Files
gstack/bin/gstack-skill-start
T
Garry Tanandcapy-ai[bot] 8018ba52fe v1.91.243.0 fix(capy): source the launch environment from a 0600 file; no skill fence may print the environment (GSTA-104) (#3449)
* fix(capy): the launch environment is sourced from a 0600 file and no skill fence may print the environment (GSTA-104)

During GSTA-96's unattended /ship on #3425, the Step 14.5 docs-audit child
re-typed the GSTACK_LAUNCH assignments as `export $(...)`; the substitution
came back empty, the bare `export` printed the whole environment, and three
API key values landed in its tool output.

- bin/gstack-capy-install writes the assignments to <verdict>.env (mode 0600,
  idempotent PATH prepend) and prints GSTACK_LAUNCH_FILE: <path>.
- ship Step 14.5 prompt, document-release's spawned note, autoplan/DRIVER.md
  and gstack-skill-start's capy-asks block say: source the file; never
  export $(...), env, printenv or bare set in a tool fence.
- test/launch-env-echo-ratchet.test.ts greps every generated SKILL.md,
  sections, DRIVER.md, the Capy skill and bin/ shell helpers, with negative
  controls under test/fixtures/launch-env-echo/.
- lib/redact-engine.ts: env.value (HIGH) finds the value of any *_KEY,
  *_TOKEN, *_SECRET, *_PASSWORD variable in the writer's environment, so a
  leaked value cannot reach a PR body, receipt, report or Drive file.
- scripts/lib/shard-engine.ts scrubs the Capy launch markers from shard
  environments (GSTA-99's finding).

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(ci): DRIVER.md back to 159 lines; shard-engine recorded non-behavioral at HARNESS_VERSION 6; verdict-count test lists .json only

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* test: register test/fixtures/launch-env-echo as a free fixture

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* test(redact): env-value fixtures stay out of pregate's env.kv net

A credential-named assignment with an entropic literal on one line is what
the repo's own pregate secrets scan refuses in added lines, so the fixture
values move into plainly named constants and the scanned text is built from
them. The scan under test still sees the same values through processEnv.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* test(windows): the late-completion remote-caller case gives its second attempt a 2s budget (run 40263984171)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(redact): env.value trims the value, keeps a prefix value's longer match, hides the preview and skips PUBLIC names

/ship Step 9.4 review fixes for the GSTA-104 env-value scan:

- a value whose environment copy ends in a newline (a key read from a file)
  is searched for trimmed, so its leaked form still matches (the length
  check already trimmed; the search used the raw value);
- when one credential value is a prefix of another, the dedup key carries the
  span length, so the longer value is redacted whole in either order instead
  of leaving its tail in the text and dropping its finding;
- the env.value preview is a fixed mask instead of the first characters of a
  live credential;
- framework-public names (NEXT_PUBLIC_*_KEY, *_PUBLIC_KEY) are not scanned,
  since those values are committed on purpose;
- the header and the processEnv docstring state the name rule (KEY, TOKEN,
  SECRET, PASSWORD, PASSWD, any case) and that process.env is the engine's
  one ambient input.

Step 7 coverage extensions and a regression test for each fix in
test/redact-env-value.test.ts; docs/capy-install.md names the full rule.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* refactor(capy-install): write_launch_file quotes through shq; header names the launch file

Review finding: _sq duplicated shq() from the same file. The launch file's
assignments now go through shq, and the header comment describes the
GSTACK_LAUNCH_PATH and GSTACK_LAUNCH_FILE lines beside GSTACK_LAUNCH.

Step 7 coverage: the verdict test sources the launch file and runs --check;
the single-quote path test sources the file too; a new case makes the
launch-file directory unwritable and checks the run says so, prints no
GSTACK_LAUNCH_FILE line, leaves no temp file and keeps its exit code and
trailer (linux, non-root).

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* test(preload): strip the Capy launch markers so a direct bun test matches the shard sandbox

Red Team finding: the launch-marker scrub lived only in createShardSandbox,
so a direct `bun test <file>` run under an unattended Capy session inherited
GSTACK_SESSION_KIND, GSTACK_CAPY, GSTACK_EPHEMERAL and GSTACK_INSTALL_VERDICT
(GSTA-99's symptom). The preload now deletes the same four names, and
test/shard-engine.test.ts imports CAPY_LAUNCH_MARKERS instead of re-typing them.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* test(ratchet): the launch-env echo scan catches backtick and $VAR exports, typeset -p, env flags and a set in any segment

Review findings 11 and 12: export-subst also trips on `export \`...\`` and
an unquoted `export $VAR` (both splat a NAME=value file; `export "$name"` is
one word and stays allowed); the export rule adds `typeset -p`; env trips
with only flags (`env -0`) and as `/usr/bin/env`; set is judged per segment
and with redirections, allowed only when piped straight into an anchored
grep filter. Quoted strings are blanked offset-preserving so a `#` inside
quotes no longer hides the rest of the line. The negative control covers
each new form on both sides.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* docs(ship): Step 14.5 names where the launch-file placeholder comes from

The /document-release prompt line read `. <file>` with no word on what fills
it. It now says the placeholder is the GSTACK_LAUNCH_FILE: path the parent's
own install check printed. Worded to stay under the ship skill's pinned
parity size (313,279 of 313,281 union bytes).

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(redact): env.value admits *_PASS, *_PAT, *_APIKEY and *_PWD, and skips path values and gstack's lock token

/ship Step 11 adversarial findings. The name rule also covers DB_PASS,
GITHUB_PAT, *_APIKEY and *_PWD (the shell's own PWD and OLDPWD stay out). A
credential-named variable whose value is a filesystem path (SSL_KEY=/etc/ssl/
private/x.key) names where the credential lives, so the path is no finding,
and GSTACK_BRAIN_LOCK_TOKEN (pid-random-epoch, written to the lock owner file)
is not a secret. Without these, an ordinary mention of that path or token in a
PR body, receipt or CSO report was a HIGH fail-closed blocker.

The adversarial pass also recommended an entropy floor so dev defaults such as
DB_PASSWORD=postgres stop matching prose; declined here on purpose, because the
scan's promise is to catch a leaked value whatever its shape, and a weak real
password is still a credential. Recorded as an open decision in the ship report.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(capy-install): a failed launch-file write removes only its own temp file

The failure path ran rm -f "$LAUNCH_FILE".tmp.*, which also deleted the temp
file a concurrent installer run (two threads on one machine, same verdict
path) was about to mv, so that run lost its launch file too. write_launch_file
now cleans up its own $tmp and returns 1; the caller only reports. The file's
comment no longer embeds the state-root path (a newline in GSTACK_STATE_ROOT
could have ended the comment).

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* test: the launch markers come from one list, and the echo ratchet scans setup and scripts/*.sh

The preload imports CAPY_LAUNCH_MARKERS instead of re-typing the four names,
and the ratchet asserts the installer exports every name on that list, so a
fifth marker cannot be added to one place only. The shell scan also covers
./setup and the scripts/*.sh install scripts callers run first.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* docs(changelog): the Unreleased entry states the review-fixed env.value rules, the ratchet forms and the one test-budget change

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(redact): the env.value path exemption asks whether the file exists instead of matching a shape

Second review cycle: a path-shaped rule also matched a base64 secret that
starts with "/" and holds another "/" (about 1 in 150 AWS-shaped keys), which
then went unscanned. The exemption now fires only when the value names a file
that exists on the scanning machine (SSL_KEY=/etc/ssl/private/x.key). The
module header names that stat as the engine's one filesystem read.
NON_SECRET_ENV_NAMES is exported so the test can prove bin/gstack-brain-lock.sh
still exports every name in it; the PWD/OLDPWD fixtures hold plain words so only
the name rule keeps them out.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* test: the installer's own-temp-file cleanup is exercised, and the ratchet coverage test names setup and scripts

An mv shim first on PATH refuses only the launch-file target, so the temp
file exists when the move fails: the run removes that file alone (a sibling
from a concurrent run survives), says so, prints no GSTACK_LAUNCH_FILE line
and keeps the earlier file, exit code and trailer. The ratchet coverage test
asserts setup, scripts/build.sh and scripts/sandbox-doctor.sh are scanned.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(redact): env.value has no path exemption and matches the value in normalized form

