Commit Graph
684 Commits
Author SHA1 Message Date
陈大猫andClaude Opus 4.6 338ba94d42 feat: add paste-only option for snippets (no auto-execute) (#375)
* feat: add "paste only" option for snippets (no auto-execute)

Add a noAutoRun flag to snippets that pastes the command into the
terminal without appending a carriage return, so users can review
and edit before manually pressing Enter.

Applies to all snippet execution paths: snippet runner (new session),
keyboard shortcut, and startup command.

Closes #371

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: use clearer wording "仅粘贴" instead of "仅上屏"

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: skip onCommandExecuted for paste-only shortcut snippets

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: persist noAutoRun on save and apply to Scripts panel clicks

- Include noAutoRun in handleSubmit serialization (was being lost)
- Pass noAutoRun through ScriptsSidePanel click handler to TerminalLayer
  so paste-only snippets work from the Scripts panel too

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-17 18:09:17 +08:00
陈大猫andClaude Opus 4.6 b7b2e91fab fix: show real error message instead of [object Object] (#373)
* fix: show real error message instead of [object Object]

When an error object (not a string or Error instance) reaches the
error display path, String(obj) produces "[object Object]". Now
extract .message from error-like objects, or JSON.stringify as fallback.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: guard JSON.stringify fallback against undefined return

JSON.stringify(undefined) returns undefined (not a string), which would
crash classifyError().toLowerCase(). Add ?? 'Unknown error' fallback.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: use non-throwing fallback for error serialization

JSON.stringify can throw on circular objects or BigInt values. Wrap in
try-catch to avoid losing the original error and leaving the stream
stuck in a streaming state.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-17 17:23:05 +08:00
cd723000fc fix: show host count in tree view (#364)
* fix: show host count in tree view

* update show host count in tree view

* perf: memoize subtree host count to avoid repeated traversals

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: yuzifu <yuzifu@TB16PGen5.Info>
Co-authored-by: bincxz <16399091+binaricat@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-17 17:00:31 +08:00
陈大猫andClaude Opus 4.6 fff031eb25 fix: remove multi_host_execute and fix MissingToolResultsError (#372)
Remove multi_host_execute tool — the AI can call terminal_execute for
each host individually, which is simpler, more reliable, and avoids
the hang issue where parallel remote commands block the stream.

Fix AI_MissingToolResultsError that occurs after user stops a stream
mid-tool-execution: when building SDK messages, skip orphaned tool
calls that have no matching tool result instead of including them
(which causes the SDK to reject the next message).

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-17 16:29:57 +08:00
陈大猫andClaude Opus 4.6 835a1231a6 feat: add skip TLS verification option for self-hosted AI providers (#369)
* feat: add skip TLS verification option for AI providers

Self-hosted AI endpoints (vLLM, text-generation-webui, etc.) often use
self-signed TLS certificates which Node.js rejects by default, causing
502 Bad Gateway errors. Add a per-provider "Skip TLS certificate
verification" checkbox that sets rejectUnauthorized=false on both
streaming and non-streaming requests.

Ref #294

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: surface real error message instead of generic 502 Bad Gateway

- Pass the actual bridge error message in statusText so Vercel AI SDK
  shows the real cause (e.g. "HTTP is only allowed for localhost",
  "URL host is not in the allowed list", TLS errors)
- Show real error details for 5xx provider errors instead of generic
  "The AI provider returned a server error" message

Previously all connection-level errors were masked as "Bad Gateway"
making it impossible for users to diagnose configuration issues.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: pass server error body details through to the user

- Read HTTP error response body before resolving (was resolving before
  body was read, losing the error detail)
- Parse OpenAI-compatible JSON error format to extract error.message
- Return error Response with body+statusText for non-2xx instead of
  empty stream, so Vercel AI SDK shows the real server error
- Now users see e.g. "502 model not loaded" instead of just "Bad Gateway"

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: widen link modifier key dropdown to prevent text wrapping

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* Revert "fix: widen link modifier key dropdown to prevent text wrapping"

This reverts commit 1f75686391.

* fix: apply skipTLSVerify to model listing requests

ModelSelector.aiFetch() didn't pass providerId, so the provider-level
skipTLSVerify was not applied when refreshing/listing models. Add
skipTLSVerify as a direct parameter alongside the provider lookup.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: keep error detail in Response body, not statusText

statusText only accepts single-line Latin-1 — multiline or non-ASCII
error messages from self-hosted gateways would throw TypeError before
the AI SDK could read them. Move detailed error to body instead.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: return JSON error body for AI SDK compatibility, fix FetchBridge type

- Wrap error responses in OpenAI-compatible JSON format so Vercel AI
  SDK's failedResponseHandler extracts the message correctly instead
  of showing a blank error
- Update FetchBridge type to match the expanded aiFetch parameter list

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: add ASCII statusText fallback for non-OpenAI SDK providers

Anthropic/Google SDKs fall back to Response.statusText when they can't
parse the error body. Add safe ASCII statusText alongside the JSON body.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-17 16:05:09 +08:00
陈大猫andClaude Opus 4.6 cd512d0800 fix: host-level keyword highlight toggle now overrides global setting (#368)
When a host explicitly disables keyword highlighting, global rules are
no longer applied to that terminal. Previously the OR logic
(globalEnabled || hostEnabled) meant per-host disable had no effect
when global highlighting was enabled.

