CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-09-09 22:48:57 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix(code-intelligence): consent that means what it says — polarity, receipts, read-only veto

Browse Source 
Four review findings on the wave's own Phase 1 port, all red-first:
'consent <repo> no' recorded consent GRANTED (the CLI ignored the
argument and always wrote true) — yes|no is now required and garbage
records nothing; Sourcebot egress receipts claimed consented=true on
paths that never checked consent — the actual consent state is threaded
into every receipt, search is fail-closed on non-loopback, and the
liveness probe's receipt says truthfully that it sends no repo content;
repoPolicyVeto only honored the deny tier while gbrain refresh writes
pages — write-class ops now veto on read-only too, matching the sync
chokepoint, via one shared lib/gbrain-repo-policy-client.ts (win32
bash invocation, spawn-vs-unreadable error distinction) used by both
call sites. Also: source ids get a host+path hash (same-name repos no
longer collide), refresh timeout raised to 120s, availability probes
run concurrently at 3s, graphify status stops JSON.parsing 100MB graphs
for a count, and every ported file carries the fork MIT notice.
+15 tests across the two suites.
This commit is contained in:
Garry Tan
2026-08-14 17:13:22 -07:00
parent 531d9a6e1f
commit 9488173b0a
13 changed files with 640 additions and 100 deletions
Download Patch File Download Diff File Expand all files Collapse all files
bin/gstack-code-intelligence
+79 -11
View File
@@ -4,12 +4,14 @@
* index and search this repo. OPTIONAL: with nothing selected, gstack works
* fine and callers use grep / the file-only decision store.
*
* Portions copyright (c) 2026 Sina Matian, time-attack/gstack (GStack 2), MIT.
*
* Usage:
* gstack-code-intelligence suggest [repo] [--json] # should the one-time indexing offer be made here?
* gstack-code-intelligence options # list providers (GBrain first) + availability
* gstack-code-intelligence status # current selection + availability
* gstack-code-intelligence consent [repo-path] <yes|no> # record per-repo indexing consent (value REQUIRED)
* gstack-code-intelligence select <gbrain|sourcebot|graphify|none>
* gstack-code-intelligence consent [repo-path] # allow indexing this repo (per-repo)
* gstack-code-intelligence index [repo-path] # index the repo with the selected provider
* gstack-code-intelligence search <query...> # search via the selected provider
*
@@ -19,11 +21,15 @@
* auto-installed.
*/
import { createHash } from "crypto";
import { realpathSync } from "fs";
import { hostname } from "os";
import { basename, resolve } from "path";
import {
CodeProviderError,
RECOMMENDED_ORDER,
detectAvailable,
getRoot,
hasConsent,
providerById,
readSelection,
@@ -125,22 +131,73 @@ function cmdSelect(arg: string | undefined): void {
if (!provider.local) out(`${LABEL[id]} sends repo content off this machine — run \`consent\` in a repo before indexing it.`);
}
function cmdConsent(pathArg: string | undefined): void {
const repoPath = resolve(pathArg ?? process.cwd());
setConsent(repoPath, true);
out(`indexing consent recorded for ${repoPath}`);
/**
* Record per-repo indexing consent: `consent [repo-path] <yes|no>`.
*
* The yes|no value is REQUIRED (true/false also accepted). It is never
* defaulted: an agent recording a user's "no" must persist consent DENIED,
* and a missing/unknown value must record NOTHING — a consent gate that
* assumes "yes" is a consent gate that lies.
*/
function cmdConsent(rest: string[]): void {
const positional = rest.filter((a) => !a.startsWith("--"));
const CONSENT_USAGE = "Usage: consent [repo-path] <yes|no> — the yes/no value is required; consent is never assumed";
if (positional.length < 1 || positional.length > 2) fail(CONSENT_USAGE);
const value = positional[positional.length - 1].toLowerCase();
let consented: boolean;
if (value === "yes" || value === "true") consented = true;
else if (value === "no" || value === "false") consented = false;
else fail(CONSENT_USAGE);
const repoPath = resolve(positional.length === 2 ? positional[0] : process.cwd());
setConsent(repoPath, consented);
out(consented ? `indexing consent recorded for ${repoPath}` : `indexing consent DENIED for ${repoPath} (recorded)`);
}
/**
* Host+path-hashed source id for GBrain/Sourcebot — the same approach as
* deriveCodeSourceId in bin/gstack-gbrain-sync.ts. A bare basename collides:
* two repos both named "api" (or the same repo on two machines against a
* federated brain) would silently share one source. Suffix = first 8 hex of
* sha1(`${hostname}::${realpath}`); base sanitized to gbrain's source-id
* charset (lowercase alnum + interior hyphens) and capped so the whole id
* stays within gbrain's 32-char limit.
