* 🗃️ db(database): add workspace_id FK constraints (migration 0107)
Phase 2 of workspace_id rollout: add the FK constraint on the 70 tables
that gained a bare `workspace_id` column in Phase 1 (0106), referencing
workspaces(id) ON DELETE CASCADE.
- schema: add `.references(() => workspaces.id, { onDelete: 'cascade' })`
to all 70 nullable workspace_id columns
- 0107_add_workspace_id_fk.sql: idempotent drizzle migration
(DROP CONSTRAINT IF EXISTS + ADD), runs in CI / dev / self-host
- 0107_concurrent.sql: production-safe out-of-band runbook
(NOT VALID + VALIDATE) to avoid write-blocking locks on large tables;
NOT run by drizzle
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* 🔥 db(database): remove stray 0107_concurrent migration file
* 🐛 fix(database): break user/workspace schema circular dependency
Move userInstalledPlugins from user.ts into connector.ts to break the
user.ts <-> workspace.ts import cycle flagged by dpdm. connector.ts
already imports both users and workspaces, and consumers import the
table from the schemas barrel, so no call sites change.
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* ♻️ refactor(message): prefer dedicated usage column over metadata.usage
Token usage was promoted out of metadata.usage into a dedicated messages.usage
column, but nothing populated it and all reads still went through metadata.usage.
- Centralize write-side promotion in the DB model (update / updateMetadata /
create), so all executor callers populate the usage column from a top-level
usage payload, falling back to metadata.usage. metadata.usage stays dual-written
for backward-compatible reads.
- Reads prefer the usage column and fall back to metadata.usage: message queries,
getTokenHeatmaps, recomputeTopicUsage, the usage record service, and context
token accounting.
- Add top-level usage to UpdateMessageParams + DBMessageItem types.
- Mark metadata.usage and the legacy flat token fields as @deprecated, pointing
to the top-level usage field.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* 🐛 fix(message): dual-write metadata.usage for top-level usage updates
When a caller passed the new top-level `usage` param without also sending
`metadata.usage`, the update wrote only `messages.usage` and left
`metadata.usage` stale/absent — legacy readers and rollback paths still consume
it during the dual-write transition. Fold the resolved usage into the metadata
patch so `metadata.usage` stays in sync regardless of how usage was passed.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* 🗃️ feat(database): add workspace_id columns to existing tables
Add a nullable `workspace_id text` column to user-owned business tables
(agents, sessions, topics, messages, files, tasks, RAG/eval, RBAC, devices,
connectors, etc.) so records can later be scoped to a workspace. Workspace
tables themselves already landed on canary via 0105_add_usage_agent_share_workspace.
Also folds in the additive device schema from #15356: the structured
`working_dirs` jsonb column + `WorkingDirEntry` type (recent_cwds kept,
now @deprecated).
Scope is deliberately column-only — the lowest-risk slice:
- migration 0106 is pure `ADD COLUMN IF NOT EXISTS` (metadata-only, ~ms locks
per table, online-safe, no app code change since columns are all NULL).
- FKs, btree indexes, and the per-user→workspace-scoped unique-constraint
conversions are intentionally deferred to follow-up PRs so each can use the
production-safe execution path Drizzle can't express (NOT VALID + VALIDATE,
CREATE INDEX CONCURRENTLY, atomic unique swap).
Scoping notes:
- devices / user_connectors / user_connector_tools: scoped (user-owned resources).
- push_tokens: left user/device-level — an Expo token is one per app install and
receives a person's notifications across all their workspaces.
- agent_shares: no workspace_id — scoped transitively via agent_id → agents.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* 🐛 fix(database): satisfy inferred row types after adding workspace_id
Adding workspace_id made it a required key in the Drizzle-inferred row types
($inferSelect), breaking call sites that build those shapes by hand:
- rbac.getUserRoles: include workspace_id in the explicit select projection
- session action: add workspaceId to the constructed chat-group literal
- test mocks (apiKey / generation / generationBatch / generationTopic): add
workspaceId: null
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* ✅ test(database): use toMatchObject for topic.create row assertions
The two `expect(createdTopic).toEqual({ ...full literal })` snapshots broke
on every new column (here: workspace_id). Switch them to toMatchObject so the
returned row may carry extra columns without churning the expected literal.
The dbTopic↔createdTopic strict comparisons are left as toEqual.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Move the self-iteration skill-management action off the inline policy
implementation onto an execAgent-dispatched builtin agent (slug
`skill-management`), mirroring the S3/S4 memoryWriter + self-iteration
migration. Adds the `agentSignalSkillManagement` serverRuntime, the
builtin-tool-agent-signal skill-management manifest/systemRole, and the
builtin-agents skill-management agent; strips the ~3.5k-line inline
skillManagement policy down to the dispatch shim.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Long-running queries (e.g. an insert stuck for 700s on lock contention)
could block indefinitely because Postgres' statement_timeout defaults to
0 (no limit) and neither the node nor neon pool configured one.
Add an optional DATABASE_STATEMENT_TIMEOUT env (milliseconds, no default)
applied to both NodePool and NeonPool as statement_timeout and
idle_in_transaction_session_timeout, so Postgres aborts a stuck statement
or idle transaction on the server side. Unset keeps the previous behavior.
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
# 🚀 LobeHub Release (20260604)
**Release Date:** June 4, 2026
**Since v2.2.1:** 88 merged PRs · 11 contributors
> This week brings Execution Devices out of the lab — run agents and
Claude Code on any configured local or remote machine — alongside Claude
Opus 4.8, token-usage analytics, and Page sharing.
---
## ✨ Highlights
- **Execution Devices** — Pick where an agent runs. Desktop and CLI
devices auto-register with a stable machine ID, route through the
gateway by channel, and surface a device switcher in the chat input. Run
remote Claude Code on a configured device, with a recent-directory
picker you can drag to reorder. (#15300, #15315, #15322, #15343, #15351,
#15371)
- **Claude Opus 4.8** — Day-one support for Anthropic's latest model.
(#15314)
- **Token-usage analytics** — A new token-usage mode on the activity
heatmap, backed by a denormalized topic usage/cost rollup so totals stay
accurate without recomputing from messages. (#15365, #15417, #15425)
- **Page sharing** — Share a Page through a dedicated document share
flow, plus new Workspace and Agent share tables. (#15309, #15439)
- **Self-iteration agents** — Agent Signal's execAgent migration lands a
server-runtime bridge, async memory writer, and a registered
self-iteration tool package, with a CLI trigger command for testing.
