feat(harvest): one run — find, skip what we hold, shelve the rest

Turns the parts into a job. Order is the point: the checkmark list is consulted BEFORE anything downloads. Checking afterwards would still dedupe the catalogue while re-downloading every paper we already have, every week, forever. Two properties the tests pin down, both learned the hard way this week: - A quiet week is not a failure. `shelved == 0` with no errors is a healthy run against a mature library; `shelved == 0` with errors is broken. Harvest::healthy() and ::added_anything() keep those apart rather than collapsing them into one ambiguous "did nothing". - A failed download leaves the paper UNSEEN. Checking it off before the PDF is safely shelved would mean one transient network error retires that paper permanently. The checkmark is written last, after the bytes and the note are both on disk. The skip test gives every candidate a pdf_url pointing at a closed port, so if the skip ever regresses the test fails loudly instead of quietly re-fetching. Live end-to-end against arXiv, run twice: RUN1 3 candidates, 0 already held, 3 shelved, 0 failed RUN2 3 candidates, 3 already held, 0 shelved, 0 failed Library<'_> groups the five values that always describe one library; passing them loose is how a run shelves into one place and catalogues into another (also silences clippy::too_many_arguments honestly rather than by allow). 391 tests, clippy clean. Co-Authored-By: Claude Opus 5 <[email protected]>
2026-08-03 07:53:56 -07:00
parent e4a395b72e
commit 30eaa50c50
5 changed files with 383 additions and 0 deletions
@@ -0,0 +1,153 @@
+//! A second run must not re-download what the first run already shelved.
+
+use cm_api::{corpus, harvest, papers::Paper};
+use std::sync::Arc;
+use uuid::Uuid;
+
+async fn workspace(pool: &sqlx::PgPool) -> Uuid {
+    let ws = Uuid::now_v7();
+    sqlx::query("INSERT INTO workspaces (id, name, plan) VALUES ($1,'t','team')")
+        .bind(ws)
+        .execute(pool)
+        .await
+        .unwrap();
+    ws
+}
+
+fn paper(id: &str) -> Paper {
+    Paper {
+        arxiv_id: id.into(),
+        title: format!("Paper {id}"),
+        authors: vec!["Ada Lovelace".into()],
+        summary: "A summary.".into(),
+        published: "2026-01-15T10:00:00Z".into(),
+        // Deliberately unreachable: if the skip works, this is never fetched.
+        pdf_url: "http://127.0.0.1:1/never.pdf".into(),
+    }
+}
+
+/// The load-bearing behaviour. Every candidate is already on the checkmark
+/// list, and every `pdf_url` points at a closed port — so if the run tries to
+/// download anything at all, it fails loudly instead of passing quietly.
+#[tokio::test]
+async fn papers_we_already_hold_are_never_downloaded_again() {
+    let pool = cm_testkit::test_pool().await;
+    let ws = workspace(&pool).await;
+    let tmp = tempfile::tempdir().unwrap();
+    let blobs: Arc<dyn cm_files::BlobStore> =
+        Arc::new(cm_files::LocalBlobStore::new(tmp.path().join("blobs")));
+    let vault = tmp.path().join("vault");
+
+    let candidates = vec![paper("2401.11111"), paper("2401.22222")];
+    for p in &candidates {
+        corpus::record(
+            &pool, ws, "lib", "source", &p.source_id(),
+            Some(&p.title), None, None, "h", None,
+        )
+        .await
+        .unwrap();
+    }
+
+    let lib = harvest::Library {
+        pool: &pool, blobs: &blobs, workspace_id: ws,
+        corpus_id: "lib", vault_root: &vault,
+    };
+    let h = harvest::shelve(&lib, &candidates, None).await.unwrap();
+
+    assert_eq!(h.candidates, 2);
+    assert_eq!(h.already_had, 2, "both were already held");
+    assert!(h.shelved.is_empty());
+    assert!(
+        h.failed.is_empty(),
+        "nothing should have been fetched at all, but got: {:?}",
+        h.failed
+    );
+    assert!(h.healthy(), "a fully-known batch is a healthy quiet week");
+    assert!(!h.added_anything(), "and it added nothing");
+    assert!(!vault.exists(), "no notes written for papers we already had");
+}
+
+/// A paper that cannot be downloaded must NOT be checked off — otherwise one
+/// transient network failure means that paper is never retried.
