Skip to content

✨ feat(heterogeneous-agent): add Codex desktop integration#14067

Merged
arvinxx merged 15 commits into
canaryfrom
feat/lobe-8052-codex-desktop-integration
Apr 23, 2026
Merged

✨ feat(heterogeneous-agent): add Codex desktop integration#14067
arvinxx merged 15 commits into
canaryfrom
feat/lobe-8052-codex-desktop-integration

Conversation

@arvinxx

@arvinxx arvinxx commented Apr 22, 2026

Copy link
Copy Markdown
Member

πŸ’» Change Type

  • ✨ feat
  • πŸ› fix
  • ♻️ refactor
  • πŸ’„ style
  • πŸ‘· build
  • ⚑️ perf
  • βœ… test
  • πŸ“ docs
  • πŸ”¨ chore

πŸ”— Related Issue

Refs LOBE-8052
Fixes LOBE-8053
Fixes LOBE-8054

πŸ”€ Description of Change

This PR covers the Codex desktop integration slice plus the follow-up hardening work that landed after the original MVP draft.

It includes:

  • refactoring the Electron heterogeneous-agent execution path into provider drivers, shared stream framing, and provider registration that can support both Claude Code and Codex
  • adding the Codex CLI driver and adapter for thread/turn/item events, session persistence, usage mapping, command execution lifecycle events, and multi-step rendering in the unified gateway/UI pipeline
  • wiring Codex into the desktop UI, including the creation entry, provider metadata, custom command detection/editing, status cards, system-tools detection, and install/auth/rate-limit guidance
  • fixing heterogeneous persistence and UX gaps discovered during integration (including Codex step splitting and cumulative tools_calling streaming to avoid orphan tool warnings)
  • adding a heterogeneous-agent debugging guide plus regression tests across the controller, adapter, executor, chat error rendering, and profile status flows

Out of scope for this PR:

  • image attachment support for the Codex CLI
  • richer non-command_execution Codex item rendering
  • further provider-specific runtime configuration beyond the current desktop integration path

πŸ§ͺ How to Test

  • Tested locally
  • Added/updated tests
  • No tests needed

Suggested verification commands:

  • cd apps/desktop && bunx vitest run --silent='passed-only' 'src/main/controllers/__tests__/HeterogeneousAgentCtr.test.ts'
  • cd packages/heterogeneous-agents && bunx vitest run --silent='passed-only' 'src/config.test.ts' 'src/registry.test.ts' 'src/adapters/codex.test.ts'
  • bunx vitest run --silent='passed-only' 'src/store/chat/slices/aiChat/actions/__tests__/gatewayEventHandler.test.ts' 'src/store/chat/slices/aiChat/actions/__tests__/heterogeneousAgentExecutor.test.ts'
  • bunx vitest run --silent='passed-only' 'src/features/Conversation/Error/index.test.tsx' 'src/features/Electron/HeterogeneousAgent/StatusGuide/index.test.tsx' 'src/routes/(main)/agent/profile/features/ProfileEditor/HeterogeneousAgentStatusCard.test.tsx'
  • bunx vitest run --silent='passed-only' 'src/routes/(main)/home/_layout/hooks/useCreateMenuItems.test.tsx'

πŸ“Έ Screenshots / Videos

Before After
N/A N/A

πŸ“ Additional Information

This description intentionally reflects the current committed branch state rather than the original MVP-only PR draft.

@vercel

vercel Bot commented Apr 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 Apr 23, 2026 10:56am

Request Review

@codecov

codecov Bot commented Apr 22, 2026

Copy link
Copy Markdown

Codecov Report

❌ Patch coverage is 89.31553% with 128 lines in your changes missing coverage. Please review.
βœ… Project coverage is 67.23%. Comparing base (042987f) to head (e1c9a1f).
⚠️ Report is 14 commits behind head on canary.