Now: hostEnabled=false suppresses global rules; hostEnabled=undefined
inherits global setting (backward compatible).

Ref #294

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-17 14:38:59 +08:00
陈大猫andClaude Opus 4.6 0c5ae13692 fix: widen settings dropdown selects to prevent text wrapping (#366)
Log Format "Plain Text (.txt)" and Link modifier key "None (click
directly)" were wrapping to two lines due to narrow widths.

Closes #294 (dropdown text wrapping)

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-17 14:36:14 +08:00
陈大猫andClaude Opus 4.6 6727248924 feat: add web search & URL fetch tools for AI agent (#365)
* feat: add web search and URL fetch tools for AI agent

Add web_search and url_fetch tools to Catty Agent, allowing the AI to
search the internet for current information and fetch webpage content.

- Support 5 search providers: Tavily, Exa, Bocha, Zhipu, SearXNG
- Settings UI with provider selection, API key encryption, and config
- web_search is conditional on config; url_fetch is always available
- Both tools are read-only and work in all permission modes (incl. observer)
- aiFetch skipHostCheck for AI tool requests to arbitrary URLs
- System prompt guidelines for when to use search/fetch
- i18n support (en + zh-CN)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: address code review findings (SSRF, key exposure, state race)

- P1: Restore SSRF protection when skipHostCheck is true — still block
  localhost, RFC1918, link-local, and cloud metadata endpoints; only
  skip the domain allowlist for public HTTPS hosts
- P2: Move web search API key decryption to main process via dedicated
  IPC handler, matching the existing provider key security model
- P2: Use configRef to avoid stale closure in async settings callbacks
  that could overwrite newer user changes

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: address second review — DNS rebinding, url_fetch approval, maxResults

- P1: url_fetch now requires approval in confirm mode (outbound GET is
  a side effect that could exfiltrate data via query strings)
- P1: Add DNS resolution check when skipHostCheck is set — resolve
  hostname and reject if any IP is private/loopback/link-local, blocking
  DNS rebinding attacks against internal services
- P2: Slice search results after provider call to enforce maxResults
  consistently (Zhipu and SearXNG ignore the limit parameter)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: address third review — localhost/IPv6 SSRF, API key blur race

- P1: Block localhost/loopback when skipHostCheck is enabled — restructure
  isAllowedFetchUrl to check private hosts first in the skipHostCheck path,
  preventing access to local services on allowlisted ports
- P1: Handle IPv6 private ranges (fc00::/7, fe80::/10, ::ffff: mapped),
  strip brackets from URL.hostname, block [::1] and fd00:: addresses
- P2: Guard handleApiKeyBlur against provider change during async
  encryption — skip stale write if provider switched while encrypting

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: address fourth review — main-process key isolation, SearXNG compat

- P1: Replace aiWebSearchDecryptKey IPC with __WEB_SEARCH_KEY__ placeholder
  pattern — renderer never sees plaintext keys; main process replaces
  placeholder in headers before HTTP request, matching provider key flow
- P1: Search API requests use normal allowlist path (not skipHostCheck),
  so SearXNG on localhost/HTTP/private networks works via aiSyncWebSearch;
  only url_fetch uses skipHostCheck for arbitrary public HTTPS URLs
- P2: Remove needsApproval from url_fetch — treat as read-only like
  sftp_read_file, consistent with observer mode allowlist

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: address fifth review — private LAN providers, maxResults default

- P1: Allow private-IP hosts that are explicitly in the provider/search
  allowlist (e.g. https://192.168.x.x model providers or SearXNG)
- P2: Remove .default(5) from web_search maxResults schema so the user's
  configured maxResults setting is used when the model omits the param

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: address sixth review — HTTPS scope, config gate, redirects

- P2: Scope HTTP exception to private/LAN IPs only — remote allowlisted
  hosts still require HTTPS to protect API keys in transit
- P2: Gate web_search tool on complete config (API key for providers that
  require it, apiHost for SearXNG) to avoid advertising a broken tool
- P2: Add redirect following (up to 5 hops) to aiFetch for url_fetch —
  handles 301/302/307 for short links, www canonicalization, etc.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: address seventh review — redirect SSRF, decrypt race, HTTPS-only

- P1: Revalidate each redirect hop against SSRF guards (allowlist check
  + DNS resolution) before following, preventing open-redirect SSRF
- P2: Add sequence counter to API key decryption effect — stale promise
  results from a previous provider are discarded on provider switch
- P3: Restrict url_fetch to HTTPS-only URLs, matching the skipHostCheck
  policy that already rejects HTTP in the bridge

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: address eighth review — OS resolver, allowlisted HTTP hosts

- P1: Use dns.lookup (OS resolver) instead of dns.resolve4/6 for private
  IP checks — matches what http.request actually connects to, respects
  /etc/hosts, mDNS, and other local resolver sources
- P2: Allow HTTP for any explicitly allowlisted host (not just literal
  private IPs), so self-hosted SearXNG at http://searxng.lan works

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: address ninth review — HTTP scope, blur ordering, decrypt flag

- P1: Narrow HTTP exception to web search apiHost only — AI provider
  endpoints remain HTTPS-only to protect credentials in transit
- P2: Add blur sequence counter to prevent out-of-order encryption
  results from overwriting newer API key saves
- P2: Reset isDecrypting flag when cancelling decrypt on provider switch,
  preventing permanently disabled API key input

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: address tenth review — DNS pinning, prompt/tool alignment

- P1: Pin validated DNS result to the HTTP request via custom lookup
  function, preventing TOCTOU/DNS-rebinding between validation and
  actual connection
- P2: Extract isWebSearchReady() helper and use it consistently in
  both tool registration and system prompt, so the model isn't told
  web search is available when config is incomplete

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: address eleventh review — single DNS lookup, redirect pinning, CGNAT

- P1: Combine DNS validation and pinning into a single lookup call,
  eliminating the TOCTOU window between hasPrivateResolution and pinnedLookup
- P1: Pin DNS for redirect targets too — resolve/validate/pin in one step
  before following each redirect hop
- P2: Add 100.64.0.0/10 (CGNAT) to private IP ranges for Tailscale and
  similar CGNAT-addressed internal services

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: address twelfth review — apiHost validation, sync on enable

- P2: Validate apiHost is a well-formed URL in isWebSearchReady(),
  preventing tool exposure when user enters a malformed host
- P2: Add webSearchConfig.enabled to sync effect deps so the main
  process gets updated immediately when the toggle changes

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: remove DNS-level SSRF checks that break fakedns/proxy environments

DNS resolution validation (dns.lookup + IP pinning) breaks in proxy
environments where fakedns resolves all domains to LAN addresses.
Revert to hostname-level checks only (blocking localhost, 127.0.0.1,
metadata endpoints, etc.) which are sufficient without false positives.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: resolve empty catch block lint warning

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-17 14:19:29 +08:00
bincxzandClaude Opus 4.6 b2406ec8a5 fix: auto-reject OSC-52 prompt for hidden tabs and restore focus
- Reject clipboard read requests when terminal is not visible (background
  tab), preventing invisible prompts that block remote programs
- Restore terminal focus after user responds to the prompt

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 21:53:52 +08:00
bincxzandClaude Opus 4.6 5fde9c2d61 fix: improve OSC-52 prompt UX
- Reject concurrent read requests instead of overwriting resolver
- Add autoFocus to Allow button for keyboard accessibility
- Support Escape key to deny the prompt

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 21:49:47 +08:00
bincxzandClaude Opus 4.6 06a6a0ac12 feat: add 'prompt' mode for OSC-52 clipboard reads
Add a fourth option 'Write + Prompt on Read' that allows clipboard
writes but shows a confirmation dialog before granting read access.
This lets users benefit from remote copy (tmux/vim) while maintaining
control over clipboard reads.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 21:42:22 +08:00
bincxzandClaude Opus 4.6 024e60ead1 fix: reject unsupported OSC-52 selection targets
Only handle clipboard target ('c'); silently ignore unsupported targets
like 'p' (PRIMARY selection) which Electron cannot access, rather than
incorrectly mapping them to the system clipboard.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 21:24:49 +08:00
bincxzandClaude Opus 4.6 9371b3d01b fix: use Electron bridge for OSC-52 read and chunk base64 encoding
- Fall back to netcattyBridge.readClipboardText() for clipboard reads
  since navigator.clipboard.readText() may be unavailable in Electron
- Chunk String.fromCharCode() calls in 8KB batches to avoid stack
  overflow on large clipboard contents

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 21:14:25 +08:00
bincxzandClaude Opus 4.6 5a1d279efd fix: add OSC-52 settings, UTF-8 support, and clipboard read
- Add osc52Clipboard setting (off/write-only/read-write), default write-only
- Fix UTF-8 decoding: use TextDecoder instead of atob for non-ASCII content
- Support clipboard read requests when mode is read-write
- Add settings UI with Select dropdown and i18n (en + zh-CN)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 21:08:11 +08:00
bincxzandClaude Opus 4.6 8b0cbf02c3 feat: add OSC-52 clipboard support for terminal
Register an OSC-52 handler on the xterm parser to allow remote programs
(e.g. tmux, vim, neovim) to write to the local system clipboard via
escape sequences. Read requests are ignored for security.

Closes #362

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 20:52:29 +08:00
bincxzandClaude Opus 4.6 42c82e46ea fix: split auth button so "continue without save" is clearly separated
The auth dialog's "Continue and Save" button had a dropdown arrow embedded
inside it, but clicking anywhere on the button (including the arrow)
triggered save. Users expected the arrow to offer a no-save option but
couldn't discover it. Refactored to a proper split button: left side
triggers "Continue and Save", right arrow opens a dropdown with
"Continue" (without saving).

Refs #356

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 19:55:04 +08:00
bincxzandClaude Opus 4.6 3cd3bbaaf7 fix: snippet package rename losing snippets and blocking case changes
Two bugs in snippet package management:

1. Renaming a package with only case changes (e.g. Speedtest → speedtest)
   was rejected as duplicate because the case-insensitive check didn't
   exclude the package being renamed.

2. Renaming/moving/deleting a package caused its snippets to disappear
   because forEach(onSave) called the state updater multiple times with
   a stale closure, each call overwriting the previous. Only the last
   snippet's update survived. Fixed by adding onBulkSave prop that
   passes the entire updated array in one call.

Fixes #357

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 19:41:27 +08:00
陈大猫 8bfb50fcbb Merge pull request #355 from yuzifu/fix-distro-detect
fix distro detect
2026-03-16 19:30:54 +08:00
bincxzandClaude Opus 4.6 c39ef879c3 fix: use effective passphrase for distro detection probe
The distro detection was using the stored key passphrase instead of the
runtime-resolved passphrase, causing silent failures when users retry
with a manually entered passphrase.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 19:22:20 +08:00
陈大猫andClaude Opus 4.6 b3d5785477 fix: allow settings window as trusted IPC sender (#354)
* fix: allow settings window as trusted IPC sender

The settings window runs in a separate BrowserWindow with its own
webContents id. validateSender() only checked the main window id,
causing "Unauthorized IPC sender" errors when fetching AI model
lists from the settings page.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: add validateSender to all remaining AI IPC handlers

15 handlers in aiBridge were missing sender validation, allowing
potential unauthorized IPC calls. Now every netcatty:ai:* handler
consistently validates the sender against trusted windows.

Affected handlers: chat:cancel, agents:discover, resolve-cli,
codex:get-integration, codex:start-login, codex:get-login-session,
codex:cancel-login, codex:logout, mcp:update-sessions,
mcp:set-command-blocklist, mcp:set-command-timeout,
mcp:set-max-iterations, mcp:set-permission-mode, acp:cancel,
acp:cleanup.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: scope settings window trust to config-only IPC handlers

Per code review feedback: the previous commit allowed the settings
window to access ALL AI IPC handlers including high-risk ones like
exec, terminal:write, and agent:spawn.

Split into two validators:
- validateSender(): main window only (exec, terminal, agent, stream)
- validateSenderOrSettings(): main + settings (fetch, sync, codex
  login, MCP config, agent discovery)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: refresh main window id on recreation and allow settings fetch

Two fixes from code review:

1. Always resolve mainWebContentsId from windowManager instead of
   caching it once, so a recreated main window is recognized.

2. Skip static host allowlist for settings window ai:fetch calls,
   since the settings UI lets users configure custom provider URLs
   that haven't been synced to providerFetchHosts yet. Basic URL
   safety (HTTPS-only, no file:// schemes) is still enforced.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: enforce HTTPS/port safety for settings window fetch requests

Per review: previous commit skipped isAllowedFetchUrl entirely for
settings window, which removed SSRF protection. Now settings window
fetches still bypass the static host allowlist (since the user is
configuring new providers) but enforce the same safety rules:
- Remote hosts must use HTTPS
- Localhost must use known ports

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: sync provider config before fetching models in settings

Instead of bypassing the URL allowlist for settings window fetches
(which weakens SSRF protection), have ModelSelector sync the current
provider's baseURL to the backend allowlist before fetching models.
This keeps the full URL safety checks intact while allowing settings
to test custom provider endpoints.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: use dedicated allowlist handler instead of syncing providers

Replace the approach of calling aiSyncProviders (which overwrites
the shared providerConfigs) with a new lightweight IPC handler
netcatty:ai:allowlist:add-host that only adds a host to the fetch
allowlist without affecting provider configs or API key resolution.

This preserves the SSRF protection while allowing settings to test
custom provider URLs that haven't been synced from the main window.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: auto-expire temporary allowlist entries after 30 seconds

Temporary hosts added via allowlist:add-host now auto-remove after
30s to prevent permanently expanding the SSRF boundary. Built-in
ports and hosts re-added by provider sync are preserved.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: prevent temp allowlist cleanup from removing synced providers

The setTimeout cleanup now checks whether the host/port belongs to
a currently synced provider config before removing it. This prevents
the scenario where a user saves a provider within the 30s TTL window
and then loses access when the timer fires.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: preserve temp allowlist entries across provider sync rebuilds

rebuildProviderFetchHosts() clears and rebuilds the allowlist from
providerConfigs, which would wipe temporary entries added by
allowlist:add-host. Now re-adds active temp entries after rebuild
to prevent race conditions between settings model listing and
provider sync from the main window.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 19:11:42 +08:00
yuzifu 05de49f7da fix distro detect
Support distro detection with passphrase keys
2026-03-16 17:32:33 +08:00
陈大猫andClaude Opus 4.6 f79f27d737 feat: add settings cloud sync support (#353)
* feat: add settings cloud sync support (closes #347)

Expand SyncPayload.settings to include all syncable user preferences
(theme, appearance, terminal, keyboard, editor, SFTP). Add
collectSyncableSettings/applySyncableSettings helpers in syncPayload.ts,
wire rehydrateAllFromStorage through App.tsx and SettingsPage.tsx so
in-memory React state updates after a cloud download.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: include settings in auto-sync uploads and sync empty customCSS

P1: useAutoSync.buildPayload now includes collectSyncableSettings()
so settings are uploaded alongside vault data.

P2: customCSS uses != null check instead of truthy, so clearing CSS
on one device is properly synced to others.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: include settings in auto-sync change detection hash

Settings-only changes (theme, terminal options, etc.) now trigger
auto-sync uploads. The data hash comparison includes the settings
snapshot alongside vault data.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: trigger auto-sync on settings changes and sync custom terminal themes

P1: Added settingsVersion (derived from all synced settings via useMemo)
to useAutoSync debounce effect dependencies. Settings-only changes now
trigger auto-sync uploads.

P2: Custom terminal themes (STORAGE_KEY_CUSTOM_THEMES) are now included
in the sync payload so custom themes are available on other devices.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: reload custom theme store after sync, include in change detection

P1: customThemeStore.loadFromStorage() is now called in
rehydrateAllFromStorage so synced custom themes are immediately
reflected in the live theme store.

P2a: customThemes added to settingsVersion dependencies so custom
theme edits trigger auto-sync.

P2b: Empty custom themes array is now preserved in sync payload
to properly propagate theme deletion.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: notify subscribers after custom theme store reload

loadFromStorage now calls notify() to trigger useSyncExternalStore
subscribers, so synced custom terminal themes are immediately
visible in all windows after apply.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 15:57:41 +08:00
陈大猫andClaude Opus 4.6 ec35daa0dd feat: add auto-update toggle setting (#351)
* feat: add auto-update toggle setting (closes #346)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: re-check auto-update toggle when startup timer fires

Address review feedback: the startup check effect now re-reads the
toggle from localStorage when the delayed timer fires, so toggling
off after launch cancels the pending check. Also avoids setting
hasCheckedOnStartupRef when disabled, allowing re-enable to trigger
a check without restart.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: address review feedback on auto-update toggle

P1: When autoDownload=false, onUpdateAvailable no longer transitions
to 'downloading' status. Instead keeps autoDownloadStatus idle so
the manual download link surfaces correctly.

P2: Added reactive autoUpdateEnabled state (synced via storage event)
as a dependency to the startup check effect. Re-enabling the toggle
mid-session now re-triggers the deferred startup check.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: address P1/P2 review feedback on auto-update toggle

P1: Main process update-available handler now checks updater.autoDownload
before setting _lastStatus to 'downloading'. When autoDownload=false,
status stays 'idle' so late-opened windows don't hydrate to a stuck
0% download state.

P2: useUpdateCheck now accepts autoUpdateEnabled as a prop from the
caller instead of relying solely on storage events (which don't fire
in the same window). SettingsPage passes settings.autoUpdateEnabled
directly, so toggling in the current window takes effect immediately.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: preserve update-available info for late-opening windows

When autoDownload is off, use status 'available' (instead of 'idle')
in the main process snapshot so late-opening windows can hydrate
version info. The renderer maps 'available' to hasUpdate=true while
keeping autoDownloadStatus='idle' for the manual download path.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: re-schedule auto-check on re-enable and guard startup timer

- IPC handler now calls startAutoCheck(2000) when re-enabling so the
  user gets automatic checks without restarting the app.
- startAutoCheck timer checks updater.autoDownload at fire time, so
  if the renderer disables auto-update via IPC before the 5s startup
  timer fires, the check is skipped.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: deduplicate auto-check scheduling and clear error on fallback success

P1: startAutoCheck now cancels any existing timer before scheduling
a new one, preventing duplicate concurrent checks from multiple
windows or re-enable toggles.

P2: checkNow fallback now clears manualCheckStatus='error' when
electron-updater successfully finds an update (res.available=true),
so the UI shows 'available' instead of a stale error state.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: only reschedule on actual re-enable and hydrate cache before toggle check

P2: Track previous autoDownload state in IPC handler so startAutoCheck
is only called on actual false→true transitions, not on every window
mount that syncs the current value.

P3: Move cache hydration (STORAGE_KEY_UPDATE_LATEST_RELEASE) before
the auto-update toggle check so cached update info is always visible
even when automatic updates are disabled.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: persist auto-update preference in main process across restarts

Read/write auto-update preference to a JSON file in userData so the
main process honors it on next launch without waiting for renderer IPC.
getAutoUpdater() now initializes autoDownload from the persisted value.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: suppress cached update toast when disabled and update IPC types

P2: Cache hydration now gates hasUpdate on autoUpdateEnabled so the
App.tsx toast doesn't fire when automatic updates are disabled.

P3: Updated global.d.ts to include 'available' in getUpdateStatus
status union and 'checking' in checkForUpdate return type.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: preserve dismissed releases, show cached updates in Settings, guard concurrent checks

P2a: Updater fallback now checks STORAGE_KEY_UPDATE_DISMISSED_VERSION
before re-surfacing a release found by electron-updater.

P2b: Cache hydration always sets hasUpdate truthfully so Settings
shows the available update. Toast suppression for disabled auto-update
moved to App.tsx (reads localStorage directly).

P3: Re-enable IPC handler checks _isChecking before scheduling
startAutoCheck to prevent concurrent electron-updater calls.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: use localStorageAdapter for lint compliance, skip IPC on initial mount

P1: Replace direct localStorage access with localStorageAdapter in
App.tsx toast guard to fix no-restricted-globals lint error.

P2: Skip setAutoUpdate IPC on initial mount to prevent overwriting
the main-process preference file when renderer localStorage has been
cleared (where the default would be true).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: hydrate auto-update state from main-process preference on mount

Add getAutoUpdate IPC handler so the renderer can query the persisted
preference from auto-update-pref.json. On mount, useSettingsState
reconciles localStorage with the main-process truth, preventing the
toggle from showing 'enabled' when the user had previously disabled
it and localStorage was cleared.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 14:54:40 +08:00
bincxzandClaude Opus 4.6 1f31629ce0 feat: add global hotkey enable/disable toggle (closes #349)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 12:36:37 +08:00
陈大猫 cc4a904dea Merge pull request #350 from binaricat/fix/gemini-empty-function-response-name
fix: resolve Gemini API error caused by empty functionResponse name
2026-03-16 11:56:57 +08:00
bincxzandClaude Opus 4.6 e9e1d87ff5 fix: resolve Gemini API error caused by empty functionResponse name
When rebuilding SDK messages from conversation history, tool-result
messages had toolName hardcoded to an empty string. This works for
OpenAI/Claude APIs but Gemini requires functionResponse.name to be
non-empty, causing AI_APICallError on every follow-up message.

Now looks up the tool name from the matching assistant tool call
via toolCallId.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 11:43:28 +08:00
yuzifu 6892e11952 enable scrollbar in dropdown lists when content exceeds max-height 2026-03-16 11:07:56 +08:00
陈大猫 f70b604996 Merge pull request #340 from binaricat/feat/ai-chat-panel
feat: AI chat panel with Vercel AI SDK
2026-03-16 01:35:15 +08:00
bincxzandClaude Opus 4.6 eeb300295d refactor: improve security, accessibility, performance, and code organization
- Security: API keys no longer transit IPC as plaintext; renderer sends
  providerId and main process decrypts via safeStorage. Add ReDoS
  protection for user-supplied blocklist regex. Sanitize error messages
  to strip file paths and sensitive URLs before displaying in chat.
- Bug fixes: approval timeout now notifies user in chat instead of
  silently aborting. statusText cleared consistently across all 7 code
  paths. useAIState persistence race condition fixed with mountedRef
  guard, storage sync validated with type checks.
- Accessibility: InlineApprovalCard uses role="alertdialog" with focus
  on approve button. ChatInput menus have proper ARIA roles, labels,
  and aria-expanded. ThinkingBlock toggle has aria-expanded/controls.
  Model selector submenu supports keyboard navigation.
- UX: switching agents preserves old session and creates new one.
  Approval card buttons disabled immediately after click.
- Performance: text-delta streaming batched via requestAnimationFrame.
- Refactor: extract useAIChatStreaming, useToolApproval, and
  useConversationExport hooks from AIChatSidePanel (1514 → 751 lines).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 00:51:23 +08:00
bincxzandClaude Opus 4.6 be36ccd167 fix: address security, correctness, and performance issues from code review
Security: add validateSender to agent IPC handlers, remove CODEX_API_KEY
and NODE_PATH from SAFE_ENV_KEYS, validate URL scheme before openExternal,
add backtick substitution to command blocklist, add 10MB buffer limits.

Bugs: fix runExternalAgentTurn timeout hang, fix limitConcurrency undefined
entries on error, treat null exitCode as failure, enforce maxBytes for SFTP reads.

Performance: debounce addMessageToSession persistence, cache compiled
blocklist regexes, add QuotaExceededError handling for localStorage writes.

UI: use local onKeyDown for PermissionDialog, move CRITICAL_PATHS to module level.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 00:18:45 +08:00
bincxzandClaude Opus 4.6 71b13a77a3 fix: address security, correctness, and performance issues from code review
Security: validate agent spawn commands against allowlist, replace execSync
with execFileSync in agent discovery, restrict localhost SSRF to known ports,
add observer mode enforcement at IPC layer, add IPC sender validation,
expand dangerous env key blocklist, add pending approval timeout.

Correctness: replace updateLastMessage with ID-based updateMessageById to
fix race condition during streaming, include tool-call/tool-result messages
in SDK context, flush debounced persist on unmount, fix ACP client break
placement, use proper AI SDK message types.

Performance: pre-compile command blocklist regexps, extract shared tool
executors to deduplicate executor.ts and tools.ts (~50% reduction each).

