Main no longer opens desktop business SQLite. A single utility-process
storage owner holds the Assistant, Knowledge, attachment, document-result,
remote-binding and native model-ledger databases and runs whole domain
transactions; Main and Runtime callers use explicit async domain operations.
- Remove the Main readWithFallback path and the supervision worker's
separate business write connection; manifests are scanned read-only and
committed by the sole writer.
- Remote events are ACKed only after commit; process loss reports
unconfirmed writes instead of replaying them.
- Use native utilityProcess messaging with one in-flight bound (32) and
ordered waiting instead of capacity rejection and retries.
- Start the storage process before the window so startup overlaps.
- Keep short tool output in memory and store full output once in owned
storage; paging, branching, restart and deletion reuse that copy.
- Put required runtime launch files under goodbuddy-prefixed owned temp
directories and reclaim confirmed stale ones; stop writing duplicate
parsed.md.
- Add lint guards for SQLite ownership and architecture, concurrency
acceptance fixtures, and maintenance/architecture documentation.
Validation: typecheck and lint pass. Alternating baseline (edf019aa) vs
candidate runs show no regression on single-session, C01, C02, C04 and a
5-minute C06; Main p99 drops from ~21 ms to ~16.7 ms under concurrency.
Fresh portable copy (1.75M events) upgrade content unchanged; real-model
output paging passes with 4 external requests. Full npm test runs had
1-9 different timing-sensitive failures per run that pass when rerun.
Not covered: C03 review publication, C07 source body, app-level C05.
Load Supervisor graphs only when opened, preserve source details on demand, reuse indexed story digests and window selection lists without losing keyboard or focus behavior. Route heavy UI reads through the existing worker, batch scoped queries and construct each publication snapshot once.
Keep remote cancellation responsive during model-route cleanup, remove late routes and retain reported usage after response-cap cancellation. Preserve Telegram pending replies through polling conflicts, show delivery errors and honor the final rate-limit cooldown.
Schema 62 adds lookup indexes without rewriting user content; older clients cannot open upgraded data. Large review publication still blocks Main and remains documented follow-up work. Record the future storage-service direction without performing the architecture migration.
Validation: exact staged code passed isolated full tests (6212 passed, 87 skipped), typecheck and lint. Three-round source performance comparisons, SQLite migration equivalence, native Electron interaction checks and current-source Linux x64 Host validation completed; eight external text-model requests.
Release note: Supervisor opens reviews without loading the entire graph, keeps long selection lists responsive and preserves details and keyboard navigation. Remote cancellation and Telegram reply recovery are more reliable; remote fixes require an Agent build containing this change.
Keep remote startup cancellable without blocking other sessions and surface local OpenCode submission failures promptly. Preserve supervisor project isolation, pause behavior and valid story destinations.
Restore generated-image channel delivery, Telegram reconnection on unchanged Save and DingTalk business-error retries. Preserve virtualized message disclosures using sparse state and release stale supervisor UI requests.
Add production-path regressions, Electron checks, isolated SQLite validation and audit evidence. Fix the SDK cleanup test fixture lifetime under garbage collection without weakening its assertions.
Validation: 6136 tests passed, 87 skipped; typecheck, lint and diff checks passed. Seven real text-model calls, current-source Linux x64 Host scenarios and large-history Electron comparisons completed.
Release note: Fix stuck runtime requests, inconsistent review results and channel delivery failures, and retain expanded details while browsing long conversations. Remote runtime fixes require an Agent build containing these changes.
Connect a user-created Telegram bot to channel projects with encrypted credentials, numeric sender allowlists, unified execution and text replies. Use Electron networking for system proxy support, with polling recovery, cancellable delivery retries and live status updates.
Add schema 61 channel support, lifecycle regression tests, Electron integration probes and feature documentation. Require the performance principles in AGENTS.md and record three alternating baseline/current Main benchmark rounds.
Validation: typecheck, lint and diff checks passed. Full suite: 6087 passed, 87 skipped, one intermittent inline-help Electron failure that passed unchanged in isolation. Real Bot plus model acceptance remains pending; the local TLS proxy probe is opt-in.
