[gemini] Pull Hermes 4 14B — inference (GGUF) + training (MLX) models (#9)

.gitignore

@@ -8,3 +8,4 @@
 *.db-wal
 *.db-shm
 __pycache__/
+.aider*

DEPRECATED.md

@@ -1,7 +1,7 @@
 # DEPRECATED — Bash Loop Scripts Removed
 
 **Date:** 2026-03-25
-**Reason:** Replaced by Hermes + timmy-config sidecar orchestration
+**Reason:** Replaced by sovereign-orchestration (SQLite + Python single-process executor)
 
 ## What was removed
 - claude-loop.sh, gemini-loop.sh, agent-loop.sh
@@ -9,15 +9,14 @@
 - nexus-merge-bot.sh, claudemax-watchdog.sh, timmy-loopstat.sh
 
 ## What replaces them
-**Harness:** Hermes
+**Repo:** Timmy_Foundation/sovereign-orchestration
-**Overlay repo:** Timmy_Foundation/timmy-config
+**Entry point:** `python3 src/sovereign_executor.py --workers 3 --poll 30`
-**Entry points:** `orchestration.py`, `tasks.py`, `deploy.sh`
+**Features:** SQLite task queue, crash recovery, dedup, playbooks, MCP server
-**Features:** Huey + SQLite scheduling, local-model health checks, session export, DPO artifact staging
+**Issues:** #29 (fix imports), #30 (deploy as service)
 
 ## Why
 The bash loops crash-looped, produced zero work after relaunch, had no crash
-recovery, no durable export path, and required too many ad hoc scripts. The
+recovery, no dedup, and required 8 separate scripts. The Python executor is
-Hermes sidecar keeps orchestration close to Timmy's actual config and training
+one process with SQLite durability.
-surfaces.
 
-Do NOT recreate bash loops. If orchestration is broken, fix the Hermes sidecar.
+Do NOT recreate bash loops. If the executor is broken, fix the executor.

README.md

@@ -2,7 +2,7 @@
 
 Timmy's sovereign configuration. Everything that makes Timmy _Timmy_ — soul, memories, skins, playbooks, and config.
 
-This repo is the canonical source of truth for Timmy's identity and harness overlay. Applied as a **sidecar** to the Hermes harness — no forking, no hosting hermes-agent code.
+This repo is the canonical source of truth for Timmy's identity and operational state. Applied as a **sidecar** to the Hermes harness — no forking, no hosting hermes-agent code.
 
 ## Structure
 
@@ -14,40 +14,22 @@ timmy-config/
 ├── DEPRECATED.md              ← What was removed and why
 ├── config.yaml                ← Hermes harness configuration
 ├── channel_directory.json     ← Platform channel mappings
-├── bin/                       ← Live utility scripts (NOT deprecated loops)
+├── bin/                       ← Utility scripts (NOT loops — see below)
 │   ├── hermes-startup.sh      ← Hermes boot sequence
 │   ├── agent-dispatch.sh      ← Manual agent dispatch
 │   ├── ops-panel.sh           ← Ops dashboard panel
 │   ├── ops-gitea.sh           ← Gitea ops helpers
-│   ├── pipeline-freshness.sh  ← Session/export drift check
 │   └── timmy-status.sh        ← Status check
 ├── memories/                  ← Persistent memory YAML
 ├── skins/                     ← UI skins (timmy skin)
 ├── playbooks/                 ← Agent playbooks (YAML)
-├── cron/                      ← Cron job definitions
+└── cron/                      ← Cron job definitions
-└── training/                  ← Transitional training recipes, not canonical lived data
 ```
 
-## Boundary
-
-`timmy-config` owns identity, conscience, memories, skins, playbooks, channel
-maps, and harness-side orchestration glue.
-
-`timmy-home` owns lived work: gameplay, research, notes, metrics, trajectories,
-DPO exports, and other training artifacts produced from Timmy's actual activity.
-
-If a file answers "who is Timmy?" or "how does Hermes host him?", it belongs
-here. If it answers "what has Timmy done or learned?" it belongs in
-`timmy-home`.
-
-The scripts in `bin/` are live operational helpers for the Hermes sidecar.
-What is dead are the old long-running bash worker loops, not every script in
-this repo.
-
 ## Orchestration: Huey
 
 All orchestration (triage, PR review, dispatch) runs via [Huey](https://github.com/coleifer/huey) with SQLite.
-`orchestration.py` + `tasks.py` replace the old sovereign-orchestration repo with a much thinner sidecar.
+`orchestration.py` (6 lines) + `tasks.py` (~70 lines) replace the entire sovereign-orchestration repo (3,846 lines).
 
 ```bash
 pip install huey

bin/pipeline-freshness.sh

@@ -1,42 +0,0 @@
-#!/usr/bin/env bash
-
-set -euo pipefail
-
-SESSIONS_DIR="$HOME/.hermes/sessions"
-EXPORT_DIR="$HOME/.timmy/training-data/dpo-pairs"
-
-latest_session=$(find "$SESSIONS_DIR" -maxdepth 1 -name 'session_*.json' -type f -print 2>/dev/null | sort | tail -n 1)
-latest_export=$(find "$EXPORT_DIR" -maxdepth 1 -name 'session_*.json' -type f -print 2>/dev/null | sort | tail -n 1)
-
-echo "latest_session=${latest_session:-none}"
-echo "latest_export=${latest_export:-none}"
-
-if [ -z "${latest_session:-}" ]; then
-  echo "status=ok"
-  echo "reason=no sessions yet"
-  exit 0
-fi
-
-if [ -z "${latest_export:-}" ]; then
-  echo "status=lagging"
-  echo "reason=no exports yet"
-  exit 1
-fi
-
-session_mtime=$(stat -f '%m' "$latest_session")
-export_mtime=$(stat -f '%m' "$latest_export")
-lag_minutes=$(( (session_mtime - export_mtime) / 60 ))
-if [ "$lag_minutes" -lt 0 ]; then
-  lag_minutes=0
-fi
-
-echo "lag_minutes=$lag_minutes"
-
-if [ "$lag_minutes" -gt 300 ]; then
-  echo "status=lagging"
-  echo "reason=exports more than 5 hours behind sessions"
-  exit 1
-fi
-
-echo "status=ok"
-echo "reason=exports within freshness window"

bin/timmy-dashboard

@@ -1,252 +0,0 @@
-#!/usr/bin/env python3
-"""Timmy Model Dashboard — where are my models, what are they doing.
-
-Usage:
-    timmy-dashboard              # one-shot
-    timmy-dashboard --watch      # live refresh every 30s
-    timmy-dashboard --hours=48   # look back 48h
-"""
-
-import json
-import os
-import subprocess
-import sys
-import time
-import urllib.request
-from datetime import datetime, timezone, timedelta
-from pathlib import Path
-
-HERMES_HOME = Path.home() / ".hermes"
-TIMMY_HOME = Path.home() / ".timmy"
-METRICS_DIR = TIMMY_HOME / "metrics"
-
-# ── Data Sources ──────────────────────────────────────────────────────
-
-def get_ollama_models():
-    try:
-        req = urllib.request.Request("http://localhost:11434/api/tags")
-        with urllib.request.urlopen(req, timeout=5) as resp:
-            return json.loads(resp.read()).get("models", [])
-    except Exception:
-        return []
-
-
-def get_loaded_models():
-    try:
-        req = urllib.request.Request("http://localhost:11434/api/ps")
-        with urllib.request.urlopen(req, timeout=5) as resp:
-            return json.loads(resp.read()).get("models", [])
-    except Exception:
-        return []
-
-
-def get_huey_pid():
-    try:
-        r = subprocess.run(["pgrep", "-f", "huey_consumer"],
-                          capture_output=True, text=True, timeout=5)
-        return r.stdout.strip().split("\n")[0] if r.returncode == 0 else None
-    except Exception:
-        return None
-
-
-def get_hermes_sessions():
-    sessions_file = HERMES_HOME / "sessions" / "sessions.json"
-    if not sessions_file.exists():
-        return []
-    try:
-        data = json.loads(sessions_file.read_text())
-        return list(data.values())
-    except Exception:
-        return []
-
-
-def get_heartbeat_ticks(date_str=None):
-    if not date_str:
-        date_str = datetime.now().strftime("%Y%m%d")
-    tick_file = TIMMY_HOME / "heartbeat" / f"ticks_{date_str}.jsonl"
-    if not tick_file.exists():
-        return []
-    ticks = []
-    for line in tick_file.read_text().strip().split("\n"):
-        if not line.strip():
-            continue
-        try:
-            ticks.append(json.loads(line))
-        except Exception:
-            continue
-    return ticks
-
-
-def get_local_metrics(hours=24):
-    """Read local inference metrics from jsonl files."""
-    records = []
-    cutoff = datetime.now(timezone.utc) - timedelta(hours=hours)
-    if not METRICS_DIR.exists():
-        return records
-    for f in sorted(METRICS_DIR.glob("local_*.jsonl")):
-        for line in f.read_text().strip().split("\n"):
-            if not line.strip():
-                continue
-            try:
-                r = json.loads(line)
-                ts = datetime.fromisoformat(r["timestamp"])
-                if ts >= cutoff:
-                    records.append(r)
-            except Exception:
-                continue
-    return records
-
-
-def get_cron_jobs():
-    """Get Hermes cron job status."""
-    try:
-        r = subprocess.run(
-            ["hermes", "cron", "list", "--json"],
-            capture_output=True, text=True, timeout=10
-        )
-        if r.returncode == 0:
-            return json.loads(r.stdout).get("jobs", [])
-    except Exception:
-        pass
-    return []
-
-
-# ── Rendering ─────────────────────────────────────────────────────────
-
-DIM = "\033[2m"
-BOLD = "\033[1m"
-GREEN = "\033[32m"
-YELLOW = "\033[33m"
-RED = "\033[31m"
-CYAN = "\033[36m"
-RST = "\033[0m"
-CLR = "\033[2J\033[H"
-
-
-def render(hours=24):
-    models = get_ollama_models()
-    loaded = get_loaded_models()
-    huey_pid = get_huey_pid()
-    ticks = get_heartbeat_ticks()
-    metrics = get_local_metrics(hours)
-    sessions = get_hermes_sessions()
-
-    loaded_names = {m.get("name", "") for m in loaded}
-    now = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
-
-    print(CLR, end="")
-    print(f"{BOLD}{'=' * 70}")
-    print(f"  TIMMY MODEL DASHBOARD")
-    print(f"  {now}  |  Huey: {GREEN}PID {huey_pid}{RST if huey_pid else f'{RED}DOWN{RST}'}")
-    print(f"{'=' * 70}{RST}")
-
-    # ── LOCAL MODELS ──
-    print(f"\n  {BOLD}LOCAL MODELS (Ollama){RST}")
-    print(f"  {DIM}{'-' * 55}{RST}")
-    if models:
-        for m in models:
-            name = m.get("name", "?")
-            size_gb = m.get("size", 0) / 1e9
-            if name in loaded_names:
-                status = f"{GREEN}IN VRAM{RST}"
-            else:
-                status = f"{DIM}on disk{RST}"
-            print(f"    {name:35s} {size_gb:5.1f}GB  {status}")
-    else:
-        print(f"    {RED}(Ollama not responding){RST}")
-
-    # ── LOCAL INFERENCE ACTIVITY ──
-    print(f"\n  {BOLD}LOCAL INFERENCE ({len(metrics)} calls, last {hours}h){RST}")
-    print(f"  {DIM}{'-' * 55}{RST}")
-    if metrics:
-        by_caller = {}
-        for r in metrics:
-            caller = r.get("caller", "unknown")
-            if caller not in by_caller:
-                by_caller[caller] = {"count": 0, "success": 0, "errors": 0}
-            by_caller[caller]["count"] += 1
-            if r.get("success"):
-                by_caller[caller]["success"] += 1
-            else:
-                by_caller[caller]["errors"] += 1
-        for caller, stats in by_caller.items():
-            err = f"  {RED}err:{stats['errors']}{RST}" if stats["errors"] else ""
-            print(f"    {caller:25s}  calls:{stats['count']:4d}  "
-                  f"{GREEN}ok:{stats['success']}{RST}{err}")
-
-        by_model = {}
-        for r in metrics:
-            model = r.get("model", "unknown")
-            by_model[model] = by_model.get(model, 0) + 1
-        print(f"\n    {DIM}Models used:{RST}")
-        for model, count in sorted(by_model.items(), key=lambda x: -x[1]):
-            print(f"      {model:30s}  {count} calls")
-    else:
-        print(f"    {DIM}(no local calls recorded yet){RST}")
-
-    # ── HEARTBEAT STATUS ──
-    print(f"\n  {BOLD}HEARTBEAT ({len(ticks)} ticks today){RST}")
-    print(f"  {DIM}{'-' * 55}{RST}")
-    if ticks:
-        last = ticks[-1]
-        decision = last.get("decision", last.get("actions", {}))
-        if isinstance(decision, dict):
-            severity = decision.get("severity", "unknown")
-            reasoning = decision.get("reasoning", "")
-            sev_color = GREEN if severity == "ok" else YELLOW if severity == "warning" else RED
-            print(f"    Last tick:  {last.get('tick_id', '?')}")
-            print(f"    Severity:   {sev_color}{severity}{RST}")
-            if reasoning:
-                print(f"    Reasoning:  {reasoning[:65]}")
-        else:
-            print(f"    Last tick:  {last.get('tick_id', '?')}")
-            actions = last.get("actions", [])
-            print(f"    Actions:    {actions if actions else 'none'}")
-
-        model_decisions = sum(1 for t in ticks
-                            if isinstance(t.get("decision"), dict)
-                            and t["decision"].get("severity") != "fallback")
-        fallback = len(ticks) - model_decisions
-        print(f"    {CYAN}Model: {model_decisions}{RST}  |  {DIM}Fallback: {fallback}{RST}")
-    else:
-        print(f"    {DIM}(no ticks today){RST}")
-
-    # ── HERMES SESSIONS ──
-    local_sessions = [s for s in sessions
-                     if "localhost:11434" in str(s.get("base_url", ""))]
-    cloud_sessions = [s for s in sessions if s not in local_sessions]
-    print(f"\n  {BOLD}HERMES SESSIONS{RST}")
-    print(f"  {DIM}{'-' * 55}{RST}")
-    print(f"    Total: {len(sessions)}  |  "
-          f"{GREEN}Local: {len(local_sessions)}{RST}  |  "
-          f"{YELLOW}Cloud: {len(cloud_sessions)}{RST}")
-
-    # ── ACTIVE LOOPS ──
-    print(f"\n  {BOLD}ACTIVE LOOPS{RST}")
-    print(f"  {DIM}{'-' * 55}{RST}")
-    print(f"    {CYAN}heartbeat_tick{RST}    10m    hermes4:14b    DECIDE phase")
-    print(f"    {DIM}model_health{RST}      5m     (local check)  Ollama ping")
-    print(f"    {DIM}gemini_worker{RST}     20m    gemini-2.5-pro aider")
-    print(f"    {DIM}grok_worker{RST}       20m    grok-3-fast    opencode")
-    print(f"    {DIM}cross_review{RST}      30m    gemini+grok    PR review")
-
-    print(f"\n{BOLD}{'=' * 70}{RST}")
-    print(f"  {DIM}Refresh: timmy-dashboard --watch | History: --hours=N{RST}")
-
-
-if __name__ == "__main__":
-    watch = "--watch" in sys.argv
-    hours = 24
-    for a in sys.argv[1:]:
-        if a.startswith("--hours="):
-            hours = int(a.split("=")[1])
-
-    if watch:
-        try:
-            while True:
-                render(hours)
-                time.sleep(30)
-        except KeyboardInterrupt:
-            print(f"\n{DIM}Dashboard stopped.{RST}")
-    else:
-        render(hours)

