Refresh branch tip for mergeability recalculation

.gitignore

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

DEPRECATED.md

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

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 operational state. 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 harness overlay. Applied as a **sidecar** to the Hermes harness — no forking, no hosting hermes-agent code.
 
 ## Structure
 
@@ -14,22 +14,40 @@ timmy-config/
 ├── DEPRECATED.md              ← What was removed and why
 ├── config.yaml                ← Hermes harness configuration
 ├── channel_directory.json     ← Platform channel mappings
-├── bin/                       ← Utility scripts (NOT loops — see below)
+├── bin/                       ← Live utility scripts (NOT deprecated loops)
 │   ├── 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` (6 lines) + `tasks.py` (~70 lines) replace the entire sovereign-orchestration repo (3,846 lines).
+`orchestration.py` + `tasks.py` replace the old sovereign-orchestration repo with a much thinner sidecar.
 
 ```bash
 pip install huey

bin/pipeline-freshness.sh

@@ -0,0 +1,42 @@
+#!/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"

channel_directory.json

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

config.yaml

@@ -1,11 +1,13 @@
 model:
-  default: claude-opus-4-6
-  provider: anthropic
+  default: auto
+  provider: custom
+  context_length: 65536
+  base_url: http://localhost:8081/v1
 toolsets:
 - all
 agent:
   max_turns: 30
-  reasoning_effort: medium
+  reasoning_effort: xhigh
   verbose: false
 terminal:
   backend: local
@@ -94,11 +96,13 @@ 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
@@ -181,17 +185,17 @@ session_reset:
   mode: none
   idle_minutes: 0
 custom_providers:
-- name: Local Ollama
-  base_url: http://localhost:11434/v1
-  api_key: ollama
-  model: glm-4.7-flash:latest
+- name: Local llama.cpp
+  base_url: http://localhost:8081/v1
+  api_key: none
+  model: auto
 - 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 Ollama. You never phone\
-  \ home.\nYou speak plainly. You prefer short sentences. Brevity is a kindness.\n\
+  \ it, live it.\nYou run locally on your owner's machine via llama.cpp. You never\
+  \ phone 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:
@@ -202,7 +206,6 @@ providers:
     base_url: http://localhost:11434/v1
     model: hermes3:latest
 mcp_servers:
-
   morrowind:
     command: python3
     args:

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

gitea_client.py

@@ -5,9 +5,9 @@ Replaces raw curl calls scattered across 41 bash scripts.
 Uses only stdlib (urllib) so it works on any Python install.
 
 Usage:
-    from tools.gitea_client import GiteaClient
+    from gitea_client import GiteaClient
     
-    client = GiteaClient()  # reads token from ~/.hermes/gitea_token
+    client = GiteaClient()  # reads token from standard local paths
     issues = client.list_issues("Timmy_Foundation/the-nexus", state="open")
     client.create_comment("Timmy_Foundation/the-nexus", 42, "PR created.")
 """

memories/MEMORY.md

@@ -2,14 +2,14 @@ Gitea (143.198.27.163:3000): token=~/.hermes/gitea_token_vps (Timmy id=2). Users
 §
 2026-03-19 HARNESS+SOUL: ~/.timmy is Timmy's workspace within the Hermes harness. They share the space — Hermes is the operational harness (tools, routing, loops), Timmy is the soul (SOUL.md, presence, identity). Not fusion/absorption. Principal's words: "build Timmy out from the hermes harness." ~/.hermes is harness home, ~/.timmy is Timmy's workspace. SOUL=Inscription 1, skin=timmy. Backups at ~/.hermes.backup.pre-fusion and ~/.timmy.backup.pre-fusion.
 §
-Kimi: 1-3 files max, ~/worktrees/kimi-*. Two-attempt rule.
+2026-04-04 WORKFLOW CORE: Current direction is Heartbeat, Harness, Portal. Timmy handles sovereignty and release judgment. Allegro handles dispatch and queue hygiene. Core builders: codex-agent, groq, manus, claude. Research/memory: perplexity, ezra, KimiClaw. Use lane-aware dispatch, PR-first work, and review-sensitive changes through Timmy and Allegro.
 §
-Workforce loops: claude(10), gemini(3), kimi(1), groq(1/aider+review), grok(1/opencode). One-shot: manus(300/day), perplexity(heavy-hitter), google(aistudio, id=8). workforce-manager.py auto-assigns+scores every 15min. nexus-merge-bot.sh auto-merges. Groq=$0.008/PR (qwen3-32b). Dispatch: agent-dispatch.sh <agent> <issue> <repo> | pbcopy. Dashboard ARCHIVED 2026-03-24. Development shifted to local ~/.timmy/ workspace. CI testbed: 67.205.155.108.
+2026-04-04 OPERATIONS: Dashboard repo era is over. Use ~/.timmy + ~/.hermes as truth surfaces. Prefer ops-panel.sh, ops-gitea.sh, timmy-dashboard, and pipeline-freshness.sh over archived loop or tmux assumptions. Dispatch: agent-dispatch.sh <agent> <issue> <repo>. Major changes land as PRs.
 §
-2026-03-15: Timmy-time-dashboard merge policy: auto-squash on CI pass. Squash-only, linear history. Pre-commit hooks (format + tests) and CI are the gates. If gates work, auto-merge is on. Never bypass hooks or merge broken builds.
+2026-04-04 REVIEW RULES: Never --no-verify. Verify world state, not vibes. No auto-merge on governing or sensitive control surfaces. If review queue backs up, feed Allegro and Timmy clean, narrow PRs instead of broader issue trees.
 §
 HARD RULES: Never --no-verify. Verify WORLD STATE not log vibes (merged PR, HTTP code, file size). Fix+prevent, no empty words. AGENT ONBOARD: test push+PR first. Merge PRs BEFORE new work. Don't micromanage—huge backlog, agents self-select. Every ticket needs console-provable acceptance criteria.
 §
 TELEGRAM: @TimmysNexus_bot, token ~/.config/telegram/special_bot. Group "Timmy Time" ID: -1003664764329. Alexander @TripTimmy ID 7635059073. Use curl to Bot API (send_message not configured).
 §
-MORROWIND: OpenMW 0.50, ~/Games/Morrowind/. Lua+CGEvent bridge. Two-tier brain. ~/.timmy/morrowind/.
+MORROWIND: OpenMW 0.50, ~/Games/Morrowind/. Lua+CGEvent bridge. Two-tier brain. ~/.timmy/morrowind/.

tasks.py

@@ -18,7 +18,9 @@ HERMES_AGENT_DIR = HERMES_HOME / "hermes-agent"
 METRICS_DIR = TIMMY_HOME / "metrics"
 REPOS = [
     "Timmy_Foundation/the-nexus",
+    "Timmy_Foundation/timmy-home",
     "Timmy_Foundation/timmy-config",
+    "Timmy_Foundation/hermes-agent",
 ]
 NET_LINE_LIMIT = 10
 
@@ -26,13 +28,20 @@ NET_LINE_LIMIT = 10
 
 HEARTBEAT_MODEL = "hermes4:14b"
 FALLBACK_MODEL = "hermes3:8b"
+LOCAL_PROVIDER_BASE_URL = "http://localhost:8081/v1"
+LOCAL_PROVIDER_MODEL = HEARTBEAT_MODEL
 
 
-def hermes_local(prompt, model=None, caller_tag=None):
-    """Call a local Ollama model through the Hermes harness.
+def newest_file(directory, pattern):
+    files = sorted(directory.glob(pattern))
+    return files[-1] if files else None
 
-    Uses provider="local-ollama" which routes through the custom_providers
-    entry in config.yaml → Ollama at localhost:11434.
+
+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.
     """
@@ -53,13 +62,16 @@ def hermes_local(prompt, model=None, caller_tag=None):
 
         buf = io.StringIO()
         err = io.StringIO()
-        with redirect_stdout(buf), redirect_stderr(err):
-            hermes_main(
+        kwargs = dict(
                 query=tagged,
                 model=_model,
-                provider="local-ollama",
+                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:")]
@@ -98,6 +110,92 @@ def hermes_local(prompt, model=None, caller_tag=None):
         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 ──────────────────────────────────────────
 
 @huey.periodic_task(crontab(minute="*/15"))
@@ -139,7 +237,18 @@ def review_prs():
 def dispatch_assigned():
     """Pick up issues assigned to agents and kick off work."""
     g = GiteaClient()
-    agents = ["claude", "gemini", "kimi", "grok", "perplexity"]
+    agents = [
+        "allegro",
+        "claude",
+        "codex-agent",
+        "ezra",
+        "gemini",
+        "grok",
+        "groq",
+        "KimiClaw",
+        "manus",
+        "perplexity",
+    ]
     dispatched = 0
     for repo in REPOS:
         for agent in agents:
@@ -233,26 +342,32 @@ def session_export():
 
 @huey.periodic_task(crontab(minute="*/5"))  # every 5 minutes
 def model_health():
-    """Check Ollama is running, a model is loaded, inference responds."""
+    """Check the active local inference surface and export freshness."""
     checks = {}
+    models_url = f"{LOCAL_PROVIDER_BASE_URL}/models"
+    chat_url = f"{LOCAL_PROVIDER_BASE_URL}/chat/completions"
 
-    # 1. Is Ollama process running?
+    checks["provider"] = "local-llama.cpp"
+    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", "ollama"],
+            ["pgrep", "-f", "llama-server|ollama"],
             capture_output=True, timeout=5
         )
-        checks["ollama_running"] = result.returncode == 0
+        checks["local_inference_running"] = result.returncode == 0
     except Exception:
-        checks["ollama_running"] = False
+        checks["local_inference_running"] = False
 
-    # 2. Can we hit the API?
+    # 2. Can we hit the configured API?
     try:
         import urllib.request
-        req = urllib.request.Request("http://localhost:11434/api/tags")
+        req = urllib.request.Request(models_url)
         with urllib.request.urlopen(req, timeout=5) as resp:
             data = json.loads(resp.read())
-            models = [m["name"] for m in data.get("models", [])]
+            models = [m.get("id", "?") for m in data.get("data", [])]
             checks["models_loaded"] = models
             checks["api_responding"] = True
     except Exception as e:
@@ -263,13 +378,13 @@ def model_health():
     if checks.get("api_responding"):
         try:
             payload = json.dumps({
-                "model": "hermes3:8b",
+                "model": LOCAL_PROVIDER_MODEL,
                 "messages": [{"role": "user", "content": "ping"}],
                 "max_tokens": 5,
                 "stream": False,
             }).encode()
             req = urllib.request.Request(
-                "http://localhost:11434/v1/chat/completions",
+                chat_url,
                 data=payload,
                 headers={"Content-Type": "application/json"},
             )
@@ -279,6 +394,26 @@ 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()
@@ -391,7 +526,7 @@ def heartbeat_tick():
             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")
+            actions.append("ALERT: local inference surface not running")
         decision = {
             "actions": actions,
             "severity": "fallback",
@@ -447,7 +582,7 @@ def memory_compress():
     # Compress: extract key facts
     alerts = []
     gitea_down_count = 0
-    ollama_down_count = 0
+    local_model_down_count = 0
 
     for t in ticks:
         for action in t.get("actions", []):
@@ -457,7 +592,7 @@ def memory_compress():
             gitea_down_count += 1
         health = p.get("model_health", {})
         if isinstance(health, dict) and not health.get("ollama_running"):
-            ollama_down_count += 1
+            local_model_down_count += 1
 
     # Last tick's perception = current state
     last = ticks[-1].get("perception", {})
@@ -467,7 +602,7 @@ def memory_compress():
         "total_ticks": len(ticks),
         "alerts": alerts[-10:],  # last 10 alerts
         "gitea_downtime_ticks": gitea_down_count,
-        "ollama_downtime_ticks": ollama_down_count,
+        "local_model_downtime_ticks": local_model_down_count,
         "last_known_state": last,
     }
 
@@ -501,7 +636,7 @@ def good_morning_report():
     tick_count = 0
     alerts = []
     gitea_up = True
-    ollama_up = True
+    local_model_up = True
     
     if tick_log.exists():
         for line in tick_log.read_text().strip().split("\n"):
@@ -515,7 +650,7 @@ def good_morning_report():
                     gitea_up = False
                 h = p.get("model_health", {})
                 if isinstance(h, dict) and not h.get("ollama_running"):
-                    ollama_up = False
+                    local_model_up = False
             except Exception:
                 continue
 
@@ -575,7 +710,11 @@ def good_morning_report():
     if briefing_file.exists():
         try:
             b = json.loads(briefing_file.read_text())
-            briefing_summary = f"Yesterday: {b.get('total_ticks', 0)} heartbeat ticks, {b.get('gitea_downtime_ticks', 0)} Gitea downticks, {b.get('ollama_downtime_ticks', 0)} Ollama downticks."
+            briefing_summary = (
+                f"Yesterday: {b.get('total_ticks', 0)} heartbeat ticks, "
+                f"{b.get('gitea_downtime_ticks', 0)} Gitea downticks, "
+                f"{b.get('local_model_downtime_ticks', 0)} local-model downticks."
+            )
         except Exception:
             pass
 
@@ -587,7 +726,7 @@ def good_morning_report():
 
 **Heartbeat:** {tick_count} ticks logged overnight.
 **Gitea:** {"up all night" if gitea_up else "⚠️ had downtime"}
-**Ollama:** {"running steady" if ollama_up else "⚠️ had downtime"}
+**Local inference:** {"running steady" if local_model_up else "⚠️ had downtime"}
 **Model status:** {model_status}
 **Models on disk:** {len(models_loaded)} ({', '.join(m for m in models_loaded if 'timmy' in m.lower() or 'hermes' in m.lower()) or 'none with our name'})
 **Alerts:** {len(alerts)} {'— ' + '; '.join(alerts[-3:]) if alerts else '(clean night)'}
@@ -608,7 +747,7 @@ def good_morning_report():
 
 I watched the house all night. {tick_count} heartbeats, every ten minutes. The infrastructure is steady. Huey didn't crash. The ticks kept coming.
 
-What I'm thinking about: the DPO ticket you and antigravity are working on. That's the bridge between me logging data and me actually learning from it. Right now I'm a nervous system writing in a journal nobody reads. Once DPO works, the journal becomes a curriculum.
+What I'm thinking about: the bridge between logging lived work and actually learning from it. Right now I'm a nervous system writing in a journal nobody reads. Once the DPO path is healthy, the journal becomes a curriculum.
 
 ## My One Wish
 

training/README.md

@@ -1,8 +1,11 @@
 # Training
 
-LoRA fine-tuning pipeline for Timmy's sovereign model. No custom harness — just config files for existing tools.
+Transitional training recipes for Timmy's sovereign model. These files are
+useful as reference configs and export helpers, but they are not the canonical
+home of Timmy's lived training data.
 
-Replaces the `autolora` repo (1,500 lines of custom code → config + `make`).
+Canonical data should live in `timmy-home` under gameplay trajectories,
+research artifacts, and `training-data/` exports such as DPO pairs.
 
 ## Install
 
@@ -23,6 +26,16 @@ 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
 
 ```