Merge pull request 'ci(audit-force-merge): fan §SOP-6 force-merge audit to molecule-core' (#150) from fan/audit-force-merge into main

molecule-core/main branch protection requires the status-check context
'Secret scan / Scan diff for credential-shaped strings (pull_request)'
but the workflow lived only in .github/workflows/, which Gitea Actions
doesn't see — every PR's required-status-checks rollup left the context
in 'expected' / never-fires state, blocking merge.

Port to .gitea/workflows/secret-scan.yml. Drops:
  - merge_group event (Gitea has no merge queue)
  - workflow_call (no cross-repo reusable invocation on Gitea)
SELF exclude lists both .github/ and .gitea/ paths so a future sync
between them stays clean. Job + step names match the GitHub workflow
so the produced status-check context name matches branch protection
unchanged.

Same regex set as the runtime's pre-commit hook
(molecule-ai-workspace-runtime: molecule_runtime/scripts/pre-commit-checks.sh).

This unblocks PR #150 (audit-force-merge fan-out) and every future
PR on molecule-core/main.

.gitea/scripts/audit-force-merge.sh

@@ -0,0 +1,118 @@
+#!/usr/bin/env bash
+# audit-force-merge — detect a §SOP-6 force-merge after PR close, emit
+# `incident.force_merge` to stdout as structured JSON.
+#
+# Vector's docker_logs source picks up runner stdout; the JSON gets
+# shipped to Loki on molecule-canonical-obs, indexable by event_type.
+# Query example:
+#
+#   {host="operator"} |= "event_type" |= "incident.force_merge" | json
+#
+# A force-merge is detected when a PR closed-with-merged=true had at
+# least one of the repo's required-status-check contexts in a state
+# other than "success" at the merge commit's SHA. That's exactly what
+# the Gitea force_merge:true API call lets through, so it's a faithful
+# detector of the override path.
+#
+# Triggers on `pull_request_target: closed` (loaded from base branch
+# per §SOP-6 security model). No-op when merged=false.
+#
+# Required env (set by the workflow):
+#   GITEA_TOKEN, GITEA_HOST, REPO, PR_NUMBER, REQUIRED_CHECKS
+#
+# REQUIRED_CHECKS is a newline-separated list of status-check context
+# names that branch protection requires. Declared in the workflow YAML
+# rather than fetched from /branch_protections (which needs admin
+# scope — sop-tier-bot has read-only). Trade dynamism for simplicity:
+# when the required-check set changes, update both branch protection
+# AND this env. Keeping them in sync is less complexity than granting
+# the audit bot admin perms on every repo.
+
+set -euo pipefail
+
+: "${GITEA_TOKEN:?required}"
+: "${GITEA_HOST:?required}"
+: "${REPO:?required}"
+: "${PR_NUMBER:?required}"
+: "${REQUIRED_CHECKS:?required (newline-separated context names)}"
+
+OWNER="${REPO%%/*}"
+NAME="${REPO##*/}"
+API="https://${GITEA_HOST}/api/v1"
+AUTH="Authorization: token ${GITEA_TOKEN}"
+
+# 1. Fetch the PR. If not merged, no-op.
+PR=$(curl -sS -H "$AUTH" "${API}/repos/${OWNER}/${NAME}/pulls/${PR_NUMBER}")
+MERGED=$(echo "$PR" | jq -r '.merged // false')
+if [ "$MERGED" != "true" ]; then
+  echo "::notice::PR #${PR_NUMBER} closed without merge — no audit emission."
+  exit 0
+fi
+
+MERGE_SHA=$(echo "$PR" | jq -r '.merge_commit_sha // empty')
+MERGED_BY=$(echo "$PR" | jq -r '.merged_by.login // "unknown"')
+TITLE=$(echo "$PR" | jq -r '.title // ""')
+BASE_BRANCH=$(echo "$PR" | jq -r '.base.ref // "main"')
+HEAD_SHA=$(echo "$PR" | jq -r '.head.sha // empty')
+
+if [ -z "$MERGE_SHA" ]; then
+  echo "::warning::PR #${PR_NUMBER} merged=true but no merge_commit_sha — cannot evaluate force-merge."
+  exit 0
+fi
+
+# 2. Required status checks declared in the workflow env.
+REQUIRED="$REQUIRED_CHECKS"
+if [ -z "${REQUIRED//[[:space:]]/}" ]; then
+  echo "::notice::REQUIRED_CHECKS empty — force-merge not applicable."
+  exit 0
+fi
+
+# 3. Status-check state at the PR HEAD (where checks ran). The merge
+#    commit doesn't get its own checks; we evaluate the PR's last
+#    commit, which is what branch protection compared against.
+STATUS=$(curl -sS -H "$AUTH" \
+  "${API}/repos/${OWNER}/${NAME}/commits/${HEAD_SHA}/status")
+declare -A CHECK_STATE
+while IFS=$'\t' read -r ctx state; do
+  [ -n "$ctx" ] && CHECK_STATE[$ctx]="$state"
+done < <(echo "$STATUS" | jq -r '.statuses // [] | .[] | "\(.context)\t\(.status)"')
+
+# 4. For each required check, was it green at merge? YAML block scalars
+#    (`|`) leave a trailing newline; skip blank/whitespace-only lines.
+FAILED_CHECKS=()
+while IFS= read -r req; do
+  trimmed="${req#"${req%%[![:space:]]*}"}"   # ltrim
+  trimmed="${trimmed%"${trimmed##*[![:space:]]}"}"  # rtrim
+  [ -z "$trimmed" ] && continue
+  state="${CHECK_STATE[$trimmed]:-missing}"
+  if [ "$state" != "success" ]; then
+    FAILED_CHECKS+=("${trimmed}=${state}")
+  fi
+done <<< "$REQUIRED"
+
+if [ "${#FAILED_CHECKS[@]}" -eq 0 ]; then
+  echo "::notice::PR #${PR_NUMBER} merged with all required checks green — not a force-merge."
+  exit 0
+fi
+
+# 5. Emit structured audit event.
+NOW=$(date -u +%Y-%m-%dT%H:%M:%SZ)
+FAILED_JSON=$(printf '%s\n' "${FAILED_CHECKS[@]}" | jq -R . | jq -s .)
+
+# Print as a single-line JSON so Vector's parse_json transform can pick
+# it up cleanly from docker_logs.
+jq -nc \
+  --arg event_type "incident.force_merge" \
+  --arg ts "$NOW" \
+  --arg repo "$REPO" \
+  --argjson pr "$PR_NUMBER" \
+  --arg title "$TITLE" \
+  --arg base "$BASE_BRANCH" \
+  --arg merged_by "$MERGED_BY" \
+  --arg merge_sha "$MERGE_SHA" \
+  --argjson failed_checks "$FAILED_JSON" \
+  '{event_type: $event_type, ts: $ts, repo: $repo, pr: $pr, title: $title,
+    base_branch: $base, merged_by: $merged_by, merge_sha: $merge_sha,
+    failed_checks: $failed_checks}'
+
+echo "::warning::FORCE-MERGE detected on PR #${PR_NUMBER} by ${MERGED_BY}: ${#FAILED_CHECKS[@]} required check(s) not green at merge time."