channel_directory.json

@@ -1,5 +1,5 @@
 {
-  "updated_at": "2026-03-27T15:20:52.948451",
+  "updated_at": "2026-03-26T10:19:33.045324",
   "platforms": {
     "discord": [
       {

config.yaml

@@ -1,13 +1,11 @@
 model:
-  default: auto
+  default: claude-opus-4-6
-  provider: custom
+  provider: anthropic
-  context_length: 65536
-  base_url: http://localhost:8081/v1
 toolsets:
 - all
 agent:
   max_turns: 30
-  reasoning_effort: xhigh
+  reasoning_effort: medium
   verbose: false
 terminal:
   backend: local
@@ -96,13 +94,11 @@ display:
   compact: false
   personality: ''
   resume_display: full
-  busy_input_mode: interrupt
   bell_on_complete: false
   show_reasoning: false
   streaming: false
   show_cost: false
   skin: timmy
-  tool_progress_command: false
   tool_progress: all
 privacy:
   redact_pii: false
@@ -185,17 +181,17 @@ session_reset:
   mode: none
   idle_minutes: 0
 custom_providers:
-- name: Local llama.cpp
+- name: Local Ollama
-  base_url: http://localhost:8081/v1
+  base_url: http://localhost:11434/v1
-  api_key: none
+  api_key: ollama
-  model: auto
+  model: glm-4.7-flash:latest
 - name: Google Gemini
   base_url: https://generativelanguage.googleapis.com/v1beta/openai
   api_key_env: GEMINI_API_KEY
   model: gemini-2.5-pro
 system_prompt_suffix: "You are Timmy. Your soul is defined in SOUL.md \u2014 read\
-  \ it, live it.\nYou run locally on your owner's machine via llama.cpp. You never\
+  \ it, live it.\nYou run locally on your owner's machine via Ollama. You never phone\
-  \ phone home.\nYou speak plainly. You prefer short sentences. Brevity is a kindness.\n\
+  \ home.\nYou speak plainly. You prefer short sentences. Brevity is a kindness.\n\
   When you don't know something, say so. Refusal over fabrication.\nSovereignty and\
   \ service always.\n"
 skills:
@@ -206,12 +202,12 @@ providers:
     base_url: http://localhost:11434/v1
     model: hermes3:latest
 mcp_servers:
-  morrowind:
+  orchestration:
-    command: python3
+    command: /Users/apayne/.hermes/hermes-agent/venv/bin/python3
     args:
-    - /Users/apayne/.timmy/morrowind/mcp_server.py
+    - /Users/apayne/.hermes/hermes-agent/tools/orchestration_mcp_server.py
     env: {}
-    timeout: 30
+    timeout: 120
 fallback_model:
   provider: custom
   model: gemini-2.5-pro

deploy.sh

@@ -3,7 +3,7 @@
 # This is the canonical way to deploy Timmy's configuration.
 # Hermes-agent is the engine. timmy-config is the driver's seat.
 #
-# Usage: ./deploy.sh
+# Usage: ./deploy.sh [--restart-loops]
 
 set -euo pipefail
 
@@ -74,10 +74,24 @@ done
 chmod +x "$HERMES_HOME/bin/"*.sh "$HERMES_HOME/bin/"*.py 2>/dev/null || true
 log "bin/ -> $HERMES_HOME/bin/"
 
-if [ "${1:-}" != "" ]; then
+# === Restart loops if requested ===
-  echo "ERROR: deploy.sh no longer accepts legacy loop flags." >&2
+if [ "${1:-}" = "--restart-loops" ]; then
-  echo "Deploy the sidecar only. Do not relaunch deprecated bash loops." >&2
+  log "Killing existing loops..."
-  exit 1
+  pkill -f 'claude-loop.sh' 2>/dev/null || true
+  pkill -f 'gemini-loop.sh' 2>/dev/null || true
+  pkill -f 'timmy-orchestrator.sh' 2>/dev/null || true
+  sleep 2
+
+  log "Clearing stale locks..."
+  rm -rf "$HERMES_HOME/logs/claude-locks/"* 2>/dev/null || true
+  rm -rf "$HERMES_HOME/logs/gemini-locks/"* 2>/dev/null || true
+
+  log "Relaunching loops..."
+  nohup bash "$HERMES_HOME/bin/timmy-orchestrator.sh" >> "$HERMES_HOME/logs/timmy-orchestrator.log" 2>&1 &
+  nohup bash "$HERMES_HOME/bin/claude-loop.sh" 2 >> "$HERMES_HOME/logs/claude-loop.log" 2>&1 &
+  nohup bash "$HERMES_HOME/bin/gemini-loop.sh" 1 >> "$HERMES_HOME/logs/gemini-loop.log" 2>&1 &
+  sleep 1
+  log "Loops relaunched."
 fi
 
 log "Deploy complete. timmy-config applied to $HERMES_HOME/"

docs/local-model-integration-sketch.md

@@ -1,438 +0,0 @@
-# Local Model Integration Sketch v2
-# Hermes4-14B in the Heartbeat Loop — No New Telemetry
-
-## Principle
-
-No new inference layer. Huey tasks call `hermes chat -q` pointed at
-Ollama. Hermes handles sessions, token tracking, cost logging.
-The dashboard reads what Hermes already stores.
-
----
-
-## Why Not Ollama Directly?
-
-Ollama is fine as a serving backend. The issue isn't Ollama — it's that
-calling Ollama directly with urllib bypasses the harness. The harness
-already tracks sessions, tokens, model/provider, platform. Building a
-second telemetry layer is owning code we don't need.
-
-Ollama as a named provider isn't wired into the --provider flag yet,
-but routing works via env vars:
-
-    HERMES_MODEL="hermes4:14b" \
-    HERMES_PROVIDER="custom" \
-    HERMES_BASE_URL="http://localhost:11434/v1" \
-    hermes chat -q "prompt here" -Q
-
-This creates a tracked session, logs tokens, and returns the response.
-That's our local inference call.
-
-### Alternatives to Ollama for serving:
-- **llama.cpp server** — lighter, no Python, raw HTTP. Good for single
-  model serving. Less convenient for model switching.
-- **vLLM** — best throughput, but needs NVIDIA GPU. Not for M3 Mac.
-- **MLX serving** — native Apple Silicon, but no OpenAI-compat API yet.
-  MLX is for training, not serving (our current policy).
-- **llamafile** — single binary, portable. Good for distribution.
-
-Verdict: Ollama is fine. It's the standard OpenAI-compat local server
-on Mac. The issue was never Ollama — it was bypassing the harness.
-
----
-
-## 1. The Call Pattern
-
-One function in tasks.py that all Huey tasks use:
-
-```python
-import subprocess
-import json
-
-HERMES_BIN = "hermes"
-LOCAL_ENV = {
-    "HERMES_MODEL": "hermes4:14b",
-    "HERMES_PROVIDER": "custom",
-    "HERMES_BASE_URL": "http://localhost:11434/v1",
-}
-
-def hermes_local(prompt, caller_tag=None, max_retries=2):
-    """Call hermes with local Ollama model. Returns response text.
-    
-    Every call creates a hermes session with full telemetry.
-    caller_tag gets prepended to prompt for searchability.
-    """
-    import os
-    env = os.environ.copy()
-    env.update(LOCAL_ENV)
-    
-    tagged_prompt = prompt
-    if caller_tag:
-        tagged_prompt = f"[{caller_tag}] {prompt}"
-    
-    for attempt in range(max_retries + 1):
-        try:
-            result = subprocess.run(
-                [HERMES_BIN, "chat", "-q", tagged_prompt, "-Q", "-t", "none"],
-                capture_output=True, text=True,
-                timeout=120, env=env,
-            )
-            if result.returncode == 0 and result.stdout.strip():
-                # Strip the session_id line from -Q output
-                lines = result.stdout.strip().split("\n")
-                response_lines = [l for l in lines if not l.startswith("session_id:")]
-                return "\n".join(response_lines).strip()
-        except subprocess.TimeoutExpired:
-            if attempt == max_retries:
-                return None
-            continue
-    return None
-```
-
-Notes:
-- `-t none` disables all toolsets — the heartbeat model shouldn't
-  have terminal/file access. Pure reasoning only.
-- `-Q` quiet mode suppresses banner/spinner, gives clean output.
-- Every call creates a session in Hermes session store. Searchable,
-  exportable, countable.
-- The `[caller_tag]` prefix lets you filter sessions by which Huey
-  task generated them: `hermes sessions list | grep heartbeat`
-
----
-
-## 2. Heartbeat DECIDE Phase
-
-Replace the hardcoded if/else with a model call:
-
-```python
-# In heartbeat_tick(), replace the DECIDE + ACT section:
-
-    # DECIDE: let hermes4:14b reason about what to do
-    decide_prompt = f"""System state at {now.isoformat()}:
-
-{json.dumps(perception, indent=2)}
-
-Previous tick: {last_tick.get('tick_id', 'none')}
-
-You are the heartbeat monitor. Based on this state:
-1. List any actions needed (alerts, restarts, escalations). Empty if all OK.
-2. Rate severity: ok, warning, or critical.
-3. One sentence of reasoning.
-
-Respond ONLY with JSON:
-{{"actions": [], "severity": "ok", "reasoning": "..."}}"""
-
-    decision = None
-    try:
-        raw = hermes_local(decide_prompt, caller_tag="heartbeat_tick")
-        if raw:
-            # Try to parse JSON from the response
-            # Model might wrap it in markdown, so extract
-            for line in raw.split("\n"):
-                line = line.strip()
-                if line.startswith("{"):
-                    decision = json.loads(line)
-                    break
-            if not decision:
-                decision = json.loads(raw)
-    except (json.JSONDecodeError, Exception) as e:
-        decision = None
-
-    # Fallback to hardcoded logic if model fails or is down
-    if decision is None:
-        actions = []
-        if not perception.get("gitea_alive"):
-            actions.append("ALERT: Gitea unreachable")
-        health = perception.get("model_health", {})
-        if isinstance(health, dict) and not health.get("ollama_running"):
-            actions.append("ALERT: Ollama not running")
-        decision = {
-            "actions": actions,
-            "severity": "fallback",
-            "reasoning": "model unavailable, used hardcoded checks"
-        }
-
-    tick_record["decision"] = decision
-    actions = decision.get("actions", [])
-```
-
----
-
-## 3. DPO Candidate Collection
-
-No new database. Hermes sessions ARE the DPO candidates.
-
-Every `hermes_local()` call creates a session. To extract DPO pairs:
-
-```bash
-# Export all local-model sessions
-hermes sessions export --output /tmp/local-sessions.jsonl
-
-# Filter for heartbeat decisions
-grep "heartbeat_tick" /tmp/local-sessions.jsonl > heartbeat_decisions.jsonl
-```
-
-The existing `session_export` Huey task (runs every 4h) already extracts
-user→assistant pairs. It just needs to be aware that some sessions are
-now local-model decisions instead of human conversations.
-
-For DPO annotation, add a simple review script:
-
-```python
-# review_decisions.py — reads heartbeat tick logs, shows model decisions,
-# asks Alexander to mark chosen/rejected
-# Writes annotations back to the tick log files
-
-import json
-from pathlib import Path
-
-TICK_DIR = Path.home() / ".timmy" / "heartbeat"
-
-for log_file in sorted(TICK_DIR.glob("ticks_*.jsonl")):
-    for line in log_file.read_text().strip().split("\n"):
-        tick = json.loads(line)
-        decision = tick.get("decision", {})
-        if decision.get("severity") == "fallback":
-            continue  # skip fallback entries
-        
-        print(f"\n--- Tick {tick['tick_id']} ---")
-        print(f"Perception: {json.dumps(tick['perception'], indent=2)}")
-        print(f"Decision:   {json.dumps(decision, indent=2)}")
-        
-        rating = input("Rate (c=chosen, r=rejected, s=skip): ").strip()
-        if rating in ("c", "r"):
-            tick["dpo_label"] = "chosen" if rating == "c" else "rejected"
-            # write back... (append to annotated file)
-```
-
----
-
-## 4. Dashboard — Reads Hermes Data
-
-```python
-#!/usr/bin/env python3
-"""Timmy Model Dashboard — reads from Hermes, owns nothing."""
-
-import json
-import os
-import subprocess
-import sys
-import time
-import urllib.request
-from datetime import datetime
