New ButlerRouterMiddleware (priority 80) intercepts user messages,
classifies intent using keyword-based domain detection, and injects
routing context into the system prompt. Supports healthcare, data
report, policy compliance, and meeting coordination domains.
- New: butler_router.rs — keyword classifier + MiddlewareContext injection
- Registered in Kernel::create_middleware_chain() at priority 80
- 9 tests passing (classification + middleware integration)
Tool execution (ShellExec, WebFetch, etc.) had no timeout, causing the
entire streaming response to hang indefinitely when a tool fails or stalls.
Now wraps execute_tool calls in tokio::time::timeout(30s) with a graceful
error message on timeout.
Priority 90 — runs before Compaction@100 and Memory@150.
Detects and replaces company names, money amounts, phone numbers,
emails, and ID card numbers with deterministic tokens (__ENTITY_N__).
External callers can restore originals via DataMasker::unmask().
CRITICAL:
- ask_clarification now terminates Agent Loop in both run() and run_streaming()
paths, preventing the LLM from continuing after requesting user clarification
HIGH:
- SaaS relay now forwards plan_mode and subagent_enabled to backend
- GatewayClient.chatStream now supports onThinkingDelta, onSubtaskStatus,
and token-bearing onComplete — aligned with kernel-types StreamCallbacks
- ZclawStreamEvent type extended with thinking_delta, subtask_status variants
and input_tokens/output_tokens fields for token tracking via Gateway path
- C-1: Add event_sender: None to ToolContext in file_write.rs and
file_read.rs test helper functions (compilation fix)
- I-1: file_write tool now echoes content preview in output JSON,
enabling streamStore.ts artifact auto-creation pipeline to work
- S-2: Fix typo "LLM 锥应错误" → "LLM 响应错误" in loop_runner.rs
- New ask_clarification tool (crates/zclaw-runtime/src/tool/builtin/ask_clarification.rs)
with 5 clarification types: missing_info, ambiguous_requirement, approach_choice, risk_confirmation, suggestion
- Registered as built-in tool in builtin.rs
- Added clarification system prompt instructions to messaging.rs system prompt
- Fixed messaging.rs skill injection: when SkillIndexMiddleware is active,
only inject usage instructions (not full skill list), avoiding duplicate injection
- Fixed pre-existing unicode arrow character causing string literal parse error
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
M1-01: Move Gemini API key from URL query param to x-goog-api-key header,
preventing key leakage in logs/proxy/telemetry (matches Anthropic/OpenAI pattern)
M1-03/M1-04: Replace Mutex .unwrap() with .unwrap_or_else(|e| e.into_inner())
in MemoryMiddleware and LoopGuardMiddleware — recovers from poison
instead of panicking async runtime
M2-08: Add input validation to agent_create — reject empty names,
out-of-range temperature (0-2), and zero max_tokens
M11-06: Replace Date.now() message ID with crypto.randomUUID()
to prevent collisions in classroom chat
1. MemoryMiddleware: replace byte-length check (query.len() < 4) with
char-count check (query.chars().count() < 2). Single CJK characters
are 3 UTF-8 bytes but 1 meaningful character — the old threshold
incorrectly skipped 1-2 char Chinese queries like "你好".
2. QueryAnalyzer: add Chinese synonym mappings for 13 common technical
terms (错误→bug, 优化→improve, 配置→config, etc.) so CJK queries
can find relevant English-keyword memories and vice versa.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
1. App.tsx: add restoreSession() call on startup to prevent redirect
to login page after refresh (isRestoring guard + BootstrapScreen)
2. CloneManager: call syncAgents() after loadClones() to restore
currentAgent and conversation history on app load
3. zclaw-memory: add get_or_create_session() so frontend session UUID
is persisted directly — kernel no longer creates mismatched IDs
4. openai.rs: assistant message content must be non-empty for
Kimi/Qwen APIs — replace empty content with meaningful placeholders
Also includes admin-v2 ModelServices unified page (merge providers +
models + API keys into expandable row layout)
- Detect providers that don't support streaming with tools (DashScope, aliyuncs, bigmodel.cn)
- Add stream_from_complete() to use non-streaming mode when tools are present
- Fix convert_response() to prioritize tool_calls over empty content
- Fix ToolUse message JSON serialization (Null -> "{}")
- Skip invalid tool calls with empty names in streaming
Root cause: DashScope Coding Plan API doesn't support stream=true with tools,
causing tool parameters to be lost or malformed.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add ExecuteSkillTool for LLM to call skills during conversation
- Implement SkillExecutor trait in Kernel for skill execution
- Update AgentLoop to support tool execution with skill_executor
- Add default skills_dir configuration in KernelConfig
- Connect frontend skillMarketStore to backend skill_list command
- Update technical documentation with Skill system architecture
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Security Configuration:
- config/security.toml with shell_exec, file_read, file_write, web_fetch, browser, and mcp settings
- Command whitelist/blacklist for shell execution
- Path restrictions for file operations
- SSRF protection for web fetch
Tool Security Implementation:
- ShellSecurityConfig with whitelist/blacklist validation
- ShellExecTool with actual command execution
- Timeout and output size limits
- Security checks before command execution
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Implement run_streaming() method with async channel
- Stream chunks from LLM driver and emit LoopEvent
- Save assistant message to memory on completion
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add StreamChunk and StreamEvent types for Tauri event emission
- Add stream() method to LlmDriver trait with async-stream
- Implement Anthropic streaming with SSE parsing
- Implement OpenAI streaming with SSE parsing
- Add placeholder stream() for Gemini and Local drivers
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
