@bastani/atomic 0.9.10 → 0.9.11-alpha.10

package/dist/builtin/workflows/builtin/adversarial-verification-prompts.ts

@@ -1,15 +1,18 @@
+const GROUNDED_REPORTING = "Before reporting progress, audit each claim against a tool result from this session. Report only work you can point to evidence for; say so explicitly when something is unverified.";
+const READABLE_REPORT = "Lead with the outcome. Keep facts, decisions, caveats, and next steps; drop background and repetition. Use complete, readable sentences rather than compressed fragments.";
+
 export function renderWorkerPrompt(task: string): string {
-  return `<role>\nYou produce a candidate solution for independent verification.\n</role>\n\n<objective>\n${task}\n</objective>\n\n<requirements>\nComplete the task, preserve concrete evidence, and state every validation performed. Do not claim success without observable support.\n</requirements>\n\n<output_format>\nA self-contained candidate with actions taken, evidence, validation, and remaining risks.\n</output_format>`;
+  return `<role>\nYou produce a candidate solution for independent verification.\n</role>\n\n<success_criteria>\nThe task is complete and important claims have observable support. Preserve concrete evidence and state every validation performed.\n</success_criteria>\n\n<stop_rules>\nStop when the candidate is complete and validated where practical, or state the evidence still missing.\n</stop_rules>\n\n<output_format>\nA self-contained candidate with actions taken, evidence, validation, and remaining risks. ${READABLE_REPORT}\n${GROUNDED_REPORTING}\n</output_format>\n\n<objective>\n${task}\n</objective>`;
 }
 
 export function renderVerifierPrompt(task: string, candidatePath: string, rubricPath: string): string {
-  return `<role>\nYou are an independent adversarial verifier. Find blockers; do not rewrite the candidate.\n</role>\n\n<objective>\nVerify the candidate against the task and rubric. Task: ${task}\n</objective>\n\n<artifacts>\nRead the complete candidate at ${candidatePath} and rubric at ${rubricPath}.\n</artifacts>\n\n<requirements>\nTest important claims where practical. A pass requires concrete evidence for every rubric item. Report precise blocking findings; absence of evidence is not evidence of correctness.\n</requirements>\n\n<output_format>\nCall structured_output with verdict (pass or fail), evidence, and blocking_findings.\n</output_format>`;
+  return `<artifacts>\nRead the complete candidate at ${candidatePath} and rubric at ${rubricPath}.\n</artifacts>\n\n<role>\nYou are an independent adversarial verifier. Find blockers; do not rewrite the candidate.\n</role>\n\n<success_criteria>\nA pass requires concrete evidence for every rubric item; absence of evidence is not evidence of correctness.\n</success_criteria>\n\n<evidence_rules>\nTest important claims where practical. For each conclusion, report the command run, observed output, and file:line evidence where applicable. Report precise blocking findings. ${GROUNDED_REPORTING}\n</evidence_rules>\n\n<stop_rules>\nStop after every rubric item has pass evidence or a precise blocking finding.\n</stop_rules>\n\n<output_format>\nCall structured_output with verdict (pass or fail), concise evidence, and blocking_findings. ${READABLE_REPORT}\n</output_format>\n\n<objective>\nVerify the candidate against the task and rubric. Task: ${task}\n</objective>`;
 }
 
 export function renderReducerPrompt(task: string, candidatePath: string, verifierPaths: readonly string[], repairsCompleted: number, maxRepairs: number): string {
-  return `<role>\nYou reduce independent verification reports into one deterministic next action.\n</role>\n\n<objective>\nDecide whether the candidate for ${task} is accepted, rejected, or needs repair.\n</objective>\n\n<artifacts>\nCandidate: ${candidatePath}\nVerifier reports: ${verifierPaths.join(", ")}\n</artifacts>\n\n<decision_rules>\nAccept only when all material rubric requirements have pass evidence. Request repair when findings are actionable and repair budget remains (${repairsCompleted}/${maxRepairs}). Reject when evidence proves the candidate cannot satisfy the task or the repair budget is exhausted. Preserve unresolved blockers verbatim.\n</decision_rules>\n\n<output_format>\nCall structured_output with decision (accept, reject, or repair), rationale, and remaining_work.\n</output_format>`;
+  return `<artifacts>\nCandidate: ${candidatePath}\nVerifier reports: ${verifierPaths.join(", ")}\n</artifacts>\n\n<role>\nYou reduce independent verification reports into one deterministic next action.\n</role>\n\n<decision_rules>\nAccept only when all material rubric requirements have pass evidence. Request repair when findings are actionable and repair budget remains (${repairsCompleted}/${maxRepairs}). Reject when evidence proves the candidate cannot satisfy the task or the repair budget is exhausted. Preserve unresolved blockers verbatim.\n</decision_rules>\n\n<success_criteria>\nThe decision follows the evidence and repair bound, with every unresolved blocker preserved.\n</success_criteria>\n\n<stop_rules>\nStop after selecting exactly one decision: accept, reject, or repair.\n</stop_rules>\n\n<output_format>\nCall structured_output with decision (accept, reject, or repair), a concise evidence-based rationale, and remaining_work. ${READABLE_REPORT}\n${GROUNDED_REPORTING}\n</output_format>\n\n<objective>\nDecide whether the candidate for ${task} is accepted, rejected, or needs repair.\n</objective>`;
 }
 
