- feat(chat): show skills list on $ trigger for Codex instead of experts.
- fix(chat): restore ~/.agents/skills/ as additional Codex skill dir.
- fix(chat): support mid-text slash trigger and keyboard scroll in autocomplete.
- fix(chat): stop plan in-progress spinner when agent is not streaming.
-----------------------------
# 发布版本 0.7.2
- 新增(聊天)：Codex 输入 $ 时显示技能列表，替代原有的专家列表；
- 修复(聊天)：恢复 ~/.agents/skills/ 作为 Codex 额外的技能目录；
- 修复(聊天)：支持在文本中间触发斜杠命令，自动补全支持键盘滚动；
- 修复(聊天)：当 agent 未在流式响应时停止 plan 进行中的 spinner。
Track the slash trigger position so the menu can open after prose, then
splice only the slash token on selection instead of clobbering the whole
input. Also scroll the highlighted row into view when keyboard navigation
moves past the popup viewport.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The Codex $ prefix autocomplete now lists skills from
acp_list_agent_skills (excluding ids that match built-in experts), while
experts remain reachable via the dedicated Sparkles button. Non-Codex
agents are unchanged and still show only their native ACP commands on
the / trigger.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Codex CLI also reads skills from ~/.agents/skills/, so include it
alongside ~/.codex/skills/ in the skill storage spec. The Codex dir
stays first so it remains the preferred write target for new links,
while lookup and unlink scan both locations.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add "Enable Skills" toggle below "Enable WebSocket" in Codex CLI settings,
writing `skills = true` under [features] in config.toml. Also add max-height
to auth.json and config.toml textareas, and fix TOML section key insertion
to avoid stray blank lines between entries.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Change Codex skill storage to use only ~/.codex/skills/ instead of
~/.agents/skills/, and never disable the expert skills button so users
can always access the empty-state hint. Also fix stale expert list in
conversation window after linking in the separate settings window by
re-fetching on window focus.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Expert skills in the chat session were derived by intersecting built-in
experts with ACP availableCommands, which caused Codex experts to never
appear since Codex does not advertise skills through ACP.
- Add `experts_list_for_agent` backend API that checks symlink status
across all global skill dirs for the given agent type
- Replace availableCommands-based expert filtering with symlink-based
query, making the settings page the single source of truth
- Use `$` prefix for Codex expert skills while keeping `/` for slash
commands and other agents' experts
- Disable the expert button when no experts are linked for the agent
- Invalidate per-agent expert cache after link/unlink in settings
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When reopening a Gemini CLI history session, session/load fails with
"Authentication required" and the fallback session/new overwrites the
DB external_id with a new session ID that has no corresponding file,
causing all historical messages to disappear.
- Skip session/new when session/load returns "Authentication required"
- Add Gemini to the parser fallback so stale external_ids recover via
folder_path + started_at matching
- Guard externalIdSavedRef for existing conversations to prevent
session/new from overwriting the persisted external_id
- Only update conversation status on disconnect when user has sent a
message, avoiding spurious "completed" flips on pure history views
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add .scrollbar-thin and .scrollbar-thin-edge utility classes in
globals.css and apply them to sidebar, file tree, git changes,
git log, session files, diff preview, and message thread panels.
Replace scattered inline webkit-scrollbar overrides with the
shared classes for consistent appearance and gutter behavior.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Import KaTeX CSS in layout.tsx to ensure math formulas display correctly
in both dev and production modes. Convert LaTeX-style `\[...\]` / `\(...\)`
delimiters to `$$...$$` / `$...$` since remark-math only supports dollar
sign delimiters, fixing formula rendering for agents like Codex.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- feat: add responsive layout support for mobile and small screens.
- feat: upgrade @lobehub/icons to v5 and update agent icon colors.
- feat: add version detection and upgrade support to install scripts.
-----------------------------
# 发布版本 0.6.9
- 新增：支持移动端和小屏幕的响应式布局适配；
- 新增：升级 @lobehub/icons 至 v5，更新代理图标配色；
- 新增：安装脚本增加版本检测与升级支持。
Add --version flag to codeg-server binary and enhance both install.sh
and install.ps1 with version detection (skip if already up-to-date),
running process stop before upgrade, and post-upgrade restart guidance.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Upgrade @lobehub/icons from v4 to v5.3.0, adopt new icon components (ClaudeCode, Codex, GeminiCLI) with Color variants, and align fallback AGENT_COLORS with official brand colors.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Restrict supported agent types to Claude Code, Codex CLI, and Gemini CLI. Reposition agent type badges to be vertically centered beside the name and API URL block in provider cards.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replace plain text inputs for model and small_model with searchable
combobox dropdowns that list models from configured providers, while
still supporting custom text entry on blur.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Block deletion of a model provider when it is referenced by any agent,
returning an error that lists the agent names so the user knows what to unlink first
- When a provider's api_url or api_key is updated, automatically propagate
the new credentials to all dependent agents: updates env_json in the database
and patches on-disk config files (Claude Code settings.json, Gemini settings.json,
Codex auth.json + config.toml, OpenCode auth.json) using the same field names
and structure as the agent settings UI
- Fix error message display in provider dialogs for both Tauri and web transports,
which throw plain objects rather than Error instances
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Patch only `OPENAI_API_KEY` and `auth_mode` in auth.json when switching
auth modes, instead of resetting the entire file
- Clean up `OPENAI_BASE_URL` from env when codex loads in official
subscription mode
- Hide API URL and API Key inputs when model provider mode is selected
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