Release note: 新增 Telegram 私聊通道，可配置 Bot Token 和用户白名单，通过通道项目处理文字请求并回复结果。支持系统代理、断线重连和停用取消；真实 Bot 与模型的完整联调仍待完成。
Share review history selection between overview and graph while preserving explicit navigation and stale-response guards. Return attention for the selected review scope and interval, and align spiral events and time with that review.
Normalize radii from message rates, including partial turns, without lifting quiet turns toward peaks. Preserve one continuous helix, uniform time height, round turn sections, and smooth transitions; equal densities retain equal radii. Document current-message and hourly-bucket limitations.
Validation: 51 focused unit tests, 2 production IPC tests, Electron DOM and geometry checks, Node/Agent/Web typecheck, targeted ESLint, and diff checks passed.
Release note: Story graphs now offer synchronized review history selection, and spiral radii reflect recorded message density within the selected review.
Remove Ask/Execute modes and general product tool approvals so requests use the selected runtime, enabled capabilities, and execution account permissions. Migrate retired application metadata while preserving user content.
Retire the Results page while retaining conversation images and stored artifacts. Add local and remote workspace file imports, timestamps and sorting, improve image discovery and saving, and refine workspace navigation and supervision responsiveness. Include the accompanying web-search changes, tests, probes, and product documentation.
Remote imports require an updated Agent. Existing artifacts are not automatically copied into project directories. Validation evidence and outstanding failures remain documented in feature progress files; no full test suite or real-model calls were rerun for this commit.
Release note: Run requests without switching work modes, import files into a selected local or remote workspace folder, sort workspace files by date, and keep using conversation images after removal of the Results page.
Require a root folder in the local project creation dialog and IPC while preserving updates to historical projects with blank paths. Show remote symlinks whose targets are directories and resolve their canonical paths when browsing.
Validation: focused UI, contract, IPC and SSH tests passed; typecheck and lint passed. Verified directory links on the shared Linux Host. Full test run timed out after a Magic Notes storage timing failure.
Release note: 新建本地项目必须选择目录；远程项目选择目录时可查看并进入指向目录的符号链接。
Add a supervisor text-model selector using existing connections and a per-conversation story graph switch above knowledge settings. Hide the switch when Supervisor is disabled and enforce conversation preferences at local and remote tool execution boundaries.
Release note: Choose a dedicated supervisor model and control whether each conversation can query existing stories and experiences. Enabling graph access does not start a review or automatically insert context.
Runtime creation, MCP launches, Obsidian, native clients and the tool-environment IPC await the initialization promise instead of startup awaiting it before the window path. A failure still fails startup with the same diagnostic.
conversations:list-summaries and conversations:get run on the readonly query worker. Activity history replace validates and serializes only changed records; a new activity-history:update IPC writes one record. Adds npm run perf:main.
Remote semantic events were written with one or two synchronous SQLite transactions each before being forwarded; recoverable conversations also rewrote the whole assistant message per event. Events now commit together at each remote checkpoint (before the Agent can acknowledge), and before non-remote, question and terminal events, on a size cap or a 50 ms timer. Only newly stored events are forwarded, in order; a failed batch rolls back and blocks later commits. Applies to interactive, background and recovery runs.
Configuration apply previously required a separate native confirmation even in Agent Runtime Execute mode, and failed in clients without an approval callback. Use existing work-mode and tool authorization instead, preserving Ask read-only access and request-scoped plan validation. Update regression tests, tool descriptions and documentation.
Validation: 267 focused tests passed; typecheck and changed-file lint passed. Full tests timed out with failures in other modules; repository lint reported errors in unchanged files.
Release note: Execute 模式下通过 Agent Runtime 修改 GoodBuddy 配置不再额外弹出确认框，Ask 模式仍保持只读。
Isolate Obsidian tests from the default browser capability, check the additional image-tool card, and center native overlay click targets below the frosted header. Retain existing permissions, identity, hit-testing and keyboard assertions; preserve unrelated uncommitted work.
Heartbeat no longer writes its own report; it triggers the shared incremental review and, per plan intervention, derives evidence-backed suggestions from the review's graph changes. Manual review is incremental by default with explicit reanalysis. The Supervisor tab is renamed Smart heartbeat with heartbeat plans, and the redundant inner plan frame is removed.
