dsh-vision-router 1.6.1 → 1.6.2

package/README.md

@@ -29,9 +29,9 @@
 <p align="center">💬 <strong>QQ community group: 1105463028</strong></p>
 
 > [!WARNING]
-> 📌 **Announcement (v1.6.1)**
+> 📌 **Announcement (v1.6.2)**
 >
-> **v1.6.1:** Deep-dive guidance after the structured pre-scan — mixed-image branch routing, a vision depth tier (quick/standard/thorough) and configurable guidance copy in the main settings; attachment limits for long screenshots restored (rc6/rc7).
+> **v1.6.2:** Stability release — fixes onboarding, OCR, model synchronization and large-image handling, improving long-session and overall runtime reliability.
 
 <p align="center">
   <img src="assets/vision-demo.gif" width="640" alt="Demo: paste an image, the agent locates the send button with vision_ground / vision_crop / vision_pixel_diff and answers with coordinates" />
@@ -154,7 +154,7 @@ The auto-vision group follows the live DSH model catalog. Adding models or chang
 
 ### 3. Paste or upload the image
 
-After choosing the “+ Auto Vision” group, paste or upload an image normally. By default the complete vision tool schema is stable from session start, so the agent can immediately use `vision_describe`, `vision_ground`, `vision_crop`, and the rest across multiple steps when needed.
+After choosing the “+ Auto Vision” model group, paste or upload an image normally. By default the complete vision tool schema is stable from session start, so the agent can immediately use `vision_describe`, `vision_ground`, `vision_crop`, and the rest across multiple steps when needed.
 
 The built-in anonymous OVH vision fallback is already configured, so normal image use needs no signup or API key. **The lower-right chat picker selects only the brain/conversation model**; vision backends do not belong there. Advanced options live under **Settings → Plugins → Plugin config → 视觉路由（自动识图）**: each vision-backend row may select any callable generative user model already configured under **Settings → Models**. DSH image-capability metadata is advisory only: undeclared or text-only-labelled models remain selectable and show a warning. At runtime Vision Router always tries the provider's registered DSH adapter first — including WebSocket, RPC and private transports — and falls through on a real failure. The direct compatibility bridge is used only when an http(s) OpenAI Chat Completions endpoint is positively identified. Leaving every user row empty is valid; the OVH chain remains the final fallback. `Vision HTTP` is an internal transport route, not a model group users should select.
 

package/README.zh.md

@@ -29,9 +29,9 @@
 <p align="center">💬 <strong>QQ 用户交流群：1105463028</strong></p>
 
 > [!WARNING]
-> 📌 **公告（v1.6.1）**
+> 📌 **公告（v1.6.2）**
 >
-> **v1.6.1：结构化预识别后的深挖引导——混合图分路识别、看图深度档位（快速/标准/细致）、可自定义识图引导（移到主设置区）；恢复超长截图的附件准入放宽（rc6/rc7 均有效）。**
+> **v1.6.2：集中修复引导、OCR、模型同步与大图处理问题，提升长会话和整体运行稳定性。**
 
 <p align="center">
   <img src="assets/vision-demo.gif" width="640" alt="演示：粘贴图片，Agent 用 vision_ground / vision_crop / vision_pixel_diff 定位发送按钮并给出坐标" />

package/entry.js

@@ -14,6 +14,12 @@ import { installAdversarialHardening } from './lib/adversarial-hardening.js'
 import { installLocalVisionStabilizer } from './lib/local-vision-stabilizer.js'
 import { installWrapperDirectoryAlias } from './lib/wrapper-directory.js'
 import { installAndroidAttachmentCompat } from './lib/android-attachment-compat.js'
+import { contextWithCoalescedAdapterUpdates } from './lib/adapter-update-coalescer.js'
+import { installTesseractExecFileCompat } from './lib/tesseract-exec-compat.js'
+import {
+  installStructuredFlowHardening,
+  normalizeGuidanceOverrides,
+} from './lib/structured-flow-hardening.js'
 import {
   attachmentContextForContract,
   installRc7SettingsCompatibility,
@@ -26,6 +32,10 @@ import {
 // for the settings namespace, so composition config and settings validation
 // agree on the same default.
 core.Config.set('progressiveTools', z.boolean().default(false))
+// Structured 1+x now also has a turn-level wall-clock budget. Individual
+// visionTaskTimeoutMs budgets remain unchanged; this one prevents a deep turn
+// from multiplying them into several minutes of serial waiting.
+core.Config.set('visionTurnBudgetMs', z.number().step(1000).min(10000).max(600000).default(90000))
 
 export * from './index.js'
 export {
@@ -73,6 +83,11 @@ export function apply(ctx, config = {}) {
   const runtimeConfig = {
     ...bootConfig,
     progressiveTools: hardenedConfig.progressiveTools === true,
+    guidanceOverrides: normalizeGuidanceOverrides(bootConfig.guidanceOverrides ?? hardenedConfig.guidanceOverrides),
+    visionTurnBudgetMs:
+      Number.isFinite(Number(bootConfig.visionTurnBudgetMs))
+        ? Number(bootConfig.visionTurnBudgetMs)
+        : 90000,
   }
   const rc7 = isRc7ContractRuntime(stabilizedCtx)
   const ownershipCtx = rc7 ? protectRc7ProviderOwnership(stabilizedCtx) : stabilizedCtx
@@ -89,6 +104,22 @@ export function apply(ctx, config = {}) {
   const attachmentCompatCtx = attachmentContextForContract(settingsCtx, logging.logger, {
     installAndroidAttachmentCompat,
   })
+  // Final structured-flow guard sits closest to core.apply so it sees the
+  // actual tool registrations and pre-step listener. It makes bootstrap
+  // one-shot, enforces fast/standard/deep quotas, tracks mixed branches,
+  // rejects empty/non-evidence results, and applies one shared turn deadline.
+  const structuredCtx = installStructuredFlowHardening(attachmentCompatCtx, runtimeConfig)
+  // DSH rc.7 publishes llm/adapters-updated synchronously from inside
+  // registerAdapter(). Coalesce only Vision Router's listener: nested events
+  // mark the topology dirty and the outer pass reruns to a fixed point, so we
+  // neither double-register a twin nor lose a provider added mid-pass.
+  const reconciledCtx = contextWithCoalescedAdapterUpdates(structuredCtx)
+  // index.js historically passes image bytes as `options.input` to the async
+  // execFile API. That option is not fed into child stdin, so Tesseract waits
+  // for data until the OCR slice expires. Materialize only this exact
+  // Tesseract-stdin call to a temporary image file; all other execFile calls
+  // keep their native behavior.
+  installTesseractExecFileCompat(reconciledCtx)
 
   // 启动诊断摘要只描述 composition/apply 的基础配置。设置服务可能稍后
   // 覆盖这些值；每个图片轮还会记录 current() 的实时决策，避免把这个
@@ -109,7 +140,7 @@ export function apply(ctx, config = {}) {
     /* diagnostics must never break apply */
   }
   try {
-    const result = core.apply(attachmentCompatCtx, runtimeConfig)
+    const result = core.apply(reconciledCtx, runtimeConfig)
     // DSH rc.7's Settings -> Models surface is backed by the configurable
     // provider directory, not by the live adapter registry alone. Publish the
     // main DeepSeek + 自动识图 route as a derived alias of official DeepSeek so