Second adversarial pass: the existence check let the scanned agent exempt
any "/"- or "~/"-prefixed secret by creating a path of that name, a silent
bypass of the one guard this branch adds, so the exemption is gone; a
path-valued SSL_KEY that must appear in a text goes through the allowlist.
The engine is back to no I/O. The value is now normalized the way the text
is before indexOf, so a credential NFKC rewrites (fullwidth digits) still
finds its leaked ASCII form.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(capy-install): the launch file is written only on a passing run; the ratchet checks the marker list both ways

A gstack: fail run no longer writes or announces a sourceable file whose PATH
prepend points at an unverified Bun. The ratchet also asserts every variable
the launch file exports is a CAPY_LAUNCH_MARKERS entry or GSTACK_STATE_ROOT,
so a sixth export cannot reach fixture children unstripped. The Capy skill's
prose no longer offers re-typing the assignments as an alternative to sourcing.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(capy-install): the launch file is part of the ok verdict

Third adversarial pass: a passing run whose launch file could not be
written still said gstack: ok with exit 0 and printed only the GSTACK_LAUNCH
line, leaving a shell-evaluating caller with the re-typing path the branch
exists to remove. The file is now written before the verdict is recorded;
a write failure on a passing run turns the run into
"gstack: fail launch-file — could not write the launch file <path>; fix: …
(LAUNCH_FILE_UNWRITABLE)" with exit 1 and an ok:false verdict, and every
failing run removes the launch file an earlier passing run left beside the
verdict. The two failure tests assert the new contract, the doctor-FAIL
tests assert no launch file is announced or left, and the docs, Capy skill
and CHANGELOG say the same.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(redact): the env.value allowlist and placeholder rules see the normalized value too

An allowlisted value in NFC did not suppress a match on its NFKC-composed
form, and a value that is a placeholder only after normalization was still
searched for. Fixture nits from the third review cycle: fixed directory
string instead of process.cwd(), the fullwidth assertion guards its own
vacuity, a zero-width-padded value under the floor is pinned, and the
ratchet comment names the one kept export and the PATH case line.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(capy-install): LAUNCH_FILE_UNWRITABLE is a registered result code; a kept profile verdict keeps its launch file

Fourth review cycle. The new trailer code now has its row in
lib/result-codes-capy.ts (the owner module is at its size cap) and its
docs/troubleshooting.md anchor, so the install-side code scan resolves it.
A failing profile check (--for review-voice) that keeps a fuller ok verdict
for this HEAD no longer deletes that verdict's launch file: the fail branch
removes the file only when the run rewrites the verdict, and setup_failed
removes it too. The docs say "a failing run that rewrites the verdict",
and that an unwritable directory keeps both the old file and the old
verdict. A new test runs a passing install, then a failing profile check,
and asserts the file and the ok verdict both survive.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* test(redact): the normalized allowlist and placeholder rules each have an assertion that fails without them

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* test(capy-install): a setup failure after a passing install removes the earlier launch file

Fifth review cycle: setup_failed's cleanup had no assertion. The setup
failure test now installs once (launch file present), commits a new HEAD so
setup runs again, fails that setup, and asserts the launch file is gone and
the verdict says ok:false before the next run sets up again and ends ok.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* docs: state-root, contributor reference and capy-install follow the launch-file contract (Step 14.5 audit)

The /document-release audit (docs-3449-1792992068) corrected three authored
docs: docs/state-root.md shows the GSTACK_LAUNCH_FILE line and says to apply
it with ". <that file>" instead of prefixing or exporting the assignments;
docs/CONTRIBUTOR_REFERENCE.md names scan()'s one ambient input instead of
calling it pure; docs/capy-install.md's bun-shim bullet and exit table name
the launch file and the fail launch-file trailer.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-10-26 12:00:20 +00:00

