chore(brand): rename the product to ReplyPier

The upstream project name is gone from code, assets, docs and build
output: brand strings, domains (replypier.site and its app/api/docs/help
subdomains), env prefixes, image and network names, the widget's public
JS API (window.ReplyPier, replypierId/BaseUrl/Config/Token), CSS tokens
(--rp-*), file and directory names, and the WordPress plugin package.

- widget loader is now webclient/replypier.min.js; both bundles rebuilt
  from source (backend/assets/widget.{js,css}, frontend/public/webclient)
- NOTICE, llms.txt, CONTRIBUTING, HELP_CENTER_INFRA and config.dev.js
  rewritten rather than string-swapped; the demo config no longer ships
  the previous vendor's Firebase/Razorpay/Google keys
- new migration replypier_ai_model_001 adds REPLYPIER to the managed
  AIModelType and rewrites pre-rename rows
- local compose project, database, role and volume renamed; LOCAL_DEPLOY
  documents carrying the old local data over

e2e/services/fake-llm/server.ts

@@ -5,7 +5,7 @@
 // replies keyed by a `[[e2e:<id>]]` marker in its agent's instructions or by the
 // agent's unique name — so parallel tests in one org never see each other's script.
 //
-// It speaks only what ChatterMate uses: non-streaming /v1/chat/completions, with or
+// It speaks only what ReplyPier uses: non-streaming /v1/chat/completions, with or
 // without a strict json_schema response_format (ChatAgent's ChatResponse), and tool
 // calls. Anything else fails loudly instead of returning something plausible.
 //
@@ -245,7 +245,7 @@ async function route(req: IncomingMessage, res: ServerResponse) {
       throw new HttpError(401, 'Incorrect API key provided.')
     }
     const body = (await readJson(req)) as ChatRequest
-    if (body.stream) throw new HttpError(400, 'the e2e fake LLM does not stream — ChatterMate never asks it to; if it does now, extend services/fake-llm')
+    if (body.stream) throw new HttpError(400, 'the e2e fake LLM does not stream — ReplyPier never asks it to; if it does now, extend services/fake-llm')
     if (!Array.isArray(body.messages)) throw new HttpError(400, 'messages[] is required')
     return send(res, 200, await answer(body, req.headers.authorization ?? ''))
   }