Prepare the approved bilingual Desktop 0.13.7 and Agent 0.13.1 release
notes, version locks, feature matrices, and Agent release notes. Package both
OpenCode and Continue in the compound Agent release and publish native
execution checklists for remote projects.
Fix Linux source validation by configuring Electron's chrome-sandbox helper
and running the full test suite under Xvfb without disabling sandboxing.
Release note: Desktop 0.13.7 adds paged canvas notes, HTTP OCR, managed app
navigation, remote Continue and execution checklists, while preserving
conversation history and improving remote/runtime recovery. Agent 0.13.1
ships OpenCode and Continue together with checklist delivery.
Validation: npm test passed; npm run typecheck passed; npm run lint passed;
npm run release:notes:verify passed; 22 release workflow tests passed. No
local production build or package was run. LoongArch preview is not included.
Keep interactive questions and answered cards at their original position in
conversation history, including remote reception, recovery, and reopening.
Preserve legacy history placement without a database migration.
Move supplementary guidance into shared accessible contextual-help popovers
across pages and settings. Add keyboard, modal, accessibility, and Electron
regressions, plus bounded opt-in live canvas-analysis validation.
Remove unused Agent, Runtime, and in-memory graph-search helpers, obsolete
mocks and browser copy; reuse the existing package-size formatter. Keep
production execution paths, protocol schemas, and released data migrations.
Validation: targeted cleanup tests, typecheck, lint, shared Linux Host
attach/read/re-attach, and added help/Electron checks passed. Final full-suite
verification passed 4,858 tests with 67 skipped and zero failures (412 files
passed, 9 skipped). Focused help checks passed 54 tests, including Electron
style comparisons and Chromium accessibility descriptions. Details and
validation boundaries are recorded in feature docs.
Release note: 修复交互式问答在回答后排到后续输出末尾的问题，重新打开会话仍保留提问位置。页面和设置中的补充说明改为标题或字段旁的按需帮助，支持鼠标与键盘操作。
Canvas analysis previously sent every page. Add a Magic Notes setting for
1-8 canvas pages, defaulting to 1 for new and historical settings. Select
the first N pages in current canvas order before capture and use the same
text/image range for saved entries, drafts and canvas-source todos.
Keep full 50-page saving/export, expose the same setting through config
tools, and use the shared settings select with an inline help icon.
Include pagination, persistence, production IPC and isolated Electron
regressions, including text-only input and scaled page boundaries.
Validation: focused feature tests and isolated Electron regressions passed;
the final compact UI passed 14 tests. Typecheck and lint were reported
passing by the coordinating agent. No full-suite pass is claimed because
the completed full test command exposed no summary. No live model calls
were made for this commit preparation.
Release note: 魔法笔记新增“发送画布页数”设置，可选 1～8 页，默认 1 页，按当前画布顺序发送前 N 页的文字和图片；标题旁问号可查看说明，保存和导出完整画布不受影响。
Keep feature inventory, user-focused prioritization, draft confirmation,
article templates, screenshot guidance and publication checks in one guide.
Use separate new-feature, improvement and bug-fix sections, with explicit
image, replacement and verification markers in drafts.
Archive the unreleased update article and its evidence review, retaining
pending screenshots and release details. Remove the split guide files and
update release-runbook references.
Validation: documentation structure, draft markers, 59 local links and
anchors, and staged whitespace checks passed. No product code changed;
product tests and builds were not run.
Keep paragraph formatting and checklist todos when removing canvas pages,
and preserve accepted undo/redo history after oversized input is rejected.
Merge restored queued text into the latest conversation draft and retain
image delivery when OCR returns image references and generated warnings only.
Deliver session MCP servers to bridged remote Continue Execute while keeping
Ask read-only and preserving local model-profile isolation. Add regression
coverage and update feature documentation. Correct stale conversation-limit
and forced-color assertions and the measured Electron layout test deadline.
Validation: 4,826 tests passed, 67 skipped; full typecheck and lint passed.
Current-source Linux x64 Execute/Ask/Execute MCP delivery passed, using 10
real text-provider requests and no image-provider requests. Image generation
itself was not exercised. Staged whitespace checks passed before commit.
Release note: 修复恢复队列时覆盖新输入、画布删页丢失清单格式及超限输入清空撤销历史的问题；图片 OCR 无正文时保留原图发送方式，远程 Continue Execute 正确保留会话 MCP 工具。
List and search all active conversations instead of only the latest 100. Preserve message history across consecutive sends instead of truncating it to 500 messages. Existing detail loading and context compression remain unchanged.
