@bastani/atomic 0.9.5-alpha.1 → 0.9.5-alpha.10

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

@@ -8,8 +8,9 @@ import {
   type GoalWorkflowInputs,
   type GoalWorkflowOutputs,
   type ReviewRecord,
+  type ReducerDecision,
 } from "./goal-types.js";
-import { writeReviewArtifact, writeReviewRoundArtifact } from "./goal-artifacts.js";
+import { artifactSafeName, writeReviewArtifact, writeReviewRoundArtifact } from "./goal-artifacts.js";
 import { appendLifecycleEvent, createGoalLedger, writeGoalLedger } from "./goal-ledger.js";
 import {
   collectRemainingWork,
@@ -17,14 +18,13 @@ import {
 } from "./goal-reducer.js";
 import { formatReviewReport, renderFinalReport } from "./goal-reports.js";
 import {
-  reviewDecisionFromResult,
-  reviewerErrorDecision,
+  parsedReviewDecisionFromResult,
   reviewDecisionToRecord,
 } from "./goal-review.js";
+import { reviewerFailureText } from "./review-convergence.js";
 import {
   WORKER_PREFLIGHT_CONTRACT,
   WORKER_RECEIPT_CONTRACT,
-  goalRunnerTools,
   renderForkedGoalWorkerPrompt,
   renderGoalContinuationPrompt,
   renderReviewerPrompt,
@@ -76,6 +76,27 @@ type GoalWorkflowOptions = {
   readonly workflowStartCwd: string;
 };
 
+function reviewerExecutionFailedDecision(input: {
+  readonly turn: number;
+  readonly reviewQuorum: number;
+  readonly reviews: readonly ReviewRecord[];
+  readonly reason: string;
+}): ReducerDecision {
+  return {
+    turn: input.turn,
+    decision: "needs_human",
+    reason: input.reason,
+    complete_votes: input.reviews.filter((review) => review.decision === "complete").length,
+    review_quorum: input.reviewQuorum,
+    parsed: input.reviews.every((review) => review.parsed),
+    approved: false,
+    stopReviewLoop: false,
+    nextAction: "needs_human",
+    finalActionRemaining: false,
+    diagnostics: input.reviews.flatMap((review) => review.parse_diagnostics),
+  };
+}
+
 export async function runGoalWorkflow(ctx: GoalRunnerContext, options: GoalWorkflowOptions): Promise<GoalWorkflowOutputs> {
     const inputs = ctx.inputs;
     const createPr = options.createPr;
@@ -93,42 +114,64 @@ 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"
       ],
-      tools: goalRunnerTools,
+      excludedTools: ["ask_user_question"],
     };
 
     const reviewerModelConfig = {
-      model: "anthropic/claude-fable-5:xhigh",
+      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:xhigh",
-          "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"
       ],
-      tools: goalRunnerTools,
+      excludedTools: ["ask_user_question"],
       schema: reviewDecisionSchema,
     };
 
@@ -192,6 +235,12 @@ export async function runGoalWorkflow(ctx: GoalRunnerContext, options: GoalWorkf
           reason: terminalRemainingWork,
           complete_votes: 0,
           review_quorum: reviewQuorum,
+          parsed: false,
+          approved: false,
+          stopReviewLoop: false,
+          nextAction: "needs_human",
+          finalActionRemaining: false,
+          diagnostics: [terminalRemainingWork],
         });
         appendLifecycleEvent(ledger, "status_decided", terminalRemainingWork, turn);
         await writeGoalLedger(ledgerPath, ledger);
@@ -224,6 +273,7 @@ export async function runGoalWorkflow(ctx: GoalRunnerContext, options: GoalWorkf
           comparisonBaseBranch,
           reviewQuorum,
           blockerThreshold,
+          createPr,
         }),
         reads: [ledgerPath, workTurnPath],
         ...reviewerModelConfig,
@@ -248,42 +298,48 @@ export async function runGoalWorkflow(ctx: GoalRunnerContext, options: GoalWorkf
       ];
 
