sortie-dogs 0.13.0 → 0.13.1

package/README.md

@@ -1,5 +1,9 @@
 # Sortie-dogs
 
+<p align="center">
+  <img src="docs/assets/sortie-dogs-logo.png" alt="Sortie-dogs logo" width="640">
+</p>
+
 **A goal-preserving, adaptive execution harness for OpenCode that optimizes cost,
 time, and proof without taking your setup over.**
 
@@ -28,6 +32,14 @@ implementation, validation, review, and model routing.
 Guides: [日本語](docs/guide-ja.md) · [简体中文](docs/guide-zh-CN.md) ·
 [Testing](docs/testing.md) · [CLI testing](docs/cli-testing.md)
 
+## SWE-bench Lite: 170/300 (56.67%)
+
+The fixed **Sortie-dogs v0.12.24** harness resolved **170 of 300 SWE-bench Lite test issues** in one pass@1 campaign, with 9 empty patches and no official evaluation errors. Every instance has a frozen prediction and an inference-time trajectory. The task Workers ran `openai/gpt-6-luna-fast#max`; operator, coordinator and review roles ran `openai/gpt-6-sol#xhigh`. This is a system result, **not** a Luna-only model comparison or a Verified/full SWE-bench score.
+
+[Technical report and per-repository results](docs/benchmarks/swebench-lite-v01224-test300-2026-09-29.md) · [Public predictions, logs and trajectories](https://github.com/zufall-upon/sortie-dogs-swebench-lite-20260929)
+
+The single official 300-instance report and frozen predictions are hash-bound in the report. Confirmed inference expense was **$162.99**; a separate **$34.60** of usage has unknown pricing and is held against the campaign cap, **not** counted as known expense. Leaderboard registration and maintainer acceptance are separate from this official local evaluation.
+
 > **Beta:** v0.12.2 builds on the v0.10.23 execution engine. Runtime behavior,
 > configuration, and generated assets may still change before 1.0.
 
@@ -202,7 +214,7 @@ not invent, probe, or translate variant names.
 - `freeTierFallbackModels`: ordered global last-resort model IDs. Default:
   `opencode/deepseek-v4-flash-free`; `[]` disables this fallback.
 - `dedicatedWorkerModel`: canonical stable serial target, default
-  `openai/gpt-6-sol` / `medium`. The v0.10 profile also supplies its explicit
+  `openai/gpt-6.1-sol` / `medium`. The v0.10 profile also supplies its explicit
   role routes below; do not infer the v0.10 worker route from this stable setting.
 - `consultation.strategy`: fixed advisor identity, optional `required`, and
   positive `maxCallsPerCandidate`; default one call and not required.
@@ -239,14 +251,14 @@ or explicit risk. Workers own static, targeted, and related checks; the root own
 canonical and full-suite checks. An unchanged candidate, command, and environment
 reuse the same evidence instead of spending the validation budget again.
 
-### Default v0.12 routes
+### Default routes
 
-- `dog-operator`: `openai/gpt-6-sol` / `xhigh`
-- `dogs-coordinator`: `openai/gpt-6-sol` / `xhigh`
+- `dog-operator`: `openai/gpt-6.1-sol` / `xhigh`
+- `dogs-coordinator`: `openai/gpt-6.1-sol` / `xhigh`
 - `dog-worker-v010`: `openai/gpt-6-luna-fast` / `max`
 - `dog-scout-v010`: `openai/gpt-6-luna-fast` / `max`
-- `dog-reviewer-v010`: `openai/gpt-6-sol` / `xhigh`
-- `dog-advisor-v010`: `openai/gpt-6-sol` / `xhigh`
+- `dog-reviewer-v010`: `openai/gpt-6.1-sol` / `xhigh`
+- `dog-advisor-v010`: `openai/gpt-6.1-sol` / `xhigh`
 
 An explicit model and variant selected in OpenCode remains authoritative for that
 session. Child role defaults fill absent native settings and may be overridden by

package/dist/asset-version.d.ts

@@ -3,5 +3,5 @@
  * installed project marker without importing every asset body.
  */
 export declare const RUNTIME_ASSET_VERSION = "0.3.89-completion-proof-v1";
-export declare const V010_RUNTIME_ASSET_VERSION = "0.13.0-fast-first-v1";
+export declare const V010_RUNTIME_ASSET_VERSION = "0.13.1-quality-first-review-v1";
 export type RuntimeAssetVersion = typeof RUNTIME_ASSET_VERSION | typeof V010_RUNTIME_ASSET_VERSION;

package/dist/asset-version.js

@@ -3,4 +3,4 @@
  * installed project marker without importing every asset body.
  */
 export const RUNTIME_ASSET_VERSION = "0.3.89-completion-proof-v1";
-export const V010_RUNTIME_ASSET_VERSION = "0.13.0-fast-first-v1";
+export const V010_RUNTIME_ASSET_VERSION = "0.13.1-quality-first-review-v1";

package/dist/core/initialize.d.ts

@@ -11,7 +11,7 @@ export declare class ProjectInitializationError extends Error {
     readonly code: ProjectInitializationErrorCode;
     constructor(code: ProjectInitializationErrorCode, message: string, options?: ErrorOptions);
 }
-export declare const V010_COORDINATOR_MODEL = "openai/gpt-6-sol#xhigh";
+export declare const V010_COORDINATOR_MODEL = "openai/gpt-6.1-sol#xhigh";
 /**
  * Report a user config that routes the v0.10 Coordinator away from its packaged model. Measured Luna
  * Coordinators repeated plans and review dispatches until timeout, so init surfaces it without editing it.

