Import full episode notes from DOCX and add importer script

.env

@@ -0,0 +1 @@
+ADMIN_PASSWORD=TestAdmin123!

.env.example

@@ -0,0 +1,23 @@
+# Copy this file to .env and fill in your real values.
+# Never commit .env to version control.
+
+# Resend API key for the contact form
+# 1. Sign up free at https://resend.com
+# 2. Go to API Keys and create a new key
+# 3. Paste it below
+RESEND_API_KEY=re_your_api_key_here
+
+# Optional: use a separate key for Contacts/Segments if your main key is send-only
+RESEND_CONTACTS_API_KEY=
+
+# Email address that receives contact form submissions
+RESEND_TO=hello@versebyversewithnate.us
+
+# Optional: automatically add contact form submitters to a Resend Segment
+# Create a Segment in Resend and paste its ID here if you want new contacts grouped.
+RESEND_SEGMENT_ID=
+
+# "From" address shown on received emails.
+# During testing you can leave this as-is (uses Resend's shared domain).
+# For production: verify your own domain at resend.com/domains and change this.
+RESEND_FROM=Verse by Verse with Nate <hello@versebyversewithnate.us>

.gitignore

@@ -17,6 +17,7 @@ dist-ssr
 # the image default and is preserved here for the Docker build context only.
 # Uncomment the line below if you do NOT want to track live data in git.
 # data/admin-content.json
+data/backups/
 
 # Editor directories and files
 .vscode/*

README.md

@@ -50,13 +50,65 @@ docker compose pull
 docker compose up -d
 ```
 
+Admin auth:
+
+- Set `ADMIN_PASSWORD` on the server/container to protect `/admin` and admin stats/maintenance endpoints.
+- Without `ADMIN_PASSWORD`, admin login is disabled until configured.
+
 The app will be available at `http://localhost:4173`.
 
+## Optional local LLM (Ollama) for grounded rewrites
+
+You can keep deterministic retrieval as the source-of-truth and optionally rewrite responses with a local model.
+
+1. Install and run Ollama on your host.
+2. Pull a small model suited to older hardware, for example:
+
+```bash
+ollama pull qwen2.5:3b-instruct
+```
+
+3. Start the API with these environment variables:
+
+```bash
+CHATBOT_LLM_ENABLED=true
+CHATBOT_LLM_BASE_URL=http://127.0.0.1:11434
+CHATBOT_LLM_MODEL=qwen2.5:3b-instruct
+CHATBOT_LLM_TIMEOUT_MS=25000
+CHATBOT_LLM_NUM_CTX=2048
+```
+
+4. Call the rewrite endpoint from your existing chat flow:
+
+`POST /api/chatbot-grounded-rewrite`
+
+Request payload shape:
+
+```json
+{
+	"question": "Who was Titus?",
+	"draftAnswer": "Deterministic answer produced by current retrieval/synthesis.",
+	"sources": ["Episode 2 - Introduction to Titus"],
+	"contextChunks": [
+		{
+			"title": "Episode 2 - Introduction to Titus",
+			"sourceLabel": "Episode 2",
+			"content": "Titus was a Gentile..."
+		}
+	]
+}
+```
+
+If the endpoint fails or is disabled, keep your deterministic answer and existing fallback behavior.
+
 Persistent admin saves:
 
 - Admin updates are written to `data/admin-content.json`.
+- Built-in page hit stats are written to `data/hit-stats.json`.
+- Detailed visitor analytics are written to `data/visitor-stats.json`.
+- Backup snapshots are written to `data/backups/`.
 - `docker-compose.yml` mounts `./data` into the container at `/app/data`.
-- This keeps your edits after container restarts/rebuilds.
+- This keeps all admin-managed data after container restarts/rebuilds/updates.
 
 ## Where to edit content
 
@@ -80,6 +132,12 @@ Persistent admin saves:
 - Enter a URL and click **Scan URL metadata** to auto-fill title, summary, domain, category, and icon when available.
 - Click **Save project** to apply updates instantly.
 - Saved edits are written to `data/admin-content.json` through the API server.
+- Built-in stats in `/admin` include page hits plus visitor details (IP, country/state/county/city, returning visitors, and recent visitor log).
+- Site Stats in `/admin` includes a Bible Questions inbox sourced from contact form submissions marked as Bible Question.
+- Analytics cookies are consent-based. Visitors can accept or decline tracking from the site banner.
+- Admin now includes maintenance actions: **Export JSON**, **Backup Now**, **Prune Old Data**, and **Clear Analytics**.
+- Admin also supports restoring from a backup snapshot from `/admin`.
+- The server creates startup + daily backup snapshots and retains recent backups automatically.
 - Use the **Theme** dropdown to switch between Sandstone, Ocean, Midnight, Forest, and Sunset.
 - Use **Remove project** to delete the selected project from your local Admin data.
 - Use **Reset project** or **Reset all** to restore defaults from `src/data/projects.ts`.

