@bastani/atomic 0.9.3 → 0.9.4-alpha.10

package/dist/builtin/workflows/builtin/ralph-models.ts

@@ -1,27 +1,42 @@
 import { reviewDecisionSchema } from "./ralph-core.js";
 
+// Model chains are curated from Atomic's agentic-coding benchmark
+// (pass@1 / avg $ per task, 2026-07-02):
+// - Placement principle: REVIEWERS get best-in-class verification quality
+//   (fable-5:xhigh 70%/$13.41 leads reviewer-A and the goal reviewer);
+//   EVERY OTHER stage gets the best measured performance-per-dollar
+//   (gpt-5.5:xhigh 67%/$7.23 for hard stages, gpt-5.5:medium 54%/$2.75 for
+//   workhorse stages, gpt-5.5:low $1.20 for retrieval).
+// - Pareto frontier: gpt-5.5 low ($1.20/27%) → gpt-5.5 medium ($2.75/54%) →
+//   fable-5 low ($3.76/60%) → gpt-5.5 high ($5.10/64%) → fable-5 medium
+//   ($6.09/65%) → gpt-5.5 xhigh ($7.23/67%) → fable-5 high ($9.18/69%) →
+//   fable-5 xhigh ($13.41/70%).
+// - Dropped as strictly dominated: claude-sonnet-5 (40-54% at $4-26, up to
+//   268 steps), claude-sonnet-4.6 (30%/$5.52), gemini-3.1-pro (12%/$9.48),
+//   gemini-3.5-flash (37%/$7.34, 276k output tokens).
+// - claude-opus-4.8 rides at :high — its value point (52%/$4.28); :xhigh
+//   doubles the cost for +2pts.
+// - glm-5.2 is reviewer-C's diversity primary only (third model family
+//   decorrelates review errors); elsewhere it is a budget fallback. Note:
+//   GLM-5.2 has only two real reasoning tiers — its thinkingLevelMap collapses
+//   minimal/low/medium/high to "high" and xhigh to "max" — so chains only use
+//   :high (budget tier, 36%/$2.84) or :xhigh (best tier, 44%/$3.92); the
+//   openrouter/z-ai mirror maps :xhigh exclusively, so it is always :xhigh.
+
 export const promptEngineerModelConfig = {
-    model: "anthropic/claude-fable-5:xhigh",
+    model: "openai-codex/gpt-5.5:xhigh",
     fallbackModels: [
-      "openai-codex/gpt-5.5:xhigh",
       "github-copilot/gpt-5.5:xhigh",
       "openai/gpt-5.5:xhigh",
-      "github-copilot/claude-opus-4.8 (1m):xhigh",
-      "anthropic/claude-opus-4-8:xhigh",
+      "anthropic/claude-fable-5:xhigh",
+      "github-copilot/claude-opus-4.8 (1m):high",
+      "anthropic/claude-opus-4-8:high",
       "zai/glm-5.2:xhigh",
       "zai-coding-cn/glm-5.2:xhigh",
-      "github-copilot/gemini-3.5-flash (1m):high",
-      "google/gemini-3.5-flash:high",
-      "google-vertex/gemini-3.5-flash:high",
-      "github-copilot/gemini-3.1-pro-preview (1m):high",
-      "google/gemini-3.1-pro-preview:high",
-      "google-vertex/gemini-3.1-pro-preview:high",
-      "openrouter/anthropic/claude-fable-5:xhigh",
       "openrouter/openai/gpt-5.5:xhigh",
-      "openrouter/anthropic/claude-opus-4-8:xhigh",
-      "openrouter/z-ai/glm-5.2:xhigh",
-      "openrouter/google/gemini-3.5-flash:high",
-      "openrouter/google/gemini-3.1-pro-preview:high"
+      "openrouter/anthropic/claude-fable-5:xhigh",
+      "openrouter/anthropic/claude-opus-4-8:high",
+      "openrouter/z-ai/glm-5.2:xhigh"
     ],
     excludedTools: ["ask_user_question"],
 };
@@ -31,21 +46,15 @@ export const researchModelConfig = {
     fallbackModels: [
         "github-copilot/gpt-5.5:medium",
         "openai/gpt-5.5:medium",
+        "anthropic/claude-fable-5:low",
         "github-copilot/claude-opus-4.8 (1m):medium",
         "anthropic/claude-opus-4-8:medium",
-        "zai/glm-5.2:medium",
-        "zai-coding-cn/glm-5.2:medium",
-        "github-copilot/gemini-3.5-flash (1m):medium",
-        "google/gemini-3.5-flash:medium",
-        "google-vertex/gemini-3.5-flash:medium",
-        "github-copilot/gemini-3.1-pro-preview (1m):medium",
-        "google/gemini-3.1-pro-preview:medium",
-        "google-vertex/gemini-3.1-pro-preview:medium",
+        "zai/glm-5.2:high",
+        "zai-coding-cn/glm-5.2:high",
         "openrouter/openai/gpt-5.5:medium",
+        "openrouter/anthropic/claude-fable-5:low",
         "openrouter/anthropic/claude-opus-4-8:medium",
-        "openrouter/z-ai/glm-5.2:medium",
-        "openrouter/google/gemini-3.5-flash:medium",
-        "openrouter/google/gemini-3.1-pro-preview:medium"
+        "openrouter/z-ai/glm-5.2:xhigh"
     ],
     excludedTools: ["ask_user_question"],
 };
@@ -55,21 +64,15 @@ export const orchestratorModelConfig = {
     fallbackModels: [
         "github-copilot/gpt-5.5:medium",
         "openai/gpt-5.5:medium",
+        "anthropic/claude-fable-5:low",
         "github-copilot/claude-opus-4.8 (1m):medium",
         "anthropic/claude-opus-4-8:medium",
-        "zai/glm-5.2:medium",
-        "zai-coding-cn/glm-5.2:medium",
-        "github-copilot/gemini-3.5-flash (1m):medium",
-        "google/gemini-3.5-flash:medium",
-        "google-vertex/gemini-3.5-flash:medium",
-        "github-copilot/gemini-3.1-pro-preview (1m):medium",
-        "google/gemini-3.1-pro-preview:medium",
-        "google-vertex/gemini-3.1-pro-preview:medium",
+        "zai/glm-5.2:high",
+        "zai-coding-cn/glm-5.2:high",
         "openrouter/openai/gpt-5.5:medium",
+        "openrouter/anthropic/claude-fable-5:low",
         "openrouter/anthropic/claude-opus-4-8:medium",
-        "openrouter/z-ai/glm-5.2:medium",
-        "openrouter/google/gemini-3.5-flash:medium",
-        "openrouter/google/gemini-3.1-pro-preview:medium"
+        "openrouter/z-ai/glm-5.2:xhigh"
     ],
     excludedTools: ["ask_user_question"],
 };
@@ -77,25 +80,17 @@ export const orchestratorModelConfig = {
 export const reviewerAModelConfig = {
     model: "anthropic/claude-fable-5:xhigh",
     fallbackModels: [
-      "github-copilot/claude-opus-4.8 (1m):xhigh",
-      "anthropic/claude-opus-4-8:xhigh",
       "openai-codex/gpt-5.5:xhigh",
       "github-copilot/gpt-5.5:xhigh",
       "openai/gpt-5.5:xhigh",
+      "github-copilot/claude-opus-4.8 (1m):high",
+      "anthropic/claude-opus-4-8:high",
       "zai/glm-5.2:xhigh",
       "zai-coding-cn/glm-5.2:xhigh",
-      "github-copilot/gemini-3.5-flash (1m):high",
-      "google/gemini-3.5-flash:high",
-      "google-vertex/gemini-3.5-flash:high",
-      "github-copilot/gemini-3.1-pro-preview (1m):high",
-      "google/gemini-3.1-pro-preview:high",
-      "google-vertex/gemini-3.1-pro-preview:high",
       "openrouter/anthropic/claude-fable-5:xhigh",
-      "openrouter/anthropic/claude-opus-4-8:xhigh",
       "openrouter/openai/gpt-5.5:xhigh",
-      "openrouter/z-ai/glm-5.2:xhigh",
-      "openrouter/google/gemini-3.5-flash:high",
-      "openrouter/google/gemini-3.1-pro-preview:high"
+      "openrouter/anthropic/claude-opus-4-8:high",
+      "openrouter/z-ai/glm-5.2:xhigh"
     ],
     excludedTools: ["ask_user_question"],
     schema: reviewDecisionSchema,
@@ -107,22 +102,14 @@ export const reviewerBModelConfig = {
       "github-copilot/gpt-5.5:xhigh",
       "openai/gpt-5.5:xhigh",
       "anthropic/claude-fable-5:xhigh",
-      "github-copilot/claude-opus-4.8 (1m):xhigh",
-      "anthropic/claude-opus-4-8:xhigh",
+      "github-copilot/claude-opus-4.8 (1m):high",
+      "anthropic/claude-opus-4-8:high",
       "zai/glm-5.2:xhigh",
       "zai-coding-cn/glm-5.2:xhigh",
-      "github-copilot/gemini-3.5-flash (1m):high",
-      "google/gemini-3.5-flash:high",
-      "google-vertex/gemini-3.5-flash:high",
-      "github-copilot/gemini-3.1-pro-preview (1m):high",
-      "google/gemini-3.1-pro-preview:high",
-      "google-vertex/gemini-3.1-pro-preview:high",
       "openrouter/openai/gpt-5.5:xhigh",
       "openrouter/anthropic/claude-fable-5:xhigh",
-      "openrouter/anthropic/claude-opus-4-8:xhigh",
-      "openrouter/z-ai/glm-5.2:xhigh",
-      "openrouter/google/gemini-3.5-flash:high",
-      "openrouter/google/gemini-3.1-pro-preview:high"
+      "openrouter/anthropic/claude-opus-4-8:high",
+      "openrouter/z-ai/glm-5.2:xhigh"
     ],
     excludedTools: ["ask_user_question"],
     schema: reviewDecisionSchema,
@@ -132,26 +119,17 @@ export const reviewerCModelConfig = {
     model: "zai/glm-5.2:xhigh",
     fallbackModels: [
       "zai-coding-cn/glm-5.2:xhigh",
-      "github-copilot/gemini-3.5-flash (1m):high",
-      "google/gemini-3.5-flash:high",
-      "google-vertex/gemini-3.5-flash:high",
-      "github-copilot/gemini-3.1-pro-preview (1m):high",
-      "google/gemini-3.1-pro-preview:high",
-      "google-vertex/gemini-3.1-pro-preview:high",
+      "openrouter/z-ai/glm-5.2:xhigh",
       "openai-codex/gpt-5.5:xhigh",
       "github-copilot/gpt-5.5:xhigh",
       "openai/gpt-5.5:xhigh",
       "anthropic/claude-fable-5:xhigh",
-      "github-copilot/claude-opus-4.8 (1m):xhigh",
-      "anthropic/claude-opus-4-8:xhigh",
-      "openrouter/anthropic/claude-fable-5:xhigh",
-      "openrouter/anthropic/claude-opus-4-8:xhigh",
+      "github-copilot/claude-opus-4.8 (1m):high",
+      "anthropic/claude-opus-4-8:high",
       "openrouter/openai/gpt-5.5:xhigh",
-      "openrouter/z-ai/glm-5.2:xhigh",
-      "openrouter/google/gemini-3.5-flash:high",
-      "openrouter/google/gemini-3.1-pro-preview:high"
+      "openrouter/anthropic/claude-fable-5:xhigh",
+      "openrouter/anthropic/claude-opus-4-8:high"
     ],
     excludedTools: ["ask_user_question"],
     schema: reviewDecisionSchema,
 };
-

