- 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>
Add global Hub singleton for cross-module access by subagent tools.
Add createSubagent() method to Hub for spawning ephemeral child agents
with isSubagent flag and custom system prompts.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implement subagent registry, persistence store, and announcement flow
for child agent lifecycle management. Includes types, registry with
auto-archive sweeper, session JSONL reading for result extraction,
and formatted announcement message delivery.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Only forward message_start/update/end (assistant role) and
tool_execution_start/end to clients. Drop agent_start, agent_end,
turn_start, turn_end, and tool_execution_update at the Hub layer.
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>
Add /model command to interactively switch models:
- /model: Show current model and list available models for provider
- /model <name>: Switch to specified model (preserves session)
Example usage:
/model # Shows claude-opus-4-5, claude-sonnet-4-5, etc.
/model claude-sonnet-4-5 # Switch to sonnet model
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Move src/agent/oauth/ to src/agent/providers/oauth/ (parent-child structure)
- Delete deprecated oauth/providers.ts re-export file
- Simplify Claude model names: claude-opus-4-5 (without date suffix)
- Update Codex models to current lineup (gpt-5.2, gpt-5.1-codex, etc.)
- Set claude-opus-4-5 as default model for claude-code provider
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
