Files
pmc-funder-tool/README.md
T
Devin AI d1c5be112e migrate agent-proxy to Netlify Edge Function so long sessions stream end-to-end
The reconnect + events.list backfill in c283d88 is correct but never ran:
the previous v2 Node Function was killed at ~27 s (well before the 20 min
reconnect budget could matter), so streams always died after the first MCP
tool batch.

Move the proxy to a Netlify Edge Function (Deno runtime) which has no
streaming-duration cap as long as we keep writing to the response body.
Same reconnect / backfill / dedupe-by-event-id pattern; same NDJSON wire
protocol to the browser. Implemented with plain fetch() against the
Anthropic REST API (npm packages on Edge are beta) so we have no SDK
runtime dependency.

Frontend now POSTs to /api/agent-proxy. The Anthropic SDK is removed
from the package; @netlify/edge-functions is added for ambient types.

Co-Authored-By: alex <alex@semipublic.co>
2026-05-13 12:40:31 +00:00

2.1 KiB
Raw Blame History

PMC Funder Discovery Tool

A React + Vite frontend (Tailwind, Noto Serif) that collects public media station details and streams an Anthropic Managed Agent response back to the browser through a Netlify Edge Function proxy.

Setup

npm install

Add your Anthropic credentials (in .env for local dev, in the Netlify UI for production):

ANTHROPIC_API_KEY=sk-ant-...
# Optional - if you've provisioned a Managed Agent in the Anthropic console:
ANTHROPIC_AGENT_ID=agent_...
# Optional - override the model:
ANTHROPIC_MODEL=claude-sonnet-4-5

Run locally

npm run dev   # netlify dev (proxies Vite + functions on :8888)

Open http://localhost:8888.

How streaming works

  1. The browser POSTs the form to /api/agent-proxy.
  2. A Netlify Edge Function (Deno runtime) creates an Anthropic Managed Agent session, opens the upstream SSE event stream, and sends the user message. It then tails the stream and re-opens it (with an events.list backfill, deduped by event id) whenever it drops mid session, until the session reports a terminal session.status_* event or a 20-minute wall-clock budget is hit.
  3. Downstream to the browser the function emits newline-delimited JSON (application/x-ndjson) — text, status, heartbeat, done, error — one object per line.
  4. The React app reads response.body.getReader(), splits on \n, and parses each line. text lines append to the brief; status lines drive a separate “what the agent is doing now” banner.
  5. A Thinking flag stays true until the first chunk arrives, then flips to a streaming state with a pulsing cursor.

Edge Functions are required here — the previous v2 Node Function ran on AWS Lambda and got killed at ~27s, well before any reconnect could fire. Edge Functions run on Deno Deploy with no streaming-duration cap as long as the function keeps writing to the response body.

Files