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.
Include cache reads and writes in the complete input denominator for OpenCode usage. Use the same calculation for stored records, summary totals, and renderer fallbacks so existing history is corrected without migration.
Add regressions for full cache hits, cache writes, mixed Runtime aggregation, and persisted conversation/system usage. Focused validation passed 41 tests; repository-wide checks were blocked by concurrent work-mode changes.
Release note: 修复 OpenCode 缓存命中率偏高或完全命中时显示为空的问题，已有用量记录在重新查询时按完整输入量计算。
The renderer no longer holds the whole history. Startup sends queued
changes, lets Main reconcile leftover pending/running records against the
stored tasks (same localized interruptedOnRestart line), then loads the
first page (200). The Activity page loads a full visible batch (500, as
before paging); "load more" shows the next batch and loads the next page
behind it; a filter switch refetches that filter's first page; leaving the
page trims to one batch. Counts, project/conversation groups, titles,
conversation status and the clear count come from activityHistory.summary
(refreshed on entry, by the page timer, the refresh button and after load
more / filter changes).
Records that are not loaded are still updated incrementally: the update
contract gains content-matched changes (upsert-call, update-request,
resolve-approval, settle-request, remove-request, remove-call) that Main
applies in SQL to shown rows; the store applies the same semantics to its
pages through the shared reference. update returns Main's stored call
records so a call whose earlier record was not loaded keeps one id. Task
refresh reconciles via Main SQL. Legacy localStorage records migrate as
incremental changes; the renderer no longer calls replace.
Tests: randomized sequences of every action, page loads, trims, flushes and
injected failures against the former full-list code on a real database;
first page <= 200 after startup; flush payload depends only on changed
records (including unloaded ones); ActivityPanel output with pages + summary
equals the full-list rendering for randomized datasets with duplicates;
restart interrupts leftover records with the same detail; clear empties the
database, pages and summary; SQL change semantics equal the reference.
Schema 57 rebuilds activity_history_records with order_seq (newer = larger;
a move to the front assigns a new maximum) and stored generated columns
(record_id, occurrence, status, status_group, kind, request_id,
conversation_id, project_id, created_at) with indexes. The order is migrated
from record_order_json exactly; legacy duplicates keep their occurrence and
only the first is shown. record_order_json is no longer written.
ActivityHistoryRepository owns the SQL: page({before, limit <= 500, filter,
projectId, conversationId}) newest first by index, summary() with the counts
and conversation titles/status the Activity page derived from the full list,
reconcile() joined with tasks with a renderer-localized detail line, update()
applied directly in SQL without reading the history, replace() for the
legacy migration, clear(). New activity-history:page/summary/reconcile IPC
with zod validation; page and summary run on the readonly worker.
perf:main measures 24,000 records: startup load 106 ms on Main (14 MB) ->
first page + summary 13.5 ms on the worker (0.6 ms loop block, 114 KB).
The renderer no longer sends the whole history on every change. Domain
actions on an external activity store update the list and queue the matching
contract changes; activity-sync.ts flushes them every 250 ms via
activityHistory.update (<= 20,000 per call), keeps failed changes queued in
order with backoff retry, and flushes on quit and unmount. replace remains
only for the legacy localStorage migration; clearing uses the new
activityHistory.clear IPC. App's activity state is gone; ActivityPanel reads
a selector. update is now required in the desktop API.
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.
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.
Also includes pending workspace changes: unsaved-change guard, keep-alive cache and live message store, knowledge workspace dialogs and perf driver updates.
Each source version is extracted once for every review scope; events carry spans and projects from their sources, and attention density is counted from messages. After publication, events are assigned to project features and sub-threads (cross-project stories only when enabled), with user rename, merge, remove, move and undo. The story graph gains a lazily loaded Three.js time-spiral view. Includes the 3D concept demo, real-data DeepSeek check scripts and docs.
Add an opt-in persistent frosted glass setting for the top bar and runtime checklist, with chat scrolling behind the header while preserving scroll anchors and window controls.
Retry transient local MCP initialization failures once after cleanup, include redacted connection diagnostics in feedback, and index lifecycle events to reduce execution statistics scans.
Release note: Add optional frosted glass appearance with chat visible behind the title bar; improve local tool connection recovery and diagnostic feedback.
Keep the notes list beside the open note, compact the detail view with a full-width sticky toolbar, and make Back to overview return to a full-width all-notes grid. Add manual note tags with AND filtering, a tag manager for rename, merge and delete, schema 51 tag tables, and tag support in the note Agent tools.
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.
