Pull Request Explorer

Summary

Replace native select with @base-ui/react primitives

Improves Windows UI rendering for overlay agent/model pickers by replacing native <select> elements with Base UI primitives, enhancing visual consistency and performance.

Health Assessment

• • Fast review and merge, minimal changes, no rework, indicates straightforward UI tweak.

Summary

Hide device switcher for regular agent chat

Removes the device switcher from regular agent chat input, preventing UI clutter and ensuring correct component usage.

Health Assessment

• • Quick fix with minimal changes, no rework, fast review.

Summary

Unify TypeScript peer resolution to 6.x

Ensures a single TypeScript 6.x version across the workspace, eliminating duplicate peer graphs and improving build stability for developers.

Health Assessment

• • Fast review and merge with minimal rework; the change is small and focused on dependency consistency.

Summary

Clean up LOBE-XXX code annotations

Improves code readability and maintainability, reducing future technical debt.

Health Assessment

• • Fast review and merge with minimal changes, indicating low risk and high confidence.

Summary

Add floating chat panel to agent document previews

Users can enable a floating chat panel in agent document previews via a Labs toggle, improving collaboration while keeping the feature disabled by default to avoid clutter.

Health Assessment

• • PR merged within 18 minutes with a single comment, indicating a straightforward change with minimal review friction.

Summary

Unify select width and migrate to base-ui Select

Standardizes select component widths and updates to the newer base-ui library, improving UI consistency and maintainability on the service-model settings page.

Health Assessment

• • Fast review and merge with minimal changes, indicating a straightforward UI refactor with low risk.

Summary

Skip redirect for agent inbox with message param

Ensures new users arriving via agent inbox links are not prematurely redirected to onboarding, preserving message delivery.

Health Assessment

• • Fast review cycle (0.4h), minimal code changes, low complexity and risk.

Summary

Fix markdown escape issue in copy

Ensures copied user messages preserve original formatting by removing unintended escape characters, improving copy‑paste accuracy.

Health Assessment

• • Quick AI‑assisted fix with minimal changes and no review delays.

Summary

Fix hetero-agent UI conflict and sync runtime mode

Ensures the device switcher and sandbox mode selector are mutually exclusive and keeps runtime mode in sync, improving user experience and preventing misconfiguration.

Health Assessment

• • Quick fix with minimal changes, AI-assisted, no back‑and‑forth, merged within 24 minutes.

Summary

Add hidden iMessage backend foundation

Adds backend support for iMessage bot integration, enabling message handling and gateway runtime without exposing UI or platform lists.

Health Assessment

• • Fast cycle time with minimal review friction; large code addition but single review round indicates efficient process.

Summary

Fix tab bar flicker with debounce

Improves desktop tab stability by debouncing route meta updates, preventing flicker and ensuring consistent title and avatar display during navigation.

Health Assessment

• • Quick review and merge with no rework, indicating a straightforward bug fix.

Summary

Fix inactive tab title when topic auto-named

Ensures background tabs in the desktop Electron app update their titles to reflect auto‑named topics, keeping tab titles consistent for users.

Health Assessment

• • Quick merge with minimal review, indicating a straightforward bug fix with clear tests.

Summary

Embed thread chat in document preview portal

Adds an embedded chat panel to the document preview portal, enabling users to converse with the agent about the document without leaving the portal, improving user engagement and reducing context switching.

Health Assessment

• • The PR was reviewed immediately and merged within 20 hours, indicating a smooth review process. The large removal of dead code and addition of a new chat feature required significant refactoring but was handled efficiently.

Summary

Fix exec-agent credential substitution logic

Ensures credentials and Klavis services are correctly substituted in exec-agent mode, preventing template placeholders from leaking into agent prompts.

Health Assessment

• • Quick, single-commit fix with AI-assisted review, minimal code churn and no major risk to production.

Summary

Fix long version string overflow in modal

Ensures the capability status tag displays correctly, improving the user interface and preventing layout issues for users checking platform agent details.

Health Assessment

• • Quick, single-file change with no review delays; minimal risk to production.

Summary

Fix placeholder handling in heterogeneous agent persistence

Ensures cloud cold‑starts don’t prepend placeholder text to Claude Code responses, improving user experience.

Health Assessment

• • Quick, single‑commit fix with fast review and no rework, indicating a low‑risk, low‑friction change.

Summary

Refactor command observation timeout handling

Improves timeout handling for command execution, enhancing reliability and reducing errors.

