@bastani/atomic 0.9.4 → 0.9.5-alpha.10

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

@@ -3,29 +3,45 @@ import { tmpdir } from "node:os";
 import { dirname, join } from "node:path";
 import { Type } from "typebox";
 import type { WorkflowTaskResult } from "../src/shared/types.js";
-import { E2E_VERIFICATION_GUIDANCE } from "./shared-prompts.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(
   {
     title: Type.String(),
     body: Type.String(),
     confidence_score: Type.Number({ minimum: 0, maximum: 1 }),
+    objective_alignment: Type.Union([
+      Type.Literal("required_by_objective"),
+      Type.Literal("consistent_with_objective"),
+      Type.Literal("beyond_objective"),
+      Type.Literal("contradicts_objective"),
+    ]),
     priority: Type.Optional(
       Type.Union([Type.Integer({ minimum: 0, maximum: 3 }), Type.Null()]),
     ),
@@ -46,6 +62,20 @@ const reviewFindingSchema = Type.Object(
   { additionalProperties: false },
 );
 
+const requirementsTraceabilitySchema = Type.Object(
+  {
+    requirement: Type.String(),
+    status: Type.Union([
+      Type.Literal("proven"),
+      Type.Literal("contradicted"),
+      Type.Literal("missing"),
+      Type.Literal("unverified"),
+    ]),
+    evidence: Type.String(),
+  },
+  { additionalProperties: false },
+);
+
 const reviewerErrorSchema = Type.Object(
   {
     kind: Type.Union([
@@ -69,6 +99,7 @@ export const reviewDecisionSchema = Type.Object(
     ]),
     overall_explanation: Type.String(),
     overall_confidence_score: Type.Number({ minimum: 0, maximum: 1 }),
+    requirements_traceability: Type.Array(requirementsTraceabilitySchema),
     stop_review_loop: Type.Boolean(),
     reviewer_error: Type.Optional(
       Type.Union([Type.Null(), reviewerErrorSchema]),
@@ -170,6 +201,7 @@ export function renderQaE2eVideoGuidance(qaVideoPath: string): string {
     `Record that QA E2E pass as a reviewable video so the user can watch the feature working. After \`playwright-cli open\`, start recording with \`playwright-cli video-start ${qaVideoPath}\`, annotate the scenario with \`playwright-cli video-chapter\` / \`playwright-cli video-show-actions\`, exercise the full user scenario, then \`playwright-cli video-stop\`. Write the video to exactly this path and overwrite any prior recording so it always reflects the latest implemented state: ${qaVideoPath}`,
     `After recording, add the video to the implementation notes as a reference: include a \`## QA E2E Video\` entry with the absolute path ${qaVideoPath} and a one-line description of the proven scenario, so the user can review the proof when this stage finishes.`,
     "If the change has no user-visible UI scenario (pure refactor, docs, infra, or non-UI library code), do not fabricate a video; record in the implementation notes that no QA E2E video applies and why.",
+    "Assume credentials, auth, and browser environment access exist until a concrete attempt proves otherwise. Before declaring the QA E2E video impractical, check credential/auth state with non-destructive commands, attempt to launch the app/flow, and record the exact command(s) plus observed failure output.",
     "If `playwright-cli` or a browser runtime is unavailable, install it once per the skill (`npm install -g @playwright/cli@latest`, then `npx playwright install chromium` for a missing browser executable). If it still cannot run, record the smallest validation actually performed and note that the QA E2E video could not be produced — never claim a video exists when it does not.",
   ].join("\n");
 }
@@ -178,6 +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: [],
@@ -186,6 +255,7 @@ export function reviewerErrorDecision(error: string): ReviewDecision {
       "Reviewer execution failed, so the review gate cannot safely approve the current repository state.",
     overall_confidence_score: 0,
     stop_review_loop: false,
+    requirements_traceability: [],
     reviewer_error: {
       kind: "reviewer_failure",
       message: error,
@@ -196,14 +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),
   };
 }
 
@@ -218,14 +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;
   }[];
 };
 
@@ -258,6 +329,7 @@ export function forkContinuationOptions(
 
 export function renderResearchPromptRefinementPrompt(args: {
   readonly request: string;
+  readonly acceptanceCriteria: string;
   readonly workflowCwdContext: PromptSection;
   readonly latestReviewReportPath: string | undefined;
 }): string {
@@ -265,6 +337,9 @@ export function renderResearchPromptRefinementPrompt(args: {
   return [
     basePrompt,
     taggedPrompt([
+      ["objective", `Research the full requested task: ${args.request}`],
+      ["acceptance_criteria", args.acceptanceCriteria],
+      ["literal_contract", LITERAL_OBJECTIVE_CONTRACT],
       args.workflowCwdContext,
       [
         "review_findings",
@@ -272,7 +347,7 @@ export function renderResearchPromptRefinementPrompt(args: {
           ? "No prior review artifact is available."
           : [
               `Latest review round artifact: ${args.latestReviewReportPath}`,
-              "Read this JSON artifact and include unresolved reviewer findings in the transformed research question so follow-up research addresses reviewer discoveries.",
+              "Read this JSON artifact and include unresolved reviewer findings in the transformed research question only when they are consistent with the literal objective and acceptance criteria.",
             ].join("\n"),
       ],
       [
@@ -285,6 +360,8 @@ export function renderResearchPromptRefinementPrompt(args: {
 
 export function renderResearchPrompt(args: {
   readonly transformedResearchQuestion: string;
+  readonly prompt: string;
+  readonly acceptanceCriteria: string;
   readonly workflowCwdContext: PromptSection;
   readonly latestReviewReportPath: string | undefined;
   readonly researchPath: string;
@@ -293,6 +370,9 @@ export function renderResearchPrompt(args: {
   return [
     basePrompt,
     taggedPrompt([
+      ["objective", `Research implementation requirements for: ${args.prompt}`],
+      ["acceptance_criteria", args.acceptanceCriteria],
+      ["literal_contract", LITERAL_OBJECTIVE_CONTRACT],
       args.workflowCwdContext,
       [
         "review_findings",
@@ -318,6 +398,7 @@ export function renderResearchPrompt(args: {
 
 export function renderForkedOrchestratorPrompt(args: {
   readonly prompt: string;
+  readonly acceptanceCriteria: string;
   readonly workflowCwdContext: PromptSection;
   readonly researchPath: string;
   readonly implementationNotesPath: string;
@@ -331,6 +412,8 @@ export function renderForkedOrchestratorPrompt(args: {
       ].join("\n"),
     ],
     ["objective", `Implement the full requested task: ${args.prompt}`],
+    ["acceptance_criteria", args.acceptanceCriteria],
+    ["literal_contract", LITERAL_OBJECTIVE_CONTRACT],
     args.workflowCwdContext,
     [
       "research",
@@ -351,10 +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",
@@ -367,6 +450,7 @@ export function renderForkedOrchestratorPrompt(args: {
 
 export type RalphInputs = {
   readonly prompt?: string;
+  readonly acceptance_criteria?: string;
   readonly max_loops?: number;
   readonly base_branch?: string;
   readonly git_worktree_dir?: string;
@@ -375,6 +459,7 @@ export type RalphInputs = {
 
 export type RalphWorkflowOptions = {
   readonly prompt: string;
+  readonly acceptanceCriteria: string;
   readonly maxLoops: number;
   readonly comparisonBaseBranch: string;
   readonly workflowStartCwd: string;

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

@@ -1,135 +1,167 @@
 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
+// Model chains are curated from Atomic's agentic-coding benchmark and the
+// July 2026 frontier refresh:
+// - 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 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
 //   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: "openai-codex/gpt-5.5:xhigh",
+    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",
-      "anthropic/claude-fable-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-fable-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: "openai-codex/gpt-5.5: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"
-    ],
-    excludedTools: ["ask_user_question"],
-};
-
-export const reviewerAModelConfig = {
-    model: "anthropic/claude-fable-5:xhigh",
+    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",
-      "openrouter/anthropic/claude-fable-5: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"],
-    schema: reviewDecisionSchema,
 };
 
