amosblomqvist
2678f04e7a
THE MESSAGE IS THE UNIT OF COVERAGE (vision-extraction-coverage.md): a per-chat append-only ledger (coverage.jsonl) records which messages the pipeline has extracted, by content fingerprint over exactly what the extraction view sees (one shared line builder — core/coverage.ts); the uncovered remainder is DERIVED at read time, never dual-tracked. A quiz answer merging into the asking message re-opens only that message; plan-block data-part attach never re-opens anything. - The trigger (turn-service) replaces every-3-quiz-answers with uncovered-tokens >= EXTRACTION.chunkTokens (4096) — quiz-less sessions extract too, content size is the honest signal. - runExtraction is now chunked: token-budgeted batches of the oldest uncovered consecutive messages (a tool call + result never split), each merged batch checkpointing its messages' coverage atomically — an abort or error loses at most the in-flight batch; merged batches stay covered. - Observation refs are batch-tagged (obs:<batchTag>:<sourceId>): re-runs of the same batch dedupe; a re-opened message's fresh understanding lands as a new event. Fixes the old obs:p1 position-collision. - New API: GET /api/graph/coverage (exact per-session derived coverage + running flags, most-uncovered first) and POST /api/graph/coverage/extract (manual run for one session, 409 while in flight). - Graph view chrome: the coverage button opens a panel with every session's covered/uncovered tokens and a per-session Extract button — the manual answer to aborted runs, errors, and dormant tails. Renders even when the graph is empty: an empty graph with uncovered sessions is exactly when it matters. Polls only while open. - Notes imports keep the whole-file checkpoint path (coverage undefined). - Tests: pure-core coverage suite (11), chunked-pipeline suite (3: multi-batch + no-op, abort-keeps-earlier-batches + remainder re-run, re-open alone + data-part invisibility), panel render suite (5); pendingQuizAnswers and its tests deleted as dead code. 486/486. Live-smoked on real GLM: manual extract of "teach me modal realism" ran one batch, wrote 4 coverage entries, panel flipped to "1.3k covered · complete" with the button disabled, graph refetched (nodes 11), usage persisted with real stats.
85 lines
3.1 KiB
TypeScript
85 lines
3.1 KiB
TypeScript
import { renderToStaticMarkup } from "react-dom/server";
|
|
import { describe, it } from "node:test";
|
|
import assert from "node:assert/strict";
|
|
import { CoveragePanel, GraphCoverageControl } from "../components/graph-coverage.tsx";
|
|
|
|
// The extraction-coverage panel (vision-extraction-coverage.md, settled
|
|
// 2026-09-15): the graph view's window into WHAT the pipeline has covered,
|
|
// with a per-session "Extract" button for the uncovered remainder. Static
|
|
// markup can't click — the closed control and the panel body are pinned
|
|
// separately. (Interaction — the fetch + POST flow — is covered by the live
|
|
// smoke.)
|
|
|
|
describe("GraphCoverageControl", () => {
|
|
it("renders the coverage button in the chrome, closed by default", () => {
|
|
const html = renderToStaticMarkup(<GraphCoverageControl />);
|
|
assert.ok(html.includes("<button"));
|
|
assert.ok(html.includes("Extraction coverage"));
|
|
assert.ok(!html.includes('data-testid="coverage-panel"'), "the panel starts closed");
|
|
});
|
|
});
|
|
|
|
describe("CoveragePanel — exact per-session coverage data", () => {
|
|
const base = {
|
|
chatId: "chat_a",
|
|
title: "Modal logic",
|
|
updatedAt: "2026-09-15T00:00:00.000Z",
|
|
totalMessages: 12,
|
|
coveredMessages: 10,
|
|
uncoveredMessages: 2,
|
|
coveredTokens: 1536,
|
|
uncoveredTokens: 384,
|
|
running: false,
|
|
};
|
|
|
|
it("shows each session's covered/uncovered tokens and the Extract button", () => {
|
|
const html = renderToStaticMarkup(
|
|
<CoveragePanel chats={[base]} loaded isBusy={() => false} onExtract={() => {}} />,
|
|
);
|
|
assert.ok(html.includes("Modal logic"));
|
|
assert.ok(html.includes("1.5k covered"));
|
|
assert.ok(html.includes("384 uncovered"));
|
|
assert.ok(html.includes("(2 msgs)"));
|
|
assert.ok(html.includes(">Extract<"), "the uncovered session offers a manual extract");
|
|
});
|
|
|
|
it("a fully covered session shows · complete with a disabled Extract button", () => {
|
|
const html = renderToStaticMarkup(
|
|
<CoveragePanel
|
|
chats={[{ ...base, uncoveredMessages: 0, uncoveredTokens: 0, coveredMessages: 12, coveredTokens: 1920 }]}
|
|
loaded
|
|
isBusy={() => false}
|
|
onExtract={() => {}}
|
|
/>,
|
|
);
|
|
assert.ok(html.includes("· complete"));
|
|
assert.ok(html.includes("disabled"), "nothing to extract — the button is honest");
|
|
assert.ok(!html.includes(">Extract<") || html.includes("disabled"));
|
|
});
|
|
|
|
it("a running session shows extracting… and no clickable duplicate start", () => {
|
|
const html = renderToStaticMarkup(
|
|
<CoveragePanel
|
|
chats={[{ ...base, running: true }]}
|
|
loaded
|
|
isBusy={(c) => c.running}
|
|
onExtract={() => {}}
|
|
/>,
|
|
);
|
|
assert.ok(html.includes("extracting…"));
|
|
assert.ok(html.includes(">Running<"));
|
|
assert.ok(html.includes("disabled"), "single-flight: the in-flight run can't be double-started");
|
|
});
|
|
|
|
it("all-covered panel: the nothing-pending line, not a row list", () => {
|
|
const html = renderToStaticMarkup(
|
|
<CoveragePanel
|
|
chats={[{ ...base, uncoveredMessages: 0, uncoveredTokens: 0 }]}
|
|
loaded
|
|
isBusy={() => false}
|
|
onExtract={() => {}}
|
|
/>,
|
|
);
|
|
assert.ok(html.includes("Every session is fully extracted — nothing pending."));
|
|
});
|
|
}); |