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/customer-site/server.ts

@@ -1,11 +1,11 @@
-// A pretend customer website with the ChatterMate widget embedded the way the
+// A pretend customer website with the ReplyPier widget embedded the way the
 // dashboard's install snippet does it. Everything about the embed comes from the
 // query string:
 //
 //   http://127.0.0.1:13000/?widget=<id>
-//     &config=<json>   → window.chattermateConfig (launcher, position, trigger, …)
-//     &token=<jwt>     → window.chattermateToken (token-authenticated widgets)
-//     &trigger=1       → adds a page button with data-chattermate-open
+//     &config=<json>   → window.replypierConfig (launcher, position, trigger, …)
+//     &token=<jwt>     → window.replypierToken (token-authenticated widgets)
+//     &trigger=1       → adds a page button with data-replypier-open
 //     &snippet=iframe  → the dashboard's iframe snippet instead of the script
 //
 // It has to be a real server on 127.0.0.1: Chrome's Local Network Access check
@@ -23,7 +23,7 @@ function arg(name: string, fallback: string): string {
 
 const port = Number(arg('port', '13000'))
 const apiUrl = arg('api', 'http://127.0.0.1:18000/api/v1')
-const loaderUrl = arg('loader', 'http://127.0.0.1:15173/webclient/chattermate.min.js')
+const loaderUrl = arg('loader', 'http://127.0.0.1:15173/webclient/replypier.min.js')
 
 interface Embed {
   widgetId: string
@@ -36,7 +36,7 @@ interface Embed {
 /** The dashboard's iframe snippet (AgentWidgetTab), classed so the page object finds it. */
 function iframeSnippet(widgetId: string): string {
   const src = `${apiUrl}/widgets/${encodeURIComponent(widgetId)}/data`
-  return `<iframe class="chattermate-iframe" src="${src}" width="100%" height="600" frameborder="0" title="AI Assistant" allow="clipboard-write"></iframe>`
+  return `<iframe class="replypier-iframe" src="${src}" width="100%" height="600" frameborder="0" title="AI Assistant" allow="clipboard-write"></iframe>`
 }
 
 function page(embed: Embed): string {
@@ -51,18 +51,18 @@ function page(embed: Embed): string {
 </html>`
   }
   const globals = [
-    `window.chattermateId = ${JSON.stringify(embed.widgetId)};`,
-    `window.chattermateBaseUrl = ${JSON.stringify(apiUrl)};`,
+    `window.replypierId = ${JSON.stringify(embed.widgetId)};`,
+    `window.replypierBaseUrl = ${JSON.stringify(apiUrl)};`,
     // config arrives as JSON text; parse it here so a malformed value fails the request, not the page.
-    embed.config ? `window.chattermateConfig = ${JSON.stringify(JSON.parse(embed.config))};` : '',
-    embed.token ? `window.chattermateToken = ${JSON.stringify(embed.token)};` : '',
+    embed.config ? `window.replypierConfig = ${JSON.stringify(JSON.parse(embed.config))};` : '',
+    embed.token ? `window.replypierToken = ${JSON.stringify(embed.token)};` : '',
   ].filter(Boolean).join('\n      ')
   return `<!doctype html>
 <html lang="en">
   <head><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1"><title>Acme Store</title></head>
   <body>
     <h1>Acme Store</h1>
-    ${embed.trigger ? '<button type="button" data-chattermate-open>Chat with us</button>' : ''}
+    ${embed.trigger ? '<button type="button" data-replypier-open>Chat with us</button>' : ''}
     <script>
       ${globals}
     </script>

e2e/services/fake-externals/server.ts

@@ -23,7 +23,7 @@
 //   Meta tokens `…:app=<id>.<secret>:…`          were issued by the customer's own Meta
 //                                              app: GET /app answers that id and checks
 //                                              appsecret_proof against that secret (any
-//                                              other token is ChatterMate's app)
+//                                              other token is ReplyPier's app)
 //   Meta POST /<number> {webhook_configuration}  verifies the override callback the way
 //                                              Meta does — a GET with hub.verify_token
 //                                              that must echo hub.challenge — before
@@ -188,13 +188,13 @@ function graphError(message: string, code = 100): Answer {
   return { status: 400, body: { error: { message, type: 'OAuthException', code, fbtrace_id: 'e2e' } } }
 }
 
-/** ChatterMate's own Meta app; its secret mirrors META_APP_SECRET in .env.e2e. */
-const CHATTERMATE_APP = { id: 'e2e-chattermate-app', secret: 'e2e-meta-app-secret' }
+/** ReplyPier's own Meta app; its secret mirrors META_APP_SECRET in .env.e2e. */
+const REPLYPIER_APP = { id: 'e2e-replypier-app', secret: 'e2e-meta-app-secret' }
 
 /** The Meta app that issued a token. */
 function appOf(token: string): { id: string; secret: string } {
   const match = /:app=([^.:]+)\.([^:]+)/.exec(token)
-  return match ? { id: match[1], secret: match[2] } : CHATTERMATE_APP
+  return match ? { id: match[1], secret: match[2] } : REPLYPIER_APP
 }
 
 /** Meta checks an override callback before taking it: the GET must echo the challenge. */

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 ?? ''))
   }