Sync latest code from src/shared/gateway-sdk/ into packages/sdk/,
update all backend imports to use @multica/sdk, and remove the
duplicate src/shared/gateway-sdk/ directory.
- Translate Chinese comments to English in SDK source
- Fix package.json exports with default condition
- Add @multica/sdk as workspace dependency for backend
- Update imports in gateway, test-client, and hub
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Document thin-shell architecture, package responsibilities, Zustand
best practices, import conventions, and new feature checklist.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Move setConfig() after imports in layout.tsx
- Add gateway disconnect cleanup in hub-init useEffect
- Replace silent catches with toast error notifications in hub store
- Optimize chat selectors with useMemo and useCallback/getState()
- Remove unused getMessagesByAgent from messages store
- Add clipboard try/catch with error toast
- Add skeleton loading states for hub sidebar and chat header
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Create gateway store in @multica/store (WS connection independent of components)
- Gateway auto-connects when hub is ready, messages handled internally
- Move scroll-fade hook to @multica/ui/hooks
- Move Chat component to @multica/ui/components
- Add setConfig() call in web layout for URL injection
- Delete all web-local hooks, components, and lib/config
- Web app is now a pure shell: layout.tsx + page.tsx
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Move useMessages from apps/web to packages/store/src/messages.ts
- Convert useState to Zustand store for global message persistence
- Add reserved interfaces: updateMessage, loadMessages, getMessagesByAgent
- Update chat.tsx imports to use @multica/store
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Move useDeviceId from apps/web to packages/store/src/device-id.ts
- Update imports in chat.tsx and use-gateway.ts to use @multica/store
- Add uuid dependency to @multica/store
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Create @multica/fetch package for HTTP client and URL config
- Migrate hub store and hub-init hook to @multica/store
- Move HubSidebar component to @multica/ui for web/desktop reuse
- Update web app imports to use shared packages
- Remove counter store example and its component-example usage
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Direct Perplexity API (pplx-*) uses "sonar-pro" model name
- OpenRouter (sk-or-*) uses "perplexity/sonar-pro" model name
- Refactor inferPerplexityBaseUrl to inferPerplexityConfig returning both baseUrl and model
- Export internal functions for potential reuse
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When loading skills, automatically check if bundled skills have a higher
version than managed skills. If so, update the managed skill to the
newer bundled version.
This ensures users get skill updates when upgrading multica, without
needing manual intervention.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove work context and workflow preferences collection since this is a
general-purpose agent not tied to specific work types.
Setup now only collects:
- Agent identity (name, style) -> soul.md
- User info (name, timezone, preferences) -> user.md
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add soul.md to the list of configurable files
- Include agent identity questions (name, role, style)
- Update file examples to show soul.md updates
- Start conversation by asking about agent's name first
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add `multica profile setup <id>` command for interactive profile setup
- Create profile-setup skill with conversational setup wizard
- Agent collects user info through natural dialogue and updates profile files
- Supports updating user.md, workspace.md, and config.json
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove identity.md and bootstrap.md from profile files
- Merge identity content into soul.md (now contains identity, personality, and behavior)
- Update templates, storage, and types to reflect new structure
- Update tests to match new profile structure
Profile now has 4 files: soul.md, user.md, workspace.md, memory.md
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Update README.md with new multica command examples
- Update CLAUDE.md common commands section
- Document all subcommands and their usage
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Simplify bin entries to multica and mu
- Update npm scripts to use new CLI entry point
- Modify build-cli.js to build single multica.mjs binary
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Create unified entry point at src/agent/cli/index.ts
- Add subcommand modules: run, chat, session, profile, skills, tools, credentials, dev
- Support both 'multica' and 'mu' aliases
- Add session management commands (list, show, delete)
- Integrate dev server commands into CLI
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Update workspace.md template with Profile Files table explaining
when to update each file
- Inject actual profile directory path in buildSystemPrompt()
- Add getProfileDir() method to ProfileManager
- Agent can now use edit/write tools to update profile files
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Enrich soul.md with core truths, boundaries, and continuity guidance
inspired by moltbot's template design
- Add user.md template for building user profile and preferences
- Add workspace.md template for workspace behavior guidelines
- Update memory.md and bootstrap.md with more structured content
- Update all related storage, types, and test files
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The tools.md template content duplicated information already present in
each tool's schema description, causing maintenance burden and potential
inconsistencies. Tool usage guidelines can be added to soul.md if needed.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add AGENTS.md file to provide guidance for AI agents using OpenAI's
convention. The file mirrors CLAUDE.md content to ensure consistent
AI-assisted development experience across different agent platforms.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Added 36 tests covering toolDisplayName, formatToolArgs, extractResultDetails, and formatResultSummary functions. Also refactored code to eliminate duplicate truncate function and remove unused variable.
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
* feat(agent): improve interactive CLI with colors, spinner, and status bar
- Add colors.ts module with ANSI terminal color utilities
- Add spinner animation for tool execution feedback
- Add persistent status bar showing session/provider/model
- Apply colors to welcome banner, prompts, commands, and suggestions
- Support NO_COLOR env for accessibility
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix(agent): correct cursor position with ANSI-colored prompts
Strip ANSI escape codes when calculating visual length of prompt
to ensure cursor is positioned correctly after colored text.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix(agent): prevent duplicate input echo in interactive CLI
Lazy-initialize readline.Interface only when multiline mode is active.
This prevents readline from interfering with autocomplete's raw mode,
which was causing user input to be echoed twice.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor(agent): move CLI files to dedicated cli/ directory
Reorganize CLI-related files into src/agent/cli/ for better separation:
- interactive.ts (was interactive-cli.ts)
- non-interactive.ts (was cli.ts)
- profile.ts, skills.ts, tools.ts (was *-cli.ts)
- autocomplete.ts, colors.ts, output.ts (CLI utilities)
Update all imports, package.json scripts, and build configuration.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Update skill-creator instructions to:
- Default to profile directory when running under a profile
- Fall back to global directory when no profile is active
- Show both directory structures
- Add profile skill removal instructions
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add 'list' action to process tool that displays all registered processes
with their ID, command, status, duration, and source (exec/process).
Example output:
ID COMMAND STATUS DURATION SOURCE
019c139c-dbb7-70ec-ab91-0a7fd2711043 curl -X POST running 15.2s [exec]
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Update Skill Precedence section to show only two sources:
1. Profile-specific skills (highest priority)
2. Global skills (~/.super-multica/skills/)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Handle tool_execution_update events in CLI output to show live progress
while commands are running. Shows the last 60 characters of output on
a single line that updates in place.
This completes the real-time streaming feature added to exec tool.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Utilize the onUpdate callback from pi-agent-core's AgentTool interface
to stream output updates in real-time while commands are executing.
- Accept onUpdate as 4th parameter in execute function
- Emit tailBuffer updates on each stdout/stderr data event
- Stop emitting updates once command is backgrounded (yielded)
This enables UI to show live command output progress via the
tool_execution_update agent event.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Previously, when a command exceeded yieldMs (default 5s) and was
auto-backgrounded, exec returned an empty output string. This caused
agents to misinterpret slow commands (like curl) as failed, leading
to infinite retry loops.
Changes:
- Implement three-layer buffer system (pending 30KB + aggregated 200KB + tail 1KB)
- Return collected output snapshot when backgrounding instead of empty string
- Increase default yieldMs from 5s to 10s for better coverage
- Add auto sweeper for terminated process cleanup (30min TTL)
- Register process immediately on spawn to capture all output
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When input exceeds terminal width, the text wraps to new lines but the
old code only cleared one line, causing screen flashing and duplicate
lines. Now tracks input line count and cursor position across wrapped
lines for proper rendering.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Automatically initialize managed skills directory with bundled skills
on first load. This ensures bundled skills are available without
requiring explicit initialization.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove bundled, extraDirs, and plugin skill sources
- Skills now load from only two sources:
1. managed (~/.super-multica/skills/) - global skills
2. profile (~/.super-multica/agent-profiles/<id>/skills/) - profile-specific
- Add initializeManagedSkills() to copy bundled skills on first run
- Delete plugin.ts (multica.plugin.json discovery)
- Update documentation and tests
This simplifies the architecture by treating bundled skills as
managed skills that are initialized once, rather than maintaining
multiple loading sources with complex precedence.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Replace phased roadmap with simple future tools list
- Add Chinese README (README.zh-CN.md)
- Add language switching links between EN/CN docs
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