       let reviewResults: WorkflowTaskResult[];
+      let reviewerBatchFailed = false;
       try {
         reviewResults = await ctx.parallel(reviewerSteps, {
           task: objective,
-          failFast: false,
+          failFast: true,
         });
       } catch (err) {
-        const message = err instanceof Error ? err.message : String(err);
-        const structured = reviewerErrorDecision(message);
+        reviewerBatchFailed = true;
         reviewResults = [
           {
             name: "reviewer-error",
             stageName: "reviewer-error",
-            text: JSON.stringify(structured, null, 2),
-            structured,
+            text: reviewerFailureText(err),
           },
         ];
       }
 
       latestReviews = await Promise.all(reviewResults.map(async (result) => {
         const reviewerName = result.name ?? result.stageName;
-        const parsed = reviewDecisionFromResult(result) ??
-          reviewerErrorDecision(
-            `Reviewer ${reviewerName} returned no structured decision.`,
-          );
-        const reviewArtifactPath = await writeReviewArtifact(
+        const normalizedReviewerName = reviewerName.replace(/-\d+$/u, "");
+        const parsed = parsedReviewDecisionFromResult(result, reviewerName);
+        const reviewArtifactPath = join(
           artifactDir,
-          reviewerName.replace(/-\d+$/u, ""),
-          parsed,
-          result.text,
+          `review-${artifactSafeName(normalizedReviewerName)}.json`,
         );
-        return reviewDecisionToRecord({
+        const record = reviewDecisionToRecord({
           turn,
-          reviewer: reviewerName.replace(/-\d+$/u, ""),
+          reviewer: normalizedReviewerName,
           artifactPath: reviewArtifactPath,
-          decision: parsed,
+          decision: parsed.decision,
+          parsed: parsed.parsed,
+          diagnostics: parsed.diagnostics,
+          allowFinalActionRemaining: createPr,
         });
+        await writeReviewArtifact(
+          artifactDir,
+          normalizedReviewerName,
+          parsed.decision,
+          result.text,
+          record.convergence_decision,
+        );
+        return record;
       }));
       latestReviewArtifactPaths = latestReviews.map((review) => review.artifact_path);
       latestReviewReportPath = await writeReviewRoundArtifact(
@@ -297,12 +353,27 @@ export async function runGoalWorkflow(ctx: GoalRunnerContext, options: GoalWorkf
         `Recorded ${latestReviews.length} reviewer decisions.`,
         turn,
       );
+      if (reviewerBatchFailed) {
+        terminalRemainingWork = collectRemainingWork(latestReviews);
+        const reason = `Reviewer execution failed before quorum could be established. Remaining work: ${terminalRemainingWork}`;
+        ledger.decisions.push(reviewerExecutionFailedDecision({
+          turn,
+          reviewQuorum,
+          reviews: latestReviews,
+          reason,
+        }));
+        ledger.status = "needs_human";
+        appendLifecycleEvent(ledger, "status_decided", reason, turn);
+        await writeGoalLedger(ledgerPath, ledger);
+        break;
+      }
 
       const reducerOutcome = reduceGoalDecision(ledger, latestReviews, {
         turn,
         maxTurns,
         reviewQuorum,
         blockerThreshold,
+        nextActionOnComplete: createPr ? "pull-request" : "finish",
       });
       if (reducerOutcome.blockerObservation !== undefined) {
         ledger.blockers.push(reducerOutcome.blockerObservation);

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

@@ -1,3 +1,5 @@
+import type { ReviewConvergenceSummary } from "./review-convergence.js";
+
 export const DEFAULT_MAX_TURNS = 10;
 // Goal Runner runs three independent reviewer personas; two approvals form a majority.
 export const DEFAULT_REVIEW_QUORUM = 2;
@@ -74,6 +76,10 @@ export type ReviewRecord = ReviewDecision & {
   readonly turn: number;
   readonly reviewer: string;
   readonly artifact_path: string;
+  readonly parsed: boolean;
+  readonly approved: boolean;
+  readonly parse_diagnostics: readonly string[];
+  readonly convergence_decision: ReviewConvergenceSummary;
 };
 
 export type BlockerObservation = {
@@ -82,7 +88,7 @@ export type BlockerObservation = {
   readonly reviewers: readonly string[];
 };
 
-export type ReducerDecision = {
+export type ReducerDecision = ReviewConvergenceSummary & {
   readonly turn: number;
   readonly decision: "complete" | "continue" | "blocked" | "needs_human";
   readonly reason: string;
@@ -130,6 +136,7 @@ export type GoalWorkflowInputs = {
   readonly acceptance_criteria?: string;
   readonly max_turns: number;
   readonly base_branch: string;
+  readonly git_worktree_dir: string;
   readonly create_pr: boolean;
 };
 

package/dist/builtin/workflows/builtin/goal.d.ts

@@ -14,6 +14,7 @@ export type GoalWorkflowInputs = WorkflowInputValues & {
   readonly acceptance_criteria?: string;
   readonly max_turns: number;
   readonly base_branch: string;
+  readonly git_worktree_dir: string;
   readonly create_pr: boolean;
 };
 
@@ -22,6 +23,7 @@ export type GoalWorkflowRunInputs = WorkflowInputValues & {
   readonly acceptance_criteria?: string;
   readonly max_turns?: number;
   readonly base_branch?: string;
+  readonly git_worktree_dir?: string;
   readonly create_pr?: boolean;
 };
 

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

@@ -25,6 +25,11 @@ export default workflow({
       default: "origin/main",
       description: "Optional branch reviewers compare the current code delta against (default origin/main).",
     }),
+    git_worktree_dir: Type.String({
+      default: "",
+      description:
+        "Optional Git worktree path. Must start inside a Git repo; absolute paths are used as-is, relative paths resolve from the repo root, existing Git worktrees from the invoking repository are reused/shared as-is, and missing paths are created from base_branch.",
+    }),
     create_pr: Type.Boolean({
       default: false,
       description:
@@ -55,6 +60,10 @@ export default workflow({
     review_report_path: Type.Optional(Type.String({ description: "JSON artifact path for the latest reviewer decision round." })),
     pr_report: Type.Optional(Type.String({ description: "Pull-request report emitted only when create_pr=true, Goal reaches complete, and the final pull-request stage runs." })),
   },
+  worktreeFromInputs: {
+    gitWorktreeDir: "git_worktree_dir",
+    baseBranch: "base_branch",
+  },
   run: async (ctx) => {
     const workflowCtx = ctx;
     const workflowStartCwd = workflowCtx.cwd ?? process.cwd();

package/dist/builtin/workflows/builtin/index.d.ts

@@ -40,6 +40,7 @@ export type GoalWorkflowInputs = WorkflowInputValues & {
   readonly acceptance_criteria?: string;
   readonly max_turns: number;
   readonly base_branch: string;
+  readonly git_worktree_dir: string;
   readonly create_pr: boolean;
 };
 export type GoalWorkflowRunInputs = WorkflowInputValues & {
@@ -47,6 +48,7 @@ export type GoalWorkflowRunInputs = WorkflowInputValues & {
   readonly acceptance_criteria?: string;
   readonly max_turns?: number;
   readonly base_branch?: string;
+  readonly git_worktree_dir?: string;
   readonly create_pr?: boolean;
 };
 export type GoalWorkflowOutputs = WorkflowOutputValues & {

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

@@ -78,14 +78,25 @@ export async function runOpenClaudeDesignWorkflow(ctx: OpenClaudeDesignContext):
   // strictly dominated in Atomic's benchmark (see ralph-models.ts). Opus stays
   // at :xhigh here — visual quality, not $/task, is the objective for design.
   const designModelConfig = {
-    model: "anthropic/claude-fable-5:xhigh",
+    model: "anthropic/claude-fable-5:high",
     fallbackModels: [
-      "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",
+      "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",
-      "openrouter/anthropic/claude-fable-5:xhigh",
-      "openrouter/anthropic/claude-opus-4-8: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