data/admin-content.json

@@ -5,7 +5,7 @@
     "aboutShowHeading": "Depth. Clarity. Application.",
     "aboutShowP1": "Verse by Verse with Nate walks through Scripture passage by passage — unpacking the original context, drawing out the meaning, and connecting each verse to how we live today.",
     "aboutShowP2": "Whether you're in the car, at the gym, or just looking for something to anchor your day, each episode is designed to feed your faith with solid, practical teaching.",
-    "aboutNate": "Nate Emmert is a husband, dad, and lifelong student of the Bible from Nashville, TN. He created Verse by Verse to share the joy of deep Scripture study in a format anyone can follow along with — no seminary required.",
+    "aboutNate": "Nate Emmert is a husband, dad, and lifelong student of the Bible from Lynchburg, Va. He created Verse by Verse to share the joy of deep Scripture study in a format anyone can follow along with — no seminary required.",
     "seriesLabel": "Now Playing",
     "seriesTitle": "Study of Titus: Sound Doctrine",
     "seriesDescription": "A deep-dive into Paul's letter to Titus — unpacking what it means to build a church and a life on sound doctrine.",
@@ -17,86 +17,5 @@
     "customLinks": [],
     "customBlocks": []
   },
-  "updatedAt": "2026-04-09T00:00:00.000Z",
-  "_legacy_projects": [
-    {
-      "slug": "verse-by-verse",
-      "title": "Verse by Verse with Nate",
-      "domain": "spotify.com",
-      "url": "https://creators.spotify.com/pod/profile/nmemmert/",
-      "category": "Podcast",
-      "access": "Public",
-      "ownership": "hosted",
-      "status": "Live",
-      "summary": "A verse-by-verse podcast from Nate Emmert focused on Scripture, story, and practical faith application.",
-      "details": "Weekly episodes explore Scripture one verse at a time, mixing theological insight, devotional reflection, and real-life application.",
-      "features": [
-        "Verse-by-verse teaching",
-        "Weekly podcast episodes",
-        "Practical reflection"
-      ],
-      "scanSource": "manual",
-      "featured": {
-        "headline": "Podcast teaching shaped around verse-by-verse discovery.",
-        "problem": "Bible study and podcast listening often feel disconnected from each other and from everyday life.",
-        "solution": "Verse by Verse with Nate brings Scripture study and podcast conversation together in a format that is easy to follow and apply.",
-        "stack": [
-          "Podcast hosting",
-          "Spotify",
-          "Verse-by-verse teaching"
-        ],
-        "highlights": [
-          "Episode guides",
-          "Scripture focus",
-          "Practical application"
-        ],
-        "nextSteps": [
-          "Add episode notes",
-          "Add guest interviews",
-          "Link transcripts and study resources"
-        ],
-        "updateNote": "Edit this content in data/admin-content.json for the Verse by Verse podcast project."
-      }
-    }
-  ],
-  "siteContent": {
-    "theme": "sand",
-    "homeEyebrow": "Verse by Verse with Nate",
-    "homeTitle": "Podcast episodes, Scripture study, and weekly reflections",
-    "homeIntro": "A podcast experience centered on verse-by-verse conversation, prayerful application, and practical faith rhythms. Explore episodes, show notes, and the latest reflections from Nate.",
-    "projectEyebrow": "Featured Episode",
-    "quickTipsTitle": "Why listeners stay engaged",
-    "quickTipsBody": "Each episode focuses on clear Scripture teaching, practical application, and encouragement you can carry into the week.",
-    "downloadsTitle": "Listen Everywhere",
-    "downloadsIntro": "Use these links to follow the show, share episodes, and stay connected with Verse by Verse with Nate.",
-    "downloads": [
-      {
-        "title": "Spotify Creator Profile",
-        "url": "https://creators.spotify.com/pod/profile/nmemmert/",
-        "description": "Open the official show profile and listen to the latest episodes."
-      }
-    ],
-    "showSidebar": false,
-    "showWeatherWidget": false,
-    "showMusicBar": false,
-    "homeSections": [
-      {
-        "id": "summary",
-        "placement": "main"
-      },
-      {
-        "id": "projects",
-        "placement": "main"
-      },
-      {
-        "id": "quickTips",
-        "placement": "main"
-      },
-      {
-        "id": "downloads",
-        "placement": "main"
-      }
-    ]
-  },
   "updatedAt": "2026-04-09T00:00:00.000Z"
 }

data/chatbot-eval.json

@@ -0,0 +1,58 @@
+[
+  { "query": "who was titus", "expectedEntryId": "cb_who_is_titus_001", "expectedTopK": 3 },
+  { "query": "who is paul", "expectedEntryId": "881279c7-3ca4-436d-a584-19cc0a5a9bf3", "expectedTopK": 3 },
+  { "query": "tell me about paul in titus", "expectedEntryId": "881279c7-3ca4-436d-a584-19cc0a5a9bf3", "expectedTopK": 4 },
+  { "query": "who was saul before his conversion", "expectedEntryId": "167fa083-5438-44a5-ac72-6dd379e937f5", "expectedTopK": 4 },
+  { "query": "who was titus and why was he in crete", "expectedEntryId": "cb_who_is_titus_001", "expectedTopK": 12 },
+  { "query": "what bible translation does nate use", "expectedEntryId": "cb_001", "expectedTopK": 1 },
+  { "query": "does the podcast use bsb", "expectedEntryId": "cb_001", "expectedTopK": 2 },
+  { "query": "which bible version do you teach from", "expectedEntryId": "cb_001", "expectedTopK": 2 },
+  { "query": "how can i stay consistent with daily bible reading", "expectedEntryId": "cb_003", "expectedTopK": 2 },
+  { "query": "help me build a daily reading habit", "expectedEntryId": "cb_003", "expectedTopK": 3 },
+  { "query": "i keep missing devotion time what should i do", "expectedEntryId": "cb_003", "expectedTopK": 4 },
+  { "query": "how should christians engage with politics", "expectedEntryId": "cb_christians_politics_001", "expectedTopK": 2 },
