framework: make tool discoverability, workspace placement and model tiering mechanical #1174

Merged
Mos merged 24 commits from feat/workspace-hygiene-tool-enforcement into main 2026-08-13 14:21:23 +00:00
3 changed files with 83 additions and 1 deletions
Showing only changes of commit 96609bdade - Show all commits
+5
View File
@@ -56,6 +56,11 @@ steps:
# and sandboxes a throwaway git repo, so it resolves no real credentials and
# joins CI directly rather than the exclusions file.
- bash packages/mosaic/framework/tools/git/test-issue-close-fail-closed.sh
# Hermetic behavioural regression for the PreToolUse wrapper guard: proves
# it still blocks the three mistakes AND still lets reads, unwrapped
# endpoints and ordinary commands through. Both directions are asserted —
# a guard that over-blocks gets routed around, which fails just as hard.
- bash packages/mosaic/framework/tools/git/test-wrapper-guard.sh
# Blocking gate (#791): a framework upgrade must never write or delete an
# operator-owned path. The HARD GATE proves an unanticipated operator sentinel
+70
View File
@@ -0,0 +1,70 @@
#!/usr/bin/env bash
# test-wrapper-guard.sh — hermetic behavioural regression for wrapper-guard.sh.
#
# Resolves no credentials, touches no network, and creates no repository: the
# guard reads a hook payload on stdin and answers with an exit code, so the whole
# contract is testable from fixtures.
#
# The fixtures are written to a temp file rather than passed inline, and this is
# not stylistic. The guard inspects the literal text of the Bash command it is
# handed. A test that embeds `git clone ... $HOME` inside its own command line
# trips the guard on the harness instead of on the fixture — which is exactly
# what happened the first time this was checked by hand. Substring matching over
# whole command text is the guard's deliberate fail-closed posture; a test that
# does not account for it silently measures the wrong thing.
#
# Exit: 0 = every fixture behaved as specified · 1 = at least one did not
set -uo pipefail
HERE="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
GUARD="${1:-$HERE/wrapper-guard.sh}"
[ -x "$GUARD" ] || { printf 'test-wrapper-guard: not executable: %s\n' "$GUARD" >&2; exit 2; }
TMP="$(mktemp -d)"; trap 'rm -rf "$TMP"' EXIT
FIXTURES="$TMP/fixtures.tsv"
# Each line: <expected-exit> TAB <hook payload> TAB <what it proves>
# 0 = allowed, 2 = blocked.
{
printf '2\t{"tool_input":{"command":"git clone https://example.invalid/x ~/wt"}}\tcheckout into $HOME is refused\n'
printf '2\t{"tool_input":{"command":"git worktree add ~/wt topic"}}\tworktree into $HOME is refused\n'
printf '0\t{"tool_input":{"command":"git clone https://example.invalid/x /src/wt"}}\tcheckout onto a work filesystem is fine\n'
printf '0\t{"tool_input":{"command":"curl -s -X GET https://git.example.invalid/api/v1/repos/a/b/pulls/1"}}\treads are never blocked\n'
printf '2\t{"tool_input":{"command":"curl -X POST -d @b https://git.example.invalid/api/v1/repos/a/b/pulls/1/reviews"}}\treview write has a wrapper\n'
printf '2\t{"tool_input":{"command":"curl -X POST -d @b https://git.example.invalid/api/v1/repos/a/b/pulls/1/merge"}}\tmerge write has a wrapper\n'
printf '2\t{"tool_input":{"command":"curl -X POST -d @b https://api.github.com/repos/a/b/issues"}}\tGitHub host is covered too\n'
printf '0\t{"tool_input":{"command":"curl -X POST -d @b https://git.example.invalid/api/v1/repos/a/b/releases"}}\tan endpoint with no wrapper passes\n'
printf '2\t{"tool_input":{"command":"curl -X POST -d {\\"event\\":\\"APPROVE\\"} https://example.invalid/x"}}\tthe APPROVE token is caught anywhere\n'
printf '0\t{"tool_input":{"command":"ls -la /src"}}\tordinary commands are untouched\n'
printf '0\t{"tool_input":{"command":"MOSAIC_WRAPPER_OVERRIDE=1 curl -X POST -d @b https://git.example.invalid/api/v1/repos/a/b/pulls"}}\tbreak-glass works\n'
printf '0\t{"tool_input":{}}\tan empty payload does not block the session\n'
} > "$FIXTURES"
fail=0 n=0
while IFS=$'\t' read -r want payload why; do
[ -n "${want:-}" ] || continue
n=$((n + 1))
printf '%s' "$payload" | "$GUARD" >/dev/null 2>&1
got=$?
if [ "$got" = "$want" ]; then
printf 'ok %s\n' "$why"
else
printf 'FAIL %s (want exit %s, got %s)\n' "$why" "$want" "$got"
fail=1
fi
done < "$FIXTURES"
printf '\n'
if [ "$fail" -eq 0 ]; then
printf 'wrapper-guard: %d/%d fixtures behaved as specified.\n' "$n" "$n"
else
cat <<'EOF'
wrapper-guard drifted from its contract.
A guard that blocks too much gets routed around, and a guard that blocks too
little is decoration. Both directions are failures here, which is why the
allowed cases are asserted as hard as the blocked ones.
EOF
fi
exit "$fail"
@@ -39,7 +39,14 @@ CMD="$(printf '%s' "$INPUT" | jq -r '.tool_input.command // empty' 2>/dev/null |
case "$CMD" in *MOSAIC_WRAPPER_OVERRIDE=1*) exit 0 ;; esac
[ "${MOSAIC_WRAPPER_OVERRIDE:-0}" = "1" ] && exit 0
W="$HOME/.config/mosaic/tools/git"
# The wrappers this guard points at are its own siblings. Resolving relative to
# this file — rather than to a hardcoded $HOME/.config/mosaic — means the guard
# names the wrappers from the same install it was launched from, and that it
# still works from a repo checkout with no installed mosaic home (which is how it
# is exercised in CI). $HOME remains the fallback for a guard invoked by an
# absolute path from somewhere unusual.
W="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
[ -x "$W/pr-review.sh" ] || W="$HOME/.config/mosaic/tools/git"
# ---- 1. checkout into $HOME ------------------------------------------------
if printf '%s' "$CMD" | grep -Eq 'git[^|;&]*(clone|worktree[[:space:]]+add)'; then