Add writeWithImages() to AsyncAgent for passing images directly to
the LLM via ImageContent. Extend Agent.run() to accept optional
images parameter. Update ChannelManager.routeIncoming() to download
media files and forward them: images as ImageContent to the LLM,
audio/video/document as file paths for agent-driven processing.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
After child subagents complete, the coalesced announcement runs as an
internal turn which rolls back all messages from the parent's in-memory
context. This causes the parent LLM to lose findings in subsequent turns.
Add persistResponse option to writeInternal that re-injects the LLM's
summary as a non-internal assistant message after the internal run
completes. The internal prompt stays hidden while the summary persists
in both memory and session JSONL for future turns.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add agent_error event type to MulticaEvent union so errors from
agent runs reach subscribe() consumers (Desktop IPC + Channel).
Make emitMulticaEvent public on Runner so AsyncAgent can emit errors.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Announcement messages from subagent completion flows were persisted as
regular user messages, polluting conversation history and leaking
orchestration instructions to frontend/CLI.
- Add `internal?: boolean` to SessionEntry message variant
- SessionManager.saveMessage accepts { internal: true } option
- SessionManager.loadMessages filters internal by default
- Agent.runInternal() tags messages as internal, rolls back from memory
- Agent.withRunMutex() prevents concurrent run/runInternal mis-tagging
- AsyncAgent.writeInternal() suppresses event forwarding during internal runs
- Announce flows use writeInternal() instead of write()
- Desktop IPC getHistory reads from session storage (filtered)
- CLI session show parses SessionEntry, supports --show-internal flag
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add localApprovalHandlers map so exec approval requests can be routed
to the Electron renderer via IPC instead of requiring a Gateway
connection. Expose setLocalApprovalHandler/removeLocalApprovalHandler
and resolveExecApproval on Hub for the IPC layer to use.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Wrap maybeCompact() in try/catch to ensure compaction_end always fires
- Widen multicaListeners type to match subscribeAll() callback signature
- Import CompactionEndEvent from SDK instead of inline type casts
- Add doc comment explaining reason field type difference (agent vs SDK)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implements a simple memory_search tool for searching memory files:
- Searches memory.md and memory/*.md files by keyword
- Returns matching lines with context (2 lines before/after)
- Supports case-sensitive/insensitive search
- Respects maxResults limit
Tool is only available when a profile is active (has profileDir).
System prompt includes memory usage guidance when tool is present.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Introduce MulticaEvent type system parallel to pi-agent-core's AgentEvent,
with compaction_start and compaction_end events. Agent.subscribeAll() merges
both event streams. maybeCompact() now emits events bracketing the compaction
work, gated by a new SessionManager.needsCompaction() pre-check.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The subagent announce flow reads the child's session file to extract
results, but saveMessage() is fire-and-forget (void enqueue). When
agent.run() completes, pending appendEntry writes may not have flushed
to disk yet, causing readLatestAssistantReply() to find no entries.
Add SessionManager.flush() and call it in AsyncAgent.write() after
agent.run() returns. This ensures waitForIdle() won't resolve until
all session data is on disk, fixing the "no return content" issue.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add getProviderInfo() and setProvider() methods to Agent class
- Expose provider methods via AsyncAgent
- Add setLlmProviderOAuthToken() for storing OAuth credentials
- Extend ProviderConfig type with OAuth fields (oauthToken, oauthRefreshToken, oauthExpiresAt)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add getMessages() to Agent and AsyncAgent for retrieving session history
- Fix type annotations in hub.ts for AgentMessage handling
- Remove duplicate type export in preload.ts
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Read reasoningMode from profile config and storedMeta when not
explicitly set via options (matching thinkingLevel pattern)
- Skip extractThinking() call when reasoningMode is "off"
- Clean up redundant ?? undefined casts in CLI entry points
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Wire reasoningMode through Agent runner, CLI output, and all CLI
entry points (run, interactive, non-interactive). In stream mode,
thinking content is printed to stderr in real-time. In on mode,
thinking is shown after message completion. Default is stream.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- reloadSystemPrompt() now updates both agent and session prompt
- reloadSystemPrompt() uses buildSkillsPrompt() consistently (not buildModelSkillsPrompt)
- Extract rebuildSystemPrompt() to eliminate duplicated builder logic
- Preserve original tool name casing in tooling summary (matching OpenClaw)
- Fix report line count to use actual newline count
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
ProfileManager.buildSystemPrompt() now delegates to the structured builder.
