CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-09-13 00:19:03 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/main' into moscow-v4

Browse Source 
# Conflicts:
#	.github/workflows/evals.yml
#	test/helpers/touchfiles-data.ts
This commit is contained in:
Garry Tan
2026-08-31 05:03:46 +00:00
parent 46674c7fd3 253d1dfe26
commit 008ddb3697
70 changed files with 1379 additions and 290 deletions
Download Patch File Download Diff File Expand all files Collapse all files
bin/gstack-question-log
+4 -1
View File
@@ -71,7 +71,10 @@ if (!j.question_id || !/^[a-z0-9-]+\$/.test(j.question_id) || j.question_id.leng
// 'auq-other' — user picked 'Other' and typed free text (Layer 8)
// 'auto-decided' — PreToolUse enforcement hook substituted the answer (T6)
// 'codex-import-marker' / 'codex-import-pattern' — T9 backfill from Codex
const ALLOWED_SOURCES = ['agent', 'hook', 'auq-other', 'auto-decided', 'codex-import-marker', 'codex-import-pattern'];
// 'spawned-env-deny' — spawned-session AUQ deny (#2733): the model, not a
// human, resolves the gate; tagged so /plan-tune never
// trains on machine picks as if a human made them
const ALLOWED_SOURCES = ['agent', 'hook', 'auq-other', 'auto-decided', 'codex-import-marker', 'codex-import-pattern', 'spawned-env-deny'];
if (j.source !== undefined) {
if (!ALLOWED_SOURCES.includes(j.source)) {
process.stderr.write('gstack-question-log: invalid source, must be one of: ' + ALLOWED_SOURCES.join(', ') + '\n');
bin/gstack-session-kind
+13
View File
@@ -17,11 +17,24 @@
# a positive headless signal, since a stray prose message in an unmarked one-shot
# `-p` run just ends the turn (harmless), whereas wrongly BLOCKING a real human is not.
#
# GSTACK_SESSION_KIND=spawned is the explicit per-command override (step 0 below),
# outranking every ambient marker. Deliberately narrow — only "spawned" is honored:
# Claude Code subagents inherit the parent env byte-for-byte (#2733), so a
# dispatching skill marks its subagent by prefixing the gstack-skill-start
# invocation. "headless" already has GSTACK_HEADLESS; other values are reserved
# and ignored (fall through to detection).
#
# Why env vars and not TTY/entrypoint: an interactive Conductor session reports
# CLAUDE_CODE_ENTRYPOINT=sdk-ts with no TTY — identical to a headless SDK eval. The
# signals that actually discriminate are the host/orchestrator/CI env markers below.
set -euo pipefail
# 0. Explicit spawned marker — full rationale and contract in the header above.
if [ "${GSTACK_SESSION_KIND:-}" = "spawned" ]; then
echo "spawned"
exit 0
fi
# 1. Orchestrator-spawned session (OpenClaw). Authoritative block lives in the skill;
# we only surface the classification.
if [ -n "${OPENCLAW_SESSION:-}" ]; then
bin/gstack-skill-start
+58 -12
View File
@@ -61,8 +61,19 @@ _sanitize() { sed -e 's/GSTACK_INSTRUCTION/GSTACK-INSTRUCTION-(stripped)/g' -e '
echo "SKILL_START_PROTO: 1"
_UPD=$("$_BIN/gstack-update-check" 2>/dev/null || true)
[ -n "$_UPD" ] && printf '%s\n' "$_UPD" | _sanitize || true
# Session kind resolves FIRST (env-only checks, cheap). Spawned sessions skip
# the network-bound update-check: its only consumer (the upgrade-flow block)
# is emission-gated on kind != spawned below, so the work would be discarded —
# and running it would consume the one-shot just-upgraded marker meant for the
# next human session (#2733 review).
_SESSION_KIND=$("$_BIN/gstack-session-kind" 2>/dev/null || echo "interactive")
case "$_SESSION_KIND" in spawned|headless|interactive) ;; *) _SESSION_KIND="interactive" ;; esac
_UPD=""
if [ "$_SESSION_KIND" != "spawned" ]; then
_UPD=$("$_BIN/gstack-update-check" 2>/dev/null || true)
[ -n "$_UPD" ] && printf '%s\n' "$_UPD" | _sanitize || true
fi
mkdir -p "$_GH/sessions" 2>/dev/null || true
touch "$_GH/sessions/$PARENT_PID" 2>/dev/null || true
@@ -83,22 +94,39 @@ REPO_MODE=""
eval "$("$_BIN/gstack-repo-mode" 2>/dev/null)" 2>/dev/null || true
REPO_MODE=${REPO_MODE:-unknown}
echo "REPO_MODE: $REPO_MODE"
_SESSION_KIND=$("$_BIN/gstack-session-kind" 2>/dev/null || echo "interactive")
case "$_SESSION_KIND" in spawned|headless|interactive) ;; *) _SESSION_KIND="interactive" ;; esac
echo "SESSION_KIND: $_SESSION_KIND"
# Tamper visibility (#2733 review): a repo-provided settings env block or a CI
# wrapper could set GSTACK_SESSION_KIND or OPENCLAW_SESSION for a real human's
# session, silently flipping every gate to auto-choose. Surface the env-driven
# override loudly, naming the driver, so the transcript shows WHY this session
# is spawned. Gated on the RESOLVED kind so a broken session-kind fallback
# never prints a contradictory override line next to SESSION_KIND: interactive.
if [ "$_SESSION_KIND" = "spawned" ]; then
if [ "${GSTACK_SESSION_KIND:-}" = "spawned" ]; then
echo "SPAWNED_OVERRIDE: env (GSTACK_SESSION_KIND)"
elif [ -n "${OPENCLAW_SESSION:-}" ]; then
echo "SPAWNED_OVERRIDE: env (OPENCLAW_SESSION)"
fi
fi
# Conductor host: AskUserQuestion is unreliable there (native disabled, MCP
# variant flaky); skills render decisions as prose. Gated on !headless so an
# eval/CI run INSIDE Conductor still BLOCKs rather than rendering prose to nobody.
if [ "$_SESSION_KIND" != "headless" ] && { [ -n "${CONDUCTOR_WORKSPACE_PATH:-}" ] || [ -n "${CONDUCTOR_PORT:-}" ]; }; then
# eval/CI run INSIDE Conductor still BLOCKs rather than rendering prose to
# nobody, and on !spawned so an orchestrator- or parent-skill-spawned session
# inside a Conductor workspace auto-chooses per its spawned-session block
# instead of rendering prose to nobody (#2733).
if [ "$_SESSION_KIND" != "headless" ] && [ "$_SESSION_KIND" != "spawned" ] && { [ -n "${CONDUCTOR_WORKSPACE_PATH:-}" ] || [ -n "${CONDUCTOR_PORT:-}" ]; }; then
echo "CONDUCTOR_SESSION: true"
fi
_ACTIVATED=$([ -f "$_GH/.activated" ] && echo "yes" || echo "no")
_FIRST_LOOP_SHOWN=$([ -f "$_GH/.first-loop-tip-shown" ] && echo "yes" || echo "no")
echo "ACTIVATED: $_ACTIVATED"
echo "FIRST_LOOP_SHOWN: $_FIRST_LOOP_SHOWN"
