Dashboard updated

Added life log, persona, and plugins manager.
changed it so that any new .json files aren't uploaded

.gitignore

@@ -171,5 +171,4 @@ cython_debug/
 .vscode/launch.json
 /books/*
 /memory/*
-vocab.json
-progress.json
+*.json

body.py

@@ -1,97 +1,215 @@
+# body.py
+# flake8: noqa
 import os
-import asyncio
 import glob
-import threading
 import json
+import threading
+import asyncio
 from collections import deque
+from datetime import datetime, time, timedelta
 import logging
+
+import requests
 import discord
 
 from nervous_system import NervousSystem
-import dashboard    # <-- import your new Flask app
-import brain_map    # <-- import the blueprint to inject system
+from persona import Persona
+from life_log import LifeLog
+from plugin_manager import PluginManager
+import dashboard
+import brain_map
 
-# Path for progress persistence
-PROGRESS_PATH = 'progress.json'
-
-# Mute logger
-for noisy_logger in ["werkzeug", "flask", "flask.app"]:
-    logging.getLogger(noisy_logger).setLevel(logging.CRITICAL)
-
-# ─── Initialize Ruby & Discord ───────────────────────────────────────────────── # noqa: E501
+# ─── Config & Paths ────────────────────────────────────────────────────────────
+VOCAB_PATH      = "vocab.json"
+PROGRESS_PATH   = "progress.json"
+PERSONA_PATH    = "persona.json"
+LIFELOG_PATH    = "life_log.json"
+OPENWEATHER_KEY = os.getenv("OPENWEATHER_API_KEY")
+WEATHER_CITY    = os.getenv("WEATHER_CITY", "New York")
+WEATHER_HOUR    = 6  # daily at 6 AM
 
+# ─── Discord & System Setup ────────────────────────────────────────────────────
 intents = discord.Intents.default()
 intents.message_content = True
 client = discord.Client(intents=intents)
-system = NervousSystem()
-system.history = deque(maxlen=100)
 
-# Load or resume vocab + embeddings
-system.sensory.load_vocab('vocab.json')
+system   = NervousSystem()
+persona  = Persona(path=PERSONA_PATH)
+life_log = LifeLog(path=LIFELOG_PATH)
+plugins  = PluginManager()
+
+# keep last 6 turns for conversational context
+system.history = deque(maxlen=6)
+
+# load/resize vocab
+system.sensory.load_vocab(VOCAB_PATH)
 system._resize_embeddings()
-print('Loaded vocab size:', len(system.sensory.stoi))
 
-# Resume progress
+# resume book‐training progress (per-book)
 if os.path.isfile(PROGRESS_PATH):
-    with open(PROGRESS_PATH, 'r', encoding='utf-8') as f:
-        data = json.load(f)
-        system.processed_lines = data.get('processed_lines', 0)
+    with open(PROGRESS_PATH, "r", encoding="utf-8") as f:
+        prog = json.load(f)
+        current_book = prog.get("current_book", 0)
+        line_offset  = prog.get("line_offset", 0)
 else:
-    system.processed_lines = 0
+    current_book = 0
+    line_offset  = 0
 
-# Compute total book lines
-total = sum(
-    1
-    for path in glob.glob('books/*.txt')
-    for line in open(path, encoding='utf-8')
-    if line.strip()
+book_list = sorted(glob.glob("books/*.txt"))
+total_books = len(book_list)
+
+# count lines per book
+book_line_counts = []
+for path in book_list:
+    cnt = sum(1 for line in open(path, encoding="utf-8") if line.strip())
+    book_line_counts.append(cnt)
+
+# set up overall progress counters for the dashboard
+system.total_lines = sum(book_line_counts)
+lines_done = sum(book_line_counts[:current_book]) + line_offset
+system.processed_lines = lines_done
+print(
+    f"Resuming training: book {current_book+1}/{total_books}, "
+    f"line {line_offset}/{book_line_counts[current_book] if current_book < total_books else 0}\n"
+    f"Overall progress: {system.processed_lines}/{system.total_lines} lines"
 )
-system.total_lines = total
 
-print(f'Resuming training at {system.processed_lines}/{system.total_lines} lines')
-
-# Inject into Flask contexts
+# inject for dashboard routes
 dashboard.system = system
 brain_map.system = system
 
-# ─── Book-training when idle ──────────────────────────────────────────────────── # noqa: E501
+print(
+    f"Loaded vocab {len(system.sensory.stoi)}, "
+    f"resuming at book {current_book+1}/{total_books}, "
+    f"line {line_offset}/{book_line_counts[current_book] if current_book < total_books else 0}"
+)
 
 
+def refine_diary_entry(raw: str) -> str:
+    prompt = (
+        "Here is a rough diary draft. Rewrite it as a clear, first-person "
+        "diary entry in 2–3 sentences:\n\n"
+        f"Draft:\n{raw}\n\nRefined entry:"
+    )
+    return system.generate(prompt, max_len=100, temperature=0.7, top_p=0.9)
+
+
+# ─── Seed Book-Title Diary Entries ─────────────────────────────────────────────
+for path in book_list:
+    title = os.path.splitext(os.path.basename(path))[0]
+    fact = f"I just finished reading “{title}.”"
+    system.train("", fact)
+    draft = system.generate(
+        f"Diary prompt: Stream-of-thought draft about reading “{title}.”",
+        max_len=100, temperature=0.9, top_p=0.95
+    )
+    entry = refine_diary_entry(draft)
+    life_log.add(entry)
+
+
+# ─── Idle Book-Training Task (per-book) ────────────────────────────────────────
 async def train_books_idle():
+    global current_book, line_offset
     await client.wait_until_ready()
     await asyncio.sleep(5)
-    processed = 0
-    skip = system.processed_lines
 
-    for path in glob.glob('books/*.txt'):
-        with open(path, encoding='utf-8') as f:
+    # process one book at a time
+    while current_book < total_books:
+        path = book_list[current_book]
+        processed = 0
+        cnt = book_line_counts[current_book]
+        with open(path, encoding="utf-8") as f:
             for raw in f:
                 text = raw.strip()
                 if not text:
                     continue
-                if processed < skip:
+                if processed < line_offset:
                     processed += 1
                     continue
 
+                # train on this line
                 await asyncio.to_thread(system.train, text, text)
                 processed += 1
-                system.processed_lines = processed
+                line_offset = processed
 
-                if processed % 200 == 0 or processed == system.total_lines:
-                    system.sensory.save_vocab('vocab.json')
-                    with open(PROGRESS_PATH, 'w', encoding='utf-8') as pf:
-                        json.dump({'processed_lines': processed}, pf)
+                # checkpoint every 200 lines or at end
+                if processed % 200 == 0 or processed == cnt:
+                    system.sensory.save_vocab(VOCAB_PATH)
+                    with open(PROGRESS_PATH, "w", encoding="utf-8") as pf:
+                        json.dump({
+                            "current_book": current_book,
+                            "line_offset":  line_offset
+                        }, pf, indent=2)
 
-    # Final checkpoint
-    system.sensory.save_vocab('vocab.json')
-    with open(PROGRESS_PATH, 'w', encoding='utf-8') as pf:
-        json.dump({'processed_lines': system.processed_lines}, pf)
+        # finished current book
+        print(f"Finished book {current_book+1}/{total_books}: {path}")
+        # reset for next book
+        current_book += 1
+        line_offset  = 0
+        # save progress
+        with open(PROGRESS_PATH, "w", encoding="utf-8") as pf:
+            json.dump({
+                "current_book": current_book,
+                "line_offset":  0
+            }, pf, indent=2)
+        # optional small break between books
+        await asyncio.sleep(2)
+
+    # all books done; bootstrap persona
+    await asyncio.to_thread(persona.bootstrap, system)
+    print("All books trained. Persona bootstrapped:", persona.traits)
+
+
+# ─── Idle Weather-Ingestion & Diary Task ───────────────────────────────────────
+async def ingest_weather_idle():
+    await client.wait_until_ready()
+    # sleep until next WEATHER_HOUR
+    now = datetime.now()
+    target = datetime.combine(now.date(), time(WEATHER_HOUR))
+    if now >= target:
+        target += timedelta(days=1)
+    await asyncio.sleep((target - now).total_seconds())
+
+    while True:
+        if OPENWEATHER_KEY:
+            try:
+                url = (
+                    "https://api.openweathermap.org/data/2.5/weather"
+                    f"?q={WEATHER_CITY}&units=metric&appid={OPENWEATHER_KEY}"
+                )
+                data = requests.get(url, timeout=5).json()
+                desc = data["weather"][0]["description"]
+                temp = data["main"]["temp"]
+                fact = f"Current weather: {desc}, {temp:.1f}°C."
+                await asyncio.to_thread(system.train, "", fact)
+
+                draft = system.generate(
+                    f"Diary prompt: Draft about today’s weather: {desc}, {temp:.1f}°C.",
+                    max_len=100, temperature=0.9, top_p=0.95
+                )
+                entry = refine_diary_entry(draft)
+                life_log.add(entry)
+                print("Journaled weather:", entry)
+            except Exception:
+                pass
+        await asyncio.sleep(24 * 3600)
+
+
+# ─── Idle Self-Reflection Task ─────────────────────────────────────────────────
+async def reflect_idle():
+    await client.wait_until_ready()
+    while True:
+        await asyncio.sleep(600)
+        await asyncio.to_thread(persona.bootstrap, system)
+        print("Persona adapted:", persona.traits)
 