Runner assembles prompt after tool resolution with safety, tooling summary,
and runtime info. Subagent prompts use minimal mode with safety constitution.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add AgentStyle type with 6 preset options (professional, friendly, etc.)
- Add getStyle/setStyle methods to ProfileManager
- Update soul.md template to include style section
- Add reloadSystemPrompt support for style changes
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add getSoulContent/updateSoulContent to ProfileManager
- Create soul.md with agent name when updating profile name
- Add reloadSystemPrompt() method to Agent and AsyncAgent
- Include soul.md content in system prompt build
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add methods to ProfileManager, Agent, and AsyncAgent for:
- Getting/setting agent display name (stored in config.json)
- Getting/setting user.md content
This enables the desktop app to manage agent settings.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Fix originalToolsConfig assignment to handle undefined properly
- Fix devNull type cast for WritableStream compatibility
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Merge auth-profiles feature from main into runner.ts
- Merge closeCallbacks feature from main into async-agent.ts
- Regenerate pnpm-lock.yaml with new dependencies
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add setToolStatus() to persist tool enable/disable to profile config
- Add getActiveTools() and reloadTools() methods
- Add getSkillsWithStatus(), getEligibleSkills(), reloadSkills() methods
- Add updateToolsConfig() and setToolEnabled() to ProfileManager
- Ensure profile directory is created on Agent initialization
- Fix reloadTools() to re-read profile config for latest changes
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Replace single-retry with while loop that exhausts all candidate profiles
- Add "format" detection to classifyError (400, malformed, bad request, schema)
- Make timeout errors rotatable (some providers hang on rate limit)
- Export classifyError and isRotatableError for testing
- Add error-classification.test.ts with coverage for all failure reasons
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Extend credentials.ts with llm.order and listProfileIdsForProvider.
Add resolveApiKeyForProfile and resolveApiKeyForProvider to resolver.
Modify runner to support dynamic API key swapping and automatic
rotation on auth/rate_limit/billing errors with retry.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Expose PiAgentCore events through the full backend pipeline:
- Agent.subscribe() transparently forwards engine events
- AsyncAgent pushes all AgentEvent into Channel alongside error Messages
- Hub discriminates ChannelItem and forwards events via StreamAction
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Create src/agent/providers/ with registry.ts and resolver.ts
- registry.ts: Provider metadata, status checking, login instructions
- resolver.ts: API key resolution, model resolution
- oauth/providers.ts now re-exports from providers/ (deprecated)
- tools.ts: Remove PROVIDER_ALIAS and DEFAULT_MODELS (moved to providers/)
- Update imports in runner.ts and chat.ts
This separates concerns:
- oauth/ only handles OAuth credential reading
- providers/ manages all provider metadata and resolution
AsyncAgent now subscribes to pi-agent-core events (message_start,
message_update, message_end) and forwards incremental text deltas
through a stream callback. Hub registers the callback and sends
stream payloads to the requesting client via Gateway.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add isOAuthProvider() and isProviderAvailable() helpers
- Show login instructions for OAuth providers without credentials
- Show configuration example for API Key providers without keys
- Fail early with helpful error message instead of cryptic API errors
Separate OAuth credential reading (external CLI tools) from the main
CredentialManager (API Key configuration in credentials.json5).
- credentials.ts: API Key configuration management
- oauth/: External OAuth credential reading (Claude Code, Codex)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add provider alias mapping (claude-code -> anthropic)
- Resolve API key from OAuth credentials for claude-code and codex
- Add default models for each provider
Co-Authored-By: Claude Opus 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>
- 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>
Add mergeToolsConfig function to combine Profile tools config with
CLI options. Profile config serves as base, CLI options override.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Use generic OPENROUTER_* env vars (OPENROUTER_API_KEY, OPENROUTER_BASE_URL,
OPENROUTER_MODEL) via the existing fallback mechanism instead of hardcoding
mappings to OPENAI_* vars. Also add a guard when resolveModel returns
undefined to throw a clear error instead of crashing on property access.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add skills?: SkillsConfig to AgentOptions
- Update runner.ts to pass skills config to SkillManager
- Merge extraSkillDirs from options with config.load.extraDirs
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
