Task 7 inadvertently overwrote 18 carefully-tuned translations across 7 languages
(ar/de/es/fr/ja/ko/pt) with the plan author's slightly different wording while
adding the new themeColor / zoomLevel / resetToDefaults keys. The new additions
remain intact; only the pre-existing keys are reverted to the project's original
translations (e.g. de "Designmodus" instead of "Design-Modus", ja
"システム追従" instead of "システムに従う"). Affects: sectionDescription,
themeMode, placeholder, system, currentTheme.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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>
- Split env vars and config file persistence into separate save operations
- Add model_provider_id field to agent_setting for tracking selected provider
- Add "Model Provider" auth mode for Claude Code, Codex CLI, and Gemini CLI
- Add "Custom Endpoint" auth mode for Claude Code (previously only official subscription)
- Unify auth mode labels across all three agents (official subscription / custom endpoint / model provider)
- When model provider is selected, fill api_url and api_key into env and config automatically
- Resolve model provider credentials at ACP connect time as a backend fallback
- Clear provider deletion cascades to agent_setting.model_provider_id
- Claude Code writes API credentials to config.env (ANTHROPIC_BASE_URL / ANTHROPIC_AUTH_TOKEN)
- Codex: switching auth modes patches config.toml instead of clearing it
- Add i18n keys for new auth modes in all 10 supported languages
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add a new settings page for managing API model providers (name, API URL,
API key, applicable agent types). Includes database migration, SeaORM
entity, backend CRUD commands/handlers, frontend settings UI with agent
type filter, add/edit/delete dialogs, and i18n support for all 10 locales.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Claude Code errors when setting config options to "auto". Strip "auto"
values from config options returned to frontend and skip set requests
with "auto" value for Claude Code agent.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
New @ file mention support in chat and fixes for terminal and Docker stability.
- feat: add @ file mention support in chat input and unify directory attachment.
- fix: update run button state when terminal tab is closed directly.
- fix: fix terminal not opening in Docker and slim down Docker image.
-----------------------------
# 发布版本 0.6.6
新增聊天输入框 @ 文件提及功能，并修复终端与 Docker 稳定性问题。
- 新增：聊天输入框支持 @ 文件提及，并统一目录附件处理逻辑；
- 修复：终端标签页直接关闭时正确更新运行按钮状态；
- 修复：修复 Docker 环境下终端无法打开的问题，并精简 Docker 镜像。
Support typing "@" in the chat input to trigger a file list popup with
filtering, keyboard navigation, and file/directory attachment. Directories
from the sidebar file tree now attach as resource links instead of injecting
text into the input.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replace crypto.randomUUID() with the existing randomUUID() utility
that falls back to crypto.getRandomValues() over plain HTTP.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Centralize terminal process lifecycle in terminal-context as single
source of truth. TerminalView reports exit/failure via callback,
context maintains exitedTerminals set, command-dropdown reacts to it.
Removes redundant polling and per-component exit event subscriptions
that raced with deferred spawn introduced in b2d10fa.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add split button with dropdown in commit dialog supporting both
"Commit" and "Commit and Push" actions
- Pass folderId through gitCommit/gitPush API calls so backend emits
events that the folder window can receive for toast notifications
- Update Tauri git_commit and git_push commands to accept folder_id
parameter with window label fallback for cross-window compatibility
- Wrap commit page with GitCredentialProvider for push authentication
- Keep commit window open when push fails so user can see the error
- Add i18n translations for all 10 locales
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Move PTY spawn from context layer to view layer so event subscription
happens before spawn, preventing loss of initial terminal output.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Generate QR code server-side when iLink API returns SPA page URL
(added qrcode + image crates for PNG generation)
- Strip bot_token from frontend response (new WeixinQrcodeStatusPublic type)
- Add request timeouts and shared HTTP client for QR code endpoints
- Fix TOCTOU race on reply_context double-lock (single lock scope)
- Extract do_send() helper to deduplicate sendmessage logic; resend now
checks ret field for context expiry instead of HTTP status only
- Cap pending_messages buffer at 50 to prevent unbounded memory growth
- Generate stable X-WECHAT-UIN per backend instance instead of per request
- Extract ILINK_CHANNEL_VERSION constant (was hardcoded in 4 places)
- Add 5-minute client-side QR expiry timeout in frontend dialog
- Track consecutive polling errors and show warning after 3 failures
- Stabilise onAuthSuccess/onClose callback refs to prevent polling restarts
- Replace dead i18n key weixinOpenQrcode with weixinPollError
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Filter messages by message_type=1 to skip bot echo and prevent loops
- Add voice message support (type=3) with voice-to-text extraction
- Check resend results and re-buffer failed messages to prevent loss
- Handle session expiry (ret=-14) with 30s pause in polling loop
- Use exponential backoff (5s–30s) for network errors instead of fixed 5s
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Display specific file paths, commands, and patterns in tool call messages
instead of generic titles (e.g. ">> Read: src/main.rs")
- Show tool call details only on completion to ensure raw_input availability
- Enrich permission request messages with tool details from rawInput
- Localize stop_reason in turn_complete messages for all 10 languages
- Fix UTF-8 byte-slice panic in format_completion for multi-byte content
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
