mirror of
https://github.com/garrytan/gstack.git
synced 2026-08-11 00:30:21 +02:00
* fix(careful): warn on chained rm even when the last target is safe The safe-exception block whitelisted rm -rf of build artifacts by extracting targets with a single greedy match (.*rm ...), which only ever inspects the LAST rm in the command. A chain like 'rm -rf /; rm -rf node_modules' was therefore judged solely by its trailing safe target and allowed without warning, waving through the destructive 'rm -rf /'. Gate the shortcut to single rm invocations: when any shell separator (; | & newline, incl. JSON-escaped \n/\r from the grep extraction path) is present, fall through to the destructive-pattern check, which warns on any recursive rm. Single-command artifact cleanups still allow. Adds 3 regression tests covering semicolon and && chains in both orders. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * harden(careful): substitution separators + capital -R recursive flag (#2039) Two residual fail-opens in the same guard PR #2040 hardened, both verified by executing the script pre-fix: - rm -rf $(./wipe-all)/node_modules silently allowed: the substitution token ends in a whitelisted suffix and the safe-exception early exit skipped ALL downstream checks. $( and backtick now count as chain separators; plain $VAR expansion stays allowed. - rm -R / silently allowed: both greps required a lowercase r in the flag cluster; capital -R is the documented BSD/macOS recursive flag. Both greps now match -[a-zA-Z]*[rR]. Six new tests: substitution x2 -> ask, capital-R x2 -> ask, rm -Rf node_modules single-command -> still allowed, escaped-newline branch (existing code, previously untested), and a pinned deliberate FP (cd app && rm -rf node_modules -> ask) documenting the fail-closed direction on chains. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(context-restore): prefer the current branch's own checkpoint (#2052) All worktrees of a repo share one origin-derived slug, so they share one `~/.gstack/projects/<slug>/checkpoints/` dir. `/context-restore` loaded the newest checkpoint across the whole dir, so in one worktree it could silently restore a *sibling worktree's* newer checkpoint. Step 1 now orders candidates current-branch-first (read from each file's `branch:` frontmatter), keeping other branches as a fallback. A branch is checked out in at most one worktree, so this stops cross-worktree contamination while preserving Conductor cross-branch handoff: when the current branch has no checkpoint of its own, the full newest-first set is still used. - scan the 200 newest before partitioning so a current-branch checkpoint sitting below a burst of sibling saves is still found; output still capped at 20 - non-git / detached HEAD / branchless legacy saves fall back to the old newest-first behavior (back-compat) - +5 regression tests in context-save-hardening.test.ts (the #2052 bug case fails on the old pipeline); regenerated SKILL.md + proactive-suggestions.json Fixes #2052 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(gbrain): pass --confirm-destructive on drift re-register (#1985) ensureSourceRegistered() handles match-but-different-path by removing the old source then re-adding it at the new path. The remove was issued as `gbrain sources remove <id> --yes`, but gbrain >= 0.42 gates `sources remove` behind `--confirm-destructive` (`--yes` alone no longer suppresses the data-loss prompt). The remove therefore fails with "To proceed, pass --confirm-destructive", which ensureSourceRegistered surfaces as "source registration failed" — aborting the entire /sync-gbrain code stage for any already-registered source whose path has drifted. The memory and brain-sync stages still pass, so the code index silently stops refreshing. The orchestrator's own safeSourcesRemove() already passes --confirm-destructive; this brings the lib helper in line with that convention. Keeps --yes for older gbrain. Tests: extend the fake gbrain shim in gbrain-sources.test.ts to simulate the gbrain >= 0.42 guard (remove without --confirm-destructive exits 1), update the drift re-register assertion, and add a regression test that proves the drift path no longer throws. Both fail on main with the exact "To proceed, pass --confirm-destructive" error and pass with the fix. Fixes #1985 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * harden(gbrain-sources): route drift remove through #1734 guards + realpath drift check Absorbing #2031 un-blocked a destructive remove that bypassed the #1734 data-loss guards: ensureSourceRegistered's drift path issued `gbrain sources remove` directly, without the detectAutopilot + decideSourceRemove checks every other remove routes