Skip to content

🐛 fix(remote-device): preserve content/state across gateway tool calls#15114

Merged
arvinxx merged 1 commit into
canaryfrom
fix/remote-device-tool-content-state
Jun 1, 2026
Merged

🐛 fix(remote-device): preserve content/state across gateway tool calls#15114
arvinxx merged 1 commit into
canaryfrom
fix/remote-device-tool-content-state

Conversation

@arvinxx

@arvinxx arvinxx commented May 22, 2026

Copy link
Copy Markdown
Member

Summary

Remote-device tool calls (cloud → device-gateway → desktop) were JSON.stringify-ing the entire IPC result into content, losing the structured state payload and leaking {success: true, ...} into the LLM-facing prompt text. This made remote tool results look like:

{"exit_code":0,"output":"...","stderr":"","stdout":"...","success":true}

— one opaque blob in content, nothing in pluginState.

Two compounding bugs:

  1. Desktop GatewayConnectionCtr.executeToolCall called raw LocalFileCtr / ShellCommandCtr handlers directly, returning the raw IPC payload. gatewayConnectionSrv.handleToolCallRequest then JSON.stringify'd the whole thing into content.
  2. GatewayHttpClient.executeToolCall had a fallback JSON.stringify(data.content ?? data) that, when content was missing, stringified the entire response body — including success and state — back into content.

Fix

  • Wire protocol (device-gateway-client): ToolCallResponseMessage.result + DeviceToolCallResult carry state?: unknown end-to-end. HTTP client drops the brittle whole-body stringify fallback.
  • DeviceProxy.executeToolCall: return type includes state?: unknown, propagates through to RuntimeExecutors which writes it to pluginState.
  • Desktop main: executeToolCall now routes through LocalSystemExecutionRuntime — the same runtime the renderer-side LocalSystemExecutor uses — so the envelope is identical (content = formatted prompt, state = structured snapshot, both produced by the runtime). handleToolCallRequest forwards the envelope as-is instead of stringifying.

Refactor: move LocalSystemExecutionRuntime

To let the desktop main process reuse the runtime without pulling React/antd peer deps in, moved LocalSystemExecutionRuntime from @lobechat/builtin-tool-local-system (renderer-coupled) to @lobechat/tool-runtime (renderer-agnostic, lives next to ComputerRuntime).

  • packages/tool-runtime/src/LocalSystemExecutionRuntime.ts (moved from builtin-tool-local-system)
  • packages/builtin-tool-local-system/src/client/executor/index.ts re-imports from @lobechat/tool-runtime
  • packages/builtin-tool-local-system/package.json drops the ./executionRuntime subpath export
  • apps/desktop adds @lobechat/tool-runtime + @lobechat/prompts to its pnpm-workspace.yaml and package.json

Test plan

  • apps/desktop: GatewayConnectionCtr tests (38 pass) — routing + envelope shape assertions
  • packages/device-gateway-client: http + client tests (58 pass) — state preserved, brittle fallback gone
  • packages/builtin-tool-local-system: executor + audit tests (64 pass) — renderer-side path unchanged
  • src/server/services/toolExecution: deviceProxy + serverRuntimes tests (176 pass)
  • bun run type-check clean for desktop main (src/main/**)
  • Manual: trigger a remote-device tool call from cloud and confirm the tool message has populated pluginState instead of a stringified blob in content

🤖 Generated with Claude Code

@vercel

vercel Bot commented May 22, 2026

Copy link
Copy Markdown

The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Actions Updated (UTC)
lobehub Ready Ready Preview, Comment May 31, 2026 4:03pm

Request Review

@dosubot dosubot Bot added the size:L This PR changes 100-499 lines, ignoring generated files. label May 22, 2026

@sourcery-ai sourcery-ai Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Sorry @arvinxx, you have reached your weekly rate limit of 500000 diff characters.

Please try again later or upgrade to continue using Sourcery

@dosubot dosubot Bot added feature:tool Tool calling and function execution platform:desktop Desktop client labels May 22, 2026
@codecov

codecov Bot commented May 22, 2026

Copy link
Copy Markdown

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 71.11%. Comparing base (e4d5017) to head (99e9754).
⚠️ Report is 2 commits behind head on canary.