+  { "query": "what does titus say about public life", "expectedEntryId": "cb_christians_politics_001", "expectedTopK": 3 },
+  { "query": "how can i be peaceable online", "expectedEntryId": "cb_christians_politics_001", "expectedTopK": 4 },
+  { "query": "give me a summary of titus 3:4-7", "expectedEntryId": "cb_titus347_summary_001", "expectedTopK": 1 },
+  { "query": "summarize titus 3 4 through 7", "expectedEntryId": "cb_titus347_summary_001", "expectedTopK": 12 },
+  { "query": "what does titus 3:4-7 teach about salvation", "expectedEntryId": "b68c5659-cc7e-42d2-ab24-a623b7404058", "expectedTopK": 2 },
+  { "query": "what is the blessed hope", "expectedEntryId": "cb_blessed_hope_001", "expectedTopK": 2 },
+  { "query": "define blessed hope from titus 2:13", "expectedEntryId": "cb_blessed_hope_001", "expectedTopK": 2 },
+  { "query": "what does makaria elpis mean", "expectedEntryId": "cb_blessed_hope_001", "expectedTopK": 3 },
+  { "query": "what does grace train us to do", "expectedEntryId": "cb_grace_trains_001", "expectedTopK": 2 },
+  { "query": "how does grace teach us to say no to ungodliness", "expectedEntryId": "cb_grace_trains_001", "expectedTopK": 3 },
+  { "query": "what is paideuo in titus 2", "expectedEntryId": "6be7a644-9276-4797-a7bb-1422b170846c", "expectedTopK": 12 },
+  { "query": "how do i submit a question to nate", "expectedEntryId": "cb_007", "expectedTopK": 1 },
+  { "query": "where can i send bible questions", "expectedEntryId": "cb_007", "expectedTopK": 12 },
+  { "query": "how do i contact nate", "expectedEntryId": "cb_007", "expectedTopK": 2 },
+  { "query": "what does titus 1 teach about church leadership", "expectedEntryId": "cb_leadership_titus1_001", "expectedTopK": 2 },
+  { "query": "elder qualifications in titus 1", "expectedEntryId": "cb_leadership_titus1_001", "expectedTopK": 12 },
+  { "query": "what should an overseer be like", "expectedEntryId": "cb_leadership_titus1_001", "expectedTopK": 3 },
+  { "query": "what did paul say about elders", "expectedEntryId": "e0ad268f-2826-41a5-b078-90f90aeda21b", "expectedTopK": 4 },
+  { "query": "episode on faithful leaders", "expectedEntryId": "e0ad268f-2826-41a5-b078-90f90aeda21b", "expectedTopK": 3 },
+  { "query": "titus 1:5-9 overview", "expectedEntryId": "e0ad268f-2826-41a5-b078-90f90aeda21b", "expectedTopK": 12 },
+  { "query": "what are false teachers doing in titus", "expectedEntryId": "56626549-7e1e-4564-8c79-2d21b49eb911", "expectedTopK": 3 },
+  { "query": "what is the circumcision group in titus", "expectedEntryId": "56626549-7e1e-4564-8c79-2d21b49eb911", "expectedTopK": 3 },
+  { "query": "empty talk and deception in titus 1", "expectedEntryId": "56626549-7e1e-4564-8c79-2d21b49eb911", "expectedTopK": 4 },
+  { "query": "what does it mean to deny god by your works", "expectedEntryId": "cb_deny_works_001", "expectedTopK": 2 },
+  { "query": "they profess to know god but deny him by actions", "expectedEntryId": "cb_deny_works_001", "expectedTopK": 3 },
+  { "query": "detestable disobedient unfit meaning", "expectedEntryId": "cb_deny_works_001", "expectedTopK": 4 },
+  { "query": "episode about grace training us", "expectedEntryId": "6be7a644-9276-4797-a7bb-1422b170846c", "expectedTopK": 2 },
+  { "query": "titus 2:11-12 episode", "expectedEntryId": "6be7a644-9276-4797-a7bb-1422b170846c", "expectedTopK": 12 },
+  { "query": "how should i share faith with skeptical family", "expectedEntryId": "cb_faith_family_001", "expectedTopK": 2 },
+  { "query": "evangelize skeptical relatives", "expectedEntryId": "cb_faith_family_001", "expectedTopK": 4 },
+  { "query": "where can i listen to the podcast", "expectedEntryId": "cb_006", "expectedTopK": 2 },
+  { "query": "how do i find verse by verse with nate on apple podcasts", "expectedEntryId": "cb_006", "expectedTopK": 3 },
+  { "query": "what is verse by verse with nate podcast", "expectedEntryId": "cb_005", "expectedTopK": 2 },
+  { "query": "tell me about the podcast", "expectedEntryId": "cb_005", "expectedTopK": 2 },
+  { "query": "how do i approach a difficult passage", "expectedEntryId": "cb_002", "expectedTopK": 2 },
+  { "query": "what should i do with confusing bible verses", "expectedEntryId": "cb_002", "expectedTopK": 3 },
+  { "query": "prayer and quiet time advice", "expectedEntryId": "cb_008", "expectedTopK": 2 },
+  { "query": "how to start a quiet time", "expectedEntryId": "cb_008", "expectedTopK": 3 },
+  { "query": "what is episode 9 about", "expectedEntryId": "4e6ec41f-b083-45b9-9581-0dc91f092f66", "expectedTopK": 12 },
+  { "query": "living between two appearings", "expectedEntryId": "4e6ec41f-b083-45b9-9581-0dc91f092f66", "expectedTopK": 2 },
+  { "query": "what is episode 12", "expectedEntryId": "b68c5659-cc7e-42d2-ab24-a623b7404058", "expectedTopK": 2 },
+  { "query": "the gospel in one paragraph", "expectedEntryId": "b68c5659-cc7e-42d2-ab24-a623b7404058", "expectedTopK": 2 },
+  { "query": "what is episode 14 about", "expectedEntryId": "14ced988-1382-4c8d-a29e-b0f531580af1", "expectedTopK": 3 },
+  { "query": "grace where it starts and where it ends", "expectedEntryId": "14ced988-1382-4c8d-a29e-b0f531580af1", "expectedTopK": 3 }
+]

data/questions.json

@@ -0,0 +1 @@
+[]

docker-compose.yml

@@ -7,6 +7,8 @@ services:
       - "4173:4173"
     environment:
       - PORT=4173
+      - ADMIN_PASSWORD=`generate a random password and set it here`
+      - RESEND_API_KEY=`set your Resend API key here`
     volumes:
-      - ./data:/app/data
+      - /media/ZimaOS-HD/AppData/siteforge/data:/app/data
     restart: unless-stopped

entrypoint.sh

@@ -1,17 +1,26 @@
 #!/bin/sh
 set -e
 
-DATA_FILE=/app/data/admin-content.json
-SEED_FILE=/app/data-seed/admin-content.json
+DATA_DIR=/app/data
+SEED_DIR=/app/data-seed
 
 # Ensure the data directory exists (in case the volume was not mounted)
-mkdir -p /app/data
+mkdir -p "$DATA_DIR"
 
-# Only seed from image defaults when no live data file exists yet.