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.
Keep cancellation and failure details in message status while preserving existing replies. Render cancellation neutrally, restore terminal metadata from history, and offer Edit again only when input can be restored.
Release note: Cancelled and failed requests show a single notice; cancellation no longer appears as an error, and Edit again accurately describes the recovery action.
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.
Sort pinned and unpinned conversations by their latest message creation time so parallel replies no longer repeatedly swap sidebar positions. Include the same timestamp in lightweight summaries while preserving updatedAt for persistence and snapshot merging.
Validation: 13 focused tests, typecheck and ESLint passed. The full test run timed out after ten minutes and reported configuration-summary and Agent offline-install failures.
Release note: Conversation order stays stable while replies stream or tools report progress; new messages still move conversations forward, with pinned conversations first.
Let users retain useful assistant replies or complete conversations without
leaving their chat workflow. Preview and edit captured text, choose an existing
note or atomically create a note with its first entry, and return to the source
conversation or message from saved records.
Add an application-scoped Notes workbar tab with title/body search and quick
text appends. Preserve drafts across conversation switches and guard closing,
replacement and disabling. Schema 48 stores optional source metadata without
rewriting file-backed bodies; source deletion retains the saved note. Older
clients cannot reopen an upgraded database without a pre-upgrade backup.
Release note: 可将助手回答或完整会话预览、编辑后加入魔法笔记，并从笔记返回原会话或消息。右侧快速笔记支持搜索和追加文字，切换会话保留草稿；采集本身不调用模型，保存后自动评论仍遵循已有设置。
Validation: isolated HEAD-based candidate passed 22 files / 930 focused tests,
plus 20 gateway tests after including its create-result fixture adjustment.
Real Electron App/preload/IPC/SQLite acceptance passed for all 502 historical
messages, exact-entry/source navigation, native keyboard input in a 214px
panel, reopen and source-deletion retention, with zero capture model calls.
Repository lint and web TypeScript passed. Cached whitespace and secret-pattern
checks passed; native-client changes and unrelated IPC extraction are excluded.
Validation limits: the isolated source tree reuses installed node_modules,
where a parallel task upgraded DSH from the committed 0.1.2-rc.1 to 0.1.7-rc.2.
Full typecheck reports 14 DSH errors in three unchanged files; the full-suite
attempt with --bail=1 also fails in deepseek-harness-host.test.ts. These are not
all-green repository or release-package results. Earlier execution-time full
suite failures and fixture repairs remain recorded in the feature progress doc.
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.
Ordinary database schema upgrades previously ran VACUUM on free pages and
showed misleading history-cleanup progress. Separate structure upgrades from
required legacy conversions, retaining reclamation intent only for retries
within the same startup. Preserve released data without new schema versions
or persistent migration markers; Agent and normal writes remain unchanged.
Add real SQLite and Worker regressions, bilingual operation-specific startup
copy, and migration documentation. Synchronize native Electron drag input
with actual resize state without weakening layout assertions.
Validation: 47 focused migration tests passed; typecheck, lint and diff checks
passed. Final full suite: 5137 passed, 74 skipped, 2 unrelated Electron failures.
Both failing Electron tests passed an isolated rerun; full CI remains unverified.
Release note: 修复普通数据库结构升级再次整理历史和回收空间的问题；仅在需要转换旧数据时执行相关处理，启动页准确显示当前升级操作。
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。
Derive attachment presence from saved queue inputs and only show the preview action when attachments exist. Cover queue metadata and button visibility with regression tests.
Release note: Queued messages without attachments no longer show the View attachments button.
Reuse the last committed activity records when comparing streaming saves instead of reading the full history for every update. Invalidate comparisons on close, data clearing and commits from other SQLite connections; preserve rollback and retry behavior.
Validation: 3 related test files / 121 tests passed; typecheck and lint passed. Ten consecutive saves now perform at most one full-history scan while preserving the WAL write reduction. Installed-app physical disk throughput remains unverified.
Release note: Reduce repeated database reads while streaming activity updates in conversations with large activity histories.
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.
Save only changed activity records instead of rewriting the entire history snapshot. Migrate existing history to schema 44 while preserving order and duplicate IDs.
Run unit tests with up to four workers and keep the configured integration phase serial. Include activity-history I/O, storage-upgrade, settings, and OpenCode isolation regression coverage.
Validation: 4 related test files / 123 tests passed; typecheck and lint passed.
Release note: Reduce disk writes while agent activity updates stream in, preserving existing activity history.
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。
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。
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.
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。
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。
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。
mesalogo