(#15360, #15364, #15392)
- **Knowledge search** — BM25 search now extends to file-backed
documents, and the portal ships an editable CodeMirror viewer for local
files with document highlighting. (#15247, #15298)
---
## 🏗️ Core Agent & Architecture
### Agent Signal & Runtime
- **execAgent migration** — Server-runtime bridge, completion
projection, async memory writer, and removal of the legacy
`executeSelfIteration` path. (#15392)
- Registered the self-iteration builtin tool package and restored the
three mode-specific self-iteration agent slugs. (#15202, #15364)
- Added a CLI trigger command with a golden-snapshot fixture for Agent
Signal. (#15360)
- **Skill priority** — Agent Builder now emits a skill-priority
instruction with matching server runtime. (#15409)
- Retry empty LLM completions instead of silently finishing the turn.
(#15355)
- Classify topic/agent/session foreign-key violations as
`ConversationParentMissing` for clearer recovery. (#15408)
- Persist canonical nested usage/performance on assistant messages, and
re-link orphan tool messages at the raw bucket write boundary. (#15359,
#15438)
- Guard `createAgent` against LLM double-encoded array fields. (#15381)
---
## 🖥️ Execution Devices & Gateway
- Auto-register desktop and CLI devices with a stable machine ID, and
add the `@lobechat/device-identity` package. (#15300, #15321)
- New Devices settings page behind the Execution Device Switcher lab,
with a device switcher shown for all agents in the chat input. (#15315,
#15371)
- `connectionId` + channel routing across the gateway client and device
list; preset the local device on the first LLM request for the 本机
target. (#15322, #15435)
- Run remote Claude Code on a configured device, with drag-to-reorder
recent-directory management and client renders for device tool results.
(#15343, #15351, #15437)
- Preserve content and state across gateway tool calls, and prevent
duplicate streaming from stale reconnects. (#15114, #15354)
---
## 🖥️ CLI & Desktop
- Preserve content/state for connect local file and shell tools; render
the `runCommand` tool result card. (#15441, #15442)
- New `lh topic view` command; CLI now auto-registers its device on
login, matching desktop. (#15340, #15377)
- Resolve CLI tools from the shell `PATH`, and clarify local command
session handling. (#15368, #15389)
- Relocate visual-ref helpers to `@lobechat/const` to fix a renderer
crash; upload `.blockmap` files to S3 for differential updates. (#15326,
#15369)
- Fix a market OAuth expiry that triggered the wrong re-login modal, and
kill dev child processes on parent shutdown. (#15246, #15290)
---
## 🗂️ Pages, Library & Knowledge
- Document share flow with business slot stubs, plus Workspace and Agent
share tables. (#15309, #15439)
- Export Agent profiles as Markdown, preserving an empty agent prompt on
export. (#15312, #15316)
- Editable CodeMirror viewer for local files with document highlighting;
BM25 search extended to file-backed documents. (#15247, #15298)
- Default new Agent-doc files to `.md` and preserve IME composition;
refresh folder data on slug switch and dedupe breadcrumb fetches.
(#15335, #15427)
---
## 💬 Chat & User Experience
- Group-by-status mode for the Topic sidebar; dropped the legacy
session→agentId compatibility path from Topic queries. (#15366, #15378)
- Restore editor focus after the file picker closes, and close the skill
dropdown before navigating to settings. (#15391, #15394)
- Strip markdown tokens from fallback Topic titles; keep an open
ActionBar popup when hovering another message. (#15303, #15372)
- Stabilize home starter loading and stop transliterating model names in
the home starter; show artifact source while streaming. (#15310, #15324,
#15386)
- Group the sidebar spacer with recents and agents. (#15373)
---
## 📊 Analytics, Tasks & Notifications
- Token-usage mode on the activity heatmap, backed by a denormalized
topic usage/cost rollup. (#15365, #15417, #15425)
- Push: new `PushChannel`, receipt cron, and `pushToken` tRPC API.
(#15233)
- Tasks now support file and image attachments. (#15141)
---
## 🧩 Models & Providers
- Support Claude Opus 4.8 and configurable model routing with starters.
(#15314, #15384)
- MiniMax M3: new model entry and an Anthropic video runtime. (#15380,
#15403)
- Add `intern-s2-preview` with `thinking_mode`, and `step-3.7-flash`
support. (#15308, #15317)
- Block disabling the official provider; fix default provider setup in
business mode. (#15379, #15382)
---
## 🎨 UI & Modals
- Migrate modals to `@lobehub/ui/base-ui` (LOBE-9711 + eval batch),
including the create-custom-model and feedback/changelog modals.
(#15401, #15416)
- Restructure confirmModal title and content across deletion flows;
polish the service-model form and migrate its Switch to base-ui.
(#15426, #15440)
- Wrap the BlueBubbles bridge config into a connection card; update
`@lobehub/ui` to v5.15.5. (#15325, #15342)
---
## 🔒 Reliability
- Replace hardcoded `session_context` values with template variables in
credentials. (#15352)
- Point `CHANGELOG_URL` to `/changelog`. (#15428)
---
## 👥 Contributors
Huge thanks to **11 contributors** who shipped **88 merged PRs** this
cycle.
@hezhijie0327 · @qybaihe · @sxjeru · @arvinxx · @Innei · @tjx666 ·
@LiJian · @sudongyuer · @cy948 · @rivertwilight · @AmAzing129
Plus @lobehubbot and renovate[bot] for maintenance.
---
**Full Changelog**: v2.2.1...release/weekly-20260604
* ✨ feat(agent-management): paginate searchAgent with real totals and cap notice
The searchAgent tool silently clamped limit to 20 with no pagination and
reported totalCount as the returned page size, so models (and users) could
never discover agents beyond the 20 most recently updated ones.
- AgentModel: extract shared where builder, add countAgents (same
conditions as queryAgents)
- lambda router + client agent service: expose countAgents
- server tool runtime & AgentManagerRuntime: pass offset through, report
real totals (workspace + marketplace), emit explicit notes when the
requested limit is capped and when more pages exist, explain
out-of-range offsets instead of claiming no matches
- manifest: add offset param, document pagination
- agent-manager-runtime: add vitest config + test scripts (suite was
previously unrunnable), repair stale store mocks
* 👷 build(ci): wire 8 tested packages into the package test workflow
An audit found 8 packages carrying test:coverage scripts that were never
added to the CI PACKAGES allowlist, so their suites never ran:
- agent-gateway-client, device-gateway-client, device-identity,
eval-dataset-parser: already green, added as-is
- eval-rubric, fetch-sse: had no package-level vitest config, so vitest
fell back to the root config whose setup/aliases break outside src/ —
added minimal configs
- heterogeneous-agents: one assertion drifted (labels registry gained
amp/hermes/openclaw/opencode) with nobody noticing — updated
- agent-manager-runtime: wired in the previous commit
All 8 verified locally with the exact CI command
(bun run --filter <pkg> test:coverage).
