fix: Migrate review-pr.sh to SDK + pr-lifecycle (#800)

Extract agent_run() into shared lib/agent-sdk.sh to eliminate code
duplication between dev-agent.sh and review-pr.sh (CI dedup check).

Rewrite review-pr.sh from tmux-based agent-session.sh to synchronous
claude -p invocations via shared agent-sdk.sh, matching the SDK pattern
from dev-agent.sh (#798).

Key changes:
- Create lib/agent-sdk.sh with shared agent_run() function
- Both dev-agent.sh and review-pr.sh now source lib/agent-sdk.sh
  instead of defining agent_run() inline
- Replace agent-session.sh (tmux + monitor_phase_loop) with agent_run()
- Add .sid file for session continuity: re-reviews resume the original
  session via --resume, so Claude remembers its prior review
- Use worktree.sh for worktree cleanup
- Remove phase file signaling — completion is automatic when claude -p
  returns
- Keep all review business logic unchanged

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

dev/dev-agent.sh

@@ -29,6 +29,7 @@ source "$(dirname "$0")/../lib/issue-lifecycle.sh"
 source "$(dirname "$0")/../lib/worktree.sh"
 source "$(dirname "$0")/../lib/pr-lifecycle.sh"
 source "$(dirname "$0")/../lib/mirrors.sh"
+source "$(dirname "$0")/../lib/agent-sdk.sh"
 
 # Auto-pull factory code to pick up merged fixes before any logic runs
 git -C "$FACTORY_ROOT" pull --ff-only origin main 2>/dev/null || true
@@ -56,43 +57,6 @@ status() {
   log "$*"
 }
 
-# =============================================================================
-# agent_run — synchronous Claude invocation (one-shot claude -p)
-# =============================================================================
-# Usage: agent_run [--resume SESSION_ID] [--worktree DIR] PROMPT
-# Sets: _AGENT_SESSION_ID (updated each call, persisted to SID_FILE)
-_AGENT_SESSION_ID=""
-
-agent_run() {
-  local resume_id="" worktree_dir=""
-  while [[ "${1:-}" == --* ]]; do
-    case "$1" in
-      --resume) shift; resume_id="${1:-}"; shift ;;
-      --worktree) shift; worktree_dir="${1:-}"; shift ;;
-      *) shift ;;
-    esac
-  done
-  local prompt="${1:-}"
-
-  local -a args=(-p "$prompt" --output-format json --dangerously-skip-permissions --max-turns 200)
-  [ -n "$resume_id" ] && args+=(--resume "$resume_id")
-  [ -n "${CLAUDE_MODEL:-}" ] && args+=(--model "$CLAUDE_MODEL")
-
-  local run_dir="${worktree_dir:-$(pwd)}"
-  local output
-  log "agent_run: starting (resume=${resume_id:-(new)}, dir=${run_dir})"
-  output=$(cd "$run_dir" && timeout "${CLAUDE_TIMEOUT:-7200}" claude "${args[@]}" 2>>"$LOGFILE") || true
-
-  # Extract and persist session_id
-  local new_sid
-  new_sid=$(printf '%s' "$output" | jq -r '.session_id // empty' 2>/dev/null) || true
-  if [ -n "$new_sid" ]; then
-    _AGENT_SESSION_ID="$new_sid"
-    printf '%s' "$new_sid" > "$SID_FILE"
-    log "agent_run: session_id=${new_sid:0:12}..."
-  fi
-}
-
 # =============================================================================
 # CLEANUP
 # =============================================================================