package/dist/builtin/workflows/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/workflows",
-  "version": "0.9.3",
+  "version": "0.9.4-alpha.10",
   "private": true,
   "description": "Atomic extension for multi-stage workflow authoring and execution.",
   "contributors": [
@@ -83,7 +83,7 @@
   },
   "peerDependencies": {
     "@bastani/atomic": "*",
-    "@earendil-works/pi-tui": "^0.80.2"
+    "@earendil-works/pi-tui": "^0.80.3"
   },
   "peerDependenciesMeta": {
     "@bastani/atomic": {

package/dist/builtin/workflows/src/engine/run-durable-finalize.ts

@@ -33,11 +33,13 @@ export async function finalizeDurableTerminalStatus(input: DurableTerminalFinali
   if (!input.isRoot) return;
   const status = input.runSnapshot.status;
   const isExitTerminal = input.runSnapshot.exited === true && status !== "running";
-  if (status !== "failed" && status !== "killed" && !isExitTerminal) return;
+  const isReturnedBlockedTerminal = status === "blocked" && input.runSnapshot.endedAt !== undefined;
+  if (status !== "failed" && status !== "killed" && !isExitTerminal && !isReturnedBlockedTerminal) return;
 
   const durableStatus = toDurableStatus(status);
   if (durableStatus !== undefined) {
-    input.durableBackend.setWorkflowStatus(input.runId, durableStatus, undefined, input.runSnapshot.resumable);
+    const resumable = status === "blocked" ? false : input.runSnapshot.resumable;
+    input.durableBackend.setWorkflowStatus(input.runId, durableStatus, undefined, resumable);
   }
   try {
     await input.durableBackend.flush?.();

