Compare commits

...
Author SHA1 Message Date
Philippe Loulidi 8cc5deff1c ref-check: see Terraform citations, resolve wildcards as globs, probe scope first
Re-review findings, each reproduced before fixing:
- .tf/.tfvars/.hcl were missing from the citation allowlist, so `backend.tf` or
  `*/.terraform.lock.hcl` in a prompt was never checked — 18 unchecked citations
  in the infra setup that motivated this feature.
- A wildcard token now resolves as a glob, scope-rebased when that is what
  matches; the suggested `glob:` ref for `pgbouncer/*/patch.yaml` used to be a
  ref that itself failed the check.
- namedPath probes the scope before the root: a scoped prompt citing `alerts/`
  means its own tree even when the root has one too.
- USAGE documents the `target` field --json now emits.
2026-08-03 16:00:33 -06:00
Philippe Loulidi 07762fe6d4 ref-check: strip anchor, line and glob prefix before the ambient-config test
`AGENTS.md#conventions` and `glob:**/.env.local` name scrubbed files too. Found by
the review on this PR.
2026-08-03 15:49:20 -06:00
Philippe Loulidi a0bd28480c ref-check: don't report scrubbed ambient config as a stale ref
The read root is scrubbed of AGENTS.md, CLAUDE.md, .env and friends, so a ref to
one is missing there by design. The template's own shared.md cites AGENTS.md, so
the review note cried wolf on every PR — including this repo's, which is how it
was found. The standalone gate is unchanged: there the tree is a real checkout.
2026-08-03 15:43:18 -06:00
Philippe Loulidi b954180d8b ref-check: cover scope-relative citations that carry an extension
A scoped prompt writes `pgbouncer/base/pdb.yaml` for what is really
`infrastructure/pgbouncer/base/pdb.yaml`. Only extensionless tokens were resolved
before, so the precise ref did not silence the citation and the only thing that
did was `glob:**/pdb.yaml` — which resolves while pointing at every same-named
file in the repo. Six agents pinning a real setup all reached for that glob.

Suggestions now name the resolved path; a token with its own wildcard keeps the
glob form.
2026-08-03 15:36:36 -06:00
4 changed files with 141 additions and 18 deletions

No files matched your search

+5 -2
View File
@@ -91,8 +91,11 @@ settle. A reviewer of this feature named the case: a Terraform prompt citing
"this is very likely going to drift" [observed] — not one of those has an extension, and
`anthropic/claude-opus-5` is shaped identically while naming no file. Syntax cannot tell
them apart, so an extensionless token counts as a citation exactly when it *names
something real*: probed against the repo root and the scope's own subtree, brace lists
and wildcards cut back to their fixed prefix. Model ids resolve to nothing and stay prose.
something real*: probed against the scope's own subtree first, then the repo root (a
scoped prompt citing `alerts/` means its own tree even when the root has one too), brace
lists cut back to their fixed prefix. A token carrying `*` resolves as a glob instead,
scope-rebased when that is what matches, so the suggested `glob:` ref itself resolves.
Model ids resolve to nothing and stay prose.
The consequence is deliberate: an extensionless path that had already drifted before
adoption is invisible (nothing distinguishes it from prose), while every one that is true
+84
View File
@@ -69,6 +69,8 @@ test("isCodeCitation separates paths from prose tokens", () => {
"src/entities/oauth/",
".github/workflows/**",
"*PrivacyPolicy.ts",
"castai-spot.tf",
"*/.terraform.lock.hcl",
]) {
expect(isCodeCitation(token)).toBe(true);
}
@@ -248,6 +250,67 @@ test("the ref the message suggests silences the citation it was suggested for",
}
});
test("a scope-relative citation WITH an extension is covered by its precise ref", async () => {
const files = (pin: string): Record<string, string> => ({
"infrastructure/pgbouncer/base/pdb.yaml": "kind: PodDisruptionBudget\n",
"server/www/k8s/pdb.yaml": "kind: PodDisruptionBudget\n",
"infrastructure/.expo-code-review/config.jsonc": "{}\n",
"infrastructure/.expo-code-review/agents/k8s.md": `${pin}\n\nSee \`pgbouncer/base/pdb.yaml\`.\n`,
});
const unpinned = await checkConfigRefs({ root: await makeRepo(files("")) });
expect(unpinned.problems).toHaveLength(1);
// the suggestion is the precise path, never a basename glob
expect(unpinned.problems[0]!.problem).toContain(
`${REF} infrastructure/pgbouncer/base/pdb.yaml —`,
);
const pinned = await checkConfigRefs({
root: await makeRepo(
files(`<!-- ${REF} infrastructure/pgbouncer/base/pdb.yaml — the PDB this rule is about -->`),
),
});
expect(pinned.problems).toEqual([]);
});
test("a scope-relative wildcard token gets a glob suggestion that itself resolves", async () => {
const files = (pin: string): Record<string, string> => ({
"infra/pgbouncer/production/patch.yaml": "x\n",
"infra/.expo-code-review/config.jsonc": "{}\n",
"infra/.expo-code-review/agents/a.md": `${pin}\nSee \`pgbouncer/*/patch.yaml\`.\n`,
});
const report = await checkConfigRefs({ root: await makeRepo(files("")) });
expect(report.problems).toHaveLength(1);
expect(report.problems[0]!.problem).toContain(`${REF} glob:infra/pgbouncer/*/patch.yaml`);
// …and that suggestion, once written, clears the citation and resolves
const pinned = await checkConfigRefs({
root: await makeRepo(files(`<!-- ${REF} glob:infra/pgbouncer/*/patch.yaml — the patches -->`)),
});
expect(pinned.problems).toEqual([]);
});
test("scope wins over root when both could satisfy an extensionless citation", async () => {
const root = await makeRepo({
"alerts/root.txt": "x\n",
"infra/alerts/scope.tf": "y\n",
"infra/.expo-code-review/config.jsonc": "{}\n",
"infra/.expo-code-review/agents/a.md": "Watch `alerts/` closely.\n",
});
const report = await checkConfigRefs({ root });
expect(report.problems).toHaveLength(1);
expect(report.problems[0]!.problem).toContain(`${REF} infra/alerts/ —`);
});
test("a token carrying its own wildcard keeps the glob suggestion", async () => {
const root = await makeRepo({
".github/workflows/deploy.yml": "on: push\n",
".expo-code-review/config.jsonc": "{}\n",
".expo-code-review/agents/sec.md": "Changes under `.github/workflows/**` are high risk.\n",
});
const report = await checkConfigRefs({ root });
expect(report.problems[0]!.problem).toContain(`${REF} glob:.github/workflows/**`);
});
test("a scope-relative annotated ref is broken, and names the root-relative fix", async () => {
const root = await makeRepo({
"infrastructure/general-central/module/main.tf": "resource {}\n",
@@ -409,6 +472,27 @@ test("reviewSetupRefNotes advises on broken refs and on cited code the PR change
).toEqual([]);
});
test("a ref to scrubbed ambient config is not review advice (the read root removes it)", async () => {
const root = await makeRepo(
setup({
"src/auth.ts": "export const a = 1;\n",
".expo-code-review/shared.md":
`<!-- ${REF} AGENTS.md — the conventions to judge against -->\n` +
`<!-- ${REF} CLAUDE.md#conventions — same, with an anchor -->\n` +
`<!-- ${REF} glob:**/.env.local — same, as a glob -->\n` +
`<!-- ${REF} src/gone.ts — really moved -->\n`,
}),
);
const setupDir = path.join(root, ".expo-code-review");
const notes = await reviewSetupRefNotes({ root, setupDirs: [setupDir], changedFiles: [] });
expect(notes).toHaveLength(1);
expect(notes[0]).toContain("1 ref(s)");
expect(notes[0]).not.toContain("shared.md:1");
// The standalone gate still reports all of them — there the tree is a real checkout.
expect((await checkConfigRefs({ root })).problems).toHaveLength(4);
});
test("setup problems are labelled by setup-dir position when the config lives outside the tree", async () => {
const code = await makeRepo({ "src/auth.ts": "export const a = 1;\n" });
const trustedBase = await makeRepo(
+1 -1
View File
@@ -25,7 +25,7 @@ Exit 0 = every ref holds. Exit 1 = at least one is broken.
Options:
--root <dir> Repository root to check (default: the current git repo).
--json Emit {ok, problems:[{file, line, kind, problem}]} on stdout.
--json Emit {ok, problems:[{file, line, kind, problem, target?}]} on stdout.
`;
const KIND_LABEL: Record<RefProblem["kind"], string> = {
+51 -15
View File
@@ -8,6 +8,7 @@ import { CONFIG_DIRNAME, stripJsonComments, stripTrailingCommas } from "../confi
import { ROUTING_FILENAME } from "../config/routing.js";
import { git, pathInside } from "./exec.js";
import { matchesIgnore } from "./noise.js";
import { isAmbientRuntimeConfig } from "./scrub.js";
/**
* Built by concatenation so this module's own regexes and doc comments are not
@@ -46,6 +47,7 @@ const CITATION_EXTENSIONS = new Set([
".css",
".go",
".graphql",
".hcl",
".h",
".hpp",
".html",
@@ -69,6 +71,8 @@ const CITATION_EXTENSIONS = new Set([
".sh",
".sql",
".swift",
".tf",
".tfvars",
".toml",
".ts",
".tsx",
@@ -95,6 +99,8 @@ export interface RefProblem {
kind: RefProblemKind;
/** One sentence, imperative where a fix is obvious. */
problem: string;
/** The ref target (or prose token) at fault. Absent for structural problems. */
target?: string;
}
export interface ParsedRef {
@@ -693,10 +699,11 @@ export async function checkConfigRefs(options: CheckConfigRefsOptions): Promise<
// Does an extensionless token name something real? Cached: prompts repeat the same
// paths, and each miss would otherwise cost a stat per occurrence.
const resolvable = new Map<string, string | null>();
/** The root-relative path an extensionless token names, or null if it names nothing. */
/** The root-relative path a token names, or null. Scope first: a scoped prompt
* citing `alerts/` means its own tree even when the root has one too. */
const namedPath = async (token: string, scopeRoot: string): Promise<string | null> => {
for (const candidate of pathishCandidates(token)) {
for (const base of [root, scopeRoot]) {
for (const base of [scopeRoot, root]) {
const absolute = path.resolve(base, candidate);
let resolved = resolvable.get(absolute);
if (resolved === undefined) {
@@ -716,6 +723,19 @@ export async function checkConfigRefs(options: CheckConfigRefsOptions): Promise<
return null;
};
/** The glob a wildcard token names, rebased onto the scope when that is what
* matches, so the suggested `glob:` ref actually resolves. */
const namedGlob = (token: string, scopeRoot: string): string | null => {
const scopeRel = path.relative(root, scopeRoot).split(path.sep).join("/");
const candidates = [...(scopeRel && scopeRel !== "." ? [`${scopeRel}/${token}`] : []), token];
for (const candidate of candidates) {
if (index.files.some((file) => matchesIgnore(file, candidate))) {
return candidate;
}
}
return null;
};
for (const dir of dirs) {
const scopeRoot = path.dirname(dir);
for (const file of await setupFiles(dir)) {
@@ -745,6 +765,7 @@ export async function checkConfigRefs(options: CheckConfigRefsOptions): Promise<
line: ref.line,
kind: problem.startsWith("cites a line number") ? "line-number-ref" : "broken-ref",
problem,
target: ref.target,
});
continue;
}
@@ -762,18 +783,15 @@ export async function checkConfigRefs(options: CheckConfigRefsOptions): Promise<
}
for (const { line, token } of findProseCitations(text)) {
// Extension or wildcard tail ⇒ a citation on shape alone. Otherwise it only
// counts if it names something real: `eas-build-worker/terraform` and
// `general-central/{module,production}` are paths, `anthropic/claude-opus-5`
// is shaped identically and is not.