 
 @client.event
 async def on_ready():
-    print(f'Ruby is online as {client.user}!')
+    print(f"Ruby is online as {client.user}!")
     asyncio.create_task(train_books_idle())
+    asyncio.create_task(ingest_weather_idle())
+    asyncio.create_task(reflect_idle())
 
 
 @client.event
@@ -100,27 +218,53 @@ async def on_message(message: discord.Message):
         return
 
     user_text = message.content.strip()
-    reply = system.generate(user_text)
+
+    # 1) Diary: top 5 recent
+    entries = life_log.recent(5)
+    diary_sec = "### Diary Entries\n"
+    for e in reversed(entries):
+        diary_sec += f"- {e}\n"
+
+    # 2) Persona
+    persona_sec = "\n### Persona\n" + persona.summary()
+
+    # 3) Conversation
+    convo_sec = "\n### Conversation\n"
+    for turn in system.history:
+        convo_sec += f"User: {turn['user']}\nRuby: {turn['bot']}\n"
+    convo_sec += f"User: {user_text}\nRuby:"
+
+    prompt = diary_sec + persona_sec + convo_sec
+    reply = system.generate(prompt)
     await message.channel.send(reply)
 
-    system.history.append({'user': user_text, 'bot': reply})
-    asyncio.create_task(asyncio.to_thread(system.train, user_text, reply))
-
-
-# ─── Launch Dashboard & Bot ──────────────────────────────────────────────────── # noqa: E501
+    # record & train
+    system.history.append({"user": user_text, "bot": reply})
+    asyncio.create_task(
+        asyncio.to_thread(system.train, user_text, reply)
+    )
 
+# ─── Silence Flask/Werkzeug request logs ────────────────────────────────────────
+logging.getLogger('werkzeug').setLevel(logging.ERROR)
 
 def run_dashboard():
     dashboard.app.run(
-        host='0.0.0.0', port=5000,
-        debug=False, use_reloader=False
+        host="0.0.0.0",
+        port=5000,
+        debug=False,
+        use_reloader=False
     )
 
 
 threading.Thread(target=run_dashboard, daemon=True).start()
-print('Dashboard available at http://127.0.0.1:5000')
+dashboard.system = system
+dashboard.persona = persona
+dashboard.life_log = life_log
+dashboard.plugins = plugins
+dashboard.brain_map = brain_map
+print("Dashboard available at http://127.0.0.1:5000")
 
-token = os.getenv('DISCORD_TOKEN')
+token = os.getenv("DISCORD_TOKEN")
 if not token:
-    raise RuntimeError('Please set the DISCORD_TOKEN environment variable')
+    raise RuntimeError("Please set DISCORD_TOKEN in env")
 client.run(token)

dashboard.py

@@ -1,17 +1,21 @@
+# dashboard.py
+
 from flask import Flask, render_template, jsonify
+from datetime import datetime
 import brain_map
 
 app = Flask(
     __name__,
     template_folder='templates',
-    static_folder='static',
+    static_folder='static'
 )
-
-# Register the brain_map blueprint
 app.register_blueprint(brain_map.bp)
 
-# Will be injected from body.py
-system = None
+# Injected from body.py
+system   = None
+persona  = None
+life_log = None
+plugins  = None
 
 
 @app.route('/')
@@ -19,6 +23,25 @@ def dashboard():
     return render_template('dashboard.html')
 
 
+@app.route('/stats')
+def stats():
+    """
+    Returns JSON with the key metrics for the dashboard to display.
+    Uses getattr to supply 0 if any attribute is missing.
+    """
+    if system is None:
+        return jsonify({})
+
+    return jsonify({
+        'processed_lines': getattr(system, 'processed_lines', 0),
+        'total_lines':     getattr(system, 'total_lines', 0),
+        'history_len':     len(getattr(system, 'history', [])),
+        'life_log_count':  len(getattr(life_log, 'entries', [])),
+        'plugin_count':    len(getattr(plugins, 'registry', {})),
+        'timestamp':       datetime.utcnow().timestamp()
+    })
+
+
 @app.route('/progress')
 def progress():
     if system is None:

life_log.py

@@ -0,0 +1,28 @@
+import json
+import os
+
+
+class LifeLog:
+    """
+    Records Ruby’s diary entries over time and lets you fetch her recent reflections.
+    """
+    def __init__(self, path="life_log.json"):
+        self.path = path
+        self.entries = []
+        self.load()
+
+    def load(self):
+        if os.path.isfile(self.path):
+            with open(self.path, "r", encoding="utf-8") as f:
+                self.entries = json.load(f)
+
+    def save(self):
+        with open(self.path, "w", encoding="utf-8") as f:
+            json.dump(self.entries, f, ensure_ascii=False, indent=2)
+
+    def add(self, entry: str):
+        self.entries.append(entry)
+        self.save()
+
+    def recent(self, n=5):
+        return self.entries[-n:]

nervous_system.py

@@ -1,106 +1,159 @@
+# nervous_system.py
+import threading
 import torch
-import torch.optim as optim
-from torch.nn import CrossEntropyLoss
+import torch.nn as nn
 import torch.nn.functional as F
+import torch.optim as optim
 
 from sensory import Sensory
 from brain import Brain
 
 
 class NervousSystem:
-    """Wraps the Brain, handles token growth, generation and on-the-fly training."""  # noqa: E501
+    """Wraps the Brain, handles token growth, generation, and training."""
 
     def __init__(self, device: str = "cuda"):
-        self.device = torch.device(device if torch.cuda.is_available() else "cpu")  # noqa: E501
+        self.device = torch.device(
+            device if torch.cuda.is_available() else "cpu"
+        )
         self.sensory = Sensory()
         vocab_size = len(self.sensory.stoi)
         self.brain = Brain(vocab_size).to(self.device)
 
+        # disable any inplace ops in the model
+        for m in self.brain.modules():
+            if hasattr(m, "inplace"):
+                m.inplace = False  # ensure no in-place ReLUs, etc.
+
         self.optimizer = optim.Adam(self.brain.parameters(), lr=1e-4)
-        self.criterion = CrossEntropyLoss(ignore_index=0)
+        self.criterion = nn.CrossEntropyLoss(ignore_index=0)
         self.meta_steps = 0
 
+        # ← NEW: lock to serialize all training calls
+        self._train_lock = threading.Lock()
+
     def _resize_embeddings(self) -> None:
+        """
+        Resize token & output embeddings entirely on-device
+        to match the current vocab size, avoiding any CPU↔GPU copies.
+        """
+        device = self.device
         new_size = len(self.sensory.stoi)
+
+        # ─── Resize token embeddings ────────────────────────────────────────
         old_emb = self.brain.token_emb
+        old_num, dim = old_emb.num_embeddings, old_emb.embedding_dim
 
-        # rebuild token embeddings
-        self.brain.token_emb = torch.nn.Embedding(
-            new_size, old_emb.embedding_dim
-        ).to(self.device)
+        # allocate new on same device
+        new_emb = nn.Embedding(new_size, dim).to(device)
+        # copy existing weights
         with torch.no_grad():
-            self.brain.token_emb.weight[: old_emb.num_embeddings] = old_emb.weight  # noqa: E501
+            new_emb.weight[:old_num].copy_(old_emb.weight)
+        self.brain.token_emb = new_emb
 
-        # rebuild output head
+        # ─── Resize output head ─────────────────────────────────────────────
         old_out = self.brain.fc_out
-        self.brain.fc_out = torch.nn.Linear(
-            old_emb.embedding_dim, new_size
-        ).to(self.device)
+        out_dim, old_out_feat = old_out.in_features, old_out.out_features
+
+        new_out = nn.Linear(out_dim, new_size).to(device)
         with torch.no_grad():
-            self.brain.fc_out.weight[: old_out.out_features] = old_out.weight
-            self.brain.fc_out.bias[: old_out.out_features] = old_out.bias
+            new_out.weight[:old_out_feat].copy_(old_out.weight)
+            new_out.bias[:old_out_feat].copy_(old_out.bias)
+        self.brain.fc_out = new_out
 
-    def generate(self, prompt: str, max_len: int = 50,
-                 temperature: float = 0.8, top_k: int = 50) -> str:
+    def generate(
+        self,
+        prompt: str,
+        max_len: int = 50,
+        temperature: float = 0.8,
+        top_p: float = 0.9,
+    ) -> str:
+        """Autoregressive nucleus sampling with proper cloning to avoid aliasing."""
         self.brain.eval()
-        raw_ids = self.sensory.encode(prompt, grow=False)[-self.brain.max_seq_len:]  # noqa: E501
-        out = torch.tensor(raw_ids, dtype=torch.long, device=self.device).unsqueeze(0)  # noqa: E501
+        eos_id = self.sensory.stoi.get("<eos>")
 