+#[tokio::test]
+async fn a_failed_download_leaves_the_paper_unseen_for_next_time() {
+    let pool = cm_testkit::test_pool().await;
+    let ws = workspace(&pool).await;
+    let tmp = tempfile::tempdir().unwrap();
+    let blobs: Arc<dyn cm_files::BlobStore> =
+        Arc::new(cm_files::LocalBlobStore::new(tmp.path().join("blobs")));
+    let vault = tmp.path().join("vault");
+
+    let candidates = vec![paper("2401.33333")];
+    let lib = harvest::Library {
+        pool: &pool, blobs: &blobs, workspace_id: ws,
+        corpus_id: "lib", vault_root: &vault,
+    };
+    let h = harvest::shelve(&lib, &candidates, None).await.unwrap();
+
+    assert_eq!(h.already_had, 0);
+    assert!(h.shelved.is_empty());
+    assert_eq!(h.failed.len(), 1, "the unreachable fetch must be reported");
+    assert!(!h.healthy(), "a failed fetch is not a quiet week");
+
+    assert!(
+        !corpus::seen(&pool, ws, "lib", "arxiv:2401.33333")
+            .await
+            .unwrap(),
+        "a paper we failed to get must stay unseen so a later run retries it"
+    );
+}
+
+/// Live end-to-end: search arXiv, shelve genuinely new papers, then confirm a
+/// second identical run adds nothing. Ignored by default (network + Postgres):
+/// `cargo test -p cm-api --test harvest_run live_ -- --ignored --nocapture`
+#[tokio::test]
+#[ignore]
+async fn live_end_to_end_run_then_rerun() {
+    let pool = cm_testkit::test_pool().await;
+    let ws = workspace(&pool).await;
+    let tmp = tempfile::tempdir().unwrap();
+    let blobs: Arc<dyn cm_files::BlobStore> =
+        Arc::new(cm_files::LocalBlobStore::new(tmp.path().join("blobs")));
+    let vault = tmp.path().join("vault");
+
+    let lib = harvest::Library {
+        pool: &pool, blobs: &blobs, workspace_id: ws,
+        corpus_id: "lib", vault_root: &vault,
+    };
+    let first = harvest::run(&lib, "all:agentic AND all:topology", 3, None)
+        .await
+        .unwrap();
+    println!("RUN1 {}", first.summary());
+    for n in &first.notes_written {
+        println!("  note: {n}");
+    }
+    assert!(first.healthy(), "failures: {:?}", first.failed);
+    assert!(first.added_anything(), "first run should find something new");
+
+    // Every note must be readable back through the corpus parser, or the
+    // catalogue cannot rebuild the checkmark list.
+    for rel in &first.notes_written {
+        let text = std::fs::read_to_string(vault.join(rel)).unwrap();
+        let parsed = corpus::parse_note(rel, &text);
+        assert!(
+            parsed
+                .declared_source_id
+                .as_deref()
+                .is_some_and(|s| s.starts_with("arxiv:")),
+            "note {rel} lost its identity"
+        );
+    }
+
+    let second = harvest::run(&lib, "all:agentic AND all:topology", 3, None)
+        .await
+        .unwrap();
+    println!("RUN2 {}", second.summary());
+    assert!(second.healthy());
+    assert!(
+        !second.added_anything(),
+        "a rerun must add nothing — got {:?}",
+        second.shelved
+    );
+    assert_eq!(second.already_had, second.candidates);
+}