Return ordinary tool exceptions as paired error results so the model can decide how to recover. Preserve cancellation, existing recovery guidance, and failed tool activities without adding automatic retries or retry limits.
Validate all three text protocols with real process execution and cover bounded errors and cancellation. Focused tests: 161 passed, 1 skipped; typecheck and lint passed. Full suite: 6230 passed, 87 skipped, 1 Obsidian temporary-directory assertion failed.
Release note: Direct-model conversations can continue after a tool fails, allowing the model to use the reported error to choose its next step.
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。
Review history and context were split across recap and graph views, while the story spiral rendered saved event intervals in a single neutral color. Share the history picker and context bar, collapse new-review inputs, improve recap and responsive detail layouts, and align graph toolbars and accessible legends.
Color actual event intervals and markers by primary story, preserve neutral gaps and unassigned events, and refresh colors across themes. Include related regression coverage, layout fixtures, overlay timing and workspace-import test adjustments, and updated design and validation documentation.
Release note: Work review and story graph now share the selected review and a compact history picker. Recaps and graph details fit smaller windows, and the time spiral uses story colors for recorded event intervals without filling gaps.
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。
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。
HTTP OCR failures in PPTX parsing were incorrectly labeled as local OCR failures. Report the selected provider and slide/image location, and retain bounded structured server diagnostics with configured-key redaction and log IDs. Preserve existing fallback behavior.
Validation: 38 focused tests, typecheck and lint passed. Full test run timed out after 200 seconds. Synthetic service probes reproduced HTTP 500; the server-side failure remains unresolved.
Release note: PPTX parsing warnings now identify the actual OCR provider and failed image location, with server diagnostics for troubleshooting.
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.
Main module evaluation drops from ~420 ms to ~330 ms. Types stay as import type; the DeepSeek Harness chunks stay static because the protocol chunk shares code with Main startup paths.
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.
Pause scroll writes while the jump-to-bottom smooth scroll runs; keep rows with pending questions, approvals, recent interactions and selection ends mounted; cache Mermaid results; copy text spanning unmounted rows; anchor the sidebar on id changes; disable native overflow-anchor for windowed lists; write terminal output on the leading edge and before clear; forward remote events every 16 ms; flush streaming text before copy/export; add performance principle P10 (no UX regressions).
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.
Leaf batches retry at half and a quarter of the text budget, navigation merges retry once; provider errors are not retried. Adds the long-session acceptance script and records the results.
Search matches query terms (CJK pairs) instead of only the whole phrase, previews show readable fields first, and the tool description says when to call it and when to stop.
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。
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.
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.
Expose save_image across direct model, MCP gateway, DeepSeek Harness and remote Agents (written on the remote host via chunked reads), and show the image MCP tool list in settings.
Scroll settings controls into the unobscured area below the measured sticky header, retaining native interaction and hit-testing assertions. Give the full legacy outbox migration fixture a scoped 15-second timeout. Product code and bilingual release notes are unchanged; validation remains in CI.
- Segment streaming Markdown so completed blocks are reused and only the growing tail is re-parsed; fall back to whole-document parsing for document-wide constructs
- Memoize conversation sidebar rows and cache per-conversation derived activity, ordering and pending approvals
- Activity page loads on entry, refreshes every 15 s while visible, and has a single header refresh button
- Include pending settings, model download source, device sharing and knowledge gateway changes in the working tree
- Add Electron streaming input benchmark and regression tests
Check detail navigation focus before the auto-focused creation input takes over. Preserve return-to-list and reading-position assertions, and include the reviewed sharing first-read test and independent validation record. Validation runs in CI per user request.
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.
Use gbd-/gbc- prefixes with a 6-char conversation hash instead of 20-char per-request hashes, lease per-conversation slots so parallel requests never share a name, and expose gateway custom tools as <server hash>_<name> within the 64-char provider limit.
mesalogo