package/dist/builtin/workflows/src/engine/run-returned-status.ts

@@ -0,0 +1,41 @@
+import type { RunEndMetadata } from "../shared/store-public-types.js";
+import type { WorkflowOutputValues } from "../shared/types.js";
+
+export interface ReturnedRunStatus {
+  readonly status: "completed" | "failed" | "blocked";
+  readonly error?: string;
+  readonly metadata?: RunEndMetadata;
+}
+
+export function classifyReturnedRunStatus(result: WorkflowOutputValues | undefined): ReturnedRunStatus {
+  const returnedStatus = result?.["status"];
+  if (returnedStatus !== "failed" && returnedStatus !== "blocked") {
+    return { status: "completed" };
+  }
+
+  const summary = result?.["summary"];
+  const error = typeof summary === "string" && summary.trim().length > 0
+    ? summary.trim()
+    : `Workflow returned status ${JSON.stringify(returnedStatus)}.`;
+  return {
+    status: returnedStatus,
+    error,
+    metadata: returnedStatus === "failed"
+      ? returnedFailureMetadata(error)
+      : returnedBlockedMetadata(),
+  };
+}
+
+function returnedFailureMetadata(error: string): RunEndMetadata {
+  return {
+    failureKind: "unknown",
+    failureRecoverability: "non_recoverable",
+    failureDisposition: "terminal_failed",
+    failureMessage: error,
+    resumable: false,
+  };
+}
+
+function returnedBlockedMetadata(): RunEndMetadata {
+  return { resumable: false };
+}

package/dist/builtin/workflows/src/engine/run.ts

@@ -41,6 +41,7 @@ import {
 import { assertWorkflowRunOutputs, normalizeWorkflowRunOutput } from "../runs/foreground/executor-outputs.js";
 import { isWorkflowDefinition, workflowDefinitionRequirementMessage } from "../runs/foreground/executor-child-helpers.js";
 import { getDurableBackend } from "../durable/factory.js";
+import { classifyReturnedRunStatus } from "./run-returned-status.js";
 import { createToolPrimitive, createCheckpointIdGenerator } from "../durable/tool-primitive.js";
 import { persistDurableCacheEntry } from "../durable/resume-catalog.js";
 import { createDurableStagePrimitive, createDurableTaskPrimitive, recordStageCheckpoint, createStageReplayKeyGenerator, recordCachedStageWithTracker } from "../durable/stage-primitive.js";
@@ -423,15 +424,16 @@ export async function run<
     assertWorkflowRunOutputs(def.name, result, def.outputs);
     assertWorkflowCreatedStage(runSnapshot);
     await durableBackend.flush?.();
-    const recorded = activeStore.recordRunEnd(runId, "completed", result);
-    appendRunEndWhenRecorded(opts.persistence, recorded, { runId, status: "completed", result, ts: Date.now() });
-    durableBackend.setWorkflowStatus(runId, "completed");
+    const returned = classifyReturnedRunStatus(result);
+    const recorded = activeStore.recordRunEnd(runId, returned.status, result, returned.error, returned.metadata);
+    appendRunEndWhenRecorded(opts.persistence, recorded, { runId, status: returned.status, result, ...(returned.error !== undefined ? { error: returned.error } : {}), ...(returned.metadata ?? {}), ts: Date.now() });
+    durableBackend.setWorkflowStatus(runId, returned.status, undefined, returned.metadata?.resumable);
     await durableBackend.flush?.();
     if (opts.persistence && durableBackend.persistent) {
       const cacheEntry = durableBackend.toCacheEntry(runId);
       if (cacheEntry) persistDurableCacheEntry(opts.persistence, cacheEntry);
     }
-    return reconcileTerminalRunResult(runId, runSnapshot, activeStore, { status: "completed", result }, opts.onRunEnd);
+    return reconcileTerminalRunResult(runId, runSnapshot, activeStore, { status: returned.status, result, error: returned.error }, opts.onRunEnd);
   } catch (err) {
     const selectedExit = findWorkflowExitSignal(err, exitScope) ?? findWorkflowExitSignal(ownController.signal.reason, exitScope);
     if (selectedExit !== undefined) return await finalizers.finalizeWorkflowExit(selectedExit);

package/dist/builtin/workflows/src/extension/config-file-loader.ts

@@ -68,7 +68,7 @@ function validateConfig(value: unknown): string | null {
       }
       for (const item of notifyOn) {
         if (!isWorkflowLifecycleNoticeKind(item)) {
-          return `"workflowNotifications.notifyOn" entries must be "completed", "failed", or "awaiting_input", got ${JSON.stringify(item)}`;
+          return `"workflowNotifications.notifyOn" entries must be "completed", "failed", "blocked", or "awaiting_input", got ${JSON.stringify(item)}`;
         }
       }
     }

package/dist/builtin/workflows/src/extension/config-loader.ts

@@ -182,7 +182,7 @@ export const WORKFLOW_CONFIG_DEFAULTS = {
   resumeInFlight: "ask" as const,
   workflowNotifications: {
     enabled: true,
-    notifyOn: ["completed", "failed", "awaiting_input"] as const,
+    notifyOn: ["completed", "failed", "blocked", "awaiting_input"] as const,
   },
 } as const;
 

package/dist/builtin/workflows/src/extension/lifecycle-notifications.ts

@@ -21,11 +21,12 @@ import { renderWorkflowNoticeCard, type WorkflowNoticeTone } from "../tui/workfl
 export const LIFECYCLE_NOTICE_CUSTOM_TYPE = "workflows:lifecycle-notice";
 export const LIFECYCLE_NOTICE_SNIPPET_LIMIT = 240;
 
-export type WorkflowLifecycleNoticeKind = "completed" | "failed" | "awaiting_input";
+export type WorkflowLifecycleNoticeKind = "completed" | "failed" | "blocked" | "awaiting_input";
 
 export const WORKFLOW_LIFECYCLE_NOTICE_KINDS = [
   "completed",
   "failed",
+  "blocked",
   "awaiting_input",
 ] as const satisfies readonly WorkflowLifecycleNoticeKind[];
 
@@ -95,8 +96,9 @@ export function seedWorkflowLifecycleNotificationState(
 ): void {
   for (const run of snapshot.runs) {
     if (!isTopLevelWorkflowRun(run)) continue;
-    if ((run.status === "completed" || run.status === "failed") && run.endedAt !== undefined) {
-      state.deliveredTerminalRuns.add(terminalRunKey(run.status, run.id));
+    const noticeKind = terminalNoticeKind(run);
+    if (noticeKind !== undefined && run.endedAt !== undefined) {
+      state.deliveredTerminalRuns.add(terminalRunKey(noticeKind, run.id));
     }
     if (run.pendingPrompt !== undefined) {
       state.deliveredInputPrompts.add(runAwaitingInputKey(run.id, run.pendingPrompt));
@@ -186,9 +188,10 @@ export function installWorkflowLifecycleNotifications(
 
   const emitTerminalNoticeOnce = (
     run: RunSnapshot,
-    kind: "completed" | "failed",
+    kind: "completed" | "failed" | "blocked",
   ): void => {
-    if (run.status !== kind || run.endedAt === undefined || !notifyOn.has(kind)) {
+    const noticeKind = terminalNoticeKind(run);
+    if (noticeKind !== kind || run.endedAt === undefined || !notifyOn.has(kind)) {
       return;
     }
 
@@ -231,6 +234,7 @@ export function installWorkflowLifecycleNotifications(
       if (!isTopLevelWorkflowRun(run)) continue;
       emitTerminalNoticeOnce(run, "completed");
       emitTerminalNoticeOnce(run, "failed");
+      emitTerminalNoticeOnce(run, "blocked");
 
       if (!notifyOn.has("awaiting_input")) continue;
       emitRunAwaitingInputNoticeOnce(run);
@@ -273,6 +277,10 @@ export function formatWorkflowLifecycleNoticeText(details: WorkflowLifecycleNoti
     const errorText = details.error ? `: ${details.error}` : "";
     return `✗ Workflow "${workflowName}" failed (run ${details.runId}${stageText})${errorText}. Inspect: /workflow status ${details.runId}`;
   }
+  if (details.kind === "blocked") {
+    const errorText = details.error ? `: ${details.error}` : "";
+    return `! Workflow "${workflowName}" ended blocked (run ${details.runId})${errorText}. Inspect: /workflow status ${details.runId}`;
+  }
   const prompt = details.promptMessage ? ` Prompt: ${details.promptMessage}` : "";
   if (details.scope === "run") {
     return `？ Workflow "${workflowName}" needs input (run ${details.runId}).${prompt} Respond: /workflow connect ${details.runId} to answer this run-level prompt.`;
@@ -286,18 +294,19 @@ export function formatWorkflowLifecycleNoticeText(details: WorkflowLifecycleNoti
 
 function makeTerminalNotice(
   run: RunSnapshot,
-  kind: "completed" | "failed",
+  kind: "completed" | "failed" | "blocked",
 ): WorkflowLifecycleNoticeDetails {
   const failedStage = run.failedStageId
     ? run.stages.find((stage) => stage.id === run.failedStageId)
     : undefined;
+  const error = run.error ?? (kind === "blocked" ? run.exitReason : undefined);
   return {
     kind,
     scope: "run",
     runId: run.id,
     workflowName: run.name,
     status: run.status,
-    ...(run.error ? { error: truncateSnippet(run.error) } : {}),
+    ...(error ? { error: truncateSnippet(error) } : {}),
     ...(run.failedStageId ? { failedStageId: run.failedStageId } : {}),
     ...(failedStage ? { stageId: failedStage.id, stageName: failedStage.name } : {}),
     ...(run.durationMs !== undefined ? { durationMs: run.durationMs } : {}),
@@ -320,7 +329,15 @@ function jsonString(value: string): string {
   return JSON.stringify(value);
 }
 