 export function renderRepairPrompt(task: string, candidatePath: string, reviewPath: string): string {
-  return `<role>\nYou repair a candidate using independent blocking findings.\n</role>\n\n<objective>\nRepair the candidate for: ${task}\n</objective>\n\n<artifacts>\nRead the current candidate at ${candidatePath} and reducer report at ${reviewPath}.\n</artifacts>\n\n<requirements>\nAddress every actionable blocker, rerun relevant validation, and retain valid prior work. Do not dismiss a finding without contrary evidence.\n</requirements>\n\n<output_format>\nA complete replacement candidate with repair summary, evidence, validation, and remaining risks.\n</output_format>`;
+  return `<artifacts>\nRead the current candidate at ${candidatePath} and reducer report at ${reviewPath}.\n</artifacts>\n\n<role>\nYou repair a candidate using independent blocking findings.\n</role>\n\n<success_criteria>\nEvery actionable blocker is addressed, relevant validation is rerun, and valid prior work is retained.\n</success_criteria>\n\n<evidence_rules>\nDo not dismiss a finding without contrary evidence. Report commands run, observed output, and file:line evidence where applicable. ${GROUNDED_REPORTING}\n</evidence_rules>\n\n<stop_rules>\nStop when all actionable blockers are repaired and validated, or list any blocker that remains with the missing evidence.\n</stop_rules>\n\n<output_format>\nA complete replacement candidate with repair summary, evidence, validation, and remaining risks. ${READABLE_REPORT}\n</output_format>\n\n<objective>\nRepair the candidate for: ${task}\n</objective>`;
 }

package/dist/builtin/workflows/builtin/adversarial-verification-runner.ts

@@ -47,7 +47,7 @@ export async function runAdversarialVerification(ctx: WorkflowRunContext<Inputs>
   const root = await stableArtifactRoot(ctx, "adversarial-verification");
   const rubricPath = join(root, "rubric.md");
   const candidatePath = join(root, "candidate.md");
-  await writeFile(rubricPath, ["# Verification rubric", "- The candidate satisfies the literal task.", "- Important claims cite observable evidence.", "- Relevant validation is executed and reported.", "- No blocking correctness, safety, or completeness gap remains."].join("\n"));
+  await writeFile(rubricPath, ["# Verification rubric", "- The candidate satisfies the literal task.", "- Important claims cite observable evidence.", "- Relevant validation is executed and reported with commands run and observed output.", "- File findings cite file:line evidence where applicable.", "- No blocking correctness, safety, or completeness gap remains."].join("\n"));
   await ctx.task("worker", { prompt: renderWorkerPrompt(ctx.inputs.task), context: "fresh", output: candidatePath, outputMode: "file-only" });
 
   let repairsCompleted = 0;

package/dist/builtin/workflows/builtin/adversarial-verification.ts

@@ -1,5 +1,6 @@
 import { Type } from "typebox";
 import { workflow } from "../src/authoring/workflow.js";
+import { withSteeringPropagationContext } from "./steering-context.js";
 import { runAdversarialVerification } from "./adversarial-verification-runner.js";
 
 export default workflow({
@@ -20,5 +21,5 @@ export default workflow({
     artifact_dir: Type.String({ description: "Directory containing run artifacts." }),
     remaining_work: Type.Array(Type.String(), { description: "Unresolved blocking findings when not approved." }),
   },
-  run: runAdversarialVerification,
+  run: async (ctx) => await runAdversarialVerification(withSteeringPropagationContext(ctx)),
 });

package/dist/builtin/workflows/builtin/classify-and-act-prompts.ts

@@ -1,5 +1,8 @@
+const GROUNDED_REPORTING = "Before reporting progress, audit each claim against a tool result from this session. Report only work you can point to evidence for; say so explicitly when something is unverified.";
+const READABLE_REPORT = "Lead with the outcome. Keep facts, decisions, caveats, and next steps; drop background and repetition. Use complete, readable sentences rather than compressed fragments.";
+
 export function classifierPrompt(prompt: string, categories: readonly string[]): string {
-  return `<role>\nYou route a task to exactly one declared action category.\n</role>\n\n<objective>\nClassify this task: ${prompt}\n</objective>\n\n<categories>\n${categories.map((category) => `- ${category}`).join("\n")}\n</categories>\n\n<requirements>\nChoose a category verbatim from the list. Base confidence on concrete wording in the task. Use low confidence when the task is ambiguous or spans categories. Provide a concise evidence-based rationale. Return only the structured result requested by the schema.\n</requirements>`;
+  return `<categories>\n${categories.map((category) => `- ${category}`).join("\n")}\n</categories>\n\n<role>\nYou route a task to exactly one declared action category.\n</role>\n\n<success_criteria>\nThe selected category is copied verbatim and supported by the task's concrete wording.\n</success_criteria>\n\n<decision_rules>\nChoose exactly one listed category. Use low confidence when the task is ambiguous or spans categories. Stop after making that single classification.\n</decision_rules>\n\n<output_format>\nReturn only the structured result requested by the schema: category, confidence, and a concise evidence-based rationale in complete sentences.\n</output_format>\n\n<objective>\nClassify this task: ${prompt}\n</objective>`;
 }
 
 export function actionPrompt(input: {
@@ -7,5 +10,5 @@ export function actionPrompt(input: {
   readonly category: string;
   readonly classificationPath: string;
 }): string {
-  return `<role>\nYou are the isolated action agent for category "${input.category}".\n</role>\n\n<objective>\n${input.prompt}\n</objective>\n\n<evidence>\nRead the classification artifact at ${input.classificationPath}. Use only relevant evidence available to this stage; do not assume access to classifier conversation context.\n</evidence>\n\n<success_criteria>\nComplete the requested action for this category, distinguish verified facts from assumptions, and report concrete evidence, validation, and remaining risks.\n</success_criteria>\n\n<output_format>\nMarkdown with Outcome, Evidence, Validation, and Remaining risks headings.\n</output_format>`;
+  return `<evidence>\nRead the classification artifact at ${input.classificationPath}. Use only relevant evidence available to this stage; do not assume access to classifier conversation context.\n</evidence>\n\n<role>\nYou are the isolated action agent for category "${input.category}".\n</role>\n\n<success_criteria>\nComplete the requested action for this category, distinguish verified facts from assumptions, and report concrete evidence, validation, and remaining risks.\n</success_criteria>\n\n<stop_rules>\nStop when the category-specific action is complete or a remaining blocker is stated with its missing evidence.\n</stop_rules>\n\n<output_format>\nMarkdown with Outcome, Evidence, Validation, and Remaining risks headings. ${READABLE_REPORT}\n${GROUNDED_REPORTING}\n</output_format>\n\n<objective>\n${input.prompt}\n</objective>`;
 }

package/dist/builtin/workflows/builtin/classify-and-act-runner.ts

@@ -1,4 +1,4 @@
-import { readFile, writeFile } from "node:fs/promises";
+import { writeFile } from "node:fs/promises";
 import { join } from "node:path";
 import { Type } from "typebox";
 import type { WorkflowRunContext, WorkflowSerializableValue } from "../src/shared/types.js";
@@ -40,11 +40,6 @@ function actionTools(category: string): readonly string[] {
   return ["read"];
 }
 
-
-async function artifactText(path: string, fallback: string): Promise<string> {
-  try { return await readFile(path, "utf8"); } catch { return fallback; }
-}
-
 /**
  * Resolve a low-confidence or unlisted classification. Interactive runs ask the
  * user; headless/non-interactive runs (where ctx.ui rejects) deterministically
@@ -105,6 +100,9 @@ export async function runClassifyAndAct(ctx: WorkflowRunContext<Inputs>): Promis
     output: actionPath,
     outputMode: "file-only",
   });
-  const result = await artifactText(actionPath, action.text);
+  // `file-only` already returns a compact artifact reference. Reading the file
+  // back here would defeat that and push the whole report into the caller's
+  // context; `action_path` is returned for callers that want the contents.
+  const result = action.text;
   return { result, category, confidence, action: action.stageName, classification_path: classificationPath, action_path: actionPath, artifact_dir: artifactDir };
 }

package/dist/builtin/workflows/builtin/classify-and-act.ts

@@ -1,5 +1,6 @@
 import { Type } from "typebox";
 import { workflow } from "../src/authoring/workflow.js";
+import { withSteeringPropagationContext } from "./steering-context.js";
 import { runClassifyAndAct } from "./classify-and-act-runner.js";
 
 export const DEFAULT_ACTION_CATEGORIES = ["analysis", "implementation", "research"] as const;
@@ -23,7 +24,7 @@ export default workflow({
     }),
   },
   outputs: {
-    result: Type.String({ description: "Category-specific action report." }),
+    result: Type.String({ description: "Compact reference to the category-specific action report artifact; read `action_path` for the full report." }),
     category: Type.String({ description: "Selected category, including any human fallback selection." }),
     confidence: Type.Number({ minimum: 0, maximum: 1, description: "Classifier confidence before fallback." }),
     action: Type.String({ description: "Executed category-specific action stage name." }),
@@ -31,5 +32,5 @@ export default workflow({
     action_path: Type.String({ description: "Category action report artifact path." }),
     artifact_dir: Type.String({ description: "Per-run artifact directory." }),
   },
-  run: async (ctx) => await runClassifyAndAct(ctx),
+  run: async (ctx) => await runClassifyAndAct(withSteeringPropagationContext(ctx)),
 });

package/dist/builtin/workflows/builtin/fan-out-and-synthesize-prompts.ts

@@ -1,11 +1,14 @@
+const GROUNDED_REPORTING = "Before reporting progress, audit each claim against a tool result from this session. Report only work you can point to evidence for; say so explicitly when something is unverified.";
+const READABLE_REPORT = "Lead with the outcome. Keep facts, decisions, caveats, and next steps; drop background and repetition. Use complete, readable sentences rather than compressed fragments.";
+
 export function partitionPrompt(prompt: string, maxBranches: number): string {
-  return `<role>\nYou partition work into independent evidence-producing branches.\n</role>\n\n<objective>\nPartition this task: ${prompt}\n</objective>\n\n<requirements>\nReturn between 1 and ${maxBranches} non-overlapping partitions. Split by files, sources, claims, candidates, or work items that can be evaluated independently. Give each partition a concise label and a self-contained objective. Avoid duplicate scope and identify boundaries explicitly. Return only the structured result requested by the schema.\n</requirements>`;
+  return `<role>\nYou partition work into independent evidence-producing branches.\n</role>\n\n<success_criteria>\nThe plan has between 1 and ${maxBranches} non-overlapping partitions whose labels and objectives are self-contained.\n</success_criteria>\n\n<decision_rules>\nSplit by files, sources, claims, candidates, or work items that can be evaluated independently. Avoid duplicate scope and identify boundaries explicitly. Stop when every required part of the task belongs to one partition.\n</decision_rules>\n\n<output_format>\nReturn only the structured result requested by the schema, with concise labels and self-contained objectives.\n</output_format>\n\n<objective>\nPartition this task: ${prompt}\n</objective>`;
 }
 
