⚡️ perf(device): preset local device on first LLM request for 本机 target#15435
Conversation
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>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 82ad3463fe
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
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>
Codecov Report❌ Patch coverage is Additional details and impacted files@@ Coverage Diff @@
## canary #15435 +/- ##
=========================================
Coverage 71.00% 71.01%
=========================================
Files 3212 3212
Lines 321350 321366 +16
Branches 35030 29263 -5767
=========================================
+ Hits 228186 228207 +21
+ Misses 92988 92983 -5
Partials 176 176
Flags with carried forward coverage won't be shown. Click here to find out more.
🚀 New features to boost your workflow:
|
`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>
Satisfies @typescript-eslint/consistent-type-imports (CI lint). 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
💻 Change Type
🔀 Description of Change
When the desktop client runs an agent against 本机 (
executionTarget: 'local'), the runtime now resolves this desktop's own gatewaydeviceIdclient-side and passes it as the run'sdeviceId.Why: The whole
activeDeviceId → buildStepToolDelta → lobe-local-systemmachinery already exists, but thelocaltarget was modeled as a mode (executionTarget + runtimeMode) rather than a concrete device. The client never told the server which device "本机" was, and the server'sactiveDeviceIdresolver only understoodboundDeviceId(thedevicetarget) plus a "exactly one online device" fallback heuristic. So with multiple devices online, picking 本机 leftactiveDeviceIdundefined → the model was forced to calllistOnlineDevices+activateDevicebeforelobe-local-systembecame available (an extra LLM round-trip, plus the{{workingDirectory}}literal leaking into the first steps).By passing the local
deviceId, the server presetsactiveDeviceIdand injectslobe-local-systeminto the first LLM payload — theactivateDeviceround-trip is skipped.Scope: purely client-side — reuses the existing server
deviceIdparam, no server changes.resolveLocalDeviceId(agentId)helper inaiChat/actions/gateway.ts(mirrorsresolveProjectSkills): desktop-only, gated onexecutionTarget === 'local', reads the local id viagatewayConnectionService.getDeviceInfo(), best-effort (any failure falls back to the server's existing heuristic).execAgentTaskcall, run in parallel withresolveProjectSkills.Edge cases (safe):
sandbox/devicetargets → helper returnsundefined, behavior unchanged.onlineDevicesguard fails the id → stays unrouted, no misrouting.topic.metadata.boundDeviceId, but that field is never read back for activation (guarded by the existingshould not reuse topic boundDeviceIdtest); each turn re-resolves from the current machine, so switching machine / moving to web self-corrects.🧪 How to Test
On desktop with 2+ devices online, select 本机 and send a message that needs the filesystem/shell (e.g. "list files in cwd"). The agent should call a
lobe-local-systemtool on its first step, with no precedingactivateDevicetool call.📝 Additional Information
Type-check is clean for the changed file (remaining
tsgoerrors are pre-existing unbuilt-workspace-package issues, unrelated to this change).🤖 Generated with Claude Code