package/dist/core/initialize.js

@@ -542,7 +542,7 @@ async function initializeRoot(requestedRoot, layout, installAssets = runtimeAsse
         preservedLegacyPaths,
     };
 }
-export const V010_COORDINATOR_MODEL = "openai/gpt-6-sol#xhigh";
+export const V010_COORDINATOR_MODEL = "openai/gpt-6.1-sol#xhigh";
 /**
  * Report a user config that routes the v0.10 Coordinator away from its packaged model. Measured Luna
  * Coordinators repeated plans and review dispatches until timeout, so init surfaces it without editing it.

package/dist/core/operator-mission.d.ts

@@ -80,7 +80,8 @@ export interface MissionExecution {
         startedAt: string;
         completedAt?: string;
         exit?: number;
-        status?: "completed" | "error";
+        status?: "running" | "completed" | "error";
+        shellID?: string;
         outcome?: "not-started" | "execution-failed" | "executed";
         result?: Record<string, unknown>;
     }[];
@@ -141,15 +142,10 @@ export interface OperatorMission {
         child?: string;
         /** Completed, independent initial review for this mission, not merely an inherited child ID. */
         initialPrompt?: string;
-        /** Reviews on this mission that found only missing evidence; bounded by MISSION_EVIDENCE_GAP_REVIEW_LIMIT. */
+        /** Observed evidence-only reviews; reporting only, never an acceptance threshold. */
         evidenceGapReviews?: number;
     };
 }
-/**
- * Evidence-only findings do not establish a defect. Each extra round costs a full Reviewer pass and often a
- * Worker unit, so after this many evidence-only reviews the candidate may be submitted with the gaps listed.
- */
-export declare const MISSION_EVIDENCE_GAP_REVIEW_LIMIT = 2;
 export declare const MISSION_CONSULTATION_LIMIT = 32;
 /** Review coverage survives a narrower replan; it is not a Worker write grant. */
 export declare function missionReviewScope(previous: MissionReviewScope | undefined, ...runs: OperatorState[]): MissionReviewScope;
@@ -217,5 +213,5 @@ export declare function missionPlan(mission: OperatorMission, raw: unknown): Ope
 export declare function missionPacket(mission: OperatorMission, run?: OperatorState): Record<string, unknown>;
 /** Models forward a short capability, never recopy the host's evidence hashes and source packet. */
 export declare function missionReviewTask(mission: OperatorMission): OperatorTask;
-/** Project grouped R-ID traces, including consecutive ranges, into the existing per-criterion mapping. */
-export declare function missionReviewTraces(mission: OperatorMission, raw: unknown): string[];
+/** Optional implementation notes supplement host-observed source/checks; prose is not a coverage gate. */
+export declare function missionReviewTraces(_mission: OperatorMission, raw: unknown): string[];

package/dist/core/operator-mission.js

@@ -18,11 +18,6 @@ export function missionValidationCommand(command) {
     const expression = `exec(${JSON.stringify(heredoc[4])})`;
     return `${heredoc[1]} -c '${expression.replaceAll("'", "'\\''")}'`;
 }
-/**
- * Evidence-only findings do not establish a defect. Each extra round costs a full Reviewer pass and often a
- * Worker unit, so after this many evidence-only reviews the candidate may be submitted with the gaps listed.
- */
-export const MISSION_EVIDENCE_GAP_REVIEW_LIMIT = 2;
 export const MISSION_CONSULTATION_LIMIT = 32;
 /** Review coverage survives a narrower replan; it is not a Worker write grant. */
 export function missionReviewScope(previous, ...runs) {
@@ -38,7 +33,7 @@ export function missionReviewVerdict(text) {
 /** Whether the recorded review permits submission and acceptance of the current candidate. */
 export function missionReviewAccepted(review) {
     return review.verdict === "PASS" || review.verdict === "skipped-low-risk" ||
-        (review.verdict === "evidence-gaps" && (review.evidenceGapReviews ?? 0) >= MISSION_EVIDENCE_GAP_REVIEW_LIMIT);
+        review.verdict === "evidence-gaps";
 }
 export function missionExecutionStatus(mission) {
     if (mission.kind !== "operation")
@@ -469,7 +464,7 @@ export function missionPacket(mission, run) {
             run_id: mission.review.runID, current_run: currentReview,
             source_fingerprint: mission.review.source, reviewer_session_id: mission.review.child ?? null,
             result: mission.review.result ?? null, evidence_gap_reviews: mission.review.evidenceGapReviews ?? 0,
-            evidence_gap_review_limit: MISSION_EVIDENCE_GAP_REVIEW_LIMIT, accepted: reviewAccepted,
+            evidence_gaps_advisory: true, accepted: reviewAccepted,
             passed: currentReview && mission.review.verdict === "PASS", permits_submission: reviewAccepted && operationComplete } : null,
         ...(run ? { run_id: run.runID, status: run.phase, decision: run.decision,
             units: run.units.map(unit => ({ id: unit.unit.id, title: unit.unit.title, status: unit.status,
@@ -482,21 +477,21 @@ export function missionPacket(mission, run) {
         next_action: mission.phase === "completed" ? "Mission completed. Report the accepted result and retained review gaps; no further dispatch or completion call is needed."
             : mission.phase === "submitted" && mission.submission?.status === "ready"
                 ? "Operator: compare the submitted candidate with the original requirements and actual evidence, then complete_mission if satisfied. Report remaining evidence gaps; they are not a review PASS."
-                : run?.phase === "awaiting-decision" ? (run.units.some(unit => unit.dispatchDenial)
-                    ? "Coordinator: inspect units[].dispatch_denial before changing the plan. Correct only its diagnosed cause; do not repeat an unchanged refused Task or replan for a host-state mismatch. Report an unresolved runtime mismatch with the loaded runtime identity; preserve requirements and cumulative spend."
-                    : run.units.some(unit => unit.status === "failed" && unit.resultClass === "acceptance" && unit.failure?.outcome === "fail" && !unit.normalRemediationUsed)
-                        ? "Coordinator: one exact declared validation failed. Reconcile the returned Worker and cumulative budget, then call retry_mission_unit once for that unit before replanning. This preserves the same scope and acceptance."
-                        : run.units.some(unit => unit.status === "failed" && unit.resultClass === "acceptance" && unit.failure?.outcome === "fail" && unit.normalRemediationUsed && !unit.terminalRescue)
-                            ? "Coordinator: the one ordinary remediation failed the declared validation again. If its native terminal, writer release, exact candidate and cumulative budget permit, call rescue_mission_unit once; inspect and report a non_rescue reason, then continue ordinary correction within budget. Rescue does not bypass validation, review or root acceptance."
-                            : "Coordinator: correct the cause and call plan_units with the remaining work and all requirements; budget is cumulative.")
-                    : run?.phase === "awaiting-acceptance" && !operationComplete
-                        ? `Requested operation is ${operationStatus}. Continue the actual operation or report its blocker; auxiliary checks and review disposition cannot complete it.`
-                        : run?.phase === "awaiting-acceptance" ? (currentReview && mission.review?.verdict === "evidence-gaps" && !reviewAccepted
-                            ? "Coordinator: the Reviewer found only missing evidence. Supply focused original-file excerpts through review_mission evidence and traces; do not re-implement. At the evidence-gap limit, review ends with the gaps listed, not with execution proof."
-                            : reviewAccepted
-                                ? "Coordinator: review permits submission. Submit the candidate with any remaining gaps; do not repeat passed validation or review. Operator performs final acceptance."
+                : mission.kind === "operation" && operationStatus === "running"
+                    ? "The declared operation is already running. Inspect its native shell/progress; do not start another Worker or run. Wait for a terminal result, or report the existing run as blocked if its completion cannot be observed."
+                    : run?.phase === "awaiting-decision" ? (run.units.some(unit => unit.dispatchDenial)
+                        ? "Coordinator: inspect units[].dispatch_denial before changing the plan. Correct only its diagnosed cause; do not repeat an unchanged refused Task or replan for a host-state mismatch. Report an unresolved runtime mismatch with the loaded runtime identity; preserve requirements and cumulative spend."
+                        : run.units.some(unit => unit.status === "failed" && unit.resultClass === "acceptance" && unit.failure?.outcome === "fail" && !unit.normalRemediationUsed)
+                            ? "Coordinator: one exact declared validation failed. Reconcile the returned Worker and cumulative budget, then call retry_mission_unit once for that unit before replanning. This preserves the same scope and acceptance."
+                            : run.units.some(unit => unit.status === "failed" && unit.resultClass === "acceptance" && unit.failure?.outcome === "fail" && unit.normalRemediationUsed && !unit.terminalRescue)
+                                ? "Coordinator: the one ordinary remediation failed the declared validation again. If its native terminal, writer release, exact candidate and cumulative budget permit, call rescue_mission_unit once; inspect and report a non_rescue reason, then continue ordinary correction within budget. Rescue does not bypass validation, review or root acceptance."
+                                : "Coordinator: correct the cause and call plan_units with the remaining work and all requirements; budget is cumulative.")
+                        : run?.phase === "awaiting-acceptance" && !operationComplete
+                            ? `Requested operation is ${operationStatus}. Continue the actual operation or report its blocker; auxiliary checks and review disposition cannot complete it.`
+                            : run?.phase === "awaiting-acceptance" ? (reviewAccepted
+                                ? "Coordinator: review permits submission. Retain advisory review notes; do not repeat passed validation or review for evidence formatting. Operator performs final acceptance against the original requirements."
                                 : "Coordinator: address recorded findings or obtain the required independent review, then submit_mission. Operator compares all requirements with source/evidence before complete_mission.")
-                            : "Coordinator: continue the next useful unit within original requirements. Return only a completion candidate, user-only decision, or scope/budget extension." };
+                                : "Coordinator: continue the next useful unit within original requirements. Return only a completion candidate, user-only decision, or scope/budget extension." };
 }
 /** Models forward a short capability, never recopy the host's evidence hashes and source packet. */
 export function missionReviewTask(mission) {
@@ -506,35 +501,12 @@ export function missionReviewTask(mission) {
     return { ...review.task, prompt: `${MISSION_REVIEW_REFERENCE}${JSON.stringify({ r: mission.root,
             m: mission.id, n: review.runID, h: digest(review.task.prompt) })}` };
 }
-/** Project grouped R-ID traces, including consecutive ranges, into the existing per-criterion mapping. */
-export function missionReviewTraces(mission, raw) {
-    if (!Array.isArray(raw) || raw.length === 0 || !raw.every(item => typeof item === "string" && item.trim())) {
-        throw new Error("mission-review-traces: supply concise implementation/test traces");
+/** Optional implementation notes supplement host-observed source/checks; prose is not a coverage gate. */
+export function missionReviewTraces(_mission, raw) {
+    if (raw === undefined)
+        return [];
+    if (!Array.isArray(raw) || !raw.every(item => typeof item === "string")) {
+        throw new Error("mission-review-traces: optional notes must be strings");
     }
-    const grouped = raw.map(text => ({ text,
-        ids: [...text.matchAll(/(?:^|[.;]\s+|[\r\n])\s*((?:R\d+\s*[-/,]?\s*)+):/gu)]
-            .flatMap(match => [...match[1].matchAll(/R(\d+)(?:\s*-\s*R(\d+))?/gu)]
-            .flatMap(([, first, last]) => {
-            const firstID = `R${first}`;
-            if (last === undefined)
-                return [firstID];
-            const lastID = `R${last}`;
-            const start = mission.requirements.findIndex(item => item.id === firstID);
-            const end = mission.requirements.findIndex(item => item.id === lastID);
-            if (start < 0 || end < 0)
-                return [firstID, lastID];
-            if (start > end)
-                throw new Error(`mission-review-traces: descending range ${firstID}-${lastID}`);
-            return mission.requirements.slice(start, end + 1).map(item => item.id);
-        })) }));
-    if (grouped.every(item => item.ids.length === 0) && raw.length === mission.requirements.length)
-        return raw;
-    const unknown = grouped.flatMap(item => item.ids).filter(id => !mission.requirements.some(requirement => requirement.id === id));
-    const missing = mission.requirements.filter(requirement => !grouped.some(item => item.ids.includes(requirement.id)));
-    if (unknown.length || missing.length)
-        throw new Error(`mission-review-traces: name the existing R IDs; ${[
-            ...(missing.length ? [`missing ${missing.map(item => item.id).join(", ")}`] : []),
-            ...(unknown.length ? [`unknown ${unknown.join(", ")}`] : []),
-        ].join("; ")}`);
-    return mission.requirements.map(requirement => grouped.filter(item => item.ids.includes(requirement.id)).map(item => item.text).join("\n"));
+    return raw.map(text => text.trim()).filter(Boolean);
 }

package/dist/core/operator-runtime.d.ts

@@ -227,6 +227,22 @@ export interface OperatorState {
     decision: string | null;
     receipt: GoalTerminalReceipt | null;
 }
+export interface OperatorProgress {
+    readonly profile: string;
+    readonly view: "progress";
+    readonly run_id: string;
+    readonly stage: OperatorPhase;
+    readonly decision: string | null;
+    readonly current_unit: {
+        readonly id: string;
+        readonly title: string;
+        readonly status: UnitState["status"];
+    } | null;
+    readonly completed_units: number;
+    readonly total_units: number;
+    readonly budget_remaining_units: number | null;
+    readonly next_action: string | null;
+}
 /** A later mission may replace an unexecuted cancellation, but must retain settled work's acceptance. */
 export declare function cancelledMissionRetainsAcceptance(state: OperatorState): boolean;
 export declare function operatorGitPathAuthorized(path: string, scopes: readonly string[], platform?: NodeJS.Platform): boolean;
@@ -371,10 +387,13 @@ export declare class OperatorRuntime {
     draftStatus(root: string): Promise<unknown | undefined>;
     completionGoalFingerprint(state: OperatorState): Promise<string>;
     verifyContinuityControls(state: OperatorState): Promise<void>;
+    /** Compact, read-only projection of the same durable run and decision as the complete packet. */
+    progress(state: OperatorState, budgetRemainingUnits: number | null, nextAction?: string | null): OperatorProgress;
     packet(state: OperatorState): unknown;
     /** Reconstruct the admitted child's instructions without trusting a lossy conversation summary. */
     workerContext(root: string, child: string): Promise<string | undefined>;
     continuationCheckpoint(root: string): Promise<string | undefined>;
+    private continuationNextAction;
     private controlReference;
     private verifyControls;
     /** Follow only the host's authorized parent-link repair; keep the durable control pin in sync. */

package/dist/core/operator-runtime.js

@@ -1904,6 +1904,16 @@ export class OperatorRuntime {
         for (const unit of current.units)
             await this.verifyControls(unit);
     }
+    /** Compact, read-only projection of the same durable run and decision as the complete packet. */
+    progress(state, budgetRemainingUnits, nextAction) {
+        const current = state.units.find(unit => unit.status !== "succeeded");
+        const authoritativeAction = nextAction !== undefined ? nextAction
+            : this.continuationNextAction(state);
+        return { profile: state.profile, view: "progress", run_id: state.runID, stage: state.phase, decision: state.decision,
+            current_unit: current === undefined ? null : { id: current.unit.id, title: current.unit.title, status: current.status },
+            completed_units: state.units.filter(unit => unit.status === "succeeded").length, total_units: state.units.length,
+            budget_remaining_units: budgetRemainingUnits, next_action: typeof authoritativeAction === "string" ? authoritativeAction : null };
+    }
     packet(state) {
         const proved = new Set(state.units.flatMap(unit => unit.evidence.flatMap(item => item.measurement.criterion_ids)));
         const current = state.units.find(unit => unit.status !== "succeeded");
@@ -2035,9 +2045,10 @@ export class OperatorRuntime {
     }
     async continuationCheckpoint(root) {
         const state = await this.read(root);
-        const cancelledRemediation = state?.phase === "cancelled" &&
-            [ACCEPTANCE_REMEDIATION_DECISION, REVIEW_REMEDIATION_DECISION].includes(state.decision ?? "");
-        if (!state || state.phase === "completed" || (state.phase === "cancelled" && !cancelledRemediation))
+        if (!state)
+            return undefined;
+        const nextAction = this.continuationNextAction(state);
+        if (nextAction === null)
             return undefined;
         const current = state.units.find(unit => unit.status !== "succeeded");
         return JSON.stringify({ authority: "durable-operator-state", root_session_id: state.rootSessionID,
@@ -2046,14 +2057,21 @@ export class OperatorRuntime {
             next_task_ref: current?.status === "pending" ? (state.units.length > 1
                 ? state.operatorSessionID === null ? this.dispatchTask(state).prompt : null
                 : current.repairValidation === null ? this.workerTask(state, current).prompt : this.repairWorkerTask(state, current).prompt) : null,
-            next_action: state.decision === ACCEPTANCE_REMEDIATION_DECISION || state.decision === REVIEW_REMEDIATION_DECISION
-                ? `call ${this.profile.toolPrefix}operator_status and execute its cancel-then-replacement next_action in this turn; do not stop after reporting status or call resume_operator`
-                : state.phase === "awaiting-acceptance" ? `call ${this.profile.toolPrefix}operator_status and follow its independent-review next_action; do not complete before review disposition`
-                    : state.phase === "prepared" ? "call operator_status, then operator_next; dispatch only the exact returned Task"
-                        : state.phase === "running" ? "call operator_status; do not duplicate the running Task"
-                            : state.phase === "cancelled"
-                                ? `call ${this.profile.toolPrefix}operator_status and execute its prepare_operator next_action in this turn; do not stop after reporting status`
-                                : `call ${this.profile.toolPrefix}operator_status and execute its exact next_action in this turn; do not stop after reporting status` });
+            next_action: nextAction });
+    }
+    continuationNextAction(state) {
+        const cancelledRemediation = state.phase === "cancelled" &&
+            [ACCEPTANCE_REMEDIATION_DECISION, REVIEW_REMEDIATION_DECISION].includes(state.decision ?? "");
+        if (state.phase === "completed" || (state.phase === "cancelled" && !cancelledRemediation))
+            return null;
+        return state.decision === ACCEPTANCE_REMEDIATION_DECISION || state.decision === REVIEW_REMEDIATION_DECISION
+            ? `call ${this.profile.toolPrefix}operator_status and execute its cancel-then-replacement next_action in this turn; do not stop after reporting status or call resume_operator`
+            : state.phase === "awaiting-acceptance" ? `call ${this.profile.toolPrefix}operator_status and follow its independent-review next_action; do not complete before review disposition`
+                : state.phase === "prepared" ? "call operator_status, then operator_next; dispatch only the exact returned Task"
+                    : state.phase === "running" ? "call operator_status; do not duplicate the running Task"
+                        : state.phase === "cancelled"
+                            ? `call ${this.profile.toolPrefix}operator_status and execute its prepare_operator next_action in this turn; do not stop after reporting status`
+                            : `call ${this.profile.toolPrefix}operator_status and execute its exact next_action in this turn; do not stop after reporting status`;
     }
     controlReference(path) {
         const local = relative(this.projectRoot, path);

package/dist/plugin/adaptive-remediation-host.d.ts

@@ -23,7 +23,7 @@ export interface AdaptiveReviewProvider {
         readonly fingerprint: string;
     }>;
 }
-export declare const DEFAULT_ADAPTIVE_REMEDIATION_MODEL = "openai/gpt-6-sol";
+export declare const DEFAULT_ADAPTIVE_REMEDIATION_MODEL = "openai/gpt-6.1-sol";
 export interface AdaptiveRemediationSessionClient extends OpenCodeModelAvailabilityClient {
     session: {
         create(input: {

package/dist/plugin/adaptive-remediation-host.js

@@ -10,7 +10,7 @@ import { produceWorktreeCommitArtifact, runContainedValidation } from "../core/w
 import { openCodeModel } from "./model-routing-hook.js";
 const SHA = /^[a-f0-9]{40}(?:[a-f0-9]{24})?$/u;
 const HASH = /^[a-f0-9]{64}$/u;
-export const DEFAULT_ADAPTIVE_REMEDIATION_MODEL = "openai/gpt-6-sol";
+export const DEFAULT_ADAPTIVE_REMEDIATION_MODEL = "openai/gpt-6.1-sol";
 const responseData = (value) => {
     if (value === null || typeof value !== "object")
         return {};

package/dist/plugin/mission-review.js

@@ -1,8 +1,8 @@
 import { createHash } from "node:crypto";
 import { execFile } from "node:child_process";
 import { createReadStream } from "node:fs";
-import { lstat, readlink } from "node:fs/promises";
-import { isAbsolute, relative, resolve, sep } from "node:path";
+import { lstat, readlink, readdir } from "node:fs/promises";
+import { isAbsolute, join, relative, resolve, sep } from "node:path";
 import { promisify } from "node:util";
 import { createInterface } from "node:readline";
 import { TOOL_ENVIRONMENT } from "../runtime-mission-assets.js";
@@ -218,7 +218,7 @@ export async function missionReviewSource(directory, run, evidence = [], baselin
     // Keep room for the baseline diff. Reserve notices only after the allocated whole lines show
     // truncation; pre-reserving every possible notice can hide all six otherwise fitting references.
     const heading = (entry) => `\n--- evidence: ${entry.path}:${entry.offset} ---\n`;
-    const truncated = (entry) => `[FOCUSED EXCERPT TRUNCATED: ${entry.path}:${entry.offset}; request a smaller range]\n`;
+    const truncated = (entry) => `[FOCUSED EXCERPT TRUNCATED: ${entry.path}:${entry.offset}; Reviewer can read the remaining lines directly]\n`;
     // Read-only reviews retain their smaller existing envelope; code reviews may use the space
     // previously reserved for automatic diff prefixes, while leaving room for changed-file context.
     const limit = writes.length ? 18_000 : 11_000;
@@ -305,13 +305,17 @@ export async function missionReviewSource(directory, run, evidence = [], baselin
     const unchanged = diff.length === 0;
     let excerpt = selected + diff;
     const paths = [...new Set([...names.split("\0"), ...ignored.split("\0")].filter(Boolean))].sort();
-    for (const path of paths) {
+    const visited = new Set();
+    const visit = async (path, includedByParent = false) => {
+        if (visited.has(path))
+            return;
+        visited.add(path);
         hash.update(JSON.stringify(path));
         try {
             const absolute = resolve(directory, path), stat = await lstat(absolute);
             hash.update(String(stat.mode));
-            const include = untracked.has(path) || unchanged;
-            const heading = `\n--- ${untracked.has(path) ? "new file" : "current file"}: ${path} ---\n`;
+            const include = includedByParent || untracked.has(path) || unchanged;
+            const heading = `\n--- ${includedByParent || untracked.has(path) ? "new file" : "current file"}: ${path} ---\n`;
             const room = include ? Math.max(0, 24_000 - Buffer.byteLength(excerpt) - Buffer.byteLength(heading)) : 0;
             let preview = Buffer.alloc(0);
             if (stat.isSymbolicLink()) {
@@ -319,7 +323,28 @@ export async function missionReviewSource(directory, run, evidence = [], baselin
                 hash.update(String(content.length)).update(content);
                 preview = content.subarray(0, room);
             }
+            else if (stat.isDirectory()) {
+                hash.update("directory");
+                if (include) {
+                    const marker = "[directory; contained artifacts follow]\n";
+                    const headingFits = Buffer.byteLength(excerpt) + Buffer.byteLength(heading) + Buffer.byteLength(marker) <= 24_000;
+                    if (headingFits)
+                        excerpt += heading + marker;
+                    else
+                        omitted.push(path);
+                }
+                // Nested repository metadata is not candidate output and can crowd out its actual files.
+                const children = (await readdir(absolute, { withFileTypes: true }))
+                    .filter(child => child.name !== ".git")
+                    .sort((left, right) => Number(left.isDirectory()) - Number(right.isDirectory()) ||
+                    (left.name < right.name ? -1 : left.name > right.name ? 1 : 0));
+                for (const child of children) {
+                    await visit(join(path, child.name).replaceAll("\\", "/"), include);
+                }
+            }
             else {
+                if (!stat.isFile())
+                    throw new Error("mission-review-source: unsupported artifact type");
                 hash.update(String(stat.size));
                 for await (const part of createReadStream(absolute)) {
                     const bytes = Buffer.isBuffer(part) ? part : Buffer.from(part);
@@ -328,7 +353,7 @@ export async function missionReviewSource(directory, run, evidence = [], baselin
                         preview = Buffer.concat([preview, bytes.subarray(0, room - preview.length)]);
                 }
             }
-            if (include) {
+            if (include && !stat.isDirectory()) {
                 const headingFits = Buffer.byteLength(excerpt) + Buffer.byteLength(heading) <= 24_000;
                 if (headingFits) {
                     const rendered = preview.includes(0) ? "[binary artifact: bytes fingerprinted]" : preview.toString("utf8");
@@ -358,7 +383,9 @@ export async function missionReviewSource(directory, run, evidence = [], baselin
                 throw error;
             hash.update("deleted");
         }
-    }
+    };
+    for (const path of paths)
+        await visit(path);
     if (external.length) {
         // A declared write scope can also be a host-managed runtime directory (e.g. Docker's data root).
         // Do not make review depend on listing it; record the missing coverage instead. Protected
@@ -375,7 +402,7 @@ export async function missionReviewSource(directory, run, evidence = [], baselin
     if (bytes.length > 24_000 && truncatedSource.length === 0)
         truncatedSource.push("(source diff exceeds excerpt budget)");
     return { fingerprint: `sha256:${hash.digest("hex")}`, excerpt: (bytes.length > 24_000 ? bytes.subarray(0, 24_000).toString("utf8") : excerpt) +
-            (truncatedSource.length ? `\n[EXCERPT TRUNCATED: ${truncatedSource.slice(0, 20).join(", ")}; supply focused traces for missing sections, not another implementation unit]` : "") +
+            (truncatedSource.length ? `\n[EXCERPT TRUNCATED: ${truncatedSource.slice(0, 20).join(", ")}; Reviewer can read/search the relevant source directly]` : "") +
             (unreadable.length ? `\n[UNINSPECTED EXTERNAL DIRECTORIES: ${unreadable.slice(0, 20).join(", ")}; select specific result files as review evidence]` : ""),
         truncatedEvidence, truncatedSource };
 }