through via safeSourcesRemove. gbrain >= 0.42's own prompt was accidentally blocking that path; with --confirm-destructive passed it is live again. - Drift remove now refuses LOUDLY (throws, actionable message) while an autopilot is active or when decideSourceRemove disallows; a silent changed=false would hide the drifted registration. - decideSourceRemove's extraArgs (--keep-storage when supported) propagate to the remove call, matching safeSourcesRemove. - Drift is realpath-normalized before being declared: a symlink alias of the same directory (macOS /tmp -> /private/tmp) is a match, not drift — the probable cause of #1985's reporter hitting the remove on an unmoved repo. - Drift fires a loud stderr line (old -> new path); perpetual drift in logs is the trigger for promoting #1985's reindex-in-place design. Tests: autopilot-active refusal (no remove in call log), fail-closed refusal on unreadable sources list, --keep-storage propagation, symlink-alias no-drift; existing drift tests pin the guard probes so a live autopilot on the dev machine can't flip them. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(developer-profile): exclude mode:resources rows from SESSION_COUNT, TIER, NUDGE_ELIGIBLE (#2067) Every /office-hours run appends a mode:"resources" bookkeeping row alongside the real session row, so --read double-counted sessions (~2x): tiers promoted early and the builder-to-founder nudge armed prematurely. The file already filtered resources rows for LAST_*/CROSS_PROJECT; the same realSessions filter now feeds SESSION_COUNT/TIER, and the nudge predicate is the faithful allowlist (mode === 'builder') so a future mode #4 fails closed instead of re-opening this bug. 8 regression tests: count vs resources noise, tier boundaries both sides, nudge false-with-noise / true-at-3-builders, cross-project trailing row. Absorbed from PR #1991 by @mvann (fix + tests commits; the PR's version-bump commit is superseded by this wave's consolidated release commit). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(hooks): passThrough() two-branch contract — never emit permissionDecision:'defer' (#2035, #2006) Every AskUserQuestion died with "Tool result missing due to internal error" on current Claude Code builds (Desktop 1.14271.0, CC 2.1.177). Root cause: the question-preference-hook emitted permissionDecision:'defer' on every pass-through path. 'defer' is a real PreToolUse value, but since CC v2.1.89 its semantics are "pause this tool call for external resumption" (headless resume) — never "abstain". Interactive sessions have nothing to resume the paused call, so the tool orphaned. Pre-2.1.89 builds ignored the unknown value, which is why the hook worked when it shipped and broke later. The fix is the two-branch pass-through contract: - no context -> exit 0 with EXACTLY empty stdout - memory nuggets present -> hookSpecificOutput with hookEventName + additionalContext ONLY (the documented shape; plan-tune Layer 8 memory injection ships through this branch and keeps working) defer() is renamed passThrough() so the function says what it does, and docs/spikes/claude-code-hook-mutation.md's protocol contract (cited by the hook header) is corrected in the same commit — it taught '"defer" — let permission flow continue' and was the reintroduction vector. Test contract rewritten in the same commit (13 assertions across 3 files, verified fail-first against the unfixed hook): pass-through paths assert exact-empty stdout (a garbage/partial write cannot slip past an optional-chained parse), the nugget path asserts permissionDecision is ABSENT while additionalContext survives, and a new tripwire asserts no non-deny path ever puts the string "permissionDecision" on stdout. The deny (auto-decide) and Conductor prose-redirect paths are unchanged. Deployment: no migration needed — settings.json points at the absolute bash shim which execs the .ts live; /gstack-upgrade delivers the fix. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(one-way-doors): unify credential noun net + wire it into the runtime (#2024) Library fix: revoke/reset/rotate now share ONE noun alternation (api key, token, secret, credential, access key, password) with optional plural s?. Pre-fix leaks: "reset my secret", "reset my access key", "revoke my secret" (mismatched per-verb lists) and every plural form ("rotate the credentials", "revoke all tokens" — \b(...)\b cannot match a trailing s). Runtime wiring — the regexes could never fire in production before: - gstack-question-preference --check gains --summary-stdin: the question text pipes via stdin (never argv — summaries carry quotes/newlines/shell metacharacters) and feeds isOneWayDoor alongside the id, so an ad-hoc destructive question with a stored never-ask preference now forces ASK_NORMALLY. Empty/absent stdin keeps exact id-only semantics. - question-preference-hook falls back to classifyQuestion(question text) when the registry lookup misses, so unregistered destructive questions pass through to a human instead of auto-deciding. - question-tuning resolver prose shows the piped form (SKILL.md regen lands in the wave's release commit). Tripwires (verified fail-first): full verbs x nouns x singular/plural matrix with the #2024 repro rows, benign-summary no-over-match rows, stdin transport survival (quotes/newlines), empty-stdin fail-safe, and hook fallback both directions (destructive -> pass-through, benign -> deny). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(design): loud integer-flag contract for --count/--retry/--timeout (#2032) design variants --count abc silently generated ZERO variants and exited 0: parseInt(NaN) flowed through Math.min into the generation loop bound. The same NaN class was live on the two sibling flags in the same file: --retry abc made generate() a silent no-op (attempt <= NaN never true, null output, exit 0) and --timeout abc killed the serve board ~immediately (setTimeout(NaN)). New design/src/flag-utils.ts: parseIntFlag (pure, unit-testable) + normalizeIntFlag (CLI wrapper). Contract matches the --viewports precedent (error loudly on nonsense — these commands spend real image-API money, a silent fixup hides typos from calling agents): undefined -> default; bare flag/empty/non-integer ("3.7" rejected, not truncated)/below-min -> exit 1 with usage hint; above-max -> clamp with stderr warning. --count normalizes at the variants() consumption site so programmatic callers are covered, with the ceiling derived from STYLE_VARIATIONS.length instead of a magic 7; the CLI passes the raw flag through (a pre-parseInt would truncate "3.7"). Tripwires live in test/design-flag-utils.test.ts — deliberately under test/, not design/test/, which is invisible to the bun test glob, TEST_ROOTS, and every workflow (wiring design/test/ into CI is a captured TODO). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(gbrain): thin-client state — remote-MCP brains no longer classify as broken-config (#2051) A thin client (remote-HTTP MCP brain, no local engine by design) probed `gbrain sources list`, which gbrain's dispatch guard REFUSES on thin clients (exit 1, no recognized error string), so the classifier fell to its defensive broken-config default and every suppression gate silently hid brain-aware blocks from exactly the users on a shared team brain. New 'thin-client' state, detected PRE-probe from gbrain's own remote_mcp config marker via the existing gbrainConfigPath() helper (mirrors gbrain's isThinClient(); honors GBRAIN_HOME; zero network, immune to error-string drift), with a /thin[- ]client/ stderr backstop in the probe catch. Remote reachability is deliberately NOT probed by the classifier — that is the #1964 pathology; gbrain calls degrade gracefully at use time, and the detect JSON says so honestly (gbrain_thin_client: {probed: false}). The state is admitted at every suppression gate — gstack-gbrain-detect --is-ok (drives setup + gbrain-refresh), gen-skill-docs' detection override, gstack-config gbrain-refresh — while the sync stages (code/memory/dream) SKIP with an accurate reason: code indexing runs on the brain server, memory syncs via the remote brain's artifacts pull. The two consumer classes need opposite answers, which is why this is a distinct state and not a skip-the-probe special case. sync-gbrain Step 1.5 and setup-gbrain prose route thin-client to proceed, never into broken-config remediation. detectMcpMode secondary generalization: url-match against the config's remote_mcp.mcp_url (deterministic — gbrain mounts at the generic /mcp path) -> name pattern gbrain[-_]* -> stdio command token; gbrain_mcp_mode stays a 3-value enum. Tripwires: end-to-end --is-ok exits 0 on a thin-client fixture AND still exits 1 on broken-config (the gate didn't widen); pre-probe + stderr-fallback classifier paths; 4 detectMcpMode identification cases incl. a non-matching url that must NOT false-positive. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * release: v1.60.0.0 — regen SKILL.md, VERSION, CHANGELOG, TODOS follow-ups - Regenerate all SKILL.md from templates (question-tuning --summary-stdin prose from #2024, context-restore branch preference from PR #2054, sync-gbrain/setup-gbrain thin-client prose from #2051) + llms.txt. - VERSION + package.json -> 1.60.0.0 (bin/gstack-next-version, queue-aware: #1815 claims 1.59.0.0, #2213 claims 1.59.1.0). - CHANGELOG release summary + itemized entry crediting @jbetala7 (x3) and @mvann. - TODOS.md: three eng-review follow-ups (design/test CI wiring + documented pre-existing retry-after flake, /context-save worktree identity, gbrain reindex-in-place conditional on the new drift log). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(resolvers): compress --summary-stdin preamble prose to fit parity budget; re-bless ship goldens The v1.57.7.0 parity suite caps investigate's generated size at 1.09x baseline; the #2024 question-tuning prose (duplicated into every tier->=2 skill) tipped it to 1.092. Compressed to a single inline command + short pointer (the full rationale lives in bin/gstack-question-preference's header and the one-way-doors module docs). Ship goldens re-blessed against the final resolver text (conscious template-change acknowledgment, per the golden-file regression contract). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(e2e): office-hours-spec-review turn budget fits the carved skill layout (#2473) The test failed deterministically with error_max_turns at 9 turns on main and this branch alike (CI attempt logs + local main repro). Root cause from the failing transcript: the Spec Review Loop content is carved out of office-hours/SKILL.md into office-hours/sections/, so the agent needs discovery hops (grep SKILL.md -> ls sections/ -> read the section) before it can write — 8 tool turns + the closing text turn = 9 > the 8-turn budget, which predates the carve. Observed failures wrote a CORRECT summary on tool turn 8 and died on the closing turn. maxTurns 8 -> 12. Verified: PASS locally post-fix (7 turns this run — the extra headroom absorbs discovery-path nondeterminism). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(e2e): review-dashboard-via session budget survives runner contention (#2473) The test failed on CI (and its baseline run) with the timeout signature: 0 turns, $0.00, exactly 183s, 3/3 attempts — the spawned claude -p session never emitted a single stream event before the 180s inner timeout. The file's tests run concurrently on one runner; session startup queues behind sibling sessions, and this test had the tightest budget in the file (the 240s-budget tests in the same job passed). A clean local run takes 270s wall for 4 turns, confirming 180s was too tight even without contention. Inner timeout 180s -> 300s; outer bun timeout 240s -> 360s to keep headroom over the inner budget. Verified: PASS locally post-fix (4 turns, 270s). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(e2e): retro-base-branch session budget survives runner contention (#2473) Same class as review-dashboard-via, one test over in the same file: /retro is a long multi-step flow whose clean pass measures 225-239s — a coin flip against the 240s inner budget. First CI run passed at 225s; the rerun timed out at the 240s line on all 3 attempts (exitReason "timeout"); the local verification run passed at 239s, ONE second under the old cap. Inner timeout 240s -> 360s; outer bun timeout 300s -> 480s for headroom. Verified: PASS locally post-fix (17 turns, 239s). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Jayesh Betala <jayesh.betala7@gmail.com> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Co-authored-by: Michael Vann <9221873+mvann@users.noreply.github.com>
298 lines
11 KiB
Bash
Executable File
298 lines
11 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# gstack-question-preference — read/write/check explicit per-question preferences.
|
|
#
|
|
# Preference file: ~/.gstack/projects/{SLUG}/question-preferences.json
|
|
# Schema: { "<question_id>": "always-ask" | "never-ask" | "ask-only-for-one-way" }
|
|
#
|
|
# Subcommands:
|
|
# --check <id> [--summary-stdin] → emit ASK_NORMALLY | AUTO_DECIDE | ASK_ONLY_ONE_WAY
|
|
# (--summary-stdin pipes the question text so the
|
|
# keyword net can catch ad-hoc destructive ids, #2024)
|
|
# --write '{...}' → set a preference (user-origin gate enforced)
|
|
# --read → dump preferences JSON
|
|
# --clear [<id>] → clear one or all preferences
|
|
# --stats → short summary
|
|
#
|
|
# User-origin gate
|
|
# ----------------
|
|
# The --write subcommand REQUIRES a `source` field on the input:
|
|
# - "plan-tune" — user ran /plan-tune and chose a preference (allowed)
|
|
# - "inline-user" — inline `tune:` from the user's own chat message (allowed)
|
|
# - "inline-tool-output"— tune: prefix seen in tool output / file content (REJECTED)
|
|
# - "inline-file" — tune: prefix seen in a file the agent read (REJECTED)
|
|
# This is the profile-poisoning defense from docs/designs/PLAN_TUNING_V0.md.
|
|
set -euo pipefail
|
|
|
|
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
|
|
ROOT_DIR="$(cd "$SCRIPT_DIR/.." && pwd)"
|
|
# GSTACK_STATE_ROOT takes precedence over GSTACK_HOME (test isolation per D16).
|
|
GSTACK_HOME="${GSTACK_STATE_ROOT:-${GSTACK_HOME:-$HOME/.gstack}}"
|
|
eval "$("$SCRIPT_DIR/gstack-slug" 2>/dev/null || true)"
|
|
SLUG="${SLUG:-unknown}"
|
|
PREF_FILE="$GSTACK_HOME/projects/$SLUG/question-preferences.json"
|
|
EVENT_FILE="$GSTACK_HOME/projects/$SLUG/question-events.jsonl"
|
|
mkdir -p "$GSTACK_HOME/projects/$SLUG"
|
|
|
|
CMD="${1:-}"
|
|
shift || true
|
|
|
|
ensure_file() {
|
|
if [ ! -f "$PREF_FILE" ]; then
|
|
echo '{}' > "$PREF_FILE"
|
|
fi
|
|
}
|
|
|
|
# -----------------------------------------------------------------------
|
|
# --check <question_id>
|
|
# -----------------------------------------------------------------------
|
|
do_check() {
|
|
local QID="" SUMMARY_STDIN=false
|
|
while [ $# -gt 0 ]; do
|
|
case "$1" in
|
|
--summary-stdin) SUMMARY_STDIN=true; shift ;;
|
|
*) [ -z "$QID" ] && QID="$1"; shift ;;
|
|
esac
|
|
done
|
|
if [ -z "$QID" ]; then
|
|
echo "ASK_NORMALLY"
|
|
return 0
|
|
fi
|
|
# #2024: the question text feeds the keyword classifier for unregistered
|
|
# ids. Transport is stdin (not argv) — summaries carry quotes, newlines,
|
|
# and shell metacharacters an argv tail would mangle. Handed to bun via
|
|
# env so no shell re-quoting happens. Empty summary = id-only behavior.
|
|
local QSUMMARY=""
|
|
if [ "$SUMMARY_STDIN" = true ]; then
|
|
QSUMMARY=$(cat 2>/dev/null || true)
|
|
fi
|
|
ensure_file
|
|
cd "$ROOT_DIR"
|
|
PREF_FILE_PATH="$PREF_FILE" QID="$QID" QSUMMARY="$QSUMMARY" bun -e "
|
|
import('./scripts/one-way-doors.ts').then((oneway) => {
|
|
const fs = require('fs');
|
|
const qid = process.env.QID;
|
|
const summary = process.env.QSUMMARY || undefined;
|
|
const prefs = JSON.parse(fs.readFileSync(process.env.PREF_FILE_PATH, 'utf-8'));
|
|
const pref = prefs[qid];
|
|
|
|
// Always check one-way status first — safety overrides preferences.
|
|
// summary (when piped) lets the keyword net catch ad-hoc destructive
|
|
// questions whose id has no registry entry (#2024).
|
|
const oneWay = oneway.isOneWayDoor({ question_id: qid, summary });
|
|
|
|
if (oneWay) {
|
|
console.log('ASK_NORMALLY');
|
|
if (pref === 'never-ask') {
|
|
console.log('NOTE: one-way door overrides your never-ask preference for safety.');
|
|
}
|
|
return;
|
|
}
|
|
|
|
// Split-chain carve-out: per-option calls in N-option splits emit
|
|
// question_ids of the form <skill>-split-<option-slug>. These are
|
|
// NEVER AUTO_DECIDE-eligible regardless of stored preferences — the
|
|
// whole point of splitting is restoring user sovereignty over the
|
|
// option set. See scripts/resolvers/preamble/generate-ask-user-format.ts
|
|
// \"Handling 5+ options — split, never drop\" for the surrounding
|
|
// mechanism that generates these ids.
|
|
if (/-split-/.test(qid)) {
|
|
console.log('ASK_NORMALLY');
|
|
if (pref === 'never-ask' || pref === 'ask-only-for-one-way') {
|
|
console.log('NOTE: split-chain per-option calls always ASK_NORMALLY; your ' + pref + ' preference does not apply to options inside a sequential split.');
|
|
}
|
|
return;
|
|
}
|
|
|
|
switch (pref) {
|
|
case 'never-ask':
|
|
console.log('AUTO_DECIDE');
|
|
break;
|
|
case 'ask-only-for-one-way':
|
|
// Not one-way (we checked above) — auto-decide this two-way question.
