Reviews now snapshot only messages in a terminal state (complete or error) and finished tasks, so a reply still streaming when the review starts waits for the next review instead of changing under it. A frozen source that still changes is skipped for that run and left for the next review, replacing the re-review at the latest version and its 200-source cap. The review period picker gains an All time option.
Show the selected role as a compact chip in the input's top-left corner, persist the choice per conversation, and snapshot it on replies so the timeline shows the role as a caption under GoodBuddy.
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.
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.
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.
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.
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.
The real Linux Host reproduced Escape being sent to the collapsed workbar
trigger after resize. Wait for the narrow viewport, open the workbar through
its existing control, and confirm the append field owns focus before input.
Keep the migration fixture and all IO assertions, with a 15-second allowance
for its 10000-record scenario. Product behavior and approved notes are unchanged.
Validation: real Linux Host full suite 5345 passed, 51 skipped; Windows focused
3 passed; complete typecheck, lint, and release-note verification passed.
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。
Remove elapsed execution-budget pauses from extraction and navigation so long reviews no longer require repeated manual continuation. Remove the pause-duration setting and update activity copy and design documentation. Preserve explicit pause, saved batches, model timeouts and concurrency limits.
Validation: recorded 13 focused tests, typecheck and targeted ESLint passed; staged diff check passed. Tests were not rerun for this commit.
Release note: 监督回顾现在持续分批处理至完成，不再每隔固定时长自动暂停；仍可主动暂停并从已保存进度继续。
mesalogo