* ✅ test(agent-management): cover searchAgent error path and market totalCount fallback
Codecov flagged 3 uncovered lines in the patch: the searchAgents catch
block (2 misses) and the totalCount ?? items.length fallback (1 partial).
Add the missing failure-path and fallback tests on both execution paths
(client AgentManagerRuntime + server tool runtime).
* 🐛 fix(cli): preserve content/state for connect local file/shell tools
Route file/shell tool calls in connect mode through LocalSystemExecutionRuntime
so the result carries formatted prompt `content` plus structured `state`, and
forward `state` over the gateway tool-call response — aligning the CLI with the
desktop gateway path (PR #15114).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* 🐛 fix(cli): preserve getCommandOutput timeout when polling running commands
Routing getCommandOutput through the runtime dropped the per-call/gateway
timeout: the CLI mapping didn't forward it and LocalSystemExecutionRuntime's
denormalizeParams stripped it before ShellProcessManager.getOutput, so polling
fell back to the 30s default and could block past the gateway budget. Carry
timeout through the runtime param type, denormalize, and the CLI mapping.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
A fast hetero-agent (Claude Code) tool can have its parent assistant's
`tools[]` momentarily dropped (stale/out-of-order `replaceMessages` snapshot,
or an optimistic `updateMessage{tools}` on the wrong assistant during a step
boundary) while the `role:'tool'` row + parentId survive. Since conversation-
flow binds a tool into its assistant solely via `assistant.tools[].id`, the
tool then renders as a top-level orphan bubble (`inspector.orphanedToolCall`).
Fix at the RAW `dbMessagesMap` write boundary — shared by `replaceMessages`
and `internal_dispatchMessage` (the optimistic-update path) — so the Source of
Truth stays consistent for optimistic updates, not just the parsed display.
`reconcileAssistantToolLinks` re-attaches the missing `tools[]` entry for any
present tool row whose parentId resolves to an assistant in the same bucket;
it only acts on present rows (never resurrects deletions) and never removes or
reorders entries.
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
The github render/inspector were registered under the snake_case
`run_command` key, but the tool call emits the camelCase `runCommand`
apiName, so the lookup missed and fell back to the generic collapsed
pill. Register both casings so the custom card renders.
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* ✨ feat(db): add usage column to messages table
Promote token usage/cost out of `metadata.usage` into a dedicated
`messages.usage` jsonb column, with btree expression indexes on
`usage.cost` and `usage.totalTokens`. Additive only — no data backfill;
`metadata.usage` stays the source of truth during the transition.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* ✨ feat(db): add agent share schema (picked from #15430)
Bring the agent-share schema layer over from #15430: new `agent_shares`
table + `topics.sender_id` column/index, schema relations and barrel
export. Migration renumbered to 0106 to sit after the usage column.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* ✨ feat(db): add workspace schema (picked from #15414)
Bring over only the standalone `workspace.ts` schema from #15414 — the
workspaces / workspace_members / workspace_invitations / workspace_audit_logs
tables (self-contained, FK to users only). None of #15414's workspaceId
column additions across other tables are included. Migration is 0108-safe,
renumbered to 0107.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* 🗃️ chore(db): squash usage/agent-share/workspace into one migration
Collapse the three stacked migrations (0105 usage, 0106 agent_share,
0107 workspace) into a single idempotent 0105_add_usage_agent_share_workspace.
Schema source is unchanged; only the migration files/snapshot/journal are
consolidated.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* ✅ test(db): add senderId to expected topic shape in create test
The picked agent-share schema added topics.senderId, so the created row
now returns it; update the two toEqual assertions accordingly.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
🚸 fix(ui): restructure confirmModal title and content across deletion flows
Move long warning sentences from `title` into `content` and use short verb titles
("Delete", "Uninstall", "Wipe Data", etc.). Add `okText`/`cancelText` i18n for all
fixed sites so confirm buttons match the action language.
Covers topic/thread/agent/group/library/file/model/skill/storage delete flows.
* ✨ feat(remote-device): add client renders for listOnlineDevices and activateDevice
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* 🐛 fix(utils): make SVG event-handler stripping engine-independent
DOMPurify's FORBID_ATTR / SVG-profile allowlist path relies on the underlying DOM's
attribute + namespace handling, which differs across engines (jsdom vs happy-dom) and
DOMPurify versions — in some CI environments on* handlers on SVG-namespaced nodes slipped
through. Add a scoped uponSanitizeAttribute hook to drop every on* attribute deterministically,
and assert by security property instead of exact serialization to drop whitespace brittleness.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* 🐛 fix(remote-device): render activation failure content when no device state
activateDevice returns success:false with explanatory content but no error and no state when
the target is offline/unknown. The tool detail view only skips custom rendering when result.error
is set, so the custom renderer's `return null` rendered a blank result. Fall back to the failure
content so the user/model still sees the message.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* 🐛 fix(utils): deterministically scrub SVG on* handlers via post-pass
The DOMPurify uponSanitizeAttribute hook still failed in CI: <script> is removed (tag filtering)
but on* handlers survive, because the attribute-sanitization phase doesn't run for SVG-namespaced
nodes in CI's DOM engine — so the hook never fires. Replace it with an explicit regex scrub on the
serialized output, which strips every on* event-handler attribute independent of the DOM engine.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* 🔒 fix(utils): loop SVG on* scrub until stable to close recombination bypass
A single-pass regex replace can leave a fresh handler behind when removing one splices the
surrounding text back together (` on onclick="x"click="y"` → ` onclick="y"`) — the CodeQL
js/incomplete-multi-character-sanitization case. Repeat the scrub until the string stops changing
so no on*= token can survive. Adds a regression test for the recombination input.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* 🐛 fix(agent-doc): default new files to .md and preserve IME composition
- Append `.md` to newly-created agent documents; pre-select only the stem
in the inline rename input so the extension stays intact.
- Wire `useIMECompositionEvent` on the explorer container so Enter pressed
during IME composition (e.g. Chinese pinyin) no longer commits the
half-formed name through pierre/trees' shadow-DOM input.
* 🐛 fix(agent-doc): use native capture listener for IME guard
React `onKeyDownCapture` can lose to pierre/trees' bubble handler in some
event ordering edge cases, and the original guard missed IMEs that report
`keyCode === 229` or fire Enter just after compositionend in the same task.
