Commit Graph
21 Commits
Author SHA1 Message Date
7639191c50 fix: preserve AI chat history across reconnects (#541)
* fix: preserve AI chat history across reconnects

* fix: retarget restored AI sessions on reconnect

* feat: format tool call results with proper line breaks

Extract stdout/stderr from structured results and unescape \n/\t
so command output displays with real line breaks like terminal output.
Supports both JSON object {stdout,stderr} and executor text formats.

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

* fix: restrict unescape to stdout/stderr fields only

Plain strings may contain legitimate backslash sequences (file paths,
regex patterns) that should not be converted. Only apply unescape to
stdout/stderr fields extracted from command execution results.

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

* fix: address review findings for AI chat reconnect

1. Add explicit activeTerminalTargetIds guard in shouldRetargetActiveSession
   to prevent retargeting sessions owned by other terminals, making the
   invariant locally verifiable.

2. Only preserve orphaned terminal sessions with hostIds — workspace,
   local, and serial sessions generate fresh IDs and would be permanently
   unreachable, wasting MAX_STORED_SESSIONS quota.

3. Clear stale streaming state when restoring a session whose ACP handle
   was already cleaned up (e.g., reconnect during mid-response), so the
   user can send new messages.

4. Restore overflow-hidden on user message bubbles to prevent content
   bleeding past rounded border corners.

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

* fix: address round 2 review findings

1. Fix streaming state clear: only clear for sessions whose targetId
   doesn't match current scope (restored from different terminal),
   not for built-in Catty chats that never set externalSessionId.

2. Exclude local/serial sessions from preservation: their synthetic
   hostIds (local-*/serial-*) change on every open and can never be
   matched back.

3. Preserve non-zero exitCode in formatted tool results so failed
   commands show a visible failure signal.

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

* fix: only clear streaming state during retarget, not for all restored sessions

The previous condition (targetId !== scopeTargetId) also fired for
built-in Catty sessions during normal operation, killing active streams.
Now streaming is only cleared when shouldRetargetActiveSession is true,
meaning the session came from a disconnected terminal where any
in-flight response is guaranteed to be dead.

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

* fix: address round 3 review findings

1. Clear externalSessionId during retarget to prevent stale ACP handle
   from surviving if retarget runs before orphan cleanup.

2. Only retarget in visible AI panels — hidden/background panels should
   not race to claim orphaned sessions.

3. Remove unescapeTerminalOutput — data flow trace confirms real newline
   characters arrive at the component. The unescape was corrupting
   legitimate backslash sequences in paths and patterns.

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

* fix: only ACP-cleanup deleted sessions, not preserved ones

Preserved sessions may be reused on reconnect. Running aiAcpCleanup
on them asynchronously could race with a newly started ACP conversation
on the same session ID, tearing down the fresh provider.

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

* fix: abort in-flight streams during retarget and restore ACP cleanup

1. Abort the active request's AbortController when retargeting a session
   with stale streaming state. Prevents late chunks from the old run
   appending into the restored chat.

2. Restore ACP cleanup for all orphaned sessions (not just deleted ones).
   Preserved sessions get a new externalSessionId on next use, so
   cleaning the old one prevents subprocess leaks without affecting
   future conversations.

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

* fix: guard hidden panels from session ownership and skip null map entries

1. Only assign restored sessions in visible panels — hidden panels
   should not race to own sessions via setActiveSessionId, preventing
   MCP/tool calls from being bound to the wrong terminal.

2. Skip null entries in activeSessionIdMap when building
   activeTerminalTargetIds — deleted chats should not block same-host
   history matching on other terminals.

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

* fix: guard MCP sync behind visibility and cancel exec/approvals on retarget

1. Only sync MCP session metadata from visible panels to prevent
   hidden panels from overwriting the scope mapping.

2. Cancel pending approvals and in-flight exec (Catty + ACP) during
   retarget, matching handleStop behavior. Prevents stale tool results
   and approval prompts from reappearing after session retarget.

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

* fix: restore MCP sync for hidden panels

MCP scope is keyed by chatSessionId so hidden panels don't overwrite
visible panels' mappings. The isVisible guard was breaking background
chats that need updated terminal session metadata after reconnects
or workspace changes.

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

* chore: remove unused deletedIds variable

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

---------

Co-authored-by: bincxz <16399091+binaricat@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-27 18:47:32 +08:00
bincxz c74b78a49d Reconcile AI session state with live sessions 2026-03-25 01:03:34 +08:00
bincxz a7f42ec93e Avoid dropping unflushed AI sessions during cleanup 2026-03-25 00:57:48 +08:00
bincxz d6fea6c328 Preserve AI session state and cleanup across panel unmounts 2026-03-25 00:52:33 +08:00
陈大猫 3d4fbf8763 fix: keep workspace MCP scope in sync (#385)
* fix: keep workspace MCP scope in sync

* fix: refresh catty workspace tool context

* fix: preserve AI stream state across tab switches

* fix: align ACP stop and resume with 1code semantics

* fix: harden ACP resume fallback for unsupported agents
2026-03-18 03:33:00 +08:00
陈大猫 9387590696 Fix ACP stop cleanup and cancel state (#384)
* Fix ACP stop cleanup and cancel state

* Block ACP tool writes after stop

* Kill ACP child processes on cleanup

* Cleanup ACP sessions when tabs disappear
2026-03-18 02:24:36 +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 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 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 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 d1a59ed40c fix: add missing cross-window sync for host permissions and agent model map
The StorageEvent handler was missing cases for STORAGE_KEY_AI_HOST_PERMISSIONS
and STORAGE_KEY_AI_AGENT_MODEL_MAP, so changes made in the settings window
were not picked up by the main window.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 17:08:50 +08:00
bincxzandClaude Opus 4.6 f90aa81b2c feat: enforce safety settings, blocklist UI, provider UX improvements, and full i18n
Safety enforcement:
- Command Timeout: use user setting in MCP Server (execViaPty/execViaChannel)
  and Catty Agent path (aiBridge execViaPtyForCatty/execViaChannel fallback)
- Max Iterations: read user setting for Catty (stepCountIs) and ACP (via IPC)
- Permission Mode: observer mode hard-blocks write ops in MCP Server dispatch;
  Catty SDK tools wired to checkToolPermission(); all synced via IPC on change

Command Blocklist UI:
- Add editable regex pattern list in Settings AI Safety section
- Reset to defaults button, add/remove patterns
- IPC sync to MCP Server on change and on mount

Provider UX:
- ModelSelector rewritten as combobox: type-to-filter with suggestions dropdown
- All providers use unified ModelSelector (modelsEndpoint optional)
- API key passed as auth header for model fetching (Bearer / x-api-key)
- Skip model fetch when no API key (except Ollama)
- Provider toggle is now mutually exclusive (activating one disables others)
- New providers default to disabled (switch off)
- Custom provider supports editable display name
- No-provider error: friendly message shown in chat

i18n:
- Full i18n coverage for Settings AI tab (~55 keys)
- Full i18n for AI chat panel (placeholder, empty state, time, sessions)
- en.ts and zh-CN.ts locale files updated

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 17:05:41 +08:00
bincxzandClaude Opus 4.6 950819746e fix: per-agent model memory and correct Claude ACP model presets
- Replace single selectedAgentModel state with per-agent agentModelMap
  persisted to localStorage, so each agent remembers its last selected model
- Default to first preset when no prior selection exists
- Fix Claude model presets: use 'default' instead of 'opus' to match
  what claude-code-acp actually exposes (default=Opus 4.6)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 15:52:58 +08:00
bincxzandClaude Opus 4.6 b2447b06d2 fix: per-scope AI chat isolation and workspace host discovery
- Fix workspace host discovery: use `activeWorkspace.root` instead of
  non-existent `.tree` property, which caused `collectSessionIds` to
  always return empty for workspaces
- Isolate AI chat state per-scope (tab/workspace): activeSessionId,
  isStreaming, abortController, and inputValue are now keyed by
  `${scopeType}:${scopeTargetId}` so different tabs don't interfere
- Add per-chatSession MCP scope metadata to prevent host list mixing
  across workspaces, with chatSessionId passed through the full IPC chain
- Store hostname/username in SSH session objects as fallback for MCP
  host info when renderer metadata is unavailable

