shoc-pr-review-runner/scripts/generate-evidence.sh

#!/usr/bin/env bash
# Render /workspace/artifacts/review-evidence.md (spec §18) from the recorded
# gate statuses and PR metadata. Every check appears with an explicit status:
# PASS / FAIL / NOT_APPLICABLE / NOT_RUN / BLOCKED. Phase-2/3 checks the Phase-1
# runner cannot execute are stated NOT_RUN with the reason — never omitted,
# never converted into a pass.
#
# Reads: REVIEW_TYPE, TICKET, REVIEW_NOTES, RUN_ID/GITHUB_RUN_ID, artifacts from
#        earlier steps ($ARTIFACTS_DIR/{frontend,backend}-pr.json, checkout.json,
#        gate-status.tsv)

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
# shellcheck source=lib.sh
source "$SCRIPT_DIR/lib.sh"

require_env REVIEW_TYPE
EVIDENCE_FILE="$ARTIFACTS_DIR/review-evidence.md"
run_id="${GITHUB_RUN_ID:-local}"

# The evidence report is only as trustworthy as the gate table it renders.
assert_gate_table_intact

# Untrusted strings (PR titles, branch names, dispatcher-supplied ticket and
# notes) must not be able to forge lines inside the evidence report — the agent
# is told the evidence report is the only source of truth for what executed.
# Control characters and newlines are stripped and the length is capped, so a
# crafted value stays on the single line it was rendered into.
sanitize() {
  printf '%s' "$1" | tr -d '\000-\037' | cut -c1-200
}

pr_field() { # pr_field <side> <jq-expr> [fallback]
  local f="$ARTIFACTS_DIR/$1-pr.json"
  if [ -f "$f" ]; then sanitize "$(jq -r "$2" "$f")"; else echo "${3:-not in scope}"; fi
}

g() { gate_status "$1"; }

# A side that has no PR under review has all its gates NOT_APPLICABLE.
side_in_scope() { # side_in_scope <frontend|backend>
  case "$REVIEW_TYPE" in
    paired) return 0 ;;
    "$1") return 0 ;;
    *) return 1 ;;
  esac
}

fe_gate() { if side_in_scope frontend; then g "$1"; else echo "NOT_APPLICABLE (backend-only review)"; fi; }
be_gate() { if side_in_scope backend; then g "$1"; else echo "NOT_APPLICABLE (frontend-only review)"; fi; }

companion_note=""
if [ "$REVIEW_TYPE" != "paired" ] && [ -f "$ARTIFACTS_DIR/checkout.json" ]; then
  cb="$(jq -r '.companion_branch' "$ARTIFACTS_DIR/checkout.json")"
  companion_note=" (companion checked out at \`$cb\` head for contract context, not under review)"
fi

cat >"$EVIDENCE_FILE" <<EOF
# Review Evidence

## Review Request
- Review type: $REVIEW_TYPE
- Frontend PR: $(pr_field frontend '"#\(.pr)"') (title and branch names appear in the untrusted section, not here)
- Backend PR: $(pr_field backend '"#\(.pr)"')
- Ticket: $(sanitize "${TICKET:-not provided}")
- Reviewer notes: $(sanitize "${REVIEW_NOTES:-none}")
- Workflow run: $run_id

## Exact Heads
- Frontend SHA: $(pr_field frontend '.short_sha')$( side_in_scope frontend || printf '%s' "$companion_note")
- Backend SHA: $(pr_field backend '.short_sha')$( side_in_scope backend || printf '%s' "$companion_note")
- Frontend base: $(pr_field frontend '.base_ref')
- Backend base: $(pr_field backend '.base_ref')

## Governance Signals
- Frontend PR CI status: $(pr_field frontend '.ci_status')
- Backend PR CI status: $(pr_field backend '.ci_status')
- Frontend PR mergeable: $(pr_field frontend '.mergeable // "unknown"')
- Backend PR mergeable: $(pr_field backend '.mergeable // "unknown"')
- CI statuses come from the PR head's check-runs; red/pending/missing is a governance signal, not silently omitted.

## Stack Status
- Frontend parent: NOT_RUN (stacked-PR resolution is Phase 4)
- Backend parent: NOT_RUN (stacked-PR resolution is Phase 4)
- Base integrity: NOT_RUN (base comparison is Phase 4)

## Backend Gates
- Restore: $(be_gate backend.restore)
- Release build: $(be_gate backend.build)
- Tests: $(be_gate backend.test)
- Migration list: NOT_RUN (database provisioning is Phase 2)
- Migration script: NOT_RUN (database provisioning is Phase 2)
- Migration apply: NOT_RUN (database provisioning is Phase 2)
- Startup: NOT_RUN (runtime environment is Phase 2)
- Health endpoint: NOT_RUN (runtime environment is Phase 2)
- API runtime scenarios: NOT_RUN (runtime environment is Phase 2)

## Frontend Gates
- Clean install: $(fe_gate frontend.install)
- Lint: $(fe_gate frontend.lint)
- TypeScript + production build: $(fe_gate frontend.build) (tsc -b runs inside the build script)
- Unit/component tests: $(fe_gate frontend.unit_tests)
- Development startup: NOT_RUN (manual route exercise is Phase 2)
- Production preview: NOT_RUN (runtime environment is Phase 2)

## Browser Validation
- Mocked Playwright: $(fe_gate frontend.e2e_mocked)
- Live Playwright: NOT_RUN (live backend integration is Phase 3; MOCKED COVERAGE IS NOT LIVE COVERAGE)
- Affected routes: NOT_RUN (live browser validation is Phase 3)
- Console errors: NOT_RUN (live browser validation is Phase 3)
- Failed requests: NOT_RUN (live browser validation is Phase 3)

## Runtime Limitations
- The Phase 1 runner does not provision a database, start either application, or run live browser flows. Any conclusion about runtime behavior must come from code inspection and is not runtime-verified.
- Disabled integrations: all (no runtime environment in Phase 1)
- Mocked external systems: the Playwright suite mocks ALL backend API calls via page.route
- Unexecuted checks: listed NOT_RUN above with reasons

## Logs and Artifacts
$(if [ -d "$LOG_DIR" ] && [ -n "$(ls -A "$LOG_DIR" 2>/dev/null)" ]; then
    for f in "$LOG_DIR"/*; do
      printf -- '- logs/%s\n' "$(basename "$f")"
    done
  else
    printf -- '- none\n'
  fi)

## Gate Detail
$(if [ -f "$GATE_STATUS_FILE" ]; then
    while IFS=$'\t' read -r key status det; do
      # shellcheck disable=SC2016 # backticks are literal markdown
      printf -- '- `%s`: %s%s\n' "$key" "$status" "${det:+ — $det}"
    done <"$GATE_STATUS_FILE"
  else
    printf -- '- no gates recorded\n'
  fi)
EOF

log "evidence written to $EVIDENCE_FILE"