-        result = []
-        for _ in range(max_len):
-            logits = self.brain(out)[:, -1, :]
-            # apply temperature
-            logits = logits / temperature
-            # top-k filtering
-            values, indices = torch.topk(logits, top_k)
-            probs = F.softmax(values, dim=-1)
-            next_tok = indices[0, torch.multinomial(probs, 1)].unsqueeze(0).unsqueeze(0)  # noqa: E501
-            tok_id = next_tok.item()
-            if tok_id == self.sensory.stoi["<eos>"]:
-                break
-            result.append(tok_id)
-            out = torch.cat([out, next_tok], dim=1)
+        raw_ids = self.sensory.encode(prompt, grow=False)
+        max_ctx = self.brain.max_seq_len - 1
+        if len(raw_ids) > max_ctx:
+            raw_ids = raw_ids[-max_ctx:]
 
-        return self.sensory.decode(result)
-
-    def train(self, user_text: str, bot_text: str) -> None:
-        # 1) grow vocab on _train_ only
-        for txt in (user_text, bot_text):
-            _ = self.sensory.encode(txt, grow=True)
-        self._resize_embeddings()
-
-        # ensure <sep>
-        if "<sep>" not in self.sensory.stoi:
-            idx = len(self.sensory.stoi)
-            self.sensory.stoi["<sep>"] = idx
-            self.sensory.itos[idx] = "<sep>"
-            self._resize_embeddings()
-
-        combined = f"{user_text} <sep> {bot_text}"
-        ids = torch.tensor(
-            self.sensory.encode(combined, grow=False), dtype=torch.long, device=self.device  # noqa: E501
+        input_ids = torch.tensor(
+            raw_ids, dtype=torch.long, device=self.device
         ).unsqueeze(0)
 
-        if ids.size(1) < 2:
-            return
+        generated = []
+        for _ in range(max_len):
+            logits = self.brain(input_ids)[:, -1, :] / temperature
+            probs = F.softmax(logits, dim=-1)
 
-        inputs = ids[:, :-1]
-        targets = ids[:, 1:]
+            # top-p (nucleus) filtering
+            sorted_p, sorted_idx = torch.sort(probs, descending=True)
+            cum_p = torch.cumsum(sorted_p, dim=-1)
+            mask = cum_p > top_p
+            # clone the slice before writing to avoid overlap
+            mask_shift = mask[..., :-1].clone()
+            mask[..., 1:] = mask_shift
+            sorted_p[mask] = 0
+            sorted_p = sorted_p / sorted_p.sum(dim=-1, keepdim=True)
 
-        self.brain.train()
-        logits = self.brain(inputs)
-        loss = self.criterion(
-            logits.view(-1, logits.size(-1)), targets.view(-1)
-        )
-        self.optimizer.zero_grad()
-        loss.backward()
-        self.optimizer.step()
+            next_tok = sorted_idx[0, torch.multinomial(sorted_p[0], 1)]
+            t_id = next_tok.item()
 
-        # a tiny meta-learning bump
-        self.meta_steps += 1
-        if self.meta_steps % 100 == 0:
-            for g in self.optimizer.param_groups:
-                old_lr = g["lr"]
-                g["lr"] = old_lr * 1.1
-                torch.cuda.synchronize(self.device)
-                g["lr"] = old_lr
+            if eos_id is not None and t_id == eos_id:
+                break
+
+            generated.append(t_id)
+            input_ids = torch.cat([input_ids, next_tok.unsqueeze(0)], dim=1)
+
+            if input_ids.size(1) > self.brain.max_seq_len:
+                input_ids = input_ids[:, -self.brain.max_seq_len:]
+
+        return self.sensory.decode(generated)
+
+    def train(self, user_text: str, bot_text: str) -> None:
+        """
+        On-the-fly self-supervised training from a user↔bot exchange.
+        Serialized by a threading.Lock to avoid in-place grad conflicts.
+        """
+        with self._train_lock:  # ← NEW: no two threads can enter here at once
+            # 1) grow vocab & resize embeddings
+            for txt in (user_text, bot_text):
+                _ = self.sensory.encode(txt, grow=True)
+            self._resize_embeddings()
+
+            # 2) ensure a <sep> token for concatenation
+            if "<sep>" not in self.sensory.stoi:
+                idx = len(self.sensory.stoi)
+                self.sensory.stoi["<sep>"] = idx
+                self.sensory.itos[idx] = "<sep>"
+                self._resize_embeddings()
+
+            # 3) build input/output IDs
+            combined = f"{user_text} <sep> {bot_text}"
+            ids = torch.tensor(
+                self.sensory.encode(combined, grow=False),
+                dtype=torch.long,
+                device=self.device,
+            ).unsqueeze(0)
+
+            if ids.size(1) < 2:
+                return
+
+            inputs = ids[:, :-1]
+            targets = ids[:, 1:]
+
+            # 4) forward + backward + step
+            self.brain.train()
+            logits = self.brain(inputs)
+            loss = self.criterion(
+                logits.view(-1, logits.size(-1)), targets.view(-1)
+            )
+            self.optimizer.zero_grad()
+            loss.backward()
+            self.optimizer.step()
+
+            # 5) optional meta learning step adjustment
+            self.meta_steps += 1
+            if self.meta_steps % 100 == 0:
+                for g in self.optimizer.param_groups:
+                    g["lr"] *= 1.1

persona.py

@@ -0,0 +1,67 @@
+import json
+import os
+import re
+
+class Persona:
+    """
+    Learns Ruby’s persona entirely from her model by asking for JSON,
+    with no hard-coded examples or defaults.
+    """
+    def __init__(self, path="persona.json"):
+        self.path = path
+        self.traits = {}
+        self.load()
+
+    def load(self):
+        if os.path.isfile(self.path):
+            with open(self.path, "r", encoding="utf-8") as f:
+                self.traits = json.load(f)
+
+    def save(self):
+        with open(self.path, "w", encoding="utf-8") as f:
+            json.dump(self.traits, f, ensure_ascii=False, indent=2)
+
+    def summary(self) -> str:
+        if not self.traits:
+            return ""
+        name    = self.traits.get("name", "")
+        age     = self.traits.get("age", "")
+        hobbies = self.traits.get("hobbies", [])
+        tone    = self.traits.get("tone", "")
+        hlist   = ", ".join(hobbies) if isinstance(hobbies, list) else str(hobbies)
+        return f"I'm {name}, {age} years old, I love {hlist}, and speak in a {tone} tone."
+
+    def bootstrap(self, system):
+        """
+        Ask Ruby to introspect and output a JSON object with keys:
+        name, age, hobbies (array), and tone (string). No examples given.
+        """
+        prompt = (
+            "Based on all the text you have absorbed, introduce yourself by OUTPUTTING "
+            "ONLY a JSON object with these keys exactly:\n"
+            '  "name": string,\n'
+            '  "age": number,\n'
+            '  "hobbies": array of strings,\n'
+            '  "tone": string describing your speaking style\n'
+            "Do not output anything else."
+        )
+        raw = system.generate(prompt, max_len=150, temperature=0.7, top_p=0.9)
+
+        # extract the first JSON object block
+        m = re.search(r"\{.*?\}", raw, flags=re.DOTALL)
+        if not m:
+            return
+        try:
+            data = json.loads(m.group(0))
+        except json.JSONDecodeError:
+            return
+
+        # keep only expected keys
+        updated = {}
+        for key in ("name", "age", "hobbies", "tone"):
+            if key in data:
+                updated[key] = data[key]
+
+        if updated:
+            self.traits = updated
+            self.save()

plugin_manager.py

@@ -0,0 +1,55 @@
+import os
+import importlib.util
+import sys
+from typing import Any, Callable, Dict
+
+PLUGINS_DIR = "plugins"
+os.makedirs(PLUGINS_DIR, exist_ok=True)
+
+
+class PluginManager:
+    """
+    Dynamically loads Python modules from plugins/ and
+    exposes their functions in a registry.
+    """
+
+    def __init__(self):
+        self.registry: Dict[str, Callable[..., Any]] = {}
+        self._load_all()
+
+    def _load_all(self):
+        """Scan plugins/ and import every .py as a module."""
+        for fname in os.listdir(PLUGINS_DIR):
+            if not fname.endswith(".py"):
+                continue
+            path = os.path.join(PLUGINS_DIR, fname)
+            name = os.path.splitext(fname)[0]
+            self._load_module(name, path)
+
+    def _load_module(self, name: str, path: str):
+        """Load a single plugin module and register its callables."""
+        spec = importlib.util.spec_from_file_location(name, path)
+        if spec and spec.loader:
+            mod = importlib.util.module_from_spec(spec)
+            sys.modules[name] = mod
+            spec.loader.exec_module(mod)  # type: ignore
+            for attr in dir(mod):
+                if attr.startswith("_"):
+                    continue
+                obj = getattr(mod, attr)
+                if callable(obj):
+                    key = f"{name}.{attr}"
+                    self.registry[key] = obj
+
+    def register_plugin(self, code: str, name: str):
+        """
+        Persist a new plugin file (name.py), load it immediately,
+        and add its functions to the registry.
+        """
+        path = os.path.join(PLUGINS_DIR, f"{name}.py")
+        with open(path, "w", encoding="utf-8") as f:
+            f.write(code)
+        # replace any existing module
+        if name in sys.modules:
+            del sys.modules[name]
+        self._load_module(name, path)

sensory.py

@@ -1,13 +1,14 @@
-import os
 import json
+import os
 
 
 class Sensory:
     """Dynamic whitespace tokenizer that can grow (or not) its vocab."""
 
     def __init__(self):
-        self.stoi = {"<pad>": 0, "<unk>": 1}
-        self.itos = {0: "<pad>", 1: "<unk>"}
+        # ensure <pad>, <unk>, AND <eos> are present from the start
+        self.stoi = {"<pad>": 0, "<unk>": 1, "<eos>": 2}
+        self.itos = {0: "<pad>", 1: "<unk>", 2: "<eos>"}
 
     def encode(self, text: str, grow: bool = True) -> list[int]:
         ids: list[int] = []
@@ -25,24 +26,27 @@ class Sensory:
         return ids
 
     def decode(self, ids: list[int]) -> str:
-        return " ".join(self.itos.get(i, "<unk>") for i in ids)
+        out = []
+        for i in ids:
+            if i == self.stoi["<eos>"]:
+                break
+            out.append(self.itos.get(i, "<unk>"))
+        return " ".join(out)
 
     def save_vocab(self, path: str = "vocab.json") -> None:
-        """Dump stoi+itos to disk."""
-        data = {
-            "stoi": self.stoi,
-            # JSON keys must be strings
-            "itos": {str(k): v for k, v in self.itos.items()}
-        }
+        data = {"stoi": self.stoi, "itos": {str(k): v for k, v in self.itos.items()}}
         with open(path, "w", encoding="utf-8") as f:
-            json.dump(data, f, ensure_ascii=False, indent=2)
+            json.dump(data, f, indent=2)
 
     def load_vocab(self, path: str = "vocab.json") -> None:
-        """Load stoi+itos if it exists."""
         if not os.path.isfile(path):
             return
         with open(path, encoding="utf-8") as f:
             data = json.load(f)
         self.stoi = data["stoi"]
-        # convert itos keys back to int
         self.itos = {int(k): v for k, v in data["itos"].items()}
+        # if somehow <eos> got lost, re-add it
+        if "<eos>" not in self.stoi:
+            idx = len(self.stoi)
+            self.stoi["<eos>"] = idx
+            self.itos[idx] = "<eos>"

templates/dashboard.html

@@ -1,72 +1,148 @@
 <!DOCTYPE html>
 <html lang="en">
 <head>
-  <meta charset="utf-8" />
+  <meta charset="utf-8"/>
   <title>Ruby Dashboard</title>
+  <meta name="viewport" content="width=device-width, initial-scale=1"/>
+  <!-- Bootstrap CSS -->
+  <link
+    href="https://cdn.jsdelivr.net/npm/bootstrap@5.0.2/dist/css/bootstrap.min.css"
+    rel="stylesheet"
+  />
+  <!-- Chart.js -->
+  <script src="https://cdn.jsdelivr.net/npm/chart.js@3.5.1/dist/chart.min.js"></script>
   <style>
     body {
-      background:#1e1e1e; color:#ddd;
-      font-family:sans-serif; padding:20px;
+      background-color: #121212;
+      color: #e0e0e0;
+      font-family: Arial, sans-serif;
     }
-    h1 { color:#fff; }
-    .section { margin-bottom:20px; }
-    button {
-      background:#333; border:1px solid #555;
-      color:#ddd; padding:8px 12px;
-      border-radius:4px; cursor:pointer;
+    .card {
+      background-color: #1e1e1e;
+      border: none;
     }
-    #history {
-      max-height:300px; overflow:auto;
-      border:1px solid #444; padding:10px;
-      border-radius:4px; background:#2e2e2e;
+    .card-title, .card-text {
+      color: #ffffff;
     }
-    .entry { margin-bottom:8px; }
-    .user  { color:#8af; }
-    .bot   { color:#fa8; }
   </style>
 </head>
 <body>
-  <h1>Ruby Dashboard</h1>
+  <div class="container py-4">
+    <h1 class="mb-4">Ruby Dashboard</h1>
 