-export const reviewerBModelConfig = {
-    model: "openai-codex/gpt-5.5:xhigh",
+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",
-      "anthropic/claude-fable-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-fable-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,
 };
 
-export const reviewerCModelConfig = {
-    model: "zai/glm-5.2:xhigh",
+export const reviewerBModelConfig = {
+    model: "openai-codex/gpt-5.6-sol:max",
     fallbackModels: [
-      "zai-coding-cn/glm-5.2:xhigh",
-      "openrouter/z-ai/glm-5.2:xhigh",
+      "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: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:xhigh",
-      "openrouter/anthropic/claude-opus-4-8:high"
+      "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,
 };
+

package/dist/builtin/workflows/builtin/ralph-review-gate.ts

@@ -1,3 +1,5 @@
+import { traceabilityProvenExceptFinalAction } from "./review-convergence.js";
+
 /**
  * Review-gate severity logic for the builtin `ralph` workflow.
  *
@@ -23,10 +25,17 @@
  * depend on the model correctly deriving that flag.
  */
 
+export type ObjectiveAlignment =
+  | "required_by_objective"
+  | "consistent_with_objective"
+  | "beyond_objective"
+  | "contradicts_objective";
+
 export type ReviewFinding = {
   readonly title: string;
   readonly body: string;
   readonly confidence_score: number;
+  readonly objective_alignment: ObjectiveAlignment;
   readonly priority?: number | null;
   readonly code_location: {
     readonly absolute_file_path: string;
@@ -46,12 +55,19 @@ export type ReviewerError = {
   readonly message: string;
   readonly attempted_recovery: string;
 };
+export type RequirementTraceability = {
+  readonly requirement: string;
+  readonly status: "proven" | "contradicted" | "missing" | "unverified";
+  readonly evidence: string;
+};
+
 
 export type ReviewDecision = {
   readonly findings: readonly ReviewFinding[];
   readonly overall_correctness: "patch is correct" | "patch is incorrect";
   readonly overall_explanation: string;
   readonly overall_confidence_score: number;
+  readonly requirements_traceability: readonly RequirementTraceability[];
   readonly stop_review_loop: boolean;
   readonly reviewer_error?: ReviewerError | null;
 };
@@ -69,6 +85,13 @@ export const MAX_BLOCKING_PRIORITY = 2;
  * approves.
  */
 export function isBlockingFinding(finding: ReviewFinding): boolean {
+  const alignment = finding.objective_alignment;
+  if (alignment === "beyond_objective" || alignment === "contradicts_objective") {
+    return false;
+  }
+  if (alignment !== "required_by_objective" && alignment !== "consistent_with_objective") {
+    return true;
+  }
   const priority = finding.priority;
   if (priority === undefined || priority === null) return true;
   return priority <= MAX_BLOCKING_PRIORITY;
@@ -76,14 +99,23 @@ export function isBlockingFinding(finding: ReviewFinding): boolean {
 
 /**
  * A single reviewer approves (would stop the loop) when it judged the patch
- * correct, surfaced no reviewer execution error, and filed no blocking
- * (P0/P1/P2) finding. P3 nice-to-haves and placeholder/dummy findings do not
- * block approval.
+ * correct, surfaced no reviewer execution error, filed no blocking (P0/P1/P2)
+ * finding, and supplied a non-empty requirement traceability map where every
+ * explicit requirement is proven. P3 nice-to-haves and placeholder/dummy
+ * findings do not block approval.
  */
-export function reviewDecisionApproved(decision: ReviewDecision): boolean {
+export function reviewDecisionApproved(
+  decision: ReviewDecision,
+  options: { readonly allowFinalActionRemaining?: boolean } = {},
+): boolean {
+  const traceability = decision.requirements_traceability;
   return (
     decision.overall_correctness === "patch is correct" &&
     decision.reviewer_error == null &&
-    !decision.findings.some(isBlockingFinding)
+    !decision.findings.some(isBlockingFinding) &&
+    traceabilityProvenExceptFinalAction({
+      traceability,
+      allowFinalActionRemaining: options.allowFinalActionRemaining === true,
+    })
   );
 }