dsh-strata-sync 0.10.7 → 0.10.9

package/README.md

@@ -11,7 +11,7 @@ The plugin reads Strata's model information, previews the changes, and updates D
 - **Sync model settings:** context window, response output limit, and confirmed input types and reasoning levels.
 - **Align compaction budgets:** update the matching policies in enabled DSH Agent presets.
 - **Control summary length:** edit the supplemental prompt and adjust two target-length ratios.
-- **Sync on startup:** optionally synchronize once after DSH becomes idle.
+- **Sync on startup:** optionally synchronize once when DSH starts.
 - **Review and recover:** preview differences, back up settings, and view the last synchronization result.
 
 Strata Server is read-only to this plugin. Synchronization does not switch or load server models, change server settings, or send test inference requests. Unconfirmed model capabilities keep their existing DSH values.
@@ -48,24 +48,26 @@ The main flow appears first: **Check differences → Review changes → Back up
 
 1. Select your Strata provider and click **Save preferences**.
 2. Click **Check differences** to inspect the loaded model and proposed changes.
-3. While DSH is idle, click **Back up and sync**.
+3. Click **Back up and sync**.
 4. **Start a new conversation** to use the updated model and Agent preset settings.
 
-Existing conversations keep their selected model route and preset revision. To make future setup automatic, enable **Automatically sync when DSH starts** and save. This option is off by default and takes effect on the next start; it waits for idle and does not poll continuously.
+Existing conversations keep their selected model route and preset revision. To make future setup automatic, enable **Automatically sync when DSH starts** and save. This option is off by default and takes effect on the next start; it can run during tasks and does not poll continuously.
 
 ## Model and output settings
 
 | Setting | How it is chosen |
 |---|---|
 | Model and context | Strata's loaded text model and verified context capacity. |
-| Response output limit | Manual override, if set; otherwise the verified Strata output default. If unavailable or unlimited, use 30% of context, capped at 16,384 tokens. |
+| Response output limit | Manual override, if set; otherwise the verified Strata output default. If unavailable or unlimited, use Strata's formula: 30% of context, at least 4,096 and at most 32,768 tokens. |
 | Input types | Confirmed server capabilities, such as text or text plus image. |
 | Reasoning levels | Verified model-template support; unknown templates preserve existing settings. |
 | Default model | Follows the loaded Strata model when **Follow the loaded Strata model as the default** is enabled. |
 
 Keep **Follow Strata output limit** enabled for automatic selection. Turn it off to set a manual override under **Advanced settings**. The preview shows the server default, effective value and source separately.
 
-When synchronizing, the plugin sets a 4,096-token summary output cap and 4,096-token compaction headroom. The effective compaction trigger is the smaller of **80% of context** and **context − response output − 4,096**. Recent-content retention is **(context − response output) × 16%**, rounded down. These are client-side budgets calculated by the plugin, not settings supplied by Strata.
+The fallback follows [Strata's local output formula](https://github.com/Niko1221/Strata/blob/main/apps/host/server/agent/profile.mjs): `max(4096, min(32768, floor(context × 0.3)))`.
+
+When synchronizing, the plugin normally sets a 4,096-token summary output cap and compaction headroom. For small windows using calculated output, both are limited to half the remaining conversation budget, rounded down; an 8K window therefore uses 2,048. The effective compaction trigger is the smaller of **80% of context** and **context − response output − headroom**. Recent-content retention is **(context − response output) × 16%**, rounded down. These compaction budgets are calculated by the plugin, not supplied by Strata.
 
 For example, with automatic output calculation, a 32K context uses a 9,830-token response allowance and an 18,842-token compaction trigger. It does **not** necessarily compact at 80%.
 

package/dist/client.js

@@ -11,11 +11,11 @@ window.__ModuleLoader__.load({
 "Automatic calculation": {"zh-Hant":"自動計算","zh-Hans":"自动计算"},
 "Server has no fixed output limit.": {"zh-Hant":"伺服器未設定固定輸出上限。","zh-Hans":"服务器未设置固定输出上限。"},
 "Server output limit could not be verified.": {"zh-Hant":"無法確認伺服器的輸出上限。","zh-Hans":"无法确认服务器的输出上限。"},
-"Leave blank to use the server output default; if absent or unlimited, use 30% of context, up to 16,384. An explicit override takes priority.": {"zh-Hant":"留空會採用伺服器輸出預設值；未提供或無固定上限時，使用上下文的 30%，最多 16,384。明確填寫的覆寫值優先。","zh-Hans":"留空采用服务器输出默认值；未提供或无固定上限时，使用上下文的 30%，最多 16,384。明确填写的覆盖值优先。"},
+"Leave blank to use the server output default; if absent or unlimited, use 30% of context, at least 4,096 and at most 32,768. An explicit override takes priority.": {"zh-Hant":"留空會採用伺服器輸出預設值；未提供或無固定上限時，使用上下文的 30%，最低 4,096、最高 32,768。明確填寫的覆寫值優先。","zh-Hans":"留空采用服务器输出默认值；未提供或无固定上限时，使用上下文的 30%，最低 4,096、最高 32,768。明确填写的覆盖值优先。"},
 "Strata returned an invalid output limit. Review the server setting before syncing.": {"zh-Hant":"Strata 回傳無效的輸出上限，請先檢查伺服器設定。","zh-Hans":"Strata 返回无效的输出上限，请先检查服务器设置。"},
-  "Runs once on the next DSH start. Waits for running tasks to finish; no periodic server checks.": {
-    "zh-Hant": "下次啟動 DSH 時同步一次；若有工作執行中，會等到閒置，不再定期檢查伺服器。",
-    "zh-Hans": "下次启动 DSH 时同步一次；如有任务运行中，会等待空闲，不再定期检查服务器。"
+  "Runs once on the next DSH start; no periodic server checks.": {
+    "zh-Hant": "下次啟動 DSH 時同步一次，不再定期檢查伺服器。",
+    "zh-Hans": "下次启动 DSH 时同步一次，不再定期检查服务器。"
   },
   "Image": {"zh-Hant":"圖片","zh-Hans":"图片"},
   "View mapping": {"zh-Hant":"查看參數對應","zh-Hans":"查看参数映射"},
@@ -239,9 +239,9 @@ window.__ModuleLoader__.load({
     "zh-Hant": "正在載入同步設定…",
     "zh-Hans": "正在加载同步设置…"
   },
-  "DSH is running a task. Synchronization will wait until all tasks are idle.": {
-    "zh-Hant": "DSH 正在執行工作，同步會等到所有工作閒置後進行。",
-    "zh-Hans": "DSH 正在执行任务，同步会等到所有任务空闲后进行。"
+  "A synchronization is applying settings. Please wait.": {
+    "zh-Hant": "正在套用同步設定，請稍候。",
+    "zh-Hans": "正在应用同步设置，请稍候。"
   },
   "Strata provider": {
     "zh-Hant": "Strata 供應者",
@@ -377,7 +377,7 @@ window.__ModuleLoader__.load({
       'Enabled': {'zh-Hant':'已啟用','zh-Hans':'已启用'},
       'Save option changes below before checking differences again.': {'zh-Hant':'請先在下方儲存選項變更，再重新檢查差異。','zh-Hans':'请先在下方保存选项更改，再重新检查差异。'},
       'Follow Strata output limit': {'zh-Hant':'輸出上限跟隨 Strata','zh-Hans':'输出上限跟随 Strata'},
-      'Use the verified server default. If none is available, calculate 30% of context, up to 16,384 tokens.': {'zh-Hant':'採用已確認的伺服器預設值；無固定值時，以上下文的 30% 計算，最多 16,384 tokens。','zh-Hans':'采用已确认的服务器默认值；无固定值时，按上下文的 30% 计算，最多 16,384 tokens。'},
+      'Use the verified server default. If none is available, calculate 30% of context, at least 4,096 and at most 32,768 tokens.': {'zh-Hant':'採用已確認的伺服器預設值；無固定值時，以上下文的 30% 計算，最低 4,096、最高 32,768 tokens。','zh-Hans':'采用已确认的服务器默认值；无固定值时，按上下文的 30% 计算，最低 4,096、最高 32,768 tokens。'},
       'Advanced settings': {'zh-Hant':'進階設定','zh-Hans':'高级设置'},
       'Manual output limit': {'zh-Hant':'手動輸出上限','zh-Hans':'手动输出上限'},
       'Turn off Follow Strata output limit to enter a manual override.': {'zh-Hant':'關閉「輸出上限跟隨 Strata」後，可輸入手動覆寫值。','zh-Hans':'关闭“输出上限跟随 Strata”后，可输入手动覆盖值。'},
@@ -511,7 +511,7 @@ REASONING_DEFAULT_CONFLICT: 'The provider default reasoning level is not support
         h('style',null,css+workflowCss),
         h('header',null,h('h2',null,'dsh-strata-sync'),h('p',{className:'ss-muted'},t('Sync the model and context budgets from Strata Server to DSH.'))),
         !state&&!loadError&&h('div',{className:'ss-status',role:'status'},t('Loading sync settings...')),
-        state?.busy&&h('div',{className:'ss-status',role:'status'},t('DSH is running a task. Synchronization will wait until all tasks are idle.')),
+        state?.busy&&h('div',{className:'ss-status',role:'status'},t('A synchronization is applying settings. Please wait.')),
         (error||loadError)&&h('div',{className:'ss-status ss-error',role:'alert'},diagnostic(error||loadError)),
         notice&&h('div',{className:'ss-status',role:'status'},t(notice)),
         conflict&&h('div',{className:'ss-status ss-error'},
@@ -570,14 +570,14 @@ REASONING_DEFAULT_CONFLICT: 'The provider default reasoning level is not support
           h('summary',{className:'ss-option-title'},h('span',null,t('Sync preferences')),h('span',{className:'ss-option-description'},t('Output limit, default model and startup sync'))),
         h('div',{className:'ss-card'},
           h('label',{className:'ss-check'},h('input',{type:'checkbox',checked:!form.manual,'aria-label':t('Follow Strata output limit'),onChange:e=>edit({manual:!e.target.checked}),disabled:pending||!state}),t('Follow Strata output limit')),
-          h('p',{className:'ss-muted'},t('Use the verified server default. If none is available, calculate 30% of context, up to 16,384 tokens.')),
+          h('p',{className:'ss-muted'},t('Use the verified server default. If none is available, calculate 30% of context, at least 4,096 and at most 32,768 tokens.')),
           activeBudget?outputValues(activeBudget,preview.server?.model):h('p',{className:'ss-muted'},t('Check differences to read the server and effective limits.')),
           h('details',{className:'ss-details',open:form.manual},h('summary',null,t('Advanced settings')),
             h('label',null,t('Manual output limit'),h('input',{type:'number',min:1,step:1,value:form.output,onChange:e=>edit({output:e.target.value}),disabled:pending||!state||!form.manual})),
             h('p',{className:'ss-muted'},t(form.manual?'A manual limit takes priority over the server default and automatic calculation.':'Turn off Follow Strata output limit to enter a manual override.')))),
         h('label',{className:'ss-check'},h('input',{type:'checkbox',checked:form.follow,onChange:e=>edit({follow:e.target.checked}),disabled:pending||!state}),t('Follow the loaded Strata model as the default')),
         h('label',{className:'ss-check'},h('input',{type:'checkbox',checked:form.auto,onChange:e=>edit({auto:e.target.checked}),disabled:pending||!state}),t('Automatically sync when DSH starts')),
-        h('p',{className:'ss-muted'},t('Runs once on the next DSH start. Waits for running tasks to finish; no periodic server checks.'))),
+        h('p',{className:'ss-muted'},t('Runs once on the next DSH start; no periodic server checks.'))),
         h('details',{className:'ss-card ss-options','data-testid':'summary-target'},
           h('summary',{className:'ss-option-title'},h('span',null,t('Dynamic summary target')),h('span',{className:'ss-badge'},t(form.summaryGuidance?'Enabled':'Optional'))),
           h('label',{className:'ss-check'},h('input',{type:'checkbox','data-testid':'summary-guidance-toggle','aria-label':t('Enable summary guidance'),checked:form.summaryGuidance,onChange:e=>edit({summaryGuidance:e.target.checked}),disabled:pending||!state}),t('Enable summary guidance')),

package/dist/core.mjs

@@ -59,18 +59,21 @@ export function normalizeBaseURL(value) {
 
 /**
  * Select the output allowance, then derive DSH's client-side compaction policy.
- * The 4096 headroom also matches the native pi-ai context safety margin.
+ * The usual 4096 headroom also matches the native pi-ai context safety margin.
  */
 export function planBudget(contextWindow, { outputTokens, serverOutputTokens } = {}) {
   if (!isContext(contextWindow) || contextWindow < 8192) {
     fail('UNSUPPORTED_CONTEXT', 'A verified context window of at least 8,192 tokens is required.');
   }
-  const output = outputTokens ?? serverOutputTokens ?? Math.min(16384, Math.floor(contextWindow * 0.3));
+  const output = outputTokens ?? serverOutputTokens ?? Math.max(4096, Math.min(32768, Math.floor(contextWindow * 0.3)));
   const outputSource = outputTokens != null ? 'manual' : serverOutputTokens != null ? 'server' : 'calculated';
   if (!Number.isSafeInteger(output) || output < 1 || output >= contextWindow) {
     fail('INVALID_OUTPUT_BUDGET', 'The output budget must be a positive integer smaller than the context window.');
   }
-  const headroomTokens = 4096;
+  // The 4K output floor must still leave compaction room in an 8K window.
+  // Keep fixed/manual budgets and the usual 4K reserve unchanged.
+  const headroomTokens = outputSource === 'calculated'
+    ? Math.min(4096, Math.floor((contextWindow - output) / 2)) : 4096;
   const thresholdRatio = 0.8;
   const retainRatio = 0.16;
   const messageBudgetTokens = contextWindow - output;

package/dist/index.js

@@ -5,7 +5,7 @@ import z from '@deepseek-ai/schemastery';
 import { discoverStrata, planBudget, StrataSyncError } from './core.mjs';
 import { DEFAULT_SUMMARY_TEMPLATE, validSummaryDivisor, validSummaryTemplate, installSummaryGuidance } from './summary.mjs';
 
