The "no covering tests found" flag only inspected a symbol's direct callers, so helpers exercised transitively by tests (logDebug runs 1,471x under npm test) were reported untested — wrong for ~40% of flagged symbols per the issue's measurement. The check now BFSes up the caller graph (3 hops, 64-lookup budget per entry) and reports indirect coverage as "tested via callers: <files>". When nothing is found it claims only what was measured — "no tests found within 3 caller hops", or the weaker "no test calls this directly" if the budget ran out — and drops the warning glyph. Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Fable 5
parent
38580e0b04
commit
f6ac7b36e6
@@ -17,6 +17,7 @@ and adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
|
||||
- On Windows, the Claude Code prompt hook written by `codegraph install` failed with "command not found" when hooks run through Git Bash, which needs the `.cmd` extension to find the launcher. The installer now writes the platform-correct command, and re-running `codegraph install` (or `codegraph upgrade`) repairs an existing install in place. (#1466)
|
||||
- Python classes used as values — `return SomeSerializer` from a factory method, `handler = SomeClass` aliases, registry dicts and lists, and classes passed as arguments — now produce reference edges in the graph. Previously these idioms were invisible, so on Django and Django REST Framework projects, asking for a serializer's callers or the impact of editing it missed the views that actually use it. Re-index after upgrading to pick up the new edges. (#1478)
|
||||
- When a file changed on disk after its last index sync, `codegraph_node` and `codegraph_explore` could return a different symbol's code under the requested name — current file bytes cut at outdated line positions — while presenting it as verbatim, trustworthy source. This hit hardest on projects queried through `projectPath` (for example, sub-projects of a monorepo), which have no live file watcher to flag pending edits. Both tools now verify each file against the index before showing sliced code: an out-of-date file is either shown whole with its full current source, or its code is withheld with a clear "changed on disk" notice — never served as a wrong slice. A fresh re-index restores normal output automatically. Thanks @inth3shadows for the thorough report and verification passes. (#1474)
|
||||
- The blast-radius section of `codegraph_explore` flagged "no covering tests found" whenever no test called a symbol directly — falsely branding helpers that tests exercise through their callers as untested (about 40% of flagged symbols in a measured sample). The check now follows caller chains up to 3 hops and reports indirect coverage as "tested via callers"; when nothing is found it states exactly what was checked instead of an unconditional warning. Thanks @inth3shadows for measuring the false-positive rate. (#1475)
|
||||
|
||||
## [1.5.0] - 2026-07-21
|
||||
|
||||
|
||||
@@ -40,6 +40,28 @@ describe('codegraph_explore — blast radius', () => {
|
||||
path.join(src, 'leaf.ts'),
|
||||
`export function lonelyLeaf() { return 42; }\n`,
|
||||
);
|
||||
// `deepHelper` is only called by production code (`midCaller`), but the
|
||||
// test file exercises it transitively — 2 caller hops up (#1475).
|
||||
fs.writeFileSync(
|
||||
path.join(src, 'util.ts'),
|
||||
`export function deepHelper() { return 1; }\n`,
|
||||
);
|
||||
fs.writeFileSync(
|
||||
path.join(src, 'mid.ts'),
|
||||
`import { deepHelper } from './util';\n` +
|
||||
`export function midCaller() { return deepHelper(); }\n`,
|
||||
);
|
||||
fs.writeFileSync(
|
||||
path.join(src, 'mid.test.ts'),
|
||||
`import { midCaller } from './mid';\n` +
|
||||
`export function checkMid() { return midCaller(); }\n`,
|
||||
);
|
||||
// `untestedHelper` has a caller but no test anywhere up its caller chain.
|
||||
fs.writeFileSync(
|
||||
path.join(src, 'untested.ts'),
|
||||
`export function untestedHelper() { return 3; }\n` +
|
||||
`export function untestedCaller() { return untestedHelper(); }\n`,
|
||||
);
|
||||
|
||||
cg = CodeGraph.initSync(testDir, { config: { include: ['**/*.ts'], exclude: [] } });
|
||||
await cg.indexAll();
|
||||
@@ -60,8 +82,28 @@ describe('codegraph_explore — blast radius', () => {
|
||||
expect(text).toMatch(/caller/); // a caller count is reported
|
||||
// It names WHERE (the caller file) — not the caller's source body.
|
||||
expect(text).toContain('feature.ts');
|
||||
// Test coverage is surfaced (either the covering test file, or the warning).
|
||||
expect(text).toMatch(/tests:.*feature\.test\.ts|no covering tests/);
|
||||
// The direct covering test file is surfaced.
|
||||
expect(text).toMatch(/tests:.*feature\.test\.ts/);
|
||||
});
|
||||
|
||||
it('surfaces tests that cover a symbol transitively through its callers (#1475)', async () => {
|
||||
const res = await handler.execute('codegraph_explore', { query: 'deepHelper' });
|
||||
const text = res.content[0].text;
|
||||
|
||||
// deepHelper's only direct caller is production code, but mid.test.ts sits
|
||||
// one more hop up — that must NOT read as "no tests".
|
||||
expect(text).toMatch(/`deepHelper`[^\n]*tested via callers:[^\n]*mid\.test\.ts/);
|
||||
const line = text.split('\n').find((l: string) => l.startsWith('- `deepHelper`'));
|
||||
expect(line).not.toMatch(/no tests found|no covering tests/);
|
||||
});
|
||||
|
||||
it('states only what was measured when no test exists up the caller chain', async () => {
|
||||
const res = await handler.execute('codegraph_explore', { query: 'untestedHelper' });
|
||||
const text = res.content[0].text;
|
||||
|
||||
// Bounded claim, no warning glyph — the tool verified nothing beyond 3 hops.
|
||||
expect(text).toMatch(/`untestedHelper`[^\n]*no tests found within 3 caller hops/);
|
||||
expect(text).not.toContain('⚠️ no covering tests found');
|
||||
});
|
||||
|
||||
it('omits symbols that have no dependents from the blast radius', async () => {
|
||||
|
||||
+46
-1
@@ -2473,7 +2473,7 @@ export class ToolHandler {
|
||||
const where = nonTest.length > 0 ? ` in ${shown}${more}` : '';
|
||||
const tests = testFiles.length > 0
|
||||
? `; tests: ${testFiles.slice(0, FILE_CAP).map((f) => `\`${f}\``).join(', ')}${testFiles.length > FILE_CAP ? ` +${testFiles.length - FILE_CAP}` : ''}`
|
||||
: '; ⚠️ no covering tests found';
|
||||
: this.indirectTestNote(cg, uniq, rel);
|
||||
|
||||
entries.push(
|
||||
`- \`${root.name}\` (${rel(root.filePath)}:${root.startLine}) — ${uniq.length} caller${uniq.length === 1 ? '' : 's'}${where}${tests}`,
|
||||
@@ -2489,6 +2489,51 @@ export class ToolHandler {
|
||||
].join('\n');
|
||||
}
|
||||
|
||||
/**
|
||||
* Test-coverage note for a blast-radius entry whose DIRECT callers include no
|
||||
* test file. A helper called only by production code can still be exercised
|
||||
* by tests further up the caller chain (#1475: 40% of directly-unflagged
|
||||
* symbols had a test within 2-3 hops), so walk up to 2 more hops before
|
||||
* claiming anything — and even then claim only what was measured.
|
||||
*/
|
||||
private indirectTestNote(cg: CodeGraph, directCallers: Node[], rel: (p: string) => string): string {
|
||||
const MAX_HOPS = 3; // direct callers are hop 1
|
||||
const BUDGET = 64; // getCallers lookups per entry — bounds god-fan-in symbols
|
||||
const FILE_CAP = 2;
|
||||
let budget = BUDGET;
|
||||
const visited = new Set(directCallers.map((n) => n.id));
|
||||
let frontier = directCallers;
|
||||
for (let hop = 2; hop <= MAX_HOPS && frontier.length > 0 && budget > 0; hop++) {
|
||||
const next: Node[] = [];
|
||||
const found = new Set<string>();
|
||||
for (const node of frontier) {
|
||||
if (budget-- <= 0) break;
|
||||
let callers: Array<{ node: Node }> = [];
|
||||
try { callers = cg.getCallers(node.id) as Array<{ node: Node }>; } catch { continue; }
|
||||
for (const c of callers) {
|
||||
const n = c?.node;
|
||||
if (!n || visited.has(n.id)) continue;
|
||||
visited.add(n.id);
|
||||
const f = rel(n.filePath);
|
||||
if (isTestFile(f)) found.add(f);
|
||||
else next.push(n);
|
||||
}
|
||||
}
|
||||
if (found.size > 0) {
|
||||
const files = [...found];
|
||||
const shown = files.slice(0, FILE_CAP).map((f) => `\`${f}\``).join(', ');
|
||||
const more = files.length > FILE_CAP ? ` +${files.length - FILE_CAP}` : '';
|
||||
return `; tested via callers: ${shown}${more}`;
|
||||
}
|
||||
frontier = next;
|
||||
}
|
||||
// Budget exhaustion means hops 2-3 weren't fully searched — fall back to
|
||||
// the weaker claim that IS established by the direct-caller check.
|
||||
return budget > 0
|
||||
? `; no tests found within ${MAX_HOPS} caller hops`
|
||||
: '; no test calls this directly';
|
||||
}
|
||||
|
||||
/**
|
||||
* Graph-connectivity relevance via Random-Walk-with-Restart (personalized
|
||||
* PageRank) from the query's matched SEED nodes over the call/reference graph.
|
||||
|
||||
Reference in New Issue
Block a user