-function terminalRunKey(kind: "completed" | "failed", runId: string): string {
+function terminalNoticeKind(run: RunSnapshot): "completed" | "failed" | "blocked" | undefined {
+  if (run.status === "failed" || run.status === "blocked") return run.status;
+  if (run.status !== "completed") return undefined;
+  const returnedStatus = run.result?.["status"];
+  if (returnedStatus === "failed" || returnedStatus === "blocked") return returnedStatus;
+  return "completed";
+}
+
+function terminalRunKey(kind: "completed" | "failed" | "blocked", runId: string): string {
   return `${kind}:${runId}`;
 }
 
@@ -361,19 +378,27 @@ function renderLifecycleNoticeCard(
   details: WorkflowLifecycleNoticeDetails,
   opts: { width: number; theme?: GraphTheme; fallbackText: string },
 ): string[] {
-  const tone: WorkflowNoticeTone = details.kind === "failed" ? "error" : details.kind === "awaiting_input" ? "warning" : "success";
+  const tone: WorkflowNoticeTone = details.kind === "failed"
+    ? "error"
+    : details.kind === "awaiting_input" || details.kind === "blocked"
+      ? "warning"
+      : "success";
   const title = details.kind === "failed"
     ? "WORKFLOW FAILED"
     : details.kind === "awaiting_input"
       ? "WORKFLOW INPUT"
-      : "WORKFLOW COMPLETE";
-  const glyph = details.kind === "failed" ? "✗" : details.kind === "awaiting_input" ? "？" : "✓";
+      : details.kind === "blocked"
+        ? "WORKFLOW BLOCKED"
+        : "WORKFLOW COMPLETE";
+  const glyph = details.kind === "failed" ? "✗" : details.kind === "awaiting_input" ? "？" : details.kind === "blocked" ? "!" : "✓";
   const stage = details.stageName ?? details.failedStageId ?? details.stageId;
   const headline = details.kind === "failed"
     ? `Workflow "${details.workflowName}" failed`
     : details.kind === "awaiting_input"
       ? `Workflow "${details.workflowName}" needs input`
-      : `Workflow "${details.workflowName}" completed`;
+      : details.kind === "blocked"
+        ? `Workflow "${details.workflowName}" ended blocked`
+        : `Workflow "${details.workflowName}" completed`;
   return renderWorkflowNoticeCard({
     title,
     glyph,

package/dist/builtin/workflows/src/runs/shared/model-fallback-failures.ts

@@ -49,7 +49,9 @@ export type ModelFallbackFailureKind =
   | "rate_limit"
   | "provider_unavailable"
   | "network_timeout"
+  | "transport_error"
   | "model_unavailable"
+  | "request_incompatible"
   | "cancelled"
   | "task_failure"
   | "unknown";
@@ -76,7 +78,9 @@ const FALLBACKABLE_FAILURE_KINDS: ReadonlySet<ModelFallbackFailureKind> = new Se
   "rate_limit",
   "provider_unavailable",
   "network_timeout",
+  "transport_error",
   "model_unavailable",
+  "request_incompatible",
 ]);
 
 function asRecord(value: unknown): Record<string, unknown> | undefined {
@@ -155,6 +159,9 @@ function normalizeCode(value: string | number | undefined): string | undefined {
 
 function kindFromStatus(status: number | undefined): ModelFallbackFailureKind | undefined {
   switch (status) {
+    case 400:
+    case 413: case 422:
+      return "request_incompatible";
     case 401:
     case 403:
       return "auth_on_candidate_provider";
@@ -191,6 +198,15 @@ function refusalKindFromCode(code: string | number | undefined): ModelFallbackFa
   }
 }
 
+const REQUEST_INCOMPATIBLE_CODES: ReadonlySet<string> = new Set([
+  "invalid_request", "invalid_request_error", "bad_request", "context_length_exceeded",
+  "request_too_large", "too_large", "request_entity_too_large", "max_tokens",
+  "max_context_length", "context_window_exceeded",
+]);
+function requestIncompatibleKindFromCode(code: string | number | undefined): ModelFallbackFailureKind | undefined {
+  const normalizedCode = normalizeCode(code);
+  return normalizedCode !== undefined && REQUEST_INCOMPATIBLE_CODES.has(normalizedCode) ? "request_incompatible" : undefined;
+}
 function kindFromCode(code: string | number | undefined): ModelFallbackFailureKind | undefined {
   const normalizedCode = normalizeCode(code);
   if (normalizedCode === undefined) return undefined;
@@ -198,6 +214,8 @@ function kindFromCode(code: string | number | undefined): ModelFallbackFailureKi
   if (refusalKind !== undefined) return refusalKind;
   const httpStatusKind = kindFromStatus(integerFrom(code));
   if (httpStatusKind !== undefined) return httpStatusKind;
+  const requestIncompatibleKind = requestIncompatibleKindFromCode(code);
+  if (requestIncompatibleKind !== undefined) return requestIncompatibleKind;
 
   switch (normalizedCode) {
     case "auth":
@@ -246,6 +264,18 @@ function kindFromCode(code: string | number | undefined): ModelFallbackFailureKi
   }
 }
 