Additional details and impacted files
@@            Coverage Diff             @@
##           canary   #14067      +/-   ##
==========================================
+ Coverage   67.04%   67.23%   +0.19%     
==========================================
  Files        2110     2124      +14     
  Lines      180144   181991    +1847     
  Branches    21374    18895    -2479     
==========================================
+ Hits       120775   122360    +1585     
- Misses      59246    59508     +262     
  Partials      123      123              
Flag Coverage Ξ”
app 60.10% <89.31%> (+0.36%) ⬆️
database 92.27% <ΓΈ> (ΓΈ)
packages/agent-runtime 79.82% <ΓΈ> (ΓΈ)
packages/context-engine 83.24% <ΓΈ> (ΓΈ)
packages/conversation-flow 92.40% <ΓΈ> (ΓΈ)
packages/file-loaders 87.02% <ΓΈ> (ΓΈ)
packages/memory-user-memory 74.74% <ΓΈ> (ΓΈ)
packages/model-bank 99.86% <ΓΈ> (ΓΈ)
packages/model-runtime 84.32% <ΓΈ> (ΓΈ)
packages/prompts 69.08% <ΓΈ> (ΓΈ)
packages/python-interpreter 92.90% <ΓΈ> (ΓΈ)
packages/ssrf-safe-fetch 0.00% <ΓΈ> (ΓΈ)
packages/utils 88.41% <ΓΈ> (ΓΈ)
packages/web-crawler 88.66% <ΓΈ> (ΓΈ)

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

Components Coverage Ξ”
Store 67.24% <96.96%> (+0.62%) ⬆️
Services 51.78% <28.57%> (-0.03%) ⬇️
Server 66.90% <ΓΈ> (ΓΈ)
Libs 52.50% <ΓΈ> (ΓΈ)
Utils 80.09% <ΓΈ> (ΓΈ)
πŸš€ New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
  • πŸ“¦ JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

@arvinxx arvinxx changed the title ✨ feat(heterogeneous-agent): integrate Codex desktop MVP ✨ feat(heterogeneous-agent): add Codex desktop integration Apr 23, 2026
@arvinxx arvinxx marked this pull request as ready for review April 23, 2026 11:13
@dosubot dosubot Bot added the size:XXL This PR changes 1000+ lines, ignoring generated files. label Apr 23, 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, your pull request is larger than the review limit of 150000 diff characters

@dosubot dosubot Bot added feature:agent Assistant/Agent configuration and behavior platform:desktop Desktop client labels Apr 23, 2026
@dosubot dosubot Bot added the πŸ“ Documentation Improvements or additions to documentation label Apr 23, 2026
@arvinxx arvinxx merged commit 82096dc into canary Apr 23, 2026
57 of 62 checks passed
@arvinxx arvinxx deleted the feat/lobe-8052-codex-desktop-integration branch April 23, 2026 11:18

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

πŸ’‘ Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: e1c9a1fcd9

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 πŸ‘.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Comment on lines +35 to +37
const inputCacheMissTokens = raw.input_tokens || 0;
const inputCachedTokens = raw.cached_input_tokens || 0;
const totalInputTokens = inputCacheMissTokens + inputCachedTokens;

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

P1 Badge Compute Codex token totals from non-cached input

input_tokens in Codex usage already includes cached tokens, so adding cached_input_tokens again overcounts every turn that hits cache. With this mapping, totalInputTokens/totalTokens are inflated whenever cached_input_tokens > 0, which will persist incorrect usage and skew any token/cost displays that rely on these fields.

Useful? React with πŸ‘Β / πŸ‘Ž.

Comment on lines +320 to +323
const status =
command === defaultCommand
? await this.app.toolDetectorManager?.detect?.(defaultCommand, true)
: await detectHeterogeneousCliCommand(

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

P2 Badge Honor session env when preflighting CLI availability

The preflight detector runs before spawn but does not receive session.env, while the actual process is spawned with session.env merged into env. In setups where the CLI is only discoverable through that per-agent environment (for example a PATH override), preflight will incorrectly report cli_not_found and abort execution even though the subsequent spawn would succeed.

Useful? React with πŸ‘Β / πŸ‘Ž.

arvinxx added a commit that referenced this pull request Apr 27, 2026
# πŸš€ LobeHub v2.1.53 (20260427)

**Release Date:** April 27, 2026
**Since v2.1.52:** 194 merged PRs Β· 17 contributors

> Introduce Heterogeneous Agent β€” Claude Code and Codex run as
first-class desktop runtimes, paired with a new Agent Signal package,
sharper desktop UX, and a wave of flagship model additions.