@@ -5,21 +5,31 @@ import { Type } from "typebox";
 import type { WorkflowTaskResult } from "../src/shared/types.js";
 import { E2E_VERIFICATION_GUIDANCE, LITERAL_OBJECTIVE_CONTRACT } from "./shared-prompts.js";
 import type { ReviewDecision } from "./ralph-review-gate.js";
+import { reviewDecisionApproved } from "./ralph-review-gate.js";
+import {
+  parseFailureDiagnostics,
+  finalActionRemaining,
+  reviewerFailureText,
+  summarizeReviewConvergence,
+  type ParsedReviewDecision,
+  type ReviewConvergenceSummary,
+} from "./review-convergence.js";
+
 
 export const DEFAULT_MAX_LOOPS = 10;
 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(
   {
@@ -200,6 +210,43 @@ export function reviewDecisionFromResult(result: WorkflowTaskResult): ReviewDeci
   return result.structured as ReviewDecision | undefined;
 }
 
+export function parsedReviewDecisionFromResult(
+  result: WorkflowTaskResult,
+  reviewer: string,
+): ParsedReviewDecision<ReviewDecision> {
+  const parsed = reviewDecisionFromResult(result);
+  if (parsed !== undefined) {
+    return { decision: parsed, parsed: true, diagnostics: [] };
+  }
+  const diagnostics = parseFailureDiagnostics(reviewer, result.text);
+  return {
+    decision: reviewerErrorDecision(diagnostics.join("\n")),
+    parsed: false,
+    diagnostics,
+  };
+}
+
+export function ralphReviewConvergence(args: {
+  readonly decision: ReviewDecision;
+  readonly parsed: boolean;
+  readonly diagnostics: readonly string[];
+  readonly allowFinalActionRemaining: boolean;
+}): ReviewConvergenceSummary {
+  const approved = reviewDecisionApproved(args.decision, {
+    allowFinalActionRemaining: args.allowFinalActionRemaining,
+  });
+  const hasFinalActionRemaining = args.allowFinalActionRemaining &&
+    finalActionRemaining(args.decision.requirements_traceability);
+  return summarizeReviewConvergence({
+    parsed: args.parsed,
+    approved,
+    stopReviewLoop: args.decision.stop_review_loop,
+    nextAction: approved && hasFinalActionRemaining ? "pull-request" : approved ? "finish" : "implementation",
+    finalActionRemaining: approved && hasFinalActionRemaining,
+    diagnostics: args.diagnostics,
+  });
+}
+
 export function reviewerErrorDecision(error: string): ReviewDecision {
   return {
     findings: [],
@@ -219,14 +266,12 @@ export function reviewerErrorDecision(error: string): ReviewDecision {
 }
 
 export function reviewerErrorResult(
-  error: string,
+  error: unknown,
 ): WorkflowTaskResult {
-  const structured = reviewerErrorDecision(error);
   return {
     name: "reviewer-error",
     stageName: "reviewer-error",
-    text: JSON.stringify(structured, null, 2),
-    structured,
+    text: reviewerFailureText(error),
   };
 }
 
@@ -241,14 +286,17 @@ export function artifactSafeName(value: string): string {
 type ReviewArtifact = {
   readonly reviewer: string;
   readonly decision: ReviewDecision;
+  readonly convergence_decision: ReviewConvergenceSummary;
   readonly raw_text: string;
 };
 
 type ReviewRoundArtifact = {
+  readonly convergence_decision: ReviewConvergenceSummary;
   readonly reviews: readonly {
     readonly reviewer: string;
     readonly artifact_path: string;
     readonly decision: ReviewDecision;
+    readonly convergence_decision: ReviewConvergenceSummary;
   }[];
 };
 
@@ -386,10 +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",