Health Assessment

• • The PR was reviewed and merged within a day, indicating a smooth process with minimal friction. The moderate scope of changes and lack of critical bugs suggest low risk.

Summary

Polish agent topic manager UI and routing

Improves user experience by reducing visual clutter, clarifying authorization prompts, and preserving navigation context when switching agents.

Health Assessment

• • Quick polish with minimal review friction, merged within 3 hours, indicating efficient process.

Summary

Prompt account selection for Google OAuth

Ensures users always see the Google account chooser during sign‑in, enabling seamless switching between multiple Google accounts and aligning with standard SSO UX.

Health Assessment

• • Fast turnaround with a single review; minimal code changes and no breaking impact.

Summary

Add CTA in folder hierarchy empty state

Provides an empty state with icon, title, hint, and Add button for libraries with no files, improving user onboarding.

Health Assessment

• • Quick review and merge within 11 hours, minimal changes, straightforward fix.

Summary

Fix sidebar order across bottom spacer

Users can now reorder sidebar items across the bottom spacer, improving customization and UI consistency.

Health Assessment

• • Quick fix with minimal rework, fast review, low risk.

Summary

Fix prompt stability for input completion

Ensures consistent prompt hashing by separating static system instructions from dynamic conversation context, improving traceability and reducing duplicate entries.

Health Assessment

• • AI-assisted fix resolved prompt hashing issue quickly with minimal code changes and immediate approval.

Summary

Fix userId dispatch, gate local-system, add device switcher

This PR fixes a missing userId error that prevented desktop device dispatch, ensures sandbox agents don’t trigger local‑system tools, and adds a UI switcher for selecting desktop devices, improving reliability and user control.

Health Assessment

• • Quick fix with minimal changes, resolved immediately after review, low risk.

Summary

Add per-agent topic management page

Users can now manage topics for each agent via a dedicated page, with filtering, bulk actions, and improved UI, enhancing productivity and reducing clutter.

Health Assessment

• • The PR underwent rapid iteration with multiple commits but was reviewed and merged within 15.5 hours, indicating efficient collaboration and low overall risk.

Summary

Disable automatic URL highlighting in chat input

Prevents unintended link serialization, improving user experience by keeping plain URLs unformatted.

Health Assessment

• • Quick fix with minimal changes, reviewed immediately, merged within 40 minutes.

Summary

Fix usage cost preservation in custom streams

This change preserves usage cost in custom streams, ensuring accurate billing and preventing revenue loss.

Health Assessment

• • Quick fix with minimal changes, reviewed immediately, no rework needed.

Summary

Add PageAgent initPage streaming arguments

Adds a streaming renderer for PageAgent initPage, allowing for live markdown previews from partial arguments.

Health Assessment

• • The PR was reviewed quickly, but the scope of changes is large, indicating potential complexity.

Summary

Fix error code capture in model runtime

Captures detailed error codes from LLM generation failures, improving error visibility. This enhances dashboard accuracy and aids troubleshooting.

Health Assessment

• • Quick fix with minimal changes, no rework, low risk.

Summary

Bump @lobehub/ui dependency to 5.15.1

Updates UI library to latest version, removing obsolete style compensations and ensuring menu components render correctly.

Health Assessment

• • Quick dependency bump with minimal code changes and immediate review, indicating low risk and high confidence in stability.

Summary

Align file icons with folder icons in explorer

Enhances visual consistency in file explorer, making navigation clearer for users. This small UI tweak improves usability and reduces cognitive load.

Health Assessment

• • Merged within 1.7 hours with no review rounds, indicating a straightforward UI fix with minimal risk.

Summary

Add OpenTelemetry instrumentation for Agent Runtime

Enables full agent invocation tree visualization in Jaeger/Grafana, improving observability and debugging for LobeHub agents.

Health Assessment

• • Rapid review and multiple commits indicate active iteration; large code changes but quick feedback suggest a healthy process.

Summary

Fix desktop hetero task notify URL, auth header, child env

Corrects bugs that prevented the desktop app from receiving openclaw results by updating the notify URL, auth header, and child environment variables.

Health Assessment

• • Fast turnaround with a single commit and no rework; minimal code changes and low complexity.

Summary

Fix per-agent working directory store handling

Ensures agent working directories are stored in state, enabling reactive updates and consistent UI across components.

Health Assessment

• • Fast turnaround with minimal changes and quick review, indicating low complexity.

Summary

Fix heavy fields in agent runtime stream events

Reduces Redis write size to avoid exceeding limits, preventing runtime crashes and improving system reliability for agent operations.

