@bastani/atomic 0.9.21-alpha.1 → 0.9.21

package/dist/builtin/web-access/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/web-access",
-  "version": "0.9.21-alpha.1",
+  "version": "0.9.21",
   "private": true,
   "description": "Atomic extension for web search, URL fetching, GitHub repo cloning, PDF/video extraction. Fork of: https://github.com/nicobailon/pi-web-access",
   "contributors": [

package/dist/builtin/workflows/CHANGELOG.md

@@ -6,6 +6,29 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 
 ## [Unreleased]
 
+## [0.9.21] - 2026-09-26
+
+### Changed
+
+- `model: "auto"` routing has a chat model answer fixed questions about the complete task, then the router chooses between a short, evidence-backed list of models without seeing the task, in at most two small requests. The new `modelRouting` setting's `allowedProviders` and `excludedProviders` lists limit which providers are candidates.
+- `model: "auto"` accepts `taskNeeds` so the caller can state the task's kind of work, difficulty, mistake cost, need for images, need for a very large context and whether speed matters, and `modelConstraints.allowedModels` sets the shortlist the router chooses between. `modelConstraints.allowedProviders` and `excludedProviders` skip whole providers and replace the `modelRouting` provider settings for that call. Falling back to the current chat model is silent unless `ATOMIC_MODEL_ROUTING_DEBUG=1`.
+- Workflow authoring guidance now tells agents to put a `model: "auto"` stage's role and objective at the start or end of its prompt or in a short `<keepContext>` span, since model routing sees only those parts of long prompts.
+
+### Fixed
+
+- The builtin `goal` and `ralph` workflows no longer count a reviewer's `stop_review_loop=true` as approval when the same review calls the patch incorrect, reports `goal_oracle_satisfied: false`, or lists a blocking finding. A run whose reviewers all flag an empty implementation no longer ends `complete` or starts the pull-request stage ([#3295](https://github.com/bastani-inc/atomic/issues/3295)).
+
+## [0.9.21-alpha.2] - 2026-09-26
+
+### Changed
+
+- `model: "auto"` routing has a chat model answer fixed questions about the complete task, then the router chooses between a short, evidence-backed list of models without seeing the task, in at most two small requests. The new `modelRouting` setting's `allowedProviders` and `excludedProviders` lists limit which providers are candidates.
+- `model: "auto"` accepts `taskNeeds` so the caller can state the task's kind of work, difficulty, mistake cost, need for images, need for a very large context and whether speed matters, and `modelConstraints.allowedModels` sets the shortlist the router chooses between. `modelConstraints.allowedProviders` and `excludedProviders` skip whole providers and replace the `modelRouting` provider settings for that call. Falling back to the current chat model is silent unless `ATOMIC_MODEL_ROUTING_DEBUG=1`.
+
+### Fixed
+
+- The builtin `goal` and `ralph` workflows no longer count a reviewer's `stop_review_loop=true` as approval when the same review calls the patch incorrect, reports `goal_oracle_satisfied: false`, or lists a blocking finding. A run whose reviewers all flag an empty implementation no longer ends `complete` or starts the pull-request stage ([#3295](https://github.com/bastani-inc/atomic/issues/3295)).
+
 ## [0.9.21-alpha.1] - 2026-09-25
 
 ### Changed

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

@@ -1,10 +1,10 @@
 import {
   adversarial_verification_default
-} from "./chunk-jaj27rqc.js";
+} from "./chunk-a1ar035d.js";
 import"./chunk-2377r57g.js";
 import"./chunk-n1910xc4.js";
-import"./chunk-crw7q5g1.js";
-import"./chunk-kspvwc24.js";
+import"./chunk-gyjck9z8.js";
+import"./chunk-9cm2ckq2.js";
 export {
   adversarial_verification_default as default
 };

