf8f2de91bd59d46764ef",
@@ -1894,12 +1894,12 @@
       "bytes": 447
     },
     "v2/durable-core/constants.d.ts": {
-      "sha256": "763799ad89e664118c556e6d496809f12f3f946a3083641aa5b5c5c15a7692ba",
-      "bytes": 3991
+      "sha256": "14b721867f0866a9a2955b19f16868c39394e80dce2bd94021e6e7f6b4f62429",
+      "bytes": 4159
     },
     "v2/durable-core/constants.js": {
-      "sha256": "9bfd85c65d303953aefd4bad643a8bc51f8cbca741bfcc0a87c6f464f5cf73dc",
-      "bytes": 3877
+      "sha256": "21a7a514d3a365c7e7690c1c57dd402a25686bfd2dea38082fcc02ee6c266a5c",
+      "bytes": 3987
     },
     "v2/durable-core/domain/ack-advance-append-plan.d.ts": {
       "sha256": "2b4a8ad0e1d9e9066f100f958e572f19af590ab70946c2396d2d5568875bdf00",
@@ -3066,8 +3066,8 @@
       "bytes": 730
     },
     "v2/projections/session-metrics.js": {
-      "sha256": "89a1ee5aae79a19c7fc60840e62741a7dd93028562e72cd26a15e4988953c6c4",
-      "bytes": 3421
+      "sha256": "89dd4c149087234e3f4f18382340a9f855942fd96595783b7d7ad5c76449536a",
+      "bytes": 3370
     },
     "v2/read-only/v1-to-v2-shim.d.ts": {
       "sha256": "b122df1d4eb4119b65465baa00f157ca4466575d3bc6ac20054a361eaff48e02",

package/dist/mcp/handlers/v2-context-budget.js

@@ -149,6 +149,24 @@ function checkContextBudget(args) {
             }),
         };
     }
+    const rawMetricsOutcome = contextObj['metrics_outcome'];
+    if (rawMetricsOutcome !== undefined && rawMetricsOutcome !== null) {
+        if (!constants_js_1.VALID_METRICS_OUTCOME.includes(rawMetricsOutcome)) {
+            const details = {
+                kind: 'context_invalid_metrics_outcome',
+                tool: args.tool,
+                invalidValue: String(rawMetricsOutcome),
+                validValues: [...constants_js_1.VALID_METRICS_OUTCOME],
+            };
+            return {
+                ok: false,
+                error: (0, types_js_1.errNotRetryable)('VALIDATION_ERROR', `context.metrics_outcome has invalid value "${String(rawMetricsOutcome)}" for ${args.tool}. Valid values: ${constants_js_1.VALID_METRICS_OUTCOME.map(v => `"${v}"`).join(', ')}.`, {
+                    suggestion: 'Set metrics_outcome to one of the valid enum values listed in validValues.',
+                    details: details,
+                }),
+            };
+        }
+    }
     return { ok: true };
 }
 function collectArtifactsForEvaluation(args) {

package/dist/mcp/handlers/v2-workflow.js

@@ -136,7 +136,7 @@ function computeWorkflowStaleness(stamp, currentVersion) {
     if (stamp === undefined) {
         return {
             level: 'possible',
-            reason: 'This workflow has not been validated against the authoring spec via workflow-for-workflows.',
+            reason: 'This workflow has not been validated against the authoring spec via wr.workflow-for-workflows.',
         };
     }
     if (stamp === currentVersion) {

package/dist/mcp/workflow-protocol-contracts.js

@@ -61,7 +61,7 @@ exports.START_WORKFLOW_PROTOCOL = {
                 'Only pass context on later continue_workflow calls if facts changed.',
             ],
             examplePayload: {
-                workflowId: 'coding-task-workflow-agentic',
+                workflowId: 'wr.coding-task',
                 workspacePath: '/Users/you/git/my-project',
                 goal: 'implement OAuth refresh token rotation',
             },
@@ -77,7 +77,7 @@ exports.START_WORKFLOW_PROTOCOL = {
                 'Pass goal on every call. A short sentence describing what you are trying to accomplish.',
             ],
             examplePayload: {
-                workflowId: 'coding-task-workflow-agentic',
+                workflowId: 'wr.coding-task',
                 workspacePath: '/Users/you/git/my-project',
                 goal: 'implement OAuth refresh token rotation',
             },

package/dist/v2/durable-core/constants.d.ts

@@ -86,3 +86,5 @@ export declare const AUTONOMY_MODE: {
     readonly FULL_AUTO_STOP_ON_USER_DEPS: "full_auto_stop_on_user_deps";
 };
 export type AutonomyModeV1 = typeof AUTONOMY_MODE[keyof typeof AUTONOMY_MODE];
+export declare const VALID_METRICS_OUTCOME: readonly ["success", "partial", "abandoned", "error"];
+export type MetricsOutcome = (typeof VALID_METRICS_OUTCOME)[number];

package/dist/v2/durable-core/constants.js

@@ -1,6 +1,6 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.AUTONOMY_MODE = exports.ADVANCE_INTENT = exports.MANIFEST_KIND = exports.EDGE_CAUSE = exports.ADVANCE_OUTCOME = exports.ENGINE_STATE = exports.EDGE_KIND = exports.PAYLOAD_KIND = exports.OUTPUT_CHANNEL = exports.EVENT_KIND = exports.DELIMITER_SAFE_ID_PATTERN = exports.SHA256_DIGEST_PATTERN = exports.MAX_RESUME_PREVIEW_BYTES = exports.RECOVERY_BUDGET_BYTES = exports.TRUNCATION_MARKER = exports.DEFAULT_RETRY_AFTER_MS = exports.SESSION_LOCK_RETRY_AFTER_MS = exports.MAX_OBSERVATION_PATH_LENGTH = exports.MAX_OBSERVATION_SHORT_STRING_LENGTH = exports.MAX_CONTEXT_DEPTH = exports.MAX_CONTEXT_BYTES = exports.MAX_VALIDATION_SUGGESTIONS_BYTES = exports.MAX_VALIDATION_ISSUES_BYTES = exports.MAX_VALIDATION_SUGGESTION_ITEM_BYTES = exports.MAX_VALIDATION_ISSUE_ITEM_BYTES = exports.MAX_OUTPUT_NOTES_MARKDOWN_BYTES = exports.MAX_DECISION_TRACE_TOTAL_BYTES = exports.MAX_DECISION_TRACE_ENTRY_SUMMARY_BYTES = exports.MAX_DECISION_TRACE_ENTRIES = exports.MAX_BLOCKER_SUGGESTED_FIX_BYTES = exports.MAX_BLOCKER_MESSAGE_BYTES = exports.MAX_BLOCKERS = void 0;
+exports.VALID_METRICS_OUTCOME = exports.AUTONOMY_MODE = exports.ADVANCE_INTENT = exports.MANIFEST_KIND = exports.EDGE_CAUSE = exports.ADVANCE_OUTCOME = exports.ENGINE_STATE = exports.EDGE_KIND = exports.PAYLOAD_KIND = exports.OUTPUT_CHANNEL = exports.EVENT_KIND = exports.DELIMITER_SAFE_ID_PATTERN = exports.SHA256_DIGEST_PATTERN = exports.MAX_RESUME_PREVIEW_BYTES = exports.RECOVERY_BUDGET_BYTES = exports.TRUNCATION_MARKER = exports.DEFAULT_RETRY_AFTER_MS = exports.SESSION_LOCK_RETRY_AFTER_MS = exports.MAX_OBSERVATION_PATH_LENGTH = exports.MAX_OBSERVATION_SHORT_STRING_LENGTH = exports.MAX_CONTEXT_DEPTH = exports.MAX_CONTEXT_BYTES = exports.MAX_VALIDATION_SUGGESTIONS_BYTES = exports.MAX_VALIDATION_ISSUES_BYTES = exports.MAX_VALIDATION_SUGGESTION_ITEM_BYTES = exports.MAX_VALIDATION_ISSUE_ITEM_BYTES = exports.MAX_OUTPUT_NOTES_MARKDOWN_BYTES = exports.MAX_DECISION_TRACE_TOTAL_BYTES = exports.MAX_DECISION_TRACE_ENTRY_SUMMARY_BYTES = exports.MAX_DECISION_TRACE_ENTRIES = exports.MAX_BLOCKER_SUGGESTED_FIX_BYTES = exports.MAX_BLOCKER_MESSAGE_BYTES = exports.MAX_BLOCKERS = void 0;
 exports.MAX_BLOCKERS = 10;
 exports.MAX_BLOCKER_MESSAGE_BYTES = 512;
 exports.MAX_BLOCKER_SUGGESTED_FIX_BYTES = 1024;
@@ -82,3 +82,4 @@ exports.AUTONOMY_MODE = {
     FULL_AUTO_NEVER_STOP: 'full_auto_never_stop',
     FULL_AUTO_STOP_ON_USER_DEPS: 'full_auto_stop_on_user_deps',
 };
+exports.VALID_METRICS_OUTCOME = ['success', 'partial', 'abandoned', 'error'];

package/dist/v2/projections/session-metrics.js

@@ -40,7 +40,7 @@ function projectSessionMetricsV2(events) {
     const durationMs = typeof d.durationMs === 'number' && Number.isFinite(d.durationMs) ? d.durationMs : undefined;
     const captureConfidence = d.captureConfidence === 'high' ? 'high' : 'none';
     const outcomeRaw = metricsContext['metrics_outcome'];
-    const outcome = outcomeRaw === 'success' || outcomeRaw === 'partial' || outcomeRaw === 'abandoned' || outcomeRaw === 'error'
+    const outcome = constants_js_1.VALID_METRICS_OUTCOME.includes(outcomeRaw)
         ? outcomeRaw
         : null;
     const prNumbers = [];

package/docs/authoring-v2.md

@@ -240,7 +240,7 @@ Profile selection guide:
 | `"research"` | Workflow produces a finding or recommendation but no commits | Outcome-only reminder on final step only |
 | `"none"` or absent | Meta-workflows, utilities, authoring tools | No injection -- existing behavior unchanged |
 
-The engine does NOT derive the profile from tags automatically. Authors must set this field explicitly. When using `workflow-for-workflows` to author or modernize a workflow, the `phase-7b` step will prompt you for this decision.
+The engine does NOT derive the profile from tags automatically. Authors must set this field explicitly. When using `wr.workflow-for-workflows` to author or modernize a workflow, the `phase-7b` step will prompt you for this decision.
 
 **Final step detection**: The engine injects the final-step footer on the last top-level step, or on the exit step of a loop that is the last top-level step. A loop in a non-terminal position does not trigger the final-step footer on its exit step.
 
@@ -551,11 +551,11 @@ To keep authoring simple:
 
 Workflows can drift out of sync with the authoring spec they were written against. WorkRail surfaces this as a `staleness` signal in `list_workflows` and `inspect_workflow` output.
 
-**How it works:** Workflows carry an optional `validatedAgainstSpecVersion` field stamped by `workflow-for-workflows` after the quality gate passes. The engine compares this against the current `spec/authoring-spec.json` version at list/inspect time and returns:
+**How it works:** Workflows carry an optional `validatedAgainstSpecVersion` field stamped by `wr.workflow-for-workflows` after the quality gate passes. The engine compares this against the current `spec/authoring-spec.json` version at list/inspect time and returns:
 
 - `none` — workflow was validated against the current spec version
 - `likely` — spec was updated since the workflow was last reviewed
-- `possible` — workflow has never been run through `workflow-for-workflows`
+- `possible` — workflow has never been run through `wr.workflow-for-workflows`
 