+const REQUEST_INCOMPATIBLE_FAILURE_PATTERNS: readonly RegExp[] = [
+  /\bcontext[_\s-]?length(?:[_\s-]?exceeded)?\b/i,
+  /\bcontext[_\s-]?window(?:[_\s-]?exceeded)?\b/i,
+  /\bmax[_\s-]?context\b/i,
+  /\bmax[_\s-]?tokens?\b/i,
+  /\brequest(?:[_\s-]?entity)?[_\s-]?too[_\s-]?large\b/i,
+  /\btoo[_\s-]?large\b/i,
+  /\b(?:unsupported|unknown|invalid)\s+(?:tool|parameter|function)\b/i,
+  /\b(?:tool|parameter|function)\s+(?:not\s+(?:supported|found|allowed)|unknown|invalid)\b/i,
+  /\binvalid[_\s-]?request(?:[_\s-]?error)?\b/i,
+  /\bbad[_\s-]?request\b/i,
+];
 const PROVIDER_REFUSAL_FAILURE_PATTERNS: readonly RegExp[] = [
   /\bfinish[_\s-]?reason\b[^\n]*\bcontent[_\s-]?filter\b/i,
   /\bcontent[_\s-]?filter(?:ed|ing)?\b/i,
@@ -258,6 +288,17 @@ const PROVIDER_REFUSAL_FAILURE_PATTERNS: readonly RegExp[] = [
   /\bprovider\b[^\n]*\brefus(?:e|al|ed|es|ing)?\b[^\n]*\b(?:prompt|request|content|policy|safety)\b/i,
 ];
 
+const TRANSPORT_OUTAGE_FAILURE_PATTERNS: readonly RegExp[] = [
+  /^connection\s+error\.?$/i,
+  /^fetch\s+failed\.?$/i,
+];
+
+function transportOutageKindFromMessage(message: string): ModelFallbackFailureKind | undefined {
+  return TRANSPORT_OUTAGE_FAILURE_PATTERNS.some((pattern) => pattern.test(message.trim()))
+    ? "transport_error"
+    : undefined;
+}
+
 function refusalKindFromMessage(message: string): ModelFallbackFailureKind | undefined {
   if (CANCELLED_FAILURE_PATTERNS.some((pattern) => pattern.test(message))) return "cancelled";
   if (NON_RETRYABLE_FAILURE_PATTERNS.some((pattern) => pattern.test(message))) return "task_failure";
@@ -268,6 +309,9 @@ function refusalKindFromMessage(message: string): ModelFallbackFailureKind | und
 function fallbackKindFromMessage(message: string, name: string | undefined): ModelFallbackFailureKind | undefined {
   const refusalKind = refusalKindFromMessage(message);
   if (refusalKind !== undefined) return refusalKind;
+  const transportOutageKind = transportOutageKindFromMessage(message);
+  if (transportOutageKind !== undefined) return transportOutageKind;
+  if (REQUEST_INCOMPATIBLE_FAILURE_PATTERNS.some((pattern) => pattern.test(message))) return "request_incompatible";
   const nameKind = kindFromCode(name);
   if (nameKind !== undefined) return nameKind;
   if (!RETRYABLE_MODEL_FAILURE_PATTERNS.some((pattern) => pattern.test(message))) return undefined;
@@ -305,6 +349,16 @@ function makeSignal(
   };
 }
 
+function fallbackSignalFromDirectMessage(
+  value: unknown,
+  source: ModelFallbackFailureSource | undefined,
+): ModelFallbackFailureSignal | undefined {
+  const message = directMessageFrom(value);
+  if (message === undefined) return undefined;
+  const kind = fallbackKindFromMessage(message, errorName(value));
+  return kind === undefined ? undefined : makeSignal(kind, value, source);
+}
+
 function fallbackSignalFromMessage(
   value: unknown,
   source: ModelFallbackFailureSource | undefined,
@@ -359,7 +413,6 @@ function structuredSignal(
     if (isRefusalSignal(diagnosticSignal)) return diagnosticSignal;
     firstNestedFallbackSignal ??= diagnosticSignal;
   }
-
   const cause = causeOf(value);
   const causeSignal = structuredSignal(cause, nestedSeen, source)
     ?? fallbackSignalFromMessage(cause, source);
@@ -368,6 +421,11 @@ function structuredSignal(
     firstNestedFallbackSignal ??= causeSignal;
   }
 
