- 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>
Problem: Agent could not invoke appropriate skills when user asked about
financial reports because LLM didn't know which skills were available.
Root causes:
1. System prompt lacked available skill list
2. SkillManifest struct missing 'triggers' field
3. SKILL.md loader not parsing triggers list
4. "财报" keyword not matching "财务报告" trigger
Changes:
- Add triggers field to SkillManifest struct
- Parse triggers list from SKILL.md frontmatter
- Inject skill list into system prompt in kernel.rs
- Add "财报", "财务数据", "盈利", "营收" triggers to finance-tracker
- Add "财报分析" trigger to analytics-reporter
- Document fix in troubleshooting.md
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>
Add BrowserHand implementation with:
- BrowserAction enum for all automation actions
- Navigate, Click, Type, Scrape, Screenshot, FillForm
- Wait, Execute (JavaScript), GetSource, GetUrl, GetTitle
- Scroll, Back, Forward, Refresh, Hover, PressKey, Upload
- Hand trait implementation with config and execute
- Integration with existing Tauri browser commands
Browser Hand enables agents to interact with web pages
for navigation, form filling, scraping, and automation.
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>
Remove temporary console.log and eprintln! statements added during
troubleshooting the model configuration issue.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
