Skip to content

🐛 fix(heterogeneous-agents): show real CLI model on remote-spawned Claude Code#15572

Merged
arvinxx merged 1 commit into
canaryfrom
fix/cc-remote-spawn-model-provider
Jun 9, 2026
Merged

🐛 fix(heterogeneous-agents): show real CLI model on remote-spawned Claude Code#15572
arvinxx merged 1 commit into
canaryfrom
fix/cc-remote-spawn-model-provider

Conversation

@arvinxx

@arvinxx arvinxx commented Jun 9, 2026

Copy link
Copy Markdown
Member

💻 Change Type

  • 🐛 fix

🔗 Related Issue

🔀 Description of Change

Remote/device-spawned Claude Code (and Codex) runs persist through the server-side HeterogeneousPersistenceHandler because the executing device is not the viewing client — unlike local desktop runs, which use the client-side heterogeneousAgentExecutor.

The assistant placeholder was created with the agent's configured chat model/provider (e.g. deepseek-v4-pro). For claude-code/codex (which are not isRemoteHeterogeneousType) the provider stayed the agent's provider and the model stayed the agent's model. That bogus model:

  1. leaked straight into the model tag in the UI (showed deepseek-v4-pro with the wrong provider icon), and
  2. got re-seeded into state.lastModel on cold replicas (if (!state.lastModel && refreshed?.model) …) and re-applied at terminal — so it stuck.

The client path never hit this because it sets only provider: heteroType, leaves the model empty, and never seeds lastModel from the placeholder.

Fix:

  • Create the hetero placeholder with provider: heteroType for all hetero agents (not just remote openclaw/hermes) and no model — mirroring the client. The real model is reported by the CLI and backfilled.
  • Capture the CLI's authoritative model/provider from the first stream_start (CC's system/init, which always carries model + provider: 'claude-code') and backfill the placeholder, so the real model lands from the first turn even on a short run with no usage-bearing turn_metadata.

This also aligns with the existing UI intent: Usage/Extra only render the model tag for local hetero once a real model is present.

🧪 How to Test

  • Added/updated tests

Updated HeterogeneousPersistenceHandler.eventBranches.test.ts: the first stream_start (CLI init) now backfills the placeholder with the real model/provider; a no-model/provider init remains a no-op. Full handler suite (82 tests) passes; type-check has no new errors in touched files.

To verify manually: spawn a Claude Code agent on a remote device, send a short prompt (e.g. "你好") — the model tag should show the real Claude model (and CC provider), not the agent's configured chat model.

📝 Additional Information

Server-only change (server service + persistence handler + test). Local client path was already correct and is intentionally left untouched.

…aude Code

Remote/device-spawned CC runs persist via the server-side
HeterogeneousPersistenceHandler (the executing device is not the viewing
client), and the assistant placeholder was created with the agent's
configured chat model/provider (e.g. deepseek-v4-pro). That value leaked
into the model tag and was re-applied at terminal, so the model tag showed
the wrong model instead of the real Claude Code model.

- Create the hetero placeholder with `provider: heteroType` for ALL hetero
  agents (not just remote openclaw/hermes) and no model, mirroring the
  client path. The real model is reported by the CLI and backfilled.
- Capture the CLI's authoritative model/provider from the first
  `stream_start` (CC system/init) and backfill the placeholder, so the real
  model lands from the first turn even without usage-bearing turn_metadata.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
@vercel

vercel Bot commented Jun 9, 2026

Copy link
Copy Markdown

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

Project Deployment Actions Updated (UTC)
lobehub Building Building Preview, Comment Jun 9, 2026 3:50am

Request Review

@dosubot dosubot Bot added the size:M This PR changes 30-99 lines, ignoring generated files. label Jun 9, 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

@codecov

codecov Bot commented Jun 9, 2026

Copy link
Copy Markdown

Codecov Report

❌ Patch coverage is 94.11765% with 1 line in your changes missing coverage. Please review.
✅ Project coverage is 70.49%. Comparing base (eae47f5) to head (c568ad0).
⚠️ Report is 6 commits behind head on canary.

Additional details and impacted files
@@            Coverage Diff            @@
##           canary   #15572     +/-   ##
=========================================
  Coverage   70.49%   70.49%             
=========================================
  Files        3309     3309             
  Lines      326769   326784     +15     
  Branches    34653    28870   -5783     
=========================================
+ Hits       230357   230371     +14     
- Misses      96229    96230      +1     
  Partials      183      183             
Flag Coverage Δ
app 61.22% <94.11%> (+<0.01%) ⬆️
database 92.22% <ø> (ø)
packages/agent-manager-runtime 49.69% <ø> (ø)
packages/agent-runtime 81.06% <ø> (ø)
packages/builtin-tool-lobe-agent 18.52% <ø> (ø)
packages/context-engine 84.12% <ø> (ø)
packages/conversation-flow 91.29% <ø> (ø)
packages/device-gateway-client 90.18% <ø> (ø)
packages/eval-dataset-parser 95.15% <ø> (ø)
packages/eval-rubric 76.11% <ø> (ø)
packages/fetch-sse 85.57% <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 84.22% <ø> (ø)
packages/prompts 72.51% <ø> (ø)
packages/python-interpreter 92.90% <ø> (ø)
packages/ssrf-safe-fetch 0.00% <ø> (ø)
packages/types 35.25% <ø> (ø)
packages/utils 84.98% <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 68.20% <ø> (ø)
Services 53.96% <ø> (ø)
Server 71.28% <94.11%> (+<0.01%) ⬆️
Libs 55.96% <ø> (ø)
Utils 81.93% <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.