+# Seed each default JSON file only when missing.
 # This runs on first boot or a fresh volume, but never overwrites existing data.
-if [ ! -f "$DATA_FILE" ] && [ -f "$SEED_FILE" ]; then
-  echo "[siteforge] No admin-content.json found. Seeding from image defaults..."
-  cp "$SEED_FILE" "$DATA_FILE"
+if [ -d "$SEED_DIR" ]; then
+  for seed_file in "$SEED_DIR"/*.json; do
+    [ -f "$seed_file" ] || continue
+
+    base_name=$(basename "$seed_file")
+    target_file="$DATA_DIR/$base_name"
+
+    if [ ! -f "$target_file" ]; then
+      echo "[siteforge] No $base_name found. Seeding from image defaults..."
+      cp "$seed_file" "$target_file"
+    fi
+  done
 fi
 
 exec node server.js

package-lock.json

@@ -13,7 +13,8 @@
         "react-dom": "^19.2.4",
         "react-markdown": "^10.1.0",
         "react-router-dom": "^7.13.1",
-        "remark-gfm": "^4.0.1"
+        "remark-gfm": "^4.0.1",
+        "resend": "^6.10.0"
       },
       "devDependencies": {
         "@eslint/js": "^9.39.4",
@@ -863,6 +864,12 @@
       "dev": true,
       "license": "MIT"
     },
+    "node_modules/@stablelib/base64": {
+      "version": "1.0.1",
+      "resolved": "https://registry.npmjs.org/@stablelib/base64/-/base64-1.0.1.tgz",
+      "integrity": "sha512-1bnPQqSxSuc3Ii6MhBysoWCg58j97aUjuCSZrGSmDxNqtytIi0k8utUenAwTZN4V5mXXYGsVUI9zeBqy+jBOSQ==",
+      "license": "MIT"
+    },
     "node_modules/@tybys/wasm-util": {
       "version": "0.10.1",
       "resolved": "https://registry.npmjs.org/@tybys/wasm-util/-/wasm-util-0.10.1.tgz",
@@ -2239,6 +2246,12 @@
       "dev": true,
       "license": "MIT"
     },
+    "node_modules/fast-sha256": {
+      "version": "1.3.0",
+      "resolved": "https://registry.npmjs.org/fast-sha256/-/fast-sha256-1.3.0.tgz",
+      "integrity": "sha512-n11RGP/lrWEFI/bWdygLxhI+pVeo1ZYIVwvvPkW7azl/rOy+F3HYRZ2K5zeE9mmkhQppyv9sQFx0JM9UabnpPQ==",
+      "license": "Unlicense"
+    },
     "node_modules/fdir": {
       "version": "6.5.0",
       "resolved": "https://registry.npmjs.org/fdir/-/fdir-6.5.0.tgz",
@@ -4309,6 +4322,12 @@
         "url": "https://github.com/sponsors/jonschlinkert"
       }
     },
+    "node_modules/postal-mime": {
+      "version": "2.7.4",
+      "resolved": "https://registry.npmjs.org/postal-mime/-/postal-mime-2.7.4.tgz",
+      "integrity": "sha512-0WdnFQYUrPGGTFu1uOqD2s7omwua8xaeYGdO6rb88oD5yJ/4pPHDA4sdWqfD8wQVfCny563n/HQS7zTFft+f/g==",
+      "license": "MIT-0"
+    },
     "node_modules/postcss": {
       "version": "8.5.8",
       "resolved": "https://registry.npmjs.org/postcss/-/postcss-8.5.8.tgz",
@@ -4582,6 +4601,27 @@
         "node": ">=0.10.0"
       }
     },
+    "node_modules/resend": {
+      "version": "6.10.0",
+      "resolved": "https://registry.npmjs.org/resend/-/resend-6.10.0.tgz",
+      "integrity": "sha512-i7CwZpYj4Oho1RxsTpLcCUkO08+HiL4NXrm6jLJ2WzJ89UGI8eROSieLONJA3hnUrf1OYnCyfq5F6POnHUMv1Q==",
+      "license": "MIT",
+      "dependencies": {
+        "postal-mime": "2.7.4",
+        "svix": "1.88.0"
+      },
+      "engines": {
+        "node": ">=20"
+      },
+      "peerDependencies": {
+        "@react-email/render": "*"
+      },
+      "peerDependenciesMeta": {
+        "@react-email/render": {
+          "optional": true
+        }
+      }
+    },
     "node_modules/resolve-from": {
       "version": "4.0.0",
       "resolved": "https://registry.npmjs.org/resolve-from/-/resolve-from-4.0.0.tgz",
@@ -4866,6 +4906,16 @@
         "url": "https://github.com/sponsors/wooorm"
       }
     },
+    "node_modules/standardwebhooks": {
+      "version": "1.0.0",
+      "resolved": "https://registry.npmjs.org/standardwebhooks/-/standardwebhooks-1.0.0.tgz",
+      "integrity": "sha512-BbHGOQK9olHPMvQNHWul6MYlrRTAOKn03rOe4A8O3CLWhNf4YHBqq2HJKKC+sfqpxiBY52pNeesD6jIiLDz8jg==",
+      "license": "MIT",
+      "dependencies": {
+        "@stablelib/base64": "^1.0.0",
+        "fast-sha256": "^1.3.0"
+      }
+    },
     "node_modules/statuses": {
       "version": "2.0.2",
       "resolved": "https://registry.npmjs.org/statuses/-/statuses-2.0.2.tgz",
@@ -4961,6 +5011,16 @@
         "node": ">=8"
       }
     },
+    "node_modules/svix": {
+      "version": "1.88.0",
+      "resolved": "https://registry.npmjs.org/svix/-/svix-1.88.0.tgz",
+      "integrity": "sha512-vm/JrrUd3bVyBE+3L33TIyVSs8gS5fYx7lrISvKlDJXTYX1ACH4REX8P1tHxsSKoZi/rvifM1t0XRc5Vc45THw==",
+      "license": "MIT",
+      "dependencies": {
+        "standardwebhooks": "1.0.0",
+        "uuid": "^10.0.0"
+      }
+    },
     "node_modules/tinyglobby": {
       "version": "0.2.15",
       "resolved": "https://registry.npmjs.org/tinyglobby/-/tinyglobby-0.2.15.tgz",
@@ -5246,6 +5306,19 @@
         "punycode": "^2.1.0"
       }
     },
+    "node_modules/uuid": {
+      "version": "10.0.0",
+      "resolved": "https://registry.npmjs.org/uuid/-/uuid-10.0.0.tgz",
+      "integrity": "sha512-8XkAphELsDnEGrDxUOHB3RGvXz6TeuYSGEZBOjtTtPm2lwhGBjLgOzLHB63IUWfBpNucQjND6d3AOudO+H3RWQ==",
+      "funding": [
+        "https://github.com/sponsors/broofa",
+        "https://github.com/sponsors/ctavan"
+      ],
+      "license": "MIT",
+      "bin": {
+        "uuid": "dist/bin/uuid"
+      }
+    },
     "node_modules/vary": {
       "version": "1.1.2",
       "resolved": "https://registry.npmjs.org/vary/-/vary-1.1.2.tgz",

package.json

@@ -5,12 +5,13 @@
   "type": "module",
   "scripts": {
     "dev": "vite",
-    "api": "node server.js",
+    "api": "node --env-file=.env server.js",
     "dev:full": "concurrently \"npm:api\" \"npm:dev\"",
     "build": "tsc -b && vite build",
-    "start": "node server.js",
+    "start": "node --env-file=.env server.js",
     "lint": "eslint .",
-    "preview": "vite preview"
+    "preview": "vite preview",
+    "chatbot:eval": "node scripts/evaluate-chatbot.mjs"
   },
   "dependencies": {
     "express": "^5.2.1",
@@ -18,7 +19,8 @@
     "react-dom": "^19.2.4",
     "react-markdown": "^10.1.0",
     "react-router-dom": "^7.13.1",
-    "remark-gfm": "^4.0.1"
+    "remark-gfm": "^4.0.1",
+    "resend": "^6.10.0"
   },
   "devDependencies": {
     "@eslint/js": "^9.39.4",

scripts/build-chatbot-from-episodes.mjs

@@ -0,0 +1,92 @@
+import { execSync } from 'child_process'
+import { readFileSync, writeFileSync } from 'fs'
+import { randomUUID } from 'crypto'
+
+const BASE = "/Users/nate.emmert/Documents/github/Siteforge/Verse by Verse with Nate Complete Series"
+const CHATBOT_FILE = "/Users/nate.emmert/Documents/github/Siteforge/data/chatbot-content.json"
+
+const FILES = [
+  { file: `${BASE}/Done/Verse_by_Verse_with_Nate_Episode02.docx`, ep: 2 },
+  { file: `${BASE}/Done/Verse_by_Verse_with_Nate_Episode03.docx`, ep: 3 },
+  { file: `${BASE}/Done/Verse_by_Verse_with_Nate_Episode04_Updated.docx`, ep: 4 },
+  { file: `${BASE}/Verse_by_Verse_with_Nate_Episode05.docx`, ep: 5 },
+  { file: `${BASE}/Verse_by_Verse_with_Nate_Episode06_expanded.docx`, ep: 6 },
+  { file: `${BASE}/Verse_by_Verse_with_Nate_Episode07.docx`, ep: 7 },
+  { file: `${BASE}/Verse_by_Verse_with_Nate_Episode08.docx`, ep: 8 },
+  { file: `${BASE}/Verse_by_Verse_with_Nate_Episode09.docx`, ep: 9 },
+  { file: `${BASE}/Verse_by_Verse_with_Nate_Episode10.docx`, ep: 10 },
+  { file: `${BASE}/Verse_by_Verse_with_Nate_Episode11.docx`, ep: 11 },
+  { file: `${BASE}/Verse_by_Verse_with_Nate_Episode12.docx`, ep: 12 },
+  { file: `${BASE}/Verse_by_Verse_with_Nate_Episode13.docx`, ep: 13 },
+  { file: `${BASE}/Verse_by_Verse_with_Nate_Episode14.docx`, ep: 14 },
+]
+
+function extractText(filePath) {
+  const xml = execSync(`unzip -p "${filePath}" word/document.xml 2>/dev/null`, { encoding: 'utf8' })
+  return xml
+    .replace(/<[^>]+>/g, ' ')
+    .replace(/&amp;/g, '&').replace(/&lt;/g, '<').replace(/&gt;/g, '>').replace(/&quot;/g, '"').replace(/&#39;/g, "'")
+    .replace(/\s+/g, ' ')
+    .trim()
+}
+
+function parseEpisode(raw, epNum) {
+  // Extract episode subtitle and passage reference from header
+  const headerMatch = raw.match(/EPISODE\s+\d+\s*[—\-\u2013\u2014]+\s*(.+?)\s+(Titus\s+[\d:]+(?:\s*[\-\u2013\u2014]+\s*[\d:]+)?)\s*·/i)
+  const subtitle = headerMatch ? headerMatch[1].trim().replace(/\s+/g, ' ') : ''
+  const passageRef = headerMatch ? headerMatch[2].trim() : 'Titus'
+  const episodeTitle = `Episode ${epNum} — ${subtitle || 'Verse by Verse with Nate'}`
+
+  // Find where the actual teaching content starts
+  let contentStart = raw.indexOf('SEGMENT 1')
+  if (contentStart === -1) contentStart = raw.indexOf('WHO WAS PAUL')
+  if (contentStart === -1) contentStart = raw.indexOf('COLD OPEN')
+  if (contentStart === -1) contentStart = 400
+
+  const rawContent = raw.slice(contentStart, contentStart + 4000)
+  const content = rawContent
+    .replace(/\[[^\]]{0,100}\]/g, '')                    // remove [stage directions]
+    .replace(/[✝🎙️📖💬🧠💡🔑✅◀▶]/gu, '')              // remove emoji
+    .replace(/SEGMENT\s+\d+\s*[—\-\u2013]+\s*/g, '\n\n') // turn SEGMENT headers into breaks
+    .replace(/\s{2,}/g, ' ')
+    .trim()
+
+  // Build keyword list
+  const verseRefs = [...new Set((raw.match(/Titus\s+\d+:\d+/g) || []))].slice(0, 5).map(k => k.toLowerCase())
+  const titleWords = subtitle.toLowerCase().replace(/[^a-z0-9\s]/g, ' ').split(/\s+/).filter(w => w.length > 3)
+  const keywords = [...new Set([
+    'titus', `episode ${epNum}`, passageRef.toLowerCase(),
+    ...verseRefs, ...titleWords
+  ])].slice(0, 20)
+
+  return {
+    id: randomUUID(),
+    type: 'episode',
+    title: `${episodeTitle} (${passageRef})`,
+    content: content.slice(0, 3900),
+    keywords,
+    createdAt: new Date().toISOString(),
+    updatedAt: new Date().toISOString(),
+  }
+}
+
+// Load existing entries (keep the 8 hand-written ones)
+const existing = JSON.parse(readFileSync(CHATBOT_FILE, 'utf8'))
+// Remove any previously generated episode entries to avoid duplication
+const baseEntries = existing.filter(e => e.type !== 'episode')
+
+const newEntries = []
+for (const { file, ep } of FILES) {
+  try {
+    const raw = extractText(file)
+    const entry = parseEpisode(raw, ep)
+    newEntries.push(entry)
+    console.log(`✓ Ep ${ep}: ${entry.title.slice(0, 80)}`)
+  } catch (err) {
+    console.error(`✗ Ep ${ep}: ${err.message}`)
+  }
+}
+
+const combined = [...baseEntries, ...newEntries]
+writeFileSync(CHATBOT_FILE, JSON.stringify(combined, null, 2), 'utf8')
+console.log(`\nDone. ${newEntries.length} episode entries added. Total: ${combined.length}`)

scripts/evaluate-chatbot.mjs

@@ -0,0 +1,137 @@
+import fs from 'node:fs/promises'
+import path from 'node:path'
+
+const root = process.cwd()
+const dataPath = path.join(root, 'data', 'chatbot-content.json')
+const evalPath = path.join(root, 'data', 'chatbot-eval.json')
+
+const STOP_WORDS = new Set([
+  'a','an','the','is','are','was','were','be','been','being','have','has','had','do','does','did',
+  'will','would','could','should','may','might','shall','can','i','you','he','she','it','we','they',
+  'me','him','her','us','them','my','your','his','its','our','their','this','that','these','those',
+  'and','but','or','nor','so','yet','for','of','in','on','at','to','from','with','by','about',
+  'what','how','why','when','where','who','which','if','then','than','as','just','not',
+])
+
+const TOKEN_ALIASES = {
+  bible: ['translation', 'version', 'scripture', 'bsb', 'berean'],
+  translation: ['version', 'bsb', 'berean', 'bible'],
+  version: ['translation', 'bsb', 'berean', 'bible'],
+  elders: ['elder', 'leadership', 'leaders', 'overseer', 'pastor'],
+  leadership: ['elders', 'elder', 'overseer', 'leaders'],
+  grace: ['salvation', 'saved', 'godliness', 'mercy'],
+  salvation: ['saved', 'grace', 'mercy', 'gospel'],
+  saved: ['salvation', 'grace', 'mercy', 'gospel'],
+  hope: ['blessed', 'appearing', 'return', 'coming'],
+  politics: ['public', 'government', 'authorities'],
+}
+
+function tokenize(text) {
+  return text
+    .toLowerCase()
+    .replace(/[^a-z0-9\s]/g, ' ')
+    .split(/\s+/)
+    .filter(token => token.length > 2 && !STOP_WORDS.has(token))
+}
+
+function expandTokens(tokens) {
+  const expanded = new Set(tokens)
+  for (const token of tokens) {
+    const aliases = TOKEN_ALIASES[token] ?? []
+    for (const alias of aliases) {
+      for (const aliasToken of tokenize(alias)) expanded.add(aliasToken)
+    }
+  }
+  return [...expanded]
+}
+
+function literalTerms(text) {
+  return [...new Set(
+    text
+      .toLowerCase()
+      .replace(/[^a-z0-9:\-\s']/g, ' ')
+      .split(/\s+/)
+      .map(term => term.trim())
+      .filter(term => term.length >= 2 && !STOP_WORDS.has(term)),
+  )]
+}
+
+function scoreEntry(entry, query) {
+  const indexText = `${entry.title} ${entry.content} ${entry.keywords.join(' ')}`.toLowerCase()
+  const queryTokens = expandTokens(tokenize(query))
+  const terms = literalTerms(query)
+
+  let score = 0
+
+  for (const token of queryTokens) {
+    if (entry.title.toLowerCase().includes(token)) score += 4
+    else if (indexText.includes(token)) score += 2
+  }
+
+  for (const term of terms) {
+    if (entry.title.toLowerCase().includes(term)) score += 2
+    else if (indexText.includes(term)) score += 1
+  }
+
+  const phrase = query.toLowerCase().replace(/[^a-z0-9:\-\s']/g, ' ').replace(/\s+/g, ' ').trim()
+  if (phrase.length > 6) {
+    if (entry.title.toLowerCase().includes(phrase)) score += 10
+    else if (indexText.includes(phrase)) score += 6