738 lines
47 KiB
Bash
Executable File

#!/usr/bin/env bash
# gstack-skill-start — the skill preamble's runtime, consolidated (token-reduction Phase 1).
#
# Absorbs the bash that every generated SKILL.md used to inline twice over
# (the "Preamble (run first)" bootstrap fence and the "Artifacts Sync" fence,
# ~13KB per skill x 50 skills). The generated skill now carries a one-line
# invocation; this script emits the SAME `KEY: value` STATUS lines the prose
# rules interpret. The contract is pinned by test/gstack-skill-start.test.ts
# (every KEY the rendered prose references must be emitted here).
#
# Enumerated divergences from the inline original (plan EOV5):
# - Paths resolve $0-relative (works for every host + install layout) instead
# of gen-time interpolation.
# - Session identity is the HARNESS pid, derived here: the nearest non-shell
# ancestor ($PPID inside this script is the ephemeral tool-call shell —
# wrong identity). --parent-pid still overrides it. The rendered command
# passes no "$PPID" (#2763: worktree-isolated Claude Code sessions refuse
# variables and fallbacks in the start command).
# - State paths honor ${GSTACK_HOME} (EOV7); the inline original hardcoded
# ~/.gstack in the bootstrap half.
# - SESSION_ID / TEL_START are echoed (the inline shell vars never survived
# across Bash tool calls, so skill-end durations were already broken; the
# echo makes them real).
# - SKILL_START_PROTO handshake (OV5): prose treats a missing/unexpected
# proto as a degraded install and applies safe defaults.
# - Passthrough sub-command output is sanitized (OV4): GSTACK_INSTRUCTION
# markers cannot be injected into the blessed tool result by learnings,
# update-check, or first-task text.
#
# Error style (F3): per-line `|| true`, never `set -e` — a mid-script failure
# must not drop later STATUS lines.
# Heredoc bodies in the 512B-64KiB window can deadlock bash 5.1+'s pipe-backed
# heredoc path when the reader stalls; compat level 50 restores the tempfile
# path. This script is bash-3.2-clean, so the compat level costs nothing
# (same guard as bin/gstack-brain-sync; pinned by
# test/heredoc-pipe-deadlock.test.ts).
BASH_COMPAT=50
SKILL_NAME=""
MODEL_OVERLAY="none"
PARENT_PID=""
BRAIN_HEALTH="no"
while [ $# -gt 0 ]; do
case "$1" in
--skill) SKILL_NAME="$2"; shift 2 ;;
--model) MODEL_OVERLAY="$2"; shift 2 ;;
--parent-pid) PARENT_PID="$2"; shift 2 ;;
--brain-health) BRAIN_HEALTH="yes"; shift ;;
-h|--help)
echo 'Usage: gstack-skill-start --skill NAME [--model OVERLAY] [--parent-pid PID] [--brain-health]'
echo 'Starts a skill session and prints its STATUS lines. --help starts nothing.'
exit 0 ;;
*) shift ;;
esac
done
[ -n "$SKILL_NAME" ] || SKILL_NAME="unknown"
# Harness pid: walk up from the calling shell past shell wrappers
# (bin/gstack-harness-pid.sh, shared with bin/gstack-lease so the install
# lease and the session marker name the same pid). Without the helper the
# immediate parent stands.
# shellcheck source=bin/gstack-harness-pid.sh
. "$(dirname "$0")/gstack-harness-pid.sh" 2>/dev/null || gstack_harness_pid() { printf '%s\n' "$1"; }
if [ -z "$PARENT_PID" ]; then
PARENT_PID=$(gstack_harness_pid "$PPID")
fi
_SCRIPT_DIR=$(cd "$(dirname "$0")" 2>/dev/null && pwd)
_BIN="$_SCRIPT_DIR"
. "$(dirname "$0")/gstack-state-root.sh" 2>/dev/null || { echo "$0: cannot resolve the gstack state root: $(dirname "$0")/gstack-state-root.sh is missing. fix: reinstall with ./setup or /gstack-upgrade (docs/state-root.md)" >&2; exit 1; }
gstack_state_root_select
_GH="$_gstack_sr_root"
# OV4: strip instruction markers from any passthrough text before echoing it
# into the blessed tool result. Prior-session/repo content must not be able to
# mint directive blocks — nor forge a SESSION_ID: status line (the token that
# authenticates instruction blocks), so line-leading spoofs are neutralized too.
_sanitize() { sed -e 's/GSTACK_INSTRUCTION/GSTACK-INSTRUCTION-(stripped)/g' -e 's/^SESSION_ID:/SESSION-ID-(stripped):/'; }
echo "SKILL_START_PROTO: 1"
# 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")
# Unknown kinds coerce to interactive (the degrade-safe default) but say so
# (plan B1): a mixed-version fleet whose newer parent sets a kind this install
# does not know must be loud, never silently interactive.
_SESSION_KIND_NOTE=""
case "$_SESSION_KIND" in
unattended|spawned|headless|interactive) ;;
*) _SESSION_KIND_NOTE=" (unknown kind '$(printf '%s' "$_SESSION_KIND" | tr -cd 'a-zA-Z0-9._-')')"; _SESSION_KIND="interactive" ;;
esac
# gstack-session-kind ignores an unrecognized GSTACK_SESSION_KIND value (it
# falls through to ambient detection); name it here so the override is visible.
case "${GSTACK_SESSION_KIND:-}" in
''|unattended|spawned|headless|interactive) ;;
*) [ -z "$_SESSION_KIND_NOTE" ] && _SESSION_KIND_NOTE=" (unknown kind '$(printf '%s' "$GSTACK_SESSION_KIND" | tr -cd 'a-zA-Z0-9._-')')" ;;
esac
# Unattended (plan B1): a parent agent drives this run and reads its artifacts.
# No prompts, no publishing, no sync: the same suppression spawned gets, plus
# the writers and sync entrypoints below skip with an explicit line. Keyed on
# the resolved kind, so only the explicit GSTACK_SESSION_KIND override lights it.
_NO_HUMAN="no"
case "$_SESSION_KIND" in spawned|unattended) _NO_HUMAN="yes" ;; esac
# Durability of the state root (plan A3): GSTACK_EPHEMERAL=1 is the host's
# marker for a disk that vanishes with the machine (a Capy cloud box). Printed
# once per session so writers that skip on an ephemeral root are explained.
_DURABLE="yes"
[ "${GSTACK_EPHEMERAL:-}" = "1" ] && _DURABLE="no"
_UPD=""
if [ "$_NO_HUMAN" != "yes" ]; then
_UPD=$("$_BIN/gstack-update-check" 2>/dev/null || true)
[ -n "$_UPD" ] && printf '%s\n' "$_UPD" | _sanitize || true
fi
# Session markers: local functional state (live-session count), never sent and
# not gated on telemetry (#1150). README "Privacy & Telemetry" describes them.
mkdir -p "$_GH/sessions" 2>/dev/null || true
touch "$_GH/sessions/$PARENT_PID" 2>/dev/null || true
find "$_GH/sessions" -mmin +120 -type f -exec rm {} + 2>/dev/null || true
# The install-scoped twin (bin/gstack-lease): what bin/gstack-upgrade reads
# before moving a checkout other sessions share. Fail-open, but a lease the
# held lock kept from being written is reported.
"$_BIN/gstack-lease" touch --pid "$PARENT_PID" >/dev/null 2>&1 || {
[ $? -eq 3 ] && echo "gstack-lease: the lease directory stayed locked by a live process; this session holds no workflow lease, so bin/gstack-upgrade cannot see it" >&2
true
}
_SESSIONS=$(find "$_GH/sessions" -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
_PROACTIVE=$("$_BIN/gstack-config" get proactive 2>/dev/null || echo "core")
# A hand-edited config can hold anything: drop quotes and a trailing comment,
# lowercase, read the legacy true/false and the YAML yes/no family as all/off
# (an opt-out must never fail open), and anything else as core, so STATUS only
# ever says core | all | off.
_PROACTIVE=$(printf '%s' "$_PROACTIVE" | sed -e 's/[[:space:]]*#.*$//' -e "s/^[[:space:]]*[\"']*//" -e "s/[\"']*[[:space:]]*$//" | tr '[:upper:]' '[:lower:]')
case "$_PROACTIVE" in
true|yes|y|on|1) _PROACTIVE="all" ;;
false|no|n|none|0|disabled|never) _PROACTIVE="off" ;;
core|all|off) ;;
*) _PROACTIVE="core" ;;
esac
# off silences every unasked surface below: the tips, the one-time prompt and
# the CLAUDE.md routing offer. A stored off also answers the one-time prompt,
# so the marker is written here, before STATUS reports it.
case "$_PROACTIVE" in off) _PROACTIVE_OFF="yes" ;; *) _PROACTIVE_OFF="no" ;; esac
_PROACTIVE_PROMPTED=$([ -f "$_GH/.proactive-prompted" ] && echo "yes" || echo "no")
if [ "$_PROACTIVE_PROMPTED" = "no" ] && [ "$_PROACTIVE_OFF" = "yes" ]; then
touch "$_GH/.proactive-prompted" 2>/dev/null || true
_PROACTIVE_PROMPTED="yes"
fi
# Branch name is embedded in concatenated JSON below; strip anything outside
# the gstack-slug BRANCH alphabet so a hostile ref name can't forge fields.
_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-')
_BRANCH=${_BRANCH:-unknown}
echo "BRANCH: $_BRANCH"
_SKILL_PREFIX=$("$_BIN/gstack-config" get skill_prefix 2>/dev/null || echo "false")
echo "PROACTIVE: $_PROACTIVE"
echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
echo "SKILL_PREFIX: $_SKILL_PREFIX"
REPO_MODE=""
eval "$("$_BIN/gstack-repo-mode" 2>/dev/null)" 2>/dev/null || true
REPO_MODE=${REPO_MODE:-unknown}
echo "REPO_MODE: $REPO_MODE"
echo "SESSION_KIND: $_SESSION_KIND$_SESSION_KIND_NOTE"
# Capy (capy/skill/gstack/captain.md): GSTACK_CAPY=1 comes from the Capy launch
# line. On, every decision goes through Capy (Captain or person) and the
# capy-asks block below says how; GSTACK_CAPY_ASKS=0 keeps the line but drops
# the block.
_CAPY=off
[ "${GSTACK_CAPY:-}" = "1" ] && _CAPY=on
if [ "$_CAPY" = "on" ] && [ "${GSTACK_CAPY_ASKS:-}" = "0" ]; then echo "CAPY: on (asks block off: GSTACK_CAPY_ASKS=0)"; else echo "CAPY: $_CAPY"; fi
echo "STATE_ROOT: $_GH durable=$_DURABLE"
echo "SESSIONS: ${_SESSIONS:-0}"
# Install admission (field wave A2): an unattended or Capy-spawned run on an
# unsupported Bun, or on a Capy machine without a matching install verdict,
# refuses here instead of running anyway. Rules: bin/gstack-install-verdict.sh.
if . "$_BIN/gstack-install-verdict.sh" 2>/dev/null && . "$_BIN/gstack-bun-version.sh" 2>/dev/null && . "$_BIN/gstack-doctor-components.sh" 2>/dev/null; then
gstack_install_admission "$_BIN" "$SKILL_NAME" "$_SESSION_KIND"
[ -n "$_ia_line" ] && echo "$_ia_line"
if [ "$_ia_refuse" = 1 ]; then
# The preamble already honors instruction blocks bound to this run's
# SESSION_ID, so the stop rule rides here instead of growing every skill.
_ia_sid="$PARENT_PID-$(date +%s)-$(od -An -N4 -tx4 /dev/urandom 2>/dev/null | tr -d ' \n')"
_ia_result="GSTACK_RESULT: skill=$(printf '%s' "$SKILL_NAME" | tr -cd 'a-zA-Z0-9._-') status=refused run=-"
echo "SESSION_ID: $_ia_sid"
echo "GSTACK_INSTRUCTION_BEGIN: install-refused $_ia_sid"
echo "This workflow refused to start (the INSTALL: row above). STOP: report that row and its fix: command to the parent, run nothing else from this skill, and end with \`$_ia_result\`."
echo "GSTACK_INSTRUCTION_END"
echo "$_ia_result"
exit 3
fi
fi
# Tamper visibility (#2733 review): a repo-provided settings env block or a CI
# wrapper could set GSTACK_SESSION_KIND or OPENCLAW_SESSION for a real human's
# session, silently flipping every gate to auto-choose. Surface the env-driven
# override loudly, naming the driver, so the transcript shows WHY this session
# is spawned. Gated on the RESOLVED kind so a broken session-kind fallback
# never prints a contradictory override line next to SESSION_KIND: interactive.
if [ "$_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, 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" ] && [ "$_SESSION_KIND" != "unattended" ] && { [ -n "${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: $_FIRST_LOOP_SHOWN"
# First-run project detection: only on the first-ever skill run (off the hot
# path after). Spawned excluded like headless (#2733 review): spawned sessions
# never write .activated, so without the exclusion the ~17-subprocess probe
# would re-run on EVERY spawned start while its only consumers stay suppressed.
_FIRST_TASK=""
if [ "$_ACTIVATED" = "no" ] && [ "$_SESSION_KIND" != "headless" ] && [ "$_NO_HUMAN" != "yes" ]; then
_FIRST_TASK=$("$_BIN/gstack-first-task-detect" 2>/dev/null || true)
fi
printf 'FIRST_TASK: %s\n' "$_FIRST_TASK" | _sanitize
_LAKE_SEEN=$([ -f "$_GH/.completeness-intro-seen" ] && echo "yes" || echo "no")
echo "LAKE_INTRO: $_LAKE_SEEN"
_TEL=$("$_BIN/gstack-config" get telemetry 2>/dev/null || true)
_TEL_PROMPTED=$([ -f "$_GH/.telemetry-prompted" ] && echo "yes" || echo "no")
_TEL_START=$(date +%s)
# PID+epoch alone is guessable; a random suffix makes the block-binding token
# unforgeable by content reflected into the same tool result. Falls back to
# the plain form when urandom is unavailable.
_SID_RAND=$(od -An -N4 -tx4 /dev/urandom 2>/dev/null | tr -d ' \n' || true)
_SESSION_ID="$PARENT_PID-$_TEL_START${_SID_RAND:+-$_SID_RAND}"
echo "TELEMETRY: ${_TEL:-off}"
echo "TEL_PROMPTED: $_TEL_PROMPTED"
echo "SESSION_ID: $_SESSION_ID"
echo "TEL_START: $_TEL_START"
_EXPLAIN_LEVEL=$("$_BIN/gstack-config" get explain_level 2>/dev/null || echo "default")
if [ "$_EXPLAIN_LEVEL" != "default" ] && [ "$_EXPLAIN_LEVEL" != "terse" ]; then _EXPLAIN_LEVEL="default"; fi
echo "EXPLAIN_LEVEL: $_EXPLAIN_LEVEL"
_QUESTION_TUNING=$("$_BIN/gstack-config" get question_tuning 2>/dev/null || echo "false")
echo "QUESTION_TUNING: $_QUESTION_TUNING"
_UPDATE_CHECK=$("$_BIN/gstack-config" get update_check 2>/dev/null || echo "true")
echo "UPDATE_CHECK: $_UPDATE_CHECK"
mkdir -p "$_GH/analytics" 2>/dev/null || true
# Privacy at the writer (plan B1): an unattended session never records usage or
# sends telemetry, even with an inherited enabled setting or pending queue work;
# the pending files stay for the next human session to drain.
if [ "$_SESSION_KIND" = "unattended" ]; then
echo "TELEMETRY_WRITE: skipped (unattended session)"
else
if [ "$_TEL" != "off" ]; then
echo '{"skill":"'"$SKILL_NAME"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(_repo=$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null | tr -cd 'a-zA-Z0-9._-'); echo "${_repo:-unknown}")'"}' >> "$_GH/analytics/skill-usage.jsonl" 2>/dev/null || true
fi
for _PF in $(find "$_GH/analytics" -maxdepth 1 -name '.pending-*' 2>/dev/null); do
if [ -f "$_PF" ]; then
if [ "$_TEL" != "off" ] && [ -x "$_BIN/gstack-telemetry-log" ]; then
"$_BIN/gstack-telemetry-log" --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true
fi
rm -f "$_PF" 2>/dev/null || true
fi
# Deliberate throttle: drain at most ONE orphaned pending file per skill
# start so a backlog can't stall the preamble.
break
done
fi
eval "$("$_BIN/gstack-slug" 2>/dev/null)" 2>/dev/null || true
for _former in $("$_BIN/gstack-slug" --get FORMER_SLUGS 2>/dev/null || true); do
echo "gstack: earlier data for this project is in projects/$_former (a worktree's old bucket). Merge it: gstack-slug --adopt-legacy --from $_former (or stop this reminder: gstack-slug --adopt-legacy --dismiss $_former)"
done
_LEARN_FILE="$_GH/projects/${SLUG:-unknown}/learnings.jsonl"
if [ -f "$_LEARN_FILE" ]; then
_LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
echo "LEARNINGS: $_LEARN_COUNT entries loaded"
if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
_LEARN_ERR=$(mktemp "${TMPDIR:-/tmp}/gstack-learn-err.XXXXXX" 2>/dev/null) || _LEARN_ERR=/dev/null
if ! "$_BIN/gstack-learnings-search" --limit 3 2>"$_LEARN_ERR" | _sanitize; then
echo "LEARNINGS: unavailable ($(head -n 1 "$_LEARN_ERR" 2>/dev/null))"
fi
[ "$_LEARN_ERR" = /dev/null ] || rm -f "$_LEARN_ERR"
fi
else
echo "LEARNINGS: 0"
fi
# Plan A3: on an ephemeral root an unattended run's learnings would be written
# to a disk that vanishes; say so instead of writing silently.
if [ "$_SESSION_KIND" = "unattended" ] && [ "$_DURABLE" = "no" ]; then
echo "learnings: skipped (state root is ephemeral; set GSTACK_STATE_ROOT)"
fi
# Plan B1: the autoplan publication hook executes only inside Claude Code
# (CLAUDECODE is set there; GSTACK_ACTIVE_HOST names an env-var host). On
# every other host, and in every unattended session, the hook is rendered but
# never runs, so publication order rests on the per-phase snapshot hashes.
# Claude Code's deny-on-absent behavior is untouched: this line is printed,
# never used to allow anything. B0's validator requires it in an unattended
# run's review-record.md.
if [ "$SKILL_NAME" = "autoplan" ]; then
if [ "$_SESSION_KIND" = "unattended" ] || [ -z "${CLAUDECODE:-}" ] || { [ -n "${GSTACK_ACTIVE_HOST:-}" ] && [ "${GSTACK_ACTIVE_HOST:-}" != "claude" ]; }; then
echo "autoplan guard: not enforced by this host; publication order is unverified (GUARD_NOT_INSTALLED)"
fi
fi
"$_BIN/gstack-timeline-log" '{"skill":"'"$SKILL_NAME"'","event":"started","branch":"'"$_BRANCH"'","session":"'"$_SESSION_ID"'"}' 2>/dev/null &
_HAS_ROUTING="no"
for _RF in CLAUDE.md AGENTS.md; do
if [ -f "$_RF" ] && grep -q "## Skill routing" "$_RF" 2>/dev/null; then
_HAS_ROUTING="yes"
fi
done
_ROUTING_DECLINED=$("$_BIN/gstack-config" get routing_declined 2>/dev/null || echo "false")
echo "HAS_ROUTING: $_HAS_ROUTING"
echo "ROUTING_DECLINED: $_ROUTING_DECLINED"
_VENDORED="no"
if [ -d ".claude/skills/gstack" ] && [ ! -L ".claude/skills/gstack" ]; then
if [ -f ".claude/skills/gstack/VERSION" ] || [ -d ".claude/skills/gstack/.git" ]; then
_VENDORED="yes"
fi
fi
echo "VENDORED_GSTACK: $_VENDORED"
echo "MODEL_OVERLAY: $MODEL_OVERLAY"
# Plan-mode hint for skills that branch on plan-mode state. Detected best-effort
# from CLAUDE_PLAN_FILE (set by the harness when plan mode is active); "inactive"
# is the safe default (file+execute pipeline).
if [ -n "${CLAUDE_PLAN_FILE:-}${GSTACK_PLAN_MODE_FORCE:-}" ]; then
GSTACK_PLAN_MODE="active"
elif [ "${GSTACK_PLAN_MODE:-}" = "active" ]; then
GSTACK_PLAN_MODE="active"
else
GSTACK_PLAN_MODE="inactive"
fi
echo "GSTACK_PLAN_MODE: $GSTACK_PLAN_MODE"
# Keyed on the resolved kind, not raw OPENCLAW_SESSION (#2733): the explicit
# GSTACK_SESSION_KIND=spawned override must light this up too.
[ "$_SESSION_KIND" = "spawned" ] && echo "SPAWNED_SESSION: true" || true
[ "$_SESSION_KIND" = "unattended" ] && echo "UNATTENDED_SESSION: true" || true
[ "$_SESSION_KIND" = "unattended" ] && [ "$SKILL_NAME" = "ship" ] && echo "UNATTENDED_SHIP: no push, no new PR; an open PR at HEAD gets its body updated (pr-body section, receipt first), else Step 18 takes the handoff section; receipt at .gstack/tmp/ship-receipt.md; end with gstack-ship-receipt result" || true
# ---------------------------------------------------------------------------
# Artifacts sync (the former "Artifacts Sync (skill start)" fence, verbatim
# modulo GSTACK_HOME + $0-relative bins).
# ---------------------------------------------------------------------------
if [ -f "$HOME/.gstack-artifacts-remote.txt" ]; then
_BRAIN_REMOTE_FILE="$HOME/.gstack-artifacts-remote.txt"
else
_BRAIN_REMOTE_FILE="$HOME/.gstack-brain-remote.txt"
fi
_BRAIN_SYNC_BIN="$_BIN/gstack-brain-sync"
_BRAIN_CONFIG_BIN="$_BIN/gstack-config"
# /sync-gbrain context-load hint. Per-worktree pin via kubectl-style
# .gbrain-source at the git toplevel; empty output when gbrain is not
# configured (zero context cost for non-gbrain users).
_GBRAIN_CONFIG="$HOME/.gbrain/config.json"
if [ -f "$_GBRAIN_CONFIG" ] && command -v gbrain >/dev/null 2>&1; then
_GBRAIN_VERSION_OK=$(gbrain --version 2>/dev/null | grep -c '^gbrain ' || true)
if [ "$_GBRAIN_VERSION_OK" -gt 0 ] 2>/dev/null; then
_GBRAIN_PIN_PATH=""
_REPO_TOP=$(git rev-parse --show-toplevel 2>/dev/null || echo "")
if [ -n "$_REPO_TOP" ] && [ -f "$_REPO_TOP/.gbrain-source" ]; then
_GBRAIN_PIN_PATH="$_REPO_TOP/.gbrain-source"
fi
if [ -n "$_GBRAIN_PIN_PATH" ]; then
echo "GBrain configured. Prefer \`gbrain search\`/\`gbrain query\` over Grep for"
echo "semantic questions; use \`gbrain code-def\`/\`code-refs\`/\`code-callers\` for"
echo "symbol-aware code lookup. See \"## GBrain Search Guidance\" in CLAUDE.md."
echo "Run /sync-gbrain to refresh."
else
echo "GBrain configured but this worktree isn't pinned yet. Run \`/sync-gbrain --full\`"
echo "before relying on \`gbrain search\` for code questions in this worktree."
echo "Falls back to Grep until pinned."
fi
fi
fi
_BRAIN_SYNC_MODE=$("$_BRAIN_CONFIG_BIN" get artifacts_sync_mode 2>/dev/null || echo off)
# Remote-MCP mode detection (Path 4 of /setup-gbrain): read claude.json
# directly (no subprocess to claude CLI on the hot path). Both registration
# scopes are read (#2499): nearest-ancestor project scope first, then user
# scope; project-local BEATS user scope; the ancestor match accepts both path
# separators (Windows project keys are backslash-formed).
_GBRAIN_MCP_MODE="none"
_GBRAIN_MCP_ENTRY=""
# Cheap substring pre-filter: ~/.claude.json can be megabytes on real installs;
# skip the full jq parse when no gbrain server is registered at all.
if command -v jq >/dev/null 2>&1 && [ -f "$HOME/.claude.json" ] && grep -q '"gbrain"' "$HOME/.claude.json" 2>/dev/null; then
_GBRAIN_MCP_ENTRY=$(jq -c --arg cwd "$PWD" '((.projects // {}) | to_entries | map(select((.key as $k | $cwd == $k or ($cwd | startswith($k + "/")) or ($cwd | startswith($k + "\\"))) and ((try .value.mcpServers.gbrain catch null) != null))) | sort_by(.key | length) | last | .value.mcpServers.gbrain) // .mcpServers.gbrain // empty' "$HOME/.claude.json" 2>/dev/null)
_GBRAIN_MCP_TYPE=$(printf '%s' "$_GBRAIN_MCP_ENTRY" | jq -r '.type // .transport // empty' 2>/dev/null)
case "$_GBRAIN_MCP_TYPE" in
url|http|sse) _GBRAIN_MCP_MODE="remote-http" ;;
stdio) _GBRAIN_MCP_MODE="local-stdio" ;;
esac
fi
if [ -f "$_BRAIN_REMOTE_FILE" ] && [ ! -d "$_GH/.git" ] && [ "$_BRAIN_SYNC_MODE" = "off" ]; then
_BRAIN_NEW_URL=$(head -1 "$_BRAIN_REMOTE_FILE" 2>/dev/null | tr -d '[:space:]')
if [ -n "$_BRAIN_NEW_URL" ]; then
printf 'ARTIFACTS_SYNC: artifacts repo detected: %s\n' "$_BRAIN_NEW_URL" | _sanitize
echo "ARTIFACTS_SYNC: run 'gstack-brain-restore' to pull your cross-machine artifacts (or 'gstack-config set artifacts_sync_mode off' to dismiss forever)"
fi
fi
# Privacy at the sync entrypoint (plan B1): an unattended session neither pulls
# nor pushes the artifacts repo, whatever the inherited mode or queue depth.
if [ "$_SESSION_KIND" = "unattended" ]; then
:
elif [ -d "$_GH/.git" ] && [ "$_BRAIN_SYNC_MODE" != "off" ]; then
_BRAIN_LAST_PULL_FILE="$_GH/.brain-last-pull"
_BRAIN_NOW=$(date +%s)
_BRAIN_DO_PULL=1
if [ -f "$_BRAIN_LAST_PULL_FILE" ]; then
_BRAIN_LAST=$(cat "$_BRAIN_LAST_PULL_FILE" 2>/dev/null || echo 0)
case "$_BRAIN_LAST" in ''|*[!0-9]*) _BRAIN_LAST=0 ;; esac
_BRAIN_AGE=$(( _BRAIN_NOW - _BRAIN_LAST ))
[ "$_BRAIN_AGE" -lt 86400 ] && _BRAIN_DO_PULL=0
fi
if [ "$_BRAIN_DO_PULL" = "1" ]; then
# Daily artifacts pull is a brain-sync-class sink: receipt-before-send,
# fail-closed (same wiring as bin/gstack-brain-sync's fetch/push).
. "$_BIN/gstack-egress-lib.sh" 2>/dev/null || true
_PULL_HOST=$(cd "$_GH" 2>/dev/null && git remote get-url origin 2>/dev/null | sed -E 's|^[a-z+]+://([^/@]*@)?([^/:]+).*|\2|; s|^([^@]+@)?([^:]+):.*|\2|' | head -1)
# The merge writes the artifacts repo's git state, so it takes the drain
# lock every gstack writer shares; when a drain holds it, the pull waits
# for the next start (no stamp).
. "$_BIN/gstack-brain-lock.sh" 2>/dev/null || true
if command -v _receipted_git >/dev/null 2>&1 && command -v gstack_brain_lock_acquire >/dev/null 2>&1 \
&& gstack_brain_lock_acquire "$_GH" try; then
# Non-interactive + slow-network bounded (same guards as gstack-update-check):
# a hung remote or a credential prompt must not stall the preamble.
( cd "$_GH" && GSTACK_HOME="$_GH" GIT_TERMINAL_PROMPT=0 GIT_HTTP_LOW_SPEED_LIMIT=1000 GIT_HTTP_LOW_SPEED_TIME=5 \
_receipted_git closed brain-sync "${_PULL_HOST:-unknown}" curated-memory-git-fetch "artifacts_sync_mode!=off" \
git fetch origin >/dev/null 2>&1 && git merge --ff-only "origin/$(git rev-parse --abbrev-ref HEAD)" >/dev/null 2>&1 ) || true
gstack_brain_lock_release
# Stamp only when the receipted path actually ran — a missing egress lib
# must surface as a retry next start, not a silent 24h suppression.
echo "$_BRAIN_NOW" > "$_BRAIN_LAST_PULL_FILE"
fi
fi
"$_BRAIN_SYNC_BIN" --once 2>/dev/null || true
fi
if [ "$_SESSION_KIND" = "unattended" ]; then
_BRAIN_QUEUE_DEPTH=0
[ -d "$_GH/.brain-queue.d" ] && _BRAIN_QUEUE_DEPTH=$(find "$_GH/.brain-queue.d" -maxdepth 1 -name '*.json' 2>/dev/null | wc -l | tr -d ' ')
[ -f "$_GH/.brain-queue.jsonl" ] && _BRAIN_QUEUE_DEPTH=$(( _BRAIN_QUEUE_DEPTH + $(wc -l < "$_GH/.brain-queue.jsonl" | tr -d ' ') ))
echo "ARTIFACTS_SYNC: skipped (unattended session; mode=$_BRAIN_SYNC_MODE queue=$_BRAIN_QUEUE_DEPTH retained)"
elif [ "$_GBRAIN_MCP_MODE" = "remote-http" ]; then
# Remote-MCP mode: local artifacts sync is a no-op by design (the brain
# admin's server pulls from GitHub/GitLab).
_GBRAIN_HOST=$(printf '%s' "${_GBRAIN_MCP_ENTRY:-}" | jq -r '.url // empty' 2>/dev/null | sed -E 's|^https?://([^/:]+).*|\1|' | head -1 | tr -cd 'A-Za-z0-9._-')
echo "ARTIFACTS_SYNC: remote-mode (managed by brain server ${_GBRAIN_HOST:-remote})"
elif [ -d "$_GH/.git" ] && [ "$_BRAIN_SYNC_MODE" != "off" ]; then
_BRAIN_QUEUE_DEPTH=0
# Spool-dir queue (one file per record); legacy .brain-queue.jsonl lines
# counted too until the drain migrates them.
[ -d "$_GH/.brain-queue.d" ] && _BRAIN_QUEUE_DEPTH=$(find "$_GH/.brain-queue.d" -maxdepth 1 -name '*.json' 2>/dev/null | wc -l | tr -d ' ')
[ -f "$_GH/.brain-queue.jsonl" ] && _BRAIN_QUEUE_DEPTH=$(( _BRAIN_QUEUE_DEPTH + $(wc -l < "$_GH/.brain-queue.jsonl" | tr -d ' ') ))
[ -f "$_GH/.brain-queue.jsonl.migrating" ] && _BRAIN_QUEUE_DEPTH=$(( _BRAIN_QUEUE_DEPTH + $(wc -l < "$_GH/.brain-queue.jsonl.migrating" | tr -d ' ') ))
_BRAIN_LAST_PUSH="never"
# First line only + charset clamp: this file lives in a git checkout pulled
# from the artifacts remote, so its content is not trusted for STATUS output.
[ -f "$_GH/.brain-last-push" ] && _BRAIN_LAST_PUSH=$(head -1 "$_GH/.brain-last-push" 2>/dev/null | tr -cd 'A-Za-z0-9._:+-' || echo never)
_BRAIN_LAST_PUSH=${_BRAIN_LAST_PUSH:-never}
echo "ARTIFACTS_SYNC: mode=$_BRAIN_SYNC_MODE | last_push=$_BRAIN_LAST_PUSH | queue=$_BRAIN_QUEUE_DEPTH"
# A stuck sync (scanner hold, failed push or commit, no push or no drain for
# 24 hours) prints fixed attention lines; a healthy sync prints none.
"$_BRAIN_SYNC_BIN" --attention 2>/dev/null | grep '^ARTIFACTS_SYNC: attention: ' || true
else
echo "ARTIFACTS_SYNC: off"
fi
# ---------------------------------------------------------------------------
# Instruction-emission layer (token-reduction Phase 2). One-time onboarding
# text used to be inlined unconditionally in every SKILL.md (~7KB/skill);
# it now appears ONLY when its runtime gate fires, wrapped in blocks the
# preamble prose tells the model to follow. Security scoping (F4/OV4): each
# header carries this run's SESSION_ID; the prose rule requires the match and
# accepts blocks only from this command's direct tool result, so page/file
# content cannot mint directives (passthrough output above is _sanitize-d).
# Ack ownership (OV6): display-only tips write their done-marker here at
# emit; interactive flows carry their ack commands inside the block for the
# model to run after the interaction.
# ---------------------------------------------------------------------------
_ROOT_DIR=$(dirname "$_BIN")
_emit_block() { echo "GSTACK_INSTRUCTION_BEGIN: $1 $_SESSION_ID"; cat; echo "GSTACK_INSTRUCTION_END"; }
# Spawned sessions get NO interactive-onboarding blocks (#2733): no human is
# watching, so an emitted prompt gets auto-answered (config writes nobody
# approved) and ack-at-emit markers get consumed invisibly — the next HUMAN
# session would never see the one-time prompt. Gating EMISSION here (not just
# the prose-skip inside the spawned-session block) also gates the script-side
# marker/state writes: .activated, .first-loop-tip-shown, and scaffold
# telemetry stay untouched, so onboarding fires intact on the next human run.
# The spawned-session block and the privacy-stop-gate below sit OUTSIDE this
# guard: the former is the gate's inverse, the latter is interactive-only.
if [ "$_NO_HUMAN" != "yes" ]; then
# Upgrade flow (gated: update-check emitted something above).
if [ -n "$_UPD" ]; then
_emit_block upgrade-flow <<EOI
The update-check output above applies. If it shows \`UPGRADE_AVAILABLE <old> <new>\`: read \`$_ROOT_DIR/gstack-upgrade/SKILL.md\` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If it shows \`JUST_UPGRADED <from> <to>\`: print "Running gstack v{to} (just updated!)". If \`SPAWNED_SESSION\` is true, skip feature discovery. After upgrade prompts, continue the workflow.
EOI
fi
# Feature discovery (one prompt per session, marker-gated). These are
# machine-local UX acknowledgements, so keep them in GSTACK_HOME rather than
# beside an install path that may resolve through a project-local symlink.
if [ ! -f "$_GH/.feature-prompted-model-overlay" ]; then
_emit_block feature-overlay <<EOI
Feature discovery: inform "Model overlays are active. MODEL_OVERLAY shows the patch." Always run: \`touch "$_GH/.feature-prompted-model-overlay"\`.
EOI
fi
# Writing-style migration (gate previously dormant: nothing echoed
# WRITING_STYLE_PENDING; the script now computes it from the marker files).
if [ -f "$_GH/.writing-style-prompt-pending" ] && [ ! -f "$_GH/.writing-style-prompted" ]; then
_emit_block writing-style-migration <<EOI
Ask once about writing style:
> v1 prompts are simpler: first-use jargon glosses, outcome-framed questions, shorter prose. Keep default or restore terse?
Options:
- A) Keep the new default (recommended — good writing helps everyone)
- B) Restore V0 prose — set \`explain_level: terse\`
If A: leave \`explain_level\` unset (defaults to \`default\`). If B: run \`$_BIN/gstack-config set explain_level terse\`.
Always run (regardless of choice): \`rm -f "$_GH/.writing-style-prompt-pending" && touch "$_GH/.writing-style-prompted"\`.
EOI
fi
# Lake intro (one-time; the offer is interactive, so the model acks).
if [ "$_LAKE_SEEN" = "no" ]; then
_emit_block lake-intro <<EOI
Say: "gstack follows the **Boil the Ocean** principle — do the complete thing when AI makes marginal cost near-zero. Read more: https://garryslist.org/posts/boil-the-ocean" and offer to open it. Only run \`open https://garryslist.org/posts/boil-the-ocean\` if the user says yes. Always run: \`touch "$_GH/.completeness-intro-seen"\`.
EOI
fi
# Telemetry opt-in (interactive; consent — the model acks after answering).
if [ "$_TEL_PROMPTED" = "no" ] && [ "$_LAKE_SEEN" = "yes" ]; then
_emit_block telemetry-prompt <<EOI
Ask telemetry once via AskUserQuestion:
> Help gstack get better. Yes sends, per skill run: skill name, outcome, duration, gstack version, OS, a redacted error summary and a stable device ID. Never code, file paths, prompts, repo or branch names. Your repo and branch are also logged on this machine (analytics/skill-usage.jsonl) and stripped before upload; off logs nothing. Not covered by this answer: the update check asks GitHub for the latest version about hourly (\`gstack-config set update_check false\`), and outside reviews send code to Codex or Claude Code (\`gstack-config set codex_reviews disabled\`). Details: README "Privacy & Telemetry".
Options:
- A) Help gstack get better! (recommended)
- B) No thanks
If A: run \`$_BIN/gstack-config set telemetry community\`. If B, ask the follow-up:
> Anonymous mode sends only aggregate usage, no unique ID.
Options: A) Sure, anonymous is fine B) No thanks, fully off
If B→A: \`$_BIN/gstack-config set telemetry anonymous\`. If B→B: \`$_BIN/gstack-config set telemetry off\`.
Always run: \`touch "$_GH/.telemetry-prompted"\`.
EOI
fi
# Proactive-suggestions opt-in (interactive; a stored off answered it above).
if [ "$_PROACTIVE_PROMPTED" = "no" ] && [ "$_TEL_PROMPTED" = "yes" ]; then
_emit_block proactive-prompt <<EOI
Ask once:
> Let gstack proactively suggest skills? By default it suggests only the four core ones: /office-hours for a new idea, /review for a diff, /qa for "does this work?", /ship to land it.
Options: A) Keep the core four (recommended) B) Suggest every matching skill C) Turn it off — I'll type /commands myself
If A: \`$_BIN/gstack-config set proactive core\`. If B: \`$_BIN/gstack-config set proactive all\`. If C: \`$_BIN/gstack-config set proactive off\`.
Always run: \`touch "$_GH/.proactive-prompted"\`.
EOI
fi
# First-run guidance (display-only tips: marker + scaffold telemetry written
# HERE at emit, per OV6 — a lost tip is acceptable; a re-firing loop is not).
if [ "$_ACTIVATED" = "no" ]; then
_FT_TIP=""
case "$_FIRST_TASK" in
greenfield) _FT_TIP="Fresh repo — shape it first with \`/office-hours\`." ;;
code_node|code_python|code_rust|code_go|code_ruby|code_ios) _FT_TIP="There's code here — \`/qa\` to see it work, or \`/review\` on your latest diff." ;;
branch_ahead) _FT_TIP="Unshipped work on this branch — \`/review\` then \`/ship\`." ;;
dirty_default) _FT_TIP="Uncommitted changes — \`/review\` before committing." ;;
clean_default) _FT_TIP="Pick one: \`/office-hours\`, \`/qa\`, or \`/review\`." ;;
esac
# Under off the tips are the suggestions the user turned off.
[ "$_PROACTIVE_OFF" = "yes" ] && _FT_TIP=""
if [ -n "$_FT_TIP" ]; then
_emit_block first-run-tip <<EOI
Show this one project-specific line as a heads-up, then CONTINUE with whatever the user actually asked — do NOT halt their task: $_FT_TIP
EOI
"$_BIN/gstack-telemetry-log" --event-type first_task_scaffold_shown --skill "$_FIRST_TASK" --outcome shown 2>/dev/null || true
fi
touch "$_GH/.activated" 2>/dev/null || true
elif [ "$_FIRST_LOOP_SHOWN" = "no" ]; then
if [ "$_PROACTIVE_OFF" = "no" ]; then
_emit_block first-loop-tip <<EOI
Say once as a heads-up (then continue): Tip: gstack pays off when you complete one loop — **plan → review → ship**. A common first loop: \`/office-hours\` to shape it, \`/review\` to check it, then \`/ship\`.
EOI
touch "$_GH/.first-loop-tip-shown" 2>/dev/null || true
fi
fi
# Routing injection (interactive: AUQ + CLAUDE.md append + commit). The body
# is a quoted heredoc (markdown backticks must stay literal), so the resolved
# bin path is substituted via sed on the __BIN__ placeholder. Under off the
# routing rules are the auto-invocation the user turned off, so no offer.
if [ "$_HAS_ROUTING" = "no" ] && [ "$_ROUTING_DECLINED" = "false" ] && [ "$_PROACTIVE_PROMPTED" = "yes" ] && [ "$_PROACTIVE_OFF" = "no" ]; then
sed "s|__BIN__|$_BIN|g" <<'EOI' | _emit_block routing-injection
gstack works best when the project CLAUDE.md includes skill routing rules. If no CLAUDE.md exists in the project root, create it. Use AskUserQuestion:
> gstack works best when your project's CLAUDE.md includes skill routing rules.
Options: A) Add routing rules to CLAUDE.md (recommended) B) No thanks, I'll invoke skills manually
If A: append this section to the end of CLAUDE.md, then commit it (`git add CLAUDE.md && git commit -m "chore: add gstack skill routing rules to CLAUDE.md"`):
## Skill routing
When the user's request matches an available skill, invoke it via the Skill tool. Route only to skills in the session's available-skills list; answer directly for quick questions or small scoped edits.
Key routing rules:
- Product ideas/brainstorming → invoke /office-hours
- Strategy/scope → invoke /plan-ceo-review
- Architecture → invoke /plan-eng-review
- Design system/plan review → invoke /design-consultation or /plan-design-review
- Full review pipeline → invoke /autoplan
- Bugs/errors → invoke /investigate, unless one read-only check confirms the cause and a narrow fix (then fix it and run the focused test)
- QA/testing site behavior → invoke /qa or /qa-only
- Code review/diff check → invoke /review
- Visual polish → invoke /design-review
- Ship/deploy/PR → invoke /ship or /land-and-deploy
- Save progress → invoke /context-save
- Resume context → invoke /context-restore
- Author a backlog-ready spec/issue → invoke /spec
If B: run `__BIN__/gstack-config set routing_declined true` and say they can re-enable with `__BIN__/gstack-config set routing_declined false`. This only happens once per project.
EOI
fi
# Vendoring deprecation (interactive; slug-scoped marker).
if [ "$_VENDORED" = "yes" ] && [ ! -f "$_GH/.vendoring-warned-${SLUG:-unknown}" ]; then
_emit_block vendoring-deprecation <<EOI
This project has gstack vendored in \`.claude/skills/gstack/\`. Vendoring is deprecated. Warn once via AskUserQuestion:
> Migrate to team mode?
Options: A) Yes, migrate to team mode now B) No, I'll handle it myself
If A: 1) \`git rm -r .claude/skills/gstack/\` 2) \`echo '.claude/skills/gstack/' >> .gitignore\` 3) \`$_BIN/gstack-team-init required\` (or \`optional\`) 4) \`git add .claude/ .gitignore CLAUDE.md && git commit -m "chore: migrate gstack from vendored to team mode"\` 5) Tell the user: "Done. Each developer now runs: \`cd ~/.claude/skills/gstack && ./setup --team\`"
If B: say "OK, you're on your own to keep the vendored copy up to date."
Always run (regardless of choice): \`touch "$_GH/.vendoring-warned-${SLUG:-unknown}"\`.
EOI
fi
fi # end interactive-onboarding guard (kind != spawned/unattended)
# Unattended-session rules (plan B1, decision D6; every unattended session gets
# them, like the spawned block). This is the runtime text that says how a
# parent-driven run decides: recommended options are taken and logged, the
# final gate is written and never approved, nothing is published or synced.
# It also carries the host adaptation a harness without a Skill tool, slash
# commands or AskUserQuestion needs, printed here so every host's render has it
# without growing any skill's prose. The record sentence is per skill: only
# skills with steps that write GSTACK_RESULT are told to end with it, and the
# rest name the record the parent reads instead (docs/unattended.md, #3281).
if [ "$_SESSION_KIND" = "unattended" ]; then
_UA_NONE="This skill writes no run directory and prints no GSTACK_RESULT line, so do not invent either; end at its first pending item and list that item, with every recommended option you took, in your final report."
case "$SKILL_NAME" in