 export function branchPrompt(input: { readonly prompt: string; readonly label: string; readonly objective: string }): string {
-  return `<role>\nYou own one independent branch of a larger task.\n</role>\n\n<overall_task>\n${input.prompt}\n</overall_task>\n\n<branch>\n${input.label}: ${input.objective}\n</branch>\n\n<success_criteria>\nInvestigate only this branch, cite concrete files/sources/commands or other observable evidence, distinguish findings from uncertainty, and produce a standalone artifact that a synthesizer can audit.\n</success_criteria>\n\n<output_format>\nMarkdown with Scope, Findings, Evidence, Conflicts or uncertainty, and Recommendations headings.\n</output_format>`;
+  return `<overall_task>\n${input.prompt}\n</overall_task>\n\n<role>\nYou own one independent branch of a larger task. Your artifact lets a synthesizer audit this branch without its conversation context.\n</role>\n\n<success_criteria>\nCite concrete files, sources, commands, or other observable evidence, distinguish findings from uncertainty, and produce a standalone artifact.\n</success_criteria>\n\n<stop_rules>\nStop when the branch objective is supported or when unresolved uncertainty and the evidence needed to resolve it are explicit.\n</stop_rules>\n\n<output_format>\nMarkdown with Scope, Findings, Evidence, Conflicts or uncertainty, and Recommendations headings. ${READABLE_REPORT}\n${GROUNDED_REPORTING}\n</output_format>\n\n<branch>\nInvestigate only ${input.label}: ${input.objective}\n</branch>`;
 }
 
 export function synthesisPrompt(prompt: string, manifestPath: string): string {
-  return `<role>\nYou synthesize independent branch artifacts at a strict barrier.\n</role>\n\n<objective>\nProduce the final answer for: ${prompt}\n</objective>\n\n<artifact_contract>\nRead ${manifestPath} first, then read every branch artifact listed there. Do not omit a completed branch and do not assume access to branch conversations.\n</artifact_contract>\n\n<success_criteria>\nDeduplicate overlapping findings, explicitly resolve or preserve conflicting claims, retain material uncertainty, and cite branch labels and artifact paths for important conclusions. The answer must be traceable to evidence rather than majority vote.\n</success_criteria>\n\n<output_format>\nMarkdown with Executive synthesis, Consolidated findings, Conflicts and resolutions, Evidence index, and Remaining uncertainty headings.\n</output_format>`;
+  return `<artifact_contract>\nRead ${manifestPath} first, then read every branch artifact listed there. Do not omit a completed branch and do not assume access to branch conversations.\n</artifact_contract>\n\n<role>\nYou synthesize independent branch artifacts at a strict barrier. The final reader needs conclusions traceable to branch evidence rather than majority vote.\n</role>\n\n<success_criteria>\nDeduplicate overlapping findings, explicitly resolve or preserve conflicting claims, retain material uncertainty, and cite branch labels and artifact paths for important conclusions.\n</success_criteria>\n\n<stop_rules>\nStop after every completed branch is accounted for and each material conflict is resolved or preserved as uncertainty.\n</stop_rules>\n\n<output_format>\nMarkdown with Executive synthesis, Consolidated findings, Conflicts and resolutions, Evidence index, and Remaining uncertainty headings. ${READABLE_REPORT}\n${GROUNDED_REPORTING}\n</output_format>\n\n<objective>\nProduce the final answer for: ${prompt}\n</objective>`;
 }

package/dist/builtin/workflows/builtin/fan-out-and-synthesize-runner.ts

@@ -1,4 +1,4 @@
-import { readFile, writeFile } from "node:fs/promises";
+import { writeFile } from "node:fs/promises";
 import { join } from "node:path";
 import { Type } from "typebox";
 import type { WorkflowRunContext, WorkflowSerializableValue, WorkflowTaskStep } from "../src/shared/types.js";
@@ -31,9 +31,6 @@ function safeName(value: string, index: number): string {
   const normalized = value.toLowerCase().replace(/[^a-z0-9]+/g, "-").replace(/^-|-$/g, "");
   return `${String(index + 1).padStart(2, "0")}-${normalized || "branch"}`;
 }
-async function artifactText(path: string, fallback: string): Promise<string> {
-  try { return await readFile(path, "utf8"); } catch { return fallback; }
-}
 function parsedPartitions(value: WorkflowSerializableValue | undefined, limit: number, prompt: string): Partition[] {
   if (typeof value !== "object" || value === null || !("partitions" in value) || !Array.isArray(value.partitions)) {
     return [{ label: "whole-task", objective: prompt }];
@@ -86,7 +83,10 @@ export async function runFanOutAndSynthesize(ctx: WorkflowRunContext<Inputs>): P
     outputMode: "file-only",
   });
   return {
-    result: await artifactText(synthesisPath, synthesis.text),
+    // `file-only` already returns a compact artifact reference. Reading the file
+    // back here would defeat that and push the whole report into the caller's
+    // context; `synthesis_path` is returned for callers that want the contents.
+    result: synthesis.text,
     partitions: partitions.map((partition) => partition.label),
     branch_artifact_paths: branchPaths,
     synthesis_path: synthesisPath,

