Sign each search request with HMAC-SHA256 using Hub ID, a per-request
nonce (UUIDv7), and unix timestamp. The signed reqId is sent in the
request body to prevent unauthorized API usage.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Rename CopilotHub references to Devv Search (constants, types, function
names, error message). Remove unused resolveTimeoutSeconds/resolveCacheTtlMs
imports and use constants directly.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove "requires API key" wording and rebrand to Devv Search across
tool definition, desktop UI, system prompt, and README.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove Brave and Perplexity providers in favor of a single CopilotHub
search endpoint (api-dev.copilothub.ai/web-search). Simplifies schema
to query-only, removes credential dependencies, retains caching.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Keep needsCompaction() method from compaction-feedback PR
- Keep tool result pruning from this branch
- Add "pruning" to CompactionEndEvent.reason type in events.ts
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adding explicit return type to help TypeScript resolve the type
correctly across different build configurations.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The desktop app imports from the root src directory, but turbo wasn't
tracking those files for cache hash calculation. This caused CI builds
to use stale hashes when types changed in the root src directory.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The CompactionResult type includes "pruning" as a reason but SessionEntry
did not, causing type errors when writing compaction entries.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Two-phase pruning approach based on OpenClaw's microcompact-style:
- Soft Trim (30% utilization): Keep head 1500 + tail 1500 chars of large tool results
- Hard Clear (50% utilization): Replace old tool results with placeholder
Protections:
- Never prunes before first real user message (bootstrap protection)
- Protects last 3 assistant messages and their corresponding tool results
- Skips image-containing tool results
- Respects tool allow/deny lists
Enabled by default in tokens/summary compaction modes.
Document how clients receive real-time events via WebSocket and IPC,
covering message lifecycle, tool execution, and compaction events with
full data structure definitions and routing pseudocode.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Widen the LocalChatEvent.event.type union to include compaction_start
and compaction_end, fixing TS2367 comparison errors in use-local-chat.
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>
- Profile: add usage hint for base path
- Memory Recall: clear step-by-step instructions for search and update
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Profile: concise directory path with single usage hint
- Memory Recall: one-liner instruction matching OpenClaw style
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>
Forward compaction_start/compaction_end events through Hub (Gateway path)
and Desktop IPC (local path) to the Zustand messages store. Adds
CompactionEvent types to the SDK, compacting/lastCompaction state to
useMessagesStore, and event routing in both connection-store and
use-local-chat.
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 original icon PNGs had pre-baked rounded corners and transparent
backgrounds. When iOS applies its own superellipse mask on Add to Home
Screen, the transparent corners were filled with white, creating a
visible white border around the icon.
Changes:
- Regenerate all icon PNGs as full-bleed (no rounded corners, opaque
background filling entire canvas) from the existing logo SVG
- Add dedicated apple-touch-icon.png at 180x180 (iOS standard size)
- Add favicon.ico for universal browser fallback
- Replace oversized app/icon.png (540x540) with 192x192 full-bleed
- Update layout.tsx to reference apple-touch-icon.png
- Add explicit purpose: "any" to 192x192 manifest entry
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Memory is now managed through profile files (memory.md, memory/*.md) using
standard read/edit tools, following OpenClaw's file-first approach.
Changes:
- Remove memory/ folder with KV-based memory tools
- Remove group:memory from tool groups
- Update system prompt to remove memory tool references
- Update README docs to reflect file-based memory approach
Agents use workspace.md instructions to manage memory via file operations.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Log storage write errors in SessionManager.enqueue() instead of
silently swallowing them
- Remove existsSync check in ensureSessionDir to avoid TOCTOU race;
mkdirSync with recursive is idempotent when dir already exists
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>
The mkdir call with { recursive: true } can throw ENOENT on macOS APFS
due to filesystem race conditions. This caused SpawnSession child agents
to silently fail — the session data was never written, so the parent
read back empty results ("子任务完成了，但没有返回内容").
Two fixes:
- Add retry logic to mkdir calls in acquireSessionWriteLock and
ensureSessionDir to handle transient ENOENT
- Add .catch() to SessionManager.enqueue() to prevent unhandled
promise rejections from fire-and-forget storage operations
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add a "verifying" connection state between "connected" and "registered"
so collaborators see clear feedback while waiting for the device owner
to approve their connection on Desktop.
Changes across the stack:
- Hub: verify RPC returns isNewDevice flag to distinguish new vs whitelisted
- SDK: emit "verifying" state before verify RPC, pass isNewDevice through
- Store: capture isNewDevice via onVerified, capture rejection via onError
- UI: ConnectionStatus (waiting), RejectedStatus (declined), and
verify success overlay (approved) replace the stuck scanner screen
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Replace overlay approach with conditional rendering for paste validation
states. Success shows checkmark icon with 600ms delay before connecting,
error shows alert with message and auto-resets after 2s. Improves
Connecting text visibility.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Rewrite user-facing text to be source-agnostic and result-focused:
- Connect prompt: "Scan to start" / "Scan a QR code to use an Agent"
- Empty chat: "Your Agent is ready"
- Input placeholder: "Ask your Agent..." / "Scan QR code to get started"
- Bump chat input font to text-base for mobile readability
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Replace sheet-based scanner with inline QrScannerView, add scan/paste
mode toggle for desktop, and fullscreen camera overlay for mobile.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Comprehensive single-source-of-truth document covering all product
modules, features, and technical details. Serves as the foundation
for subsequent UI design, copywriting, and user journey documents.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Rewrite QrScannerView with full state machine (idle/requesting/scanning/
detected/success/error), corner bracket animations snapping to QR
cornerPoints, flash toggle, and haptic feedback.
Add QrScannerSheet as bottom sheet wrapper for mobile. Simplify
ConnectPrompt to use useIsMobile() — mobile shows scan button + sheet,
desktop shows paste-only UI.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add cornerPoints, hasFlash/toggleFlash, and manual start/stop/pause
to useQrScanner. Change enabled default to false for click-to-start.
Add scoped CSS animations for scanner bracket breathing and error shake.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Swap the plain <textarea> for a minimal Tiptap (ProseMirror) editor
with IME-safe Enter-to-submit, Shift+Enter newline, placeholder
support, and an optional imperative ref (getText/setText/focus/clear).
All rich-text extensions are disabled — only plain text is allowed.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The sessions_spawn tool was not showing in the desktop tools UI because
TOOL_GROUPS and ALL_KNOWN_TOOLS were missing the subagent group.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
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>