Health Assessment

• • Fast turnaround with a single commit and no review rework indicates a straightforward, low‑risk bug fix that quickly restored stability to the agent runtime stream handling.

Summary

Fix heteroIngest race by passing assistantMessageId

This change eliminates race conditions that caused agent executions to fail, ensuring conversations complete without errors. It improves reliability and user experience for agents.

Health Assessment

• • Quick resolution with minimal review, indicating a straightforward bug fix.

Summary

Improve Vite route chunk preloading

Enhance performance by prewarming more route chunks during idle time, covering additional desktop secondary routes.

Health Assessment

• • The PR was merged quickly with minimal review comments, indicating a straightforward and well-tested change.

Summary

Add missing i18n keys for follow-up feature

Ensures Settings UI displays localized labels for follow-up suggestions in Chinese and English, improving user experience.

Health Assessment

• • Quick fix with minimal changes, reviewed immediately, no rework needed.

Summary

Fix llm-generation-tracing scenario backfill

Corrects tracing metadata so new rows record proper task brief and judge scenarios, improving data accuracy and reducing unknown entries.

Health Assessment

• • The PR was merged within 36 minutes with no review rounds, indicating a straightforward, low‑risk fix that required minimal code changes.

Summary

Fix Turbopack glob warning in LLM tracing

This change removes a noisy build-time warning that was inflating the build trace. It improves developer experience by keeping build logs clean and reducing build time.

Health Assessment

• • Quick fix with minimal changes, no rework, fast review, low risk.

Summary

Implement Hermes agent chain logic

Adds direct CLI integration for Hermes agents, enabling faster, multi‑turn chat responses and improved platform capability for users.

Health Assessment

• • Fast review cycle (0h) and single round of AI‑powered feedback led to a quick merge with minimal friction.

Summary

Fix image responses to explain text-only content

Improves user experience by providing clear guidance when image generation returns text-only responses, preventing confusion and mislabeling safety refusals.

Health Assessment

• • The PR was merged within 12 hours with minimal review comments, indicating a smooth review process and low complexity.

Summary

Add tracing ID pre-allocation and feedback router

Enables per-call feedback loop for LLM generation, improving observability and user feedback handling.

Health Assessment

• • Fast review and single commit indicate smooth process, but large scope and many files suggest high impact and potential risk.

Summary

Normalize, dedupe, and fix project overview

Streamlines skill documentation by removing duplicate entries and standardizing descriptions, improving maintainability. Adds an audit skill to automate future checks, ensuring consistent quality.

Health Assessment

• • Rapid review and merge with minimal iterations, indicating straightforward documentation updates.

Summary

Add task-handoff tracing and prompt versioning

Adds precise task-handoff tracing and prompt versioning, improving analytics and debugging. Also updates UI preview styling for clearer file previews.

Health Assessment

• • Quick turnaround with minimal rework; AI assistance accelerated development.

Summary

Add execution target switcher in chat composer

Enables users to select where heterogeneous agents run—desktop, cloud sandbox, or remote device—enhancing flexibility and control over agent execution.

Health Assessment

• • Rapid review and single commit cycle, but the PR introduces a large, cross‑cutting feature spanning frontend UI and backend dispatch logic, indicating a high‑impact change with potential integration complexity.

Summary

Add execAgent plumbing for self-iteration migration

Establishes infrastructure for future agent execution enhancements, enabling safer migration without impacting current functionality.

Health Assessment

• • PR merged within 30 minutes with minimal review, indicating low complexity and high confidence in the changes.

Summary

Health Assessment

Summary

Refactor user memories to resolve agent config

This refactor enables user memory services to resolve agent configuration from per‑user ServiceModel settings, improving flexibility and reducing reliance on environment defaults.

Health Assessment

• • The PR had a quick review turnaround and minimal back‑and‑forth, but the large code churn suggests significant refactoring effort.

Summary

Fix image MIME normalization for uploads

Ensures image MIME types match actual bytes, preventing provider validation errors and improving upload reliability.

Health Assessment

• • Fast 1.5‑hour cycle with AI‑driven reviews and no human blockers, quickly resolving MIME mismatch issues.

Summary

Fix agent projectSkills visibility regardless of device

Ensures client-provided project skills are always surfaced to the agent, preventing silent failures when device resolution fails. This improves reliability and user experience.

Health Assessment

• • Quick fix with minimal changes, no rework, fast review, low risk.