- Bind a native `keydown` capture listener on the container so we can
inspect `composedPath()` and confirm the keydown originated inside the
shadow-DOM rename input.
- Extend the IME guard with an `imeSessionRef` that stays true through one
extra microtask after compositionend.
- Drop the React `onKeyDownCapture` prop in favour of the native listener.
* ⏪ revert(agent-doc): drop IME guard pending pierre/trees upstream fix
The inline rename input lives in pierre/trees' shadow DOM and we can't
reliably suppress its IME-composing Enter commit from the outside. Roll
back the local hack and track the issue upstream instead. The default
`.md` extension and stem-only selection on rename stay in place.
* ✨ feat(agent-doc): preselect stem on inline rename too
Existing files entering inline rename (right-click → Rename, or F2) now
narrow the selection to the stem after pierre/trees' `input.select()`,
matching the new-file flow so the user never has to retype `.md`.
* 🐛 fix(agent-doc): preserve extension on filename collisions
* 💄 feat(stats): ladder shorten number up to B and T tiers
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* 💄 feat(stats): move token summary below overview and surface cumulative tokens
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* 💄 style(stats): add 12px gap between overview cards and token summary
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* 💄 style(stats): move heatmap summary under the activity title
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* ⚡️ perf(device): preset local device on first LLM request for 本机 target
When the desktop runs an agent against the local machine (executionTarget
'local'), resolve this desktop's own gateway deviceId client-side and pass it
as the run's `deviceId`. The server then presets `activeDeviceId` and injects
`lobe-local-system` into the very first LLM payload, skipping the extra
`activateDevice` round-trip the model was forced to make whenever more than one
device was online.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* ✅ test(device): cover local deviceId resolution in executeGatewayAgent
Asserts the client forwards this desktop's deviceId only for the local (本机)
target — including the unset-on-desktop fallback — and never for sandbox,
explicit remote device, or off-desktop runs.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* 🐛 fix(device): gate local-device binding on effective runtime mode
`resolveLocalDeviceId` defaulted an unset `agencyConfig.executionTarget` to
'local' and sent this desktop's deviceId. But the legacy ModeSelector writes
only `runtimeMode`, leaving executionTarget unset — so an explicit cloud/none
run would still get a deviceId, which the server turns into activeDeviceId and
injects lobe-local-system, wrongly routing a cloud run to the local machine.
Gate on `isLocalSystemEnabledById` (effective runtimeMode === 'local'), the
source of truth both selectors agree on.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* 🚨 fix(test): use import-type alias instead of inline import() type
Satisfies @typescript-eslint/consistent-type-imports (CI lint).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* 🚧 wip(agent-signal): S1 — self-iteration tools as static primitives, no side-channel
Rewrite all three self-iteration execAgent tool surfaces (review / reflection /
feedback-intent) as static, named primitives instead of reusing the dynamic
createServerToolSet / createToolSet factory (which carries the legacy
reserveOperation / receipt / completeOperation side channel the migration removes).
Package (builtin-tool-agent-signal):
- AgentSignalToolService.invoke (generic bag) → AgentSignalRuntimeService, a
narrow named DB-primitive seam (skillManagement precedent). Artifact recorders
echo their input; reads/mutations route to one primitive each. The runtime
carries no dedupe / receipt / operation-state side channel — idempotency and
receipt projection live on the completion path, not the tool call.
Server primitives (pure live-DB reads + writes, keyed to api names):
- review/server.ts createReviewRuntimePrimitives — proposal lifecycle + resource
tools, parameterized by window scalars from the operation marker, reusing the
existing snapshot/preflight/projection/brief helpers.
- tools/runtimePrimitives.ts createResourceRuntimePrimitives — the skill-read /
skill-write / writeMemory surface shared by reflection and feedback-intent.
- No context blob and no getEvidenceDigest: evidence is embedded in the agent
prompt, so tools only touch live state.
serverRuntimes: agentSignalReview / agentSignalReflection / agentSignalFeedbackIntent
thin factories wiring ToolExecutionContext → primitives → package runtime, all
registered. createServerToolSet / createToolSet left untouched (legacy
executeSelfIteration path, removed in S4).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* 🚧 wip(agent-signal): S2 — completion-path receipt projection from finalState
Replace the in-runtime receipt accumulator with finalState-driven projection on
the completion path. finalState is only in hand inside the completion lifecycle
(S3 final snapshots are write-only — get() is a null stub; the operation row has
no messages; prod webhook hooks strip finalState), so receipts must be projected
from the one point state exists.
- CompletionLifecycle.emitSignalEvents: extract the compact, kind-tagged tool
outcomes from the terminal state (extractSelfIterationCompletionPayload) and
carry them on the agent.execution.completed payload — only for marked
self-iteration runs, never the full message history.
- completionPolicy: forward the payload to onSelfIterationCompleted.
- completion/buildSelfIterationReceipts: project mutations + artifacts into
user-visible receipts, mirroring the legacy createReceipts kind/status/target
mapping. Deterministic receipt ids (sourceId + tool call id) → idempotent
re-projection; the store dedupes by id.
- completion/selfIterationCompletionHandler: build + persist receipts.
- orchestrator: wire the handler into createDefaultAgentSignalPolicies.
- agent-signal source type: add an opaque selfIteration field to the
agent.execution.completed payload.
Inert until the dispatch side stamps the operation marker (S3 / S4): without a
marker the extractor returns undefined and the handler no-ops.
Tests: buildSelfIterationReceipts (5) + extractCompletionPayload (4); completion
policy + CompletionLifecycle + orchestrator suites green.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* 🚧 wip(agent-signal): S3 part 1 — completion-side memory receipt support (inert)
Foundation for migrating the memory writer to the async execAgent path: teach
the completion path to project a memory receipt from a finished memory-writer
run. Inert until the dispatch side stamps a kind:'memory' marker (part 2).
- completion routing is now keyed on the operation MARKER (the selfIteration
payload), not the agent slug — a memory writer runs as the user's own agent,
so a slug check would miss it. completionPolicy gates on payload presence;
agentId loosened to string.
- extractCompletionPayload: for a kind:'memory' run, synthesize a writeMemory
mutation from the run's finalState (the memory builtin tool results are not
kind-tagged, so extractMutations finds nothing) via resolveMemoryActionResultFromState.
- buildSelfIterationReceipts: a memory run surfaces as just its action receipt,
no aggregate review summary.
- extract the pure memory finalState parsers into a dependency-light
./memoryActionResult module so the completion lifecycle can reuse them without
dragging the heavy memory-runner module (ModelRuntime/AgentService/…) into its
graph. userMemory re-exports them for backward compat.
- bump a too-tight (5s) timeout on the real-orchestration integration test.
Tests: completion (12) + completionPolicy (8) + userMemory (12) green; agentSignal
policies + orchestrator suites (138) green; type-check clean.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* ♻️ refactor(agent-signal): S3 — migrate memoryWriter to async execAgent + completion receipt
Flip the memory-writer action from a blocking executeSync run to an async
queued operation (autoStart) stamped with an agent-signal `memory` marker.
The user-visible "memory saved" receipt is no longer projected synchronously
from the action result — it is projected on the completion path from the run's
finalState (extractMemoryMutations → buildSelfIterationReceipts), so the receipt
appears a few seconds later once the run completes.
- userMemory.ts: add `dispatch` path enqueuing via createOperation(autoStart),
stamping appContext.agentSignal so completion can project the receipt.
- receiptService.ts: drop the synchronous memory receipt projection (would
duplicate the async one, with a premature empty target).
- types.ts: add `agentSignal` marker to OperationCreationParams.appContext.
- tests: cover the memory-kind completion loop end-to-end (single memory
receipt, correct target + anchor, no aggregate summary).
Note: the memory run uses createOperation (not execAgent), so it never
synthesises a user message and cannot recurse into analyzeIntent — no
suppressSignal needed on this path.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* 🚧 wip(agent-signal): S4 step 0 — forward agentSignal marker through execAgent
Foundation for migrating self-iteration onto execAgent: let a background run
carry its agent-signal marker so the S2 completion path can project receipts.
- Move AgentSignalOperationMarker / AgentSignalOperationKind into @lobechat/types
(ExecAgentAppContext can now reference it); operationMarker.ts re-exports the
type and keeps the runtime parse/validate helpers.
- ExecAgentAppContext: add `agentSignal?` field.
- execAgent: forward `appContext.agentSignal` into createOperation's appContext
(it was dropped by the curated passthrough), so it lands in
state.metadata.agentSignal — the key the completion extractor reads.
No behaviour change yet: nothing sets appContext.agentSignal on the execAgent
path until the self-iteration dispatch helper lands.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* 🚧 wip(agent-signal): S4 step 0b — self-iteration execAgent dispatch helper
Shared primitive for migrating the 3 self-iteration modes off the hand-rolled
runtime onto async execAgent (used by reflection/feedback/nightly-review next).
- enqueueSelfIterationRun(): create an isolated thread (when anchored), then
execAgent the builtin slug with suppressSignal + the agent-signal marker on
appContext, autoStart, headless. Returns immediately (fire-and-forget).
- marker: add `agentId` (the reviewed user agent). A slug run resolves the
operation agentId to the builtin agent, so receipts must attribute to the
reviewed agent carried on the marker.
- buildSelfIterationReceipts: attribute to `marker.agentId ?? agentId` (memory
runs leave it unset and fall back to the run agentId — unchanged).
Not wired into the mode handlers yet.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* ♻️ refactor(agent-signal): S4 — migrate executeSelfIteration to async execAgent
Replace the hand-rolled `executeSelfIteration` runtime (new AgentRuntime +
custom call_llm executor + 6 closure side-channels) with the standard async
`execAgent` queue path. nightly-review / self-reflection / self-feedback-intent
now enqueue via `enqueueSelfIterationRun → execAgent` and project their
receipts/briefs on the `agent.execution.completed` completion path.
- Delete `execute.ts` (1500 lines) + `execute.test.ts`; gut the three server
adapters (review/reflection/feedback) to drop the synchronous run path and
the legacy receipt/runtime wiring.
- `aiAgent`: background runs execute under a builtin slug but attribute their
resource tools + receipts to the *reviewed* user agent via the run marker.
- Drop the orchestrator's `writeDailyBrief` default — nightly review writes its
brief in-run via the builtin review serverRuntime primitive.
- Add `ReviewRunStatus.Dispatched` for enqueued background runs.
- Completion-path debug logging across CompletionLifecycle / completionPolicy /
completion handler.
Part of LOBE-9434 (S4 · LOBE-9876).
* 🐛 fix(agent-signal): make execAgent resolve builtin slugs + give self-iteration agents a mini model
Live-testing the S4 self-iteration → execAgent path surfaced two gaps that kept
background runs (nightly-review / self-reflection / self-feedback-intent) from
ever dispatching:
- execAgent threw `Agent not found: <slug>` when addressed purely by a builtin
slug (the self-iteration dispatch path) because getAgentConfig only resolves
persisted rows. Lazily materialize the virtual builtin row via
AgentModel.getBuiltinAgent — mirrors the inbox/task precedent — then re-resolve.
- The three self-iteration builtin agents had no `persist` model, so runs fell
back to the user's default chat model. Give them `persist: { DEFAULT_MINI_MODEL,
DEFAULT_MINI_PROVIDER }` (gpt-5.4-mini), matching the legacy executeSelfIteration
behavior.
Verified live: self-reflection now dispatches, the async operation reaches `done`,
and a `review` completion receipt is projected on the completion path. Adds two
execAgent.builtinRuntime tests (builtin-slug materialization + unknown-id still
throws).
Part of LOBE-9434 (S4).
* 🚨 fix(agent-signal): use type-only import for createServerSelfReviewBriefWriter
After the S4 gutting, review/server.ts only uses createServerSelfReviewBriefWriter
in a `ReturnType<typeof ...>` position — split it into a type-only import to
satisfy @typescript-eslint/consistent-type-imports (the lone lint:ts error).
* 🐛 fix(agent-signal): carry tool apiName in result content so action receipts project
The agent runtime persists tool messages with only content/role/tool_call_id (no
message-level apiName), so the completion extractor's `message.apiName` read was
always undefined in live runs — buildSelfIterationReceipts then dropped every
mutation via `if (!apiName) return []`, so durable skill/proposal writes produced
no action receipt (only the summary survived; memory was exempt via a hard-coded
apiName).
Fix the extraction channel, not the shared runtime:
- ExecutionRuntime stamps `apiName` into the result content alongside `kind`.
- extractFromFinalState reads apiName from the content (message.apiName fallback).
Tests reworked to the real persisted shape (apiName in content, no message-level
apiName) — the prior mocks hid the bug.
Part of LOBE-9434 (S4).
* 🐛 fix(agent-signal): persist run marker to operation metadata for server tools
Self-iteration server tools (nightly-review etc.) read the run marker from
`agent_operations.metadata` via readAgentSignalMarker, but recordStart only
persisted a trimmed appContext and never wrote metadata — so in live runs the
marker was always undefined and review/proposal writes fell back to a 1970
window/localDate + operationId source (non-idempotent).
recordStart now persists `metadata: { agentSignal }` from appContext.agentSignal,
so the tool path matches the completion path (which reads it from finalState).
Part of LOBE-9434 (S4).
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
- align memory model InputNumber height (32px) with base-ui Select trigger via local ConfigProvider
- stack optional features as switch above model select, switch right-aligned
- migrate optional features Switch from antd to @lobehub/ui/base-ui
* ✨ feat(stats): add daily token-usage mode to activity heatmap
Add a Messages/Tokens toggle to the stats activity heatmap. The token
mode sums assistant messages' `metadata.usage.totalTokens` (the source of
truth for usage) bucketed by the day each message was created, so tokens
land on the day they were actually consumed rather than on a topic's
creation date. Aggregation runs in SQL (SUM over the jsonb path, GROUP BY
date) and levels are scaled relative to the busiest day.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* 💄 feat(stats): format heatmap token counts and add token stat row
- Format tooltip token counts compactly (e.g. 44.2K, 12.5M) via the chart's
customTooltip; message counts get thousand separators.
- Add a token-dimension summary row (cumulative / peak daily / current streak
/ longest streak) shown in token mode, derived client-side from the heatmap
data over the past year.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* ✨ feat(stats): add longest-task duration to token heatmap stats
Add the "longest task" figure to the token-mode stats row, computed from
the longest wall-clock agent operation (completedAt - startedAt) over the
past year — MAX in SQL on the agent_operations table, scoped by user and
using the (user_id, created_at) index. Rendered as a compact 1h 15m / 45s
duration.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* 💄 feat(stats): default heatmap to token mode and move toggle beside title
- Token is now the first/default segmented option (Messages second); the
share card keeps Messages as its default.
- Move the Messages/Tokens toggle next to the section title (left) via a new
StatsFormGroup `afterTitle` slot; day tags stay on the right.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* ♻️ refactor: migrate modals to @lobehub/ui/base-ui (LOBE-9711 + eval)
Move 5 root createModal sites (LibraryModal/AddFilesToKnowledgeBase,
LibraryModal/CreateNew, Electron/AuthRequiredModal, SkillStore,
SkillStore/SkillDetail) to base-ui imperative createModal. Drop
allowFullscreen/destroyOnHidden/getContainer (base-ui handles them),
rename children→content, afterClose→onOpenChangeComplete, styles.body
→styles.content.
For AuthRequiredModal, base-ui imperative ModalInstance.update only
accepts Partial<BaseModalProps>, so the previous closable/keyboard
dynamic lock is reduced to maskClosable only — Esc/X close cannot be
blocked during sign-in.
Convert 11 declarative <Modal open … /> sites under eval/bench to
imperative createXxxModal factories, splitting each into Content.tsx
(body) + index.tsx (factory). Update callers in eval/index.tsx,
bench/[id]/{datasets/[id],features/{BenchmarkHeader,DatasetsTab,
RunsTab,TestCasesTab},runs/[id]/{index,features/RunHeader}} to call
factories on click instead of toggling local open state.
Delete unused TestCasePreviewModal.tsx (dead code); extract the
inline preview Modal from TestCasesTab into a new
TestCasePreviewModal feature folder.
* ♻️ refactor: move modal actions to base-ui footer slot, drop content padding overrides
Per @innei feedback on PR #15416:
- base-ui's ModalContent already has 12px/16px default padding; remove
manual paddingBlock/paddingInline wrappers in Content components and
drop styles.content.padding=0 overrides in factories.
- Move OK/Cancel (and other actions) into the createModal({footer}) slot
using base-ui's ModalFooter atom for proper flex/justify-end styling.
- Form submit wired via antd Form's name + Button form=name htmlType=submit
so the footer button outside Form can submit it. Shared loading state
flows from Content to Footer via a per-modal closure that calls
instance.update({footer: ...}).
New helper src/utils/createFormModal.tsx encapsulates the common pattern
for plain form modals (Cancel + Submit). Custom factories (RunCreate
split-button, BatchResume with selection counter, DatasetImport step-aware
footer, AuthRequired sign-in flow) use inline closure plumbing.
Touched files: 11 modal pairs (Content + Footer + index) + 1 helper.
* 🔥 chore: remove dead AddFilesToKnowledgeBase modal
`useAddFilesToKnowledgeBaseModal` exported from
`src/features/LibraryModal/AddFilesToKnowledgeBase/` had no callers in
the main codebase — only its own test referenced it. Remove the entire
folder (index, SelectForm, index.test) and drop the re-export from
`LibraryModal/index.ts`.
* 💄 style: bleed SkillStore scroll viewport past modal content padding
base-ui ModalContent has 12px/16px default padding, which insets the
SkillStore scroll viewport and makes the scrollbar look blocked. Pull
the body wrapper out with negative margins (marginInline: -16,
marginBlockEnd: -12) so the inner scroll container sits flush with the
modal edge. Grid items inside the scroll keep their own 16px padding.
* 🐛 fix: cast Modal.update to ImperativeModalProps for footer typing
base-ui's ModalInstance.update is typed as Partial<BaseModalProps>,
which excludes the `footer` and `content` fields that only
ImperativeModalProps carries. At runtime the imperative updateModal
spreads any shape, so the cast is sound — narrow it at each call site.
Also delete src/routes/(main)/eval/bench/[benchmarkId]/features/
DatasetRunCreateModal/, an orphaned re-export of RunCreateModal's
removed default export.
* ✨ feat(agent-builder): add skill priority instruction and server runtime
- Add <skill_coexistence> section to agent-builder system prompt so the
model always prefers Agent Builder tools over LobeHub skills for
agent configuration tasks when both are active simultaneously
- Add agentBuilder server runtime to support background (QStash)
execution: implements updateConfig, updatePrompt, searchMarketTools,
getAvailableModels (DB-backed, LobeHub provider first, max 20 chat
models), and installPlugin (market source only; official/OAuth tools
return a clear unsupported error)
- Register agentBuilderRuntime in the server runtime registry
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* ✨ feat(agent-builder): fix identity confusion when user provides agent name/purpose
Add <identity_boundary> section and example to prevent the AgentBuilder
from roleplaying as the agent being configured. Short phrases like
"健康助手，咨询健康问题" must be interpreted as configuration requests,
not service requests.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* 🐛 fix(agent-builder): address three server runtime issues
- getAvailableModels: use AiInfraRepos instead of raw AiProviderModel +
AiModelModel so builtin providers (DEFAULT_MODEL_PROVIDER_LIST) are
included even when the user has no DB-customized providers
- installPlugin (official): allow builtin tools (lobe-web-browsing etc.)
to be enabled directly; only block OAuth-requiring tools (Klavis,
LobehubSkill) that cannot be installed in background context
- installPlugin (market): fetch and persist the marketplace MCP manifest
on install so server tool discovery can find and execute the plugin
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* 🐛 fix(model-runtime): classify ollamacloud "context window exceeds limit" as ExceededContextWindow
ollamacloud surfaces context-window overflow as a generic 400 the upstream
labels ProviderBizError. Document the ollamacloud provenance on the existing
`context window exceeds` ECW pattern and add a regression test asserting the
message wins over the 400 / ProviderBizError catch-alls.
Fixes LOBE-9913
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* 🔥 chore(model-runtime): drop redundant ollamacloud note on ECW pattern
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
- New docs/usage/agent/{codex,claude-code}.{mdx,zh-CN.mdx} cover how to
delegate the Codex and Claude Code CLIs from the LobeHub desktop app
(install, sign-in, working-directory pinning, in-chat tool renderers,
resume behavior, execution targets, limitations).
- Rename docs/usage/getting-started/image-generation.{mdx,zh-CN.mdx} to
generation.{mdx,zh-CN.mdx} and expand to cover the Video workspace
alongside Image.
- Update <Card> links in sibling resource/vision docs to point at the
new /generation slug.
When a user deletes a topic (or agent/session/thread) while an agent operation
is still running, the assistant/tool-message INSERT fails with a Postgres 23503
foreign_key_violation on the corresponding `messages` FK. The persist-error
guard only recognised the `messages_parent_id_messages_id_fk` self-FK, so every
other reference deletion slipped through as a raw `Failed query: insert into
"messages"` 500 — surfacing to the user as a driver/SQL error and polluting the
error dashboard as DatabasePersistError noise (one of the longest-standing
top error categories).
Generalise `isParentMessageMissingError` → `isMidOperationReferenceMissingError`
to match a 23503 violation on any of the mid-operation-deletable `messages`
references (parent / quota message, topic, agent, session, thread). These all
mean "the referenced context was deleted mid-flight" — a lost race against the
user, not a runtime failure — so they are normalised to the typed, user-side
`ConversationParentMissing` error like the parent case already was.
Out-of-scope FKs (e.g. `messages_user_id_users_id_fk`, other tables) stay real
failures.
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
✨ feat(chat-input): show execution-device switcher for all agents and add desktop download link
- Remove `!isHeterogeneous` guard so the device switcher surfaces for every agent type (not just non-heterogeneous), controlled by the existing Lab toggle
- Make the sandbox/runtime-env mode selector mutually exclusive with the device switcher: hide it when `enableExecutionDeviceSwitcher` is on
- Add a "下载桌面端 / Get Desktop App" quick link in the execution-device popover header (right side) linking to https://lobehub.com/downloads
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* ♻️ refactor(modal): convert create custom model modal to base-ui imperative API
* ♻️ refactor(modal): convert edit model modal to base-ui imperative API
* 🐛 fix: make extend params preview read-only
Replaced all LOBE-XXX references in comments with descriptive context
instead of internal Linear issue markers. As an open-source project, these
internal references should not be exposed.
Changes:
- LOBE-9834 (empty completion): replaced with inline descriptions of the
"empty completion" failure mode
- LOBE-6587 (task scheduler): replaced with "task scheduler infra" ref
- LOBE-6634 (getTaskDetail model/provider): updated TODO description
- LOBE-9434 #5/#7 (execAgent migration): removed issue markers
12 files changed
Co-authored-by: Arvin Xu <arvinxx@users.noreply.github.com>
Migrate `FeedbackModal` and `ChangelogModal` from declarative `@lobehub/ui`
modals + a `useFeedbackModal` zustand store to the `@lobehub/ui/base-ui`
imperative `createModal()` API. Call sites now invoke `openFeedbackModal()`
/ `openChangelogModal()` directly — no more open/close state plumbing
through `(main)/_layout` or `(mobile)/me/(home)`. The `useFeedbackModal`
hook is removed.
Also:
- Wrap the email address in `feedback.emailContact` with a `<email>` tag
(Trans component → mailto link); all 18 locale files updated.
- Restore the external link on the changelog modal header pointing to
`CHANGELOG_URL`; the previous Button used `onClick={onClose}` despite
the ArrowUpRight icon suggesting an external navigation.
- Footer test mocks updated to match the new module exports.
Picking files via the antd `Upload` dropdown (paperclip / plus menus) and via
the AgentTasks attachment helpers leaves focus on `document.body` once the OS
file picker dismisses, so the editor cursor disappears and users do not know
they can keep typing.
Refocus the editor right after the file picker yields:
- `ChatInput/ActionBar/Upload`: subscribe to `editor` from the chat input
store and call `editor?.focus()` in the three `beforeUpload` handlers
(image / file / folder).
- `ChatInput/ActionBar/Plus`: same fix for the unified file-or-image upload
entry; add `editor` to the items `useMemo` deps.
- `EditorCanvas/editorAttachments`: refocus inside `insertFilesIntoEditor`
so every AgentTasks composer (CommentInput, CommentCard, FeedbackInput,
CreateTask*, TaskInstruction via `pickAndInsertAttachments`) recovers
the cursor too.
Fixes LOBE-9862
The skill market dropdown's settings button navigates to /settings/skill
but does not close the controlled dropdown first, so the popup persists
after the trigger has unmounted (LOBE-9852).
Also restore the negative margins on the skill market footer (regressed
in #15214 when bumping @lobehub/ui to 5.15.1) so the stats row aligns
with the dropdown's outer padding.
Apply the same defensive close-before-navigate to ModelSwitchPanel:
- ListItemRenderer no-provider / empty-model rows previously navigated
without calling onClose at all.
- Footer and GenerationListItemRenderer now close before navigate
instead of after, for a consistent ordering.
Closes LOBE-9852
Sliced raw user input was leaking syntax (#, **, ``` etc.) into topic / thread / agent / group / document titles whenever LLM summarization had not yet produced a clean title. Run the source string through `markdownToTxt` (remove-markdown) before slicing so the visible fallback is plain text.
* ♻️ refactor(topic): drop legacy session→agentId compatibility in topic queries
Topic ownership is fully migrated to `topics.agentId`, so the
`agentsToSessions` lookup that mapped a legacy `sessionId` back to an agent
is no longer reachable in practice. Remove it from the agent query, count,
and batch-delete paths — they now match `topics.agentId` directly.
- `query()`: drop the `agentsToSessions` pre-query and the `sessionId` OR
branch; keep the inbox fully-orphan fallback (all owner columns null),
which is unrelated to session linkage.