-export const inject = ['configEditor', 'connection', 'agents', 'credentials', 'agentPresets'];
+export const inject = ['configEditor', 'connection', 'credentials', 'agentPresets'];
 export const Config = z.object({
   providerId: z.string().default(''),
   autoSync: z.boolean().default(false),
@@ -134,10 +134,6 @@ export function apply(ctx, initialConfig) {
     if (candidates.length !== 1) refuse('provider-required', 'Choose which existing provider connects to Strata Server.');
     return candidates[0];
   }
-  function busy() {
-    // DSH 0.2.1-rc.3 reports maintenance as idle while manual compaction can still run.
-    return ctx.agents.list().some((agent) => agent.status !== 'idle' || agent.phase?.kind === 'maintenance');
-  }
   function refreshSettings() {
     settings = { providerId: '', autoSync: false, followLoadedModel: true, ...entry(PACKAGE).options.config };
   }
@@ -160,7 +156,8 @@ export function apply(ctx, initialConfig) {
       });
     } catch { /* The page remains usable when the required provider is absent. */ }
     return { ...publicSettings(), defaultSummaryPromptTemplate: DEFAULT_SUMMARY_TEMPLATE, settingsRevision: hash(publicSettings()),
-      busy: busy() || !!writeBarrier, providers, lastPreview, lastApplied, lastError };
+      // UI busy describes a configuration write, never a running Agent task.
+      busy: !!writeBarrier, providers, lastPreview, lastApplied, lastError };
   }
   async function credential(providerId, route) {
     if (route.apiKeyEnv) {
@@ -272,7 +269,7 @@ export function apply(ctx, initialConfig) {
     const warnings = [...discovered.warnings ?? [], ...(before.owners.some((owner) => owner.targets.some((target) => target.config.auto === false)) ? ['DSH_AUTO_COMPACTION_DISABLED'] : [])];
     const presetIds = before.owners.flatMap((owner) => owner.presetId ? [owner.presetId] : []);
     const view = { providerId, server: { baseURL: discovered.baseURL, model: discovered.model, warnings }, budget, current, compactions, capabilityEdits, capabilityStatus,
-      presetIds, needsNewConversation: presetIds.length > 0, changes, fingerprint, busy: busy() };
+      presetIds, needsNewConversation: presetIds.length > 0, changes, fingerprint, busy: !!writeBarrier };
     previewSnapshots.set(view, before);
     lastPreview = view;
     lastError = null;
@@ -302,7 +299,7 @@ export function apply(ctx, initialConfig) {
     ensureOpen();
     payload(request, ['fingerprint', 'providerId', 'outputTokens']);
     if (typeof request.fingerprint !== 'string' || !request.fingerprint) refuse('preview-required', 'Preview the proposed changes before applying them.');
-    if (busy()) refuse('busy', 'A DSH task is running. Wait until all tasks are idle before syncing.');
+
     const view = await preview({ ...(request.providerId ? { providerId: request.providerId } : {}), ...(own(request, 'outputTokens') ? { outputTokens: request.outputTokens } : {}) });
     ensureOpen();
     if (view.fingerprint !== request.fingerprint) refuse('stale-preview', 'The server or DSH settings changed. Review a fresh preview.');
@@ -312,7 +309,7 @@ export function apply(ctx, initialConfig) {
       lastApplied = appliedSummary(view, null, false);
       return { applied: false, backupPath: null, preview: view };
     }
-    if (busy()) refuse('busy', 'A DSH task started. Sync has been deferred.');
+
     writeBarrier = new Promise((resolve) => { releaseWrite = resolve; });
     let backupPath;
     const completed = [];
@@ -320,7 +317,7 @@ export function apply(ctx, initialConfig) {
       backupPath = await backup();
       ensureOpen();
       assertSnapshot(before);
-      if (busy()) refuse('busy', 'A DSH task started. Sync has been deferred.');
+
       const modelId = view.server.model.id;
       const llmNext = clone(before.llm);
       const route = llmNext.providers[view.providerId];
@@ -354,7 +351,7 @@ export function apply(ctx, initialConfig) {
         if (hash(original) === hash(next)) continue;
         await ctx.configEditor.edit(entry(name, id), (current) => {
           ensureOpen();
-          if (busy()) refuse('busy', 'A DSH task started. Sync has been deferred.');
+
           // ConfigEditor may queue this callback behind another settings edit.
           // Recheck every owner when our first write actually begins.
           if (completed.length === 0) assertSnapshot(before);
@@ -393,7 +390,7 @@ export function apply(ctx, initialConfig) {
     if (typeof request.expectedRevision !== 'string' || request.expectedRevision !== hash(publicSettings())) {
       refuse('stale-settings', 'Sync preferences changed. Reload the latest preferences before saving.');
     }
-    if (busy()) refuse('busy', 'Wait until all DSH tasks are idle before changing sync settings.');
+
     const next = { ...settings };
     if (own(request, 'providerId')) {
       if (typeof request.providerId !== 'string') refuse('invalid-request', 'Provider must be a string.');
@@ -432,7 +429,7 @@ export function apply(ctx, initialConfig) {
       if (hash(current) !== hash(original) || hash(publicSettings(current)) !== request.expectedRevision) {
         refuse('stale-settings', 'Sync preferences changed while saving. Reload the latest preferences.');
       }
-      if (busy()) refuse('busy', 'Wait until all DSH tasks are idle before changing sync settings.');
+
       return next;
     });
     settings = next;
@@ -517,7 +514,7 @@ export function apply(ctx, initialConfig) {
     try {
       refreshSettings();
       if (!settings.autoSync) { startup.pending = false; clearInterval(timer); return; }
-      if (busy() || inFlight || startup.running) return;
+      if (inFlight || startup.running) return;
     } catch (error) {
       // The host can withdraw a required entry during reload. Do not leave an
       // unhandled timer rejection or retry an unsupported profile indefinitely.
@@ -526,7 +523,7 @@ export function apply(ctx, initialConfig) {
       clearInterval(timer);
       return;
     }
-    // Discovery can outlive an idle period. Busy/disposed attempts keep the one
+    // Concurrent sync/disposed attempts keep the one
     // startup operation pending; successful/no-op and terminal errors consume it.
     startup.running = true;
     let deferred = false;
@@ -548,7 +545,7 @@ export function apply(ctx, initialConfig) {
   // edits are rejected as nested HMR transactions. Mirror Hmr.watchConfig():
   // detach only timer creation, while every write still uses ConfigEditor and
   // its normal runExclusive queue. `executing` is a version-specific host seam.
-  // This timer only waits for startup readiness/idle; no recurring server polling.
+  // This timer only waits for startup readiness; no recurring server polling.
   const createTimer = () => setInterval(() => { void poll(); }, 1_000);
   const executing = ctx.get('hmr')?.executing;
   if (startup.pending) timer = typeof executing?.exit === 'function' ? executing.exit(createTimer) : createTimer();

package/docs/CAPABILITIES.md

@@ -1,6 +1,6 @@
 # Verified model capabilities
 
-Capability synchronization uses the preview, backup, rollback and idle-only synchronization workflow. It does not send generation requests or alter Strata Server.
+Capability synchronization uses the preview, backup, rollback and coordinated configuration-write workflow. It does not send generation requests or alter Strata Server.
 
 ## Input types
 

package/docs/README.zh-CN.md

@@ -11,7 +11,7 @@
 - **同步模型设置：**上下文窗口、回复输出上限，以及已确认的输入类型和推理等级。
 - **对齐压缩预算：**更新已启用的 DSH Agent 预设中，对应模型的压缩策略。
 - **控制摘要长度：**编辑补充提示词，调整两项目标长度比例。
-- **启动时同步：**可选择在 DSH 启动并空闲后同步一次。
+- **启动时同步：**可选择在 DSH 启动后同步一次。
 - **预览与恢复：**检查差异、备份设置，并查看最近一次同步结果。
 
 插件只读访问 Strata Server。同步不会切换或加载服务器模型、修改服务器设置，也不会发送测试推理请求。无法确认的模型能力会保留 DSH 原有值。
@@ -48,24 +48,26 @@ dsh plugin --profile desktop add dsh-strata-sync --registry=https://registry.npm
 
 1. 选择 Strata 提供方，点击**保存偏好**。
 2. 点击**检查差异**，查看已加载模型与拟修改的设置。
-3. 在 DSH 空闲时，点击**备份并同步**。
+3. 点击**备份并同步**。
 4. **开启新对话**，使用更新后的模型与 Agent 预设。
 
-已有对话会保留原先选定的模型路由和预设版本。如需自动设置，可勾选**启动 DSH 时自动同步**并保存。此选项默认关闭，下次启动才生效；会等待空闲，不会持续轮询。
+已有对话会保留原先选定的模型路由和预设版本。如需自动设置，可勾选**启动 DSH 时自动同步**并保存。此选项默认关闭，下次启动才生效；可在任务执行中同步，不会持续轮询。
 
 ## 模型与输出设置
 
 | 设置 | 如何决定 |
 |---|---|
 | 模型与上下文 | 采用 Strata 已加载的文本模型及已确认的上下文容量。 |
-| 回复输出上限 | 优先使用手动覆盖值；否则采用已确认的 Strata 输出默认值。无法取得或未限制时，使用上下文的 30%，最多 16,384 tokens。 |
+| 回复输出上限 | 优先使用手动覆盖值；否则采用已确认的 Strata 输出默认值。无法取得或未限制时，使用 Strata 官方公式：上下文的 30%，最低 4,096、最高 32,768 tokens。 |
 | 输入类型 | 采用服务器已确认的能力，例如文本或文本＋图片。 |
 | 推理等级 | 根据已验证的模型模板确定；未知模板保留原有设置。 |
 | 默认模型 | 启用**默认模型跟随 Strata 已加载的模型**时，跟随服务器当前模型。 |
 