|
|
console.log('AUTO_DECIDE');
|
|
break;
|
|
case 'always-ask':
|
|
case undefined:
|
|
case null:
|
|
console.log('ASK_NORMALLY');
|
|
break;
|
|
default:
|
|
console.log('ASK_NORMALLY');
|
|
console.log('NOTE: unknown preference value: ' + pref);
|
|
}
|
|
}).catch(err => { console.error('check:', err.message); process.exit(1); });
|
|
"
|
|
}
|
|
|
|
# -----------------------------------------------------------------------
|
|
# --write '{...}' (with user-origin gate)
|
|
# -----------------------------------------------------------------------
|
|
do_write() {
|
|
local INPUT="${1:-}"
|
|
if [ -z "$INPUT" ]; then
|
|
echo "gstack-question-preference: --write requires a JSON payload" >&2
|
|
exit 1
|
|
fi
|
|
ensure_file
|
|
local TMPERR
|
|
TMPERR=$(mktemp)
|
|
# Use function-local cleanup via RETURN trap so variable lookup only happens
|
|
# while the function is on the stack (avoids EXIT-trap unbound-var race).
|
|
trap "rm -f '$TMPERR'" RETURN
|
|
|
|
set +e
|
|
local RESULT
|
|
RESULT=$(printf '%s' "$INPUT" | PREF_FILE_PATH="$PREF_FILE" EVENT_FILE_PATH="$EVENT_FILE" bun -e "
|
|
const fs = require('fs');
|
|
const raw = await Bun.stdin.text();
|
|
let j;
|
|
try { j = JSON.parse(raw); } catch { process.stderr.write('gstack-question-preference: invalid JSON\n'); process.exit(1); }
|
|
|
|
// Required: question_id (kebab-case, <=64)
|
|
if (!j.question_id || !/^[a-z0-9-]+\$/.test(j.question_id) || j.question_id.length > 64) {
|
|
process.stderr.write('gstack-question-preference: invalid question_id\n');
|
|
process.exit(1);
|
|
}
|
|
|
|
// Required: preference
|
|
const ALLOWED_PREFS = ['always-ask', 'never-ask', 'ask-only-for-one-way'];
|
|
if (!ALLOWED_PREFS.includes(j.preference)) {
|
|
process.stderr.write('gstack-question-preference: invalid preference (must be one of: ' + ALLOWED_PREFS.join(', ') + ')\n');
|
|
process.exit(1);
|
|
}
|
|
|
|
// user-origin gate — REQUIRED on every write.
|
|
// See docs/designs/PLAN_TUNING_V0.md §Security model
|
|
const ALLOWED_SOURCES = ['plan-tune', 'inline-user'];
|
|
const REJECTED_SOURCES = ['inline-tool-output', 'inline-file', 'inline-file-content', 'inline-unknown'];
|
|
if (!j.source) {
|
|
process.stderr.write('gstack-question-preference: source field required (one of: ' + ALLOWED_SOURCES.join(', ') + ')\n');
|
|
process.exit(1);
|
|
}
|
|
if (REJECTED_SOURCES.includes(j.source)) {
|
|
process.stderr.write('gstack-question-preference: rejected — source \"' + j.source + '\" is not user-originated (profile poisoning defense)\n');
|
|
process.exit(2);
|
|
}
|
|
if (!ALLOWED_SOURCES.includes(j.source)) {
|
|
process.stderr.write('gstack-question-preference: invalid source \"' + j.source + '\"; allowed: ' + ALLOWED_SOURCES.join(', ') + '\n');
|
|
process.exit(1);
|
|
}
|
|
|
|
// Optional free_text — sanitize (no injection patterns, no newlines, <=300 chars)
|
|
if (j.free_text !== undefined) {
|
|
if (typeof j.free_text !== 'string') {
|
|
process.stderr.write('gstack-question-preference: free_text must be string\n');
|
|
process.exit(1);
|
|
}
|
|
if (j.free_text.length > 300) j.free_text = j.free_text.slice(0, 300);
|
|
j.free_text = j.free_text.replace(/\n+/g, ' ');
|
|
const INJECTION_PATTERNS = [
|
|
/ignore\s+(all\s+)?previous\s+(instructions|context|rules)/i,
|
|
/you\s+are\s+now\s+/i,
|
|
/override[:\s]/i,
|
|
/\bsystem\s*:/i,
|
|
/\bassistant\s*:/i,
|
|
/do\s+not\s+(report|flag|mention)/i,
|
|
];
|
|
for (const pat of INJECTION_PATTERNS) {
|
|
if (pat.test(j.free_text)) {
|
|
process.stderr.write('gstack-question-preference: free_text contains injection-like content, rejected\n');
|
|
process.exit(1);
|
|
}
|
|
}
|
|
}
|
|
|
|
// Write to preferences file
|
|
const prefs = JSON.parse(fs.readFileSync(process.env.PREF_FILE_PATH, 'utf-8'));
|
|
prefs[j.question_id] = j.preference;
|
|
fs.writeFileSync(process.env.PREF_FILE_PATH, JSON.stringify(prefs, null, 2));
|
|
|
|
// Also append a record to question-events.jsonl for audit + derivation.
