#!/usr/bin/env bash
# One tick of the Claude side of the agent loop (plan + review + deploy check).
# State lives in Gitea issue labels; see docs/tasks/TASK-agent-loop-pilot-20261013.md §4.
#
# Order per tick: release stale locks → deploy checks (no model) → at most ONE
# model run: a review (agent/待验收) first, else a plan (agent/待规划).
# The script, not the model, owns label transitions and validates every claim
# the model makes (brief exists on staging, reviewed SHA is the branch head,
# staging contains it) before posting.
set -euo pipefail

HERE="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
GITEA="$HERE/gitea.sh"
REPO_DIR="${JYOTISHA_REPO_DIR:-/workspace/Jyotisha}"
LOOP_WT="${AGENT_LOOP_WORKTREE:-$REPO_DIR/.worktrees/agent-loop}"
CONF_DIR="$HOME/.config/jyotisha-agent"
STATE_DIR="${AGENT_LOOP_STATE_DIR:-$HOME/.local/state/jyotisha-agent}"
PILOT_LABEL="${AGENT_LOOP_SCOPE_LABEL:-agent/试点}"
HEALTH_URL="${AGENT_LOOP_HEALTH_URL:-https://staging.jyotisha.chat/api/health}"
PLAN_TIMEOUT="${AGENT_LOOP_PLAN_TIMEOUT:-40m}"
REVIEW_TIMEOUT="${AGENT_LOOP_REVIEW_TIMEOUT:-75m}"
MAX_BUDGET="${AGENT_LOOP_MAX_BUDGET_USD:-25}"
DEPLOY_WAIT_HOURS="${AGENT_LOOP_DEPLOY_WAIT_HOURS:-3}"
MAX_BOUNCES=2
MAX_ERRORS=3

mkdir -p "$STATE_DIR/runs"
LOG="$STATE_DIR/claude-tick.log"
log() { printf '%s %s\n' "$(date -u +%FT%TZ)" "$*" >> "$LOG"; }

[[ -e "$CONF_DIR/STOP" ]] && { log "STOP file present, skipping"; exit 0; }
exec 9> "$STATE_DIR/claude.lock"
flock -n 9 || { log "another tick is running, skipping"; exit 0; }

STATES=(agent/待规划 agent/待执行 agent/待验收 agent/部署中 agent/待真机 agent/需拍板)

# ---------- helpers ----------

has_label() { "$GITEA" labels "$1" | grep -qxF "$2"; }

set_state() {   # set_state N NEW_STATE — drop every other state label, add NEW_STATE
  local n="$1" new="$2" s
  for s in "${STATES[@]}"; do [[ "$s" == "$new" ]] || "$GITEA" remove-label "$n" "$s"; done
  "$GITEA" add-label "$n" "$new"
}

post() {        # post N MARKER BODY_FILE — marker first line, Chinese body, footer
  local n="$1" marker="$2" body="$3" out
  out="$(mktemp)"
  { printf '%s\n' "$marker"; cat "$body"; printf '\n\n— Claude（自动循环 · %s）\n' "$RUN_ID"; } > "$out"
  "$GITEA" comment "$n" "$out"
  rm -f "$out"
}

post_text() {   # post_text N MARKER TEXT
  local f; f="$(mktemp)"; printf '%s\n' "$3" > "$f"; post "$1" "$2" "$f"; rm -f "$f"
}

# Public repository: refuse to post anything that looks like personal data or a secret.
privacy_ok() {
  ! grep -qE '[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,}|eyJ[A-Za-z0-9_-]{10,}\.[A-Za-z0-9_-]{10,}|-----BEGIN [A-Z ]*PRIVATE KEY|(api[_-]?key|secret|password|passwd|token)[[:space:]]*[:=][[:space:]]*[^[:space:]<]{8,}' "$1"
}

# Marker fields: <!-- agent:claude review sha=abc verdict=fail ... -->
marker_field() { sed -nE "s/.* $1=([^ ]+).*/\1/p" <<<"$2"; }

# gitea.sh returns only trusted accounts' text (jesse, Claude, Grok);
# anyone else's comment never reaches a model.
OWNER="${AGENT_LOOP_OWNER:-jesse}"
comments_json() { "$GITEA" comments "$1"; }

# Bodies' first lines (markers) of agent comments, oldest first.
markers() { comments_json "$1" | jq -r '.[].body | split("\n")[0] | select(startswith("<!-- agent:"))'; }

latest_marker() { markers "$1" | grep -F "$2" | tail -1 || true; }

count_errors_since_progress() {   # consecutive claude error markers since the last non-error claude marker
  markers "$1" | grep -F 'agent:claude' | tac | awk '/agent:claude error/{c++; next} {exit} END{print c+0}'
}

prepare_worktree() {
  git -C "$REPO_DIR" fetch -q origin --prune
  if [[ ! -d "$LOOP_WT" ]]; then
    git -C "$REPO_DIR" worktree add -q --detach "$LOOP_WT" origin/staging
  fi
  git -C "$LOOP_WT" checkout -q --detach -f origin/staging
  git -C "$LOOP_WT" clean -q -fd   # ignored deps (node_modules, .venv) survive
}

build_context() {   # build_context N MODE OUT_JSON [EXTRA_JSON]
  local n="$1" mode="$2" out="$3" extra="${4:-null}"
  jq -n \
    --argjson issue "$("$GITEA" issue "$n" | jq '{number, title, body, created_at, labels: [.labels[].name]}')" \
    --argjson comments "$(comments_json "$n" | jq '[.[] | {created_at, body}]')" \
    --arg mode "$mode" \
    --arg staging "$(git -C "$REPO_DIR" rev-parse origin/staging)" \
    --argjson extra "$extra" \
    '{mode: $mode, origin_staging: $staging, issue: $issue, comments: $comments, extra: $extra}' > "$out"
}

run_claude() {      # run_claude PROMPT_FILE SCHEMA_FILE CONTEXT_FILE TIMEOUT OUT_JSON [DOCS_ONLY]
  local prompt="$1" schema="$2" ctx="$3" tmo="$4" out="$5" docs_only="${6:-0}"
  (
    cd "$LOOP_WT"
    export GIT_CONFIG_COUNT=1 GIT_CONFIG_KEY_0=core.hooksPath GIT_CONFIG_VALUE_0="$HERE/hooks/claude"
    export AGENT_LOOP_DOCS_ONLY="$docs_only" AGENT_LOOP_CONTEXT="$ctx"
    timeout --kill-after=60 "$tmo" claude -p \
      "$(cat "$prompt")

本轮上下文文件（JSON）：$ctx" \
      --output-format json \
      --json-schema "$(cat "$schema")" \
      --settings "$HERE/claude-settings.json" \
      --permission-mode dontAsk \
      --max-budget-usd "$MAX_BUDGET"
  ) > "$out" 2>> "$LOG"
}

fail_run() {        # fail_run N STATE REASON — keep the state, count errors, escalate after MAX_ERRORS
  local n="$1" state="$2" reason="$3" errs
  post_text "$n" "<!-- agent:claude error state=$state -->" "本轮自动处理没有完成：$reason。状态保持不变，下一轮重试。"
  errs="$(count_errors_since_progress "$n")"
  if (( errs >= MAX_ERRORS )); then
    set_state "$n" agent/需拍板
    post_text "$n" "<!-- agent:claude escalate -->" "@$OWNER 连续 $errs 轮自动处理失败，已停下等你决定。最近一次原因：$reason。日志在开发机 $LOG。"
  fi
}

# ---------- 1. stale locks on this side ----------
# flock above guarantees no other tick runs here, so any Claude lock label is a crash leftover.

for lock in agent/规划中 agent/验收中; do
  for n in $("$GITEA" issues "$lock,$PILOT_LABEL" | jq -r '.[].number'); do
    "$GITEA" remove-label "$n" "$lock"
    state=agent/待规划; [[ "$lock" == agent/验收中 ]] && state=agent/待验收
    log "issue #$n: released stale lock $lock"
    RUN_ID="lock-release"; fail_run "$n" "$state" "上一轮在处理中途中断（锁 $lock 已释放）"
  done
done

RUN_ID="$(date -u +%Y%m%dT%H%M%SZ)"
RUN_DIR="$STATE_DIR/runs/$RUN_ID"

# ---------- 2. deploy checks (no model) ----------

deployed="$(curl -sS -m 20 "$HEALTH_URL" | jq -r '.deployment.gitCommit // empty' 2>/dev/null || true)"
for n in $("$GITEA" issues "agent/部署中,$PILOT_LABEL" | jq -r '.[].number'); do
  m="$(latest_marker "$n" 'agent:claude review')"
  want="$(marker_field staging "$m")"
  checklist="$(marker_field checklist "$m")"
  [[ -z "$want" ]] && { set_state "$n" agent/需拍板; post_text "$n" "<!-- agent:claude escalate -->" "@$OWNER 找不到验收记录里的 staging 提交号，无法核对部署，请人工看一下。"; continue; }
  git -C "$REPO_DIR" fetch -q origin
  ok=0
  if [[ -n "$deployed" ]]; then
    if git -C "$REPO_DIR" merge-base --is-ancestor "$want" "$deployed" 2>/dev/null; then ok=1
    elif (cd "$REPO_DIR" && deploy/is-docs-only-range.sh "$deployed" "$want" >/dev/null 2>&1); then ok=1
    fi
  fi
  if (( ok )); then
    note="staging 已部署：/api/health 的 deployment.gitCommit = ${deployed:0:9}，包含本次改动 ${want:0:9}。"
    [[ -n "$checklist" && "$checklist" != "-" ]] && note="$note

请照真机清单走一遍：\`$checklist\`。没问题就关闭本 issue；有问题直接在下面写，并把标签改回 \`agent/待规划\`。"
    post_text "$n" "<!-- agent:claude deployed sha=$deployed -->" "@$OWNER $note"
    set_state "$n" agent/待真机
    log "issue #$n: deployed $deployed contains $want → 待真机"
  else
    since="$(comments_json "$n" | jq -r '[.[] | select(.body | startswith("<!-- agent:claude review"))] | last | .created_at')"
    age_h=$(( ( $(date +%s) - $(date -d "$since" +%s) ) / 3600 ))
    if (( age_h >= DEPLOY_WAIT_HOURS )); then
      set_state "$n" agent/需拍板
      post_text "$n" "<!-- agent:claude escalate -->" "@$OWNER 推上 staging 已 ${age_h} 小时，部署仍未包含 ${want:0:9}（当前部署 ${deployed:0:9}）。可能是门禁红了，请到 Gitea Actions 看一下。"
      log "issue #$n: deploy wait exceeded"
    fi
  fi
done

# ---------- 3. one model run: review first, then plan ----------

pick() { "$GITEA" issues "$1,$PILOT_LABEL" | jq -r --arg lock "$2" '[.[] | select([.labels[].name] | index($lock) | not)] | .[0].number // empty'; }

n="$(pick agent/待验收 agent/验收中)"
if [[ -n "$n" ]]; then
  mode=review; lock=agent/验收中; state=agent/待验收
else
  n="$(pick agent/待规划 agent/规划中)"
  [[ -z "$n" ]] && { log "nothing to do"; exit 0; }
  mode=plan; lock=agent/规划中; state=agent/待规划
fi

mkdir -p "$RUN_DIR"
log "issue #$n: $mode start ($RUN_ID)"
"$GITEA" add-label "$n" "$lock"
trap '"$GITEA" remove-label "$n" "$lock" || true' EXIT
prepare_worktree

if [[ "$mode" == review ]]; then
  rep="$(latest_marker "$n" 'agent:grok report')"
  branch="$(marker_field branch "$rep")"; sha="$(marker_field sha "$rep")"
  if [[ -z "$branch" || -z "$sha" ]]; then
    fail_run "$n" "$state" "找不到 Grok 的回报（缺 branch 或 sha）"; exit 0
  fi
  head="$(git -C "$REPO_DIR" ls-remote origin "refs/heads/$branch" | cut -f1)"
  if [[ "$head" != "$sha" ]]; then
    fail_run "$n" "$state" "分支 $branch 当前 head ${head:0:9} 与 Grok 回报的 ${sha:0:9} 不一致，等 Grok 重新回报"; exit 0
  fi
  fails="$(markers "$n" | grep -F 'agent:claude review' | grep -cF 'verdict=fail' || true)"
  extra="$(jq -nc --arg b "$branch" --arg s "$sha" --argjson f "${fails:-0}" '{branch:$b, sha:$s, previous_failed_reviews:$f}')"
else
  extra=null
fi

build_context "$n" "$mode" "$RUN_DIR/context.json" "$extra"
tmo="$PLAN_TIMEOUT"; [[ "$mode" == review ]] && tmo="$REVIEW_TIMEOUT"
if ! run_claude "$HERE/prompts/claude-$mode.md" "$HERE/prompts/claude-$mode.schema.json" "$RUN_DIR/context.json" "$tmo" "$RUN_DIR/out.json"; then
  fail_run "$n" "$state" "模型运行超时或异常退出（run $RUN_ID）"; exit 0
fi
res="$(jq -c '.structured_output // empty' "$RUN_DIR/out.json" 2>/dev/null || true)"
[[ -z "$res" ]] && { fail_run "$n" "$state" "模型没有给出结构化结果（run $RUN_ID）"; exit 0; }
printf '%s' "$res" > "$RUN_DIR/result.json"
jq -r '.comment_markdown' <<<"$res" > "$RUN_DIR/comment.md"
privacy_ok "$RUN_DIR/comment.md" || { fail_run "$n" "$state" "评论草稿疑似含个人资料或密钥，已拦下未发（草稿在开发机 $RUN_DIR）"; exit 0; }

git -C "$REPO_DIR" fetch -q origin
next="$(jq -r '.next // .verdict' <<<"$res")"

if [[ "$mode" == plan ]]; then
  case "$next" in
    待执行)
      brief="$(jq -r .brief_path <<<"$res")"; br="$(jq -r .branch <<<"$res")"
      git -C "$REPO_DIR" cat-file -e "origin/staging:$brief" 2>/dev/null \
        || { fail_run "$n" "$state" "任务书 $brief 不在 origin/staging 上"; exit 0; }
      [[ "$br" =~ ^codex/[a-z0-9][a-z0-9-]*-[0-9]{8}$ ]] \
        || { fail_run "$n" "$state" "分支名 $br 不符合 codex/<主题>-<日期>"; exit 0; }
      post "$n" "<!-- agent:claude plan brief=$brief branch=$br base=$(git -C "$REPO_DIR" rev-parse origin/staging) -->" "$RUN_DIR/comment.md"
      set_state "$n" agent/待执行 ;;
    需拍板)
      post "$n" "<!-- agent:claude decision -->" "$RUN_DIR/comment.md"
      set_state "$n" agent/需拍板 ;;
    *) fail_run "$n" "$state" "模型给出未知的下一状态 $next"; exit 0 ;;
  esac
else
  verdict="$(jq -r .verdict <<<"$res")"; reviewed="$(jq -r .reviewed_sha <<<"$res")"
  [[ "$reviewed" == "$sha" ]] || { fail_run "$n" "$state" "验收结论针对 ${reviewed:0:9}，不是 Grok 回报的 ${sha:0:9}"; exit 0; }
  head_now="$(git -C "$REPO_DIR" ls-remote origin "refs/heads/$branch" | cut -f1)"
  [[ "$head_now" == "$sha" ]] || { fail_run "$n" "$state" "验收期间分支有新推送（${head_now:0:9}），下一轮重验"; exit 0; }
  case "$verdict" in
    pass)
      st="$(jq -r .staging_sha <<<"$res")"; cl="$(jq -r '.checklist_path // "-"' <<<"$res")"
      git -C "$REPO_DIR" merge-base --is-ancestor "$sha" "$st" 2>/dev/null \
        && git -C "$REPO_DIR" merge-base --is-ancestor "$st" origin/staging 2>/dev/null \
        || { fail_run "$n" "$state" "结论为通过，但 origin/staging 不包含 ${sha:0:9}（声称的 staging ${st:0:9}）"; exit 0; }
      post "$n" "<!-- agent:claude review sha=$sha verdict=pass staging=$st checklist=${cl:--} -->" "$RUN_DIR/comment.md"
      set_state "$n" agent/部署中 ;;
    fail)
      fix="$(jq -r .fix_brief_path <<<"$res")"
      git -C "$REPO_DIR" cat-file -e "origin/staging:$fix" 2>/dev/null \
        || { fail_run "$n" "$state" "结论为未通过，但修复单 $fix 不在 origin/staging 上"; exit 0; }
      post "$n" "<!-- agent:claude review sha=$sha verdict=fail brief=$fix branch=$branch -->" "$RUN_DIR/comment.md"
      if (( ${fails:-0} + 1 >= MAX_BOUNCES )); then
        set_state "$n" agent/需拍板
        post_text "$n" "<!-- agent:claude escalate -->" "@$OWNER 这一单已被验收打回 $(( ${fails:-0} + 1 )) 次，按规矩停下，等你决定是继续、改方向还是放弃。"
      else
        set_state "$n" agent/待执行
      fi ;;
    decision)
      post "$n" "<!-- agent:claude review sha=$sha verdict=decision -->" "$RUN_DIR/comment.md"
      set_state "$n" agent/需拍板 ;;
    *) fail_run "$n" "$state" "模型给出未知的验收结论 $verdict"; exit 0 ;;
  esac
fi
log "issue #$n: $mode done → $next"