Commit Graph

209 Commits

Author SHA1 Message Date
ekko cd77e5ba2e Align i18n locale coverage (#878) 2026-05-20 17:13:32 +08:00
Zhicheng Han 6578873d9e [verified] Fix group chat agent member sync (#877) 2026-05-20 17:13:15 +08:00
ekko 866d243978 update 0.5.31 changelog (#874) 2026-05-20 15:34:09 +08:00
ekko 201330652d fix: raise mobile session drawer overlay (#871)
Co-authored-by: Codex <codex@openai.com>
2026-05-20 15:06:12 +08:00
ekko c90eba226d [codex] add customizable profile avatars (#870)
* add customizable profile avatars

* keep profile avatar visible when sidebar collapses

* simplify collapsed profile avatar styling

* force managed gateway startup in docker

* limit gateway autostart to active profile

* restore all profile gateway autostart

* fix managed gateway runtime detection
2026-05-20 14:15:01 +08:00
ekko 663afb61ff Improve profile runtime controls (#868)
* Improve profile runtime controls

* Restore profile selector test id

* Update profile switch e2e flow
2026-05-20 12:59:34 +08:00
chinrunja 479fef8a84 Fix i18n lang bug (#858) (#867) 2026-05-20 12:47:52 +08:00
Zhicheng Han 5fc7dce9c8 Fix file browser absolute path copy (#860) 2026-05-20 10:36:49 +08:00
Zhicheng Han 7f6b691238 [verified] Fix group chat final stream rendering (#859) 2026-05-20 10:31:30 +08:00
Zhicheng Han 904ca8c648 feat(group-chat): add @all mention routing (#857)
Add modular group-chat mention routing helpers for the reserved @all token, route it to every non-sender agent, and strip routing tokens before model input.

Expose @all in mention autocomplete, highlight it in group messages, reserve literal all agent names, and cover boundary/partial-match regressions with tests.
2026-05-20 10:21:57 +08:00
ekko 0547fd6b6a [codex] Harden context compression history handling (#848)
* Use token threshold for chat compression

* Add compression settings controls

* Use config for chat compression

* Cover protected messages in compression tests

* Remove message-count compression limit

* Harden compression window fallback

* Rebuild stale compression snapshots

* Harden stale compression snapshots

* Update changelog for compression hardening

* Prefer local history session details
2026-05-19 17:58:39 +08:00
ekko 84e343fc22 Add 0.5.30 changelog (#846) 2026-05-19 16:19:56 +08:00
ekko 9a9416c99c Fix bridge history, profile models, and Windows gateway handling (#845)
* feat: support profile-aware group chat bridge flows

* feat: route cron jobs through hermes cli

* Fix group chat routing and isolate bridge tests

* Add Grok image-to-video media skill

* Default Grok videos to media directory

* Fix bridge profile fallback and cron repeat clearing

* Refine bridge chat and gateway platform handling

* Filter bridge tool-call text deltas

* Preserve structured bridge chat history

* Prepare beta release build artifacts

* Fix Windows run profile resolution

* Fix Windows path compatibility checks

* Fix profile-scoped model page display

* Hide Windows subprocess windows for jobs and updates

* Hide Windows file backend subprocess windows

* Avoid Windows gateway restart lock conflicts

* Treat Windows gateway lock as running on startup

* Force release Windows gateway lock on restart

* Tighten Windows gateway lock cleanup

* Update chat e2e source expectation

* Bump package version to 0.5.30

---------

Co-authored-by: Codex <codex@openai.com>
2026-05-19 16:09:59 +08:00
Zhicheng Han 3d74d78698 fix: tighten collapsed sidebar layout (#834) 2026-05-19 08:33:53 +08:00
ekko d2cbce2f13 Adjust outline user item background (#836)
* feat:新增大纲功能

* Adjust outline user item background

---------

Co-authored-by: chenxusheng <chenxusheng@haizhi.com>
2026-05-19 08:25:01 +08:00
ekko bbfd818106 update zai models and sidebar divider (#819) 2026-05-17 20:47:52 +08:00
ekko 6516d86dfc Limit run-time model list waiting (#812) 2026-05-17 12:51:23 +08:00
ekko 5e8f8bd4a1 Add session-level bridge model settings (#811) 2026-05-17 12:20:53 +08:00
ekko bcfc5053c4 Add 0.5.26 changelog (#809) 2026-05-17 10:09:25 +08:00
ekko 53f0301da4 Add Hermes Agent package fallback and xAI OAuth (#808) 2026-05-17 09:45:56 +08:00
ekko 0c2bafc619 [codex] Add local tool trace toggle (#806)
* test: harden tool approval browser contract

* test: cover tool trace display edge cases

* test: cover resumed tool trace edge cases

* feat: hide tool traces by default

* Add local tool trace toggle

---------

Co-authored-by: Zhicheng Han <zhicheng.han@mathematik.uni-goettingen.de>
2026-05-17 09:01:59 +08:00
ekko 569ddc28da fix(logs): keep loading state below filters (#802)
Co-authored-by: Codex <codex@openai.com>
2026-05-16 22:49:09 +08:00
WenhuaXia f2c8ace7c2 fix: custom_providers base_url and dynamic deliver targets (#801)
- custom_providers: always use user's base_url instead of
  PROVIDER_PRESETS matching by name that overwrites local URLs
- JobFormModal: dynamically add connected platform channels
  (Telegram, Discord, Slack, WhatsApp, Matrix, WeChat, WeCom,
  Feishu, DingTalk) to job deliver target dropdown

Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-16 22:07:02 +08:00
luSkyl 8571a7d0ac Explain gateway stopped states with Web UI diagnostics (#663)
* feat: add gateway diagnostics to Web UI status

* fix: improve gateway diagnostics mobile layout
2026-05-16 21:24:48 +08:00
ekko 840cb6cd9f fix: correct session reset mode options (#800)
* fix: correct session reset mode options

- Change 'hourly' to 'daily' to match gateway SessionResetPolicy
- Add 'none' option (officially supported in CLI setup wizard)
- Add 'modeDaily' and 'modeNone' i18n keys

* fix: add i18n keys for session reset mode fixes (en)

* fix: add i18n keys for session reset mode fixes (zh)

* fix: add i18n keys for session reset mode fixes (de)

* fix: add i18n keys for session reset mode fixes (es)

* fix: add i18n keys for session reset mode fixes (fr)

* fix: add i18n keys for session reset mode fixes (ja)

* fix: add i18n keys for session reset mode fixes (ko)

* fix: add i18n keys for session reset mode fixes (pt)

* fix zh-TW session reset labels

---------

Co-authored-by: GaoZzr <55678517+GaoZzr@users.noreply.github.com>
2026-05-16 21:18:59 +08:00
ekko 048a0ad87e fix mobile terminal drawer sizing (#799) 2026-05-16 21:01:00 +08:00
ekko db0c23bf5e [codex] add QQBot and DingTalk channel settings (#787)
* add qqbot and dingtalk channel settings

* remove history session context menu
2026-05-16 13:54:38 +08:00
ekko 217b721648 clear stale compression status on run start (#783) 2026-05-16 11:15:29 +08:00
ekko 24e906998a support windows markdown media paths (#780) 2026-05-16 10:43:51 +08:00
ekko cf9d0c6008 prepare 0.5.25 changelog (#778) 2026-05-16 09:40:25 +08:00
ekko 07257a8964 [codex] proxy provider model fetches (#777)
* proxy provider model fetches

* add provider model proxy e2e
2026-05-16 08:57:00 +08:00
Zhicheng Han d066806d86 test: 补强浏览器 P0 契约测试 (#772)
* test: cover terminal browser contract

* test: harden P0 browser contracts
2026-05-16 08:56:34 +08:00
ZhangKai | 张凯 87a8e95d66 feat: add MiMo TTS provider 语音TTS提供接入MiMo (#752)
* feat: add MiMo TTS provider with preset voices, voice design and voice clone

