- next.config.ts: add react-markdown + entire unified/remark/rehype
ecosystem to transpilePackages — fixes TypeError 'z'/'j'/'aa' prod
crashes caused by ESM-only packages not being bundled for webpack
- Dockerfile: bake HEALTHCHECK --start-period=60s on 127.0.0.1 so
rolling deploys pass on first health probe (was failing on ::1 IPv6)
- Hosting tab: full rewrite — live URL chip, copy button, redeploy
button, inline log viewer, domain list, empty state with prompt
nudge. Single-card layout replaces master-detail for 1-3 endpoints.
- Settings page: new /project/:id/settings route with danger zone +
typed "delete" confirmation for project deletion
- Status pill: "View logs" link appears on build failures
- URL chips: collapse extras into "+N more" pill when >2 visible
- Chat errors: structured "Tool error:" prefix; network errors
distinguished from server errors
Made-with: Cursor
The chat panel now reads projectId from the URL and tags every thread
to it, so:
- Threads listed in the side panel are filtered to the project the user
is currently viewing (workspace-level chats still work from /projects).
- New conversations started from a project page are persisted with that
project_id, surviving page reloads.
- The system prompt prepends an ACTIVE PROJECT block so tool calls
(apps_create, devcontainer_ensure, etc.) use the right projectId
without the user having to name it.
- A small chip in the chat header shows which project the AI is
currently talking about.
Schema migrates idempotently on first request (project_id column +
composite index on fs_chat_threads).
Made-with: Cursor
Today the chat shows ✓-icon tool trays with no narration between
calls — the user has no idea WHY the AI just called fs_edit or
ship. Meanwhile Gemini is producing 500-1000 chars of first-person
reasoning per round ("Updating the Express Server: A Quick
Production Deployment / Right, so we have a basic Express server
here, nothing fancy. I need to get a new version live...") and
billing us for those tokens — we just weren't asking for them.
Three layers:
1. lib/ai/gemini-chat.ts
- generationConfig.thinkingConfig.includeThoughts = true (default
true, opt-out via includeThoughts: false). We're already paying
for thinking tokens regardless of this flag — it just controls
whether the model returns the human-readable summary or only the
compressed signature.
- callGeminiChat now returns { text, thoughts, toolCalls,
finishReason } and the parser splits parts by `part.thought`.
CRITICAL bug avoided: previously `if (part.text) text += ...`
would have lumped thoughts into the chat bubble verbatim.
- streamGeminiChat yields `{ type: 'thinking' }` for thought parts.
2. app/api/chat/route.ts
- New SSE event: `data: {"type":"thinking","text":"..."}`
- Emitted on every round alongside text + tool_start.
- Recovery-summary branch also emits thoughts so even when the
model produces no user-facing prose, the user sees the model's
reasoning instead of dead silence.
3. components/vibn-chat/chat-panel.tsx
- Message gains optional `thoughts` field (in-memory only — we do
NOT persist thoughts to fs_chat_messages; they're ephemeral and
cheap to drop).
- New ThinkingBubble component: dashed-border italic pill above
the assistant bubble, collapsed by default to show one-line
preview, click to expand for full chain. Strips Gemini's
"**Section Heading**" prefixes from the preview.
- SSE handler accumulates thinking chunks onto the in-flight
assistant message.
UX impact: instead of staring at fs.read ✓ fs.edit ✓ ship ✓ icons,
the user sees "Examining the target server file..." → "Shipping the
twenty-crm project..." in real time. Costs zero additional tokens
(we already paid for the thoughts).
Cleanup: removed scripts/probe-gemini-raw.ts and
scripts/probe-recovery-summary.ts — diagnostic scripts that
identified this opportunity, no longer needed in-tree.
Made-with: Cursor
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
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
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
- 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
- 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