---

## ✨ Highlights

- **Introduce Heterogeneous Agent** β€” Claude Code and Codex run as
first-class desktop agents: subagent rendering, partial-message
streaming, multi-turn resume, terminal error surfacing, rich tool
inspectors, and runtime polish. (#14162, #13754, #14067, #14001, #13970,
#13942)
- **Screen capture & Quick Chat tray** β€” New desktop screen capture
overlay (macOS permission-gated) with Quick Chat tray and upload
pipeline improvements; chat input auto-focuses on overlay mount.
(#13818, #14097, #14105)
- **Desktop topic & tab UX** β€” Dedicated topic popup window with
cross-window sync, Cmd+W/Cmd+T tab shortcuts, TabBar polish, recent
working directories expanded to 20, and human approval notifications.
(#13957, #13983, #13972, #14036, #14092)
- **Git workflow built-in** β€” One-click pull/push from the branch chip,
ahead/behind badge, and submodule/worktree repo detection. (#14041,
#13980, #13978)
- **Agent Signal package** β€” New `@lobechat/agent-signal` runtime for
dynamic memory feedback signals, with OTel metrics and self-iteration in
Lab. (#14157, #14170, #14159, #14169, #14187)
- **New models** β€” Claude Opus 4.7 with `xhigh` effort tier, GPT-5.5,
DeepSeek V4 Flash/Pro with reasoning slider, Kimi K2.6, MiMo-V2.5/Pro,
gpt-image-2, Qwen3.6 Flash/Plus, and Pixverse-c1. (#13903, #14147,
#14114, #14004, #14089, #14039, #13923)
- **New providers** β€” OpenCode Zen, OpenCode Go, and Azure OpenAI Router
runtime. (#13943, #14064, #13823)
- **Mobile settings overhaul** β€” Full settings menu and responsive
profile layout for mobile. (#14019)

---

## πŸ—οΈ Heterogeneous Agent

- Claude Code runtime, working-directory awareness, and sidebar polish.
(#13970)
- CC subagent rendering with persistent streamed text; parallel-tool
orphan fix. (#14001, #13968, #14024)
- Per-step usage persisted to each step assistant message. (#13964)
- Per-phase workflow expand defaults; full-expand toggle with
three-level expansion. (#14171, #13906)
- Hetero-mode actions bar; tool inspector polish. (#13963, #14034,
#14030)
- Codex desktop integration with rich tool rendering and devtools
preview. (#14067, #14100)
- Codex terminal error surfacing and CLI output tracing. (#14166)
- Tighten `isCanUseVision` default and add aggregator fallback. (#14172)
- Persist `ccSessionId` in topic metadata for CC multi-turn resume.
(#13902)
- CC account card, topic filter, and integration polish. (#13955,
#13942, #13950)
- Token-level deltas streamed via `--include-partial-messages`. (#13929)

---

## 🧠 Agent Signal & Self-Iteration

- New `@lobechat/agent-signal` package with dynamic feedback signals.
(#14157)
- AgentSignalRuntime wired through agent-tracing and observability-otel
metrics. (#14170, #14159)
- Self-iteration feature flag added to Lab; front-side flag check.
(#14169, #14186)
- Signal policy for receiving memory feedback dynamically. (#14187)

---

## πŸ’¬ Conversation

- Queue follow-up sends during running CC turns. (#14179)
- Persist per-topic chat scroll position; pin user message + fold long
messages. (#14191, #14056)
- Inline resend when editing last user message. (#14080)
- Disable first-block markdown streaming to prevent flicker. (#14193,
#13904)
- Prevent Markdown stream replay when vlist remounts streaming items.
(#14086)
- Stop repinning after manual scroll; unify scroll-to-user + spacer
hooks. (#14099, #14132)

---

## πŸ“± Platforms & Integrations

### Desktop / Electron

- Screen capture overlay, Quick Chat tray, and upload pipeline
improvements. (#13818)
- macOS permission gate for screen capture; auto-focus chat panel input.
(#14097, #14105)
- Dedicated topic popup window with cross-window sync. (#13957)
- TabBar polish: `+` button for new topic, dark theme blend, close icon
by default. (#13972, #14203, #13973)
- Recent working directories expanded from 5 to 20; submodule/worktree
repo detection. (#14036, #13978)
- Cmd+W / Cmd+T tab shortcuts and global shortcut consolidation.
(#13983, #13880)
- Linux icon configuration; human approval desktop notifications.
(#14042, #14092)

### Git Workflow

- One-click pull/push from branch chip; ahead/behind badge with
refactored GitCtr. (#14041, #13980)