Also: i18n for hardcoded English strings, remove dead detectDoomLoop code,
add bypass-resistant blocklist patterns, include permissionMode in ACP
provider reuse fingerprint.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-16 00:10:17 +08:00
bincxzandClaude Opus 4.6 808d021ebe fix: address security, correctness, and performance issues from code review
- Use crypto.randomBytes for PTY markers instead of Math.random
- Replace execSync with execFileSync to prevent command injection
- Fix sftp_write_file missing safety check (pass path to guardWriteOperation)
- Add IPC input validation for handleExec, handleSftpRead, handleMultiExec
- Add maxBytes bounds validation in executor, tools, and MCP server
- Fix approval race condition (clear ref after destructuring, strict messageId match)
- Shorten API key plaintext lifetime in memory
- Fix stream cancellation race with AbortController registered before request
- Delay revokeObjectURL for download timing
- Extract shared limitConcurrency to infrastructure/ai/concurrency.ts
- Add execStream null check in execViaChannel

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 23:46:13 +08:00
bincxzandClaude Opus 4.6 d03117733d fix: clear statusText on tool-call and tool-result events
The "Waiting for response from agent..." status text was persisting
after tool completion because only onTextDelta cleared statusText.
When an agent went directly from tool-result to a new tool-call
without emitting text, the stale statusText remained visible.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 23:34:10 +08:00
bincxzandClaude Opus 4.6 1816c3d0df fix: resolve eslint warnings in AI chat panel components
- Copy abortControllersRef to variable before cleanup
- Remove unnecessary useMemo deps (activeTabId, workspaces)
- Remove unused Shield import
- Add missing deps (t, isCustom) to useMemo/useCallback

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 23:28:50 +08:00
bincxzandClaude Opus 4.6 b192ee1764 fix: address security, correctness, and performance issues from code review
Security: sanitize command input in resolveCliFromPath, add host allowlist
to streaming endpoint, enforce permission model in MCP server tools, add
safety check to terminal:write IPC, fix broken blocklist regex, remove
renderer-controlled allowedHosts parameter.

Correctness: use sessionsRef for latest state in handleSend, merge
add+update to avoid race condition in streaming, mark assistant message
completed after tool-result, return JSON-RPC error for unhandled ACP
permission requests, add finished guard in ptyExec.

Performance: custom React.memo comparator for ChatMessageList, fix doom
loop detection threshold.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 23:27:47 +08:00
bincxzandClaude Opus 4.6 0b9cb86c4e fix: address security and correctness issues from code review
- Add command blocklist check to terminal_send_input (executor + SDK tools)
- Add session scope validation to all tools in executor.ts
- Fix abort handler to call aiChatCancel instead of aiChatStream
- Enforce URL allowlist in fetch proxy to prevent SSRF
- Wrap event.sender.send with safeSend for destroyed window check
- Filter dangerous env vars (LD_PRELOAD, NODE_OPTIONS, etc.) from agent spawn
- Fix stale debouncedPersistSessions closure using sessionsRef
- Fix cleanupOrphanedSessions race when sessions load before workspaces
- Fix limitConcurrency implementation using Set + finally pattern
- Improve command blocklist regex patterns with word boundaries
- Add regex validation with error feedback in SafetySettings
- Add confirmation dialog for provider removal
- Fix React key warning for tool-role messages in ChatMessageList
- Remove debug console.warn in TerminalLayer
- Remove unused nanoid dependency
- Remove redundant platform-specific codex-acp binary from dependencies

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 23:10:51 +08:00
bincxzandClaude Opus 4.6 d8d29d1709 fix: address code review findings for AI chat panel
Security:
- Apply checkCommandSafety() in aiExec IPC handler to enforce command blocklist
- Add critical path validation in handleSftpRemove (normalize + blocklist)
- Change rm -rf to rm -r so permission errors surface

Stream lifecycle:
- Abort all active streams on component unmount (abortControllersRef cleanup)
- Wrap stream reader in try/finally with releaseLock() to prevent leaks
- Use refs for inputValue/images in handleSend to stabilize callback identity

State persistence:
- Clear debounce timer before synchronous persist in destructive operations
  (clearSessionMessages, deleteSession, deleteSessionsByTarget)
- Add 10MB max buffer guard in ACP client and MCP server NDJSON parsing

i18n:
- Replace hardcoded English strings with t() calls in InlineApprovalCard,
  PermissionDialog, ConversationExport, ThinkingBlock, AgentSelector
- Add 23 new i18n keys to en.ts and zh-CN.ts

Misc:
- Remove debug console.log statements in mcpServerBridge

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 22:38:03 +08:00
bincxzandClaude Opus 4.6 0820569166 fix: use session ID in approval finally block for streaming cleanup
The finally block in handleApprovalResponse still used scope key (sk)
instead of session ID (sid) for setStreamingForScope and abort controller
cleanup, causing the streaming indicator to not clear after approval flow.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 21:09:28 +08:00
bincxzandClaude Opus 4.6 545506ac86 fix: track streaming state per session instead of per scope
When switching agents or creating a new chat within the same scope,
the stop button stayed red because streaming was keyed by scopeKey
(which doesn't change). Now streaming and abort controllers are keyed
by sessionId, so switching to a different session correctly shows the
idle state while the old session continues streaming in background.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 21:00:29 +08:00
bincxzandClaude Opus 4.6 29fca33ffd fix: reduce stall timeout to 3s and show status with shimmer effect
- Reduce ACP stall detection from 15s to 3s for faster feedback
- Add statusText field to ChatMessage for transient status display
- Render status text with thinking-shimmer CSS animation
- Clear statusText when real content arrives (onTextDelta)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 20:35:17 +08:00
bincxzandClaude Opus 4.6 216ea7f177 feat: show ACP agent status messages (stall detection) in chat
- Add stall detection in ACP stream loop: if no chunk received for 15s,
  send a "Waiting for response..." status event to the chat panel
- Add onStatus callback to AcpAgentCallbacks, render as italic text
- Forward status events from main process to renderer via acp:event IPC