Validation: 7 focused tests, typecheck and lint passed. Full test run timed out after reporting failures in App completion visibility and WorkspacePrimitives forced-color contracts.
Release note: 会话列表和搜索不再限制为最近 100 个会话；发送消息不再截断超过 500 条的历史记录。
Graph extraction could exhaust its fixed 8192-token budget before returning
structured content. OpenAI requests now omit output-token limits, while
Anthropic uses the model connection limit required by its protocol.
Provider limits, timeout, cancellation and bounded response handling remain.
Use the shared accessible icon button for image downloads in chat and the
image viewer. Add graph request regression coverage and document the limits.
Release note: 知识图谱抽取不再额外限制为 8192 tokens；OpenAI 由模型服务决定输出上限，Anthropic 沿用模型连接配置。聊天和图片预览中的下载按钮统一为带提示的图标按钮。
Simplify sidebar selection and note record framing, compact the empty composer, and emphasize note titles. Replace redundant AI comment headings with an accessible panel toggle.
Add view-only canvas zoom and fit width, correct PDF import/export icons, and allow image files up to 20 MiB. Include regression coverage and updated design documentation.
Release note: Notes have clearer navigation and a more compact writing area. Canvases support zoom and fit width, and image imports accept files up to 20 MiB.
Keep model selection and switching feedback in the composer. Report automatic runtime status failures through notifications and move the send button accessible description into the composer.
Release note: Remove the duplicate top-right model/runtime badge while retaining switching feedback and error notifications.
Parsing test menus and application notifications could appear behind modal overlays or become unreachable while the background was inert. Share a stable top-layer portal that belongs to the owning or active modal, preserving notification timers, keyboard navigation and focus restoration.
Add unit and Electron regression coverage for settings, nested parsing results, application center, inference monitoring and native dialogs, with matching UI guidance and validation evidence.
Validation recorded in the preceding implementation: 4,793 tests passed and 67 skipped; typecheck, lint, isolated production build and Electron UI checks passed. Staged diff whitespace checks passed before this commit.
Release note: Menus and notifications remain visible and usable while settings or other dialogs are open, including keyboard navigation and notification dismissal.
Document the compact import cancellation control and progress-card layout. Record the prior full-suite results, focused attachment and Electron checks, and production probe review with their validation boundaries.
Release note: 附件查看结果、更多操作、移除和导入取消采用紧凑图标按钮，并提供悬停提示和键盘焦点说明，减少窄窗口中的布局拥挤。
Add HTTP PaddleOCR-VL settings and shared document previews for chat and knowledge imports. Preserve attachment originals and parsed assets across drafts, messages and queues; support explicit image OCR, selecting document images into a conversation draft, and restoring queued input for editing.
Protect unsaved note bodies and titles during navigation and asynchronous updates. Match canvas analysis to source revisions, invalidate affected comments, preserve annotations during pagination, and provide a resizable record index with saved width preferences.
Existing OCR settings retain local behavior. Historical attachments without saved originals are not reconstructed. Advanced OCR options depend on the configured service; image sending depends on the effective model and Runtime.
Validation: full typecheck and lint passed; 477 focused tests passed across 12 files; staged whitespace checks passed. The full repository suite was not rerun for this commit.
Release note: Keep note drafts safe while switching workspaces, resize the record index, and revisit saved document attachments with OCR previews and selected images in chat.
Magic Notes previously supported rich-text records without a paged drawing or
PDF annotation workflow. Add the integrated PeopleLib Fabric and Quill editor
with flowing text, pen/highlighter, object transforms, images, paper templates,
PDF backgrounds with native text extraction, and raster PDF export. Saves are
manual; undo/redo remains scoped to an annotation page or Quill mode.
Analyze drafts, saved canvases and canvas-source todos with page images and
text when the default model supports images, or an explicitly labelled
text-only fallback. Keep successful saves when automatic analysis fails and
prevent MCP plain-text replacement of canvas records.
Move entry bodies and binary assets into local note files with schema 38
migration and verified readback. SQLite retains metadata, indexes, revisions,
todos and comments. Backups must coordinate SQLite and the adjacent notes
directory while writes are paused or the app is closed; no one-click backup
action is included.
Show a continuous record stream with independent collapsible record index and
AI pane, real first-page thumbnails, and scroll-only record navigation. Open a
blank text/canvas composer by default and reset it after creation. Protect
unsaved drafts and establish normalized editor baselines after saving so clean
records do not prompt again when leaving.
