Files
fusion/scripts/__tests__/reconcile-task-state-consistency.test.mjs
gsxdsm 3a016b1f17 fix(scripts): four FNXC stamps carried hour 26, and main has been red on them (#3010)
## `main` is currently red on `check-fnxc-future-dates`

Four stamps read `2026-07-30-26:10` — an hour that cannot exist.

They're exactly what #2995 taught this gate to catch. That PR landed the
hour validation (`00-23`) *after* #2999 had already merged these four,
so the gate started reporting a defect that was already sitting there
rather than one introduced afterwards. **The guard is working**; nothing
was checking before it.

```
scripts/lib/backend-db.mjs:41
scripts/reconcile-task-state-consistency.mjs:8, :51
scripts/__tests__/reconcile-task-state-consistency.test.mjs:109
```

Corrected by **literal normalisation** — 26:10 on the 30th *is* 02:10 on
the 31st — rather than flattening them to an arbitrary in-range hour.
AGENTS.md specifies `yyyy-MM-dd-hh:mm`, and the stamp exists to give a
readable why-does-this-exist trail, so the ordering is the part worth
preserving.

## The baseline tightening rides along, and it's a date rollover

Stamps written yesterday as `2026-07-31` were future *then* and were
baselined as such. Today they're past, so **176 files ratchet to zero**.
Nobody did anything.

The gate rewrites the baseline as a side effect and exits 0, so leaving
it uncommitted dirties the tree on every subsequent run **for everyone**
— which is why it belongs in this commit rather than a later one.
Re-recording on a decrease is the rule this gate and its siblings
already state.

Worth knowing about the design, since I wrote it: this churn recurs
whenever a day boundary passes with future-dated stamps in the baseline,
and it shrinks only as people stop writing them — which is the behaviour
the gate exists to produce. **93 files still carry a non-zero
allowance**, so the drain isn't finished. If it stays noisy once those
clear, the gate's fail-on-tighten contract is the thing to revisit, not
the stamps.

## Measured

| check | result |
|---|---|
| gate | red before, **exit 0 after**, stable across two consecutive
runs |
| baseline | −176/+25 entries, all date-rollover |
| inert-seam · sql-literal · lane-wiring · census | all green |
| reconciler's own suite | green |

## One correction to a claim I made earlier this session

While investigating I reported the gate as hanging for 600s. It wasn't —
the harness killed the process (exit 144) and the empty output made it
look like a stall. The gate completes in seconds. Noting it because I
nearly filed a performance bug against a healthy script.

Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-31 00:36:21 -07:00

169 lines
5.6 KiB
JavaScript

import test from "node:test";
import assert from "node:assert/strict";
import { findTaskStateInconsistencies, runReconciliation } from "../reconcile-task-state-consistency.mjs";
function createStore(tasks) {
const state = new Map(tasks.map((task) => [task.id, { ...task }]));
const calls = { moveTask: 0, logEntry: 0 };
return {
calls,
async listTasks() {
return Array.from(state.values()).map((task) => ({ ...task }));
},
async moveTask(id, toColumn) {
calls.moveTask += 1;
const task = state.get(id);
assert.ok(task);
assert.equal(toColumn, "done");
if (task.column === "done") {
task.status = undefined;
task.error = undefined;
task.worktree = undefined;
task.blockedBy = undefined;
task.recoveryRetryCount = undefined;
task.nextRecoveryAt = undefined;
}
return { ...task };
},
async logEntry(id, action, outcome) {
calls.logEntry += 1;
assert.equal(action, "FN-4000 reconciliation");
assert.match(outcome, /FN-4000 reconciliation/);
return { id };
},
getTask(id) {
return state.get(id);
},
};
}
test("detects known bad done/failed fixture", () => {
const issues = findTaskStateInconsistencies({
id: "FN-X",
column: "done",
status: "failed",
error: "oops",
worktree: "wt",
});
assert.deepEqual(issues, [
"done-task-has-transient-failure-state",
"failed-status-outside-in-review",
]);
});
test("dry-run reports inconsistency without mutating", async () => {
const store = createStore([
{ id: "FN-1", column: "done", status: "failed", error: "bad" },
{ id: "FN-2", column: "in-review", status: "failed" },
]);
const result = await runReconciliation({ store, dryRun: true });
assert.equal(result.findings.length, 1);
assert.equal(result.findings[0].taskId, "FN-1");
assert.equal(store.calls.moveTask, 0);
assert.equal(store.calls.logEntry, 0);
assert.equal(store.getTask("FN-1").status, "failed");
});
test("apply reconciles done task and emits exactly one note", async () => {
const store = createStore([
{
id: "FN-3990",
column: "done",
status: "failed",
error: "stale",
worktree: "worktrees/old",
blockedBy: "FN-1",
recoveryRetryCount: 2,
nextRecoveryAt: "2026-05-11T00:00:00.000Z",
},
]);
const result = await runReconciliation({
store,
dryRun: false,
noteByTaskId: {
"FN-3990": "FN-4000 reconciliation: custom note",
},
});
assert.equal(result.findings.length, 1);
assert.equal(result.actions[0].action, "reconciled");
assert.equal(store.calls.moveTask, 1);
assert.equal(store.calls.logEntry, 1);
const task = store.getTask("FN-3990");
assert.equal(task.status, undefined);
assert.equal(task.error, undefined);
assert.equal(task.worktree, undefined);
assert.equal(task.blockedBy, undefined);
assert.equal(task.recoveryRetryCount, undefined);
assert.equal(task.nextRecoveryAt, undefined);
});
/*
FNXC:OperatorScriptLaneAssumptions 2026-07-31-02:10:
THE INVARIANT: both consistency checks ask the task's OWN lanes, and they failed in OPPOSITE directions.
Keyed on the literals, `hasDoneTransient` (`column === "done"`) NEVER fires on a renamed board, so a
finished card still holding a worktree and `status:"failed"` goes unreported and unnormalized. Meanwhile
`failed-status-outside-in-review` (`column !== "in-review"`) fires for EVERY failed card, because no
column equals the literal — a report listing the whole board, which looks like the tool working.
Reverted, the first case returns [] (the miss) and the second returns the spurious flag (the flood).
*/
test("reports stale transient state in a RENAMED complete lane", () => {
/* No `status:"failed"` here on purpose: it would ALSO trip the second check (a failed card outside
the review lane is genuinely flagged), which would blur which of the two this case is pinning. */
const task = { id: "FN-R1", column: "shipped", worktree: "/tmp/wt" };
assert.deepEqual(
findTaskStateInconsistencies(task, { complete: "shipped", review: "checking" }),
["done-task-has-transient-failure-state"],
);
});
test("does NOT flag a failed card that is sitting in the board's own review lane", () => {
const task = { id: "FN-R2", column: "checking", status: "failed" };
assert.deepEqual(findTaskStateInconsistencies(task, { complete: "shipped", review: "checking" }), []);
});
test("still flags a failed card outside the resolved review lane", () => {
const task = { id: "FN-R3", column: "building", status: "failed" };
assert.deepEqual(
findTaskStateInconsistencies(task, { complete: "shipped", review: "checking" }),
["failed-status-outside-in-review"],
);
});
test("unresolved lanes keep exactly the legacy behaviour", () => {
assert.deepEqual(
findTaskStateInconsistencies({ id: "FN-L", column: "done", status: "failed" }),
["done-task-has-transient-failure-state", "failed-status-outside-in-review"],
);
});
test("runReconciliation normalizes a renamed complete lane by moving the card to its OWN column", async () => {
const moves = [];
const store = {
async listTasks() { return [{ id: "FN-R4", column: "shipped", status: "failed", worktree: "/tmp/w" }]; },
async moveTask(id, toColumn) { moves.push([id, toColumn]); return { id }; },
async logEntry() { return { id: "FN-R4" }; },
};
const result = await runReconciliation({
store,
dryRun: false,
resolveLanes: async () => ({ complete: "shipped", review: "checking" }),
});
assert.deepEqual(moves, [["FN-R4", "shipped"]]);
assert.equal(result.actions[0].action, "reconciled");
});