dsh-decision-layer 0.5.4 → 0.5.5

package/README.en.md

@@ -4,7 +4,7 @@
 
 `dsh-decision-layer` adds structured, explicitly scoped decisions to the DeepSeek Harness (DSH) agent loop, backed by a pluggable adjudication backend. Dangerous-call gating, output self-check, tool narrowing, and loop prevention hook into the agent loop as automatic interventions.
 
-> **0.5.4 is a preview release.** The plugin works, but how much real value the adjudication interventions add is still being explored — every threshold is an unvalidated heuristic default. Treat it as something to observe, not a proven guarantee of impact. See [ROADMAP.md](<ROADMAP.md>) for scope and progress.
+> **0.5.5 is a preview release.** The plugin works, but how much real value the adjudication interventions add is still being explored — every threshold is an unvalidated heuristic default. Treat it as something to observe, not a proven guarantee of impact. See [ROADMAP.md](<ROADMAP.md>) for scope and progress.
 
 ## Installation
 
@@ -49,4 +49,4 @@ Restart `dsh web` and refresh after installing or updating: the host and client
 
 ## Safety boundary and development
 
-Automatic intervention only subtracts: the gate only denies, narrowing only removes tools, and neither grants new permissions. The gate defers to native DSH approval on backend failure rather than allowing; self-check, narrowing, and loop-guard errors skip intervention. The redacted summary sent to the backend carries only tool name and command/path with secret redaction — never file content. Node.js `>=20.11`; `npm test` and `npm run build:client` run local checks. Rebuild and commit `lib/client.js` with any client change. 0.5.4 is a preview: the interventions work, but their real value and thresholds are still being explored — feedback on misjudgments and feel observed in the decision log is welcome.
+Automatic intervention only subtracts: the gate only denies, narrowing only removes tools, and neither grants new permissions. The gate defers to native DSH approval on backend failure rather than allowing; self-check, narrowing, and loop-guard errors skip intervention. The redacted summary sent to the backend carries only tool name and command/path with secret redaction — never file content. Node.js `>=20.11`; `npm test` and `npm run build:client` run local checks. Rebuild and commit `lib/client.js` with any client change. 0.5.5 is a preview: the interventions work, but their real value and thresholds are still being explored — feedback on misjudgments and feel observed in the decision log is welcome.

package/README.md

@@ -4,7 +4,7 @@
 
 DeepSeek Harness（DSH）的结构化裁决插件。它把有明确判断标准的问题交给同协议的裁决后端，供 agent 在需要时使用，并在 agent loop 上接入危险门控、产出自检、工具收窄和防循环等自动介入。
 
-> **0.5.4 是体验版。** 插件功能已可用，但裁决介入能带来多少实际价值仍在探索中——各决策点的阈值都是未经验证的启发式默认值，建议先以观察心态体验，别当成经过验证的效果保证。功能与后续进度以 [ROADMAP.md](<ROADMAP.md>) 为准。
+> **0.5.5 是体验版。** 插件功能已可用，但裁决介入能带来多少实际价值仍在探索中——各决策点的阈值都是未经验证的启发式默认值，建议先以观察心态体验，别当成经过验证的效果保证。功能与后续进度以 [ROADMAP.md](<ROADMAP.md>) 为准。
 
 ## 安装
 
@@ -53,4 +53,4 @@ dsh plugin --profile web add file:/绝对路径/dsh-decision-layer
 
 ## 开发
 
-服务端使用 Node.js `>=20.11`（`.mjs`，无需构建）；客户端用 TypeScript + esbuild 构建。`npm test` 跑本地测试，`npm run build:client` 生成 `lib/client.js`。改动客户端后需重建并连同 `lib/client.js` 一起提交，否则 GitHub 安装拿到的是旧 bundle。0.5.4 为体验版：介入能力已可用，但实际价值与阈值仍在探索，欢迎反馈决策日志观察到的误判与体感。
+服务端使用 Node.js `>=20.11`（`.mjs`，无需构建）；客户端用 TypeScript + esbuild 构建。`npm test` 跑本地测试，`npm run build:client` 生成 `lib/client.js`。改动客户端后需重建并连同 `lib/client.js` 一起提交，否则 GitHub 安装拿到的是旧 bundle。0.5.5 为体验版：介入能力已可用，但实际价值与阈值仍在探索，欢迎反馈决策日志观察到的误判与体感。

package/lib/client.js

@@ -1113,14 +1113,20 @@ function ConfigForm({ t, fetchFn = fetch }) {
     setNarrowOn(features?.narrow !== false);
     setCompleteOn(features?.complete !== false);
   };
-  const applyConfig = (value) => {
+  const applyBackend = (value) => {
     setConfig(value);
+  };
+  const applyAdvanced = (value) => {
     setCheckMode(value.checkSettings?.mode ?? "observe");
     setNarrowMode(value.narrowSettings?.mode ?? "enforce");
     setCompleteMode(value.completeSettings?.mode ?? "observe");
     setKeepPrefixes(prefixesText(value.narrowSettings));
     setMaxCandidates(String(maxCandidatesOf(value.narrowSettings)));
     setThreshold(String(thresholdOf(value.narrowSettings)));
+  };
+  const applyConfig = (value) => {
+    applyBackend(value);
+    applyAdvanced(value);
     applyFeatures(value.features);
   };
   (0, import_react4.useEffect)(() => {
@@ -1141,6 +1147,23 @@ function ConfigForm({ t, fetchFn = fetch }) {
       live = false;
     };
   }, [t, fetchFn]);
+  const toggleFeature = async (features, revert) => {
+    setBusy(true);
+    try {
+      const value = await request2("config", fetchFn, {
+        method: "PUT",
+        headers: { "content-type": "application/json" },
+        body: JSON.stringify({ features })
+      });
+      applyFeatures(value.features);
+    } catch {
+      revert();
+      setMessage({ text: t("error"), ok: false });
+    } finally {
+      setBusy(false);
+    }
+  };
+  const featureState = () => ({ gate: gateOn, check: checkOn, narrow: narrowOn, complete: completeOn });
   const saveAdvanced = async (event) => {
     event.preventDefault();
     const parsedCap = Number.parseInt(maxCandidates, 10);
@@ -1155,11 +1178,10 @@ function ConfigForm({ t, fetchFn = fetch }) {
         body: JSON.stringify({
           checkSettings: { mode: checkMode },
           narrowSettings: { mode: narrowMode, keepPrefixes: parsePrefixes(keepPrefixes), maxCandidates: cap, threshold: thresh },
-          completeSettings: { mode: completeMode },
-          features: { gate: gateOn, check: checkOn, narrow: narrowOn, complete: completeOn }
+          completeSettings: { mode: completeMode }
         })
       });
-      applyConfig(value);
+      applyAdvanced(value);
       setAdvancedDirty(false);
       setMessage({ text: t("saved"), ok: true });
     } catch {
@@ -1186,7 +1208,7 @@ ${url}`)) return;
           ...needsHttpConsent ? { confirmHttpUrl: url } : {}
         })
       });
-      applyConfig(value);
+      applyBackend(value);
       setKey("");
       setBackendDirty(false);
       setMessage({ text: t("saved"), ok: true });
@@ -1241,10 +1263,10 @@ ${url}`)) return;
           {
             label: t("featureGate"),
             checked: gateOn,
-            disabled: !ready,
+            disabled: !ready || busy,
             onChange: (next) => {
               setGateOn(next);
-              setAdvancedDirty(true);
+              void toggleFeature({ ...featureState(), gate: next }, () => setGateOn(!next));
             }
           }
         ),
@@ -1254,10 +1276,10 @@ ${url}`)) return;
           {
             label: t("featureCheck"),
             checked: checkOn,
-            disabled: !ready,
+            disabled: !ready || busy,
             onChange: (next) => {
               setCheckOn(next);
-              setAdvancedDirty(true);
+              void toggleFeature({ ...featureState(), check: next }, () => setCheckOn(!next));
             }
           }
         ),
@@ -1267,10 +1289,10 @@ ${url}`)) return;
           {
             label: t("featureNarrow"),
             checked: narrowOn,
-            disabled: !ready,
+            disabled: !ready || busy,
             onChange: (next) => {
               setNarrowOn(next);
-              setAdvancedDirty(true);
+              void toggleFeature({ ...featureState(), narrow: next }, () => setNarrowOn(!next));
             }
           }
         ),
@@ -1280,10 +1302,10 @@ ${url}`)) return;
           {
             label: t("featureComplete"),
             checked: completeOn,
-            disabled: !ready,
+            disabled: !ready || busy,
             onChange: (next) => {
               setCompleteOn(next);
-              setAdvancedDirty(true);
+              void toggleFeature({ ...featureState(), complete: next }, () => setCompleteOn(!next));
             }
           }
         ),

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "dsh-decision-layer",
-  "version": "0.5.4",
+  "version": "0.5.5",
   "description": "A structured decision layer for the DeepSeek Harness agent loop: a danger-call gate, output self-check, tool narrowing, and loop guard backed by a pluggable adjudication model.",
   "keywords": [
     "dsh",