### Mobile

- Full settings menu and responsive profile layout. (#14019)
- Agent route added to mobile router; mobile agent topic route
registered. (#14103, #14158)
- Session list skeleton row layout corrected. (#14040)

### Bot / Messaging

- DM strategy support; bot emoji and markdown render optimization.
(#14201, #14091, #14140)
- Slack webhook fix; bot platform setup guide reference. (#14052,
#14121)

---

## πŸ€– Models & Providers

### New models

- **Claude Opus 4.7** with `xhigh` effort tier; strip temperature/top_p.
(#13903, #13909)
- **GPT-5.5**. (#14147)
- **DeepSeek V4** Flash/Pro cards with reasoning slider; cache-hit and
Pro discount pricing. (#14114, #14209, #14196, #14131)
- **Kimi K2.6** model with LobeHub-hosted card. (#14004, #14006)
- **MiMo-V2.5 / V2.5-Pro**. (#14089)
- **gpt-image-2**, **Qwen3.6 Flash/Plus**, **Pixverse-c1**. (#14039,
#13923)

### New providers

- **OpenCode Zen** and **OpenCode Go** with env-var support. (#13943,
#14064)
- **Azure OpenAI Router** runtime support. (#13823)
- Model alias mapping for image and video runtimes. (#13896)
- Seedance video models migrated to Dreamina. (#14144)

### Runtime reliability

- Sanitize invalid tool_call arguments to unbreak strict providers.
(#14033)
- Tolerate null `function.name` in streaming tool_call deltas. (#14139)
- Preserve Gemini 3 `thoughtSignature` in `call_tools_batch`
normalization. (#14032)
- Downgrade `image_url` parts when target model lacks vision. (#14029)
- Preserve Cloudflare provider error context. (#14136)
- Use `safety_identifier` for OpenAI Responses API. (#14148)
- Unwrap underlying PG error in `formatErrorEventData`. (#14038)

---

## πŸ–₯️ User Experience

- **Onboarding** β€” Preset agent naming suggestions, structured hunk ops
for `updateDocument`, persona analytics snapshot, footer promotion
pipeline, wrap-up button. (#13931, #13989, #13930, #13853, #13934)
- **Document workflow** β€” Agent documents promoted as primary workspace
panel; history management and compare workflow; web-crawl docs
associated with agent documents. (#13924, #13725, #13893)
- **cmdk** β€” Agent identity surfaced on topic search results;
topic/message search scoped to current agent. (#14204, #13960)
- **Floating chat panel** and workspace improvements. (#13887)
- **Topic completion status** with dropdown action and filter. (#14005)

---

## πŸ”§ Tooling

- Redis-backed feature flag provider for runtime config. (#14098)
- Vite upgraded to 8.0.0 with Rolldown strict execution order. (#12720,
#14058)
- `@lobechat/model-bank` automated npm release with provenance. (#14015,
#14017, #14018)
- Skill activation fallback when `activateTools` cannot find identifier.
(#14010)
- Cron tool: timezone and existing jobs injected into system prompt;
clarified `lobe-gtd` and `lobe-cron` descriptions. (#14012, #14013)

---

## πŸ”’ Security & Reliability

- **Security:** uuid bumped to v14 (advisory). (#14083)
- **Security:** validate avatar URL and scope old-avatar deletion to
owner. (#13982)
- **Security:** clear OIDC sessions on better-auth signout; return 401
(not 500) for expired OIDC JWT. (#13916, #14014)
- **Reliability:** scope pending-approval check to current assistant
turn. (#14182)
- **Reliability:** sanitize heterogeneous-agent attachment cache
filenames. (#13937)
- **Reliability:** reduce subagent task status error noise. (#14026)

---

## πŸ‘₯ Contributors

Huge thanks to **17 contributors** who shipped **194 merged PRs** this
week.

@hardy Β· @shaun0927 Β· @hezhijie0327 Β· @sxjeru Β· @arvinxx Β· @Innei Β·
@tjx666 Β· @lijian Β· @neko Β· @rdmclin2 Β· @AmAzing129 Β· @sudongyuer Β·
@CanisMinor Β· @rivertwilight

Plus @lobehubbot and renovate[bot] for maintenance.

---

**Full Changelog**:
v2.1.52...v2.1.53
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

πŸ“ Documentation Improvements or additions to documentation feature:agent Assistant/Agent configuration and behavior platform:desktop Desktop client size:XXL This PR changes 1000+ lines, ignoring generated files.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant