Files
clawmates/crates/cm-api/src/routes/library.rs
T
Omar SobhandClaude Opus 5 ad89ef94cd
ci / gates (push) Failing after 7s
ci / rust (push) Skipped
ci / frontend (push) Skipped
ci / e2e (push) Skipped
ci / publish (push) Skipped
feat(library): attribute a run to a mission, and prove what it contributed
`corpus_items.mission_id` has existed since the table landed and nothing
could populate it. `POST /api/library/runs` now accepts `missionId`, which
is the seam the wizard needs: a mission-driven run is the same run, tagged.

`corpus::contributed()` answers the question a continuous mission has to
be able to answer — did THIS run add anything new. Because `record` never
reassigns mission_id on conflict, the mission that first found a source
keeps the credit, so a rerun cannot inflate its own count by re-recording
what an earlier run already held. The test asserts exactly that: two
missions see the same paper, the finder reports 1 and the rerun reports 0.

This is the check the 0030-0044 generation of continuous research did not
have. It could run weekly forever and every run looked like success.

The test also earned its FK: the first version attributed to a bare UUID
and the database refused it. Attribution to a mission that does not exist
is not attribution, so the test now seeds real mission rows.

400 tests, clippy clean.

Co-Authored-By: Claude Opus 5 <[email protected]>
2026-08-03 11:43:41 -07:00

163 lines
5.1 KiB
Rust

//! The paper library: trigger a run, see what it holds.
//!
//! Thin on purpose. The work lives in [`crate::library`]; this exposes it so
//! a run can be started by a person, a schedule, or the UI rather than only
//! from an integration test.
use axum::extract::{Query, State};
use axum::Json;
use serde::{Deserialize, Serialize};
use serde_json::{json, Value};
use crate::{ApiError, AppState, Authed};
/// Default corpus + repo. Single-operator deployment, so these are constants
/// rather than another table to keep in sync; a second library becomes a
/// request field the day one exists.
const DEFAULT_CORPUS: &str = "valhalla-vault";
const DEFAULT_VAULT_URL: &str = "https://git.redclaw.dev/redclaw/valhalla-vault.git";
#[derive(Deserialize)]
pub struct RunRequest {
/// arXiv queries. Omitted → the topics this project is actually working on.
#[serde(default)]
pub topics: Option<Vec<String>>,
/// Papers per topic. Clamped, because a broad first run against an empty
/// library can otherwise pull hundreds of PDFs in one go.
#[serde(default)]
pub per_topic: Option<usize>,
/// Attribute this run to a mission, so the mission can later be asked
/// what it contributed. `corpus_items.mission_id` has existed since the
/// table landed; without this field nothing could ever populate it.
#[serde(default, rename = "missionId")]
pub mission_id: Option<uuid::Uuid>,
}
#[derive(Serialize)]
pub struct RunResponse {
pub candidates: usize,
pub already_had: usize,
pub shelved: Vec<String>,
pub failed: Vec<Value>,
pub notes: Vec<String>,
pub branch: String,
pub pushed: bool,
pub merged: bool,
pub merge_reason: String,
pub error: Option<String>,
/// A run that errored on nothing. Reported explicitly so a caller does not
/// have to infer health from an empty `shelved` list — a quiet week and a
/// broken run both shelve zero papers.
pub healthy: bool,
}
/// POST /api/library/runs — harvest now.
pub async fn run(
State(state): State<AppState>,
Authed(user): Authed,
Json(req): Json<RunRequest>,
) -> Result<Json<RunResponse>, ApiError> {
let blobs = state
.blobs
.clone()
.ok_or_else(|| {
eprintln!("library: blob storage is not configured; cannot shelve PDFs");
ApiError::Internal
})?;
let topics = req
.topics
.filter(|t| !t.is_empty())
.unwrap_or_else(crate::library::default_topics);
let per_topic = req.per_topic.unwrap_or(5).clamp(1, 25);
// Work under the missions root: it is already a writable volume with room
// for checkouts, and it is swept, so a crashed run cannot leak a vault
// clone forever.
let work_root = std::env::temp_dir().join("clawmates-library");
let out = crate::library::run_to_vault(
&state.pool,
&blobs,
user.workspace_id.as_uuid(),
DEFAULT_CORPUS,
DEFAULT_VAULT_URL,
&work_root,
&topics,
per_topic,
req.mission_id,
)
.await
.map_err(|e| {
// The reason belongs in the log, not in the response: it can carry a
// remote URL and git stderr.
eprintln!("library: run failed: {e}");
ApiError::Internal
})?;
Ok(Json(RunResponse {
candidates: out.harvest.candidates,
already_had: out.harvest.already_had,
shelved: out.harvest.shelved.clone(),
failed: out
.harvest
.failed
.iter()
.map(|(id, why)| json!({ "source_id": id, "error": why }))
.collect(),
notes: out.harvest.notes_written.clone(),
healthy: out.harvest.healthy(),
branch: out.branch,
pushed: out.pushed,
merged: out.merged,
merge_reason: out.merge_reason,
error: out.error,
}))
}
#[derive(Deserialize)]
pub struct ListQuery {
#[serde(default)]
pub kind: Option<String>,
#[serde(default)]
pub limit: Option<i64>,
}
/// `(source_id, title, url, note path)` as stored.
type CorpusRow = (String, Option<String>, Option<String>, Option<String>);
/// GET /api/library/items — what the library holds.
pub async fn list(
State(state): State<AppState>,
Authed(user): Authed,
Query(q): Query<ListQuery>,
) -> Result<Json<Vec<Value>>, ApiError> {
let limit = q.limit.unwrap_or(100).clamp(1, 500);
let kind = q.kind.unwrap_or_else(|| "source".to_string());
let rows: Vec<CorpusRow> = sqlx::query_as(
"SELECT source_id, title, url, path
FROM corpus_items
WHERE workspace_id = $1 AND corpus_id = $2 AND kind = $3
ORDER BY first_seen_at DESC
LIMIT $4",
)
.bind(user.workspace_id.as_uuid())
.bind(DEFAULT_CORPUS)
.bind(kind)
.bind(limit)
.fetch_all(&state.pool)
.await
.map_err(|e| {
eprintln!("library: list corpus: {e}");
ApiError::Internal
})?;
Ok(Json(
rows.into_iter()
.map(|(source_id, title, url, path)| {
json!({ "sourceId": source_id, "title": title, "url": url, "notePath": path })
})
.collect(),
))
}