Validation: latest recorded focused run passed 149 tests across five files;
typecheck, lint and git diff --check passed. The prior user-reported full run
passed 4,713 tests before later corrections and UI changes; it is not a full
validation of this final snapshot. Tests were not rerun for this commit, as
requested; independent systematic review follows the commit.
Release note: Create paged notes with handwriting, flowing text and PDF
annotations, browse records through thumbnails, and request AI comments with
an explicit text-only fallback. Existing notes migrate to local file storage;
backups now need both the database and notes directory.
Display native OpenCode and Continue checklists alongside scheduled tasks, preserving request ownership, explicit clears and saved progress. Bundle both remote runtimes and support managed Continue installation, model routing, cancellation and restart continuation.
Validation: real local and Linux remote model checks, full Electron remote Continue flows, typecheck and lint passed. Full suite: 4707 passed, 67 skipped, one OpenCode compaction failure passed targeted rerun.
Release note: Display native execution checklists above conversations and support managed remote Continue projects with saved progress and cancellation recovery.
Reuse unchanged task and activity state, preserve activity nodes across reordering, and isolate historical tool rendering. Add regression coverage for progress, terminal states, copying, and component reuse.
File-level snapshot also includes existing runtime checklist and remote Continue UI changes in the selected files. Their remaining dependencies are still uncommitted in the worktree; this commit is not a standalone validated build.
Validation on the combined worktree: typecheck and lint passed; full tests had one packaging timeout that passed separately. Real-model UI runs verified parallel child tasks, progress, details, and persistence with existing internal-network certificate trust unchanged.
Release note: Reduce unnecessary UI updates while subagents stream progress and preserve activity list state when records reorder.
Replace the crowded note sidebar with a card overview and full note detail. Keep tasks in a stable split view with source content and AI comments, compact header navigation, and search-adjacent status filters. Preserve drafts and return context.
Validation: 93 focused tests, typecheck, lint, and isolated Electron renderer checks passed. Full suite was interrupted; renderer probes used in-memory APIs.
Release note: Notes now open from a card overview, while todos keep a stable task list beside their details. Compact view and filter controls leave more room for reading and editing.
Preserve icon spacing in graph and document search fields against shared input styles. Update scheduled approval tests to expand the collapsed project task list before interacting with task approvals.
Release note: Knowledge search fields now keep the search icon clear of placeholder and entered text.
Collapse the project task list by default while retaining create and filter actions. Move the project name into the conversation statistics card and keep the running task count visible independently of list filters.
Validation: 60 sidebar tests, typecheck, and lint passed. The earlier full test run encountered an offline dependency package failure and timed out.
Release note: 项目任务默认收起，标题旁显示运行中任务数量；项目名称整合到当前会话统计卡片中。
Constrain nested subagent grids so long tool summaries cannot widen progress and final output beyond the card. Preserve text wrapping and local scrolling for code and tables, and extend the layout regression test.
Release note: Subagent progress and results now stay within the card width, keeping long text and tool status controls readable.
Show distinct WeChat, WeCom, and DingTalk marks in channel settings and the project dropdown. Bundle the SVGs locally and inherit the interface foreground color.
Release note: 远程通道设置和项目下拉列表统一使用微信、企业微信、钉钉各自的黑白品牌图标。
Wait for OpenCode session cancellation before reusing a conversation, and replace the session after unconfirmed cancellation. Preserve terminal message state when stale streaming snapshots arrive so finished conversations return to Send.
Validated with full production Electron UI and the configured real text model: queued requests complete, cancellation followed by immediate resend completes, and Stop clears. Focused tests: 362 passed; typecheck and targeted lint passed. Live dispatch counting limitations are recorded in the feature evidence.
Release note: Consecutive OpenCode requests no longer inherit a previous cancellation, and finished conversations no longer retain the Stop button after stale updates.
Move pin and whole-note deletion into hover and focus menus on note rows. Preserve editor drafts when operating on notes and reuse destructive confirmation with keyboard navigation.
Commit the eight affected files in full, including existing application-settings integration and UI design edits in those files. Validation was performed against the shared worktree; unrelated changes remain uncommitted.
Release note: 魔法笔记的置顶和删除移至列表项的更多菜单，与会话列表保持一致，并保留未保存的编辑内容。
Accept package-declared OpenCode, Node and koffi versions instead of desktop release pins. Preserve signature, hash, protocol and package-internal version consistency checks.