- Store runtime selection as { provider?, model? } layers and resolve them per
field (conversation -> project -> global); drop the legacy auto provider.
- Migrate stored selections (database v49) and clear deleted profile ids.
- Re-resolve selections in Main per request and at queue dispatch.
- Add ProjectRuntimeSelector and a two-column RuntimeModelPicker; manage
link opens model connections; restore per-runtime default model tabs.
- Stop duplicating trusted instructions and history across OpenCode,
Continue and DeepSeek Harness runtimes.
- Document the layered design, global provider removal plan and planned
purpose-specific models.
Add a System tasks tab to run history that splits background usage (supervisor, auto-supervision, magic notes, knowledge base, delegation) from conversation usage, with a manual refresh button and automatic refresh when usage is recorded. Record previously dropped usage from supervisor reviews, image regeneration, knowledge graph extraction, and remote embeddings.
Local direct-model text conversations could not use manual context compaction,
and disabling automatic compression prevented saved summaries from being reused.
Restore the composer action regardless of the automatic setting or threshold,
use the selected summary connection, and persist summaries for subsequent
requests while retaining recent turns and full conversation history.
Image connections, remote channel conversations, and SSH projects remain outside
the local direct-model compaction workflow. Add focused regressions, a local
Electron end-to-end test, and an opt-in two-request live probe.
Validation: staged snapshot passed typecheck, changed-file ESLint, 13 focused
tests, and the Electron end-to-end test with two local HTTP fixture requests.
No additional real-model calls were made during commit verification.
Release note: 修复本地直连文本模型无法手动压缩上下文的问题。现在关闭自动压缩或尚未达到触发阈值时，也可点击“压缩上下文”；摘要会随会话保存并用于后续对话，同时保留最近轮次和完整历史。
Remove the fixed gateway capability lifetime so active requests retain knowledge, notes, browser, configuration, and custom MCP access. Preserve token validation and request cancellation or cleanup revocation, and replace the misleading knowledge expiry error with a tool authorization error.
Remove native-client clock overrides and cover long-running scoped and HTTP MCP calls. Validation: 34 focused tests passed; changed-file lint passed. Repository typecheck and lint remain blocked by unrelated manual-compaction and sidebar probe files.
Release note: Long-running Agent requests no longer lose tool access after ten minutes, including when the knowledge-base switch is off. Request cancellation and completion still revoke access.
Avoid hidden activity renders, no-op message saves and attachment scans when pinning conversations. Reuse note body inspection and skip unchanged attachment reference writes while preserving recovery and cleanup behavior.
Skip unnecessary Markdown normalization and memoize subagent lookups without delaying live rich text. Add storage operation counts and real Electron rendering equivalence benchmarks; full-render speedup remains unproven.
Validation: 5397 tests passed, 84 skipped; typecheck passed. Lint passed excluding two existing untracked sidebar probe files.
Release note: Reduce repeated rendering and disk work during chat, conversation pinning and note startup while preserving existing content and interactions.
Expose saved decisions, timelines and source evidence through read-only Story Graph tools across Model, Harness and local/remote OpenCode and Continue. Supervisor enablement and runtime assignments govern discovery and calls; reads do not invoke models or modify stored evidence. Remote use requires matching Desktop and Agent changes.
Make Continue discussion show the complete editable message with a separated destination and shared action layout. Sending uses the visible draft without reattaching removed context.
Validation: existing focused MCP, runtime, controlled Linux Host, discussion component and Electron layout checks plus typechecks; staged diff check passed. Cross-scope fact reuse, historical reconstruction and full package acceptance remain deferred.
Release note: Agents can consult saved supervisor decisions and their sources when continuing work. Continue discussion now lets you review and edit the complete message before sending.
Let users continue discussions without opening sources first, edit a question, and send source-linked review context to the target conversation. Add explicit conversation navigation and remove redundant context disclosure and entity-writeback controls. Hide empty automatic supervision metrics until activity exists.
Release note: Continue work directly from supervision feedback or graph sources with relevant context, fewer controls, and clearer automatic supervision empty states.
Add a default-on persisted desktop notification switch that takes effect immediately for background task results while leaving in-app notifications unchanged. Group General settings into shortcut, conversation and notification, and workspace and download cards.