 **Stamping a workflow:**
 
@@ -564,7 +564,7 @@ npm run stamp-workflow -- workflows/my-workflow.json
 git add workflows/my-workflow.json && git commit -m "chore: stamp workflow"
 ```
 
-The stamp must be committed to take effect. The `workflow-for-workflows` Phase 7 step includes a reminder to do this.
+The stamp must be committed to take effect. The `wr.workflow-for-workflows` Phase 7 step includes a reminder to do this.
 
 **Visibility:** By default, the staleness signal is only shown for user-owned/imported workflows (`personal`, `rooted_sharing`, `external`). Built-in and legacy_project workflows are excluded. Set `WORKRAIL_DEV=1` to see staleness for all categories (useful for catalog maintenance).
 

package/docs/changelog-recent.md

@@ -117,7 +117,7 @@ Structured migration workflow for moving code between platforms (Android to iOS,
 
 Since you've created workflows yourself, these changes are directly relevant.
 
-### `workflow-for-workflows.v2.json` was rebuilt
+### `wr.workflow-for-workflows.v2.json` was rebuilt
 
 The workflow used to create or modernize other workflows was significantly redesigned. The full phase structure now includes:
 
@@ -179,12 +179,12 @@ A visual catalog of every available workflow. Eight category filter pills. Click
 WorkRail can now detect when a workflow hasn't been reviewed against the current authoring spec. Three signal levels:
 
 - `none` -- validated against the current spec (has a version stamp and it's current)
-- `possible` -- no version stamp (was never run through `workflow-for-workflows`)
+- `possible` -- no version stamp (was never run through `wr.workflow-for-workflows`)
 - `likely` -- has a stamp, but the spec has been updated since the workflow was last reviewed
 
 This shows up in `list_workflows` output (agents see it) and in the CI registry validation check. It's shown only for non-built-in workflows -- built-in workflows ship with their own quality process and don't show staleness signals.
 
-**What this means for your team:** Your team's existing workflows will show as `possible` (no stamp) until they're run through `workflow-for-workflows.v2.json`. That's expected -- it's not an error, just a signal that they haven't been through the new quality gate. Over time, as you modernize them, they'll show `none`.
+**What this means for your team:** Your team's existing workflows will show as `possible` (no stamp) until they're run through `wr.workflow-for-workflows.v2.json`. That's expected -- it's not an error, just a signal that they haven't been through the new quality gate. Over time, as you modernize them, they'll show `none`.
 
 ---
 

package/docs/configuration.md

@@ -407,7 +407,7 @@ When `isComplete: true` is returned, summarize all work done across the workflow
 After creating this file, the agent becomes available via the Agent tool:
 
 ```
-Agent(subagent_type="workrail-executor", prompt="Start the bug-investigation-agentic workflow...")
+Agent(subagent_type="workrail-executor", prompt="Start the wr.bug-investigation workflow...")
 ```
 
 ### Cursor

package/docs/design/adaptive-coordinator-context-candidates.md

@@ -59,7 +59,7 @@ Must stay consistent with:
 - `src/v2/durable-core/schemas/artifacts/` (typed artifact schemas)
 - `workflows/wr.discovery.json` (Phase 7 -- if emitting artifact)
 - `workflows/wr.shaping.json` (Step 1 -- if adding file search)
-- `workflows/coding-task-workflow-agentic.json` (Phase 0.5 -- no changes expected)
+- `workflows/wr.coding-task.json` (Phase 0.5 -- no changes expected)
 
 ---
 

package/docs/design/adaptive-coordinator-context.md

@@ -73,7 +73,7 @@ WorkTrain sessions are fully isolated. Each spawned session starts from the work
 
 **1. File-based handoff (wr.shaping -> coding):**
 - `wr.shaping` Step 9 writes `.workrail/current-pitch.md` at the workspace path
-- `coding-task-workflow-agentic` Phase 0.5 actively searches for upstream docs via repo search, WebFetch, MCP integrations
+- `wr.coding-task` Phase 0.5 actively searches for upstream docs via repo search, WebFetch, MCP integrations
 - Phase 0.5 would find `.workrail/current-pitch.md` automatically
 - **Status: effectively already works** -- no coordinator intervention needed for Shaping->Coding
 

package/docs/design/adaptive-coordinator-routing-candidates.md

@@ -16,9 +16,9 @@
 
 3. **Monolithic coordinator vs per-mode decomposition**: `pr-review.ts` is 1462 lines for one pipeline mode. Five modes in one file would be unmanageable. The right architecture decomposes into mode files with a thin dispatcher -- but this requires deciding the seam deliberately.
 
-4. **`recommendedPipeline` verbatim vs advisory**: If classify-task-workflow's pipeline output is authoritative, the coordinator cannot apply static overrides. If advisory, the coordinator re-implements routing and classify-task's rules become redundant for common cases.
+4. **`recommendedPipeline` verbatim vs advisory**: If wr.classify-task's pipeline output is authoritative, the coordinator cannot apply static overrides. If advisory, the coordinator re-implements routing and classify-task's rules become redundant for common cases.
 
-5. **Phase 0.5 vs coordinator routing for upstream context**: `coding-task-workflow-agentic` Phase 0.5 auto-detects `pitch.md`. The coordinator's "should I skip shaping?" routing decision partially overlaps with this detection. They must agree.
+5. **Phase 0.5 vs coordinator routing for upstream context**: `wr.coding-task` Phase 0.5 auto-detects `pitch.md`. The coordinator's "should I skip shaping?" routing decision partially overlaps with this detection. They must agree.
 
 ### What the codebase already solves (and how)
 
@@ -29,12 +29,12 @@
 - Escalation-first: every failure produces `escalated: true` + `escalationReason`, never silent substitution
 - TRACE log before acting on routing decision
 
-**`classify-task-workflow.json`:**
+**`wr.classify-task.json`:**
 - Exists as of v3.40.0. Single LLM step, no tools, outputs `recommendedPipeline` as ordered workflow ID array
 - Output format: structured text block with `recommendedPipeline: ["...", "..."]` line
 - Note: `spawn_agent` does NOT return artifacts (v3.40.0 limitation #5) -- output must be read via `spawnSession` + `awaitSessions` + `getAgentResult` + note parsing
 
-**Phase 0.5 (`coding-task-workflow-agentic`):**
+**Phase 0.5 (`wr.coding-task`):**
 - Already detects `pitch.md` and sets `solutionFixed=true`, skipping design phases
 - The coordinator's "IMPLEMENT mode" (skip discovery/shaping) and Phase 0.5 are complementary, not conflicting
 
@@ -78,7 +78,7 @@ From CLAUDE.md (stated) and pr-review.ts (practiced):
 - `src/cli-worktrain.ts` -- needs `worktrain run pipeline` subcommand wiring
 - `src/coordinators/pr-review.ts` -- must remain unchanged; new coordinator is additive
 - `src/trigger/types.ts` -- if Candidate D's `pipelineMode` field is added; otherwise unchanged
-- `workflows/classify-task-workflow.json` -- coordinator depends on its note output format; format changes break parsing
+- `workflows/wr.classify-task.json` -- coordinator depends on its note output format; format changes break parsing
 - `src/coordinators/routing/route-task.ts` (new) -- pure routing function; all mode selection logic lives here
 - `src/coordinators/modes/*.ts` (new files) -- each mode's pipeline execution logic
 - Test suite: each mode coordinator needs its own unit tests with `CoordinatorDeps` fakes
@@ -110,8 +110,8 @@ type PipelineMode =
 **Per-mode pipelines:**
 - REVIEW_ONLY: `mr-review-workflow.agentic.v2` -> route by verdict
 - QUICK_REVIEW: same + light model config, no arch audit override
-- IMPLEMENT: `coding-task-workflow-agentic` (Phase 0.5 picks up pitch) -> PR -> review -> merge
-- FULL: `wr.discovery` -> `wr.shaping` -> `coding-task-workflow-agentic` -> PR -> review -> merge
+- IMPLEMENT: `wr.coding-task` (Phase 0.5 picks up pitch) -> PR -> review -> merge
+- FULL: `wr.discovery` -> `wr.shaping` -> `wr.coding-task` -> PR -> review -> merge
 
 **Tensions resolved:** determinism, YAGNI, no LLM latency.
 **Tensions accepted:** all ambiguous tasks fall to FULL (wasteful for Medium complexity tasks that don't need full discovery).
@@ -125,14 +125,14 @@ type PipelineMode =
 
 ---
 
-### Candidate B: classify-task-workflow as authoritative source
+### Candidate B: wr.classify-task as authoritative source
 
-**Summary:** Always spawn `classify-task-workflow` first, parse `recommendedPipeline` output, execute the returned workflow sequence. Pipeline modes are not named at the coordinator level.
+**Summary:** Always spawn `wr.classify-task` first, parse `recommendedPipeline` output, execute the returned workflow sequence. Pipeline modes are not named at the coordinator level.
 
 **Architecture:**
 ```typescript
 async function routeTask(goal, workspace, deps): Promise<Result<readonly string[], string>> {
-  const handle = await deps.spawnSession('classify-task-workflow', `Classify: ${goal}`, workspace);
+  const handle = await deps.spawnSession('wr.classify-task', `Classify: ${goal}`, workspace);
   await deps.awaitSessions([handle], CLASSIFY_TIMEOUT_MS); // 3 minutes max
   const agentResult = await deps.getAgentResult(handle);
   return parseRecommendedPipeline(agentResult.recapMarkdown);
@@ -141,12 +141,12 @@ async function routeTask(goal, workspace, deps): Promise<Result<readonly string[
 
 `parseRecommendedPipeline` is a pure function parsing the text block (two-tier: JSON array first, regex fallback).
 
-**Fallback:** if parsing fails, default to `['wr.discovery', 'coding-task-workflow-agentic', 'mr-review-workflow.agentic.v2']`.
+**Fallback:** if parsing fails, default to `['wr.discovery', 'wr.coding-task', 'mr-review-workflow.agentic.v2']`.
 
 **Tensions resolved:** intelligent routing for all tasks including ambiguous ones; single source of truth for pipeline selection rules.
 **Tensions accepted:** non-deterministic; 5-15 second LLM latency per dispatch; no typed `PipelineMode` discriminated union (pipeline is a string[] at coordinator level).
-**Boundary:** classify-task-workflow is the routing authority; coordinator is a runner.
-**Failure mode:** classify-task-workflow misclassifies a PR-only task and returns discovery+coding phases, wasting 30+ minutes. Recovery: add a pre-check for PR number before spawning classify-task (hybrid).
+**Boundary:** wr.classify-task is the routing authority; coordinator is a runner.
+**Failure mode:** wr.classify-task misclassifies a PR-only task and returns discovery+coding phases, wasting 30+ minutes. Recovery: add a pre-check for PR number before spawning classify-task (hybrid).
 **Repo pattern:** departs from determinism-over-cleverness principle. No named discriminated union.
 **Gain:** routing rules live in a workflow file -- updatable without code deployment.
 **Give up:** determinism, transparency, typed modes, dispatch speed for obvious cases.
@@ -157,7 +157,7 @@ async function routeTask(goal, workspace, deps): Promise<Result<readonly string[
 
 ### Candidate C: Static-first with LLM fallback (hybrid, recommended for routing)
 
-**Summary:** Two-tier `routeTask()`: Tier 1 applies static rules (pure, covers 80% of cases); Tier 2 falls back to classify-task-workflow for ambiguous tasks and returns a `CLASSIFY_AND_RUN` mode.
+**Summary:** Two-tier `routeTask()`: Tier 1 applies static rules (pure, covers 80% of cases); Tier 2 falls back to wr.classify-task for ambiguous tasks and returns a `CLASSIFY_AND_RUN` mode.
 
 **PipelineMode type (6 variants):**
 ```typescript
@@ -180,7 +180,7 @@ async function routeTask(
   // Tier 1: static (pure, no I/O except filesystem check for pitch.md)
   const staticMode = applyStaticRules(goal, workspace);
   if (staticMode !== null) return ok(staticMode);
-  // Tier 2: classify-task-workflow
+  // Tier 2: wr.classify-task
   const classified = await runClassification(goal, workspace, deps);
   if (classified.kind === 'err') return err(`classification failed: ${classified.error}`);
   return ok({ kind: 'CLASSIFY_AND_RUN', classifiedPipeline: classified.value, goal });
@@ -293,7 +293,7 @@ export async function runAdaptivePipeline(
 
 ### Recommendation: Candidate C (routing mechanism) + Candidate E (architecture)
 
-**Routing (C):** Two-tier static-first with LLM fallback. Static rules cover the 4 well-defined cases at zero cost and latency. `CLASSIFY_AND_RUN` handles genuinely ambiguous tasks via classify-task-workflow. This precisely mirrors the `parseFindingsFromNotes` two-tier strategy already established in `pr-review.ts`.
+**Routing (C):** Two-tier static-first with LLM fallback. Static rules cover the 4 well-defined cases at zero cost and latency. `CLASSIFY_AND_RUN` handles genuinely ambiguous tasks via wr.classify-task. This precisely mirrors the `parseFindingsFromNotes` two-tier strategy already established in `pr-review.ts`.
 
 **Architecture (E):** Per-mode coordinator files with thin dispatcher. Each mode file follows `pr-review.ts` independently. The dispatcher's `switch(mode.kind)` is exhaustive with `assertNever`. Adding a new mode is additive.
 
@@ -301,7 +301,7 @@ export async function runAdaptivePipeline(
 
 ### Why not A (pure static)?
 
-Candidate A is simpler but all tasks without static signals fall to FULL (wr.discovery + wr.shaping + coding). A genuinely vague idea needs FULL. But a Medium complexity coding task with no pitch.md and no PR number -- e.g., `"refactor auth.ts to use Result types"` -- also falls to FULL, running unnecessary discovery phases. Candidate C covers this case with classify-task-workflow returning `['coding-task-workflow-agentic', 'mr-review-workflow.agentic.v2']`.
+Candidate A is simpler but all tasks without static signals fall to FULL (wr.discovery + wr.shaping + coding). A genuinely vague idea needs FULL. But a Medium complexity coding task with no pitch.md and no PR number -- e.g., `"refactor auth.ts to use Result types"` -- also falls to FULL, running unnecessary discovery phases. Candidate C covers this case with wr.classify-task returning `['wr.coding-task', 'mr-review-workflow.agentic.v2']`.
 
 ### Why not B (pure LLM)?
 
@@ -319,7 +319,7 @@ Non-deterministic routing is unacceptable for the coordinator. A PR review task
 
 ### Pivot conditions
 
-1. If classify-task-workflow format drifts and `parseRecommendedPipeline` fails more than 10% of the time -> pivot to pure static (Candidate A) and accept FULL as default for ambiguous tasks
+1. If wr.classify-task format drifts and `parseRecommendedPipeline` fails more than 10% of the time -> pivot to pure static (Candidate A) and accept FULL as default for ambiguous tasks
 2. If trigger operators need deterministic routing for automated workflows -> add `pipelineMode` to TriggerDefinition (Candidate D addition)
 3. If context-passing agent's design requires structured handoff data from routing to mode executors -> add a `contextBundle` field to mode types (implementation change, not routing design change)
 

package/docs/design/adaptive-coordinator-routing-review.md

@@ -151,6 +151,6 @@ Even though not called at MVP, having the pure function ready preserves the upgr
 
 1. **wr.discovery output standardization**: the routing design assumes wr.discovery notes are injected by the coordinator as `assembledContextSummary` for wr.shaping. But wr.discovery's `designDocPath` output location is not standardized (finding from context-passing agent's doc). The FULL mode executor must parse `lastStepNotes` from the discovery session to build the shaping context -- this is per the context-passing agent's Candidate D (coordinator-injected text). This concern is correctly owned by the context-passing design, not the routing design.
 
-2. **classify-task-workflow format stability**: if `parseRecommendedPipeline()` is written as a pure function now, it has no tests against real classify-task output. The function should include an integration test stub that documents the expected format.
+2. **wr.classify-task format stability**: if `parseRecommendedPipeline()` is written as a pure function now, it has no tests against real classify-task output. The function should include an integration test stub that documents the expected format.
 
 3. **REVIEW_ONLY vs pr-review coordinator**: the existing `worktrain run pr-review` command already provides REVIEW_ONLY+QUICK_REVIEW behavior. The new `worktrain run pipeline --mode review_only` should either (a) delegate to pr-review coordinator, or (b) reimplement the same logic in `modes/review-only.ts`. Recommendation: (a) delegate -- avoid duplicating the fix-agent loop logic. Document this delegation explicitly.