Validate both cached 0.11.18 packages and Linux x64 installation, bootstrap, health and stop. Related regression suite: 326 passed, 1 skipped; unrelated full-workspace check failures are recorded in the remote Host design.
Release note: Desktop updates no longer reject intact older Agent packages solely because their bundled runtime versions differ.
Claim idle conversation inputs before publishing queue changes so immediately dispatched messages do not briefly appear as pending. Preserve busy conversation queueing and add a regression assertion for notification ordering.
Validation: 369 focused tests, typecheck, and changed-file lint passed. Full-suite runs timed out with failures in other modules; repository lint reports errors in the existing story-graph demo.
Release note: Fix a brief pending-queue flash when sending a message while the agent is idle.
Raise note_search limit to 100 while preserving the default and output budget. Return scoped-tool argument validation failures as tool errors so models can correct and retry instead of receiving MCP internal errors.
Validation: 64 focused tests, typecheck and changed-file lint passed. Full tests timed out with two heartbeat migration failures; full lint reports unrelated story-graph demo errors.
Release note: 笔记搜索单次最多支持 100 条结果；内置 MCP 参数错误会返回明确提示，便于模型纠正后重试。
Task Center previously separated task approvals from their tasks and showed an empty approval section. Associated approvals now appear with allow-once and deny actions inside task cards, and those tasks appear under Active. Only unassociated approvals retain a separate section; no approval section or badge is shown when there are no pending requests.
Release note: Review and handle pending approvals directly in their Task Center cards. Tasks awaiting approval appear under Active, while requests without a matching task remain separately accessible.
Task Center previously split unbound tasks into a global scope and tasks needing attention into a separate filter. Keep Current project and All projects, label unbound tasks, and restore legacy global scope preferences as all-projects without changing task data.
Keep Active, Paused, and Finished filters. Active includes idle, queued, running, waiting_approval, failed, and interrupted tasks; task details and project-scoped approvals remain available.
Release note: Task Center now offers Current project or All projects and groups tasks needing attention under Active, while retaining project labels and approval actions.
Keep successful background conversations in project activity until their chat is visible and loaded. Track completion in memory for the current client session; initial history, failures and cancellations do not create completion notices.
Include whole-file companion changes already present in App and shared UI: preserve the workspace beneath Settings, show inline reply-copy feedback, and keep project settings inside the project menu. Include their component tests and documentation; navigation demo source changes remain unstaged.
Validation: 77 focused activity tests, typecheck and lint passed; Electron component fixtures passed 112 checks. Full suite: 4365 passed, 3 failed, 67 skipped (offline inventory timeout and two heartbeat migration failures). Commit-time staged whitespace check passed; tests were not rerun.
Release note: 后台会话完成后保留已完成提示，进入对应聊天后自动清除，避免错过任务结果。
Align remote ACP tool recovery with local runtime behavior when the model responds after a tool failure and completes normally. Preserve original errors and derive recovery state from committed remote events so reconnecting safely replays partial terminal events.
Validation: 461 focused tests, typecheck, lint, and shared Linux Host recovery scenarios passed. Full-suite validation has two pre-existing heartbeat migration fixture failures involving the pinned column.
Release note: 修复远端 Agent 在读取等工具失败后已正常回复，任务仍被误判为失败的问题，并修复断线重连时的工具状态恢复。
Keep the add button after the last tab in the scrollable strip. Show transparent floating scroll arrows on hover without reducing tab space, preserve keyboard and touch access, and reveal activated tabs.
Update tab interaction documentation and regression coverage. Exclude documentation demos from ESLint.
Validation: 66 focused tests, typecheck and lint passed. Full tests reported Agent package and runtime reuse failures before timeout; desktop visual verification remains pending.
Release note: Workbar tabs now keep the add button beside the last tab and reveal floating scroll arrows when hovering over an overflowing tab bar.
Links requesting a new window were silently blocked. Open them in managed browser tabs with the existing session restrictions, clean up script-closed tabs, and follow click-created tabs in subsequent direct and MCP browser tools.
Validation: 232 targeted tests and Windows Electron E2E passed; typecheck and lint passed. The full suite retains six failures outside the popup path.
Release note: Browser links that open a new page now open in a managed tab, and AI browser actions follow the new page after a click.
Persist conversation pins across restarts and show pinned conversations first, including older history. Anchor action menus above the list without shifting neighboring rows, with keyboard dismissal and sidebar-close cleanup.