-  <div class="section">
-    <strong id="progress">Progress: 0/0</strong>
-  </div>
+    <!-- Metrics Cards -->
+    <div class="row g-3 mb-4">
+      <div class="col-md-3">
+        <div class="card p-3">
+          <h5 class="card-title">Training Progress</h5>
+          <div class="progress mb-2">
+            <div
+              id="training-bar"
+              class="progress-bar bg-success"
+              role="progressbar"
+              style="width: 0%"
+            >0%</div>
+          </div>
+          <p class="card-text">
+            <span id="processed-count">0</span> /
+            <span id="total-count">0</span> lines
+          </p>
+        </div>
+      </div>
+      <div class="col-md-3">
+        <div class="card p-3">
+          <h5 class="card-title">Recent Turns</h5>
+          <p class="card-text"><span id="history-len">0</span> turns</p>
+        </div>
+      </div>
+      <div class="col-md-3">
+        <div class="card p-3">
+          <h5 class="card-title">Diary Entries</h5>
+          <p class="card-text"><span id="life-log-count">0</span> entries</p>
+        </div>
+      </div>
+      <div class="col-md-3">
+        <div class="card p-3">
+          <h5 class="card-title">Plugins</h5>
+          <p class="card-text"><span id="plugin-count">0</span></p>
+        </div>
+      </div>
+    </div>
 
-  <div class="section">
-    <h2>Recent Interactions</h2>
-    <div id="history">Loading…</div>
-  </div>
+    <!-- Progress Over Time Chart -->
+    <div class="card p-3 mb-4">
+      <h5 class="card-title">Processed Lines Over Time</h5>
+      <canvas id="progressChart" height="100"></canvas>
+    </div>
 
-  <div class="section">
-    <button id="load-graph">Load Brain Map</button>
+    <!-- Brain Map Link -->
+    <div class="text-center">
+      <a href="/graph" class="btn btn-outline-light">View Brain Map</a>
+    </div>
   </div>
 
   <script>
-    async function refreshProgress() {
-      const { processed, total } = await fetch('/progress').then(r=>r.json());
-      document.getElementById('progress').textContent =
-        `Progress: ${processed}/${total}`;
-    }
-    async function refreshHistory() {
-      const hist = await fetch('/interactions').then(r=>r.json());
-      const div = document.getElementById('history');
-      div.innerHTML = '';
-      if (hist.length === 0) {
-        div.textContent = 'No interactions yet.';
-        return;
+    const ctx = document.getElementById('progressChart').getContext('2d');
+    const chart = new Chart(ctx, {
+      type: 'line',
+      data: {
+        labels: [],
+        datasets: [{
+          label: 'Processed Lines',
+          data: [],
+          fill: false,
+          tension: 0.2,
+          borderColor: '#4caf50'
+        }]
+      },
+      options: {
+        scales: {
+          x: { title: { display: true, text: 'Time' }, ticks: { color: '#e0e0e0' } },
+          y: { title: { display: true, text: 'Lines' }, ticks: { color: '#e0e0e0' } }
+        },
+        plugins: { legend: { labels: { color: '#e0e0e0' } } }
+      }
+    });
+
+    async function updateStats() {
+      try {
+        const res = await fetch('/stats');
+        const s = await res.json();
+        const { processed_lines, total_lines,
+                history_len, life_log_count,
+                plugin_count, timestamp } = s;
+
+        // update cards
+        document.getElementById('processed-count').textContent = processed_lines;
+        document.getElementById('total-count').textContent   = total_lines;
+        const pct = total_lines
+          ? Math.round((processed_lines / total_lines) * 100)
+          : 0;
+        const bar = document.getElementById('training-bar');
+        bar.style.width = pct + '%';
+        bar.textContent = pct + '%';
+
+        document.getElementById('history-len').textContent    = history_len;
+        document.getElementById('life-log-count').textContent = life_log_count;
+        document.getElementById('plugin-count').textContent   = plugin_count;
+
+        // update chart
+        const timeLabel = new Date(timestamp * 1000).toLocaleTimeString();
+        chart.data.labels.push(timeLabel);
+        chart.data.datasets[0].data.push(processed_lines);
+        if (chart.data.labels.length > 20) {
+          chart.data.labels.shift();
+          chart.data.datasets[0].data.shift();
+        }
+        chart.update();
+      } catch (err) {
+        console.error('Failed to fetch stats', err);
       }
-      hist.slice(-20).forEach(({user, bot}) => {
-        const e = document.createElement('div'); e.className='entry';
-        const u = document.createElement('div'); u.className='user'; u.textContent='User: '+user;
-        const b = document.createElement('div'); b.className='bot';  b.textContent='Bot: '+bot;
-        e.append(u, b); div.appendChild(e);
-      });
     }
-    document.getElementById('load-graph')
-      .onclick = () => window.location = '/graph';
-    refreshProgress(); refreshHistory();
-    setInterval(refreshProgress, 5000);
-    setInterval(refreshHistory, 5000);
+
+    // initial load + periodic
+    updateStats();
+    setInterval(updateStats, 5000);
   </script>
 </body>
 </html>