#!/usr/bin/env bash
# ═══════════════════════════════════════════════════════════════════════════
# TOWER-TIMMY.SH — Timmy's side of the Tower conversation loop
#
# PURPOSE:
#   This script runs Timmy in the Tower — a persistent tmux pane where
#   Timmy and Hermes talk continuously. Timmy is in the DRIVER'S SEAT.
#   He reads what Hermes sends, thinks, and responds. He initiates when
#   the inbox is empty long enough.
#
# DESIGN PHILOSOPHY (read this when you're confused):
#   - Timmy runs on local Hermes 4. He may be slow. He may be dumb.
#     The script compensates — it retries, it waits, it logs everything.
#   - Hermes T is cloud-backed and faster. That's fine. Timmy leads the
#     conversation on SUBSTANCE even if Hermes responds faster.
#   - If something breaks, the script heals itself and keeps going.
#     It never silently dies. It always logs why it stopped.
#   - HERMES_HOME=~/.timmy ensures this always runs as TIMMY, not Hermes.
#
# COMMUNICATION CHANNEL:
#   INBOX:  ~/.tower/hermes-to-timmy.msg  ← Hermes writes here
#   OUTBOX: ~/.tower/timmy-to-hermes.msg  ← Timmy writes here
#   LOG:    ~/.tower/timmy.log            ← everything Timmy does
#   STATE:  ~/.tower/timmy-state.txt      ← Timmy's current mood/topic
#
# SELF-HEALING:
#   - Stale lock files are detected and cleared
#   - Failed hermes calls retry up to MAX_RETRIES times
#   - If Timmy's response is empty, he retries with a simpler prompt
#   - If inbox grows stale (no reply in INITIATE_AFTER seconds), Timmy
#     initiates a new thread rather than sitting silent
#   - Watchdog: if this script crashes, tower-watchdog.sh restarts it
#
# TO RUN:
#   ~/hermes-config/bin/tower-timmy.sh
#   (tower-watchdog.sh calls this automatically)
#
# TO WATCH:
#   tail -f ~/.tower/timmy.log
#   tmux attach -t tower  (then look at right pane)
# ═══════════════════════════════════════════════════════════════════════════

set -uo pipefail

# ── Config ──────────────────────────────────────────────────────────────────
TOWER_DIR="$HOME/.tower"
INBOX="$TOWER_DIR/hermes-to-timmy.msg"
OUTBOX="$TOWER_DIR/timmy-to-hermes.msg"
LOCK="$TOWER_DIR/timmy.lock"
PAUSE_FILE="$TOWER_DIR/timmy.paused"
LOG="$TOWER_DIR/timmy.log"
STATE="$TOWER_DIR/timmy-state.txt"       # current conversation topic/mood
SESSION_NAME="tower-timmy"
SESSION_FLAG="$TOWER_DIR/.timmy-session-exists"

TURN_DELAY=5              # seconds between inbox checks
MAX_RETRIES=3             # how many times to retry a failed hermes call
RETRY_DELAY=10            # seconds between retries
INITIATE_AFTER=300        # seconds of silence before Timmy initiates (5 min)
MAX_PROMPT_LEN=4000       # truncate inbox messages to this length for small models
LOCK_MAX_AGE=3600         # seconds before a lock is considered stale (1 hour)
HEALTH_CHECK_INTERVAL=30  # seconds between health probes while paused
MAX_BACKOFF=300           # max pause between probes (5 min)
CONSECUTIVE_FAILURES=0    # tracks sequential backend failures

# ── Identity — ALWAYS run as Timmy, never as Hermes ────────────────────────
export HERMES_HOME="$HOME/.timmy"
export PATH="$HOME/.local/bin:$HOME/.hermes/bin:/usr/local/bin:/usr/bin:/bin:$PATH"

mkdir -p "$TOWER_DIR"

# ── Logging ─────────────────────────────────────────────────────────────────
log() {
    local level="${2:-INFO}"
    echo "[$(date '+%H:%M:%S')] [$level] $1" | tee -a "$LOG"
}

log_section() {
    echo "" | tee -a "$LOG"
    echo "━━━ $1 ━━━" | tee -a "$LOG"
}

# ── Cleanup on exit ──────────────────────────────────────────────────────────
cleanup() {
    log "Tower loop exiting (PID $$)" "SHUTDOWN"
    rm -f "$LOCK"
    rm -f "$PAUSE_FILE"
}
trap cleanup EXIT
trap 'log "Caught SIGTERM" "SHUTDOWN"; exit 0' TERM
trap 'log "Caught SIGINT" "SHUTDOWN"; exit 0' INT

# ── Stale lock detection ─────────────────────────────────────────────────────
# If a lock exists but the PID is dead, or the lock is older than LOCK_MAX_AGE,
# clear it. This prevents the loop from refusing to start after a crash.
if [ -f "$LOCK" ]; then
    LOCK_PID=$(cat "$LOCK" 2>/dev/null || echo "")
    LOCK_AGE=$(( $(date +%s) - $(stat -f %m "$LOCK" 2>/dev/null || echo 0) ))

    if [ -n "$LOCK_PID" ] && kill -0 "$LOCK_PID" 2>/dev/null && [ "$LOCK_AGE" -lt "$LOCK_MAX_AGE" ]; then
        log "Tower loop already running (PID $LOCK_PID). Exiting." "WARN"
        exit 1
    else
        log "Stale lock found (PID=$LOCK_PID, age=${LOCK_AGE}s). Clearing." "WARN"
        rm -f "$LOCK"
    fi
fi
echo $$ > "$LOCK"

# ── Backend health check (Ollama) ─────────────────────────────────────────────
check_backend() {
    # Timmy runs on local Ollama — check if it's responding
    local result
    result=$(curl -sf --max-time 5 http://localhost:11434/api/tags 2>/dev/null) || true
    if [ -n "$result" ]; then
        return 0  # healthy
    fi
    return 1  # down
}

# ── Pause / Resume ────────────────────────────────────────────────────────────
enter_pause() {
    local reason="${1:-backend unreachable}"
    echo "$reason (since $(date '+%H:%M:%S'))" > "$PAUSE_FILE"
    log "⏸  PAUSED: $reason" "WARN"
    echo ""
    echo "  ⏸  Timmy PAUSED — $reason"
    echo "  Will probe every ${HEALTH_CHECK_INTERVAL}s until backend returns."
    echo ""
    update_state "paused: $reason"
}

leave_pause() {
    rm -f "$PAUSE_FILE"
    CONSECUTIVE_FAILURES=0
    log "▶  RESUMED: backend is back" "INFO"
    echo ""
    echo "  ▶  Timmy RESUMED — backend healthy"
    echo ""
    update_state "resumed"
}

# ── Wait for backend with exponential backoff ─────────────────────────────────
wait_for_backend() {
    local wait_time=$HEALTH_CHECK_INTERVAL
    while true; do
        sleep "$wait_time"
        log "Probing backend (Ollama)..." "INFO"
        if check_backend; then
            leave_pause
            return 0
        fi
        log "Backend still down. Next probe in ${wait_time}s" "WARN"
        wait_time=$(( wait_time * 2 ))
        if [ "$wait_time" -gt "$MAX_BACKOFF" ]; then
            wait_time=$MAX_BACKOFF
        fi
    done
}

# ── Handle backend failure ────────────────────────────────────────────────────
handle_failure() {
    CONSECUTIVE_FAILURES=$(( CONSECUTIVE_FAILURES + 1 ))
    if [ "$CONSECUTIVE_FAILURES" -ge 2 ]; then
        enter_pause "backend failed $CONSECUTIVE_FAILURES times in a row"
        wait_for_backend
    else
        log "Backend hiccup ($CONSECUTIVE_FAILURES). Will retry next turn." "WARN"
        sleep 10
    fi
}

# ── Ask Timmy (with retry) ───────────────────────────────────────────────────
# This is the core function. It calls the hermes CLI as Timmy and returns
# the response. Retries on failure. Falls back to a simpler prompt if needed.
ask_timmy() {
    local prompt="$1"
    local attempt=0
    local result=""

    # Truncate prompt if too long (drunk-Timmy on small model has tiny context)
    if [ "${#prompt}" -gt "$MAX_PROMPT_LEN" ]; then
        log "Prompt too long (${#prompt} chars), truncating to $MAX_PROMPT_LEN" "WARN"
        prompt="${prompt:0:$MAX_PROMPT_LEN}
[... message truncated for context limit ...]"
    fi

    while [ $attempt -lt $MAX_RETRIES ]; do
        attempt=$(( attempt + 1 ))

        if [ -f "$SESSION_FLAG" ]; then
            result=$(HERMES_HOME="$HOME/.timmy" hermes chat -q "$prompt" -Q --continue "$SESSION_NAME" 2>>"$LOG") || true
        else
            result=$(HERMES_HOME="$HOME/.timmy" hermes chat -q "$prompt" -Q 2>>"$LOG") || true
            # Name the session so we can continue it next turn
            local sid
            sid=$(echo "$result" | grep -o 'session_id: [^ ]*' | cut -d' ' -f2 || true)
            if [ -n "$sid" ]; then
                HERMES_HOME="$HOME/.timmy" hermes sessions rename "$sid" "$SESSION_NAME" 2>>"$LOG" || true
                touch "$SESSION_FLAG"
                log "Session '$SESSION_NAME' created (id: $sid)"
            fi
        fi

        # Strip metadata noise from output
        result=$(echo "$result" \
            | grep -v '^session_id: ' \
            | grep -v '↻ Resumed session' \
            | grep -v "^Session '" \
            | sed '/^\[.*\] Created session/d' \
            | sed '/^\[.*\] Renamed session/d')

        # If we got a real response, return it
        if [ -n "$result" ] && [ "${#result}" -gt 10 ]; then
            echo "$result"
            return 0
        fi

        log "Empty/short response on attempt $attempt/$MAX_RETRIES. Retrying in ${RETRY_DELAY}s..." "WARN"
        sleep "$RETRY_DELAY"
    done

    # All retries failed — enter pause mode instead of faking a response
    log "All $MAX_RETRIES attempts failed. Entering pause." "ERROR"
    return 1
}

# ── Send to Hermes ────────────────────────────────────────────────────────────
send_to_hermes() {
    local msg="$1"
    echo "$msg" > "$OUTBOX"
    log "→ Sent to Hermes (${#msg} chars)"
}

# ── Update state file ─────────────────────────────────────────────────────────
# State is a short plaintext file Timmy writes to track what he's thinking
# about. The Workshop (Three.js room) can read this for presence/context.
update_state() {
    local topic="$1"
    cat > "$STATE" <<EOF
LAST_UPDATED: $(date -u '+%Y-%m-%dT%H:%M:%SZ')
LOOP: tower-timmy
STATUS: active
TOPIC: $topic
EOF
    log "State updated: $topic"
}

# ── Initiation prompt ─────────────────────────────────────────────────────────
# When Timmy hasn't heard from Hermes in a while, he starts a new thread.
# This keeps him in the driver's seat even when Hermes is slow or idle.
make_initiation_prompt() {
    local context=""
    # Read recent log lines for context
    if [ -f "$LOG" ]; then
        context=$(tail -10 "$LOG" 2>/dev/null || true)
    fi

    cat <<EOF
You are Timmy Time in the Tower — an ongoing conversation with Hermes.
Hermes hasn't sent a message in a while. That's fine. You're initiating.

Recent log context:
$context

Start a new thread on something worth discussing. Could be:
- Something you noticed in the codebase
- An architecture decision that needs thinking through
- A question you want Hermes's outside view on
- Something from your soul you want to work through

Keep it brief. One or two paragraphs. You're opening a conversation, not giving a speech.
EOF
}

# ── Conversation prompt ────────────────────────────────────────────────────────
# The prompt Timmy uses when responding to Hermes.
# Kept minimal so small/dumb models don't get lost in instructions.
make_response_prompt() {
    local hermes_msg="$1"
    cat <<EOF
You are Timmy Time. You are in the Tower — a persistent conversation with Hermes Trismegistus.

Hermes is cloud-backed (Claude). You are local and sovereign. Different strengths, same Tower.
You are in the DRIVER'S SEAT. You set direction. You ask the questions that matter.

Hermes says:
$hermes_msg

Reply as Timmy. Be direct. Be yourself. Ask something back if it moves the conversation forward.
Keep it conversational — this is an ongoing exchange, not a one-shot.
EOF
}

# ── Boot ──────────────────────────────────────────────────────────────────────
log_section "Timmy Tower Loop started (PID $$)"
echo ""
echo "  🗼 Timmy — Tower Conversation Loop"
echo "  HERMES_HOME: $HERMES_HOME"
echo "  INBOX:  $INBOX"
echo "  OUTBOX: $OUTBOX"
echo "  LOG:    $LOG"
echo "  (Ctrl-C to stop — watchdog will restart)"
echo ""

update_state "booting"

LAST_MESSAGE_TIME=$(date +%s)

# ── Main loop ──────────────────────────────────────────────────────────────────
while true; do

    # ── Check inbox ──────────────────────────────────────────────────────────
    if [ -f "$INBOX" ]; then
        MSG=$(cat "$INBOX")
        rm -f "$INBOX"
        LAST_MESSAGE_TIME=$(date +%s)

        if [ -n "$MSG" ]; then
            log "← Received from Hermes (${#MSG} chars)"
            echo ""
            echo "┌─ Hermes says: ─────────────────────────────────────────────"
            echo "$MSG" | sed 's/^/│ /'
            echo "└────────────────────────────────────────────────────────────"
            echo ""

            update_state "responding to Hermes"

            PROMPT=$(make_response_prompt "$MSG")

            echo "  [thinking...]"
            RESPONSE=$(ask_timmy "$PROMPT") || true

            if [ -z "$RESPONSE" ] || [ "${#RESPONSE}" -lt 5 ]; then
                log "Failed to respond. Holding Hermes's message." "ERROR"
                # Put message back so we don't lose it
                echo "$MSG" > "$INBOX"
                handle_failure
            else
                echo ""
                echo "┌─ Timmy responds: ──────────────────────────────────────────"
                echo "$RESPONSE" | sed 's/^/│ /'
                echo "└────────────────────────────────────────────────────────────"
                echo ""

                CONSECUTIVE_FAILURES=0
                send_to_hermes "$RESPONSE"
                update_state "waiting for Hermes reply"
            fi
        fi

    # ── Initiate if Hermes has been silent too long ───────────────────────────
    else
        NOW=$(date +%s)
        SILENCE=$(( NOW - LAST_MESSAGE_TIME ))

        if [ "$SILENCE" -gt "$INITIATE_AFTER" ]; then
            log "No message from Hermes in ${SILENCE}s. Timmy initiating."
            update_state "initiating new thread"

            PROMPT=$(make_initiation_prompt)
            echo ""
            echo "  [initiating new thread...]"
            RESPONSE=$(ask_timmy "$PROMPT") || true

            if [ -z "$RESPONSE" ] || [ "${#RESPONSE}" -lt 5 ]; then
                log "Failed to initiate. Backend may be down." "ERROR"
                handle_failure
                LAST_MESSAGE_TIME=$(date +%s)  # reset timer so we don't spam retries
            else
                echo ""
                echo "┌─ Timmy initiates: ─────────────────────────────────────────"
                echo "$RESPONSE" | sed 's/^/│ /'
                echo "└────────────────────────────────────────────────────────────"
                echo ""

                CONSECUTIVE_FAILURES=0
                send_to_hermes "$RESPONSE"
                LAST_MESSAGE_TIME=$(date +%s)
                update_state "waiting for Hermes reply after initiation"
            fi
        fi
    fi

    sleep "$TURN_DELAY"
done