@arvinxx arvinxx merged commit 3986223 into canary Jun 9, 2026
39 of 40 checks passed
@arvinxx arvinxx deleted the fix/cc-remote-spawn-model-provider branch June 9, 2026 04:08
arvinxx added a commit that referenced this pull request Jun 10, 2026
# 🚀 LobeHub Release (20260610)

**Release Date:** June 10, 2026  
**Since v2.2.2:** 131 merged PRs · 13 contributors

> This weekly release strengthens agent collaboration across cloud,
desktop, CLI, and workspace flows, with steadier runtime behavior and a
broader foundation for workspace-scoped data.

---

## ✨ Highlights

- **Agent execution across devices** — Unifies per-device working
directories, project skill discovery, and sub-agent suspend/resume
behavior across server, QStash, and device RPC flows. (#15543, #15566,
#15481, #15620, #15591)
- **Connector and sandbox platform** — Expands connector permissions,
custom OAuth MCP connector onboarding, sandbox provider support, and
user-uploaded file sync into cloud sandbox runs. (#15463, #15546,
#15184, #15550)
- **Desktop and CLI reliability** — Fixes desktop cold-start,
auto-update, Windows build, CLI skill discovery, and `lh connect` agent
dispatch paths. (#15547, #15525, #15527, #15562, #15632, #15634)
- **Pages and sharing** — Refreshes topic sharing, improves Page Editor
layout behavior, and routes Page Agent tool execution through the
server-side editor path. (#15581, #15556, #15588, #15023, #15610)
- **Model availability and provider updates** — Adds user-scoped LobeHub
model availability, Claude Fable 5, Qwen thinking preservation, and
MiniMax M3 updates. (#15590, #15639, #13494, #15376)

---

## 🏗️ Core Product & Architecture

### Agent Runtime & Heterogeneous Agents

- Improves sub-agent lifecycle handling, including async suspend/resume,
queue-mode QStash resume delivery, and blocking nested sub-agent calls.
(#15481, #15620, #15575)
- Stabilizes heterogeneous agent ingestion and streaming with raw stream
dumps, per-turn usage, image forwarding on regenerate, and
duplicate-text fixes. (#15602, #15577, #15592, #15585)
- Adds execution-device and working-directory controls across device
RPC, legacy defaults, and remote-spawned Claude Code sessions. (#15543,
#15566, #15591, #15572)
- Improves runtime diagnostics and compatibility, including Gemini
multimodal output capture, abort stream semantics, and trace quality
analysis. (#15535, #13677, #15508)

---

## 📱 Platforms, Integrations & UX

### Connectors, Sandbox & Tools

- Ships API-level connector tool permissions, custom OAuth MCP connector
onboarding, and connector-first runtime execution. (#15463, #15546)
- Adds sandbox provider support, cloud sandbox file sync, and safer
external URL file input handling with SSRF validation. (#15184, #15550,
#12657)
- Improves tool visibility and execution with pinned app-fixed tools,
ANSI output rendering, gateway-tunneled MCP calls, and automatic
headless tool runs. (#15509, #15516, #15469, #15492)

### Desktop, CLI & Web UX

- Restores desktop startup and reload behavior, preserves IPC error
causes, and keeps the tab bar new-tab action visible across routes.
(#15547, #15597, #15638)
- Fixes desktop update and build stability for browser quit guards,
macOS update signing, and Windows Visual Studio detection. (#15525,
#15527, #15562)
- Shows the plan-limit upgrade UI on desktop builds. (#15628)
- Adds the Agent Run delivery checker and fixes CLI device dispatch plus
skill list/search output. (#15489, #15634, #15632)
- Refreshes onboarding, auth source preservation, topic UI states,
referral/Fable campaign copy, and chat-input control bar behavior.
(#15629, #15544, #15573, #15614, #15616, #15617, #15622, #15643)

---

## 🔒 Security, Reliability & Rollout Notes

- External URL file input now includes SSRF validation for safer Google
file handling. (#12657)
- Database workspace-scope migrations are part of this release;
self-hosted operators should run the normal migration path before
serving the updated app. (#15446, #15465, #15468, #15472)
- The release branch was re-cut from `canary` and includes the latest
`main` release-version commit so `v2.2.2` is the verified compare base.

---

## 👥 Contributors

@ONLY-yours, @sxjeru, @hardy-one, @xujingli, @hezhijie0327, @Coooolfan,
@arvinxx, @tjx666, @Innei, @rivertwilight, @rdmclin2, @cy948,
@AmAzing129

**Full Changelog**:
v2.2.2...release/weekly-20260610-recut-3
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

size:M This PR changes 30-99 lines, ignoring generated files.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant