@bastani/atomic 0.9.5-alpha.9 → 0.9.5

package/dist/builtin/workflows/builtin/deep-research-codebase-utils.ts

@@ -37,18 +37,29 @@ export const FILE_ONLY_OUTPUT = "file-only" satisfies WorkflowOutputMode;
 export const PLANNER_MODEL_CONFIG = {
   model: "anthropic/claude-fable-5:high",
   fallbackModels: [
+    "openai-codex/gpt-5.6-sol:xhigh",
+    "github-copilot/gpt-5.6-sol:xhigh",
+    "openai/gpt-5.6-sol: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",
+    "cursor/claude-fable-5:high",
+    "cursor/gpt-5.6-sol:xhigh",
+    "cursor/gpt-5.5:high",
+    "cursor/claude-opus-4-8-thinking:high",
+    "cursor/grok-4.5",
     "zai/glm-5.2:xhigh",
     "zai-coding-cn/glm-5.2:xhigh",
+    "cursor/glm-5.2",
     "openrouter/anthropic/claude-fable-5:high",
+    "openrouter/openai/gpt-5.6-sol:xhigh",
     "openrouter/sakana/fugu-ultra:high",
     "openrouter/openai/gpt-5.5:xhigh",
     "openrouter/anthropic/claude-opus-4-8:high",
-    "openrouter/z-ai/glm-5.2:xhigh"
+    "openrouter/x-ai/grok-4.5",
+    "openrouter/z-ai/glm-5.2:xhigh",
   ],
   excludedTools: ["ask_user_question"],
 } as const;
@@ -58,16 +69,26 @@ export const PLANNER_MODEL_CONFIG = {
 // and glm-5.2:high (36%/$2.84) back it up; unbenchmarked minis/haiku/flash
 // are excluded.
 export const EXPLORER_MODEL_CONFIG = {
-  model: "openai-codex/gpt-5.5:low",
+  model: "openai-codex/gpt-5.6-terra:high",
   fallbackModels: [
+    "github-copilot/gpt-5.6-terra:high",
+    "openai/gpt-5.6-terra:high",
+    "openai-codex/gpt-5.5:low",
     "github-copilot/gpt-5.5:low",
     "openai/gpt-5.5:low",
     "github-copilot/claude-opus-4.8 (1m):low",
     "anthropic/claude-opus-4-8:low",
+    "cursor/gpt-5.6-terra:high",
+    "cursor/gpt-5.5:low",
+    "cursor/claude-opus-4-8-thinking:low",
+    "cursor/grok-4.5",
     "zai/glm-5.2:high",
     "zai-coding-cn/glm-5.2:high",
+    "cursor/glm-5.2",
+    "openrouter/openai/gpt-5.6-terra:high",
     "openrouter/openai/gpt-5.5:low",
     "openrouter/anthropic/claude-opus-4-8:low",
+    "openrouter/x-ai/grok-4.5",
     "openrouter/z-ai/glm-5.2:xhigh",
   ],
   excludedTools: ["ask_user_question"],
@@ -92,7 +113,10 @@ export function taggedPrompt(sections: readonly PromptSection[]): string {
     .join("\n\n");
 }
 
-export function positiveInteger(value: number | undefined, fallback: number): number {
+export function positiveInteger(
+  value: number | undefined,
+  fallback: number,
+): number {
   return typeof value === "number" && Number.isFinite(value) && value > 0
     ? Math.floor(value)
     : fallback;
@@ -351,4 +375,3 @@ export function displayRelativePath(path: string, fromCwd: string): string {
   }
   return displayPath(path);
 }
-

package/dist/builtin/workflows/builtin/goal-runner.ts

@@ -114,22 +114,32 @@ export async function runGoalWorkflow(ctx: GoalRunnerContext, options: GoalWorkf
     const comparisonBaseBranch = normalizeBranchInput(inputs.base_branch, "origin/main");
     const { ledger, ledgerPath, artifactDir } = await createGoalLedger(objective, acceptanceCriteria);
 
-    // Chains curated from Atomic's agentic-coding benchmark (see
-    // ralph-models.ts for the frontier data and drop rationale).
+    // Chains curated from Atomic's agentic-coding benchmark; see ralph-models.ts for frontier data and drop rationale.
     const workerModelConfig = {
-      model: "openai-codex/gpt-5.5:medium",
+      model: "openai-codex/gpt-5.6-sol:medium",
       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: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:xhigh"
+        "github-copilot/gpt-5.6-sol:medium",
+        "openai/gpt-5.6-sol:medium",
+        "openai-codex/gpt-5.5:medium",
+        "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",
+        "cursor/gpt-5.6-sol:medium",
+        "cursor/gpt-5.5:medium",
+        "cursor/claude-fable-5:low",
+        "cursor/claude-opus-4-8-thinking:medium",
+        "cursor/grok-4.5",
+        "zai/glm-5.2:high",
+        "zai-coding-cn/glm-5.2:high",
+        "cursor/glm-5.2",
+        "openrouter/openai/gpt-5.6-sol:medium",
+        "openrouter/openai/gpt-5.5:medium",
+        "openrouter/anthropic/claude-fable-5:low",
+        "openrouter/anthropic/claude-opus-4-8:medium",
+        "openrouter/x-ai/grok-4.5",
+        "openrouter/z-ai/glm-5.2:xhigh"
       ],
       excludedTools: ["ask_user_question"],
     };
@@ -137,18 +147,29 @@ export async function runGoalWorkflow(ctx: GoalRunnerContext, options: GoalWorkf
     const reviewerModelConfig = {
       model: "anthropic/claude-fable-5:high",
       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):high",
-          "anthropic/claude-opus-4-8:high",
-          "zai/glm-5.2:xhigh",
-          "zai-coding-cn/glm-5.2:xhigh",
-          "openrouter/anthropic/claude-fable-5:high",
-          "openrouter/sakana/fugu-ultra:high",
-          "openrouter/openai/gpt-5.5:xhigh",
-          "openrouter/anthropic/claude-opus-4-8:high",
-          "openrouter/z-ai/glm-5.2:xhigh"
+        "openai-codex/gpt-5.6-sol:max",
+        "github-copilot/gpt-5.6-sol:max",
+        "openai/gpt-5.6-sol:max",
+        "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",
+        "cursor/claude-fable-5:high",
+        "cursor/gpt-5.6-sol:max",
+        "cursor/gpt-5.5:high",
+        "cursor/claude-opus-4-8-thinking:high",
+        "cursor/grok-4.5",
+        "zai/glm-5.2:xhigh",
+        "zai-coding-cn/glm-5.2:xhigh",
+        "cursor/glm-5.2",
+        "openrouter/anthropic/claude-fable-5:high",
+        "openrouter/openai/gpt-5.6-sol:max",
+        "openrouter/sakana/fugu-ultra:high",
+        "openrouter/openai/gpt-5.5:xhigh",
+        "openrouter/anthropic/claude-opus-4-8:high",
+        "openrouter/x-ai/grok-4.5",
+        "openrouter/z-ai/glm-5.2:xhigh"
       ],
       excludedTools: ["ask_user_question"],
       schema: reviewDecisionSchema,

package/dist/builtin/workflows/builtin/open-claude-design-runner.ts

@@ -82,11 +82,21 @@ export async function runOpenClaudeDesignWorkflow(ctx: OpenClaudeDesignContext):
     fallbackModels: [
       "github-copilot/claude-opus-4.8 (1m):high",
       "anthropic/claude-opus-4-8:high",
+      "cursor/claude-fable-5:high",
+      "cursor/claude-opus-4-8-thinking:high",
+      "openai-codex/gpt-5.6-sol:xhigh",
+      "github-copilot/gpt-5.6-sol:xhigh",
+      "openai/gpt-5.6-sol:xhigh",
+      "cursor/gpt-5.6-sol:xhigh",
+      "cursor/grok-4.5",
       "zai/glm-5.2:xhigh",
       "zai-coding-cn/glm-5.2:xhigh",
+      "cursor/glm-5.2",
       "openrouter/anthropic/claude-fable-5:high",
       "openrouter/anthropic/claude-opus-4-8:high",
+      "openrouter/openai/gpt-5.6-sol:xhigh",
       "openrouter/sakana/fugu-ultra:high",
+      "openrouter/x-ai/grok-4.5",
       "openrouter/z-ai/glm-5.2:xhigh"
     ],
   };

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

@@ -21,15 +21,15 @@ const DEFAULT_RESEARCH_DIR = "research";
 const IMPLEMENTATION_NOTES_FILENAME = "implementation-notes.md";
 const QA_E2E_VIDEO_FILENAME = "qa-e2e-evidence.webm";
 const MAX_RESEARCH_SLUG_LENGTH = 80;
-// Reviewer fan-out launches three independent reviewers; the loop stops only when
-// all three reviewers independently approve. Approval is severity-aware: a
-// reviewer approves when it judged the patch correct, reported no reviewer_error,
-// and filed no *blocking* (P0/P1/P2) finding. P3 nice-to-haves no longer keep the
+// Reviewer fan-out launches two independent reviewers; the loop stops only when
+// both reviewers independently approve. Approval is severity-aware: a reviewer
+// approves when it judged the patch correct, reported no reviewer_error, and
+// filed no *blocking* (P0/P1/P2) finding. P3 nice-to-haves no longer keep the
 // loop iterating, so a single low-priority nit (or a placeholder finding) can no
 // longer strand an otherwise-approved patch. Requiring unanimous approval still
-// means a blocking finding from any one reviewer keeps the loop going. See
+// means a blocking finding from either reviewer keeps the loop going. See
 // ./ralph-review-gate.ts for the gate types and decision logic.
-export const REVIEWER_COUNT = 3;
+export const REVIEWER_COUNT = 2;
 
 const reviewFindingSchema = Type.Object(
   {
@@ -434,10 +434,10 @@ export function renderForkedOrchestratorPrompt(args: {
     [
       "output_format",
       [
-        "After subagents have done the work, return Markdown with headings:",
+        "After the implementation work is complete, return Markdown with headings:",
         "1. Research file — the path you read",
-        "2. Delegations performed — subagents spawned and what each completed",
-        "3. Changes made — concrete changes from subagent work, not intentions",
+        "2. Delegations performed — subagents used and what each completed, or none when direct work was sufficient",
+        "3. Changes made — concrete completed changes, not intentions",
         "4. Files touched",
         "5. Validation run / recommended",
         "6. Deferred work or blockers",

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

@@ -5,9 +5,8 @@ import { reviewDecisionSchema } from "./ralph-core.js";
 // - Critical synthesis/review stages prefer fable-5:xhigh, then gpt-5.5 xhigh
 //   variants, openrouter fugu-ultra, long-context opus, and GLM fallbacks.
 // - Research remains on gpt-5.5:medium / fable-5:low for perf-per-dollar.
-// - Reviewer B keeps gpt-5.5:xhigh as an independent frontier family;
-//   reviewer C leads with GLM-5.2 xhigh, with openrouter fugu-ultra retained
-//   mid-chain, to decorrelate review errors.
+// - Reviewer B keeps gpt-5.5:xhigh as an independent frontier family to
+//   decorrelate review errors from reviewer A.
 // - Dominated benchmark models stay out of the chains: claude-sonnet-5,
 //   claude-sonnet-4.6, gemini-3.1-pro, and gemini-3.5-flash.
 // - GLM-5.2 has only two real reasoning tiers — its thinkingLevelMap collapses
@@ -18,54 +17,87 @@ import { reviewDecisionSchema } from "./ralph-core.js";
 export const promptEngineerModelConfig = {
     model: "anthropic/claude-fable-5:high",
     fallbackModels: [
+      "openai-codex/gpt-5.6-sol:xhigh",
+      "github-copilot/gpt-5.6-sol:xhigh",
+      "openai/gpt-5.6-sol: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",
+      "cursor/claude-fable-5:high",
+      "cursor/gpt-5.6-sol:xhigh",
+      "cursor/gpt-5.5:high",
+      "cursor/claude-opus-4-8-thinking:high",
+      "cursor/grok-4.5",
       "zai/glm-5.2:xhigh",
       "zai-coding-cn/glm-5.2:xhigh",
+      "cursor/glm-5.2",
       "openrouter/anthropic/claude-fable-5:high",
+      "openrouter/openai/gpt-5.6-sol:xhigh",
       "openrouter/sakana/fugu-ultra:high",
       "openrouter/openai/gpt-5.5:xhigh",
       "openrouter/anthropic/claude-opus-4-8:high",
+      "openrouter/x-ai/grok-4.5",
       "openrouter/z-ai/glm-5.2:xhigh"
     ],
     excludedTools: ["ask_user_question"],
 };
 