.gitea/scripts/sop-tier-check.sh

@@ -0,0 +1,149 @@
+#!/usr/bin/env bash
+# sop-tier-check — verify a Gitea PR satisfies the §SOP-6 approval gate.
+#
+# Reads the PR's tier label, walks approving reviewers, and checks each
+# approver's Gitea team membership against the tier's eligible-team set.
+# Marks pass only when at least one non-author approver is in an eligible
+# team.
+#
+# Invoked from `.gitea/workflows/sop-tier-check.yml`. The workflow sets
+# the env vars below; this script does no IO outside of stdout/stderr +
+# the Gitea API.
+#
+# Required env:
+#   GITEA_TOKEN   — bot PAT with read:organization,read:user,
+#                   read:issue,read:repository scopes
+#   GITEA_HOST    — e.g. git.moleculesai.app
+#   REPO          — owner/name (from github.repository)
+#   PR_NUMBER     — int (from github.event.pull_request.number)
+#   PR_AUTHOR     — login (from github.event.pull_request.user.login)
+#
+# Optional:
+#   SOP_DEBUG=1   — print per-API-call diagnostic lines (HTTP codes,
+#                   raw response bodies). Default: off.
+#
+# Stale-status caveat: Gitea Actions does not always re-fire workflows
+# on `labeled` / `pull_request_review:submitted` events. If the
+# sop-tier-check status is stale (e.g. red after labels/approvals were
+# added), push an empty commit to the PR branch to force a synchronize
+# event, OR re-request reviews. Tracked: internal#46.
+
+set -euo pipefail
+
+debug() {
+  if [ "${SOP_DEBUG:-}" = "1" ]; then
+    echo "  [debug] $*" >&2
+  fi
+}
+
+# Validate env
+: "${GITEA_TOKEN:?GITEA_TOKEN required}"
+: "${GITEA_HOST:?GITEA_HOST required}"
+: "${REPO:?REPO required (owner/name)}"
+: "${PR_NUMBER:?PR_NUMBER required}"
+: "${PR_AUTHOR:?PR_AUTHOR required}"
+
+OWNER="${REPO%%/*}"
+NAME="${REPO##*/}"
+API="https://${GITEA_HOST}/api/v1"
+AUTH="Authorization: token ${GITEA_TOKEN}"
+echo "::notice::tier-check start: repo=$OWNER/$NAME pr=$PR_NUMBER author=$PR_AUTHOR"
+
+# Sanity: token resolves to a user
+WHOAMI=$(curl -sS -H "$AUTH" "${API}/user" | jq -r '.login // ""')
+if [ -z "$WHOAMI" ]; then
+  echo "::error::GITEA_TOKEN cannot resolve a user via /api/v1/user — check the token scope and that the secret is wired correctly."
+  exit 1
+fi
+echo "::notice::token resolves to user: $WHOAMI"
+
+# 1. Read tier label
+LABELS=$(curl -sS -H "$AUTH" "${API}/repos/${OWNER}/${NAME}/issues/${PR_NUMBER}/labels" | jq -r '.[].name')
+TIER=""
+for L in $LABELS; do
+  case "$L" in
+    tier:low|tier:medium|tier:high)
+      if [ -n "$TIER" ]; then
+        echo "::error::Multiple tier labels: $TIER + $L. Apply exactly one."
+        exit 1
+      fi
+      TIER="$L"
+    ;;
+  esac
+done
+if [ -z "$TIER" ]; then
+  echo "::error::PR has no tier:low|tier:medium|tier:high label. Apply one before merge."
+  exit 1
+fi
+debug "tier=$TIER"
+
+# 2. Tier → eligible teams
+case "$TIER" in
+  tier:low)    ELIGIBLE="engineers managers ceo" ;;
+  tier:medium) ELIGIBLE="managers ceo" ;;
+  tier:high)   ELIGIBLE="ceo" ;;
+esac
+debug "eligible_teams=$ELIGIBLE"
+
+# Resolve team-name → team-id once. /orgs/{org}/teams/{slug}/... endpoints
+# don't exist on Gitea 1.22; we have to use /teams/{id}.
+ORG_TEAMS_FILE=$(mktemp)
+trap 'rm -f "$ORG_TEAMS_FILE"' EXIT
+HTTP_CODE=$(curl -sS -o "$ORG_TEAMS_FILE" -w '%{http_code}' -H "$AUTH" \
+  "${API}/orgs/${OWNER}/teams")
+debug "teams-list HTTP=$HTTP_CODE size=$(wc -c <"$ORG_TEAMS_FILE")"
+if [ "${SOP_DEBUG:-}" = "1" ]; then
+  echo "  [debug] teams-list body (first 300 chars):" >&2
+  head -c 300 "$ORG_TEAMS_FILE" >&2; echo >&2
+fi
+if [ "$HTTP_CODE" != "200" ]; then
+  echo "::error::GET /orgs/${OWNER}/teams returned HTTP $HTTP_CODE — token likely lacks read:org scope. Add a SOP_TIER_CHECK_TOKEN secret with read:organization scope at the org level."
+  exit 1
+fi
+declare -A TEAM_ID
+for T in $ELIGIBLE; do
+  ID=$(jq -r --arg t "$T" '.[] | select(.name==$t) | .id' <"$ORG_TEAMS_FILE" | head -1)
+  if [ -z "$ID" ] || [ "$ID" = "null" ]; then
+    VISIBLE=$(jq -r '.[]?.name? // empty' <"$ORG_TEAMS_FILE" 2>/dev/null | tr '\n' ' ')
+    echo "::error::Team \"$T\" not found in org $OWNER. Teams visible: $VISIBLE"
+    exit 1
+  fi
+  TEAM_ID[$T]="$ID"
+  debug "team-id: $T → $ID"
+done
+
+# 3. Read approving reviewers
+REVIEWS=$(curl -sS -H "$AUTH" "${API}/repos/${OWNER}/${NAME}/pulls/${PR_NUMBER}/reviews")
+APPROVERS=$(echo "$REVIEWS" | jq -r '[.[] | select(.state=="APPROVED") | .user.login] | unique | .[]')
+if [ -z "$APPROVERS" ]; then
+  echo "::error::No approving reviews. Tier $TIER requires approval from {$ELIGIBLE} (non-author)."
+  exit 1
+fi
+debug "approvers: $(echo "$APPROVERS" | tr '\n' ' ')"
+
+# 4. For each approver: check non-author + team membership (by id)
+OK=""
+for U in $APPROVERS; do
+  if [ "$U" = "$PR_AUTHOR" ]; then
+    debug "skip self-review by $U"
+    continue
+  fi
+  for T in $ELIGIBLE; do
+    ID="${TEAM_ID[$T]}"
+    CODE=$(curl -sS -o /dev/null -w '%{http_code}' -H "$AUTH" \
+      "${API}/teams/${ID}/members/${U}")
+    debug "probe: $U in team $T (id=$ID) → HTTP $CODE"
+    if [ "$CODE" = "200" ] || [ "$CODE" = "204" ]; then
+      echo "::notice::approver $U is in team $T (eligible for $TIER)"
+      OK="yes"
+      break
+    fi
+  done
+  [ -n "$OK" ] && break
+done
+
+if [ -z "$OK" ]; then
+  echo "::error::Tier $TIER requires approval from a non-author member of {$ELIGIBLE}. Got approvers: $APPROVERS — none of them satisfied team membership. Set SOP_DEBUG=1 to see per-probe HTTP codes."
+  exit 1
+fi
+echo "::notice::sop-tier-check passed: $TIER, approver in {$ELIGIBLE}"