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 20:26:11 +08:00
bincxzandClaude Opus 4.6 b280caded2 fix: default Codex model selection includes thinking level suffix
When no model is stored, the default was bare "gpt-5.4" which Codex
rejects. Now defaults to "gpt-5.4/xhigh" (highest thinking level)
for models that require a thinking level suffix.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 20:12:42 +08:00
bincxzandClaude Opus 4.6 2d4f260f0b fix: address review findings from refactoring review
- Fix stale closure: add updateLastMessage to handleApprovalResponse deps
- Use random heredoc delimiter to prevent content corruption when file
  contains the literal delimiter string
- Remove dead ensureClaudeConfigDir function from claudeHelpers

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 20:03:36 +08:00
bincxzandClaude Opus 4.6 e69bc53aa4 feat: improve error display with structured error messages in AI chat
- Add errorInfo field to ChatMessage with type classification
  (network/auth/timeout/provider/agent/unknown) and retryable flag
- Create errorClassifier.ts to map raw error strings into user-friendly
  structured messages with actionable hints
- Replace inline "**Error:**" text appending with dedicated error messages
  rendered as styled error cards with AlertCircle icon
- Ensure streaming indicator is cleared immediately on error in ACP and
  external agent flows (not just in finally block)
- Mark previous message executionStatus as failed only when it was running

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 19:55:04 +08:00
bincxzandClaude Opus 4.6 a55da77471 refactor: fix security issues, remove dead code, and split monolithic files
Security:
- Fix command injection in 15+ shell interpolation sites with shellQuote()
- Add token-based authentication to MCP TCP server
- Fix heredoc delimiter collision in SFTP write fallbacks
- Add case-insensitive flag to mcpServerBridge command blocklist
- Add exhaustive default case to createModelFromConfig

Architecture:
- Split aiBridge.cjs (1971→1483 lines) into 4 modules:
  shellUtils, codexHelpers, claudeHelpers, ptyExec
- Split SettingsAITab.tsx (1480→520 lines) into 10 sub-components
- Extract shared processCattyStream from AIChatSidePanel.tsx (-168 lines)
- Consolidate duplicate PTY execution logic into shared ptyExec.cjs
- Consolidate duplicate stripAnsi/toUnpackedAsarPath utilities

Code quality:
- Remove ~33 debug console.log statements from production code
- Remove dead code: terminal_read_output stub, checkToolPermission,
  isCommandAllowed, READ_ONLY_TOOLS
- Unify bridge type accessor in useAIState.ts (eliminate 15 unsafe casts)
- Add localStorage session pruning (50 sessions / 200 messages cap)
- Fix ModelSelector onBlur race condition (setTimeout → preventDefault)
- Fix duplicate getShellEnv() calls in Codex helpers
- Remove unused _config param from claudeAgentAdapter
- Type claudeAgentAdapter bridge parameter directly as ClaudeBridge

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 19:45:50 +08:00
bincxzandClaude Opus 4.6 33d3a86d83 feat: show permission mode switcher for all agents, not just Catty
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 18:57:41 +08:00
bincxzandClaude Opus 4.6 304ebf1e3b feat: add inline permission mode switcher for Catty Agent in chat input
Show a clickable chip next to the model selector in ChatInput footer
that lets users quickly toggle between Observer/Confirm/Auto permission
modes. Only visible when Catty Agent is selected (ACP agents handle
their own tool approval flow).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 18:52:19 +08:00
bincxzandClaude Opus 4.6 2788dbdff5 feat: replace modal permission dialog with inline approval cards and fix approval continuation flow
Replace the full-screen PermissionDialog modal with inline InlineApprovalCard
rendered within chat messages. Implement the multi-turn approval flow so that
clicking Approve actually resumes the agent loop via a new streamText call with
proper SDK tool-approval-response messages.

Fix toolCallId extraction (toolCall.toolCallId, not chunk.toolCallId) and use
correct SDK field name (input, not args) for ToolCallPart content parts.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 18:30:55 +08:00
bincxzandClaude Opus 4.6 84fe0134c9 feat: implement UI-level tool confirmation for Catty Agent confirm mode
Use Vercel AI SDK's native `needsApproval` on write tools (terminal_execute,
terminal_send_input, sftp_write_file, multi_host_execute) when permission
mode is "confirm". When the SDK emits a `tool-approval-request` stream event,
show the existing PermissionDialog component for user to approve/reject.

- tools.ts: replace manual checkToolPermission() calls with `needsApproval`
  property on write tools; keep blocklist checks in execute()
- AIChatSidePanel: handle `tool-approval-request` chunk type, show
  PermissionDialog via Promise-based pause, resolve on user action
- Add i18n key for tool denied message

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 18:04:11 +08:00
bincxzandClaude Opus 4.6 06dc7400f2 fix: use Sparkles icon for AI settings tab to match top toolbar
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 17:10:26 +08:00