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 12:59:47 +08:00
bincxzandClaude Opus 4.6 f53bc05cb3 feat: overhaul AI settings, fix Catty Agent streaming and tool execution
AI Settings:
- Remove External Agents section, add dedicated Codex/Claude Code sections
  with auto-detection and manual path override
- Add OpenRouter model list auto-fetch with searchable dropdown
- Remove standalone Default Model section, integrate into provider cards
- Provider toggle now acts as mutual-exclusive active selector
- Add cross-window state sync via storage events
- Add ErrorBoundary around AI tab for graceful error handling

Catty Agent fixes:
- Fix streaming: use .chat() instead of default Responses API, use
  getReader() pattern instead of for-await, handle text-delta/text chunk
  types correctly per SDK v6
- Fix API key: decrypt encrypted key before passing to SDK
- Fix terminal_execute: use PTY stream (visible in terminal) with MCP
  markers instead of invisible SSH exec channel
- Fix multi-turn: only pass user/assistant text history, skip tool
  messages to avoid SDK schema validation errors
- Fix tool result display: create new assistant message after tool
  results so follow-up text renders correctly

Other:
- Add netcatty:ai:resolve-cli IPC handler for CLI path validation
- Remove Gemini from agent discovery (only Codex + Claude Code)
- Fix lint errors across ChatInput, TerminalLayer, SettingsAITab
- Strip MCP markers from tool execution stdout

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 03:53:39 +08:00
bincxzandClaude Opus 4.6 847df7a023 feat: add MCP server for remote host access, model selector, and PTY execution
- Create netcatty-remote-hosts MCP server (TCP bridge + stdio child process)
  exposing terminal_execute, sftp_*, get_environment tools to ACP agents
- Execute commands via PTY stream with self-erasing markers for terminal
  visibility; disable pagers automatically; 60s timeout fallback
- Inject MCP server into both Codex (ACP) and Claude Code (ACP) sessions
- Add model selector popover with hardcoded presets for Claude (Opus/Sonnet/
  Haiku) and Codex (GPT 5.4, Codex 5.3/5.2/5.1, o3/o4-mini) with thinking
  level sub-menus
- Fix multi-step tool call message flow (mutable flag instead of stale closure)
- Remove CLAUDE_CONFIG_DIR isolation to fix Claude auth; switch Claude to ACP
- Add startup cleanup for orphaned AI sessions
- Guard collectSessionIds against undefined workspace tree
- Remove permission mode chip from chat input

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 00:43:04 +08:00
bincxzandClaude Opus 4.6 150724fc7c fix: enforce session-agent binding and scope-based lifecycle management
- Switching agent deactivates current session, next message creates a new one
- Filter history sessions by both scopeType and targetId
- Restore agent selector when resuming a historical session
- Auto-cleanup AI sessions when terminal/workspace instances are destroyed

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 21:42:09 +08:00
bincxzandClaude Opus 4.6 72887c35b5 feat: add AI chat panel with Vercel AI SDK integration
Add a comprehensive AI assistant feature to netcatty, enabling AI-powered
terminal automation and multi-host orchestration.

Core features:
- AI chat side panel (Zed-style) with agent selector, session history,
  conversation export (Markdown/JSON/TXT), and streaming responses
- Catty Agent: built-in terminal assistant with 9 tools (terminal exec,
  SFTP read/write, multi-host orchestration) using zod schemas
- BYOK provider support: OpenAI, Anthropic, Google, Ollama, OpenRouter,
  and custom OpenAI-compatible endpoints
- Three-tier permission model: Observer / Confirm / Autonomous
- Command safety: blocklist patterns, doom loop detection, abort support
- External agent support: ACP protocol (JSON-RPC over stdio) for
  Claude Agent, Codex CLI, Gemini CLI, and custom agents

Tech stack:
- Vercel AI SDK (ai, @ai-sdk/openai, @ai-sdk/anthropic, @ai-sdk/google)
  with streamText + fullStream for streaming tool-call loops
- AI Elements: adapted conversation (use-stick-to-bottom), message
  (streamdown markdown), prompt-input (InputGroup) components
- Custom bridge fetch adapter routing all API calls through Electron
  main process IPC to avoid CORS
- zod for tool parameter schemas

UI components:
- AIChatSidePanel, AgentSelector, ChatInput, ChatMessageList
- PermissionDialog, ExecutionPlan, ConversationExport
- AI Elements: conversation, message, tool-call, prompt-input
- New UI primitives: InputGroup, Spinner
- Settings AI tab for BYOK configuration and safety settings

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 14:22:28 +08:00