* refactor: remove MiMo voice clone feature
2026-05-16 08:55:23 +08:00
Zhicheng Han 68fbd568b7 docs: clarify session search scope (#774) 2026-05-16 08:29:51 +08:00
ekko 8bb71b5592 fix tool approval flow (#773) 2026-05-16 00:11:51 +08:00
ekko fbb0236af4 Update docs and CLI upgrade notes (#760) 2026-05-15 16:13:51 +08:00
ekko 8196e49478 [codex] Add group chat room reset and clone (#756)
* Add group chat room reset and clone

* Clean npm cache before self update
2026-05-15 15:52:16 +08:00
ekko 94f1061734 align bridge multimodal handling (#755) 2026-05-15 14:47:29 +08:00
ekko 3d49f778fb align compression token estimates (#749) 2026-05-15 13:50:27 +08:00
ekko 2dbc3e1c10 chore: update changelog for 0.5.23 (#747) 2026-05-15 13:03:03 +08:00
ekko 48dcaee6c2 feat: add bridge session commands (#743) 2026-05-15 12:04:03 +08:00
Leo_yang 4d3b5097ce feat: add clear visible models selection (#733)
* feat: add clear visible models selection

* fix: complete visible models translations

---------

Co-authored-by: Harukaon <18928954435+Harukaon@users.noreply.github.com>
Co-authored-by: Harukaon <Harukaon@users.noreply.github.com>
2026-05-14 23:36:07 +08:00
ekko 7da934fe8b revert: remove i18n lazy loading and highlight.js selective import (#736)
Revert the dynamic import() for i18n locales and highlight.js core+
registration from #696. Dynamic imports create separate chunk files
that cause 404 errors for users after updating when the browser still
references old chunk hashes.

Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-14 23:32:33 +08:00
ekko d0f1e7d1f2 Fix bridge compression history handling (#726)
* feat(bridge): refactor compression to use DB history and add structured logging

- Extract buildDbHistory() to share message loading between buildCompressedHistory and forceCompressBridgeHistory
- forceCompressBridgeHistory now reads from local DB instead of using Python-provided messages, ensuring consistency with api_server path
- Pass sessionId to compressor for snapshot-aware compression
- Add force_compress flag to bridge chat requests
- Add bridgeLogger structured logging for compression lifecycle
- Simplify schemas, session-sync, and providers

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* fix bridge compression history handling

---------

Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-14 21:02:59 +08:00
memeflyfly 7420f7aad5 feat(chat): add custom drag-resize handle on input top border (#725)
* feat(chat): add custom drag-resize handle on input top border

* fix(chat): skip auto-resize when user has manually set height via drag handle
2026-05-14 21:02:44 +08:00
memeflyfly bb83ac7d9e feat(settings): add debounce to NInputNumber in Memory/Agent/Session settings (#718) 2026-05-14 15:47:17 +08:00
rqbbss e6f403b787 fix: preserve newlines in chat message markdown rendering (#714) 2026-05-14 15:38:26 +08:00
ekko bd6c4dc82e fix: restore Hermes session history listing (#716) 2026-05-14 15:23:19 +08:00
Butter Rice Cake of Gemini f6df0fecfa perf: 优化体积,highlight.js按需导入与i18n按需加载 (#696)
* perf: 优化打包体积,highlight.js按需导入与i18n按需加载

1. highlight.js: 从全量导入改为 core + 注册27种常用语言,减少约500~800KB
2. i18n: 只同步加载en语言包,其他8种语言改为异步加载,首屏减少约350~400KB
3. 使用vue-i18n的setLocaleMessage API动态注册语言包
4. 新增switchLocale函数统一处理语言切换
5. 同步更新相关测试文件的mock路径和API适配

* 修复类型断言
2026-05-14 12:39:36 +08:00
Salvia AI 1b4733e755 feat(tts): add zh-TW and zh-HK Edge TTS voice options (#705)
- Add 3 Taiwanese Mandarin voices (小晨, 小宇, 云哲)
- Add 3 Hong Kong Cantonese voices (希雅, 希文, 文龙)
- Voices are from edge-tts --list-voices official catalog
2026-05-14 12:07:49 +08:00