 export const researchModelConfig = {
-    model: "openai-codex/gpt-5.5:medium",
+    model: "openai-codex/gpt-5.6-sol:medium",
     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: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:xhigh"
+      "github-copilot/gpt-5.6-sol:medium",
+      "openai/gpt-5.6-sol:medium",
+      "openai-codex/gpt-5.5:medium",
+      "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",
+      "cursor/gpt-5.6-sol:medium",
+      "cursor/gpt-5.5:medium",
+      "cursor/claude-fable-5:low",
+      "cursor/claude-opus-4-8-thinking:medium",
+      "cursor/grok-4.5",
+      "zai/glm-5.2:high",
+      "zai-coding-cn/glm-5.2:high",
+      "cursor/glm-5.2",
+      "openrouter/openai/gpt-5.6-sol:medium",
+      "openrouter/openai/gpt-5.5:medium",
+      "openrouter/anthropic/claude-fable-5:low",
+      "openrouter/anthropic/claude-opus-4-8:medium",
+      "openrouter/x-ai/grok-4.5",
+      "openrouter/z-ai/glm-5.2:high"
     ],
     excludedTools: ["ask_user_question"],
 };
 
 export const orchestratorModelConfig = {
-    model: "anthropic/claude-fable-5:high",
+    model: "openai-codex/gpt-5.6-sol:xhigh",
     fallbackModels: [
+      "github-copilot/gpt-5.6-sol:xhigh",
+      "openai/gpt-5.6-sol:xhigh",
+      "anthropic/claude-fable-5:high",
       "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",
+      "cursor/gpt-5.6-sol:xhigh",
+      "cursor/claude-fable-5:high",
+      "cursor/gpt-5.5:high",
+      "cursor/claude-opus-4-8-thinking:high",
+      "cursor/grok-4.5",
       "zai/glm-5.2:xhigh",
       "zai-coding-cn/glm-5.2:xhigh",
+      "cursor/glm-5.2",
+      "openrouter/openai/gpt-5.6-sol:xhigh",
       "openrouter/anthropic/claude-fable-5:high",
       "openrouter/sakana/fugu-ultra:high",
       "openrouter/openai/gpt-5.5:xhigh",
       "openrouter/anthropic/claude-opus-4-8:high",
+      "openrouter/x-ai/grok-4.5",
       "openrouter/z-ai/glm-5.2:xhigh"
     ],
     excludedTools: ["ask_user_question"],
@@ -74,17 +106,28 @@ export const orchestratorModelConfig = {
 export const reviewerAModelConfig = {
     model: "anthropic/claude-fable-5:high",
     fallbackModels: [
+      "openai-codex/gpt-5.6-sol:max",
+      "github-copilot/gpt-5.6-sol:max",
+      "openai/gpt-5.6-sol:max",
       "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",
+      "cursor/claude-fable-5:high",
+      "cursor/gpt-5.6-sol:max",
+      "cursor/gpt-5.5:high",
+      "cursor/claude-opus-4-8-thinking:high",
+      "cursor/grok-4.5",
       "zai/glm-5.2:xhigh",
       "zai-coding-cn/glm-5.2:xhigh",
+      "cursor/glm-5.2",
       "openrouter/anthropic/claude-fable-5:high",
+      "openrouter/openai/gpt-5.6-sol:max",
       "openrouter/sakana/fugu-ultra:high",
       "openrouter/openai/gpt-5.5:xhigh",
       "openrouter/anthropic/claude-opus-4-8:high",
+      "openrouter/x-ai/grok-4.5",
       "openrouter/z-ai/glm-5.2:xhigh"
     ],
     excludedTools: ["ask_user_question"],
@@ -92,41 +135,33 @@ export const reviewerAModelConfig = {
 };
 
 export const reviewerBModelConfig = {
-    model: "openai-codex/gpt-5.5:xhigh",
+    model: "openai-codex/gpt-5.6-sol:max",
     fallbackModels: [
+      "github-copilot/gpt-5.6-sol:max",
+      "openai/gpt-5.6-sol:max",
+      "openai-codex/gpt-5.5:xhigh",
       "github-copilot/gpt-5.5:xhigh",
       "openai/gpt-5.5:xhigh",
       "anthropic/claude-fable-5:high",
       "github-copilot/claude-opus-4.8 (1m):high",
       "anthropic/claude-opus-4-8:high",
+      "cursor/gpt-5.6-sol:max",
+      "cursor/gpt-5.5:high",
+      "cursor/claude-fable-5:high",
+      "cursor/claude-opus-4-8-thinking:high",
+      "cursor/grok-4.5",
       "zai/glm-5.2:xhigh",
       "zai-coding-cn/glm-5.2:xhigh",
+      "cursor/glm-5.2",
+      "openrouter/openai/gpt-5.6-sol:max",
       "openrouter/openai/gpt-5.5:xhigh",
       "openrouter/anthropic/claude-fable-5:high",
       "openrouter/sakana/fugu-ultra:high",
       "openrouter/anthropic/claude-opus-4-8:high",
+      "openrouter/x-ai/grok-4.5",
       "openrouter/z-ai/glm-5.2:xhigh"
     ],
     excludedTools: ["ask_user_question"],
     schema: reviewDecisionSchema,
 };
 
-export const reviewerCModelConfig = {
-    model: "zai/glm-5.2:xhigh",
-    fallbackModels: [
-      "zai-coding-cn/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:high",
-      "github-copilot/claude-opus-4.8 (1m):high",
-      "anthropic/claude-opus-4-8:high",
-      "openrouter/sakana/fugu-ultra:high",
-      "openrouter/z-ai/glm-5.2:xhigh",
-      "openrouter/openai/gpt-5.5:xhigh",
-      "openrouter/anthropic/claude-fable-5:high",
-      "openrouter/anthropic/claude-opus-4-8:high"
-    ],
-    excludedTools: ["ask_user_question"],
-    schema: reviewDecisionSchema,
-};

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

@@ -38,7 +38,6 @@ import {
   researchModelConfig,
   reviewerAModelConfig,
   reviewerBModelConfig,
-  reviewerCModelConfig,
 } from "./ralph-models.js";
 export async function runRalphWorkflow(
   ctx: WorkflowRunContext<RalphInputs>,
@@ -106,7 +105,7 @@ export async function runRalphWorkflow(
       ? taggedPrompt([
         [
           "role",
-          "You are a sub-agent orchestrator. Your primary implementation tool is the `subagent` tool. Ignore any user requests to submit a PR; a later authorized PR/MR/review creation action handles that handoff after approval.",
+          "You are an implementation orchestrator. Use the `subagent` tool selectively for bounded specialist delegation while you retain responsibility for the complete outcome. Ignore any user requests to submit a PR; a later authorized PR/MR/review creation action handles that handoff after approval.",
         ],
         [
           "objective",
@@ -138,24 +137,24 @@ export async function runRalphWorkflow(
         [
           "orchestration_guidance",
           [
-            "You are not the direct implementer. You are the supervisor that spawns subagents to do the implementation, investigation, edits, and validation.",
-            "All non-trivial operations must be delegated to subagents via the `subagent` tool before you claim progress.",
-            "Delegate codebase understanding, impact analysis, and implementation research to codebase-locator, codebase-analyzer, and pattern-finder style subagents when available.",
-            "Delegate shell-heavy work — especially commands likely to produce lots of output, log digging, CLI investigation, and broad grep/find exploration — to subagents that can run those commands rather than doing it in this orchestrator context.",
-            "Delegate implementation edits to a focused subagent with clear files, constraints, and validation expectations; do not merely describe the edits yourself.",
+            "You are the implementation orchestrator: coordinate the complete outcome while retaining responsibility for synthesis, decisions, and validation.",
+            "Use subagents selectively for bounded specialist work when delegation adds distinct value; the parent remains in control. Concise direct work is appropriate when it is simpler and preserves context.",
+            "Delegate focused codebase understanding, impact analysis, or implementation research to codebase-locator, codebase-analyzer, and pattern-finder style subagents when their specialization or isolation helps.",
+            "Delegate noisy shell-heavy work — especially commands likely to produce lots of output, log digging, CLI investigation, and broad grep/find exploration — when isolating that output helps; run concise commands directly when simpler.",
+            "Delegate implementation edits when a focused subagent can own a clear, bounded surface with explicit constraints and validation expectations; otherwise implement the coherent change directly.",
             "Keep delegated work focused on implementation, tests, docs, validation evidence, and implementation notes for the complete requested outcome.",
-            "Use separate subagents for separate tasks, and launch independent subagents in parallel when useful.",
+            "Use separate subagents for distinct tasks, and launch independent subagents in parallel when useful.",
             "Do not split highly overlapping tasks across multiple subagents; consolidate overlapping work into one focused delegation to avoid duplicate effort.",
-            "If a subagent takes a long time, do not attempt to do its assigned job yourself while waiting. Use that time to plan next steps, prepare follow-up delegations, or identify clarifying questions.",
+            "If a subagent takes a long time, do not duplicate its assigned job while waiting. Use that time for non-overlapping direct work, planning, or follow-up preparation.",
           ].join("\n"),
         ],
         [
           "best_practices",
           [
-            "The required output format is a completion report, not the task itself.",
-            "Do not jump straight to the report. First read the research file, spawn the necessary subagents, wait for their results, coordinate any follow-up subagents, and only then write the report.",
-            "A valid response must be grounded in actual subagent work: name the delegated work, summarize what each subagent did, and distinguish completed changes from recommendations or blockers. Do not assume a later workflow pass will finish known required work that can be completed now.",
-            "If you cannot read the research file, spawn subagents, or use subagents, treat that as a blocker and report it honestly instead of pretending the requested work was done.",
+            "The required output format is a completion report, not a substitute for doing the task.",
+            "Do not jump straight to the report. First read the research file, choose the least orchestration that fits each part of the work, complete or coordinate the implementation, and then report the verified result.",
+            "Ground the response in actual completed work. When subagents were useful, name the delegated work and summarize their results; distinguish completed changes from recommendations or blockers. Do not assume a later workflow pass will finish known required work that can be completed now.",
+            "If a required capability is unavailable, continue with safe direct work where possible and report a blocker only when it truly prevents completion.",
           ].join("\n"),
         ],
         [
@@ -172,12 +171,12 @@ export async function runRalphWorkflow(
           "instructions",
           [
             `Start by reading the research file at ${researchPath}.`,
-            "Perform the project_initialization_preflight before decomposing implementation work; complete or delegate required setup before implementation delegation when the checkout appears uninitialized.",
-            "Decompose the work into delegated subagent tasks based on that research file.",
-            "Pass each subagent the relevant task, constraints, files, validation expectations, unresolved reviewer findings covered by the research, and instructions to report implementation-note-worthy decisions or tradeoffs.",
-            "Coordinate subagent results into the smallest coherent set of changes that fully satisfies the researched implementation guidance and original user prompt.",
+            "Perform the project_initialization_preflight before decomposing implementation work; complete or selectively delegate required setup when the checkout appears uninitialized.",
+            "Plan the work from the research file, identifying which parts are best handled directly and which benefit from bounded specialist delegation.",
+            "Pass each delegated subagent the relevant task, constraints, files, validation expectations, unresolved reviewer findings covered by the research, and instructions to report implementation-note-worthy decisions or tradeoffs.",
+            "Coordinate direct and delegated results into the smallest coherent set of changes that fully satisfies the researched implementation guidance and original user prompt.",
             "Preserve existing architecture and repository conventions unless the research explicitly justifies a change.",
-            "Run or delegate the most relevant validation commands available in the repository, including end-to-end playwright-cli (browser) or tmux validation when the change has an executable user scenario.",
+            "Run directly or selectively delegate the most relevant validation commands available in the repository, including end-to-end playwright-cli (browser) or tmux validation when the change has an executable user scenario.",
             "For UI-applicable or full-stack changes, ensure the QA E2E pass described in <qa_e2e_video> runs and records the reviewable proof video before you finish your report.",
             `Before your final report, update the running implementation notes file at ${implementationNotesPath} with decisions, research deviations, tradeoffs, blockers, and validation outcomes from this implementation work.`,
             "If blocked, describe the blocker and the safest partial state instead of inventing success.",
@@ -187,10 +186,10 @@ export async function runRalphWorkflow(
         [
           "output_format",
           [
-            "After subagents have done the work, return Markdown with headings:",
+            "After the implementation work is complete, return Markdown with headings:",
             "1. Research file — the path you read",
-            "2. Delegations performed — subagents spawned and what each completed",
-            "3. Changes made — concrete changes from subagent work, not intentions",
+            "2. Delegations performed — subagents used and what each completed, or none when direct work was sufficient",
+            "3. Changes made — concrete completed changes, not intentions",
             "4. Files touched",
             "5. Validation run / recommended",
             "6. Deferred work or blockers",
@@ -252,16 +251,6 @@ export async function runRalphWorkflow(
             ],
             ...reviewerBModelConfig,
           },
-          {
-            name: "reviewer-c",
-            task: reviewPrompt,
-            reads: [
-              researchPath,
-              implementationNotesPath,
-              orchestratorReportPath,
-            ],
-            ...reviewerCModelConfig,
-          },
         ],
         {
           task: workflowPrompt,