*/
function hashedSourceId(repoPath: string): string {
let real = repoPath;
try {
real = realpathSync(repoPath);
} catch {
// path may not exist yet at id-derivation time — hash the resolved form
}
const host = process.env.GSTACK_HOSTNAME || hostname();
const suffix = createHash("sha1").update(`${host}::${real}`).digest("hex").slice(0, 8);
const base =
basename(real)
.toLowerCase()
.replace(/[^a-z0-9]+/g, "-")
.replace(/^-+|-+$/g, "")
.slice(0, 23)
.replace(/-+$/, "") || "repo";
return `${base}-${suffix}`;
}
async function cmdIndex(pathArg: string | undefined): Promise<void> {
const provider = resolveSelectedProvider();
if (!provider) fail("no provider selected; run `select <provider>` first");
const repoPath = resolve(pathArg ?? process.cwd());
// Indexing is write-class: hasConsent's default op class applies, so a
// `deny` OR `read-only` repo trust policy vetoes it (code indexing writes
// pages — same semantics as gstack-gbrain-sync's runCodeImport).
const consented = hasConsent(repoPath);
if (!provider!.local && !consented) {
fail(`${provider!.label} would send this repo's content off the machine. Run \`gstack-code-intelligence consent ${repoPath}\` first.`);
const recorded = readSelection().consents[repoPath] === true;
fail(recorded
? `${provider!.label} indexing is blocked by the repo trust policy (deny or read-only — code indexing writes pages). Change with: gstack-gbrain-repo-policy set <origin-url> read-write`
: `${provider!.label} would send this repo's content off the machine. Run \`gstack-code-intelligence consent ${repoPath} yes\` first.`);
}
// Graphify keys sources on the repo path; GBrain/Sourcebot on a short id.
const sourceId = provider!.id === "graphify" ? repoPath : basename(repoPath);
// Graphify keys sources on the repo path; GBrain/Sourcebot on a short
// host+path-hashed id (bare basenames collide across same-named repos).
const sourceId = provider!.id === "graphify" ? repoPath : hashedSourceId(repoPath);
const repo = { id: sourceId, path: repoPath };
try {
const registered = await provider!.registerSource(repo, { consented });
@@ -159,8 +216,16 @@ async function cmdSearch(terms: string[]): Promise<void> {
if (!query) fail("Usage: search <query...>");
const provider = resolveSelectedProvider();
if (!provider) fail("no provider selected; run `select <provider>` first (or use grep)");
// Search is read-class: a read-only repo trust policy still allows it
// (mirrors gstack-gbrain-sync: search allowed, page writes never), but a
// deny tier — or no recorded consent at all — still refuses for non-local
// providers, because the query text itself is repo-derived content. The
// consent repo is the one this provider indexed (search reads that graph);
// loopback providers need no consent, so their path is unchanged.
const searchRoot = getRoot(provider!.id) ?? resolve(process.cwd());
const consented = hasConsent(searchRoot, undefined, "read");
try {
const hits = await provider!.search(query, { limit: 10 });
const hits = await provider!.search(query, { limit: 10, consented });
if (!hits.length) {
out("(no results)");
return;
@@ -176,6 +241,9 @@ function handleProviderError(err: unknown, label: string): never {
if (err.code === "PROVIDER_UNAVAILABLE") {
fail(`${label} is unavailable (${err.message}). gstack still works — fall back to grep / file-only.`);
}
if (err.code === "PROVIDER_NOT_CONSENTED") {
fail(`${label} ${err.code}: ${err.message} Run \`gstack-code-intelligence consent <repo-path> yes\` first (a deny repo trust policy overrides recorded consent).`);
}
fail(`${label} ${err.code}: ${err.message}`);
}
fail(err instanceof Error ? err.message : String(err));
@@ -193,13 +261,13 @@ async function main(): Promise<void> {
case "select":
return cmdSelect(rest[0]);
case "consent":
return cmdConsent(rest[0]);
return cmdConsent(rest);
case "index":
return cmdIndex(rest[0]);
case "search":
return cmdSearch(rest);
default:
fail("Usage: suggest [path] [--json] | options | status | select <provider> | consent [path] | index [path] | search <query...>");
fail("Usage: suggest [path] [--json] | options | status | select <provider> | consent [path] <yes|no> | index [path] | search <query...>");
}
}