.gitea/workflows/audit-force-merge.yml

@@ -0,0 +1,58 @@
+# audit-force-merge — emit `incident.force_merge` to runner stdout when
+# a PR is merged with required-status-checks not green. Vector picks
+# the JSON line off docker_logs and ships to Loki on
+# molecule-canonical-obs (per `reference_obs_stack_phase1`); query as:
+#
+#   {host="operator"} |= "event_type" |= "incident.force_merge" | json
+#
+# Closes the §SOP-6 audit gap (the doc says force-merges write to
+# `structure_events`, but that table lives in the platform DB, not
+# Gitea-side; Loki is the practical equivalent for Gitea Actions
+# events). When the credential / observability stack converges later,
+# this can sync into structure_events from Loki via a backfill job —
+# the structured JSON shape is forward-compatible.
+#
+# Logic in `.gitea/scripts/audit-force-merge.sh` per the same script-
+# extract pattern as sop-tier-check.
+
+name: audit-force-merge
+
+# pull_request_target loads from the base branch — same security model
+# as sop-tier-check. Without this, an attacker could rewrite the
+# workflow on a PR and skip the audit emission for their own
+# force-merge. See `.gitea/workflows/sop-tier-check.yml` for the full
+# rationale.
+on:
+  pull_request_target:
+    types: [closed]
+
+jobs:
+  audit:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: read
+    # Skip when PR is closed without merge — saves a runner.
+    if: github.event.pull_request.merged == true
+    steps:
+      - name: Check out base branch (for the script)
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
+        with:
+          ref: ${{ github.event.pull_request.base.sha }}
+      - name: Detect force-merge + emit audit event
+        env:
+          # Same org-level secret the sop-tier-check workflow uses.
+          GITEA_TOKEN: ${{ secrets.SOP_TIER_CHECK_TOKEN || secrets.GITHUB_TOKEN }}
+          GITEA_HOST: git.moleculesai.app
+          REPO: ${{ github.repository }}
+          PR_NUMBER: ${{ github.event.pull_request.number }}
+          # Required-status-check contexts to evaluate at merge time.
+          # Newline-separated. Mirror this against branch protection
+          # (settings → branches → protected branch → required checks).
+          # Declared here rather than fetched from /branch_protections
+          # because that endpoint requires admin write — sop-tier-bot is
+          # read-only by design (least-privilege).
+          REQUIRED_CHECKS: |
+            sop-tier-check / tier-check (pull_request)
+            Secret scan / Scan diff for credential-shaped strings (pull_request)
+        run: bash .gitea/scripts/audit-force-merge.sh

.gitea/workflows/secret-scan.yml

@@ -0,0 +1,191 @@
+name: Secret scan
+
+# Hard CI gate. Refuses any PR / push whose diff additions contain a
+# recognisable credential. Defense-in-depth for the #2090-class incident
+# (2026-04-24): GitHub's hosted Copilot Coding Agent leaked a ghs_*
+# installation token into tenant-proxy/package.json via `npm init`
+# slurping the URL from a token-embedded origin remote. We can't fix
+# upstream's clone hygiene, so we gate here.
+#
+# Same regex set as the runtime's bundled pre-commit hook
+# (molecule-ai-workspace-runtime: molecule_runtime/scripts/pre-commit-checks.sh).
+# Keep the two sides aligned when adding patterns.
+#
+# Ported from .github/workflows/secret-scan.yml so the gate actually
+# fires on Gitea Actions. Differences from the GitHub version:
+#   - drops `merge_group` event (Gitea has no merge queue)
+#   - drops `workflow_call` (no cross-repo reusable invocation on Gitea)
+#   - SELF path updated to .gitea/workflows/secret-scan.yml
+# The job name + step name are identical to the GitHub workflow so the
+# status-check context (`Secret scan / Scan diff for credential-shaped
+# strings (pull_request)`) matches branch protection on molecule-core/main.
+
+on:
+  pull_request:
+    types: [opened, synchronize, reopened]
+  push:
+    branches: [main, staging]
+
+jobs:
+  scan:
+    name: Scan diff for credential-shaped strings
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          fetch-depth: 2  # need previous commit to diff against on push events
+
+      # For pull_request events the diff base may be many commits behind
+      # HEAD and absent from the shallow clone. Fetch it explicitly.
+      - name: Fetch PR base SHA (pull_request events only)
+        if: github.event_name == 'pull_request'
+        run: git fetch --depth=1 origin ${{ github.event.pull_request.base.sha }}
+
+      - name: Refuse if credential-shaped strings appear in diff additions
+        env:
+          # Plumb event-specific SHAs through env so the script doesn't
+          # need conditional `${{ ... }}` interpolation per event type.
+          # github.event.before/after only exist on push events;
+          # pull_request has pull_request.base.sha / pull_request.head.sha.
+          PR_BASE_SHA: ${{ github.event.pull_request.base.sha }}
+          PR_HEAD_SHA: ${{ github.event.pull_request.head.sha }}
+          PUSH_BEFORE: ${{ github.event.before }}
+          PUSH_AFTER: ${{ github.event.after }}
+        run: |
+          # Pattern set covers GitHub family (the actual #2090 vector),
+          # Anthropic / OpenAI / Slack / AWS. Anchored on prefixes with low
+          # false-positive rates against agent-generated content. Mirror of
+          # molecule-ai-workspace-runtime/molecule_runtime/scripts/pre-commit-checks.sh
+          # — keep aligned.
+          SECRET_PATTERNS=(
+            'ghp_[A-Za-z0-9]{36,}'           # GitHub PAT (classic)
+            'ghs_[A-Za-z0-9]{36,}'           # GitHub App installation token
+            'gho_[A-Za-z0-9]{36,}'           # GitHub OAuth user-to-server
+            'ghu_[A-Za-z0-9]{36,}'           # GitHub OAuth user
+            'ghr_[A-Za-z0-9]{36,}'           # GitHub OAuth refresh
+            'github_pat_[A-Za-z0-9_]{82,}'   # GitHub fine-grained PAT
+            'sk-ant-[A-Za-z0-9_-]{40,}'      # Anthropic API key
+            'sk-proj-[A-Za-z0-9_-]{40,}'     # OpenAI project key
+            'sk-svcacct-[A-Za-z0-9_-]{40,}'  # OpenAI service-account key
+            'sk-cp-[A-Za-z0-9_-]{60,}'       # MiniMax API key (F1088 vector — caught only after the fact)
+            'xox[baprs]-[A-Za-z0-9-]{20,}'   # Slack tokens
+            'AKIA[0-9A-Z]{16}'               # AWS access key ID
+            'ASIA[0-9A-Z]{16}'               # AWS STS temp access key ID
+          )
+
+          # Determine the diff base. Each event type stores its SHAs in
+          # a different place — see the env block above.
+          case "${{ github.event_name }}" in
+            pull_request)
+              BASE="$PR_BASE_SHA"
+              HEAD="$PR_HEAD_SHA"
+              ;;
+            *)
+              BASE="$PUSH_BEFORE"
+              HEAD="$PUSH_AFTER"
+              ;;
+          esac
+
+          # On push events with shallow clones, BASE may be present in
+          # the event payload but absent from the local object DB
+          # (fetch-depth=2 doesn't always reach the previous commit
+          # across true merges). Try fetching it on demand. If the
+          # fetch fails — e.g. the SHA was force-overwritten — we fall
+          # through to the empty-BASE branch below, which scans the
+          # entire tree as if every file were new. Correct, just slow.
+          if [ -n "$BASE" ] && ! echo "$BASE" | grep -qE '^0+$'; then
+            if ! git cat-file -e "$BASE" 2>/dev/null; then
+              git fetch --depth=1 origin "$BASE" 2>/dev/null || true
+            fi
+          fi
+
+          # Files added or modified in this change.
+          if [ -z "$BASE" ] || echo "$BASE" | grep -qE '^0+$' || ! git cat-file -e "$BASE" 2>/dev/null; then
+            # New branch / no previous SHA / BASE unreachable — check the
+            # entire tree as added content. Slower, but correct on first
+            # push.
+            CHANGED=$(git ls-tree -r --name-only HEAD)
+            DIFF_RANGE=""
+          else
+            CHANGED=$(git diff --name-only --diff-filter=AM "$BASE" "$HEAD")
+            DIFF_RANGE="$BASE $HEAD"
+          fi
+
+          if [ -z "$CHANGED" ]; then
+            echo "No changed files to inspect."
+            exit 0
+          fi
+
+          # Self-exclude: this workflow file legitimately contains the
+          # pattern strings as regex literals. Without an exclude it would
+          # block its own merge. Both the .github/ original and this
+          # .gitea/ port are excluded so a sync between them stays clean.
+          SELF_GITHUB=".github/workflows/secret-scan.yml"
+          SELF_GITEA=".gitea/workflows/secret-scan.yml"
+
+          OFFENDING=""
+          # `while IFS= read -r` (not `for f in $CHANGED`) so filenames
+          # containing whitespace don't word-split silently — a path
+          # with a space would otherwise produce two iterations on
+          # tokens that aren't real filenames, breaking the
+          # self-exclude + diff lookup.
+          while IFS= read -r f; do
+            [ -z "$f" ] && continue
+            [ "$f" = "$SELF_GITHUB" ] && continue
+            [ "$f" = "$SELF_GITEA" ] && continue
+            if [ -n "$DIFF_RANGE" ]; then
+              ADDED=$(git diff --no-color --unified=0 "$BASE" "$HEAD" -- "$f" 2>/dev/null | grep -E '^\+[^+]' || true)
+            else
+              # No diff range (new branch first push) — scan the full file
+              # contents as if every line were new.
+              ADDED=$(cat "$f" 2>/dev/null || true)
+            fi
+            [ -z "$ADDED" ] && continue
+            for pattern in "${SECRET_PATTERNS[@]}"; do
+              if echo "$ADDED" | grep -qE "$pattern"; then
+                OFFENDING="${OFFENDING}${f} (matched: ${pattern})\n"
+                break
+              fi
+            done
+          done <<< "$CHANGED"
+
+          if [ -n "$OFFENDING" ]; then
+            echo "::error::Credential-shaped strings detected in diff additions:"
+            # `printf '%b' "$OFFENDING"` interprets backslash escapes
+            # (the literal `\n` we appended above becomes a newline)
+            # WITHOUT treating OFFENDING as a format string. Plain
+            # `printf "$OFFENDING"` is a format-string sink: a filename
+            # containing `%` would be interpreted as a conversion
+            # specifier, corrupting the error message (or printing
+            # `%(missing)` artifacts).
+            printf '%b' "$OFFENDING"
+            echo ""
+            echo "The actual matched values are NOT echoed here, deliberately —"
+            echo "round-tripping a leaked credential into CI logs widens the blast"
+            echo "radius (logs are searchable + retained)."
+            echo ""
+            echo "Recovery:"
+            echo "  1. Remove the secret from the file. Replace with an env var"
+            echo "     reference (e.g. \${{ secrets.GITHUB_TOKEN }} in workflows,"
+            echo "     process.env.X in code)."
+            echo "  2. If the credential was already pushed (this PR's commit"
+            echo "     history reaches a public ref), treat it as compromised —"
+            echo "     ROTATE it immediately, do not just remove it. The token"
+            echo "     remains valid in git history forever and may be in any"
+            echo "     log/cache that consumed this branch."
+            echo "  3. Force-push the cleaned commit (or stack a revert) and"
+            echo "     re-run CI."
+            echo ""
+            echo "If the match is a false positive (test fixture, docs example,"
+            echo "or this workflow's own regex literals): use a clearly-fake"
+            echo "placeholder like ghs_EXAMPLE_DO_NOT_USE that doesn't satisfy"
+            echo "the length suffix, OR add the file path to the SELF exclude"
+            echo "list in this workflow with a short reason."
+            echo ""
+            echo "Mirror of the regex set lives in the runtime's bundled"
+            echo "pre-commit hook (molecule-ai-workspace-runtime:"
+            echo "molecule_runtime/scripts/pre-commit-checks.sh) — keep aligned."
+            exit 1
+          fi
+
+          echo "✓ No credential-shaped strings in this change."

.gitea/workflows/sop-tier-check.yml

@@ -1,33 +1,29 @@
 # sop-tier-check — canonical Gitea Actions workflow for §SOP-6 enforcement.
 #
-# Copy this file to `.gitea/workflows/sop-tier-check.yml` in any repo that
-# wants the §SOP-6 PR gate enforced. Pair with branch protection on the
-# protected branch:
-#   required_status_checks: ["sop-tier-check"]
-#   required_approving_reviews: 1
-#   approving_review_teams: ["ceo", "managers", "engineers"]
+# Logic lives in `.gitea/scripts/sop-tier-check.sh` (extracted 2026-05-09
+# from the previous inline-bash version). The script is the single source
+# of truth; this workflow file just sets env + invokes it.
 #
-# What it does:
-#   1. Reads the PR's `tier:*` label (low | medium | high). Fails if absent
-#      or ambiguous.
-#   2. Reads every approving review on the PR.
-#   3. For each approver, queries Gitea team membership.
-#   4. Marks the check success only if at least one approver is in a team
-#      whose tier-tag covers the PR's tier label, AND the approver is not
-#      the author.
+# Copy BOTH files (`.gitea/workflows/sop-tier-check.yml` +
+# `.gitea/scripts/sop-tier-check.sh`) into any repo that wants the
+# §SOP-6 PR gate enforced. Pair with branch protection on the protected
+# branch:
+#   required_status_checks:    ["sop-tier-check / tier-check (pull_request)"]
+#   required_approving_reviews: 1
+#   approving_review_teams:    ["ceo", "managers", "engineers"]
 #
 # Tier → eligible-team mapping (mirror of dev-sop §SOP-6):
 #   tier:low    → engineers, managers, ceo
 #   tier:medium → managers, ceo
 #   tier:high   → ceo
 #
-# Author identity is excluded automatically; Gitea's review system already
-# rejects self-reviews, but this workflow re-checks defensively in case the
-# native rule is bypassed (admin override, branch-protection edit, etc.).
+# Force-merge: Owners-team override remains available out-of-band via
+# the Gitea merge API; force-merge writes `incident.force_merge` to
+# `structure_events` per §Persistent structured logging gate (Phase 3).
 #
-# Force-merge: Owners-team override remains available out-of-band via the
-# Gitea merge API; force-merge writes `incident.force_merge` to
-# structure_events per §Persistent structured logging gate (Phase 3).
+# Set `SOP_DEBUG: '1'` in the env block to enable per-API-call diagnostic
+# lines — useful when diagnosing token-scope or team-id-resolution
+# issues. Default off.
 
 name: sop-tier-check
 
@@ -40,9 +36,9 @@ name: sop-tier-check
 # `pull_request_target` (added in Gitea 1.21 via go-gitea/gitea#25229)
 # is the documented mitigation.
 #
-# This workflow does NOT call `actions/checkout`, so no untrusted code
-# is ever executed in the runner — we only HTTP-call the Gitea API. If
-# a future change adds a checkout step, it MUST pin to
+# This workflow does NOT call `actions/checkout` of PR HEAD code, so no
+# untrusted code is ever executed in the runner — we only HTTP-call the
+# Gitea API. If a future change adds a checkout step, it MUST pin to
 # `${{ github.event.pull_request.base.sha }}` (NOT `head.sha`) to keep
 # the trust boundary.
 on:
@@ -58,127 +54,28 @@ jobs:
       contents: read
       pull-requests: read
     steps:
+      - name: Check out base branch (for the script)
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
+        with:
+          # Pin to base.sha — pull_request_target's protection only
+          # works if we never check out PR HEAD. Same SHA the workflow
+          # itself was loaded from.
+          ref: ${{ github.event.pull_request.base.sha }}
       - name: Verify tier label + reviewer team membership
         env:
-          # SOP_TIER_CHECK_TOKEN is the read-only `sop-tier-bot` PAT,
-          # provisioned with read:org scope and added to ceo/managers/
-          # engineers teams (a Gitea team-membership probe requires the
-          # caller to be a member of the team being probed). The auto-
-          # injected GITHUB_TOKEN's scope is repo-level only and cannot
-          # query org team membership, hence the dedicated secret.
-          # Falls back to GITHUB_TOKEN so the workflow at least starts and
-          # surfaces a clear error when the secret is missing.
+          # SOP_TIER_CHECK_TOKEN is the org-level secret for the
+          # sop-tier-bot PAT (read:organization,read:user,read:issue,
+          # read:repository). Stored at the org level
+          # (/api/v1/orgs/molecule-ai/actions/secrets) so per-repo
+          # configuration is unnecessary — every repo in the org
+          # picks it up automatically.
+          # Falls back to GITHUB_TOKEN with a clear error if missing.
           GITEA_TOKEN: ${{ secrets.SOP_TIER_CHECK_TOKEN || secrets.GITHUB_TOKEN }}
           GITEA_HOST: git.moleculesai.app
           REPO: ${{ github.repository }}
           PR_NUMBER: ${{ github.event.pull_request.number }}
           PR_AUTHOR: ${{ github.event.pull_request.user.login }}
-        run: |
-          set -euo pipefail
-          if [ -z "${GITEA_TOKEN:-}" ]; then
-            echo "::error::Neither GITEA_TOKEN nor GITHUB_TOKEN is available. Add a GITEA_TOKEN secret with org-membership read scope to enable team-based approval gating."
-            exit 1
-          fi
-          OWNER="${REPO%%/*}"
-          NAME="${REPO##*/}"
-          API="https://${GITEA_HOST}/api/v1"
-          AUTH="Authorization: token ${GITEA_TOKEN}"
-          echo "::notice::tier-check start: repo=$OWNER/$NAME pr=$PR_NUMBER author=$PR_AUTHOR"
-          # Sanity-check the token resolves a user; surfaces token-scope problems
-          # early instead of failing on a downstream call with no context.
-          WHOAMI=$(curl -sS -H "$AUTH" "${API}/user" | jq -r '.login // ""')
-          if [ -z "$WHOAMI" ]; then
-            echo "::error::GITEA_TOKEN cannot resolve a user via /api/v1/user — check the token scope and that the secret is wired correctly."
-            exit 1
-          fi
-          echo "::notice::token resolves to user: $WHOAMI"
-
-          # 1. Read tier label
-          LABELS=$(curl -sS -H "$AUTH" "${API}/repos/${OWNER}/${NAME}/issues/${PR_NUMBER}/labels" | jq -r '.[].name')
-          TIER=""
-          for L in $LABELS; do
-            case "$L" in
-              tier:low|tier:medium|tier:high)
-                if [ -n "$TIER" ]; then
-                  echo "::error::Multiple tier labels: $TIER + $L. Apply exactly one."
-                  exit 1
-                fi
-                TIER="$L"
-              ;;
-            esac
-          done
-          if [ -z "$TIER" ]; then
-            echo "::error::PR has no tier:low|tier:medium|tier:high label. Apply one before merge."
-            exit 1
-          fi
-          echo "tier=$TIER"
-
-          # 2. Tier → eligible teams
-          case "$TIER" in
-            tier:low)    ELIGIBLE="engineers managers ceo" ;;
-            tier:medium) ELIGIBLE="managers ceo" ;;
-            tier:high)   ELIGIBLE="ceo" ;;
-          esac
-          echo "eligible_teams=$ELIGIBLE"
-
-          # Resolve team-name → team-id once. The /orgs/{org}/teams/{slug}/...
-          # endpoints don't exist on Gitea 1.22; we have to use /teams/{id}.
-          # Fail loud on missing team rather than treating it as "user not in
-          # team" — that'd mask a misconfigured deployment.
-          ORG_TEAMS_FILE=$(mktemp)
-          HTTP_CODE=$(curl -sS -o "$ORG_TEAMS_FILE" -w '%{http_code}' -H "$AUTH" \
-            "${API}/orgs/${OWNER}/teams")
-          echo "teams-list HTTP=$HTTP_CODE size=$(wc -c <"$ORG_TEAMS_FILE")"
-          echo "teams-list body (first 300 chars):"
-          head -c 300 "$ORG_TEAMS_FILE"; echo
-          if [ "$HTTP_CODE" != "200" ]; then
-            echo "::error::GET /orgs/${OWNER}/teams returned HTTP $HTTP_CODE — token likely lacks read:org scope. Add a SOP_TIER_CHECK_TOKEN secret with read:organization scope."
-            exit 1
-          fi
-          declare -A TEAM_ID
-          for T in $ELIGIBLE; do
-            ID=$(jq -r --arg t "$T" '.[] | select(.name==$t) | .id' <"$ORG_TEAMS_FILE" | head -1)
-            if [ -z "$ID" ] || [ "$ID" = "null" ]; then
-              VISIBLE=$(jq -r '.[]?.name? // empty' <"$ORG_TEAMS_FILE" 2>/dev/null | tr '\n' ' ')
-              echo "::error::Team \"$T\" not found in org $OWNER. Teams visible: $VISIBLE"
-              exit 1
-            fi
-            TEAM_ID[$T]="$ID"
-            echo "team-id: $T → $ID"
-          done
-
-          # 3. Read approving reviewers
-          REVIEWS=$(curl -sS -H "$AUTH" "${API}/repos/${OWNER}/${NAME}/pulls/${PR_NUMBER}/reviews")
-          APPROVERS=$(echo "$REVIEWS" | jq -r '[.[] | select(.state=="APPROVED") | .user.login] | unique | .[]')
-          if [ -z "$APPROVERS" ]; then
-            echo "::error::No approving reviews. Tier $TIER requires approval from {$ELIGIBLE} (non-author)."
-            exit 1
-          fi
-          echo "approvers: $(echo $APPROVERS | tr '\n' ' ')"
-
-          # 4. For each approver: check non-author + team membership (by id)
-          OK=""
-          for U in $APPROVERS; do
-            if [ "$U" = "$PR_AUTHOR" ]; then
-              echo "skip self-review by $U"
-              continue
-            fi
-            for T in $ELIGIBLE; do
-              ID="${TEAM_ID[$T]}"
-              CODE=$(curl -sS -o /dev/null -w '%{http_code}' -H "$AUTH" \
-                "${API}/teams/${ID}/members/${U}")
-              echo "  probe: $U in team $T (id=$ID) → HTTP $CODE"
-              if [ "$CODE" = "200" ] || [ "$CODE" = "204" ]; then
-                echo "::notice::approver $U is in team $T (eligible for $TIER)"
-                OK="yes"
-                break
-              fi
-            done
-            [ -n "$OK" ] && break
-          done
-
-          if [ -z "$OK" ]; then
-            echo "::error::Tier $TIER requires approval from a non-author member of {$ELIGIBLE}. Got approvers: $APPROVERS — none of them satisfied team membership (probe HTTP codes above)."
-            exit 1
-          fi
-          echo "::notice::sop-tier-check passed: $TIER, approver in {$ELIGIBLE}"
+          # Set to '1' for diagnostic per-API-call output. Off by default
+          # so production logs aren't noisy.
+          SOP_DEBUG: '0'
+        run: bash .gitea/scripts/sop-tier-check.sh