- `count()` / `batchDeleteByAgentId()`: match `topics.agentId` only.
- Remove the now-unused `agentsToSessions` import.
Tests updated to assert session-only legacy topics are no longer matched.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* ♻️ refactor(topic): make topic rank/recent agent-centric, drop returned sessionId
Topic ownership is `topics.agentId`, so the topic ranking and recent-topic
queries no longer need to expose or resolve a legacy `sessionId`.
- `TopicModel.rank()` now selects `topics.agentId` instead of `sessionId`;
`TopicRankItem.sessionId` → `agentId`.
- `TopicModel.queryRecent()` stops selecting `sessionId`.
- `recentTopics` TRPC procedure: drop the `agentsToSessions` batch resolve
and the `after()` runtime agentId backfill — both keyed off the legacy
session mapping. Agent topics now map straight through `topic.agentId`.
- Topic ranking UI navigates to `SESSION_CHAT_TOPIC_URL(agentId, topicId)`
(`/agent/:aid/:topicId`), falling back to the inbox agent id when a topic
has no agentId, replacing the old `/agent?session=...` query-param link.
Rank test asserts `agentId`; the broader `getTopics` session-resolution
path is intentionally left untouched.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* ⏪ revert(topic): restore session→agentId resolution in query/count/delete
The integration tests (topic.integration.test.ts) showed this compatibility
is still load-bearing: the topic write path (createTopic / batchCreateTopics
/ updateTopic) persists `sessionId` with `agentId = null`, so dropping the
read-side session→agentId resolution made freshly-created topics
unqueryable/undeletable by agentId.
Revert the read-side removal from `query()` / `count()` /
`batchDeleteByAgentId()` (and their tests) until the write path is migrated to
store `agentId` directly. The agent-centric `rank()` / `queryRecent()` /
`recentTopics` surface changes are kept.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* ♻️ refactor(topic): drop session→agentId compatibility from topic read paths
Topic ownership is fully migrated to `topics.agentId` (old data backfilled,
new app no longer depends on sessionId), so the legacy session resolution in
the topic read paths is dead and can go.
- `query()` / `count()` / `batchDeleteByAgentId()`: match `topics.agentId`
directly; drop the `agentsToSessions` lookup + `topics.sessionId` OR branch.
The inbox fully-orphan fallback (all owner columns null) is kept.
- `getTopics` TRPC procedure: drop the `after()` runtime agentId backfill and
the now-unused `AgentMigrationRepo` wiring / `after` import. The sessionId→
agentId reverse-resolution of the query *filter* is kept for clients that
still pass a sessionId.
- Update topic integration + model tests to agent-native fixtures; remove the
legacy-session and runtime-migration cases that exercised the removed path.
The write path (createTopic/batchCreate/updateTopic) is intentionally left
unchanged per scope; no data migration is performed.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* ♻️ refactor(topic): keep getTopics runtime agentId backfill during transition
Restore the `after()` runtime migration in `getTopics` (and the
`AgentMigrationRepo` wiring / `after` import). The read paths no longer
resolve sessionId, but the backfill is still needed to migrate straggler
legacy (sessionId-only) topics over the transition window; a legacy topic is
backfilled on first query and becomes agentId-queryable thereafter.
Restore the migration integration tests, adjusted: they assert the agentId
backfill happens after the query rather than expecting legacy rows in the
first (now agentId-only) response.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* ♻️ refactor(topic): keep recentTopics runtime agentId backfill
Restore the recentTopics session→agentId backfill removed earlier: re-select
`sessionId` in `queryRecent` (internal only — not exposed in the RecentTopic
response) and re-add the `batchResolveAgentIdFromSessions` resolution + the
`after()` migrateAgentId backfill. Like the getTopics backfill, this keeps
migrating straggler legacy (sessionId-only) topics during the transition.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* 💄 chore(topic): drop unnecessary comment churn in topic router/model
Revert the migration/backfill comments to their original wording so the
restored getTopics/recentTopics blocks are byte-identical to canary, and drop
the extra queryRecent select comment. No logic change.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* ♻️ refactor(agent): replace session-based assistant ranking with agent-native rank
The assistant usage ranking was session-centric (SessionModel.rank joining
agentsToSessions, returning a sessionId; UI linked /agent?session=...). Rework
it as agent-native:
- Add `AgentRankItem` type (id = agentId); remove `SessionRankItem`.
- Add `AgentModel.rank`: count topics grouped by `topics.agentId`, joined to
agents for avatar/title, ordered by count. Mirrors the recents filter
(real agents + inbox, excluding other virtual agents). No sessions involved.
- Add `agent.rankAgents` TRPC procedure + `agentService.rankAgents`; remove
`session.rankSessions`, `sessionService.rankSessions`, `SessionModel.rank/_rank`.
- AssistantsRank UI: navigate to `SESSION_CHAT_URL(agentId)` → `/agent/:aid`,
resolving the inbox title via the store's inboxAgentId.
Move the rank tests from session.test.ts to agent.test.ts.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* ✨ feat(topic): add group-by-status mode to topic sidebar
Add a new "By status" grouping option to the agent topic sidebar. Topics
bucket into fixed-priority groups — waitingForHuman first, then running,
then active, with the remaining states below. Topics without a status are
treated as active. Only non-empty groups render.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* ✨ feat(topic): resolve group-by-status ordering on the server
The sidebar only loads the first page of topics, so grouping that partial
list client-side could hide high-priority topics (awaiting-human / running)
that live on a later page. Push the ordering to the query instead.
- Add `sortBy: 'updatedAt' | 'status'` to the topics query (TRPC + model).
`status` orders by a priority CASE (waitingForHuman → running → active →
paused → failed → completed → archived) before the updatedAt tiebreaker,
so the most important topics always land on the first page.
- Plumb `sortBy` through the service, store fetch action (incl. SWR key),
and the shared topic hooks; `useFetchChatTopics` requests `status` ordering
only when the resolved agent group mode is `byStatus` (group sessions keep
the default). The client still buckets for display, now over a correctly
ordered page.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* 🐛 fix(topic): bucket streaming topics under "running" in group-by-status
A topic generating a response shows the loading ring via the client-only
`topicLoadingIds` state, not a persisted `status`, so it was landing in the
"active" group. Mirror the sidebar TopicItem icon precedence when bucketing:
waitingForHuman wins, then a topic that is streaming on this client (or
persisted as running) goes to "running", then the persisted status.
The loading overlay stays client-side (the server can't know a given client
is mid-stream); the selector passes `topicLoadingIds` into the byStatus
grouping only.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
YuTengjing