Commit Graph

6 Commits

Author SHA1 Message Date
4f84a19e75 feat(chat): Stop button to cancel in-flight AI turns
Standard chat-app pattern: while the AI is streaming or running
tools, the Send button morphs into a Stop control (filled square
inside a faded spinner). Click it (or press Esc) to abort the turn.

Why: with MAX_TOOL_ROUNDS=18, a confused tool-loop can chew through
60-90s of compute and tokens. The user had no way to interrupt — they
just watched ✓ icons accumulate. Stop fixes that.

How:

Client (chat-panel.tsx):
- abortRef holds the in-flight AbortController; lives in a ref so the
  Stop button can reach it without re-rendering on every chunk.
- sendMessage creates a fresh controller and passes signal to fetch.
- cancelMessage calls .abort(); also bound to Escape while sending.
- Button morph: while `sending`, render lucide Square overlaid on a
  faded Loader2 spin, switch onClick to cancelMessage, swap aria/title
  to "Stop generating (Esc)".
- Catch DOMException AbortError separately from network errors and
  append "(stopped by user)" to the partial assistant message.
- Textarea no longer disabled during streaming so users can queue
  the next prompt; Enter still won't submit until the turn ends.

Server (app/api/chat/route.ts):
- request.signal is captured before the ReadableStream and an `aborted`
  flag is flipped on the addEventListener('abort', ...) callback.
- Loop checkpoints `aborted` (a) at the top of every round, (b) before
  the inner tool-call loop, (c) before each individual executeMcpTool
  call. Picks the next safe boundary instead of yanking mid-call.
- On abort: emit a "(stopped by user)" text chunk + an "aborted" event,
  skip the round-cap recovery summary (don't pay for tokens the user
  just canceled), persist the partial assistant message normally.
- Fetch errors that come from the abort propagating into Gemini's HTTP
  client are recognized and downgraded from "error" to "aborted".
- safeClose() guards against double controller.close() when the abort
  races with normal completion.

Made-with: Cursor
2026-04-28 14:56:35 -07:00
afd76b394f fix(chat): preserve thread history across page reloads
Two bugs, one symptom (every reload silently spawned a blank thread,
the previous conversation was orphaned in the sidebar):

1. Race in the auto-thread effect.
   On mount: threads = [], activeThread = null, /api/chat/threads
   fetch in flight. The auto-create effect re-ran the moment the
   workspace + auth resolved, saw threads.length === 0, and called
   newThread() before the fetch ever returned. When the historical
   threads finally landed, activeThread was already pinned to the new
   empty one.

   Gate on a `threadsLoaded` flag that flips true after the first
   loadThreads() resolves. Auto-create can no longer fire before
   history is known.

2. activeThread wasn't persisted.
   Even with the race fixed, refreshing the page would reset the
   sidebar to the top thread (most recently updated). After a deploy
   that's usually the brand-new empty thread we just spawned, not the
   conversation the user was actually in.

   Persist activeThread to localStorage keyed by workspace. Reload
   restores the same thread; switching workspaces resets cleanly.

Made-with: Cursor
2026-04-28 14:26:34 -07:00
210fba4e08 Fix chat panel token fetch: use /api/workspaces not URL slug
URL param 'mark-account' != workspace slug 'mark'. Fetch default token
from /api/workspaces?include_default_token=true which resolves the real
slug server-side.

Made-with: Cursor
2026-04-27 16:26:55 -07:00
56e7c2fb5c Fix auto-token fetch: use keys?include_default_token=true instead of /keys/default
Avoids the Next.js dynamic route conflict with [keyId].
Chat panel now correctly bootstraps MCP token on mount with no user action.

Made-with: Cursor
2026-04-27 16:04:38 -07:00
1e138d69d6 Auto-mint default MCP token on workspace creation
- ensureWorkspaceForUser() now calls mintWorkspaceApiKey('default') on first workspace creation
- Legacy workspaces without a default key get one minted on first request
- GET /api/workspaces/[slug]/keys/default reveals (or mints) the default token for session users
- Chat panel fetches the token automatically on mount, caches it in localStorage
- No manual setup needed — tool calling works immediately on first sign-in

Made-with: Cursor
2026-04-27 15:43:27 -07:00
5e07bbf39d Add Vibn AI chat panel powered by Gemini 3.1 Pro
- Right-docked chat panel on all workspace pages ([workspace]/layout.tsx)
- Streaming SSE responses with Gemini 3.1 Pro preview via generativelanguage API
- Full tool-calling loop (up to 6 rounds): deploys apps, lists projects, registers
  domains, fetches logs — all via existing MCP dispatcher
- Persistent conversation history: fs_chat_threads + fs_chat_messages tables (Postgres)
- Thread management: create, list, rename (auto-title from first message), delete
- Panel collapses to a tab; open state persisted to localStorage
- Read-only mode hint when no MCP token is present
- Graceful content margin shift when panel is open

Made-with: Cursor
2026-04-27 15:40:32 -07:00