Add schema 36 migration, focused regression coverage, and feature documentation. File-level staging also includes existing workbar styles and browser contract adjustments in shared files.
Validation: 145 backend tests and 237 App tests passed; typecheck and lint passed. Full test run timed out with Runtime and Agent package failures; native Electron visual validation remains pending.
Release note: 会话菜单新增置顶和取消置顶，重启后仍保留；操作菜单现在悬浮显示，不再挤动下方会话。
Derive application and default terminal titles from the current locale while preserving renamed and unmarked legacy terminal titles. Add locale-switch and layout-restoration regression coverage.
File-level scope also includes existing browser popup selection and close handling in the sidebar, its regression test, and workbar documentation updates.
Validation: 74 focused tests passed; typecheck and lint passed. Full test runs timed out with failures in settings navigation, Agent packaging, and database migration tests. Electron verification remains outstanding.
Release note: Workbar application and new default terminal titles now follow the interface language, including after restoring a layout; custom and legacy terminal names are preserved.
Load lightweight conversation summaries and hydrate full history only when
needed, preserving search, copy, export, queued requests, and remote questions.
Keep unchanged image reconciliation messages stable so list refreshes no
longer resend the entire saved history.
Prepare Desktop 0.13.6 with the approved bilingual notes and aligned feature
matrices. Agent remains 0.13.0; no LoongArch preview or navigation demo edits
are included. Development validation passed 4301 tests with 67 skipped;
the user requested CI validation instead of repeating local release checks.
Release note: 历史会话按需加载，减少切回应用时的重复保存和内存占用，同时保留完整历史、搜索与续聊。
Preserve the published English and Chinese README community QR-code updates. Desktop 0.13.5, Agent 0.13.0, approved bilingual release notes, and the validated product code remain unchanged.
Record the approved bilingual release notes and align Desktop and Agent version metadata. Refresh both feature lists with image tools, PPTX OCR, Runtime process reuse, and the completed/to-implement status convention.
Agent 0.13.0 requires Desktop 0.13.5. Keep Node 24.19.0 and OpenCode 1.18.29 unchanged, preserve published release history, and exclude the LoongArch preview.
Validation: bilingual release notes verified; 4293 tests passed and 67 skipped; typecheck, lint, version consistency, and 63 documentation links passed. No new real model calls, Host reruns, local production build, or packaging. Full UI-driven image invocation and local/remote switching are not covered by the existing validation records.
Image-only PPTX attachments failed with no indexable text even when a local
OCR model was configured. PPTX parsing now recognizes embedded PNG, JPEG
and WebP images through the existing local OCR path, preserves native text
and slide locators, and honors the selected parsing workflow.
OCR workers previously retained model sessions and WASM memory indefinitely
after successful parsing. Release the worker after 60 seconds with no active
or queued requests, reuse it for continuous work, and reload on demand.
Fast text/index modes still skip OCR. This does not render Office layouts,
recognize inherited master images, or change Agent execution permissions.
Validated four real PPTX attachments (40 pages), idle memory release and a
nine-page reimport after model reload on Windows x64 with PP-OCRv6 Tiny.
49 local OCR requests and zero text-model calls. All 4293 tests passed
with 67 skipped; typecheck, lint and the isolated Electron build passed.
Release note: 修复已配置本地 OCR 时图片型 PPTX 仍无法导入的问题，识别结果保留幻灯片定位。OCR 空闲 60 秒后自动释放模型运行内存，连续解析复用模型，下次使用时自动重新加载。
Record YAML application import/export, configurable market URLs, and future ShareServer distribution responsibilities. Define a local model management entry with managed-process and external-service boundaries; both remain planned capabilities.
Specify read-only OpenCode and Continue checklists above conversations, including remote Agent delivery and validation requirements. Record native runtime test evidence and distinguish planned work from implemented behavior.
Add model-controlled image invocation and read-only runtime assignments. Route image tools through Main so accepted operations retain their originating conversation when chat runtimes change, with saved references, cancellation, and manual recovery.
Keep Node hashing outside browser-shared contracts to restore production builds. Validation includes the production build, typecheck, lint, focused regressions, real Host transport checks, and two successful real image requests. Full UI-driven runtime switching acceptance remains documented as pending.
Release note: 开启图片模型的会话调用后，聊天助手可调用图片生成与编辑工具，Runtime 分配自动管理。图片成果保存在原会话，可继续修改，并独立显示生成状态和取消入口。
mesalogo