@bastani/atomic 0.9.5-alpha.8 → 0.9.5

package/dist/builtin/workflows/README.md

@@ -5,7 +5,7 @@
   An open-source Atomic workflow extension: install it, author workflows in TypeScript, run them from chat.
 </p>
 
-Use workflows by default for non-trivial tasks, structured requests, and objectives with verifiable done criteria, including implementation, build, debugging, bug-fix, migration, new-feature, scoped multi-file, and validation-heavy docs/code work. Prompt language such as `do X until Y`, `repeat until`, `iterate until`, `review/fix until passing`, or `run checks and fix until green` is a strong signal to map the work to a workflow with an explicit stop condition rather than a direct chat turn.
+Use the least orchestration that fits the user's intent: keep interactive/exploratory work inline, use bounded single/chain/parallel subagents while the parent remains in control, and use workflows for clearly delegated, well-defined autonomous jobs that are likely long-running/background-oriented or materially need durable stages, artifacts/checkpoints, resumability, HIL, gates, retries, or bounded loops. Multiple steps, files, tests, validation, or parallelism alone do not require a workflow. Loop or stop-condition requests such as `do X until Y`, `repeat until`, `iterate until`, `review/fix until passing`, `run checks and fix until green`, or `keep going until done` are key workflow signals when the user delegates execution because they already define control flow and a completion condition. When workflow execution fits, Atomic may always author a custom TypeScript `workflow({...})` inline with normal coding tools if that shape best achieves the task; it is not limited to installed workflows or direct modes. Named workflows can be builtin, project, user, or package supplied, and direct task/tasks/chain modes cover one-off tracked shapes.
 
 <p align="center">
   <a href="#authoring-api">Authoring API</a>
@@ -300,7 +300,7 @@ Worktree semantics:
 - Symlinked repo/worktree paths preserve their logical spelling in the default cwd, matching Codex-style worktree behavior.
 - Explicit `cwd` still wins. Relative `cwd` values are resolved against the worktree default cwd; absolute `cwd` values are used as provided.
 
-`worktree: true` is different: it creates temporary isolated worktrees for direct task/parallel/chain execution and cleans them up afterward. It is mutually exclusive with `gitWorktreeDir`, which is intended for named/reusable worktrees that remain available across retries.
+`worktree: true` is different: it creates temporary isolated worktrees for direct task/parallel/chain execution and cleans them up afterward. It is mutually exclusive with `gitWorktreeDir`, which is intended for named/reusable worktrees that remain available across retries and `/workflow resume`. Durable resume records the original invocation cwd and resolved reusable-worktree metadata, then replays from that original repository context rather than whichever cwd the resumed interactive session currently has. Reusable worktree setup is cached within a workflow run, read-only Git repository probes retry a transient timeout once, and slow Git subprocess failures include the exact command, cwd, timeout, elapsed time, exit status/signal, and spawn error details.
 
 For advanced integrations, the SDK also exports `setupGitWorktree(options)`, which returns `{ worktreeRoot, cwd, repositoryRoot, created }` and uses the same validation/path behavior as the executor.
 
@@ -542,7 +542,7 @@ Tradeoff: `Type.Unsafe<T>()` does not deeply validate at runtime — it trusts t
 
 Input overrides are bare `key=value` tokens (no leading `--`). Values are JSON-parsed when possible, so numbers, booleans, and quoted strings work as expected (e.g. `count=3`, `flag=true`, `prompt="multi word value"`). A whole-object override can be passed as a single JSON token (e.g. `{"prompt":"...","count":3}`). Runtime validation is strict: unknown input keys, missing required values, type mismatches, and invalid `select` choices fail before a named workflow run starts.
 
