feat(cost): persist run_id on generated posts + back-populate for v0.8.1 reaper

The orphan-research-row reaper (upcoming commit) needs a cheap way to
answer "which posts belong to this run_id?" when amortizing a stranded
`llm_research` row back to its siblings. Relying on the generation_log
post_id column is circular: if the pipeline died before amortize_research
ran, we'd trust the same table we're trying to repair.

- `Publisher::build_meta()` now accepts `?string $run_id` and writes
  `_prautoblogger_run_id => $run_id` when non-empty. Null/empty preserves
  existing null-safe legacy behaviour.
- `Publisher::create_post()` forwards the $run_id it already receives
  into build_meta — one-line plumbing, no new parameters at call sites.
- `Activator::backpopulate_run_id_meta_v081()` runs once per site,
  gated by `prautoblogger_migrated_run_id_meta_v081` option. Walks
  `wp_prautoblogger_generation_log`, pairs (post_id, min(run_id)),
  writes `_prautoblogger_run_id` on any post that doesn't already have
  it. Uses `metadata_exists()` so it's a no-op on re-run.
- Activator also schedules the new daily `prautoblogger_reap_orphan_research_rows`
  cron at 03:15 — 15 min after the primary generation cron — so live
  pipelines have time to finish amortizing cleanly before the reaper scans.
- Deactivator unschedules the new hook alongside the existing cron hooks.

No user-visible behaviour change yet. The reaper handler ships in the
next commit; this one just ensures it will have the data + schedule it
needs when it lands.

Part of the v0.8.1 bundle (thread research-cost-reaper).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

includes/class-activator.php

@@ -28,6 +28,7 @@ class PRAutoBlogger_Activator {
 		self::create_tables();
 		self::set_default_options();
 		self::schedule_cron();
+		self::backpopulate_run_id_meta_v081();
 
 		// Store the DB version so we can run migrations on future updates.
 		update_option( 'prautoblogger_db_version', PRAUTOBLOGGER_DB_VERSION, false );
@@ -225,5 +226,62 @@ class PRAutoBlogger_Activator {
 		if ( ! wp_next_scheduled( 'prautoblogger_collect_metrics' ) ) {
 			wp_schedule_event( time() + HOUR_IN_SECONDS, 'prautoblogger_six_hours', 'prautoblogger_collect_metrics' );
 		}
+
+		// v0.8.1: daily reaper for orphan `llm_research` rows. Pinned to
+		// 03:15 so it runs 15 min after the primary generation cron, giving
+		// any live pipeline time to finish and call amortize_research_costs
+		// cleanly before the reaper scans.
+		if ( ! wp_next_scheduled( 'prautoblogger_reap_orphan_research_rows' ) ) {
+			$tomorrow = strtotime( 'tomorrow 03:15' );
+			if ( false !== $tomorrow ) {
+				wp_schedule_event( $tomorrow, 'daily', 'prautoblogger_reap_orphan_research_rows' );
+			}
+		}
+	}
+
+	/**
+	 * One-shot v0.8.1 migration — back-populate `_prautoblogger_run_id`
+	 * post_meta for existing posts from their gen-log rows.
+	 *
+	 * Lets the orphan-research-row reaper (v0.8.1+) attribute historic
+	 * orphan rows to sibling posts via post_meta lookup, without having
+	 * to walk the generation_log table. Gated by
+	 * `prautoblogger_migrated_run_id_meta_v081` so it runs exactly once
+	 * per site.
+	 *
+	 * Side effects: adds post_meta rows for existing PRAutoBlogger posts
+	 *               that don't already have `_prautoblogger_run_id`.
+	 *
+	 * @return void
+	 */
+	private static function backpopulate_run_id_meta_v081(): void {
+		if ( get_option( 'prautoblogger_migrated_run_id_meta_v081' ) ) {
+			return;
+		}
+
+		global $wpdb;
+		$gen_log = $wpdb->prefix . 'prautoblogger_generation_log';
+
+		// For each (post_id, run_id) pair present in the gen-log, write
+		// the run_id meta if it's not already set. Uses the first run_id
+		// seen per post — in practice each post is linked to exactly one run.
+		// phpcs:ignore WordPress.DB.DirectDatabaseQuery.DirectQuery
+		$pairs = $wpdb->get_results(
+			"SELECT post_id, MIN(run_id) AS run_id FROM {$gen_log}
+			WHERE post_id IS NOT NULL AND run_id IS NOT NULL AND run_id != ''
+			GROUP BY post_id"
+		);
+
+		if ( is_array( $pairs ) ) {
+			foreach ( $pairs as $row ) {
+				$post_id = (int) ( $row->post_id ?? 0 );
+				$run_id  = (string) ( $row->run_id ?? '' );
+				if ( $post_id > 0 && '' !== $run_id && ! metadata_exists( 'post', $post_id, '_prautoblogger_run_id' ) ) {
+					update_post_meta( $post_id, '_prautoblogger_run_id', $run_id );
+				}
+			}
+		}
+
+		update_option( 'prautoblogger_migrated_run_id_meta_v081', '1' );
 	}
 }

includes/class-deactivator.php

@@ -36,6 +36,7 @@ class PRAutoBlogger_Deactivator {
 		$hooks = [
 			'prautoblogger_daily_generation',
 			'prautoblogger_collect_metrics',
+			'prautoblogger_reap_orphan_research_rows',
 		];
 
 		foreach ( $hooks as $hook ) {

includes/core/class-publisher.php

@@ -87,7 +87,7 @@ class PRAutoBlogger_Publisher {
 			'post_status'  => $post_status,
 			'post_type'    => 'post',
 			'post_author'  => PRAutoBlogger_Post_Assembler::get_default_author_id(),
-			'meta_input'   => $this->build_meta( $idea, $review ),
+			'meta_input'   => $this->build_meta( $idea, $review, $run_id ),
 		];
 
 		/** @see class-prautoblogger.php — listeners registered in main loader. */
@@ -120,15 +120,22 @@ class PRAutoBlogger_Publisher {
 	/**
 	 * Build post_meta array for generation metadata.
 	 *
+	 * The `_prautoblogger_run_id` key (added v0.8.1) lets the orphan-research
+	 * reaper attribute an orphan `llm_research` row back to its sibling
+	 * articles without re-walking the gen_log table. See
+	 * core/class-research-reaper.php.
+	 *
 	 * @param PRAutoBlogger_Article_Idea     $idea
 	 * @param PRAutoBlogger_Editorial_Review $review
+	 * @param string|null                    $run_id Pipeline run UUID, or null in legacy paths.
 	 * @return array<string, mixed>
 	 */
 	private function build_meta(
 		PRAutoBlogger_Article_Idea $idea,
-		PRAutoBlogger_Editorial_Review $review
+		PRAutoBlogger_Editorial_Review $review,
+		?string $run_id = null
 	): array {
-		return [
+		$meta = [
 			'_prautoblogger_generated'       => '1',
 			'_prautoblogger_analysis_id'     => $idea->get_analysis_id(),
 			'_prautoblogger_source_ids'      => wp_json_encode( $idea->get_source_ids() ),
@@ -143,5 +150,9 @@ class PRAutoBlogger_Publisher {
 			'_prautoblogger_article_type'    => $idea->get_article_type(),
 			'_prautoblogger_target_keywords' => wp_json_encode( $idea->get_target_keywords() ),
 		];
+		if ( null !== $run_id && '' !== $run_id ) {
+			$meta['_prautoblogger_run_id'] = $run_id;
+		}
+		return $meta;
 	}
 }