+  }
+
+  return score
+}
+
+async function main() {
+  const [contentRaw, evalRaw] = await Promise.all([
+    fs.readFile(dataPath, 'utf8'),
+    fs.readFile(evalPath, 'utf8'),
+  ])
+
+  const entries = JSON.parse(contentRaw)
+  const tests = JSON.parse(evalRaw)
+
+  let pass = 0
+  const failures = []
+
+  for (const test of tests) {
+    const ranked = entries
+      .map(entry => ({ entry, score: scoreEntry(entry, test.query) }))
+      .sort((a, b) => b.score - a.score)
+
+    const topK = ranked.slice(0, test.expectedTopK)
+    const hit = topK.some(item => item.entry.id === test.expectedEntryId)
+
+    if (hit) {
+      pass += 1
+      continue
+    }
+
+    failures.push({
+      query: test.query,
+      expectedEntryId: test.expectedEntryId,
+      expectedTopK: test.expectedTopK,
+      actualTop: topK.map(item => ({ id: item.entry.id, title: item.entry.title, score: item.score })),
+    })
+  }
+
+  const total = tests.length
+  const pct = ((pass / total) * 100).toFixed(1)
+
+  console.log(`Chatbot eval: ${pass}/${total} (${pct}%) passed`)
+
+  if (failures.length > 0) {
+    console.log('\nFailures:')
+    for (const failure of failures) {
+      console.log(`- Query: ${failure.query}`)
+      console.log(`  Expected: ${failure.expectedEntryId} in top ${failure.expectedTopK}`)
+      console.log(`  Actual: ${failure.actualTop.map(item => `${item.id} (${item.score})`).join(', ')}`)
+    }
+    process.exitCode = 1
+  }
+}
+
+main().catch(error => {
+  console.error(error)
+  process.exitCode = 1
+})

scripts/fix-chatbot-titles.mjs

@@ -0,0 +1,26 @@
+import { readFileSync, writeFileSync } from 'fs'
+
+const path = '/Users/nate.emmert/Documents/github/Siteforge/data/chatbot-content.json'
+const data = JSON.parse(readFileSync(path, 'utf8'))
+
+const fixes = {
+  2:  { title: 'Episode 2 — Introduction to Titus (Background & Overview)', extra: ['introduction', 'background', 'overview', 'crete', 'letter'] },
+  5:  { title: 'Episode 5 — The Danger of Empty Words (Titus 1:10–13a)', extra: ['danger', 'empty', 'words', 'false', 'teacher', 'titus 1:10', 'titus 1:13'] },
+  6:  { title: 'Episode 6 — Words That Deny What We Claim to Believe (Titus 1:13b–16)', extra: ['deny', 'claim', 'believe', 'titus 1:13', 'titus 1:16'] },
+  14: { title: 'Episode 14 — Grace: Where It Starts and Where It Ends (Titus 3:12–15)', extra: ['grace', 'starts', 'ends', 'review', 'titus 3:12', 'titus 3:15'] },
+}
+
+let count = 0
+for (const entry of data) {
+  const m = entry.title.match(/^Episode (\d+)/)
+  if (!m) continue
+  const ep = Number(m[1])
+  if (fixes[ep]) {
+    entry.title = fixes[ep].title
+    entry.keywords = [...new Set([...entry.keywords, ...fixes[ep].extra])].slice(0, 20)
+    count++
+  }
+}
+
+writeFileSync(path, JSON.stringify(data, null, 2), 'utf8')
+console.log(`Fixed ${count} entries. Total: ${data.length}`)

scripts/import-episodes-from-docx.mjs

@@ -0,0 +1,194 @@
+import { execFileSync } from 'node:child_process'
+import { randomUUID } from 'node:crypto'
+import { promises as fs } from 'node:fs'
+import path from 'node:path'
+
+const ROOT = '/Users/nate.emmert/Documents/github/Siteforge'
+const DOCS_DIR = path.join(ROOT, 'Verse by Verse with Nate Complete Series')
+const CHATBOT_FILE = path.join(ROOT, 'data', 'chatbot-content.json')
+
+const STOP_WORDS = new Set([
+  'the', 'and', 'for', 'that', 'with', 'this', 'from', 'your', 'you', 'are', 'but', 'not', 'have',
+  'has', 'was', 'were', 'his', 'her', 'our', 'their', 'into', 'about', 'what', 'when', 'where',
+  'which', 'will', 'just', 'they', 'them', 'then', 'than', 'how', 'why', 'can', 'all', 'through',
+])
+
+function parseEpisodeNumber(filePath) {
+  const match = path.basename(filePath).match(/Episode(\d+)/i)
+  return match ? Number(match[1]) : null
+}
+
+function getVariantRank(filePath) {
+  const name = path.basename(filePath).toLowerCase()
+  let score = 0
+  if (name.includes('expanded')) score += 30
+  if (name.includes('updated')) score += 20
+  if (!name.includes('expanded') && !name.includes('updated')) score += 10
+  if (filePath.includes(`${path.sep}Done${path.sep}Old${path.sep}`)) score -= 25
+  return score
+}
+
+async function collectDocxFiles(dir) {
+  const out = []
+  const items = await fs.readdir(dir, { withFileTypes: true })
+  for (const item of items) {
+    const fullPath = path.join(dir, item.name)
+    if (item.isDirectory()) {
+      out.push(...await collectDocxFiles(fullPath))
+      continue