-Workflows always run as **background tasks** in interactive sessions — the chat editor stays free while a run executes. Press **F2** (or `/workflow connect <run-id>`) to attach to the live graph viewer; HIL prompts (`ctx.ui.input/confirm/select/editor/custom`) appear as awaiting-input graph nodes. Press Enter on a focused node, or click a visible graph node directly, to open that stage and answer locally, never as a modal dialog over the chat. Attached stage chats capture mouse/trackpad wheel events by default so scrolling stays inside the active stage transcript or prompt instead of falling through to terminal/main-chat scrollback. Press `ctrl+t` to toggle **copy mode**: copy mode disables workflow-chat mouse reporting so normal terminal/tmux text selection can work; press `ctrl+t` again to leave copy mode and restore workflow-chat scrolling. While copy mode is on, wheel/trackpad gestures are handled by the terminal/tmux and may scroll terminal scrollback, so leave copy mode before using the wheel again. Human input is detected when those runtime `ctx.ui.*` calls execute; workflows no longer have a declaration-time HIL flag.
+Workflows always run as **background tasks** in interactive sessions — the chat editor stays free while a run executes. Press **F2** (or `/workflow connect <run-id>`) to attach to the live graph viewer; HIL prompts (`ctx.ui.input/confirm/select/editor/custom`) appear as awaiting-input graph nodes. Press Enter on a focused node, or click a visible graph node directly, to open that stage and answer locally, never as a modal dialog over the chat. Attached stage chats capture mouse/trackpad wheel events by default so scrolling stays inside the active stage transcript or prompt instead of falling through to terminal/main-chat scrollback. Press `ctrl+t` to toggle **copy mode**: copy mode disables workflow-chat mouse reporting so normal terminal/tmux text selection can work; press `ctrl+t` again to leave copy mode and restore workflow-chat scrolling. Archived read-only stage transcripts show the same copy-mode footer/status, allowing their transcript text to be selected and copied while preserving `esc` close and `ctrl+d` graph navigation. While copy mode is on, wheel/trackpad gestures are handled by the terminal/tmux and may scroll terminal scrollback, so leave copy mode before using the wheel again. Human input is detected when those runtime `ctx.ui.*` calls execute; workflows no longer have a declaration-time HIL flag.
 
 Durable resume preserves the original completed-stage shape: replayed stage/task/parallel/child checkpoints retain summaries, durations, session/model metadata, and parallel branch parentage in the graph instead of flattening fanout branches into a sequential replay chain.
 
@@ -557,7 +557,7 @@ Prompt answer replay is live-memory only. `StageSnapshot.promptAnswerState` repo
 ```json
 {
   "name": "workflow",
-  "description": "Run named workflows or direct one-off task/tasks/chain workflows; discover with list/get/inputs, inspect status/stages/stage details, send prompt answers or steering, pause/resume/interrupt/kill runs, and reload workflow resources. For large stage handoffs, write context to files/artifacts, pass paths via reads, and prompt downstream agents to 'Read the file at <path>...' instead of injecting large previous text. For transcripts, prefer status/stages/stage to get sessionFile/transcriptPath, quote the exact path without rewriting separators (Windows backslashes are valid), then search it with rg/grep and read small ranges; transcript is path-only by default when sessionFile/transcriptPath exists, explicit tail/limit returns bounded previews, and missing transcript paths fall back to a small preview.",
+  "description": "Run named builtin, project, user, or package workflows, or direct one-off task/tasks/chain workflows; when workflow execution fits but another shape would better achieve the task, author a custom TypeScript workflow({...}) inline with normal coding tools, reload it, and run it; discover with list/get/inputs, inspect status/stages/stage details, send prompt answers or steering, pause/resume/interrupt/kill runs, and reload workflow resources. For large stage handoffs, write context to files/artifacts, pass paths via reads, and prompt downstream agents to 'Read the file at <path>...' instead of injecting large previous text. For transcripts, prefer status/stages/stage to get sessionFile/transcriptPath, quote the exact path without rewriting separators (Windows backslashes are valid), then search it with rg/grep and read small ranges; transcript is path-only by default when sessionFile/transcriptPath exists, explicit tail/limit returns bounded previews, and missing transcript paths fall back to a small preview.",
   "parameters": {
     "workflow": "string (optional) — workflow ID or normalized name",
     "inputs": "object (optional) — key/value map of workflow inputs",
@@ -683,7 +683,7 @@ Child workflow outputs: `result`, `status`, `approved`, `goal_id`, `objective`,
 
 ### `ralph`
 
-Raw prompt → prompt-engineering research → orchestrate → review workflow with optional final-stage PR handoff: use the raw prompt as the operative objective, keep optional `acceptance_criteria` as the immutable original task contract (defaulting to `prompt`), transform the prompt into a codebase and online research question with `/skill:prompt-engineer`, run `/skill:research-codebase` against it, write findings under `research/`, delegate implementation through sub-agents from that research, run parallel reviewers across Claude Fable 5, GPT-5.5 Codex, and Gemini 3.1 Pro model families, and iterate until approval or the loop limit. Ralph's research, orchestrator, and reviewer prompts receive the objective next to the literal acceptance contract; when launching follow-up Ralph runs from reviewer findings, pass the ORIGINAL task text as `acceptance_criteria` so deltas cannot drift from the contract. Ralph's orchestrator and reviewers are prompted to verify user-visible behavior end-to-end when practical with `playwright-cli`-skilled subagents for web/frontend flows that may depend on backend/API behavior and tmux-skilled subagents for TUI or terminal-app scenarios. They must assume credentials/auth/environment access exists until concrete non-destructive checks plus an actual launch/flow attempt prove otherwise; skipped E2E is valid only when exact attempted commands and observed failure output are recorded. For UI-applicable or full-stack changes, the orchestrator runs a `playwright-cli` end-to-end QA pass and records a reviewable proof video, references it in the implementation notes, and exposes it as the `qa_video_path` output; reviewers receive that path and inspect the actual video before treating it as proof. Review decisions include `requirements_traceability`, a non-empty clause-by-clause map over every prompt/acceptance-criteria requirement, and Ralph approval requires every entry to be `proven`; worker-authored tests/snapshots passing are circular evidence unless tied to independent current-state proof. When `create_pr=true`, the final `pull-request` stage attaches or links that video to the created PR/MR/review. Follow-up iterations pass unresolved review artifacts into prompt-engineering/research and fork research from prior research session data when available. Ralph skips PR creation by default; prompt text alone does not opt in. Pass `create_pr=true` to authorize only the final `pull-request` stage to inspect provider credentials and attempt provider-appropriate PR/MR/review creation (for example GitHub `gh`, Azure Repos `az repos pr create`, or Sapling/Phabricator tooling). Ralph's own PR-creation instructions live in that final stage. Reviewers inspect repository infrastructure directly as needed; Ralph no longer runs separate `infra-*` discovery stages.
+Raw prompt → prompt-engineering research → orchestrate → review workflow with optional final-stage PR handoff: use the raw prompt as the operative objective, keep optional `acceptance_criteria` as the immutable original task contract (defaulting to `prompt`), transform the prompt into a codebase and online research question with `/skill:prompt-engineer`, run `/skill:research-codebase` against it, write findings under `research/`, delegate implementation through sub-agents from that research, run parallel reviewers across Claude Fable 5 and GPT-5.5 Codex model families, and iterate until approval or the loop limit. Ralph's research, orchestrator, and reviewer prompts receive the objective next to the literal acceptance contract; when launching follow-up Ralph runs from reviewer findings, pass the ORIGINAL task text as `acceptance_criteria` so deltas cannot drift from the contract. Ralph's orchestrator and reviewers are prompted to verify user-visible behavior end-to-end when practical with `playwright-cli`-skilled subagents for web/frontend flows that may depend on backend/API behavior and tmux-skilled subagents for TUI or terminal-app scenarios. They must assume credentials/auth/environment access exists until concrete non-destructive checks plus an actual launch/flow attempt prove otherwise; skipped E2E is valid only when exact attempted commands and observed failure output are recorded. For UI-applicable or full-stack changes, the orchestrator runs a `playwright-cli` end-to-end QA pass and records a reviewable proof video, references it in the implementation notes, and exposes it as the `qa_video_path` output; reviewers receive that path and inspect the actual video before treating it as proof. Review decisions include `requirements_traceability`, a non-empty clause-by-clause map over every prompt/acceptance-criteria requirement, and Ralph approval requires every entry to be `proven`; worker-authored tests/snapshots passing are circular evidence unless tied to independent current-state proof. When `create_pr=true`, the final `pull-request` stage attaches or links that video to the created PR/MR/review. Follow-up iterations pass unresolved review artifacts into prompt-engineering/research and fork research from prior research session data when available. Ralph skips PR creation by default; prompt text alone does not opt in. Pass `create_pr=true` to authorize only the final `pull-request` stage to inspect provider credentials and attempt provider-appropriate PR/MR/review creation (for example GitHub `gh`, Azure Repos `az repos pr create`, or Sapling/Phabricator tooling). Ralph's own PR-creation instructions live in that final stage. Reviewers inspect repository infrastructure directly as needed; Ralph no longer runs separate `infra-*` discovery stages.
 
 ```text
 /workflow ralph prompt="Migrate the database layer to Drizzle ORM" max_loops=3 base_branch=develop

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

@@ -8,6 +8,7 @@ import {
   type GoalWorkflowInputs,
   type GoalWorkflowOutputs,
   type ReviewRecord,
+  type ReducerDecision,
 } from "./goal-types.js";
 import { artifactSafeName, writeReviewArtifact, writeReviewRoundArtifact } from "./goal-artifacts.js";
 import { appendLifecycleEvent, createGoalLedger, writeGoalLedger } from "./goal-ledger.js";
@@ -75,6 +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;
@@ -92,22 +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"],
     };
@@ -115,18 +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,
@@ -255,12 +298,14 @@ 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) {
+        reviewerBatchFailed = true;
         reviewResults = [
           {
             name: "reviewer-error",
@@ -308,6 +353,20 @@ 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,

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,
-};