digua cdb2bfea7c feat: unify LLM streaming with thinking display and Web/cache API shims ...

- Extract runSimpleLlmStream to @openchatlab/node-runtime for shared
  Electron/Server streaming with thinking_start/delta/end event handling
- Simplify Electron IPC ai.ts by delegating to shared stream function
- Add thinking/thinkingDone fields to LlmStreamChunk and preload types
- Add collapsible thinking process display in SQL LAB with auto-scroll
- Implement Web chatStream via SSE with proper error propagation
- Add /_web/cache/save-to-downloads and show-in-folder server routes
- Add cacheApi shim in Web registry for server-side file operations
- Increase SQL LAB maxTokens to 4096 to accommodate reasoning models
- Detect finishReason:length and show token limit error message
- Add i18n keys for thinking/thinkingProcess/errorTokenLimit (4 locales)

2026-05-18 22:32:00 +08:00

..

main

feat: unify LLM streaming with thinking display and Web/cache API shims

2026-05-18 22:32:00 +08:00

preload

feat: unify LLM streaming with thinking display and Web/cache API shims

2026-05-18 22:32:00 +08:00

shared

feat: 上下文压缩逻辑优化

2026-05-06 23:56:45 +08:00