+  // Direct-message classification runs after nested traversal so a generic wrapper
+  // ("invalid request"/"400 bad request") cannot mask a non-retryable nested signal.
+  const directMessageSignal = fallbackSignalFromDirectMessage(value, source);
+  if (directMessageSignal !== undefined) return directMessageSignal;
+
   const statusKind = kindFromStatus(statusFrom(value));
   if (statusKind !== undefined) return makeSignal(statusKind, value, source);
   if (codeKind !== undefined) return makeSignal(codeKind, value, source);

package/dist/builtin/workflows/src/shared/persistence-restore-helpers.ts

@@ -335,7 +335,7 @@ export function restoreTerminalRuns(entries: readonly SessionEntry[], store: Sto
     const exitReason = end["exitReason"];
     const resumable = end["resumable"];
     const restoredAuthorExit = isWorkflowExitTerminalStatus(status) &&
-      (exited === true || status !== "completed" || typeof exitReason === "string" || resumable === false);
+      (exited === true || typeof exitReason === "string");
     if (status === "completed" && !restoredAuthorExit && stages.some((stage) => stage.status !== "completed")) continue;
     store.recordRunStart({
       id: runId,

package/dist/builtin/workflows/src/shared/store-public-types.ts

@@ -83,8 +83,9 @@ export interface Store {
    * Records the end of a run.
    * Returns `true` if state changed, `false` if the run was not found or
    * already in a terminal state (completed | failed | killed | skipped | cancelled | blocked).
-   * `result` is applied for intentional success/exit statuses (completed | skipped | cancelled | blocked).
-   * `error` is only applied for status "failed" | "killed".
+   * `result` is applied for intentional success/exit statuses (completed | skipped | cancelled | blocked)
+   * and for workflows that intentionally return a failed status with structured outputs.
+   * `error` is applied for status "failed" | "killed" | "blocked".
    */
   recordRunEnd(
     runId: string,

package/dist/builtin/workflows/src/shared/store-run-methods.ts

@@ -82,11 +82,12 @@ export function createRunStoreMethods(context: StoreContext): RunStoreMethods {
         run.pausedAt = undefined;
       }
       run.durationMs = elapsedRunMs(run, run.endedAt);
+      if (result !== undefined && shouldStoreRunResult(status)) run.result = result;
       const wasBlocked = run.blockedAt !== undefined || run.failureDisposition === "active_blocked";
       delete run.blockedAt;
       if (status === "completed" || status === "skipped" || status === "cancelled" || status === "blocked") {
-        if (result !== undefined) run.result = result;
         clearRunFailureMetadata(run);
+        if (status === "blocked" && error !== undefined) run.error = error;
         if (metadata !== undefined) applyRunEndMetadata(run, metadata);
       } else {
         if (wasBlocked && error === undefined) delete run.error;
@@ -227,3 +228,7 @@ export function createRunStoreMethods(context: StoreContext): RunStoreMethods {
     },
   };
 }
+
+function shouldStoreRunResult(status: RunStatus): boolean {
+  return status === "completed" || status === "skipped" || status === "cancelled" || status === "blocked" || status === "failed";
+}

package/dist/bun/cli.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"cli.d.ts","sourceRoot":"","sources":["../../src/bun/cli.ts"],"names":[],"mappings":"","sourcesContent":["#!/usr/bin/env node\nimport { APP_NAME } from \"../config.ts\";\n\nprocess.title = APP_NAME;\nprocess.emitWarning = (() => {}) as typeof process.emitWarning;\n\nimport { restoreSandboxEnv } from \"./restore-sandbox-env.ts\";\n\nrestoreSandboxEnv();\n\nawait import(\"./register-bedrock.ts\");\nawait import(\"../cli.ts\");\n"]}
+{"version":3,"file":"cli.d.ts","sourceRoot":"","sources":["../../src/bun/cli.ts"],"names":[],"mappings":"","sourcesContent":["#!/usr/bin/env node\nimport { APP_NAME } from \"../config.ts\";\n\nprocess.title = APP_NAME;\nprocess.emitWarning = (() => {}) as typeof process.emitWarning;\n\nimport { restoreSandboxEnv } from \"./restore-sandbox-env.ts\";\n\nrestoreSandboxEnv();\n\n// No top-level await: the compiled binary is built with --bytecode (CJS),\n// which forbids TLA anywhere in the bundled graph.\nvoid import(\"./register-bedrock.ts\").then(() => import(\"../cli.ts\"));\n"]}