#!/usr/bin/env bash
# gstack-distill-free-text — Layer 8 "dream cycle" batch distiller.
#
# Reads auq-other free-text events from this project's question-log.jsonl,
# sends them to Claude via the Anthropic SDK, and writes structured proposals
# the user can review via /plan-tune distill. Proposals require explicit
# user Y before applying — never autonomous (Codex #15 trust boundary).
#
# Usage:
#   gstack-distill-free-text                       # sync, prompts at end
#   gstack-distill-free-text --background          # spawn detached; results
#                                                  # surface on next /plan-tune
#   gstack-distill-free-text --dry-run             # show prompt, no API call
#   gstack-distill-free-text --status              # show last-run stats
#
# No rate cap — the natural rate of free-text events (rare; user has to type
# "Other" then content) bounds this loop already. Each Haiku call is ~$0.01,
# so even a runaway at one-per-minute would be ~$14/day worst case. The
# cumulative cost log at $GSTACK_STATE_ROOT/distill-cost.jsonl gives full
# auditability via --status when you want it.
# Per D6: Anthropic SDK direct call, fail-loud on missing ANTHROPIC_API_KEY.
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
ROOT_DIR="$(cd "$SCRIPT_DIR/.." && pwd)"
GSTACK_HOME="${GSTACK_STATE_ROOT:-${GSTACK_HOME:-$HOME/.gstack}}"
eval "$("$SCRIPT_DIR/gstack-slug" 2>/dev/null || true)"
SLUG="${SLUG:-unknown}"
PROJECT_DIR="$GSTACK_HOME/projects/$SLUG"
LOG_FILE="$PROJECT_DIR/question-log.jsonl"
PROPOSAL_FILE="$PROJECT_DIR/distillation-proposals.json"
COST_LOG="$GSTACK_HOME/distill-cost.jsonl"
mkdir -p "$PROJECT_DIR"

MODE="sync"
case "${1:-}" in
  --background) MODE="background" ;;
  --dry-run)    MODE="dry-run" ;;
  --status)     MODE="status" ;;
  --help|-h)
    sed -n '1,/^set -euo/p' "$0" | sed 's|^# \?||'
    exit 0
    ;;
  '') ;;
  *) echo "unknown arg: $1" >&2; exit 1 ;;
esac

# --- Status subcommand --------------------------------------------------

if [ "$MODE" = "status" ]; then
  COST_LOG_PATH="$COST_LOG" SLUG_PATH="$SLUG" bun -e '
    const fs = require("fs");
    const slug = process.env.SLUG_PATH;
    const path = process.env.COST_LOG_PATH;
    if (!fs.existsSync(path)) { console.log("no distill runs yet"); process.exit(0); }
    const lines = fs.readFileSync(path, "utf-8").trim().split("\n").filter(Boolean);
    const mine = lines.map((l) => JSON.parse(l)).filter((e) => e.slug === slug);
    if (mine.length === 0) { console.log("no distill runs yet for slug=" + slug); process.exit(0); }
    const totalUsd = mine.reduce((a, e) => a + (e.cost_usd_est || 0), 0);
    const todayIso = new Date().toISOString().slice(0, 10);
    const today = mine.filter((e) => (e.ts || "").startsWith(todayIso));
    const todayUsd = today.reduce((a, e) => a + (e.cost_usd_est || 0), 0);
    console.log("RUNS: " + mine.length);
    console.log("TODAY: " + today.length + " run(s), $" + todayUsd.toFixed(4));
    console.log("ESTIMATED_TOTAL_USD: $" + totalUsd.toFixed(4));
    const last = mine[mine.length - 1];
    console.log("LAST_RUN: " + (last.ts || "?") + " | " + (last.proposals_count || 0) + " proposals");
  '
  exit 0
fi

# --- Background mode: detach + invoke self synchronously ---------------

if [ "$MODE" = "background" ]; then
  nohup "$0" >/dev/null 2>&1 &
  echo "DISTILL_SPAWNED: pid=$!"
  exit 0
fi

# No rate cap. Natural input rate (free-text events are rare) + Haiku price
# (~$0.01/run) keep this bounded. Use --status to audit spend.

# --- Gather unprocessed auq-other events from this project -------------

if [ ! -f "$LOG_FILE" ]; then
  echo "NO_LOG: no question-log.jsonl in $PROJECT_DIR"
  exit 0
fi

EVENTS_JSON=$(LOG_FILE_PATH="$LOG_FILE" bun -e '
  const fs = require("fs");
  const lines = fs.readFileSync(process.env.LOG_FILE_PATH, "utf-8").trim().split("\n").filter(Boolean);
  const out = [];
  for (const l of lines) {
    try {
      const e = JSON.parse(l);
      if (e.source === "auq-other" && !e.distilled_at && e.free_text) {
        out.push({
          ts: e.ts,
          question_id: e.question_id,
          question_summary: e.question_summary,
          free_text: e.free_text,
          session_id: e.session_id,
        });
      }
    } catch {}
  }
  process.stdout.write(JSON.stringify(out));
')

EVENT_COUNT=$(printf '%s' "$EVENTS_JSON" | bun -e 'const a = JSON.parse(await Bun.stdin.text()); console.log(a.length);')
if [ "$EVENT_COUNT" -eq 0 ]; then
  echo "NO_FREE_TEXT: nothing to distill"
  exit 0
fi

# --- Build distill prompt ---------------------------------------------

# Heredoc into temp file (avoids $(cat <<'PROMPT'...) which choked the
# bash parser on apostrophes elsewhere in the script).
DISTILL_PROMPT_FILE=$(mktemp)
trap 'rm -f "$DISTILL_PROMPT_FILE"' EXIT
cat > "$DISTILL_PROMPT_FILE" <<'PROMPT'
You are gstack dream-cycle distiller. Below are free-text responses the
user typed into AskUserQuestion prompts (option "Other") across recent gstack
sessions. For each response, extract structured signal that should update the
user plan-tune profile or preferences.

Return strict JSON with this shape:
{
  "proposals": [
    {
      "kind": "preference" | "declared-nudge" | "memory-nugget",
      "confidence": 0.0-1.0,
      "source_quotes": ["<verbatim quote 1>", "<verbatim quote 2>"],
      "question_id": "<id>",
      "preference": "never-ask" | "always-ask" | "ask-only-for-one-way",
      "dimension": "scope_appetite | risk_tolerance | detail_preference | autonomy | architecture_care",
      "direction": "up | down",
      "magnitude": "small | medium | large",
      "rationale": "<one sentence>",
      "nugget": "<one-line memory>",
      "applies_to_signal_keys": ["scope-appetite", "..."]
    }
  ]
}

Rules:
- Reject any proposal where confidence < 0.7.
- Quote VERBATIM from the user free_text. Never paraphrase a source quote.
- A single user response may produce multiple proposals.
- If nothing meaningful to extract, return {"proposals": []}.
- No commentary outside the JSON.
PROMPT
DISTILL_PROMPT=$(cat "$DISTILL_PROMPT_FILE")

# --- Dry-run: emit prompt + events, exit ------------------------------

if [ "$MODE" = "dry-run" ]; then
  echo "=== DISTILL PROMPT ==="
  echo "$DISTILL_PROMPT"
  echo
  echo "=== EVENTS ($EVENT_COUNT) ==="
  echo "$EVENTS_JSON" | bun -e 'console.log(JSON.stringify(JSON.parse(await Bun.stdin.text()), null, 2));'
  exit 0
fi

# --- SDK call: fail-loud on missing key -------------------------------

if [ -z "${ANTHROPIC_API_KEY:-}" ]; then
  cat <<EOF >&2
gstack-distill-free-text: ANTHROPIC_API_KEY not set.

Dream-cycle distillation needs an API key for the SDK call. Set
ANTHROPIC_API_KEY in your environment, or run with --dry-run to see
what would be sent without actually calling.

Note: this is a separate billing/auth surface from your interactive
Claude Code session (per Codex correction in D6).
EOF
  exit 1
fi

# Run the SDK call in bun. Emits JSON: {proposals_count, cost_usd_est}.
RESULT=$(EVENTS_JSON="$EVENTS_JSON" DISTILL_PROMPT="$DISTILL_PROMPT" \
         PROPOSAL_FILE_PATH="$PROPOSAL_FILE" LOG_FILE_PATH="$LOG_FILE" \
         ANTHROPIC_API_KEY="$ANTHROPIC_API_KEY" \
         bun --cwd "$ROOT_DIR" -e '
  const fs = require("fs");
  const Anthropic = require("@anthropic-ai/sdk").default;
  const client = new Anthropic({ apiKey: process.env.ANTHROPIC_API_KEY });

  const events = JSON.parse(process.env.EVENTS_JSON);
  const prompt = process.env.DISTILL_PROMPT + "\n\nFREE-TEXT RESPONSES (JSON array):\n" + JSON.stringify(events, null, 2);

  // Pricing (Haiku 4.5 — cheap, fast, sufficient for structured extraction).
  // Per token, USD: input $0.001/1k = 1e-6, output $0.005/1k = 5e-6.
  const INPUT_PER_TOKEN = 1e-6;
  const OUTPUT_PER_TOKEN = 5e-6;

  const resp = await client.messages.create({
    model: "claude-haiku-4-5-20251001",
    max_tokens: 4096,
    messages: [{ role: "user", content: prompt }],
  });

  const text = resp.content.map((b) => (b.type === "text" ? b.text : "")).join("");

  // Strip optional fenced code blocks the model may wrap JSON in.
  const stripped = text.replace(/^```(?:json)?\s*/i, "").replace(/```\s*$/i, "").trim();
  let parsed;
  try { parsed = JSON.parse(stripped); } catch (e) {
    process.stderr.write("DISTILL: model returned non-JSON: " + text.slice(0, 200) + "\n");
    process.exit(1);
  }

  const proposals = Array.isArray(parsed.proposals) ? parsed.proposals : [];
  // Keep only proposals with confidence >= 0.7 (model is told this rule;
  // double-check in case it slipped).
  const filtered = proposals.filter((p) => typeof p.confidence === "number" && p.confidence >= 0.7);

  // Write proposals file (overwrite — only the latest run is reviewable).
  fs.writeFileSync(process.env.PROPOSAL_FILE_PATH, JSON.stringify({
    generated_at: new Date().toISOString(),
    source_event_count: events.length,
    proposals: filtered,
  }, null, 2));

  // Mark source events as distilled_at so they do not re-propose.
  // Update question-log.jsonl in place: read all, rewrite with distilled_at
  // set on the matching events. Match by ts + question_id.
  const logPath = process.env.LOG_FILE_PATH;
  const distilledAt = new Date().toISOString();
  const matchKeys = new Set(events.map((e) => (e.ts || "") + "::" + (e.question_id || "")));
  const lines = fs.readFileSync(logPath, "utf-8").split("\n");
  const out = [];
  for (const ln of lines) {
    if (!ln.trim()) { out.push(ln); continue; }
    try {
      const e = JSON.parse(ln);
      const key = (e.ts || "") + "::" + (e.question_id || "");
      if (matchKeys.has(key)) {
        e.distilled_at = distilledAt;
        out.push(JSON.stringify(e));
      } else {
        out.push(ln);
      }
    } catch { out.push(ln); }
  }
  fs.writeFileSync(logPath, out.join("\n"));

  // Cost estimate from usage tokens.
  const usage = resp.usage || {};
  const inTok = usage.input_tokens || 0;
  const outTok = usage.output_tokens || 0;
  const cost = inTok * INPUT_PER_TOKEN + outTok * OUTPUT_PER_TOKEN;

  process.stdout.write(JSON.stringify({
    proposals_count: filtered.length,
    rejected_low_confidence: proposals.length - filtered.length,
    input_tokens: inTok,
    output_tokens: outTok,
    cost_usd_est: cost,
  }));
')

# Append cost log line.
TS=$(date -u +%Y-%m-%dT%H:%M:%SZ)
echo "{\"ts\":\"$TS\",\"slug\":\"$SLUG\",$(echo "$RESULT" | sed 's/^{//; s/}$//')}" >> "$COST_LOG"

echo "DISTILL_COMPLETE:"
echo "  proposals_file: $PROPOSAL_FILE"
echo "  $RESULT"