Additional details and impacted files
@@            Coverage Diff            @@
##           canary   #15114     +/-   ##
=========================================
  Coverage   71.11%   71.11%             
=========================================
  Files        3188     3188             
  Lines      318686   318701     +15     
  Branches    34769    29017   -5752     
=========================================
+ Hits       226638   226660     +22     
+ Misses      91876    91869      -7     
  Partials      172      172             
Flag Coverage Δ
app 61.95% <ø> (+<0.01%) ⬆️
database 92.39% <ø> (ø)
packages/agent-runtime 80.48% <ø> (ø)
packages/builtin-tool-lobe-agent 18.52% <ø> (ø)
packages/context-engine 84.17% <ø> (ø)
packages/conversation-flow 91.29% <ø> (ø)
packages/file-loaders 87.89% <ø> (ø)
packages/memory-user-memory 74.99% <ø> (ø)
packages/model-bank 99.99% <ø> (ø)
packages/model-runtime 84.70% <ø> (ø)
packages/prompts 72.68% <ø> (ø)
packages/python-interpreter 92.90% <ø> (ø)
packages/ssrf-safe-fetch 0.00% <ø> (ø)
packages/types 35.87% <ø> (ø)
packages/utils 88.47% <ø> (ø)
packages/web-crawler 88.08% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

Components Coverage Δ
Store 68.44% <ø> (ø)
Services 54.61% <25.00%> (-0.04%) ⬇️
Server 72.37% <100.00%> (+0.01%) ⬆️
Libs 57.01% <ø> (ø)
Utils 81.44% <ø> (ø)
🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
  • 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

The cloud→gateway→desktop path was JSON.stringify-ing the entire IPC result
into `content`, dropping `state` and leaking `{success: true, ...}` into the
LLM-facing prompt. Routes remote tool calls through `LocalSystemExecutionRuntime`
(same runtime the renderer uses) so `content` is the formatted prompt and
`state` flows through `DeviceProxy` → `RuntimeExecutors` into `pluginState`.

Also moves `LocalSystemExecutionRuntime` from `@lobechat/builtin-tool-local-system`
(renderer-coupled, React/antd peers) into `@lobechat/tool-runtime` so the
desktop main process can reuse it without pulling UI deps.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
@arvinxx arvinxx force-pushed the fix/remote-device-tool-content-state branch from 90249e1 to 99e9754 Compare May 31, 2026 15:57
@arvinxx arvinxx merged commit 7d1086b into canary Jun 1, 2026
35 checks passed
@arvinxx arvinxx deleted the fix/remote-device-tool-content-state branch June 1, 2026 03:01
arvinxx added a commit that referenced this pull request Jun 1, 2026
… renderer crash (#15369)

🐛 fix(desktop): relocate visual-ref helpers to @lobechat/const

PR #15114 added @lobechat/prompts + @lobechat/tool-runtime to the desktop
nested pnpm workspace. pnpm then linked their @lobechat/types dependency to
the desktop type-only stub (apps/desktop/stubs/types) inside the SHARED
packages/*/node_modules, which the renderer/web build also consumes. The
runtime value import `createVisualFileRef` (in prompts/files/{image,video}.ts)
resolved to the stub — which only surfaces types — so the renderer crashed on
boot with `SyntaxError: ... does not provide an export named createVisualFileRef`.

The stub is load-bearing: pointing the desktop workspace at the real
@lobechat/types fails install (model-bank@workspace:* dependency cascade), so
the stub must stay. Fix the contract instead: visual-ref helpers are runtime
logic, not types, so they don't belong in @lobechat/types. Move the
zero-dependency helpers to @lobechat/const/visualRef (already a real desktop
member, no cascade) and import them via the narrow subpath. prompts/tool-runtime
now only `import type` from @lobechat/types, so the stub link is harmless.

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
arvinxx added a commit that referenced this pull request Jun 3, 2026
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>
arvinxx added a commit that referenced this pull request Jun 3, 2026
…#15442)

* 🐛 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>
@arvinxx arvinxx mentioned this pull request Jun 3, 2026
arvinxx added a commit that referenced this pull request Jun 4, 2026
# 🚀 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
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

feature:tool Tool calling and function execution platform:desktop Desktop client size:L This PR changes 100-499 lines, ignoring generated files.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant