Update workspace.md template to prevent agents from claiming to
"remember" things without actually editing files. The new guidance:
- Uses "No Mental Notes!" as a strong warning
- Lists specific trigger phrases (记住, Remember, I prefer, etc.)
- Maps each trigger to the appropriate file to edit
- Explicitly forbids saying "I'll remember" without file edits
This addresses the issue where agents would acknowledge user
preferences verbally but not persist them to profile files.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Change `multica dev` default from gateway+console+web to desktop app
- Remove console from dev command options (use embedded Hub in desktop)
- Update package.json scripts to reflect new defaults
- Update README.md and CLAUDE.md architecture documentation
The desktop app has an embedded Hub, so no separate console/gateway is
needed for local development. Gateway is now optional, only needed for
remote client access.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Simplify 4-layer policy to 3-layer:
- Layer 1: Global allow/deny (user config)
- Layer 2: Provider-specific rules
- Layer 3: Subagent restrictions
Removed:
- ToolProfileId type (minimal/coding/web/full)
- TOOL_PROFILES constant
- getProfilePolicy function
- profile field from ToolsConfig
Users can achieve the same effect using allow/deny with group:* syntax.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Resolve tools before building subagent system prompt so the
"## Tooling" section is included, matching OpenClaw's pattern.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Only inject workspace.md into system prompt (not soul, user, memory)
- Add profile directory path to workspace section for on-demand file access
- Agent now reads soul.md, user.md, memory.md on first session using tools
- Reduces system prompt size and improves token efficiency
- Aligns with workspace.md template instructions ("Read soul.md first")
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>
Add AsyncAgent.subscribe() that allows multiple subscribers to receive
the same agent events, enabling local IPC chat to coexist with other
event consumers.
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>
Add ReasoningMode type (off/on/stream) to AgentOptions and related
config types. Add extractThinking() for extracting thinking content
blocks from LLM responses, mirroring the existing extractText() pattern.
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>
Structured, mode-aware system prompt builder inspired by OpenClaw.
Supports three modes (full/minimal/none), safety constitution,
conditional tool sections, runtime info, and prompt telemetry.
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>
- Rename storage path from ~/.super-multica/devices/ to
~/.super-multica/client-devices/ for clarity
- Change JSON format from bare array to { version, devices[] }
dict for future extensibility
- Auto-migrate legacy array format on load
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Merge remote main branch, keeping both device verification (ws-auth-handshake)
and agent settings/profile features from main.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add 60s timeout to pending device confirms to prevent Promise leaks
when client disconnects before user responds
- Add offDeviceConfirmRequest to preload and clean up IPC listener on
component unmount to prevent duplicate listener accumulation
- Extract duplicated parseUserAgent into shared lib/parse-user-agent.ts
- Clean up expired tokens in DeviceStore.registerToken to prevent
memory accumulation from unscanned QR codes
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When an unverified device sends a non-RPC message, reply with an
"error" action containing UNAUTHORIZED code so the client knows
verification is required.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Extend DeviceEntry with optional DeviceMeta field. Verify handler
extracts meta from params and passes it through to onConfirmDevice
callback and deviceStore.allowDevice for persistence.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add DeviceStore for managing one-time tokens and persistent device
whitelist. Create async verify RPC handler that validates tokens and
awaits Desktop user confirmation for first-time connections. Whitelisted
devices (reconnections) pass through instantly. Add message guard to
reject unverified device traffic.
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>
- Disable noUnusedLocals/noUnusedParameters in desktop tsconfig
(external src/ files have unused imports that fail strict checking)
- Add TSchema constraint to wrapTool generic to satisfy AgentTool type
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 profileId option to createAgent() method
- Default to "default" profile for all agents
- Ensures every agent has an associated profile for memory and config
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>
Unify locking strategy across the project by using a custom synchronous
file lock (exclusive-create based, with PID stale detection) instead of
the proper-lockfile dependency, matching the pattern in session-write-lock.
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>
- Add proper-lockfile for concurrent-safe store updates with fallback
- Add "format" to AuthProfileFailureReason
- Two-level round-robin sort: credential type priority (OAuth > API key), then lastUsed
- Filter out profiles with missing/invalid credentials from candidates
- Add preferredProfile option to resolveAuthProfileOrder
- Export coerceStore and ensureAuthStoreFile for testing
- Add store.test.ts with coerceStore, load/save round-trip, corruption handling
- Update order.test.ts mocks for resolver and registry dependencies
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Port from OpenClaw:
- session-write-lock: file-level write lock with atomic creation, reference
counting, stale lock detection, and process cleanup handlers
- session-file-repair: auto-detect and repair malformed JSONL lines with
backup and atomic rename
- session-transcript-repair: fix tool call/result pairing issues including
displaced results, duplicates, orphans, and missing inputs
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add minLength:1 to sessions_spawn task parameter to prevent empty
task strings. Remove parentSessionId from AgentOptions as the
subagent registry tracks lineage via requesterSessionId.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Call initSubagentRegistry() after setHub() in Hub constructor to
restore persisted runs. Call shutdownSubagentRegistry() before
closing agents in shutdown() to mark active runs as ended.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Replace for-await stream consumption in watchChildAgent with
waitForIdle() + onClose() callbacks on AsyncAgent. This prevents
conflict with Hub.consumeAgent() which also reads the Channel.
Add shutdownSubagentRegistry() for clean Hub shutdown, guard
Hub access with isHubInitialized(), and clean resumedRuns in sweep.
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>
Implement multi-profile auth system with exponential-backoff cooldowns,
modeled after OpenClaw's auth-profiles system. Includes types, constants,
persistent store (auth-profiles.json), usage tracking with cooldown
calculation, and profile ordering with round-robin and explicit modes.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Register sessions_spawn tool in the tool system with TypeBox schema.
Subagents are blocked from spawning nested subagents via both tool
policy (DEFAULT_SUBAGENT_TOOL_DENY) and runtime guard. Add group:subagent
tool group and parentSessionId to AgentOptions.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
