Commit Graph

21 Commits

Author SHA1 Message Date
lucaronin
6ee7f219f5 feat: add gemini cli agent support 2026-04-29 11:16:52 +02:00
lucaronin
3db1ed9dc5 fix: split ai permission tooltips 2026-04-29 10:44:20 +02:00
lucaronin
7a7ef5d9ca fix: improve ai permission toggle contrast 2026-04-29 10:35:19 +02:00
lucaronin
d2d4746d5c feat: add vault ai agent permission modes 2026-04-29 01:26:33 +02:00
lucaronin
38fb8a7370 feat: copy mcp config from app 2026-04-28 14:03:10 +02:00
lucaronin
2fe6c5b580 fix: respect selected ai agent in right panel 2026-04-28 07:36:22 +02:00
lucaronin
db82aee172 refactor: consolidate ai agent session flow 2026-04-28 04:20:40 +02:00
lucaronin
9265b8f117 fix: stabilize AI composer text editing 2026-04-26 22:11:54 +02:00
lucaronin
daa1e3e985 fix: keep ai composer responsive after image paste 2026-04-24 13:52:58 +02:00
lucaronin
9536efee0e fix: persist AI panel chats across reopen 2026-04-20 10:28:48 +02:00
lucaronin
d540d76f73 feat: support selectable cli ai agents 2026-04-13 19:37:59 +02:00
lucaronin
7933fe1bfb feat: add inline AI prompts to command palette 2026-04-12 13:14:18 +02:00
lucaronin
d0c3a6b889 refactor: remove Trash system — delete is now permanent with confirm modal
Remove all vestiges of the abandoned Trash system: trashed/trashedAt fields
from types, frontmatter parsing, sidebar filtering, editor banners, inspector
components, mock data, and all related tests. Delete is already permanent via
useDeleteActions with a confirmation dialog. Notes with trashed:true in
existing vault frontmatter are now treated as normal notes (the flag is
ignored by the parser).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-06 12:21:56 +02:00
lucaronin
3e05a9425a test: add Playwright smoke test for exact-match search ranking
Verifies that searching "Writing" in Quick Open shows the exact title
match first, followed by prefix matches. Also adds Refactoring test
entries to mock data and demo vault.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-08 23:53:00 +01:00
lucaronin
35afd09364 fix: AI chat wikilinks — system prompt + integration tests
Root cause: buildContextSnapshot (the system prompt used when a note is
active — the common case) did NOT instruct the AI to use [[wikilinks]].
Only buildAgentSystemPrompt (the fallback when no context) had it.
So the AI almost never produced clickable wikilinks.

Fix: Add the [[Note Title]] wikilink instruction to
buildContextSnapshot's preamble.

The click handler chain was already correct (verified with new
integration tests): MarkdownContent → AiMessage → AiPanel →
notes.handleNavigateWikilink → findWikilinkTarget → handleSelectNote.

Tests added:
- Unit: buildContextSnapshot includes wikilink instruction
- Integration: clicking wikilinks in AiPanel calls onOpenNote
- Playwright: wikilink renders, click opens note in tab

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-07 13:42:32 +01:00
lucaronin
21e0cb6c6e fix: handle Escape at panel level and manage focus across active states
Move Escape handler from input onKeyDown to a window-level listener
scoped to the panel, so it works even when input is disabled during
AI response. When agent is active, focus transfers to the panel
container; when idle, focus returns to the input.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-03 14:34:18 +01:00
lucaronin
4041655d95 fix: auto-focus AI Chat input on panel open and close on Escape
When AI Chat panel mounts (via Cmd+I), the input field now receives
focus automatically so users can type immediately without clicking.
Pressing Escape in the input closes the panel.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-03 14:30:12 +01:00
Luca Rossi
7d563b28fd feat: contextual AI chat on open note (Cmd+I) (#169)
- Cmd+I toggles AI panel with context from the active note
- Context bar shows note title in AI panel when a note is open
- useAiAgent accepts optional contextPrompt used as system prompt
- ai-context.ts extracts structured context from note + related entries
- Updated AiPanel, EditorRightPanel, App, useAppCommands, useCommandRegistry
- 1292 frontend tests pass, coverage 78.96%

Co-authored-by: Test <test@test.com>
2026-03-02 05:00:29 +01:00
Luca Rossi
e0c5753be6 feat: replace Anthropic API with Claude CLI for AI chat and agent panels (#159)
* feat: add claude CLI subprocess backend for AI panels

Add claude_cli.rs module that spawns the local `claude` CLI as a
subprocess instead of calling the Anthropic API directly. This removes
the need for users to configure an API key — the CLI uses the user's
existing Claude authentication.

- find_claude_binary(): discovers claude in PATH or common locations
- check_cli(): returns install/version status for the frontend
- run_chat_stream(): spawns claude -p with stream-json for chat panel
- run_agent_stream(): spawns claude with MCP vault tools for agent panel
- Parses stream-json NDJSON events and emits typed Tauri events
- Remove http:default capability (no longer calling APIs from frontend)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat: replace Anthropic API with Claude CLI for AI chat and agent panels

Remove direct Anthropic API calls and the entire tool-use loop from the frontend.
Both AI Chat and AI Agent panels now delegate to the `claude` CLI subprocess via
Tauri commands, streaming NDJSON events back to the UI.

Key changes:
- ai-chat.ts / ai-agent.ts: replace SSE/API streaming with Tauri invoke + listen
- useAIChat / useAiAgent hooks: simplified to use CLI streaming callbacks
- AIChatPanel / AiPanel: remove API key dialogs, model selectors, undo support
- SettingsPanel: remove Anthropic key field (no longer needed)
- claude_cli.rs: add comprehensive tests (37 total, 90% coverage)
- mock-handlers: replace ai_chat with check_claude_cli / stream_claude_* stubs
- Net -432 lines across 17 files

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: add --verbose flag to claude CLI subprocess args

* chore: exclude search.rs and lib.rs from coverage (qmd integration + Tauri setup)

---------

Co-authored-by: Test <test@test.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-01 19:49:58 +01:00
lucaronin
e405ea74d9 feat: wire AI agent panel to Claude API with tool calling
- Add ai-agent.ts: tool definitions (14 MCP tools), agent loop with
  tool_use handling, WebSocket bridge execution (port 9710)
- Add useAiAgent hook: state machine (idle/thinking/tool-executing/done),
  message management, abort support, undo tracking
- Update AiPanel.tsx: replace mock messages with real hook, add model
  selector, input bar, empty state
- Add /api/ai/agent Vite proxy: non-streaming Anthropic endpoint for
  tool-use loop
- Add design/ai-agent-wiring.pen with state machine diagram

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-28 22:16:06 +01:00
Luca Rossi
aeb4f640c5 feat: AI agent panel UI — 3-layer panel with action cards and WebSocket activity hook (#149)
* feat: AI agent panel UI — 3-layer panel with action cards and WebSocket activity hook

* style: rustfmt mcp.rs

---------

Co-authored-by: Test <test@test.com>
2026-02-28 21:30:47 +01:00