Skip to content

🐛 fix(hetero): forward user images on regenerate so vision input isn't dropped#15592

Merged
arvinxx merged 2 commits into
canaryfrom
fix/hetero-regenerate-image-loss
Jun 9, 2026
Merged

🐛 fix(hetero): forward user images on regenerate so vision input isn't dropped#15592
arvinxx merged 2 commits into
canaryfrom
fix/hetero-regenerate-image-loss

Conversation

@arvinxx

@arvinxx arvinxx commented Jun 9, 2026

Copy link
Copy Markdown
Member

💡 Description of Change

The heterogeneous (Claude Code / Codex) regenerate / resend path
(runHeterogeneousFromExistingMessage) only forwarded the text prompt to
executeHeterogeneousAgent — it never carried the original user message's
imageList.

The normal send path already reads imageList off the persisted user
message and passes it through to the CLI (conversationLifecycle.ts). The
regenerate path was asymmetric, so re-running an image turn lost the
attachment:

  • When the session couldn't be resumed (e.g. cwd changed →
    resolveHeteroResume drops the sessionId), the image was gone entirely.
  • When resume succeeded the prior image still lived in the CLI's session
    context, which is why this only reproduced sometimes.

Fix (3 edits, one file)

  • runHeterogeneousFromExistingMessage now accepts an optional imageList
    and forwards it to executeHeterogeneousAgent (same shape as the send path).
  • regenerateUserMessage's hetero branch passes the original message's
    item.imageList.

🔗 Related

Part of the heterogeneous-agent vision support.

Stacked PR — based on fix/agent-working-dir-by-device (#15591) because
both edit the same runHeterogeneousFromExistingMessage function and #15591
isn't on canary yet. Retarget this PR's base to canary once #15591
merges
(GitHub usually auto-retargets).

✅ How to Test

  1. In a desktop hetero (Claude Code) agent, send a message with an image
    attachment
    , get a response.
  2. Click regenerate on that turn.
  3. The CLI should receive the same image again (vision input preserved),
    instead of re-running on text only.

Automated: bunx vitest run src/features/Conversation/store/slices/generation/regenerateHeteroImages.test.ts
— asserts executeHeterogeneousAgent receives the original imageList, and
undefined when the message had no images. Verified the image-forwarding case
fails without the fix and passes with it.

🤖 Generated with Claude Code

arvinxx and others added 2 commits June 9, 2026 18:53
…egacy-only

The chat-input directory picker writes the selection to
`agencyConfig.workingDirByDevice[deviceId]`, but the send / regenerate /
streaming / placeholder paths resolved the agent working directory via
selectors that only read the legacy `localAgentWorkingDirectoryMap`. So a
freshly picked directory was silently dropped and execution fell back to a
default cwd (the app's own repo), losing the user's project and `--resume`.

Make both `getAgentWorkingDirectoryById` and `currentAgentWorkingDirectory`
device-aware: per-device choice > legacy > desktop/home, with the target
device resolved from a passed-in `currentDeviceId` (kept out of the selector
so hook callers stay reactive). Update all call sites to supply the device id.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
…t dropped

The hetero regenerate/resend path (`runHeterogeneousFromExistingMessage`)
only forwarded the text prompt to `executeHeterogeneousAgent`, never the
original user message's `imageList`. The send path reads imageList off the
persisted user message and passes it along; this path must too. Without it,
regenerating an image turn re-ran the CLI with no attachments (fully lost
when the session couldn't be resumed, e.g. cwd changed).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
@dosubot dosubot Bot added the size:S This PR changes 10-29 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

@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 11:06am

Request Review

@dosubot dosubot Bot added feature:agent Assistant/Agent configuration and behavior feature:vision labels Jun 9, 2026
@codecov

codecov Bot commented Jun 9, 2026

Copy link
Copy Markdown

Codecov Report

❌ Patch coverage is 87.23404% with 6 lines in your changes missing coverage. Please review.
✅ Project coverage is 67.13%. Comparing base (b295265) to head (41a405d).
⚠️ Report is 10 commits behind head on canary.

Additional details and impacted files
@@             Coverage Diff             @@
##           canary   #15592       +/-   ##
===========================================
- Coverage   79.34%   67.13%   -12.21%     
===========================================
  Files         996     3353     +2357     
  Lines      123342   338472   +215130     
  Branches     9977    36139    +26162     
===========================================
+ Hits        97864   227248   +129384     
- Misses      25287   111033    +85746     
  Partials      191      191               
Flag Coverage Δ
app 60.14% <87.23%> (?)
database 89.90% <ø> (ø)
packages/agent-manager-runtime 49.69% <ø> (ø)
packages/agent-runtime 81.06% <ø> (ø)
packages/app-config 44.58% <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/env 11.42% <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/locales 0.87% <ø> (ø)
packages/memory-user-memory 74.99% <ø> (ø)
packages/model-bank 99.99% <ø> (ø)
packages/model-runtime 84.23% <ø> (ø)
packages/prompts 72.51% <ø> (ø)
packages/python-interpreter 92.90% <ø> (ø)
packages/ssrf-safe-fetch 0.00% <ø> (ø)
packages/trpc 40.43% <ø> (ø)
packages/types 35.21% <ø> (ø)
packages/utils 85.06% <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 68.24% <84.37%> (∅)
Services 54.25% <ø> (∅)
Server 97.03% <ø> (∅)
Libs 54.23% <ø> (∅)
Utils 82.08% <ø> (-17.92%) ⬇️
🚀 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.

Base automatically changed from fix/agent-working-dir-by-device to canary June 9, 2026 11:45
@dosubot dosubot Bot added size:L This PR changes 100-499 lines, ignoring generated files. and removed size:S This PR changes 10-29 lines, ignoring generated files. labels Jun 9, 2026
@arvinxx arvinxx merged commit 6c6c869 into canary Jun 9, 2026
64 of 67 checks passed
@arvinxx arvinxx deleted the fix/hetero-regenerate-image-loss branch June 9, 2026 11:50
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

feature:agent Assistant/Agent configuration and behavior feature:vision 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