sortie-dogs 0.13.5 → 0.13.6

package/README.md

@@ -35,10 +35,10 @@ 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)
 
-**Current release: [v0.13.5](https://github.com/zufall-upon/Sortie-dogs/releases/tag/v0.13.5)**
-([release notes](docs/release-v0.13.5.md)). The default Mission runtime retains the `v010`
+**Current release: [v0.13.6](https://github.com/zufall-upon/Sortie-dogs/releases/tag/v0.13.6)**
+([release notes](docs/release-v0.13.6.md)). The default Mission runtime retains the `v010`
 profile, command and configuration names for compatibility; these names do not mean v0.10 is installed.
-The current asset marker is `0.13.5-live-state-v1`.
+The current asset marker is `0.13.6-acceptance-reuse-v1`.
 
 ## SWE-bench Lite: 170/300 (56.67%)
 
@@ -48,7 +48,7 @@ The fixed **Sortie-dogs v0.12.24** harness resolved **170 of 300 SWE-bench Lite
 
 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.
 
-Historical scores below belong to their fixed candidates, not v0.13.5. SWE-bench is a separate,
+Historical scores below belong to their fixed candidates, not v0.13.6. SWE-bench is a separate,
 optional measurement rather than a mandatory release gate.
 
 > **Beta:** v0.13.x is still stabilizing. Runtime behavior,
@@ -93,7 +93,18 @@ existing local bridge loads enforcement and model routing. OpenCode can reload w
 but replacing an installed dependency may require a full restart. A new chat session alone does not
 prove the newly installed plugin is loaded.
 
-## v0.13.5 runtime updates
+## v0.13.6 runtime updates
+
+PR #156 references recorded formal PASS evidence in acceptance summaries instead of fetching
+the same successful unit's native history again for display. Missing/failed proof retains history
+diagnostics; historical evidence is not current freshness or acceptance. Identical external artifact
+inventories are shared only inside one snapshot refresh, never across later calls. Operator guidance
+proceeds to acceptance when current evidence covers the request and no concrete gap remains.
+Existing freshness/review guards, provider/model selection and cache-prefix machinery remain unchanged.
+No end-to-end speedup or live token/cache-hit improvement was measured. Release receipts:
+`_testenv/releases/0.13.6/`; see [release notes](docs/release-v0.13.6.md).
+
+## v0.13.5 runtime updates (retained)
 
 PR #154 preserves stable model instructions and appends changed host state at native history
 boundaries, with complete current-state reconstruction after compaction. Genuine Reviewer tools
@@ -413,7 +424,7 @@ register stable and `v010` from the same package installation path in one host.
 Project-local installation is recommended. To expose the current Mission assets globally:
 
 ```sh
-npm install --global sortie-dogs@0.13.5
+npm install --global sortie-dogs@0.13.6
 sortie-dogs init --global --profile v010
 ```
 
@@ -425,7 +436,7 @@ can resolve a **separate dependency** under that config root. Updating npm-globa
 it. For that layout, also install the same release at the actual config root, then rerun global init:
 
 ```sh
-npm install --prefix "$HOME/.config/opencode" sortie-dogs@0.13.5
+npm install --prefix "$HOME/.config/opencode" sortie-dogs@0.13.6
 sortie-dogs init --global --profile v010
 ```
 
@@ -448,7 +459,7 @@ version, preserves user configuration, and stops safely on unknown ownership or
 conflicting files.
 
 Align any exact version pin or separate bridge dependency with the intended release too. An installed
-marker of `0.13.5-live-state-v1` identifies the assets; it does not prove an already-running
+marker of `0.13.6-acceptance-reuse-v1` identifies the assets; it does not prove an already-running
 OpenCode process has reloaded the plugin.
 
 There is no supported uninstall command. Remove the npm dependency separately,

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 = "0.13.5-live-state-v1";
+export declare const V010_RUNTIME_ASSET_VERSION = "0.13.6-acceptance-reuse-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 = "0.13.5-live-state-v1";
+export const V010_RUNTIME_ASSET_VERSION = "0.13.6-acceptance-reuse-v1";