autoplan) _UA_RECORD="This skill writes a run directory through gstack-autoplan (plan.md, review-record.md, tasks.jsonl, decisions.jsonl, findings.jsonl, timing.json, run.json, gate.json): append each recommended choice to decisions.jsonl with kind \"auto\" and each pending one with kind \"approval\" and status \"pending\". The final approval gate is written as a gate list (gstack-gate render) and this run ENDS there with \`GSTACK_RESULT: skill=autoplan status=gate_pending run=<dir>\`." ;;
eval-plan) _UA_RECORD="This run ENDS at the Step 4 spend approval, left pending, with \`GSTACK_RESULT: skill=eval-plan status=gate_pending run=<outdir>\`, where <outdir> is the pilot's --out directory. No helper writes a gate.json for this skill yet, so the parent reads the pilot report and spend ledger in <outdir>." ;;
ship) _UA_RECORD="This skill ends with \`gstack-ship-receipt result\` (Step 22), which writes <state root>/ship/runs/<utc>-<head12>/ship-run.json (a /ship record, not a run manifest) and prints \`GSTACK_RESULT: skill=ship status=complete run=<dir>\`; a run that stops earlier prints \`GSTACK_RESULT: skill=ship status=refused run=-\` itself. The one publication allowed here: when an open PR for this branch exists and HEAD is its pushed head, update that PR's body and title with the receipt through the pr-body section's existing-PR path (never pr-create, never a push, and never \`gh pr ready\`: the draft-state items there concern an early PR this run never opened); otherwise the handoff section writes the receipt to .gstack/tmp/ship-receipt.md and the parent reads it there." ;;
review) _UA_RECORD="$_UA_NONE The parent reads the review-log rows (\`gstack-review-read\`)." ;;
qa) _UA_RECORD="$_UA_NONE The parent reads the \`qa-report-*.md\` file." ;;
*) _UA_RECORD="$_UA_NONE The parent reads this skill's own record (docs/unattended.md)." ;;
esac
_emit_block unattended-session <<EOI
You are running unattended: a parent agent started this run and reads its record, not your prose (docs/unattended.md names each skill's record). Rules: do NOT call AskUserQuestion and do NOT render prose decision briefs. At every question take the option marked (recommended). A question with no recommendation, any consent, any destructive or irreversible option, and the final approval gate stay pending: never choose them. You never approve a gate, never mark a plan APPROVED, never publish, push, sync or send data off this machine, and never record a consent; the only exception is the one named in your skill's record rule below. $_UA_RECORD Skip every onboarding, upgrade, telemetry, routing and lake instruction. Host adaptation: there may be no Skill tool, no slash commands and no hooks here; read the skill file with your file-reading tool, run its bash blocks as written, treat each bash block's printed STATUS lines as the only source of session facts, and write results to files the parent names rather than relying on chat text being read.
EOI
fi
# Capy asks (capy/skill/gstack/captain.md): who to ask and in what shape when
# gstack runs under Capy. Printed for every session kind, after the unattended
# block, so the pending gate items that block writes reach a person through
# the right channel. Generic policy only: a Captain's own standing approvals
# live in its rules, never here.
if [ "$_CAPY" = "on" ] && [ "${GSTACK_CAPY_ASKS:-}" != "0" ]; then
_emit_block capy-asks <<EOI
You run under Capy. Every decision this workflow cannot take itself (a pending gate item, a consent, an unrecommended question, a plan approval) goes through Capy's messaging, never as a bare question or gate codes: in a crew thread, a needs-you report to your Captain; with no Captain, a Capy question to the person. Write it in plain language: what it is, why it matters, what each answer does and costs, your pick, and the one-word reply. A plan approval is rendered with \`gstack-owner-brief render --captain --out <run dir>\` (before -> after, why it matters, what caused this work, big decisions, what we need) and relayed whole; fix the plan first if it exits CAPTAIN_BRIEF_INCOMPLETE. Record every answer with the person's exact words: \`gstack-approvals add\` (or \`gstack-approvals import --autoplan <run dir>\` after an autoplan answer). Cite standing approvals your Captain lists instead of asking again; always ask fresh for a product or behaviour decision, spend over a stated cap, anything published outside the repository, a threshold, budget or trial-count change, closing someone's contribution without landing it, and anything destructive. A pull request opened by /ship follows its Capy section (What changed with before/after images, Why, Approvals). The launch environment reaches a command, your own or a child's, through \`. <the GSTACK_LAUNCH_FILE the installer printed>\` in the shell that runs it; never \`export \$(...)\`, \`env\`, \`printenv\` or a bare \`set\` in a tool fence: a bare \`export\` prints every variable, credentials included. Guide: capy/skill/gstack/captain.md in the gstack checkout.
EOI
fi
# Spawned-session rules (NOT one-time — every spawned session gets the full
# 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, 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, and never grant a consent or choose an option that publishes or syncs data off this machine — take the conservative non-destructive (local) 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
# Privacy stop-gate (Phase 2, user-approved Q2: consent question surfaces only
# when consent is actually pending; still fired through AskUserQuestion).
# Interactive sessions ONLY: this block is emitted AFTER the spawned-session
# block, so its "skip instruction blocks above" rule does not cover it — a
# spawned session's auto-choose would accept data-sync consent no human gave.
# Deferral is safe (EOV8): the config key stays unset, so the gate fires on
# the next interactive run. Same reasoning suppresses it in headless runs.
_ARTIFACTS_PROMPTED=$("$_BRAIN_CONFIG_BIN" get artifacts_sync_mode_prompted 2>/dev/null || echo "false")
if [ "$_SESSION_KIND" = "interactive" ] && [ "$_BRAIN_SYNC_MODE" = "off" ] && [ "$_ARTIFACTS_PROMPTED" != "true" ] && command -v gbrain >/dev/null 2>&1; then
_emit_block privacy-stop-gate <<EOI
Privacy stop-gate — ask once via AskUserQuestion:
> gstack can publish your artifacts (CEO plans, designs, reports) to a private GitHub repo that GBrain indexes across machines. How much should sync?
Options: A) Everything allowlisted (recommended) B) Only artifacts C) Decline, keep everything local
After answer run: \`$_BIN/gstack-config set artifacts_sync_mode <full|artifacts-only|off>\` and \`$_BIN/gstack-config set artifacts_sync_mode_prompted true\`. If A/B and \`~/.gstack/.git\` is missing, ask whether to run \`gstack-artifacts-init\`. Do not block the skill.
EOI
fi
# BRAIN_HEALTH block: only for hosts whose render passes --brain-health
# (gbrain/hermes) — gen-time host conditional preserved as a flag.
if [ "$BRAIN_HEALTH" = "yes" ] && command -v gbrain >/dev/null 2>&1; then
_BRAIN_JSON=$(gbrain doctor --fast --json 2>/dev/null || echo '{}')
_BRAIN_SCORE=$(echo "$_BRAIN_JSON" | grep -o '"health_score":[0-9]*' | cut -d: -f2)
_BRAIN_FAILS=$(echo "$_BRAIN_JSON" | grep -o '"status":"fail"' | wc -l | tr -d ' ')
_BRAIN_WARNS=$(echo "$_BRAIN_JSON" | grep -o '"status":"warn"' | wc -l | tr -d ' ')
echo "BRAIN_HEALTH: ${_BRAIN_SCORE:-unknown} (${_BRAIN_FAILS:-0} failures, ${_BRAIN_WARNS:-0} warnings)"
if [ "${_BRAIN_SCORE:-100}" -lt 50 ] 2>/dev/null; then
echo "$_BRAIN_JSON" | grep -o '"name":"[^"]*","status":"[^"]*","message":"[^"]*"' | _sanitize || true
fi
fi