+    }
+    if (!item.isFile()) continue
+    if (!item.name.toLowerCase().endsWith('.docx')) continue
+    if (item.name.startsWith('~$')) continue
+    out.push(fullPath)
+  }
+  return out
+}
+
+function pickBestPerEpisode(docxFiles) {
+  const byEpisode = new Map()
+
+  for (const filePath of docxFiles) {
+    const episode = parseEpisodeNumber(filePath)
+    if (!episode) continue
+
+    const current = byEpisode.get(episode)
+    const next = {
+      filePath,
+      episode,
+      rank: getVariantRank(filePath),
+    }
+
+    if (!current || next.rank > current.rank) {
+      byEpisode.set(episode, next)
+    }
+  }
+
+  return [...byEpisode.values()].sort((a, b) => a.episode - b.episode)
+}
+
+function extractDocText(filePath) {
+  const output = execFileSync('textutil', ['-convert', 'txt', '-stdout', filePath], { encoding: 'utf8' })
+  return output
+}
+
+function normalizeContent(text) {
+  const lines = text
+    .split(/\r?\n/)
+    .map(line => line.replace(/\s+/g, ' ').trim())
+    .filter(Boolean)
+
+  const filtered = lines.filter(line => {
+    const upper = line.toUpperCase()
+    if (upper === 'VERSE BY VERSE WITH NATE') return false
+    if (upper === 'A JOURNEY THROUGH SCRIPTURE') return false
+    return true
+  })
+
+  return filtered.join(' ').replace(/\s{2,}/g, ' ').trim()
+}
+
+function buildKeywords(title, content, existingKeywords = []) {
+  const tokens = `${title} ${content.slice(0, 1600)}`
+    .toLowerCase()
+    .replace(/[^a-z0-9\s:-]/g, ' ')
+    .split(/\s+/)
+    .filter(token => token.length >= 3 && !STOP_WORDS.has(token))
+
+  const counts = new Map()
+  for (const token of tokens) {
+    counts.set(token, (counts.get(token) ?? 0) + 1)
+  }
+
+  const top = [...counts.entries()]
+    .sort((a, b) => b[1] - a[1])
+    .slice(0, 20)
+    .map(([token]) => token)
+
+  return [...new Set([...(existingKeywords ?? []), ...top])].slice(0, 25)
+}
+
+function getEpisodeFromTitle(title = '') {
+  const match = title.match(/Episode\s+(\d+)/i)
+  return match ? Number(match[1]) : null
+}
+
+function getEntryTitleFallback(episodeNumber, rawText, existingTitle) {
+  if (existingTitle && existingTitle.trim()) return existingTitle
+
+  const lineMatch = rawText.match(new RegExp(`EPISODE\\s+${episodeNumber}\\s*[—-]\\s*([^\\n]+)`, 'i'))
+  if (lineMatch) {
+    return `Episode ${episodeNumber} — ${lineMatch[1].trim()}`
+  }
+  return `Episode ${episodeNumber}`
+}
+
+async function run() {
+  const raw = await fs.readFile(CHATBOT_FILE, 'utf8')
+  const entries = JSON.parse(raw)
+
+  const docxFiles = await collectDocxFiles(DOCS_DIR)
+  const selected = pickBestPerEpisode(docxFiles)
+
+  const existingByEpisode = new Map()
+  for (const entry of entries) {
+    const episode = getEpisodeFromTitle(entry.title)
+    if (episode) existingByEpisode.set(episode, entry)
+  }
+
+  const now = new Date().toISOString()
+  let updated = 0
+  let added = 0
+
+  for (const item of selected) {
+    const rawText = extractDocText(item.filePath)
+    const content = normalizeContent(rawText)
+    if (!content) continue
+
+    const existing = existingByEpisode.get(item.episode)
+
+    if (existing) {
+      existing.type = 'episode'
+      existing.title = getEntryTitleFallback(item.episode, rawText, existing.title)
+      existing.content = content
+      existing.keywords = buildKeywords(existing.title, content, existing.keywords)
+      existing.updatedAt = now
+      updated += 1
+      continue
+    }
+
+    entries.push({
+      id: randomUUID(),
+      type: 'episode',
+      title: getEntryTitleFallback(item.episode, rawText, ''),
+      content,
+      keywords: buildKeywords(`Episode ${item.episode}`, content, []),
+      createdAt: now,
+      updatedAt: now,
+    })
+    added += 1
+  }
+
+  entries.sort((a, b) => {
+    const aEp = getEpisodeFromTitle(a.title)
+    const bEp = getEpisodeFromTitle(b.title)
+    if (aEp && bEp) return aEp - bEp
+    if (aEp && !bEp) return 1
+    if (!aEp && bEp) return -1
+    return 0
+  })
+
+  await fs.writeFile(CHATBOT_FILE, `${JSON.stringify(entries, null, 2)}\n`)
+
+  console.log(`Episodes selected from docs: ${selected.length}`)
+  console.log(`Updated entries: ${updated}`)
+  console.log(`Added entries: ${added}`)
+  for (const item of selected) {
+    console.log(`- Episode ${item.episode}: ${path.relative(ROOT, item.filePath)}`)
+  }
+}
+
+run().catch(error => {
+  console.error(error)
+  process.exitCode = 1
+})