Bisect provider-rejected batches in triage and deep assessment

DeepSeek's content filter rejects a whole request (400 "Content Exists
Risk") when one article trips it, which cost the other articles in the
batch their assessment and retried them every run. New curate/batch.rs
runs both stages through a bisecting runner: a rejected batch is split
until the offending article is isolated, that article is retried once on
the editor provider when it is a different one, and a still-rejected
article is recorded as a provider_rejected assessment row so it is not
retried for assessment_reuse_days. Cache reuse accepts rows from either
configured model. Each stage logs reused/requested/rejected counts, the
curation: line shows rejections when non-zero, explain prints them, and
the llm_assess span reports the deep-set size.

Implemented by a Claude agent from an orchestrator brief; verified
fmt/clippy(-W dead_code)/test green (354 lib tests).

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01A1rCLQeKBgnBo3oTgHuTMe

src/curate/admit.rs

@@ -494,4 +494,49 @@ mod tests {
         .expect("thin row");
         assert_eq!(reason, "recently_rejected");
     }
+
+    #[tokio::test]
+    async fn provider_rejected_rows_do_not_mark_an_article_recently_rejected() {
+        let dir = tempfile::tempdir().expect("tempdir");
+        let db = Db::open_and_migrate(&dir.path().join("hygiene.db"))
+            .await
+            .expect("db");
+        sqlx::query(
+            "INSERT INTO articles (id, canonical_url, title, first_seen) VALUES
+             (1, 'https://example.com/1', 'Refused', '2026-09-02T00:00:00Z')",
+        )
+        .execute(db.pool())
+        .await
+        .expect("article");
+        sqlx::query(
+            "INSERT INTO article_assessments
+             (article_id, stage, model, prompt_version, score, fit, kind, rationale, assessed_at)
+             VALUES (1, 'triage', 'model', 1, NULL, NULL, 'provider_rejected',
+                     'deepseek: Content Exists Risk', '2026-09-02T04:00:00Z'),
+                    (1, 'deep', 'model', 1, NULL, NULL, 'provider_rejected',
+                     'deepseek: Content Exists Risk', '2026-09-02T04:00:00Z')",
+        )
+        .execute(db.pool())
+        .await
+        .expect("rejection rows");
+        let run_id = db
+            .start_run(
+                "2026-09-02".parse().expect("date"),
+                "2026-09-02T05:30:00Z".parse().expect("timestamp"),
+            )
+            .await
+            .expect("run");
+        let eligible = hygiene(
+            &db,
+            run_id,
+            vec![article(1, "Refused", 500)],
+            "2026-09-02".parse().expect("date"),
+            &CurationConfig::default(),
+            "2026-09-02T05:30:00Z".parse().expect("timestamp"),
+        )
+        .await
+        .expect("hygiene");
+        assert_eq!(eligible.len(), 1, "a NULL score is not a low score");
+        assert_eq!(eligible[0].article.id, 1);
+    }
 }