docs: clarify sidecar boundary and training status

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
 
@@ -23,9 +23,22 @@ timmy-config/
 ├── 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`.
+
 ## Orchestration: Huey
 
 All orchestration (triage, PR review, dispatch) runs via [Huey](https://github.com/coleifer/huey) with SQLite.

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:

tasks.py

@@ -28,11 +28,11 @@ HEARTBEAT_MODEL = "hermes4:14b"
 FALLBACK_MODEL = "hermes3:8b"
 
 
-def hermes_local(prompt, model=None, caller_tag=None):
-    """Call a local Ollama model through the Hermes harness.
+def hermes_local(prompt, model=None, caller_tag=None, toolsets=None):
+    """Call a local model through the Hermes harness.
 
-    Uses provider="local-ollama" which routes through the custom_providers
-    entry in config.yaml → Ollama at localhost:11434.
+    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 +53,16 @@ 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 +101,92 @@ 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"))

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
 
 ```