 保持**输出上限跟随 Strata**开启，即可自动选择。关闭后可在**高级设置**输入手动覆盖值。预览会分别显示服务器默认值、实际应用值及其来源。
 
-同步时，插件将摘要输出上限和压缩预留空间均设为 4,096 tokens。实际压缩阈值取**上下文的 80%**与**上下文 − 回复输出预算 − 4,096**中的较小值，近期内容保留量为 **（上下文 − 回复输出预算）× 16%**，向下取整。这些是插件计算的客户端预算，并非 Strata 提供的设置。
+自动计算采用 [Strata 官方输出公式](https://github.com/Niko1221/Strata/blob/main/apps/host/server/agent/profile.mjs)：`max(4096, min(32768, floor(context × 0.3)))`。
+
+同步时，摘要输出上限和压缩余量通常均为 4,096 tokens。小窗口使用自动计算输出时，两者最多为剩余对话预算的一半，向下取整；因此 8K 窗口使用 2,048。实际压缩阈值取**上下文的 80%**与**上下文 − 回复输出预算 − 压缩余量**中的较小值，近期内容保留量为 **（上下文 − 回复输出预算）× 16%**，向下取整。这些压缩预算由插件计算，并非 Strata 提供的设置。
 
 例如，采用自动输出计算时，32K 上下文的回复预算为 9,830 tokens，压缩阈值为 18,842 tokens，**不一定在 80% 时压缩**。
 

package/docs/README.zh-TW.md

@@ -11,7 +11,7 @@
 - **同步模型設定：**上下文視窗、回覆輸出上限，以及已確認的輸入類型和推理等級。
 - **對齊壓縮預算：**更新已啟用的 DSH Agent 預設中，對應模型的壓縮政策。
 - **控制摘要長度：**編輯補充提示詞，調整兩項目標長度比例。
-- **啟動時同步：**可選擇在 DSH 啟動並閒置後同步一次。
+- **啟動時同步：**可選擇在 DSH 啟動後同步一次。
 - **預覽與復原：**檢查差異、備份設定，並查看最近一次同步結果。
 
 外掛僅以唯讀方式存取 Strata Server。同步不會切換或載入伺服器模型、修改伺服器設定，也不會傳送測試推論請求。無法確認的模型能力會保留 DSH 原有值。
@@ -48,24 +48,26 @@ dsh plugin --profile desktop add dsh-strata-sync --registry=https://registry.npm
 
 1. 選擇 Strata 提供方，點選**儲存偏好**。
 2. 點選**檢查差異**，查看已載入模型與預計修改的設定。
-3. 在 DSH 閒置時，點選**備份並同步**。
+3. 點選**備份並同步**。
 4. **開啟新對話**，使用更新後的模型與 Agent 預設。
 
-既有對話會保留原先選定的模型路由和預設版本。如需自動設定，可勾選**啟動 DSH 時自動同步**並儲存。此選項預設關閉，下次啟動才生效；會等待閒置，不會持續輪詢。
+既有對話會保留原先選定的模型路由和預設版本。如需自動設定，可勾選**啟動 DSH 時自動同步**並儲存。此選項預設關閉，下次啟動才生效；可在任務執行中同步，不會持續輪詢。
 
 ## 模型與輸出設定
 
 | 設定 | 如何決定 |
 |---|---|
 | 模型與上下文 | 採用 Strata 已載入的文字模型及已確認的上下文容量。 |
-| 回覆輸出上限 | 優先使用手動覆寫值；否則採用已確認的 Strata 輸出預設值。無法取得或未限制時，使用上下文的 30%，最多 16,384 tokens。 |
+| 回覆輸出上限 | 優先使用手動覆寫值；否則採用已確認的 Strata 輸出預設值。無法取得或未限制時，使用 Strata 官方公式：上下文的 30%，最低 4,096、最高 32,768 tokens。 |
 | 輸入類型 | 採用伺服器已確認的能力，例如文字或文字＋圖片。 |
 | 推理等級 | 依已驗證的模型範本決定；未知範本保留原有設定。 |
 | 預設模型 | 啟用**預設模型跟隨 Strata 已載入的模型**時，跟隨伺服器目前模型。 |
 