const named = isCodeCitation(token) ? null : await namedPath(token, scopeRoot);
const isWild = token.includes("*");
const named = isWild ? namedGlob(token, scopeRoot) : await namedPath(token, scopeRoot);
// Shape alone makes a citation; otherwise it must name something real, or
// `anthropic/claude-opus-5` would read as a path.
if (!isCodeCitation(token) && !named) {
continue;
}
// Coverage must accept the path the token RESOLVED to, not just the token as
// written: a prompt says `cert-manager` and the ref that pins it is
// `infrastructure/cert-manager/`. Without this, the fix the message suggests
// does not silence the citation it was suggested for.
// Coverage accepts the resolved path too, else the only ref that silences a
// scope-relative citation is an over-broad `glob:**/<basename>`.
const forms = [...citationForms(token), ...(named ? coveringForms(named) : [])];
if (
ignored.has(token) ||
@@ -785,9 +803,12 @@ export async function checkConfigRefs(options: CheckConfigRefsOptions): Promise<
continue;
}
const lineCitation = LINE_CITATION_RE.exec(token);
// For an extensionless token the suggestion is the path that actually resolved,
// which is also how a scope-relative citation learns its root-relative form.
const suggestion = named ?? suggestedRef(token);
// A wildcard token means the family; anything else gets the precise resolved path.
const suggestion = isWild
? named
? `${GLOB_PREFIX}${named}`
: suggestedRef(token)
: (named ?? suggestedRef(token));
problems.push({
file: relative,
line,
@@ -795,6 +816,7 @@ export async function checkConfigRefs(options: CheckConfigRefsOptions): Promise<
problem: lineCitation
? `\`${token}\` pins a line number; cite the file or a \`#symbol\` instead, as \`${REF_MARK} ${suggestedRef(lineCitation[1]!)}\``
: `\`${token}\` cites code without a ref; add \`${REF_MARK} ${suggestion} — why it matters\` (or \`${IGNORE_MARK} ${token}\` if it is not a path)`,
target: token,
});
}
}
@@ -821,6 +843,13 @@ export async function checkConfigRefs(options: CheckConfigRefsOptions): Promise<
};
}
/** The file a target names, with any `glob:` prefix, `#anchor` or `:line` stripped. */
function citedBasename(target: string): string {
const withoutPrefix = target.startsWith(GLOB_PREFIX) ? target.slice(GLOB_PREFIX.length) : target;
const withoutLine = LINE_CITATION_RE.exec(withoutPrefix)?.[1] ?? withoutPrefix;
return path.basename(splitAnchor(withoutLine)[0]);
}
/** How many examples a review-side note names before saying "and N more". */
const NOTE_EXAMPLES = 5;
@@ -848,7 +877,14 @@ export async function reviewSetupRefNotes(options: {
return []; // a check that cannot run must never degrade the review
}
const notes: string[] = [];
const broken = report.problems.filter((problem) => problem.kind !== "unannotated-citation");
// The read root is scrubbed of ambient runtime config (AGENTS.md, CLAUDE.md, .env…),
// so a ref to one is missing by design here, not stale. The template itself cites
// AGENTS.md, which would make this note cry wolf on every PR.
const broken = report.problems.filter(
(problem) =>
problem.kind !== "unannotated-citation" &&
!(problem.target && isAmbientRuntimeConfig(citedBasename(problem.target))),
);
if (broken.length > 0) {
notes.push(
`The reviewer setup cites code that no longer resolves (${broken.length} ref(s)): ` +