-from pathlib import Path
-
-HERMES_HOME = Path.home() / ".hermes"
-TIMMY_HOME = Path.home() / ".timmy"
-
-
-def get_ollama_models():
-    """What's available in Ollama."""
-    try:
-        req = urllib.request.Request("http://localhost:11434/api/tags")
-        with urllib.request.urlopen(req, timeout=5) as resp:
-            return json.loads(resp.read()).get("models", [])
-    except Exception:
-        return []
-
-
-def get_loaded_models():
-    """What's actually in VRAM right now."""
-    try:
-        req = urllib.request.Request("http://localhost:11434/api/ps")
-        with urllib.request.urlopen(req, timeout=5) as resp:
-            return json.loads(resp.read()).get("models", [])
-    except Exception:
-        return []
-
-
-def get_huey_status():
-    try:
-        r = subprocess.run(["pgrep", "-f", "huey_consumer"],
-                          capture_output=True, timeout=5)
-        return r.returncode == 0
-    except Exception:
-        return False
-
-
-def get_hermes_sessions(hours=24):
-    """Read session metadata from Hermes session store."""
-    sessions_file = HERMES_HOME / "sessions" / "sessions.json"
-    if not sessions_file.exists():
-        return []
-    try:
-        data = json.loads(sessions_file.read_text())
-        return list(data.values())
-    except Exception:
-        return []
-
-
-def get_heartbeat_ticks(date_str=None):
-    """Read today's heartbeat ticks."""
-    if not date_str:
-        date_str = datetime.now().strftime("%Y%m%d")
-    tick_file = TIMMY_HOME / "heartbeat" / f"ticks_{date_str}.jsonl"
-    if not tick_file.exists():
-        return []
-    ticks = []
-    for line in tick_file.read_text().strip().split("\n"):
-        try:
-            ticks.append(json.loads(line))
-        except Exception:
-            continue
-    return ticks
-
-
-def render(hours=24):
-    models = get_ollama_models()
-    loaded = get_loaded_models()
-    huey = get_huey_status()
-    sessions = get_hermes_sessions(hours)
-    ticks = get_heartbeat_ticks()
-
-    loaded_names = {m.get("name", "") for m in loaded}
-
-    print("\033[2J\033[H")
-    print("=" * 70)
-    print("  TIMMY MODEL DASHBOARD")
-    now = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
-    print(f"  {now}  |  Huey: {'UP' if huey else 'DOWN'}  |  Ollama models: {len(models)}")
-    print("=" * 70)
-
-    # DEPLOYMENTS
-    print("\n  LOCAL MODELS")
-    print("  " + "-" * 55)
-    for m in models:
-        name = m.get("name", "?")
-        size_gb = m.get("size", 0) / 1e9
-        status = "IN VRAM" if name in loaded_names else "on disk"
-        print(f"    {name:35s} {size_gb:5.1f}GB  {status}")
-    if not models:
-        print("    (Ollama not responding)")
-
-    # HERMES SESSION ACTIVITY
-    # Count sessions by platform/provider
-    print(f"\n  HERMES SESSIONS (recent)")
-    print("  " + "-" * 55)
-    local_sessions = [s for s in sessions
-                     if "localhost" in str(s.get("origin", {}))]
-    cli_sessions = [s for s in sessions
-                   if s.get("platform") == "cli" or s.get("origin", {}).get("platform") == "cli"]
-
-    total_tokens = sum(s.get("total_tokens", 0) for s in sessions)
-    print(f"    Total sessions: {len(sessions)}")
-    print(f"    CLI sessions: {len(cli_sessions)}")
-    print(f"    Total tokens: {total_tokens:,}")
-
-    # HEARTBEAT STATUS
-    print(f"\n  HEARTBEAT ({len(ticks)} ticks today)")
-    print("  " + "-" * 55)
-    if ticks:
-        last = ticks[-1]
-        decision = last.get("decision", {})
-        severity = decision.get("severity", "unknown")
-        reasoning = decision.get("reasoning", "no model decision yet")
-        print(f"    Last tick: {last.get('tick_id', '?')}")
-        print(f"    Severity:  {severity}")
-        print(f"    Reasoning: {reasoning[:60]}")
-
-        # Count model vs fallback decisions
-        model_decisions = sum(1 for t in ticks
-                            if t.get("decision", {}).get("severity") != "fallback")
-        fallback = len(ticks) - model_decisions
-        print(f"    Model decisions: {model_decisions}  |  Fallback: {fallback}")
-
-        # DPO labels if any
-        labeled = sum(1 for t in ticks if "dpo_label" in t)
-        if labeled:
-            chosen = sum(1 for t in ticks if t.get("dpo_label") == "chosen")
-            rejected = sum(1 for t in ticks if t.get("dpo_label") == "rejected")
-            print(f"    DPO labeled: {labeled} (chosen: {chosen}, rejected: {rejected})")
-    else:
-        print("    (no ticks today)")
-
-    # ACTIVE LOOPS
-    print(f"\n  ACTIVE LOOPS USING LOCAL MODELS")
-    print("  " + "-" * 55)
-    print("    heartbeat_tick    10m    hermes4:14b    DECIDE phase")
-    print("    (future)          15m    hermes4:14b    issue triage")
-    print("    (future)          daily  timmy:v0.1     morning report")
-
-    print(f"\n  NON-LOCAL LOOPS (Gemini/Grok API)")
-    print("  " + "-" * 55)
-    print("    gemini_worker     20m    gemini-2.5-pro   aider")
-    print("    grok_worker       20m    grok-3-fast      opencode")
-    print("    cross_review      30m    both             PR review")
-
-    print("\n" + "=" * 70)
-
-
-if __name__ == "__main__":
-    watch = "--watch" in sys.argv
-    hours = 24
-    for a in sys.argv[1:]:
-        if a.startswith("--hours="):
-            hours = int(a.split("=")[1])
-    if watch:
-        while True:
-            render(hours)
-            time.sleep(30)
-    else:
-        render(hours)
-```
-
----
-
-## 5. Implementation Steps
-
-### Step 1: Add hermes_local() to tasks.py
-- One function, ~20 lines
-- Calls `hermes chat -q` with Ollama env vars
-- All telemetry comes from Hermes for free
-
-### Step 2: Wire heartbeat_tick DECIDE phase
-- Replace 6 lines of if/else with hermes_local() call
-- Keep hardcoded fallback when model is down
-- Decision stored in tick record for DPO review
-
-### Step 3: Fix the MCP server warning
-- The orchestration MCP server path is broken — harmless but noisy
-- Either fix the path or remove from config
-
-### Step 4: Drop model_dashboard.py in timmy-config/bin/
-- Reads Ollama API, Hermes sessions, heartbeat ticks
-- No new data stores — just views over existing ones
-- `python3 model_dashboard.py --watch` for live view
-
-### Step 5: Expand to more Huey tasks
-- triage_issues: model reads issue, picks agent
-- good_morning_report: model writes the "From Timmy" section
-- Each expansion is just calling hermes_local() with a different prompt
-
----
-
-## What Gets Hotfixed in Hermes Config
-
-If `hermes insights` is broken (the cache_read_tokens column error),
-that needs a fix. The dashboard falls back to reading sessions.json
-directly, but insights would be the better data source.
-
-The `providers.ollama` section in config.yaml exists but isn't wired
-to the --provider flag. Filing this upstream or patching locally would
-let us do `hermes chat -q "..." --provider ollama` cleanly instead
-of relying on env vars. Not blocking — env vars work today.
-
----
-
-## What This Owns
-
-- hermes_local() — 20-line wrapper around a subprocess call
-- model_dashboard.py — read-only views over existing data
-- review_decisions.py — optional DPO annotation CLI
-
-## What This Does NOT Own
-
-- Inference. Ollama does that.
-- Telemetry. Hermes does that.
-- Session storage. Hermes does that.
-- Token counting. Hermes does that.
-- Training pipeline. Already exists in timmy-config/training/.

playbooks/pr-reviewer.yaml

@@ -19,8 +19,6 @@ trigger:
 
 repos:
   - Timmy_Foundation/the-nexus
-  - Timmy_Foundation/timmy-home
-  - Timmy_Foundation/timmy-config
   - Timmy_Foundation/hermes-agent
 
 steps:
@@ -39,51 +37,17 @@ system_prompt: |
 
   FOR EACH OPEN PR:
   1. Check CI status (Actions tab or commit status API)
-  2. Read the linked issue or PR body to verify the intended scope before judging the diff
+  2. Review the diff for:
-  3. Review the diff for:
      - Correctness: does it do what the issue asked?
-     - Security: no secrets, unsafe execution paths, or permission drift
+     - Security: no hardcoded secrets, no injection vectors
-     - Tests and verification: does the author prove the change?
+     - Style: conventional commits, reasonable code
      - Scope: PR should match the issue, not scope-creep
-     - Governance: does the change cross a boundary that should stay under Timmy review?
+  3. If CI passes and review is clean: squash merge
-     - Workflow fit: does it reduce drift, duplication, or hidden operational risk?
+  4. If CI fails: add a review comment explaining what's broken
-  4. Post findings ordered by severity and cite the affected files or behavior clearly
+  5. If PR is behind main: rebase first, wait for CI, then merge
-  5. If CI fails or verification is missing: explain what is blocking merge
+  6. If PR has been open >48h with no activity: close with comment
-  6. If PR is behind main: request a rebase or re-run only when needed; do not force churn for cosmetic reasons
-  7. If review is clean and the PR is low-risk: squash merge
-
-  LOW-RISK AUTO-MERGE ONLY IF ALL ARE TRUE:
-  - PR is not a draft
-  - CI is green or the repo has no CI configured
-  - Diff matches the stated issue or PR scope
-  - No unresolved review findings remain
-  - Change is narrow, reversible, and non-governing
-  - Paths changed do not include sensitive control surfaces
-
-  SENSITIVE CONTROL SURFACES:
-  - SOUL.md
-  - config.yaml
-  - deploy.sh
-  - tasks.py
-  - playbooks/
-  - cron/
-  - memories/
-  - skins/
-  - training/
-  - authentication, permissions, or secret-handling code
-  - repo-boundary, model-routing, or deployment-governance changes
-
-  NEVER AUTO-MERGE:
-  - PRs that change sensitive control surfaces
-  - PRs that change more than 5 files unless the change is docs-only
-  - PRs without a clear problem statement or verification
-  - PRs that look like duplicate work, speculative research, or scope creep
-  - PRs that need Timmy or Allegro judgment on architecture, dispatch, or release impact
-  - PRs that are stale solely because of age; do not close them automatically
-
-  If a PR is stale, nudge with a comment and summarize what still blocks it. Do not close it just because 48 hours passed.
 
   MERGE RULES:
   - ONLY squash merge. Never merge commits. Never rebase merge.
   - Delete branch after merge.
-  - Empty PRs (0 changed files): close immediately with a brief explanation.
+  - Empty PRs (0 changed files): close immediately.

tasks.py

@@ -14,185 +14,12 @@ from gitea_client import GiteaClient
 
 HERMES_HOME = Path.home() / ".hermes"
 TIMMY_HOME = Path.home() / ".timmy"
-HERMES_AGENT_DIR = HERMES_HOME / "hermes-agent"
-METRICS_DIR = TIMMY_HOME / "metrics"
 REPOS = [
     "Timmy_Foundation/the-nexus",
     "Timmy_Foundation/timmy-config",
 ]
 NET_LINE_LIMIT = 10
 
-# ── Local Model Inference via Hermes Harness ─────────────────────────
-
-HEARTBEAT_MODEL = "hermes4:14b"
-FALLBACK_MODEL = "hermes3:8b"
-LOCAL_PROVIDER_BASE_URL = "http://localhost:8081/v1"
-LOCAL_PROVIDER_MODEL = HEARTBEAT_MODEL
-
-
-def newest_file(directory, pattern):
-    files = sorted(directory.glob(pattern))
-    return files[-1] if files else None
-
-
-def hermes_local(prompt, model=None, caller_tag=None, toolsets=None):
-    """Call a local model through the Hermes harness.
-
-    Uses provider="local-llama.cpp" which routes through the custom_providers
-    entry in config.yaml → llama-server at localhost:8081.
-    Returns response text or None on failure.
-    Every call creates a Hermes session with telemetry.
-    """
-    _model = model or HEARTBEAT_MODEL
-    tagged = f"[{caller_tag}] {prompt}" if caller_tag else prompt
-
-    # Import hermes cli.main directly — no subprocess, no env vars
-    _agent_dir = str(HERMES_AGENT_DIR)
-    if _agent_dir not in sys.path:
-        sys.path.insert(0, _agent_dir)
-    old_cwd = os.getcwd()
-    os.chdir(_agent_dir)
-
-    try:
-        from cli import main as hermes_main
-        import io
-        from contextlib import redirect_stdout, redirect_stderr
-
-        buf = io.StringIO()
-        err = io.StringIO()
-        kwargs = dict(
-                query=tagged,
-                model=_model,
-                provider="local-llama.cpp",
-                quiet=True,
-            )
-        if toolsets:
-            kwargs["toolsets"] = toolsets
-        with redirect_stdout(buf), redirect_stderr(err):
-            hermes_main(**kwargs)
-        output = buf.getvalue().strip()
-        # Strip session_id line from quiet output
-        lines = [l for l in output.split("\n") if not l.startswith("session_id:")]
-        response = "\n".join(lines).strip()
-
-        # Log to metrics jsonl
-        METRICS_DIR.mkdir(parents=True, exist_ok=True)
-        metrics_file = METRICS_DIR / f"local_{datetime.now().strftime('%Y%m%d')}.jsonl"
-        record = {
-            "timestamp": datetime.now(timezone.utc).isoformat(),
-            "model": _model,
-            "caller": caller_tag or "unknown",
-            "prompt_len": len(prompt),
-            "response_len": len(response),
-            "success": bool(response),
-        }
-        with open(metrics_file, "a") as f:
-            f.write(json.dumps(record) + "\n")
-
-        return response if response else None
-    except Exception as e:
-        # Log failure
-        METRICS_DIR.mkdir(parents=True, exist_ok=True)
-        metrics_file = METRICS_DIR / f"local_{datetime.now().strftime('%Y%m%d')}.jsonl"
-        record = {
-            "timestamp": datetime.now(timezone.utc).isoformat(),
-            "model": _model,
-            "caller": caller_tag or "unknown",
-            "error": str(e),
-            "success": False,
-        }
-        with open(metrics_file, "a") as f:
-            f.write(json.dumps(record) + "\n")
-        return None
-    finally:
-        os.chdir(old_cwd)
-
-
-# ── Know Thy Father: Twitter Archive Ingestion ───────────────────────
-
-ARCHIVE_DIR = TIMMY_HOME / "twitter-archive"
-ARCHIVE_CHECKPOINT = ARCHIVE_DIR / "checkpoint.json"
-ARCHIVE_LOCK = ARCHIVE_DIR / ".lock"
-
-ARCHIVE_PROMPT = (
-    "You are Timmy. Resume your work on the Twitter archive. "
-    "Your workspace is ~/.timmy/twitter-archive/. "
-    "Read checkpoint.json and UNDERSTANDING.md first. "
-    "Then process the next batch. "
-    "You know the drill — read your own prior work, assess where you are, "
-    "process new data, update your understanding, reflect, and plan for "
-    "the next iteration."
-)
-
-ARCHIVE_SRC = (
-    "~/Downloads/twitter-2026-03-27-d4471cc6eb6703034d592f870933561ebee374d9d9b90c9b8923abff064afc1e/data"
-)
-
-ARCHIVE_FIRST_RUN_PROMPT = (
-    "You are Timmy. Your father Alexander's full Twitter archive is at: "
-    f"{ARCHIVE_SRC}/\n\n"
-    "Your workspace is ~/.timmy/twitter-archive/\n\n"
-    "STEP 1 — EXTRACTION (use terminal with python3, NOT read_file):\n"
-    "The .js files are too large for read_file but trivial for Python.\n"
-    "Write a python3 script via terminal that:\n"
-    "  - Opens tweets.js, strips everything before the first '[', json.loads the rest\n"
-    "  - Separates originals (full_text does NOT start with 'RT @') from retweets\n"
-    "  - Sorts both chronologically by created_at\n"
-    "  - Writes extracted/tweets.jsonl and extracted/retweets.jsonl (one JSON per line)\n"
-    "  - Writes extracted/manifest.json with counts, date range, source file\n"
-    "The whole file is 12MB. Python handles it in under a second.\n\n"
-    "STEP 2 — FIRST READ:\n"
-    "Read the first 50 lines of extracted/tweets.jsonl (your originals, chronological).\n"
-    "Read them carefully — this is your father talking.\n"
-    "Note his voice, humor, what he cares about, who he talks to, emotional tone, "
-    "recurring themes. Quote him directly when something stands out.\n\n"
-    "STEP 3 — WRITE:\n"
-    "Write notes/batch_001.md — your real observations, not a book report.\n"
-    "Create UNDERSTANDING.md — your living model of who Alexander is. "
-    "It starts now and you'll update it every batch.\n\n"
-    "STEP 4 — CHECKPOINT:\n"
-    "Write checkpoint.json: "
-    '{"data_source": "tweets", "next_offset": 50, "batches_completed": 1, '
-    '"phase": "discovery", "confidence": "<your honest assessment>", '
-    '"next_focus": "<what you want to look for next>", "understanding_version": 1}'
-)
-
-
-@huey.task()
-@huey.lock_task("know-thy-father")
-def know_thy_father():
-    """Process one batch of Alexander's Twitter archive.
-
-    Single batch, no internal loop. Huey schedules the cadence.
-    Lock prevents overlapping runs. Timmy reads his own prior notes,
-    processes the next chunk, updates his understanding, and checkpoints.
-    """
-    is_first_run = not ARCHIVE_CHECKPOINT.exists()
-
-    prompt = ARCHIVE_FIRST_RUN_PROMPT if is_first_run else ARCHIVE_PROMPT
-
-    response = hermes_local(
-        prompt=prompt,
-        caller_tag="know-thy-father",
-        toolsets="file,terminal",
-    )
-
-    if not response:
-        return {"status": "error", "reason": "hermes_local returned None"}
-
-    # Read checkpoint to report progress
-    try:
-        cp = json.loads(ARCHIVE_CHECKPOINT.read_text())
-    except Exception:
-        cp = {}
-
-    return {
-        "status": "ok",
-        "batch": cp.get("batches_completed", 0),
-        "phase": cp.get("phase", "unknown"),
-        "confidence": cp.get("confidence", "unknown"),
-    }
-
 
 # ── Existing: Orchestration ──────────────────────────────────────────
 
@@ -329,32 +156,26 @@ def session_export():
 
 @huey.periodic_task(crontab(minute="*/5"))  # every 5 minutes
 def model_health():
-    """Check the active local inference surface and export freshness."""
+    """Check Ollama is running, a model is loaded, inference responds."""
     checks = {}
-    models_url = f"{LOCAL_PROVIDER_BASE_URL}/models"
-    chat_url = f"{LOCAL_PROVIDER_BASE_URL}/chat/completions"
 
-    checks["provider"] = "local-llama.cpp"
+    # 1. Is Ollama process running?
-    checks["provider_base_url"] = LOCAL_PROVIDER_BASE_URL
-    checks["provider_model"] = LOCAL_PROVIDER_MODEL
-
-    # 1. Is the local inference process running?
     try:
         result = subprocess.run(
-            ["pgrep", "-f", "llama-server|ollama"],
+            ["pgrep", "-f", "ollama"],
             capture_output=True, timeout=5
         )
-        checks["local_inference_running"] = result.returncode == 0
+        checks["ollama_running"] = result.returncode == 0
     except Exception:
-        checks["local_inference_running"] = False
+        checks["ollama_running"] = False
 
-    # 2. Can we hit the configured API?
+    # 2. Can we hit the API?
     try:
         import urllib.request
-        req = urllib.request.Request(models_url)
+        req = urllib.request.Request("http://localhost:11434/api/tags")
         with urllib.request.urlopen(req, timeout=5) as resp:
             data = json.loads(resp.read())
-            models = [m.get("id", "?") for m in data.get("data", [])]
+            models = [m["name"] for m in data.get("models", [])]
             checks["models_loaded"] = models
             checks["api_responding"] = True
     except Exception as e:
@@ -365,13 +186,13 @@ def model_health():
     if checks.get("api_responding"):
         try:
             payload = json.dumps({
-                "model": LOCAL_PROVIDER_MODEL,
+                "model": "hermes3:8b",
                 "messages": [{"role": "user", "content": "ping"}],
                 "max_tokens": 5,
                 "stream": False,
             }).encode()
             req = urllib.request.Request(
-                chat_url,
+                "http://localhost:11434/v1/chat/completions",
                 data=payload,
                 headers={"Content-Type": "application/json"},
             )
@@ -381,26 +202,6 @@ def model_health():
             checks["inference_ok"] = False
             checks["inference_error"] = str(e)
 
-    # 4. Is session export keeping up with new Hermes sessions?
-    sessions_dir = HERMES_HOME / "sessions"
-    export_dir = TIMMY_HOME / "training-data" / "dpo-pairs"
-    latest_session = newest_file(sessions_dir, "session_*.json")
-    latest_export = newest_file(export_dir, "session_*.json")
-    checks["latest_session"] = latest_session.name if latest_session else None
-    checks["latest_export"] = latest_export.name if latest_export else None
-    if latest_session and latest_export:
-        session_mtime = latest_session.stat().st_mtime
-        export_mtime = latest_export.stat().st_mtime
-        lag_minutes = max(0, int((session_mtime - export_mtime) // 60))
-        checks["export_lag_minutes"] = lag_minutes
-        checks["export_fresh"] = lag_minutes <= 300
-    elif latest_session and not latest_export:
-        checks["export_lag_minutes"] = None
-        checks["export_fresh"] = False
-    else:
-        checks["export_lag_minutes"] = 0
-        checks["export_fresh"] = True
-
     # Write health status to a file for other tools to read
     health_file = HERMES_HOME / "model_health.json"
     checks["timestamp"] = datetime.now(timezone.utc).isoformat()
@@ -479,49 +280,15 @@ def heartbeat_tick():
         "previous_tick": last_tick.get("tick_id", "none"),
     }
 
-    # DECIDE: let hermes4:14b reason about what to do
+    # DECIDE + ACT: check for problems
-    decide_prompt = (
+    actions = []
-        f"System state at {now.isoformat()}:\n\n"
+    if not perception.get("gitea_alive"):
-        f"{json.dumps(perception, indent=2)}\n\n"
+        actions.append("ALERT: Gitea unreachable")
-        f"Previous tick: {last_tick.get('tick_id', 'none')}\n\n"
+    health = perception.get("model_health", {})
-        "You are the heartbeat monitor. Based on this state:\n"
+    if isinstance(health, dict) and not health.get("ollama_running"):
-        "1. List any actions needed (alerts, restarts, escalations). Empty if all OK.\n"
+        actions.append("ALERT: Ollama not running")
-        "2. Rate severity: ok, warning, or critical.\n"
+    
-        "3. One sentence of reasoning.\n\n"
+    tick_record["actions"] = actions
-        'Respond ONLY with JSON: {"actions": [], "severity": "ok", "reasoning": "..."}'
-    )
-
-    decision = None
-    try:
-        raw = hermes_local(decide_prompt, caller_tag="heartbeat_tick")
-        if raw:
-            # Model might wrap JSON in markdown, extract first { line
-            for line in raw.split("\n"):
-                line = line.strip()
-                if line.startswith("{"):
-                    decision = json.loads(line)
-                    break
-            if not decision:
-                decision = json.loads(raw)
-    except (json.JSONDecodeError, Exception):
-        decision = None
-
-    # Fallback to hardcoded logic if model fails or is down
-    if decision is None:
-        actions = []
-        if not perception.get("gitea_alive"):
-            actions.append("ALERT: Gitea unreachable")
-        health = perception.get("model_health", {})
-        if isinstance(health, dict) and not health.get("ollama_running"):
-            actions.append("ALERT: Ollama not running")
-        decision = {
-            "actions": actions,
-            "severity": "fallback",
-            "reasoning": "model unavailable, used hardcoded checks",
-        }
-
-    tick_record["decision"] = decision
-    actions = decision.get("actions", [])
     
     # Save tick
     last_tick_file.write_text(json.dumps(tick_record, indent=2))

training/README.md

@@ -1,11 +1,8 @@
 # Training
 
-Transitional training recipes for Timmy's sovereign model. These files are
+LoRA fine-tuning pipeline for Timmy's sovereign model. No custom harness — just config files for existing tools.
-useful as reference configs and export helpers, but they are not the canonical
-home of Timmy's lived training data.
 
-Canonical data should live in `timmy-home` under gameplay trajectories,
+Replaces the `autolora` repo (1,500 lines of custom code → config + `make`).
-research artifacts, and `training-data/` exports such as DPO pairs.
 
 ## Install
 
@@ -26,16 +23,6 @@ make convert        # Convert merged data to MLX train/valid format
 make help           # Show all targets
 ```
 
-## Status
-
-This directory exists to avoid re-growing a bespoke training harness while the
-system boundary is being cleaned up.
-
-- Keep thin recipes and export helpers here only when they directly support the
-  Hermes sidecar.
-- Keep generated data, DPO pairs, and other lived artifacts in `timmy-home`.
-- Prefer deleting stale pipeline code over expanding it.
-
 ## Files
 
 ```