package/dist/core/operator-mission.js

@@ -534,6 +534,15 @@ export async function missionAcceptanceSummary(mission, run, operators, observe)
         const provenance = { run_id: item.state.runID, unit_id: unit.unit.id, worker_session_id: unit.childSessionID,
             state_archive_path: item.path, handoff_path: unit.handoffPath, historical: item.historical,
             authority: "native declared-command observations; not additional formal evidence or current freshness" };
+        // Settled proof already records these commands. Do not fetch the same native
+        // history again merely to render acceptance; freshness is checked separately.
+        const proofs = unit.evidence ?? [];
+        if (unit.status === "succeeded" && unit.unit.validation.every(command => proofs.some(proof => proof.execution.exit_code === 0 && proof.execution.outcome === "pass" &&
+            proof.execution.command.includes(command)))) {
+            return { ...provenance, status: "recorded-formal-evidence",
+                evidence_ids: proofs.map(proof => proof.evidence_id),
+                details_ref: { field: "formal_validation", run_id: item.state.runID, unit_id: unit.unit.id } };
+        }
         try {
             if (!observe || !unit.childSessionID)
                 throw new Error("native-worker-history-unavailable");

package/dist/plugin/protected-snapshot.js

@@ -164,13 +164,19 @@ function outside(projectRoot, path) {
     const scoped = relative(projectRoot, path).replaceAll("\\", "/");
     return scoped === ".." || scoped.startsWith("../") || isAbsolute(scoped);
 }
-async function declaredScopeDigest(projectRoot, paths, manifestHash, source, excluded = [], binding, candidatePolicy) {
+async function declaredScopeDigest(projectRoot, paths, manifestHash, source, excluded = [], binding, candidatePolicy, artifactsMemo) {
     const local = paths.filter(path => !outside(projectRoot, path));
     const external = paths.filter(path => outside(projectRoot, path));
     const project = await protectedScopeDigest(projectRoot, local, manifestHash, source ? "project-files-v1" : undefined, excluded, binding, candidatePolicy);
     if (project === undefined)
         return undefined;
-    const artifacts = await declaredArtifacts(external).catch(() => undefined);
+    const key = JSON.stringify(external);
+    let pending = artifactsMemo?.get(key);
+    if (!pending) {
+        pending = declaredArtifacts(external);
+        artifactsMemo?.set(key, pending);
+    }
+    const artifacts = await pending.catch(() => undefined);
     return artifacts && goalFingerprint({ project, external: artifacts.entries.filter(([path]) => !excluded.some(root => !outside(root, path))) });
 }
 /** An existing operation may create its declared outputs. Compare its other inputs during execution;
@@ -274,8 +280,11 @@ export async function refreshProtectedSnapshot(projectRoot, binding) {
         }
     }
     if (binding.source_policy === "declared-paths-v1") {
-        const source = await declaredScopeDigest(projectRoot, sourcePaths, manifestHash, true, [], binding);
-        const candidate = await declaredScopeDigest(projectRoot, candidatePaths, manifestHash, false, [], binding, binding.candidate_policy);
+        // Reuse identical external inventories only inside this read-only refresh.
+        // A later status/completion call always observes filesystem changes anew.
+        const artifactsMemo = new Map();
+        const source = await declaredScopeDigest(projectRoot, sourcePaths, manifestHash, true, [], binding, undefined, artifactsMemo);
+        const candidate = await declaredScopeDigest(projectRoot, candidatePaths, manifestHash, false, [], binding, binding.candidate_policy, artifactsMemo);
         return source === undefined || candidate === undefined ? undefined : { source, candidate };
     }
     // Legacy evidence retains its original recipe; a new policy cannot relabel stale proof as fresh.

package/dist/runtime-mission-assets.js

@@ -162,8 +162,8 @@ quality threshold and explicit model/budget choice. Follow AGENTS.md and use the
     For a Coordinator ready candidate, use operator_status's acceptance_summary: verbatim original
     requests, anchored cumulative formal validation, current review disposition (author self-recheck
     is not independent approval) and recorded delivery state.
-    Historical results are references, not current freshness PASS. Inspect source or evidence only for
-    concrete unresolved gaps; do not routinely search run archives or reread every source/test file.
+     If current evidence covers the request and no concrete gap remains, proceed to acceptance.
+     Historical results are not current freshness PASS; read source or artifacts only to resolve a gap.
      Existing validation freshness and Review guards still apply; this summary does not accept the mission.
      One compact status check can lead directly to review_mission and its returned Reviewer Task; original
      requests, diff and checks are supplied automatically. Add traces only for concrete extra information.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "sortie-dogs",
-  "version": "0.13.5",
+  "version": "0.13.6",
   "description": "Bounded agent harness and validated orchestration loop plugin for OpenCode",
   "keywords": [
     "opencode",