Skip to content

Releases: EKKOLearnAI/hermes-studio

v0.6.17

17 Jun 10:46

Choose a tag to compare

Changelog

  • 修复 Codex 和 Claude Code 的对话启动问题。

v0.6.16

17 Jun 03:03

Choose a tag to compare

Highlights

  • Bumped Web UI and desktop package versions to 0.6.16.
  • Added the 0.6.16 frontend changelog entry and localized changelog strings across all client locales.
  • Updated the website Web UI version manifest with 0.6.16.
  • Provider settings now preserve custom API modes, cover LongCat correctly, support deleting v12 provider entries, and keep model catalogs in sync with auth and API-key image providers.
  • Chat commands now include reload-skills, web title updates, unknown slash passthrough, and a clean session context API without tool calls or tool results.
  • Session navigation, file drag-and-drop uploads, symlinked skill discovery, packaged static asset delivery, Linux desktop viewport sizing, and live compression status rows were polished.
  • Added outbound relay and MCU login flow support, plus a Web UI CLI --no-open flag.

Validation

  • Release created from release/frontend-0.6.16-changelog at e8b994b.
  • npm run openapi:generate
  • npm run test -- tests/client/i18n-coverage.test.ts
  • npm run harness:check
  • git diff --check

v0.6.15

15 Jun 01:44
b2d5b62

Choose a tag to compare

Highlights

  • Chat sidebars were redesigned, with clearer history loading controls for long conversations.
  • Added the skill command picker for discovering and inserting available skill commands from chat input.
  • Added Claude and Gemini OAuth providers, normalized Gemini model IDs, and added model selector refresh for config.yaml changes.
  • Refreshed Thinking indicators and toolbar layout so reasoning progress is easier to read without interrupting message flow.
  • Restored visible dark-theme borders for input and select form controls.
  • Improved runtime startup checks, desktop self-update handling, gateway shutdown/respawn behavior, and desktop server shutdown cleanup.
  • Updated README and website showcase media.
  • Removed inline clear controls from the auxiliary model editor fields.

Validation

  • Release created from main at f3365ce.
  • npm run build passed for the auxiliary model editor change before merge.

v0.6.14

12 Jun 00:32
cab4210

Choose a tag to compare

What's Changed

Full Changelog: v0.6.13...v0.6.14

v0.6.13

10 Jun 02:48
cede4b9

Choose a tag to compare

Changes

  • Alibaba Coding Plan now includes the qwen3.7-plus model preset.
  • File handling is safer with literal-dot path validation and malformed skill-import filename rejection.
  • Chat is more stable on mobile and in browsers without speech synthesis support.
  • Agent failures now preserve the bridge error tail, and Claude Code root-permission launches are more reliable.
  • Desktop updates are more reliable: Windows upgrades close stale Hermes Studio processes, Cloudflare is checked first, and GitHub remains the fallback feed.
  • Release automation now keeps Web UI and Docker releases out of GitHub Latest while full desktop releases are manually promoted to Latest.

v0.6.12

09 Jun 12:59
b2de33a

Choose a tag to compare

Highlights

  • Coding Agent is now a fuller chat experience with dedicated sessions, clearer history, preserved tool/final output, and better chat-state recovery.
  • Claude Code and Codex launch more reliably from the desktop app on Windows, with corrected command resolution and readable failure messages.
  • Coding Agent reasoning, queue status, and error states are easier to follow with stored reasoning content and a nonblocking queue overlay.
  • Desktop runtime version management supports Coding Agent workflows with active-version switching, website version manifests, release packaging support, and desktop-only visibility.

Frontend Updates

  • Per-session reasoning effort controls are available for compatible chat models and hidden for Coding Agents where they do not apply.
  • Group chat mention positioning, active Profile uploads, file downloads, Markdown previews, and highlighted code block wrapping were improved.
  • The changelog modal is taller and the latest changelog entries are localized across supported languages, with 0.6.11 wording cleanup in non-English locales.

