Anand 51ff999b8d AI assistant: reasoning effort that works locally, usage stats, perf and UX fixes ...

- Map reasoning effort to chat_template_kwargs.enable_thinking alongside
  reasoning_effort, so the selector actually toggles thinking on Qwen3-class
  local runtimes (LM Studio/vLLM/Ollama), which ignore reasoning_effort
  entirely. Falls back cleanly on hosted APIs that reject the extra field.
- Track and render per-message token usage (prompt/completion/tokens-per-sec)
  from the ferrum_usage SSE envelope, with an estimated fallback.
- Persist reasoningEffort and createdAt on conversations/messages.
- Memoize Markdown on text so streaming a response no longer re-parses every
  already-committed message on each token.
- AI provider settings: auto-add all discovered models on first save instead
  of requiring a second click per model.
- SSE event stream: clear the write deadline so long-lived connections don't
  get cut mid-stream.

2026-09-11 09:22:49 +05:30

..

public

Fix contaminated default theme and expand to 6 distinct looks

2026-09-03 14:52:13 +05:30

src

AI assistant: reasoning effort that works locally, usage stats, perf and UX fixes

2026-09-11 09:22:49 +05:30

.gitignore

Initial commit

2026-09-03 08:36:04 +05:30

.oxlintrc.json

Initial commit

2026-09-03 08:36:04 +05:30

embed.go

Initial commit

2026-09-03 08:36:04 +05:30

index.html

Initial commit

2026-09-03 08:36:04 +05:30

package-lock.json

Add API keys, MCP server, admin AI providers, and a built-in local LLM option

2026-09-06 13:26:30 +05:30

package.json

Add API keys, MCP server, admin AI providers, and a built-in local LLM option

2026-09-06 13:26:30 +05:30

tsconfig.app.json

Initial commit

2026-09-03 08:36:04 +05:30

tsconfig.json

Initial commit

2026-09-03 08:36:04 +05:30

tsconfig.node.json

Initial commit

2026-09-03 08:36:04 +05:30

vite.config.ts

Initial commit

2026-09-03 08:36:04 +05:30

vitest.config.ts

Initial commit

2026-09-03 08:36:04 +05:30