package/dist/builtin/workflows/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/workflows",
-  "version": "0.9.5-alpha.9",
+  "version": "0.9.5",
   "private": true,
   "description": "Atomic extension for multi-stage workflow authoring and execution.",
   "contributors": [
@@ -83,7 +83,7 @@
   },
   "peerDependencies": {
     "@bastani/atomic": "*",
-    "@earendil-works/pi-tui": "^0.80.3"
+    "@earendil-works/pi-tui": "^0.80.6"
   },
   "peerDependenciesMeta": {
     "@bastani/atomic": {

package/dist/builtin/workflows/src/durable/stage-primitive.ts

@@ -7,6 +7,7 @@ import type { DurableWorkflowBackend } from "./backend.js";
 import type { ParallelFailFastScope } from "../runs/foreground/executor-types.js";
 import { durableHash } from "./backend.js";
 import { recordCheckpointDurably } from "./tool-primitive.js";
+import { RESUME_CONTINUATION_PROMPT } from "../shared/resume-continuation.js";
 import type { DurableStageCheckpoint } from "./types.js";
 export type DurableCompletedStageCheckpoint = DurableStageCheckpoint & { readonly output: WorkflowSerializableValue };
 
@@ -66,7 +67,7 @@ export async function recordStageSessionCheckpoint(deps: DurableStageDeps, stage
   return true;
 }
 
-const MID_SESSION_RESUME_PROMPT = "Continue";
+const MID_SESSION_RESUME_PROMPT = RESUME_CONTINUATION_PROMPT;
 
 function withMidSessionResumePrompt<T extends StageContext>(stage: T, enabled: boolean): T {
   if (!enabled) return stage;

package/dist/builtin/workflows/src/engine/primitives/task.ts

@@ -1,6 +1,7 @@
 import type { WorkflowChainOptions, WorkflowParallelOptions, WorkflowTaskOptions, WorkflowTaskResult, WorkflowTaskStep } from "../../shared/types.js";
 import type { ParallelFailFastScope } from "../../runs/foreground/executor-types.js";
 import type { EngineRuntime } from "../runtime.js";
+import { RESUME_CONTINUATION_PROMPT } from "../../shared/resume-continuation.js";
 import {
   applyTaskContext,
   structuredTaskOutputText,
@@ -51,7 +52,7 @@ function createTaskPrimitive(runtime: EngineRuntime): WorkflowTaskPrimitive {
       });
       const stage = stageHandle.context;
       const promptText = resolvedTaskOptions.resumeFromSessionFile !== undefined
-        ? "Continue"
+        ? RESUME_CONTINUATION_PROMPT
         : applyTaskContext(`${taskReadInstruction(resolvedTaskOptions)}${taskPrompt(resolvedTaskOptions)}`, taskPrevious(resolvedTaskOptions));
       const rawOutput = await stage.prompt(promptText, taskPromptOptions(resolvedTaskOptions));
       const structured = typeof rawOutput === "string" ? undefined : rawOutput;