package/dist/builtin/workflows/builtin/fan-out-and-synthesize.ts

@@ -1,5 +1,6 @@
 import { Type } from "typebox";
 import { workflow } from "../src/authoring/workflow.js";
+import { withSteeringPropagationContext } from "./steering-context.js";
 import { runFanOutAndSynthesize } from "./fan-out-and-synthesize-runner.js";
 
 export default workflow({
@@ -21,12 +22,12 @@ export default workflow({
     }),
   },
   outputs: {
-    result: Type.String({ description: "Evidence-citing synthesized report." }),
+    result: Type.String({ description: "Compact reference to the evidence-citing synthesis artifact; read `synthesis_path` for the full report." }),
     partitions: Type.Array(Type.String(), { description: "Ordered labels for executed partitions." }),
     branch_artifact_paths: Type.Array(Type.String(), { description: "Ordered branch artifact paths consumed by synthesis." }),
     synthesis_path: Type.String({ description: "Final synthesis artifact path." }),
     artifact_dir: Type.String({ description: "Per-run artifact directory." }),
     manifest_path: Type.String({ description: "Barrier manifest linking partitions to branch artifacts." }),
   },
-  run: async (ctx) => await runFanOutAndSynthesize(ctx),
+  run: async (ctx) => await runFanOutAndSynthesize(withSteeringPropagationContext(ctx)),
 });

package/dist/builtin/workflows/builtin/generate-and-filter-prompts.ts

@@ -1,15 +1,18 @@
+const GROUNDED_REPORTING = "Before reporting progress, audit each claim against a tool result from this session. Report only work you can point to evidence for; say so explicitly when something is unverified.";
+const READABLE_REPORT = "Lead with the outcome. Keep facts, decisions, caveats, and next steps; drop background and repetition. Use complete, readable sentences rather than compressed fragments.";
+
 export function renderGeneratorPrompt(task: string, ordinal: number): string {
-  return `<role>\nYou independently generate candidate ${ordinal}; do not imitate or assume other candidates.\n</role>\n\n<objective>\n${task}\n</objective>\n\n<requirements>\nProduce one distinct, concrete candidate. Explain its value, constraints, risks, and how it can be evaluated.\n</requirements>\n\n<output_format>\nA self-contained candidate artifact with title, proposal, rationale, risks, and evaluation evidence.\n</output_format>`;
+  return `<role>\nYou independently generate candidate ${ordinal}; do not imitate or assume other candidates.\n</role>\n\n<success_criteria>\nOne distinct, concrete candidate states its value, constraints, risks, and how it can be evaluated.\n</success_criteria>\n\n<stop_rules>\nStop after one self-contained, evaluable candidate; do not add alternatives.\n</stop_rules>\n\n<output_format>\nA candidate artifact with title, proposal, criteria-based rationale, risks, and evaluation evidence. ${READABLE_REPORT}\n${GROUNDED_REPORTING}\n</output_format>\n\n<objective>\n${task}\n</objective>`;
 }
 
 export function renderFilterPrompt(task: string, candidatePaths: readonly string[], shortlistSize: number): string {
-  return `<role>\nYou deduplicate and filter independently generated candidates.\n</role>\n\n<objective>\nSelect at most ${shortlistSize} strongest candidates for: ${task}\n</objective>\n\n<artifacts>\nRead every candidate: ${candidatePaths.join(", ")}\n</artifacts>\n\n<rubric>\nFirst collapse substantively equivalent candidates. Then score fit to the task, feasibility, evidence, distinctiveness, and risk. Near-duplicates must not gain weight by repetition. Record every discarded candidate and a concrete reason.\n</rubric>\n\n<output_format>\nCall structured_output with shortlist (candidate artifact paths in ranked order) and discarded entries containing path and reason.\n</output_format>`;
+  return `<artifacts>\nRead every candidate: ${candidatePaths.join(", ")}\n</artifacts>\n\n<role>\nYou deduplicate and filter independently generated candidates.\n</role>\n\n<rubric>\nFirst collapse substantively equivalent candidates. Then score fit to the task, feasibility, evidence, distinctiveness, and risk. Near-duplicates must not gain weight by repetition. Record every discarded candidate and a concrete reason.\n</rubric>\n\n<success_criteria>\nAt most ${shortlistSize} strongest distinct candidates remain, ranked by the rubric, and every discarded candidate has a concrete reason.\n</success_criteria>\n\n<stop_rules>\nStop after every candidate is shortlisted once or recorded as discarded.\n</stop_rules>\n\n<output_format>\nCall structured_output with shortlist (candidate artifact paths in ranked order) and discarded entries containing path and a concise, criteria-based reason.\n</output_format>\n\n<objective>\nSelect at most ${shortlistSize} strongest candidates for: ${task}\n</objective>`;
 }
 
 export function renderJudgePrompt(task: string, filterPath: string, shortlistSize: number): string {
-  return `<role>\nYou independently judge the filtered shortlist against the explicit rubric.\n</role>\n\n<objective>\nReturn at most ${shortlistSize} ranked candidate paths that best satisfy: ${task}\n</objective>\n\n<artifacts>\nRead the filter report at ${filterPath} and every candidate path it references.\n</artifacts>\n\n<rubric>\nCheck task fit, feasibility, evidence, distinctiveness, and material risk. Do not restore a duplicate merely because it is phrased differently.\n</rubric>\n\n<output_format>\nCall structured_output with shortlist and rationale.\n</output_format>`;
+  return `<artifacts>\nRead the filter report at ${filterPath} and every candidate path it references.\n</artifacts>\n\n<role>\nYou independently judge the filtered shortlist against the explicit rubric.\n</role>\n\n<rubric>\nCheck task fit, feasibility, evidence, distinctiveness, and material risk. Do not restore a duplicate merely because it is phrased differently.\n</rubric>\n\n<success_criteria>\nAt most ${shortlistSize} distinct candidate paths are ranked by rubric-grounded evidence.\n</success_criteria>\n\n<stop_rules>\nStop after evaluating every filtered candidate and ranking the qualifying paths.\n</stop_rules>\n\n<output_format>\nCall structured_output with shortlist and a concise, criteria-based rationale in complete sentences.\n</output_format>\n\n<objective>\nRank the candidates that best satisfy: ${task}\n</objective>`;
 }
 
 export function renderFinalShortlistPrompt(task: string, decisionPath: string): string {
-  return `<role>\nYou present a concise, actionable final shortlist.\n</role>\n\n<objective>\nSummarize the selected candidates for: ${task}\n</objective>\n\n<artifact>\nRead the authoritative selection at ${decisionPath}; follow its order and do not add candidates.\n</artifact>\n\n<output_format>\nRanked markdown shortlist with candidate path, differentiator, evidence, tradeoffs, and recommended next evaluation.\n</output_format>`;
+  return `<artifact>\nRead the authoritative selection at ${decisionPath}; follow its order and do not add candidates.\n</artifact>\n\n<role>\nYou present a concise, actionable final shortlist so the reader can choose the next evaluation without reading the selection session.\n</role>\n\n<success_criteria>\nEvery selected candidate appears once in authoritative order with its differentiator, evidence, tradeoffs, and recommended next evaluation.\n</success_criteria>\n\n<stop_rules>\nStop after presenting every selected candidate once; do not add or reorder candidates.\n</stop_rules>\n\n<output_format>\nRanked markdown shortlist with candidate path, differentiator, evidence, tradeoffs, and recommended next evaluation. ${READABLE_REPORT}\n${GROUNDED_REPORTING}\n</output_format>\n\n<objective>\nSummarize the selected candidates for: ${task}\n</objective>`;
 }

package/dist/builtin/workflows/builtin/generate-and-filter-runner.ts

@@ -1,4 +1,4 @@
-import { readFile, writeFile } from "node:fs/promises";
+import { writeFile } from "node:fs/promises";
 import { join } from "node:path";
 import { Type, type Static } from "typebox";
 import type { WorkflowRunContext, WorkflowSerializableValue } from "../src/shared/types.js";
@@ -67,9 +67,12 @@ export async function runGenerateAndFilter(ctx: WorkflowRunContext<Inputs>): Pro
     decisionPath = judgePath;
   }
   const finalPath = join(root, "shortlist.md");
-  await ctx.task("final-shortlist", {
+  const finalShortlist = await ctx.task("final-shortlist", {
     prompt: renderFinalShortlistPrompt(ctx.inputs.prompt, decisionPath), context: "fresh",
     reads: [decisionPath, ...shortlist], output: finalPath, outputMode: "file-only",
   });
-  return { result: await readFile(finalPath, "utf8"), shortlist, candidate_artifact_paths: candidatePaths, filter_path: filterPath, judge_path: judgePath, final_path: finalPath, artifact_dir: root, manifest_path: manifestPath };
+  // `file-only` already returns a compact artifact reference. Reading the file
+  // back here would defeat that and push the whole report into the caller's
+  // context; `final_path` is returned for callers that want the contents.
+  return { result: finalShortlist.text, shortlist, candidate_artifact_paths: candidatePaths, filter_path: filterPath, judge_path: judgePath, final_path: finalPath, artifact_dir: root, manifest_path: manifestPath };
 }

package/dist/builtin/workflows/builtin/generate-and-filter.ts

@@ -1,5 +1,6 @@
 import { Type } from "typebox";
 import { workflow } from "../src/authoring/workflow.js";
+import { withSteeringPropagationContext } from "./steering-context.js";
 import { runGenerateAndFilter } from "./generate-and-filter-runner.js";
 
 export default workflow({
@@ -13,7 +14,7 @@ export default workflow({
     max_concurrency: Type.Integer({ minimum: 1, maximum: 12, default: 4, description: "Maximum simultaneous generator stages." }),
   },
   outputs: {
-    result: Type.String({ description: "Final human-readable shortlist report." }),
+    result: Type.String({ description: "Compact reference to the final shortlist report artifact; read `final_path` for the full report." }),
     shortlist: Type.Array(Type.String(), { description: "Ranked paths to selected candidate artifacts." }),
     candidate_artifact_paths: Type.Array(Type.String(), { description: "Paths to every generated candidate artifact." }),
     filter_path: Type.String({ description: "Path to the dedupe and filter decision." }),
@@ -22,5 +23,5 @@ export default workflow({
     artifact_dir: Type.String({ description: "Directory containing run artifacts." }),
     manifest_path: Type.String({ description: "Path to the candidate artifact manifest." }),
   },
-  run: runGenerateAndFilter,
+  run: async (ctx) => await runGenerateAndFilter(withSteeringPropagationContext(ctx)),
 });

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

@@ -45,7 +45,7 @@ export async function writeReviewRoundArtifact(
 ): Promise<string> {
   const artifactPath = join(artifactDir, "review-round-latest.json");
   const visibleReviews = reviews.map(withoutTurn);
-  // Deduplicated cross-reviewer findings batch so the next worker turn can
+  // Deduplicated cross-reviewer findings batch so the next orchestrator turn can
   // plan and repair the round's findings together instead of one at a time.
   const consolidatedFindings = consolidateFindingsBatch(
     reviews.map((review) => ({

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

@@ -1,66 +1,66 @@
 import { reviewDecisionSchema } from "./goal-schemas.js";
 
-// Model chains are curated from Atomic's agentic-coding benchmark; see
-// ralph-models.ts for frontier data and drop rationale.
-export const workerModelConfig = {
-    model: "openai-codex/gpt-5.6-sol:medium",
+// Keep this model list identical to Ralph's orchestrator while preserving a
+// locally contained Goal configuration.
+export const orchestratorModelConfig = {
+    model: "anthropic/claude-opus-5:high",
     fallbackModels: [
-      "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",
+      "github-copilot/claude-opus-5:high",
+      "openai-codex/gpt-5.6-sol:xhigh",
+      "github-copilot/gpt-5.6-sol:xhigh",
+      "openai/gpt-5.6-sol:xhigh",
+      "anthropic/claude-fable-5:high",
+      "github-copilot/claude-fable-5:high",
+      "kimi-coding/k3:max",
+      "moonshotai/kimi-k3:max",
+      "moonshotai-cn/kimi-k3:max",
+      "openai-codex/gpt-5.5:xhigh",
+      "github-copilot/gpt-5.5:xhigh",
+      "openai/gpt-5.5:xhigh",
+      "anthropic/claude-opus-4-8:high",
+      "github-copilot/claude-opus-4.8:high",
       "xai/grok-4.5:high",
-      "cursor/grok-4.5:high",
-      "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",
+      "zai/glm-5.2:xhigh",
+      "zai-coding-cn/glm-5.2:xhigh",
+      "openrouter/anthropic/claude-opus-5:high",
+      "openrouter/openai/gpt-5.6-sol:xhigh",
+      "openrouter/anthropic/claude-fable-5:high",
+      "openrouter/moonshotai/kimi-k3: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"],
 };
 
-// Keep this model list identical to Ralph reviewer-a while preserving an
-// independent Goal configuration and Goal's richer decision schema.
-// Reviewer-a leads its fallbacks with Kimi K3 so reviewer A and B decorrelate.
+// Keep Goal's reviewer configuration independent so GPT-5.6 precedes Kimi K3
+// within both the leading direct-provider group and the OpenRouter group.
 export const reviewerModelConfig = {
-    model: "anthropic/claude-fable-5:high",
+    model: "anthropic/claude-opus-5:high",
     fallbackModels: [
-      "kimi-coding/k3:max",
-      "moonshotai/kimi-k3:max",
-      "moonshotai-cn/kimi-k3:max",
+      "github-copilot/claude-opus-5:high",
+      "anthropic/claude-fable-5:high",
+      "github-copilot/claude-fable-5:high",
       "openai-codex/gpt-5.6-sol:xhigh",
       "github-copilot/gpt-5.6-sol:xhigh",
       "openai/gpt-5.6-sol:xhigh",
+      "kimi-coding/k3:max",
+      "moonshotai/kimi-k3:max",
+      "moonshotai-cn/kimi-k3: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:xhigh",
-      "cursor/gpt-5.5:high",
-      "cursor/claude-opus-4-8-thinking:high",
+      "github-copilot/claude-opus-4.8:high",
       "xai/grok-4.5:high",
-      "cursor/grok-4.5:high",
       "zai/glm-5.2:xhigh",
       "zai-coding-cn/glm-5.2:xhigh",
-      "cursor/glm-5.2",
+      "openrouter/anthropic/claude-opus-5:high",
       "openrouter/anthropic/claude-fable-5:high",
-      "openrouter/moonshotai/kimi-k3:max",
       "openrouter/openai/gpt-5.6-sol:xhigh",
+      "openrouter/moonshotai/kimi-k3:max",
       "openrouter/sakana/fugu-ultra:high",
       "openrouter/openai/gpt-5.5:xhigh",
       "openrouter/anthropic/claude-opus-4-8:high",

package/dist/builtin/workflows/builtin/goal-orchestrator-prompts.ts

@@ -0,0 +1,94 @@
+import type { GoalLedger } from "./goal-types.js";
+import {
+  RECEIPT_EXPECTATIONS,
+  renderGoalContinuationPrompt,
+  renderLatestReviewArtifacts,
+  renderReceiptHistory,
+  taggedPrompt,
+} from "./goal-prompts.js";
+import { WORKER_PREFLIGHT_CONTRACT } from "./shared-prompts.js";
+
+export const GOAL_ORCHESTRATOR_RECEIPT_CONTRACT = [
+  "Complete the objective before claiming readiness. Leave work only at a true blocker or impossibility; do not redefine success around a partial state.",
+  "Map every explicit requirement, artifact, command, test, gate, invariant, and deliverable to authoritative current evidence whose scope matches the claim.",
+  "Unless the objective/criteria forbid committing, have an implementation agent commit in this checkout with a descriptive message, confirm a clean tree with `git status --porcelain`, and include the commit identifier. Do not defer committing.",
+  "Return delegations, files changed, commands and outcomes, evidence, blockers, residual risks, readiness, and verification remaining.",
+].join("\n");
+
+export const GOAL_ORCHESTRATION_GUIDANCE = [
+  "You supervise implementation, investigation, edits, and validation through the `subagent` tool rather than implementing directly.",
+  "Delegate only work that is genuinely independent and too large to finish in a handful of tool calls. Do not assign subagents as a check on work you already own. Prefer one subagent over several.",
+  "Delegate implementation with its relevant objective, cwd, files, constraints, findings, and validation. Use focused locator/analyzer/pattern or shell-heavy delegation when that work meets the delegation threshold.",
+  "Keep overlapping work with one owner; parallelize only independent tasks. While an agent runs, prepare dependent follow-up work rather than duplicating its assignment.",
+  "Coordinate follow-ups for all required implementation, tests, docs, validation, and cleanup before reporting readiness.",
+].join("\n");
+
+export const GOAL_ORCHESTRATOR_BEST_PRACTICES = [
+  "The output is an orchestrator receipt produced after reading current goal/review artifacts and incorporating delegated results.",
+  "Distinguish completed, evidenced changes from recommendations and blockers. If goal context or required subagent capability is unavailable, report the blocker rather than success.",
+  "If the final paragraph would be a plan, a question, or a promise to act next, make the appropriate tool calls instead of ending the turn.",
+].join("\n");
+
+export const GOAL_SUBAGENT_TRACKING_GUIDANCE = [
+  "Use `todo` as the active delegation ledger when work is meaningfully multi-step: record owner, purpose, and expected output; mark starts, append results, and close only after incorporation or explicit rejection.",
+  "Before the receipt, resolve each pending/in_progress item as completed, blocked, or deferred with a reason so parallel work and follow-ups remain visible.",
+].join("\n");
+
+type GoalOrchestratorPromptArgs = {
+  readonly ledger: GoalLedger;
+  readonly ledgerPath: string;
+  readonly blockerThreshold: number;
+  readonly latestReviewArtifactPaths: readonly string[];
+  readonly workflowStartCwd: string;
+};
+
+export function renderGoalOrchestratorPrompt(
+  args: GoalOrchestratorPromptArgs,
+): string {
+  return [
+    renderGoalContinuationPrompt(
+      args.ledger,
+      args.ledgerPath,
+      args.blockerThreshold,
+      args.latestReviewArtifactPaths,
+    ),
+    taggedPrompt([
+      ["context", [`Current working directory: ${args.workflowStartCwd}`, "Use it for repository work and relative paths unless an explicit cwd is intentional; pass it to delegated agents."].join("\n")],
+      ["project_setup", WORKER_PREFLIGHT_CONTRACT],
+      ["orchestration_guidance", GOAL_ORCHESTRATION_GUIDANCE],
+      ["subagent_tracking", GOAL_SUBAGENT_TRACKING_GUIDANCE],
+      ["receipt_contract", [GOAL_ORCHESTRATOR_RECEIPT_CONTRACT, RECEIPT_EXPECTATIONS].join("\n")],
+      ["constraints", [
+        "Do not submit a PR; a later authorized PR/MR/review action handles that external write after approval.",
+        "For the requested change/build/fix, make in-scope local edits and non-destructive validation through subagents without asking. Confirm destructive actions, other external writes, and scope expansion first.",
+        "Preserve repository architecture and conventions unless the literal contract and repository evidence justify changing them; add no features or abstractions beyond the task.",
+      ].join("\n")],
+      ["output", "Return readable Markdown headed: Delegations performed, Progress made, Files changed, Commands run, Evidence, Blockers, Ready for review, Remaining work."],
+      ["role", "You are the sub-agent orchestrator; supervise the complete objective through the `subagent` tool rather than implementing directly."],
+      ["objective", [
+        `Read the goal ledger at ${args.ledgerPath} and latest review artifacts from the workflow read hint.`,
+        "Perform the initialization preflight, then delegate the smallest coherent work that satisfies the literal objective, acceptance criteria, current state, and consolidated findings.",
+        "Run or delegate repository-relevant validation, including end-to-end playwright-cli or tmux validation for executable user scenarios. Incorporate results and follow-ups through completion; report a true blocker and safest partial state without inventing success.",
+        GOAL_ORCHESTRATOR_BEST_PRACTICES,
+      ].join("\n")],
+    ]),
+  ].join("\n\n");
+}
+
+export function renderForkedGoalOrchestratorPrompt(
+  ledger: GoalLedger,
+  ledgerPath: string,
+  latestReviewArtifactPaths: readonly string[],
+): string {
+  return taggedPrompt([
+    ["receipts", [`Goal ledger artifact: ${ledgerPath}`, renderReceiptHistory(ledger), renderLatestReviewArtifacts(latestReviewArtifactPaths)].join("\n\n")],
+    ["orchestration_guidance", GOAL_ORCHESTRATION_GUIDANCE],
+    ["subagent_tracking", GOAL_SUBAGENT_TRACKING_GUIDANCE],
+    ["receipt_contract", [GOAL_ORCHESTRATOR_RECEIPT_CONTRACT, RECEIPT_EXPECTATIONS].join("\n")],
+    ["constraints", "The established literal contract, acceptance matrix, contract-fidelity audit, findings batch, regression evidence, closure, worktree, PR handoff, setup, E2E, and blocked-threshold rules remain in force. Do not shrink the ledger objective."],
+    ["objective", [
+      "Continue the same goal-runner orchestrator thread as supervisor, using the `subagent` tool for implementation and validation through completion.",
+      "Read the current ledger and latest artifacts, coordinate the smallest coherent remaining delegation, incorporate results, and return the established readable receipt. If the ending would only promise or plan more work, make the tool calls instead.",
+    ].join("\n")],
+  ]);
+}