package/dist/builtin/workflows/builtin/{chunk-cw86srkf.js → chunk-632fxeb8.js}

@@ -1,7 +1,7 @@
 import {
   workflow,
   withBuiltinContext
-} from "./chunk-crw7q5g1.js";
+} from "./chunk-gyjck9z8.js";
 import {
   stableArtifactRoot
 } from "./chunk-rc5ec5xx.js";

package/dist/builtin/workflows/builtin/{chunk-w18kbz63.js → chunk-94f8zfz1.js}

@@ -1,7 +1,7 @@
 import {
   workflow,
   withBuiltinContext
-} from "./chunk-crw7q5g1.js";
+} from "./chunk-gyjck9z8.js";
 import {
   score_progress,
   classify_trend

package/dist/builtin/workflows/builtin/{chunk-kspvwc24.js → chunk-9cm2ckq2.js}

@@ -178,7 +178,7 @@ var SCOPE_DISCIPLINE_CONTRACT = keepContext([
 `));
 var EVIDENCE_CLOSURE_POLICY = [
   "Convergence flag (stop_review_loop):",
-  "- stop_review_loop is the single authoritative convergence signal; the harness trusts it without recomputing approval from findings, priorities, or requirements_traceability.",
+  "- stop_review_loop is the convergence signal. The harness does not recompute approval from requirements_traceability, but it does not count stop_review_loop=true as approval when the same review says the patch is incorrect, reports goal_oracle_satisfied=false, or lists a blocking finding.",
   "- Derive stop_review_loop=false while any objective-relevant blocking work remains: a P0/P1/P2 finding, a required_by_objective finding at any priority including P3, or an unproven implementation/validation requirement.",
   "- Derive stop_review_loop=true when independent verification proves implementation and validation and only non-blocking items remain: consistent_with_objective P3 items, beyond_objective/contradicts_objective observations, an authorized post-approval PR/MR/review action, or reviewer quorum. Never hold it false for those items.",
   "- If the bounded loop ends first, preserve unresolved findings and remaining work for a human rather than relabeling them."

package/dist/builtin/workflows/builtin/{chunk-jaj27rqc.js → chunk-a1ar035d.js}

@@ -1,7 +1,7 @@
 import {
   workflow,
   withBuiltinContext
-} from "./chunk-crw7q5g1.js";
+} from "./chunk-gyjck9z8.js";
 import {
   parse_rubric,
   normalize_criteria,

package/dist/builtin/workflows/builtin/{chunk-wh19f5ee.js → chunk-d3xhj946.js}

@@ -1,7 +1,7 @@
 import {
   workflow,
   withBuiltinContext
-} from "./chunk-crw7q5g1.js";
+} from "./chunk-gyjck9z8.js";
 import {
   keepContext,
   REVIEWER_CALIBRATION_RULES,
@@ -24,7 +24,7 @@ import {
   EVIDENCE_CLOSURE_POLICY,
   WORKTREE_DISCIPLINE_CONTRACT,
   REVIEW_CODE_DELTA_CONTRACT
-} from "./chunk-kspvwc24.js";
+} from "./chunk-9cm2ckq2.js";
 import {
   VERIFICATION_SCALE
 } from "./chunk-n1910xc4.js";
@@ -33,12 +33,13 @@ import {
   record_convergence,
   convergence_escalation_evidence,
   finalActionRemaining,
+  stopReviewLoopContradictions,
   consolidateFindingsBatch,
   parseFailureDiagnostics,
   reviewerFailureText,
   summarizeReviewConvergence,
   reverify_consolidated_batch
-} from "./chunk-73c5tayt.js";
+} from "./chunk-kgn5wz1c.js";
 import {
   fold_usage
 } from "./chunk-tgt0s5e5.js";
@@ -52,7 +53,7 @@ import { dirname, join } from "node:path";
 import { Type } from "typebox";
 // dist/builtin/workflows/builtin/ralph-review-gate.ts
 function reviewDecisionApproved(decision) {
-  return decision.stop_review_loop === true && decision.reviewer_error == null;
+  return decision.stop_review_loop === true && decision.reviewer_error == null && stopReviewLoopContradictions(decision).length === 0;
 }
 
 // dist/builtin/workflows/builtin/ralph-core.ts

package/dist/builtin/workflows/builtin/{chunk-crw7q5g1.js → chunk-gyjck9z8.js}

@@ -1,6 +1,6 @@
 import {
   withSteeringPropagationContext2
-} from "./chunk-kspvwc24.js";
+} from "./chunk-9cm2ckq2.js";
 
 // dist/builtin/workflows/src/authoring/workflow.ts
 import { basename } from "node:path";

package/dist/builtin/workflows/builtin/{chunk-maqv731g.js → chunk-hj8mh07f.js}

@@ -1,7 +1,7 @@
 import {
   workflow,
   withBuiltinContext
-} from "./chunk-crw7q5g1.js";
+} from "./chunk-gyjck9z8.js";
 import {
   keepContext,
   REVIEWER_CALIBRATION_RULES,
@@ -24,19 +24,21 @@ import {
   EVIDENCE_CLOSURE_POLICY,
   WORKTREE_DISCIPLINE_CONTRACT,
   REVIEW_CODE_DELTA_CONTRACT
-} from "./chunk-kspvwc24.js";
+} from "./chunk-9cm2ckq2.js";
 import {
   workflowArtifactDirectoryPath,
   ensureWorkflowArtifactDirectory,
   record_convergence,
   convergence_escalation_evidence,
   finalActionRemaining,
+  stopReviewLoopContradictions,
+  contradictedStopReviewLoopGap,
   consolidateFindingsBatch,
   parseFailureDiagnostics,
   reviewerFailureText,
   summarizeReviewConvergence,
   reverify_consolidated_batch
-} from "./chunk-73c5tayt.js";
+} from "./chunk-kgn5wz1c.js";
 import {
   VERIFICATION_SCALE
 } from "./chunk-n1910xc4.js";
@@ -321,7 +323,7 @@ function reduceGoalDecision(ledger, turnReviews, options) {
         ...summary,
         turn: options.turn,
         decision: "complete",
-        reason: `Reviewer quorum met: ${completeVotes}/${options.reviewQuorum} reviewers independently reported stop_review_loop=true with no reviewer execution errors.`,
+        reason: `Reviewer quorum met: ${completeVotes}/${options.reviewQuorum} reviewers independently reported stop_review_loop=true with a correct patch, a satisfied goal oracle, no blocking findings, and no reviewer execution errors.`,
         complete_votes: completeVotes,
         review_quorum: options.reviewQuorum
       }
@@ -459,7 +461,7 @@ function parsedReviewDecisionFromResult(result, reviewer) {
   };
 }
 function reviewApproved(decision) {
-  return decision.stop_review_loop === true && decision.reviewer_error == null;
+  return decision.stop_review_loop === true && decision.reviewer_error == null && stopReviewLoopContradictions(decision).length === 0;
 }
 function reviewerErrorDecision(message) {
   return {
@@ -492,6 +494,7 @@ function blockerFromReviewDecision(decision) {
 function reviewDecisionToRecord(args) {
   const blocker = blockerFromReviewDecision(args.decision);
   const approved = reviewApproved(args.decision);
+  const contradictions = args.decision.stop_review_loop === true ? stopReviewLoopContradictions(args.decision) : [];
   const hasFinalActionRemaining = args.allowFinalActionRemaining && finalActionRemaining(args.decision.requirements_traceability);
   const verificationGap = args.decision.verification_remaining.trim();
   const traceabilityGaps = args.decision.requirements_traceability.filter((entry) => entry.status !== "proven").map((entry) => `${entry.status}: ${entry.requirement} — ${entry.evidence}`);
@@ -499,7 +502,8 @@ function reviewDecisionToRecord(args) {
     ...args.decision.findings.map((finding) => `[${finding.objective_alignment}] ${finding.title}: ${finding.body}`),
     ...traceabilityGaps,
     ...approved || verificationGap.length === 0 ? [] : [verificationGap],
-    ...args.decision.reviewer_error == null ? [] : [`${args.decision.reviewer_error.kind}: ${args.decision.reviewer_error.message}`]
+    ...args.decision.reviewer_error == null ? [] : [`${args.decision.reviewer_error.kind}: ${args.decision.reviewer_error.message}`],
+    ...contradictions.length === 0 ? [] : [contradictedStopReviewLoopGap(contradictions)]
   ];
   const nextAction = approved ? hasFinalActionRemaining ? "pull-request" : "finish" : blocker === null ? "implementation" : "blocked";
   const convergenceDecision = summarizeReviewConvergence({

package/dist/builtin/workflows/builtin/{chunk-0nrgfbag.js → chunk-kb7s3gx2.js}

@@ -1,7 +1,7 @@
 import {
   workflow,
   withBuiltinContext
-} from "./chunk-crw7q5g1.js";
+} from "./chunk-gyjck9z8.js";
 import {
   scoring_prompt_reads,
   build_scoring_prompt

package/dist/builtin/workflows/builtin/{chunk-73c5tayt.js → chunk-kgn5wz1c.js}

@@ -10476,6 +10476,24 @@ function findingBlocksClosure(finding) {
     return true;
   return priority <= MAX_BLOCKING_PRIORITY;
 }
+function stopReviewLoopContradictions(verdict) {
+  const contradictions = [];
+  if (verdict.overall_correctness !== "patch is correct") {
+    contradictions.push(`overall_correctness is "${verdict.overall_correctness}"`);
+  }
+  if (verdict.goal_oracle_satisfied === false) {
+    contradictions.push("goal_oracle_satisfied is false");
+  }
+  for (const finding of verdict.findings) {
+    if (findingBlocksClosure(finding)) {
+      contradictions.push(`blocking finding "${finding.title}"`);
+    }
+  }
+  return contradictions;
+}
+function contradictedStopReviewLoopGap(contradictions) {
+  return `stop_review_loop=true was not counted as approval because the same review reports ${contradictions.join("; ")}`;
+}
 function findingConsolidationKey(finding) {
   const normalizedTitle = finding.title.replace(/^\s*\[P[0-3]\]\s*/iu, "").toLowerCase().replace(/\s+/gu, " ").trim();
   return `${finding.code_location?.absolute_file_path ?? ""}::${normalizedTitle}`;
@@ -10696,4 +10714,4 @@ async function reverify_consolidated_batch(ctx, input) {
   return apply_reverify_results(input.batch, audits);
 }
 
-export { workflowArtifactDirectoryPath, ensureWorkflowArtifactDirectory, createWorkflowArtifactDirectory, record_convergence, convergence_escalation_evidence, finalActionRemaining, consolidateFindingsBatch, parseFailureDiagnostics, reviewerFailureText, summarizeReviewConvergence, reverify_consolidated_batch };
+export { workflowArtifactDirectoryPath, ensureWorkflowArtifactDirectory, createWorkflowArtifactDirectory, record_convergence, convergence_escalation_evidence, finalActionRemaining, stopReviewLoopContradictions, contradictedStopReviewLoopGap, consolidateFindingsBatch, parseFailureDiagnostics, reviewerFailureText, summarizeReviewConvergence, reverify_consolidated_batch };

package/dist/builtin/workflows/builtin/{chunk-2hak3b7g.js → chunk-nkj4qhj6.js}

@@ -1,7 +1,7 @@
 import {
   workflow,
   withBuiltinContext
-} from "./chunk-crw7q5g1.js";
+} from "./chunk-gyjck9z8.js";
 
 // dist/builtin/workflows/builtin/open-claude-design.ts
 import { Type as Type2 } from "typebox";

package/dist/builtin/workflows/builtin/{chunk-bzdvx2xr.js → chunk-r97ndfvt.js}

@@ -1,7 +1,7 @@
 import {
   workflow,
   withBuiltinContext
-} from "./chunk-crw7q5g1.js";
+} from "./chunk-gyjck9z8.js";
 import {
   stableArtifactRoot
 } from "./chunk-rc5ec5xx.js";

package/dist/builtin/workflows/builtin/{chunk-vkmpdat4.js → chunk-wf876n16.js}

@@ -1,7 +1,7 @@
 import {
   workflow,
   withBuiltinContext
-} from "./chunk-crw7q5g1.js";
+} from "./chunk-gyjck9z8.js";
 import {
   parse_rubric,
   normalize_criteria,

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

@@ -1,9 +1,9 @@
 import {
   DEFAULT_ACTION_CATEGORIES2,
   classify_and_act_default
-} from "./chunk-bzdvx2xr.js";
-import"./chunk-crw7q5g1.js";
-import"./chunk-kspvwc24.js";
+} from "./chunk-r97ndfvt.js";
+import"./chunk-gyjck9z8.js";
+import"./chunk-9cm2ckq2.js";
 export {
   DEFAULT_ACTION_CATEGORIES2 as DEFAULT_ACTION_CATEGORIES,
   classify_and_act_default as default

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

@@ -1,8 +1,8 @@
 import {
   fan_out_and_synthesize_default
-} from "./chunk-cw86srkf.js";
-import"./chunk-crw7q5g1.js";
-import"./chunk-kspvwc24.js";
+} from "./chunk-632fxeb8.js";
+import"./chunk-gyjck9z8.js";
+import"./chunk-9cm2ckq2.js";
 export {
   fan_out_and_synthesize_default as default
 };

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

@@ -1,10 +1,10 @@
 import {
   generate_and_filter_default
-} from "./chunk-0nrgfbag.js";
+} from "./chunk-kb7s3gx2.js";
 import"./chunk-2377r57g.js";
 import"./chunk-n1910xc4.js";
-import"./chunk-crw7q5g1.js";
-import"./chunk-kspvwc24.js";
+import"./chunk-gyjck9z8.js";
+import"./chunk-9cm2ckq2.js";
 export {
   generate_and_filter_default as default
 };

package/dist/builtin/workflows/builtin/goal.js

@@ -1,12 +1,12 @@
 import {
   goal_default
-} from "./chunk-maqv731g.js";
-import"./chunk-73c5tayt.js";
+} from "./chunk-hj8mh07f.js";
+import"./chunk-kgn5wz1c.js";
 import"./chunk-2377r57g.js";
 import"./chunk-z0d03ktm.js";
 import"./chunk-n1910xc4.js";
-import"./chunk-crw7q5g1.js";
-import"./chunk-kspvwc24.js";
+import"./chunk-gyjck9z8.js";
+import"./chunk-9cm2ckq2.js";
 export {
   goal_default as default
 };

package/dist/builtin/workflows/builtin/index.js

@@ -1,36 +1,36 @@
-import"./chunk-crw7q5g1.js";
-import"./chunk-kspvwc24.js";
+import"./chunk-gyjck9z8.js";
+import"./chunk-9cm2ckq2.js";
 import"./chunk-n1910xc4.js";
 import"./chunk-2377r57g.js";
 import {
   adversarial_verification_default
-} from "./chunk-jaj27rqc.js";
+} from "./chunk-a1ar035d.js";
 import {
   classify_and_act_default
-} from "./chunk-bzdvx2xr.js";
+} from "./chunk-r97ndfvt.js";
 import {
   fan_out_and_synthesize_default
-} from "./chunk-cw86srkf.js";
+} from "./chunk-632fxeb8.js";
 import {
   generate_and_filter_default
-} from "./chunk-0nrgfbag.js";
-import"./chunk-73c5tayt.js";
+} from "./chunk-kb7s3gx2.js";
+import"./chunk-kgn5wz1c.js";
 import"./chunk-z0d03ktm.js";
 import {
   goal_default
-} from "./chunk-maqv731g.js";
+} from "./chunk-hj8mh07f.js";
 import {
   open_claude_design_default
-} from "./chunk-2hak3b7g.js";
+} from "./chunk-nkj4qhj6.js";
 import {
   loop_until_done_default
-} from "./chunk-w18kbz63.js";
+} from "./chunk-94f8zfz1.js";
 import {
   ralph_default
-} from "./chunk-wh19f5ee.js";
+} from "./chunk-d3xhj946.js";
 import {
   tournament_default
-} from "./chunk-vkmpdat4.js";
+} from "./chunk-wf876n16.js";
 export {
   adversarial_verification_default as adversarialVerification,
   classify_and_act_default as classifyAndAct,

package/dist/builtin/workflows/builtin/loop-until-done.js

@@ -1,10 +1,10 @@
 import {
   loop_until_done_default
-} from "./chunk-w18kbz63.js";
+} from "./chunk-94f8zfz1.js";
 import"./chunk-z0d03ktm.js";
 import"./chunk-n1910xc4.js";
-import"./chunk-crw7q5g1.js";
-import"./chunk-kspvwc24.js";
+import"./chunk-gyjck9z8.js";
+import"./chunk-9cm2ckq2.js";
 export {
   loop_until_done_default as default
 };

package/dist/builtin/workflows/builtin/open-claude-design.js

@@ -1,8 +1,8 @@
 import {
   open_claude_design_default
-} from "./chunk-2hak3b7g.js";
-import"./chunk-crw7q5g1.js";
-import"./chunk-kspvwc24.js";
+} from "./chunk-nkj4qhj6.js";
+import"./chunk-gyjck9z8.js";
+import"./chunk-9cm2ckq2.js";
 export {
   open_claude_design_default as default
 };

package/dist/builtin/workflows/builtin/ralph.js

@@ -1,12 +1,12 @@
 import {
   ralph_default
-} from "./chunk-wh19f5ee.js";
-import"./chunk-73c5tayt.js";
+} from "./chunk-d3xhj946.js";
+import"./chunk-kgn5wz1c.js";
 import"./chunk-2377r57g.js";
 import"./chunk-z0d03ktm.js";
 import"./chunk-n1910xc4.js";
-import"./chunk-crw7q5g1.js";
-import"./chunk-kspvwc24.js";
+import"./chunk-gyjck9z8.js";
+import"./chunk-9cm2ckq2.js";
 export {
   ralph_default as default
 };

package/dist/builtin/workflows/builtin/steering-context.js

@@ -1,6 +1,6 @@
 import {
   withSteeringPropagationContext2
-} from "./chunk-kspvwc24.js";
+} from "./chunk-9cm2ckq2.js";
 export {
   withSteeringPropagationContext2 as withSteeringPropagationContext
 };

package/dist/builtin/workflows/builtin/tournament.js

@@ -1,10 +1,10 @@
 import {
   tournament_default
-} from "./chunk-vkmpdat4.js";
+} from "./chunk-wf876n16.js";
 import"./chunk-2377r57g.js";
 import"./chunk-n1910xc4.js";
-import"./chunk-crw7q5g1.js";
-import"./chunk-kspvwc24.js";
+import"./chunk-gyjck9z8.js";
+import"./chunk-9cm2ckq2.js";
 export {
   tournament_default as default
 };

package/dist/builtin/workflows/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bastani/workflows",
-  "version": "0.9.21-alpha.1",
+  "version": "0.9.21",
   "private": true,
   "description": "Atomic extension for multi-stage workflow authoring and execution.",
   "contributors": [