Validation: 756 related tests passed, 1 skipped; typecheck and lint passed. Full suite timed out with three supervision preview failures; native OS notification delivery was not manually verified.
Release note: 通用设置新增默认开启的桌面通知开关，可随时关闭系统任务提醒并保留应用内提示；设置项按用途分组，方便查找。
Resolve 15 shared-control, overlay and responsive-layout issues plus the MCP editor being hidden behind settings. Restore theme contrast, danger and disabled states, visible keyboard focus, and consistent Continue fields. Keep the workbar add button reachable and model protocol values readable in narrow containers.
Make nested MCP and image dialogs usable above their parents with focus restoration, keep project Escape handling within the active modal, release native browser views for overlapping help, and restore keyboard access and Escape in sandboxed HTML previews without relaxing sandbox permissions. Add unit and real Electron regression coverage and update design and validation documentation.
Release note: 修复深浅主题下控件边框、危险操作、禁用状态和键盘焦点显示不一致的问题。MCP 编辑器与图片预览可在父弹窗上正常操作，HTML 全屏预览支持键盘进入和 Escape 返回；窄工作栏的添加按钮保持可用，模型连接协议文字完整可读。
Validation: the full suite recorded 5309 passed, 3 failed and 83 skipped. The ProjectSwitcher initial-focus regression was then fixed, and App, ProjectSwitcher and overlay Electron tests passed all 331 cases. The other two HeartbeatCenter failures were reproduced on isolated HEAD 11facf0 and remain pre-existing. Typecheck and lint passed after the fix; staged whitespace checks passed. The full suite was not rerun after the focused fix.
Limits: Electron evidence is from Windows development runs, with fixtures for unrelated services and native occlusion throttling disabled in some drivers. No production build, packaging, macOS/Linux, remote Agent host or external MCP connection validation; skipped tests and the documented scaling and native-select coverage gaps remain.
Add composer shortcuts for local Continue and OpenCode terminals and the official DeepSeek Harness Web client, using the current project and model bridge. Manage browser service reuse, stop actions and terminal cleanup. Upgrade DeepSeek Harness to 0.1.7-rc.2 and Cordis to 4.0.4.
Include the coordinated IPC handler extraction and related tests and documentation. Remote native-client coordinator wiring, managed Node consolidation, Ask MCP mappings and full desktop/package acceptance remain unfinished; this commit records the implemented local workflow and supporting SSH groundwork.
Validation: typecheck and lint passed; 267 focused tests passed and 5 skipped. No new real-provider calls were made for this commit. Prior real-model evidence and remaining acceptance work are documented in the feature progress files.
Release note: 本地项目选择 Continue 或 OpenCode 后，可从输入框下方打开原生终端；选择 DS 后，可打开使用当前项目和模型的官方 Web 客户端。客户端使用独立会话，DS 网页关闭后服务继续运行，可在 GoodBuddy 中停止；远程入口尚未完成。
Users can now read, search, and update existing local Obsidian notes through
built-in tools without configuring an external MCP server or Obsidian plugin.
Add vault discovery, an optional folder scope, and independent test, save,
enablement, and runtime assignment controls in MCP settings.
Bundle MCPVault 0.16.0 and its runtime dependencies, exposing 19 shared tools
to direct models and managed local OpenCode and Continue conversations.
Obsidian is disabled by default. Ask remains read-only; Execute permits
writes. Scope and assignment changes revoke existing Obsidian grants.
DeepSeek Harness and remote execution remain unsupported.
Validate the isolated staged snapshot with its own dependency installation:
typecheck, lint, production build, and 540 tests across 14 files passed.
No paid model calls were repeated. Physical-offline, installer, and other
platform acceptance remain pending as documented in the feature record.
Release note: Connect local Obsidian vaults in MCP settings to find notes and
write conversation results back to them. Test all registered vaults or a
chosen folder before enabling access; no Obsidian plugin is required.
Allow only one active review across manual starts, automatic runs and resume. Add cancellation that holds admission through runtime cleanup, preserves saved batches and prevents cancelled runs from resuming.
Keep review controls usable during execution, show a dismissible progress notice and remove redundant filter labels. Include focused regressions and lifecycle documentation.
Release note: Supervision reviews can now be cancelled from Activity records. Starting another review shows the active review instead of duplicating work, while scope, time and refresh controls remain available.
