fix(e2e): #1644 Part A — peer-visibility scripts consume inline auth_token #1680

Merged
hongming merged 2 commits from fix/1644-peer-visibility-inline-auth-token into main 2026-05-23 19:52:06 +00:00
2 changed files with 38 additions and 51 deletions
+32 -20
View File
@@ -24,14 +24,12 @@
#
# Only PROVISIONING differs from staging:
# - staging: POST /cp/admin/orgs (cold EC2 tenant) + per-tenant admin
# token + each workspace's MCP bearer from create response or an admin
# token-mint fallback.
# token + each workspace's MCP bearer from the POST /workspaces
# create response.
# - local: POST /workspaces directly against the local stack
# (BASE, default http://localhost:8080), MCP bearer minted via
# GET /admin/workspaces/:id/test-token (e2e_mint_test_token —
# deterministic, gated by MOLECULE_ENV != production). Same model
# every other local E2E (test_priority_runtimes_e2e.sh,
# test_api.sh) already uses; no new credential/provision flow.
# (BASE, default http://localhost:8080), MCP bearer consumed inline
# from the create response (auth_token field). Same model every
# other local E2E uses; no new credential/provision flow.
#
# By default the local backend creates external-mode workspace rows and
# drives the literal MCP path directly. That keeps the local peer-visibility
@@ -81,6 +79,17 @@ NAME_PREFIX="PV-Local-$$-$(date +%H%M%S)"
log() { echo "[$(date +%H:%M:%S)] $*"; }
ok() { echo "[$(date +%H:%M:%S)] ✅ $*"; }
extract_auth_token() {
python3 -c "
import sys, json
try:
d = json.load(sys.stdin)
except Exception:
print(''); sys.exit(0)
print(d.get('auth_token') or d.get('connection', {}).get('auth_token') or '')
" 2>/dev/null
}
CREATED_WSIDS=()
ADMIN_BEARER="${MOLECULE_ADMIN_TOKEN:-${ADMIN_TOKEN:-}}"
ADMIN_AUTH=()
@@ -131,17 +140,6 @@ if ! curl -fsS "$BASE/health" -m 5 >/dev/null 2>&1; then
echo "::error::Local stack not healthy at $BASE/health — bring it up (make up) before this gate. Infra, not a workspace bug (feedback_fix_root_not_symptom)." >&2
exit 1
fi
# admin/test-token is the local MCP-bearer mint path; it 404s in
# production. If it is off, this gate cannot drive the literal call.
if ! curl -fsS "$BASE/admin/workspaces/preflight-probe/test-token" ${ADMIN_AUTH[@]+"${ADMIN_AUTH[@]}"} -m 5 >/dev/null 2>&1; then
# A 404 here is EITHER "no such ws" (fine — endpoint is enabled) OR the
# endpoint is disabled (MOLECULE_ENV=production). Distinguish by body.
PROBE=$(curl -s "$BASE/admin/workspaces/preflight-probe/test-token" ${ADMIN_AUTH[@]+"${ADMIN_AUTH[@]}"} -m 5 2>/dev/null)
if echo "$PROBE" | grep -qi 'production\|disabled\|not found.*endpoint'; then
echo "::error::GET /admin/workspaces/:id/test-token disabled (MOLECULE_ENV=production?). Cannot mint a local MCP bearer." >&2
exit 1
fi
fi
ok " local stack healthy"
# ─── Resolve per-runtime provisioning secrets ──────────────────────────
@@ -244,6 +242,12 @@ log "1/5 provisioning parent ($PARENT_RUNTIME, mode=$PV_LOCAL_PROVISION_MODE) +
P_RESP=$(curl -s -X POST "$BASE/workspaces" ${ADMIN_AUTH[@]+"${ADMIN_AUTH[@]}"} -H "Content-Type: application/json" \
-d "{\"name\":\"${NAME_PREFIX}-parent\",\"runtime\":\"$PARENT_RUNTIME\",\"tier\":3$PARENT_EXTRA,\"secrets\":$PARENT_SECRETS}")
PARENT_ID=$(echo "$P_RESP" | python3 -c 'import json,sys;print(json.load(sys.stdin).get("id",""))' 2>/dev/null)