package/dist/plugin/model-cost.d.ts

@@ -1,9 +1,9 @@
 export declare const MODEL_COST_PRICING_SNAPSHOT: {
-    readonly checkedAt: "2026-09-23";
+    readonly checkedAt: "2026-09-30";
     readonly currency: "USD";
     readonly unit: "1M tokens";
-    readonly sources: readonly ["https://developers.openai.com/api/docs/pricing", "https://developers.openai.com/api/docs/models/gpt-6-astra", "https://developers.openai.com/api/docs/models/gpt-6-sol", "https://developers.openai.com/api/docs/models/gpt-6-luna", "https://developers.openai.com/api/docs/guides/fast-mode", "https://developers.openai.com/api/docs/models/gpt-5.6-sol", "https://developers.openai.com/api/docs/models/gpt-5.6-terra", "https://developers.openai.com/api/docs/models/gpt-5.6-luna", "https://platform.claude.com/docs/en/about-claude/pricing"];
-    readonly assumptions: readonly ["OpenAI Standard pricing; requests above 272,000 total input/cache tokens use 2x input/cache and 1.5x output pricing.", "Anthropic Standard pricing with the 5-minute cache-write rate; Batch, Flex, regional, tool, and subscription charges are excluded.", "variant and serviceTier are separate; model variants do not alter the selected Standard token price.", "GPT-6 Sol and GPT-6 Luna use their official Standard schedules; the OpenCode gpt-6-luna-fast selector sends API model gpt-6-luna with priority service tier.", "GPT-6 Sol/Luna Fast (service_tier fast or priority) is priced at 2x the applicable Standard rates, including cache and long-context multipliers.", "gpt-5.6-luna-fast is retained only as a compatibility price for historical host catalog entries; it has no published model page and is exactly twice the GPT-5.6 Luna Standard schedule."];
+    readonly sources: readonly ["https://developers.openai.com/api/docs/pricing", "https://developers.openai.com/api/docs/models/gpt-6-astra", "https://developers.openai.com/api/docs/models/gpt-6-sol", "https://developers.openai.com/api/docs/models/gpt-6.1-sol", "https://developers.openai.com/api/docs/models/gpt-6-luna", "https://developers.openai.com/api/docs/guides/fast-mode", "https://developers.openai.com/api/docs/models/gpt-5.6-sol", "https://developers.openai.com/api/docs/models/gpt-5.6-terra", "https://developers.openai.com/api/docs/models/gpt-5.6-luna", "https://platform.claude.com/docs/en/about-claude/pricing"];
+    readonly assumptions: readonly ["OpenAI Standard pricing; requests above 272,000 total input/cache tokens use 2x input/cache and 1.5x output pricing.", "Anthropic Standard pricing with the 5-minute cache-write rate; Batch, Flex, regional, tool, and subscription charges are excluded.", "variant and serviceTier are separate; model variants do not alter the selected Standard token price.", "GPT-6 Sol, GPT-6.1 Sol, and GPT-6 Luna use their official Standard schedules; the OpenCode gpt-6-luna-fast selector sends API model gpt-6-luna with priority service tier.", "For GPT-6 Sol, GPT-6.1 Sol, and GPT-6 Luna, Fast mode (service_tier fast or priority, including the gpt-6.1-sol-fast selector) multiplies applicable Standard rates by 2, including cache and long-context multipliers.", "gpt-5.6-luna-fast is retained only as a compatibility price for historical host catalog entries; it has no published model page and is exactly twice the GPT-5.6 Luna Standard schedule."];
 };
 export interface ModelCostUsage {
     readonly providerID: string | undefined;

package/dist/plugin/model-cost.js

@@ -1,11 +1,12 @@
 export const MODEL_COST_PRICING_SNAPSHOT = {
-    checkedAt: "2026-09-23",
+    checkedAt: "2026-09-30",
     currency: "USD",
     unit: "1M tokens",
     sources: [
         "https://developers.openai.com/api/docs/pricing",
         "https://developers.openai.com/api/docs/models/gpt-6-astra",
         "https://developers.openai.com/api/docs/models/gpt-6-sol",
+        "https://developers.openai.com/api/docs/models/gpt-6.1-sol",
         "https://developers.openai.com/api/docs/models/gpt-6-luna",
         "https://developers.openai.com/api/docs/guides/fast-mode",
         "https://developers.openai.com/api/docs/models/gpt-5.6-sol",
@@ -17,14 +18,15 @@ export const MODEL_COST_PRICING_SNAPSHOT = {
         "OpenAI Standard pricing; requests above 272,000 total input/cache tokens use 2x input/cache and 1.5x output pricing.",
         "Anthropic Standard pricing with the 5-minute cache-write rate; Batch, Flex, regional, tool, and subscription charges are excluded.",
         "variant and serviceTier are separate; model variants do not alter the selected Standard token price.",
-        "GPT-6 Sol and GPT-6 Luna use their official Standard schedules; the OpenCode gpt-6-luna-fast selector sends API model gpt-6-luna with priority service tier.",
-        "GPT-6 Sol/Luna Fast (service_tier fast or priority) is priced at 2x the applicable Standard rates, including cache and long-context multipliers.",
+        "GPT-6 Sol, GPT-6.1 Sol, and GPT-6 Luna use their official Standard schedules; the OpenCode gpt-6-luna-fast selector sends API model gpt-6-luna with priority service tier.",
+        "For GPT-6 Sol, GPT-6.1 Sol, and GPT-6 Luna, Fast mode (service_tier fast or priority, including the gpt-6.1-sol-fast selector) multiplies applicable Standard rates by 2, including cache and long-context multipliers.",
         "gpt-5.6-luna-fast is retained only as a compatibility price for historical host catalog entries; it has no published model page and is exactly twice the GPT-5.6 Luna Standard schedule.",
     ],
 };
 const OPENAI = {
     "gpt-6-astra": { input: 10, cacheRead: 1, cacheWrite: 12.5, output: 50 },
     "gpt-6-sol": { input: 2, cacheRead: 0.2, cacheWrite: 2.5, output: 10 },
+    "gpt-6.1-sol": { input: 2, cacheRead: 0.1, cacheWrite: 2.5, output: 10 },
     "gpt-6-luna": { input: 0.1, cacheRead: 0.01, cacheWrite: 0.125, output: 0.5 },
     "gpt-5.6-sol": { input: 4, cacheRead: 0.4, cacheWrite: 5, output: 20 },
     "gpt-5.6": { input: 4, cacheRead: 0.4, cacheWrite: 5, output: 20 },
@@ -43,14 +45,16 @@ export function estimateModelUsageCost(usage) {
         usage.outputTokens, usage.reasoningTokens];
     if (!counts.every(tokenCount))
         return { status: "unpriced", reason: "missing-usage" };
-    const alias = usage.providerID?.toLowerCase() === "openai" && usage.modelID === "gpt-6-luna-fast";
+    const lunaFastAlias = usage.providerID?.toLowerCase() === "openai" && usage.modelID === "gpt-6-luna-fast";
+    const sol61FastAlias = usage.providerID?.toLowerCase() === "openai" && usage.modelID === "gpt-6.1-sol-fast";
+    const alias = lunaFastAlias || sol61FastAlias;
     const fast = alias || (["fast", "priority"].includes(usage.serviceTier?.toLowerCase() ?? "") &&
-        usage.providerID?.toLowerCase() === "openai" && ["gpt-6-sol", "gpt-6-luna"].includes(usage.modelID ?? ""));
+        usage.providerID?.toLowerCase() === "openai" && ["gpt-6-sol", "gpt-6.1-sol", "gpt-6-luna"].includes(usage.modelID ?? ""));
     if (usage.serviceTier !== undefined && !(fast ? ["standard", "default", "fast", "priority"] : ["standard", "default"]).includes(usage.serviceTier.toLowerCase())) {
         return { status: "unpriced", reason: "unsupported-service-tier" };
     }
     const provider = usage.providerID?.toLowerCase();
-    const model = alias ? "gpt-6-luna" : usage.modelID;
+    const model = lunaFastAlias ? "gpt-6-luna" : sol61FastAlias ? "gpt-6.1-sol" : usage.modelID;
     const base = provider === "openai" && model !== undefined && Object.hasOwn(OPENAI, model) ? OPENAI[model]
         : provider === "anthropic" && model !== undefined && Object.hasOwn(ANTHROPIC, model) ? ANTHROPIC[model] : undefined;
     if (base === undefined)