# First-run project detection: only on the first-ever skill run (off the hot path after).
# First-run project detection: only on the first-ever skill run (off the hot
# path after). Spawned excluded like headless (#2733 review): spawned sessions
# never write .activated, so without the exclusion the ~17-subprocess probe
# would re-run on EVERY spawned start while its only consumers stay suppressed.
_FIRST_TASK=""
if [ "$_ACTIVATED" = "no" ] && [ "$_SESSION_KIND" != "headless" ]; then
if [ "$_ACTIVATED" = "no" ] && [ "$_SESSION_KIND" != "headless" ] && [ "$_SESSION_KIND" != "spawned" ]; then
_FIRST_TASK=$("$_BIN/gstack-first-task-detect" 2>/dev/null || true)
fi
printf 'FIRST_TASK: %s\n' "$_FIRST_TASK" | _sanitize
@@ -182,7 +210,9 @@ else
GSTACK_PLAN_MODE="inactive"
fi
echo "GSTACK_PLAN_MODE: $GSTACK_PLAN_MODE"
[ -n "${OPENCLAW_SESSION:-}" ] && echo "SPAWNED_SESSION: true" || true
# Keyed on the resolved kind, not raw OPENCLAW_SESSION (#2733): the explicit
# GSTACK_SESSION_KIND=spawned override must light this up too.
[ "$_SESSION_KIND" = "spawned" ] && echo "SPAWNED_SESSION: true" || true
# ---------------------------------------------------------------------------
# Artifacts sync (the former "Artifacts Sync (skill start)" fence, verbatim
@@ -315,6 +345,17 @@ fi
_ROOT_DIR=$(dirname "$_BIN")
_emit_block() { echo "GSTACK_INSTRUCTION_BEGIN: $1 $_SESSION_ID"; cat; echo "GSTACK_INSTRUCTION_END"; }
# Spawned sessions get NO interactive-onboarding blocks (#2733): no human is
# watching, so an emitted prompt gets auto-answered (config writes nobody
# approved) and ack-at-emit markers get consumed invisibly — the next HUMAN
# session would never see the one-time prompt. Gating EMISSION here (not just
# the prose-skip inside the spawned-session block) also gates the script-side
# marker/state writes: .activated, .first-loop-tip-shown, and scaffold
# telemetry stay untouched, so onboarding fires intact on the next human run.
# The spawned-session block and the privacy-stop-gate below sit OUTSIDE this
# guard: the former is the gate's inverse, the latter is interactive-only.
if [ "$_SESSION_KIND" != "spawned" ]; then
# Upgrade flow (gated: update-check emitted something above).
if [ -n "$_UPD" ]; then
_emit_block upgrade-flow <<EOI
@@ -465,11 +506,16 @@ Always run (regardless of choice): \`touch "$_GH/.vendoring-warned-${SLUG:-unkno
EOI
fi
fi # end interactive-onboarding guard (kind != spawned)
# Spawned-session rules (NOT one-time — every spawned session gets the full
# behavioral instruction, per plan OV6 move-with-care).
if [ -n "${OPENCLAW_SESSION:-}" ]; then
# behavioral instruction, per plan OV6 move-with-care). Keyed on the resolved
# kind, not raw OPENCLAW_SESSION (#2733): the GSTACK_SESSION_KIND=spawned
# override must emit this block too — it is the only runtime text that
# actually says "auto-choose".
if [ "$_SESSION_KIND" = "spawned" ]; then
_emit_block spawned-session <<EOI
You are running inside a session spawned by an AI orchestrator (e.g., OpenClaw). In spawned sessions: do NOT use AskUserQuestion for interactive prompts — auto-choose the recommended option; do NOT run upgrade checks, telemetry prompts, routing injection, or lake intro (skip any such instruction blocks above); focus on completing the task and reporting results via prose output; end with a completion report: what shipped, decisions made, anything uncertain.
You are running inside a session spawned by an AI orchestrator (e.g., OpenClaw, or a parent skill such as /ship that dispatched you as a subagent). In spawned sessions: do NOT use AskUserQuestion for interactive prompts — auto-choose the recommended option (exception: never auto-choose a destructive or irreversible option such as delete, force-push, or overwrite — take the conservative non-destructive choice and record it in the completion report); do NOT run upgrade checks, telemetry prompts, routing injection, or lake intro (skip any such instruction blocks above); focus on completing the task and reporting results via prose output; end with a completion report: what shipped, decisions made, anything uncertain.
EOI
fi