 保持**輸出上限跟隨 Strata**開啟，即可自動選擇。關閉後可在**進階設定**輸入手動覆寫值。預覽會分別顯示伺服器預設值、實際套用值及其來源。
 
-同步時，外掛將摘要輸出上限和壓縮預留空間均設為 4,096 tokens。實際壓縮門檻取**上下文的 80%**與**上下文 − 回覆輸出預算 − 4,096**中的較小值，近期內容保留量為 **（上下文 − 回覆輸出預算）× 16%**，向下取整。這些是外掛計算的客戶端預算，並非 Strata 提供的設定。
+自動計算採用 [Strata 官方輸出公式](https://github.com/Niko1221/Strata/blob/main/apps/host/server/agent/profile.mjs)：`max(4096, min(32768, floor(context × 0.3)))`。
+
+同步時，摘要輸出上限和壓縮餘裕通常均為 4,096 tokens。小視窗使用自動計算輸出時，兩者最多為剩餘對話預算的一半，向下取整；因此 8K 視窗使用 2,048。實際壓縮門檻取**上下文的 80%**與**上下文 − 回覆輸出預算 − 壓縮餘裕**中的較小值，近期內容保留量為 **（上下文 − 回覆輸出預算）× 16%**，向下取整。這些壓縮預算由外掛計算，並非 Strata 提供的設定。
 
 例如，採用自動輸出計算時，32K 上下文的回覆預算為 9,830 tokens，壓縮門檻為 18,842 tokens，**不一定在 80% 時壓縮**。
 

package/docs/VALIDATION.md

@@ -11,12 +11,15 @@ Validation date: 2026-10-30 (Asia/Taipei).
 
 ## Automated verification
 
-All **156 automated tests pass** for the current runtime. Coverage includes:
+All **162 automated tests pass** for the current runtime. Coverage includes:
+
+- Automatic output matches Strata's 30% formula with a 4,096 floor and 32,768 ceiling. Tests cover 8K through 1M contexts, rounding at the ceiling, unchanged server/manual precedence, valid small-window compaction budgets and all three UI translations. The 8K calculated-output case limits compaction headroom and summary cap to 2,048; 32K and larger retain 4,096.
 
 - Actual pi-ai context clamping across multiple input sizes, near-full and exhausted context, independent source length, additional prompt costs, disabled-mode zero discovery and restored native requests.
 - Native Cordis waterfall dispatch, immutable messages, concurrent summaries, duplicate hooks, cancellation, metadata failures, early stream closure, native errors and unload.
 - Verified model discovery, selected-provider/loaded-model matching, alias validation, input types, model-specific reasoning choices and eight mocked SDK wire cases.
-- Preference validation, idle guards, stale-preview rejection, concurrent edits, backup and rollback, startup synchronization, hot reload and enabled Agent preset policies.
+- Preference validation, synchronization write guards, stale-preview rejection, concurrent edits, backup and rollback, startup synchronization, hot reload and enabled Agent preset policies.
+- Synchronization during suspended generation and summary streams, including maintenance status, uses synthetic responses with a mocked ConfigEditor. Requests complete unchanged; simultaneous sync is rejected, new steps wait during writes, and both success and rollback release the barrier. These tests do not exercise a live desktop task or native ConfigEditor reload during a real model stream.
 - Three-language settings rendering, editable prompt preservation, custom divisors, preview ceilings, default-off behavior and preference conflicts.
 
 The package verifier checks the public file list, English root README selection, translated documentation links, entry points, source/build consistency and publishing metadata. It excludes private configuration, user conversations, credentials, backups and the native-prompt test fixture from the public package.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "dsh-strata-sync",
-  "version": "0.10.7",
+  "version": "0.10.9",
   "description": "Native DSH settings UI for synchronizing Strata Server models, context and compaction budgets",
   "type": "module",
   "main": "dist/index.js",