# PARENT_TOKEN captured for symmetry with the per-sibling auth-token
# capture in the runtime loop below + reserved for follow-up steps
# that need parent-side auth. Current downstream steps reach the parent
# via admin token, so the variable isn't dereferenced — SC2034.
# shellcheck disable=SC2034 # captured for downstream parent-auth use; see #1644 follow-up
PARENT_TOKEN=$(echo "$P_RESP" | extract_auth_token)
if [ -z "$PARENT_ID" ]; then
echo "::error::parent create failed: $(echo "$P_RESP" | head -c 300)" >&2
exit 1
@@ -259,6 +263,8 @@ log " PARENT_ID=$PARENT_ID runtime=$PARENT_RUNTIME"
WS_IDS_MAP=""
# shellcheck disable=SC2034 # map values are updated through portable eval-based helpers.
VERDICT_MAP=""
# shellcheck disable=SC2034 # map values are updated through portable eval-based helpers.
WS_TOKENS_MAP=""
_map_set() { # _map_set <mapvarname> <key> <value>
local __m="$1" __k="$2" __v="$3" __cur
eval "__cur=\$$__m"
@@ -294,11 +300,17 @@ for rt in $PV_RUNTIMES; do
R=$(curl -s -X POST "$BASE/workspaces" ${ADMIN_AUTH[@]+"${ADMIN_AUTH[@]}"} -H "Content-Type: application/json" \
-d "{\"name\":\"${NAME_PREFIX}-$rt\",\"runtime\":\"$CREATE_RUNTIME\",\"tier\":2,\"parent_id\":\"$PARENT_ID\"$CREATE_EXTRA,\"secrets\":$SEC}")
WID=$(echo "$R" | python3 -c 'import json,sys;print(json.load(sys.stdin).get("id",""))' 2>/dev/null)
WTOK=$(echo "$R" | extract_auth_token)
if [ -z "$WID" ]; then
echo "::error::$rt workspace create failed: $(echo "$R" | head -c 300)" >&2
exit 1
fi
if [ -z "$WTOK" ]; then
echo "::error::$rt workspace create did not return an auth_token — cannot drive the literal MCP call" >&2
exit 1
fi
_map_set WS_IDS_MAP "$rt" "$WID"
_map_set WS_TOKENS_MAP "$rt" "$WTOK"
CREATED_WSIDS+=("$WID")
ALL_WS_IDS="$ALL_WS_IDS $WID"
ACTIVE_RUNTIMES="$ACTIVE_RUNTIMES $rt"
@@ -356,10 +368,10 @@ log "4/5 driving the LITERAL list_peers MCP call per online runtime..."
echo ""
for rt in $ONLINE_RUNTIMES; do
wid="$(_map_get WS_IDS_MAP "$rt")"
WTOK=$(e2e_mint_test_token "$wid" 2>/dev/null || true)
WTOK="$(_map_get WS_TOKENS_MAP "$rt")"
if [ -z "$WTOK" ]; then
echo "--- $rt (ws=$wid) ---"
echo "$rt: could not mint a local MCP bearer (admin/test-token) — cannot drive the literal call"
echo "$rt: workspace create did not return an auth_token — cannot drive the literal call"
_map_set VERDICT_MAP "$rt" "FAIL(no-bearer)"
REGRESSED=1
echo ""