Validation

  • npm run test -- tests/client/i18n-coverage.test.ts
  • npm run build

hermes-0.16.0-runtime

09 Jun 04:28
1034313

Choose a tag to compare

[codex] allow manual website version inputs (#1429)

* allow manual website version inputs

* map website downloads to release version

v0.6.11

06 Jun 03:49
bfa0c53

Choose a tag to compare

更新内容

  • LAN 设备发现新增配对审批、申请历史、重复申请处理、状态同步,以及撤销设备权限时的清理逻辑
  • LAN Peer 已接入 MCP,包含内置 MCP 启动、命令 shim、Peer Socket 重连、本地连接列表,以及终端会话数量限制
  • 统一后端 TTS 合成和 MiMo 音色复刻设置已可用,并支持保存设置前试听
  • Gateway 自动启动配置现在支持按 Profile 多选过滤、白名单行为和启动 Profile 选择测试
  • 聊天滚动和动效更稳定,修复初次进入滚动到底部、滚动锁定、底部跟随时机和 reduced-motion 淡入处理
  • Agent Bridge 和运行时流程更可靠,修复 abort 超时、恢复时误启动、execute-code 授权记忆、Windows Gateway 恢复和开发终端代理
  • 安全性增强:加固 Web UI Origin 策略、安全响应头,并限制 server token 只能走本地回环访问
  • 群聊和工具结果渲染更稳定,支持重连后重新加入房间、保留 reasoning/tool 边界、加固工具 payload 渲染并优化 diff 展示
  • 技能和 Workspace 流程支持外部技能目录、导入/删除自动刷新、按 sourcePath 分组、本地化文件夹选择文案和移动端技能操作图标
  • 设备页布局、原生会话标题、浏览器标签标题、Kanban 父任务 ID 和 OpenRouter 归属文案做了界面优化

Commit: bfa0c53

v0.6.10

03 Jun 09:53
1d19be2

Choose a tag to compare

What's Changed

  • Desktop runtime startup is more resilient with download source selection, safer archive extraction, corrected runtime cache paths, Windows CLI launch fixes, and localized progress/error screens.
  • Auxiliary compression model settings let each Profile choose a dedicated provider/model for chat context compression instead of always using the active chat model.
  • Provider model catalogs can now be refreshed from the UI.
  • Users can upload profile avatars, and group chat members now sync and display account avatars consistently.
  • Workspace file browsing now supports richer text previews and context-menu coverage for source and document files.
  • Agent Bridge is more reliable with refreshed tool approval allowlists and Windows tasklist/taskkill output decoding that avoids UnicodeDecodeError crashes.
  • Website copy now consistently presents the product as Hermes Studio while keeping npm package, CLI, repository, and environment variable identifiers unchanged.
  • OpenAPI docs now include avatar, auxiliary model config, provider model cache refresh, and Hermes session import endpoints.
  • Memory notes can now be saved with empty content, making it possible to clear personal notes without a failed save.
  • Repository harness docs now track chat-chain changes so bridge and chat-runtime updates are documented before CI passes.

v0.6.9

02 Jun 07:09
dd03bea

Choose a tag to compare

Highlights

  • Rebranded the app and distribution metadata to Hermes Studio across the browser title, sidebar, website title, package metadata, homepage links, and OpenRouter attribution.
  • Added Russian localization to the language switcher, including community-contributed client UI translations.
  • Added changelog coverage for 0.6.8 and 0.6.9.

Desktop

  • Added tray controls, manual update checks, update notifications, and local-browser launch support for the packaged Web UI.
  • Improved update checks with release-feed fallback handling when GitHub API requests are rate-limited or tag-scoped metadata is missing.
  • Fixed macOS update install flow so Restart stops the local Web UI server and lets electron-updater complete quit/install.
  • Improved Windows desktop startup with hidden Python/bridge subprocesses, terminal popup fixes, tray icon sizing, browser packaging fixes, and bridge startup fixes.
  • Improved cross-platform packaging with macOS signing file-limit fixes, Linux writable paths, runtime cold-start handling, and workflow checkout fixes.
  • Desktop packages continue to embed the runtime metadata tag hermes-0.15.2-runtime; the app release tag is not used as the runtime tag.

Runtime and UI

  • Fixed Profile-scoped provider credentials/auth handling and gateway/runtime startup compatibility.
  • Fixed Chrome Web Speech controls so pause/resume operates on the current message instead of restarting playback.
  • Preserved unsent chat drafts, improved mobile layout overflow, added SSH file-provider custom ports, and made preview actions nonblocking.
  • Preferred provider context-length settings where available.

Release and Website

  • Added download mirrors and sequenced website deploys after desktop releases.
  • Cleaned up desktop smoke-check behavior.