package/dist/plugin/model-routing.d.ts

@@ -7,18 +7,18 @@ export interface RoleModelRoute {
     readonly fallback?: readonly ModelTarget[];
 }
 export type ModelRoutingConfig = Readonly<Record<string, RoleModelRoute>>;
-/** The stable serial implementation route stays on Sol when Luna fan-out is unsafe or unavailable. */
-export declare const DEDICATED_WORKER_MODEL = "openai/gpt-6-sol";
+/** The stable serial implementation route stays on GPT-6.1 Sol when Luna fan-out is unsafe or unavailable. */
+export declare const DEDICATED_WORKER_MODEL = "openai/gpt-6.1-sol";
 export declare const DEDICATED_WORKER_VARIANT = "medium";
 /** Luna executes only units admitted to the fabric; it is not the serial worker's fallback target. */
 export declare const LUNA_FABRIC_WORKER_MODEL = "openai/gpt-6-luna";
 export declare const LUNA_FABRIC_WORKER_VARIANT = "max";
 export declare const LUNA_FABRIC_WORKER_ROLE = "dog-luna-worker";
-/** The coordinator uses Sol 6 High so routing and progress decisions do not bottleneck the workflow. */
-export declare const DEFAULT_COORDINATOR_MODEL = "openai/gpt-6-sol";
+/** The coordinator uses GPT-6.1 Sol High so routing and progress decisions do not bottleneck the workflow. */
+export declare const DEFAULT_COORDINATOR_MODEL = "openai/gpt-6.1-sol";
 export declare const DEFAULT_COORDINATOR_VARIANT = "high";
-/** Compatibility names retained for the pre-v0.8 explicit Sol target. */
-export declare const ESCALATION_WORKER_MODEL = "openai/gpt-6-sol";
+/** Compatibility names retained for the pre-v0.8 explicit Sol route. */
+export declare const ESCALATION_WORKER_MODEL = "openai/gpt-6.1-sol";
 export declare const ESCALATION_WORKER_VARIANT = "medium";
 export declare const DEDICATED_WORKER_ROLES: readonly ["implementation", "remediation", "blocker-resolution", "sol-worker-mk2a2", "dog-worker"];
 /** Ordered last-resort targets used only when the host proves a policy target unavailable. */
@@ -38,7 +38,7 @@ export declare const LUNA_FABRIC_WORKER_ROUTING: ModelRoutingConfig;
 export declare function fixedWorkerRouting(dedicatedTarget?: ModelTarget): ModelRoutingConfig;
 export declare const FIXED_MODEL_ROUTING: ModelRoutingConfig;
 export declare const RECOMMENDED_LUNA_MODEL = "openai/gpt-6-luna";
-/** Coordinator state and routing use Sol 6 High; bounded evidence retrieval uses Luna High. */
+/** Coordinator state and routing use GPT-6.1 Sol High; bounded evidence retrieval uses Luna High. */
 export declare const DEFAULT_COORDINATOR_ROUTING: ModelRoutingConfig;
 /** Evidence gathering is retrieval rather than reasoning, so the scout stays one effort tier lower. */
 export declare const RECOMMENDED_SCOUT_VARIANT = "high";