+6 -31
View File
@@ -40,10 +40,10 @@
# drives: POST /cp/admin/orgs (provision), GET
# /cp/admin/orgs/:slug/admin-token (per-tenant token), DELETE
# /cp/admin/tenants/:slug (teardown). The per-tenant admin token drives
# tenant workspace creation; each workspace's OWN auth_token drives its
# MCP call. External-like runtimes may return the token in POST
# /workspaces; managed container runtimes usually require the admin token
# mint fallback below.
# tenant workspace creation; each workspace's OWN auth_token is consumed
# inline from the POST /workspaces 201 response to drive its MCP call.
# No dev-only admin token-mint routes are used in this E2E
# (feedback_no_dev_only_routes_in_e2e).
#
# Required env:
# MOLECULE_ADMIN_TOKEN CP admin bearer — Railway staging CP_ADMIN_API_TOKEN
@@ -265,44 +265,19 @@ log " PARENT_ID=$PARENT_ID"
# WS_IDS[runtime]=id ; WS_TOKENS[runtime]=auth_token (the MCP bearer)
declare -A WS_IDS WS_TOKENS
ALL_WS_IDS="$PARENT_ID"
TOKEN_ERRORS=0
TOKEN_ERROR_SUMMARY=""
for rt in $PV_RUNTIMES; do
R=$(tenant_call POST /workspaces \
-d "{\"name\":\"pv-$rt\",\"runtime\":\"$rt\",\"tier\":2,\"parent_id\":\"$PARENT_ID\",\"secrets\":$SECRETS_JSON}")
WID=$(echo "$R" | python3 -c "import sys,json; print(json.load(sys.stdin).get('id',''))" 2>/dev/null)
# External-like runtimes may return connection.auth_token on create.
# Managed container runtimes usually return only id/status here, then
# receive their bearer through registry/bootstrap; for this literal MCP
# driver we mint through the production-safe admin token route below.
WTOK=$(echo "$R" | extract_auth_token)
[ -n "$WID" ] || fail "$rt workspace create failed: $(echo "$R" | head -c 300)"
TOKEN_DIAG=""
if [ -z "$WTOK" ]; then
TTOK_FILE=$(mktemp)
TTOK_CODE=$(tenant_call_capture POST "/admin/workspaces/$WID/tokens" "$TTOK_FILE" 2>/dev/null || echo "curl_error")
TTOK_RESP=$(cat "$TTOK_FILE" 2>/dev/null || true)
WTOK=$(echo "$TTOK_RESP" | extract_auth_token)
TOKEN_DIAG="POST /admin/workspaces/$WID/tokens -> HTTP $TTOK_CODE body: $(echo "$TTOK_RESP" | redact_token_body)"
rm -f "$TTOK_FILE"
fi
[ -n "$WID" ] || fail "$rt workspace create failed: $(echo \"$R\" | head -c 300)"
[ -n "$WTOK" ] || fail "$rt workspace create did not return an auth_token — cannot drive its MCP call (workspace_id=$WID; create_resp: $(echo \"$R\" | redact_token_body))"
WS_IDS[$rt]="$WID"
if [ -z "$WTOK" ]; then
TOKEN_ERRORS=$((TOKEN_ERRORS + 1))
TOKEN_ERROR_SUMMARY="${TOKEN_ERROR_SUMMARY}
[$rt] workspace did not return or mint an auth_token — cannot drive its MCP call (workspace_id=$WID; create_resp: $(echo "$R" | redact_token_body); token_fallbacks: $TOKEN_DIAG)"
log " $rt$WID (token acquisition failed; continuing to classify other runtimes)"
continue
fi
WS_TOKENS[$rt]="$WTOK"
ALL_WS_IDS="$ALL_WS_IDS $WID"
log " $rt$WID"
done
if [ "$TOKEN_ERRORS" -gt 0 ]; then
fail "token acquisition failed for $TOKEN_ERRORS runtime(s):$TOKEN_ERROR_SUMMARY"
fi
if [ "${PV_TOKEN_DIAGNOSTIC_ONLY:-0}" = "1" ]; then
ok "token diagnostic passed for runtimes: $PV_RUNTIMES"
exit 0