Replace truncated review input with paged, resumable batches and retain extracted facts and source references through navigation summaries. Expose concurrency, timeouts, batch budgets and response capacity in supervisor settings.
Separate automatic supervision from review results, activity and settings; use a standard plan modal and show execution stages with saved batch details. Fix historical entity identity mapping, navigation output validation and arbitrary summary length failures.
Include focused regressions, isolated real-data validation scripts and updated design and verification records. Overall layout acceptance remains outstanding; this commit does not claim that all visual issues are resolved.
Release note: 监督回顾支持完整分页、分批保存和暂停后继续，可配置并发、超时及响应容量；修复实体引用、汇总校验和长摘要报错，并重新组织自动监督与活动记录入口。
Address Desktop CI 35849362694 failures with isolated OpenCode config dependencies, cleared IPC lookup counts, Supervisor default-off expectations, and polling-safe UI fixtures and timeouts.
Record the failed candidate CI and follow-up validation: 14 focused tests, typecheck, and lint passed. Product code, versions, and bilingual release notes are unchanged. The revised candidate requires approval and successful main-branch CI before tagging.
Complete the pending Supervisor changes with opt-in execution, incremental automatic reviews, and activity history. Preserve saved preferences and plans, skip model calls for unchanged input, and keep full replay and cancellation limitations explicit.
Update both release versions, bilingual notes, feature matrices, migration fixtures, and validation evidence. Clear stale browser errors after a successful close retry. Focused validation passed 690 tests across 35 files, plus notes verification, typecheck, and lint; full CI and native release acceptance remain pending. No local production build or packaging was run.
Release note: Enable Supervisor to review work, trace story graphs, and inspect manual or automatic activity without repeating model calls for unchanged input. Desktop 0.13.12 and Agent 0.13.3 also prepare idle remote Runtime cleanup and retirement of replaced Agents; update Desktop before the Host environment. Database upgrades require a pre-upgrade backup for rollback.
Remote tasks could leave idle Runtime processes behind, and replaced Agent
installations lacked a drain-and-exit lifecycle. Keep the current Agent
resident, let displaced Agents finish existing work and reconnect for its
results, then retire them without restarting obsolete installations.
Reclaim Runtime processes when their last active task finishes, preserve
pending questions and shared active tasks, and restore conversation history
when the next turn starts. Remove the Remote Projects technical preview label
from settings, errors, tests, and current documentation; the feature remains
disabled by default.
Validation recorded during implementation: 213 lifecycle tests and 28 focused
UI/IPC tests passed, as did SettingsPanel and lint. Linux x64 real-Host checks
used 8 provider requests. Broader tests and final typecheck encountered
unrelated concurrent changes; details and coverage limits are documented.
Release note: 远程任务结束后自动释放空闲运行进程，下一轮对话恢复历史；更新后的旧 Agent 等待已有任务完成再退出，当前 Agent 保持常驻。远程项目移除“技术预览”标识，仍默认关闭。
Extend the existing heartbeat workspace with scoped work reviews, result-specific story graphs, source inspection, and pinned conversation or task feedback. Connect confirmed continuation and local knowledge entity previews through the desktop APIs, and preserve result history and user corrections in schema 43.
Include focused regression tests, an isolated visual fixture, and implementation evidence. Full event-by-event replay, Experiment targets, no-change handling, and cancellation remain incomplete; this commit does not claim complete feature acceptance. Existing automatic plans remain active when the application entry is disabled.
Release note: Review work progress in the Supervisor workspace, trace graph events to saved sources, and open a matching review from pinned conversation or task feedback.
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。
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.
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.
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。
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。
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。
Multiple projects could spawn duplicate heavyweight runtimes, while settings
changes and remote reconnection could cancel or strand native conversations.
Share compatible local OpenCode and DeepSeek Harness process owners and
Agent-owned ACP connections, retaining workspace routing, per-session modes,
model attribution, question ownership, targeted cancellation and idle cleanup.
Restore remote pending questions and terminal task projections across reconnect
and desktop restart, and preserve accepted ordinary requests during settings
replacement while cancelling expert-team parents with their replaced scheduler.