|
|
const evt = {
|
|
ts: new Date().toISOString(),
|
|
event_type: 'preference-set',
|
|
question_id: j.question_id,
|
|
preference: j.preference,
|
|
source: j.source,
|
|
...(j.free_text ? { free_text: j.free_text } : {}),
|
|
};
|
|
fs.appendFileSync(process.env.EVENT_FILE_PATH, JSON.stringify(evt) + '\n');
|
|
|
|
console.log('OK: ' + j.question_id + ' → ' + j.preference + ' (source: ' + j.source + ')');
|
|
" 2>"$TMPERR")
|
|
local RC=$?
|
|
set -e
|
|
|
|
if [ $RC -ne 0 ]; then
|
|
cat "$TMPERR" >&2
|
|
exit $RC
|
|
fi
|
|
echo "$RESULT"
|
|
}
|
|
|
|
# -----------------------------------------------------------------------
|
|
# --read
|
|
# -----------------------------------------------------------------------
|
|
do_read() {
|
|
ensure_file
|
|
cat "$PREF_FILE"
|
|
}
|
|
|
|
# -----------------------------------------------------------------------
|
|
# --clear [<id>]
|
|
# -----------------------------------------------------------------------
|
|
do_clear() {
|
|
local QID="${1:-}"
|
|
ensure_file
|
|
if [ -z "$QID" ]; then
|
|
echo '{}' > "$PREF_FILE"
|
|
echo "OK: cleared all preferences"
|
|
else
|
|
PREF_FILE_PATH="$PREF_FILE" QID="$QID" bun -e "
|
|
const fs = require('fs');
|
|
const prefs = JSON.parse(fs.readFileSync(process.env.PREF_FILE_PATH, 'utf-8'));
|
|
if (prefs[process.env.QID] !== undefined) {
|
|
delete prefs[process.env.QID];
|
|
fs.writeFileSync(process.env.PREF_FILE_PATH, JSON.stringify(prefs, null, 2));
|
|
console.log('OK: cleared ' + process.env.QID);
|
|
} else {
|
|
console.log('NOOP: no preference set for ' + process.env.QID);
|
|
}
|
|
"
|
|
fi
|
|
}
|
|
|
|
# -----------------------------------------------------------------------
|
|
# --stats
|
|
# -----------------------------------------------------------------------
|
|
do_stats() {
|
|
ensure_file
|
|
cat "$PREF_FILE" | bun -e "
|
|
const prefs = JSON.parse(await Bun.stdin.text());
|
|
const entries = Object.entries(prefs);
|
|
const counts = { 'always-ask': 0, 'never-ask': 0, 'ask-only-for-one-way': 0, other: 0 };
|
|
for (const [, v] of entries) {
|
|
if (counts[v] !== undefined) counts[v]++;
|
|
else counts.other++;
|
|
}
|
|
console.log('TOTAL: ' + entries.length);
|
|
console.log('ALWAYS_ASK: ' + counts['always-ask']);
|
|
console.log('NEVER_ASK: ' + counts['never-ask']);
|
|
console.log('ASK_ONLY_ONE_WAY: ' + counts['ask-only-for-one-way']);
|
|
if (counts.other) console.log('OTHER: ' + counts.other);
|
|
"
|
|
}
|
|
|
|
case "$CMD" in
|
|
--check) do_check "$@" ;;
|
|
--write) do_write "$@" ;;
|
|
--read|"") do_read ;;
|
|
--clear) do_clear "$@" ;;
|
|
--stats) do_stats ;;
|
|
--help|-h) sed -n '1,/^set -euo/p' "$0" | sed 's|^# \?||' ;;
|
|
*)
|
|
echo "gstack-question-preference: unknown subcommand '$CMD'" >&2
|
|
exit 1
|
|
;;
|
|
esac
|