golangLAKEHOUSE/scripts/cutover/parity/session_log_parity.sh

#!/usr/bin/env bash
# session_log_parity — verify Rust gateway and Go validatord write
# byte-equivalent SessionRecord JSONL rows from identical input.
#
# Why: the longitudinal session log (one row per /v1/iterate session)
# is the offline-analysis layer. Cross-runtime drift means a DuckDB
# query that works against one log fails against the other — the
# whole "unified longitudinal view" theory unravels. This probe is
# the regression gate.
#
# Approach (pure schema check, no live daemon needed):
#   1. Build both runtimes' session_log writers as standalone helper
#      binaries that take a fixture JSON on stdin and emit one row.
#   2. Feed identical fixture inputs through each.
#   3. Diff the resulting rows after normalizing the few fields that
#      MUST differ (timestamp, daemon).
#
# Outputs: reports/cutover/gauntlet_2026-05-02/parity/session_log_parity.md
#
# Exit 0 on schema match; exit 1 on drift.

set -uo pipefail
cd "$(dirname "$0")/../../.."

RUST_REPO="${RUST_REPO:-/home/profit/lakehouse}"
RUST_BIN="${RUST_BIN:-$RUST_REPO/target/release/parity_session_log}"
GO_BIN="${GO_BIN:-./bin/parity_session_log_go}"
OUT_DIR="reports/cutover/gauntlet_2026-05-02/parity"
mkdir -p "$OUT_DIR"
OUT="$OUT_DIR/session_log_parity.md"

export PATH="$PATH:/usr/local/go/bin"

# ── Build both helpers ─────────────────────────────────────────────
go build -o "$GO_BIN" ./scripts/cutover/parity/session_log_helper

if [ ! -x "$RUST_BIN" ]; then
  echo "[session-log-parity] building Rust helper..."
  (cd "$RUST_REPO" && cargo build -p gateway --bin parity_session_log --release 2>&1 | tail -3)
fi
if [ ! -x "$RUST_BIN" ]; then
  echo "[session-log-parity] SKIP: $RUST_BIN missing"
  exit 0
fi

# ── Fixtures ───────────────────────────────────────────────────────
# Parallel arrays — labels and fixtures keyed by index. Avoids a
# separator-in-string scheme (the prior `||` form silently injected
# a `|` character into every fixture body, which both helpers then
# rejected with empty output → trivially-equal "match" — caught
# during initial probe authoring 2026-05-02).
LABELS=(
  "accepted_grounded"
  "max_iter_exhausted"
  "infra_error"
  "unicode_in_prompt"
)
FIXTURES=(
  '{"session_id":"trace-1","kind":"fill","model":"qwen3.5:latest","provider":"ollama","prompt":"produce a fill","iterations":1,"max_iterations":3,"final_verdict":"accepted","attempts":[{"iteration":0,"verdict_kind":"accepted","span_id":"sp-0"}],"artifact":{"fills":[{"candidate_id":"W-1"}]},"grounded_in_roster":true,"duration_ms":50}'
  '{"session_id":"trace-2","kind":"fill","model":"qwen3.5:latest","provider":"ollama","prompt":"P","iterations":3,"max_iterations":3,"final_verdict":"max_iter_exhausted","attempts":[{"iteration":0,"verdict_kind":"validation_failed","error":"phantom W-X","span_id":"sp-a"},{"iteration":1,"verdict_kind":"validation_failed","error":"phantom W-Y","span_id":"sp-b"},{"iteration":2,"verdict_kind":"no_json","span_id":"sp-c"}],"duration_ms":3200}'
  '{"session_id":"trace-3","kind":"playbook","model":"qwen","provider":"ollama","prompt":"P","iterations":0,"max_iterations":3,"final_verdict":"infra_error","attempts":[{"iteration":0,"verdict_kind":"infra_error","error":"connection refused"}],"duration_ms":12}'
  '{"session_id":"trace-4","kind":"playbook","model":"qwen","provider":"ollama","prompt":"Café résumé ⭐ 你好","iterations":1,"max_iterations":3,"final_verdict":"accepted","attempts":[{"iteration":0,"verdict_kind":"accepted","span_id":"sp-u"}],"artifact":{"endorsed_names":["W-1"],"operation":"fill: X x1 in A, B","fingerprint":"abc"},"duration_ms":80}'
)

normalize() {
  # Strip the few fields that MUST differ between Rust+Go runs
  # (timestamp = now; daemon = producer name). Sort the keys so the
  # JSON serialization order doesn't break a byte-equal diff.
  jq -cS 'del(.timestamp) | del(.daemon)' <<<"$1"
}

TOTAL=0; MATCH=0; DIFF=0
DIFF_DETAIL=""

for i in "${!FIXTURES[@]}"; do
  label="${LABELS[$i]}"
  fixture="${FIXTURES[$i]}"
  TOTAL=$((TOTAL+1))
  rust_row=$(printf '%s' "$fixture" | "$RUST_BIN" 2>&1 || echo '{"error":"rust_helper_failed"}')
  go_row=$(printf '%s' "$fixture" | "$GO_BIN" 2>&1 || echo '{"error":"go_helper_failed"}')
  # Refuse trivial-equal-empty matches: if either side produced no
  # parseable JSON at all, mark this as a diff rather than a match.
  if ! echo "$rust_row" | jq -e . >/dev/null 2>&1; then
    rust_norm="<rust helper failed: $(echo "$rust_row" | head -c 200)>"
  else
    rust_norm=$(normalize "$rust_row")
  fi
  if ! echo "$go_row" | jq -e . >/dev/null 2>&1; then
    go_norm="<go helper failed: $(echo "$go_row" | head -c 200)>"
  else
    go_norm=$(normalize "$go_row")
  fi
  if [ "$rust_norm" = "$go_norm" ]; then
    MATCH=$((MATCH+1))
  else
    DIFF=$((DIFF+1))
    DIFF_DETAIL="$DIFF_DETAIL"$'\n\n'"### $label"$'\n\n''**Rust:**'$'\n''```json'$'\n'"$rust_norm"$'\n''```'$'\n\n''**Go:**'$'\n''```json'$'\n'"$go_norm"$'\n''```'
  fi
done

# ── Report ─────────────────────────────────────────────────────────
{
  echo "# session_log parity probe — Rust gateway vs Go validatord"
  echo
  echo "**Date:** $(date -u +%Y-%m-%dT%H:%M:%SZ)"
  echo "**Rust helper:** \`$RUST_BIN\`"
  echo "**Go helper:** \`$GO_BIN\`"
  echo
  echo "Identical fixture inputs through each runtime's"
  echo "\`SessionRecord\` builder + JSON marshaler. Match = byte-equal"
  echo "after stripping \`timestamp\` (per-run wall clock) + \`daemon\`"
  echo "(\"gateway\" on Rust side, \"validatord\" on Go side; both are"
  echo "valid producers in the same longitudinal log)."
  echo
  echo "**Tally:** $MATCH match · $DIFF diff (out of $TOTAL fixtures)"
  if [ -n "$DIFF_DETAIL" ]; then
    echo
    echo "## Divergences"
    echo "$DIFF_DETAIL"
  else
    echo
    echo "_No divergences — schema parity holds across all fixtures._"
  fi
} > "$OUT"

echo "[parity] session_log: $MATCH match / $DIFF diff (out of $TOTAL) → $OUT"
[ "$DIFF" -eq 0 ]