Extend regression coverage and Agent type checks. Record measured resource and
real-model validation results, including failures and limitations.
Also include the conversation media-generation design drafts (not an implemented
feature), documentation entry links and dedicated Linux test-directory guidance.
Desktop and Agent changes must be delivered together for shared process results.
Validation: typecheck and lint passed; staged content and documentation links
checked. Prior full regression and live-model evidence are recorded in progress
notes; no new full test suite or model calls were run for this commit.
Release note: 多项目会话现在复用兼容的 OpenCode 和 DeepSeek Harness 进程，减少重复启动并保持工作区、工具和取消隔离。修复远端问答在断线、重启及配置更新后的恢复与状态同步问题，Desktop 与 Agent 需配套更新。
Copied local files previously required the attachment picker. The chat
composer now imports one or more supported files directly from paste,
sharing parsing progress, limits, and batch rollback with file selection.
Text and screenshot paste remain available, and failures preserve drafts.
Validation: prior 166 focused tests, typecheck, and lint passed; 28 targeted
tests passed again before commit. The prior full suite had 4214 passes,
67 skips, and 6 window-recovery failures; window tests passed 10/10 alone.
Native clipboard behavior was verified on Windows; macOS/Linux remain unverified.
Release note: 现在可在文件管理器中复制一个或多个支持的本地文件，直接粘贴到聊天输入框添加附件；可查看读取和解析进度，失败时保留草稿与已有附件。
Remove code with no production path: the probeStatus value 'healthy' that no
probe can produce, the external.transportConfirm string and the
remote-missing and config-invalid state strings that nothing renders,
KnowledgeService.searchHybridMany which lost its last caller when chat search
moved to retrieveMany, and the sourceUrl field that no provider parser
populates.
Keep sourceUrl in externalKnowledgeLocatorSchema because that schema parses
already-persisted citations. Point the affected fixtures at catalog-ready,
the status testInstance actually writes.
Document why ProjectActivity adjusts state during render: the guarded call is
the recommended pattern for resetting state on prop changes here, and the
repository lint rule rejects the useEffect alternative.
Connect Dify, FastGPT and RAGFlow through read-only bindings, encrypted local credentials, shared retrieval and persistent citations. Configuration and removal affect GoodBuddy only.
Show active conversations across projects, retain older live work, and improve project dialog scrolling. Queue concurrent questions and route managed SSH OpenCode questions through the Agent. Preserve recoverable read/search errors and partial search results.
Document the Electron UI automation standard, real model and external knowledge validation, and remaining acceptance limits.
Validation: earlier full regression passed 4081 tests with 66 skipped; subsequent focused remote-question checks and real Linux evidence are recorded in feature progress. Precommit typecheck and lint passed; latest project dialog and shared UI suites passed 58 tests. The full suite was not rerun for the final dialog changes.
Release note: Use external knowledge in conversations, find active work across projects, and answer concurrent local or managed SSH OpenCode questions. Managed SSH questions require the updated Agent adapter.
Allow users to close leased browser tabs without cancelling the AI request or revoking its other tools. Closed-page operations report a recoverable error; explicit navigation creates a dedicated replacement tab for direct-model and MCP calls.
Add regression coverage and real Electron lifecycle checks, and update browser behavior documentation.
Release note: 浏览器标签页被 AI 请求占用时也可关闭，其他任务继续运行；再次导航会打开独立新页。
Image requests previously sent only the current prompt and attachments, so
follow-up edits could lose the previous image and conversation requirements.
Reuse the latest successful image from the existing artifact store together
with text history, including after reopening the app. Explicit attachments
take priority, and configured model IDs remain unchanged.
When image editing is explicitly unsupported, continue with text-based image
generation and retain a quiet message footer explaining the missing image
context. Keep genuine provider errors and cancellation visible. Add focused
regressions, persisted footer metadata, and aligned feature documentation.
Validated with four real sub-gpt-image-2 image requests and a simulated
unsupported-edit response. Image regressions, typecheck and lint passed;
the full working-tree run had two unrelated concurrent Runtime-menu failures.
Release note: 连续改图会自动带上上一张图片和文字上下文，重开对话后仍可继续修改。上游明确不支持编辑时仍可按文字生图，仅在回复底部轻提示未使用参考图片。
mesalogo