#!/usr/bin/env bash
# =============================================================================
# batch-eval.sh — revm-based batch fitness evaluator
#
# Replaces the per-candidate Anvil+forge-script pipeline with in-process EVM
# execution via Foundry's native revm backend (FitnessEvaluator.t.sol).
#
# Speedup: compiles each candidate once (unavoidable — different Solidity per
# candidate), then runs ALL attack sequences in a single in-process forge test
# with O(1) memory snapshot/revert instead of RPC calls per attack.
#
# Usage:
#   ./tools/push3-evolution/revm-evaluator/batch-eval.sh \
#       [--output-dir /tmp/scores] \
#       candidate0.push3 candidate1.push3 ...
#
# Output (stdout):
#   One JSON object per candidate:
#     {"candidate_id":"gen0_c000","fitness":123456789}
#
# Exit codes:
#   0  Success.
#   1  Candidate-level error (transpile/compile failed for at least one candidate).
#   2  Infrastructure error (missing tool, BASE_RPC_URL not set, forge test failed).
#
# Environment:
#   BASE_RPC_URL   Required. Base network RPC endpoint for forking.
#   ATTACKS_DIR    Optional. Path to *.jsonl attack files.
#                  (default: <repo>/onchain/script/backtesting/attacks)
#   OUTPUT_DIR     Optional. Directory to copy scores.jsonl into (--output-dir overrides).
# =============================================================================

set -euo pipefail

export PATH="${HOME}/.foundry/bin:${PATH}"

SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
REPO_ROOT="$(cd "$SCRIPT_DIR/../../.." && pwd)"
ONCHAIN_DIR="$REPO_ROOT/onchain"
TRANSPILER_DIR="$REPO_ROOT/tools/push3-transpiler"
TRANSPILER_OUT="$ONCHAIN_DIR/src/OptimizerV3Push3.sol"
# Use OptimizerV3 (inherits Optimizer → UUPS compatible, has getLiquidityParams)
# instead of standalone OptimizerV3Push3 which lacks UUPS hooks.
OPTIMIZERV3_SOL="$ONCHAIN_DIR/src/OptimizerV3.sol"
ARTIFACT_PATH="$ONCHAIN_DIR/out/OptimizerV3.sol/OptimizerV3.json"
DEFAULT_ATTACKS_DIR="$ONCHAIN_DIR/script/backtesting/attacks"

# =============================================================================
# Argument parsing
# =============================================================================

OUTPUT_DIR="${OUTPUT_DIR:-}"

declare -a PUSH3_FILES=()

while [[ $# -gt 0 ]]; do
    case $1 in
        --output-dir) OUTPUT_DIR="$2"; shift 2 ;;
        --*) echo "Unknown option: $1" >&2; exit 2 ;;
        *) PUSH3_FILES+=("$1"); shift ;;
    esac
done

if [ "${#PUSH3_FILES[@]}" -eq 0 ]; then
    echo "Usage: $0 [--output-dir DIR] candidate1.push3 ..." >&2
    exit 2
fi

# =============================================================================
# Environment checks
# =============================================================================

BASE_RPC_URL="${BASE_RPC_URL:-}"
if [ -z "$BASE_RPC_URL" ]; then
    echo "  [batch-eval] ERROR: BASE_RPC_URL env var required for Base network fork" >&2
    exit 2
fi

for _tool in forge node python3; do
    command -v "$_tool" &>/dev/null || { echo "  [batch-eval] ERROR: $_tool not found in PATH" >&2; exit 2; }
done

# =============================================================================
# Helpers
# =============================================================================

log() { echo "  [batch-eval]  $*" >&2; }
fail2() { echo "  [batch-eval]  ERROR: $*" >&2; exit 2; }

# =============================================================================
# Step 1 — Ensure transpiler dependencies are installed
# =============================================================================

if [ ! -d "$TRANSPILER_DIR/node_modules" ]; then
    log "Installing transpiler dependencies…"
    (cd "$TRANSPILER_DIR" && npm install --silent) || fail2 "npm install in push3-transpiler failed"
fi

# =============================================================================
# Step 2 — Transpile + compile each candidate, extract bytecodes into manifest
# =============================================================================

MANIFEST_DIR="$(mktemp -d)"
IDS_FILE="$MANIFEST_DIR/ids.txt"
BYTECODES_FILE="$MANIFEST_DIR/bytecodes.txt"

: > "$IDS_FILE"
: > "$BYTECODES_FILE"

COMPILED_COUNT=0
FAILED_IDS=""

for PUSH3_FILE in "${PUSH3_FILES[@]}"; do
    PUSH3_FILE="$(cd "$(dirname "$PUSH3_FILE")" && pwd)/$(basename "$PUSH3_FILE")"
    CANDIDATE_ID="$(basename "$PUSH3_FILE" .push3)"

    # Transpile Push3 → OptimizerV3Push3.sol
    TRANSPILE_EC=0
    (
        cd "$TRANSPILER_DIR"
        npx ts-node src/index.ts "$PUSH3_FILE" "$TRANSPILER_OUT"
    ) >/dev/null 2>&1 || TRANSPILE_EC=$?

    if [ "$TRANSPILE_EC" -ne 0 ]; then
        log "WARNING: transpile failed for $CANDIDATE_ID (exit $TRANSPILE_EC) — skipping"
        FAILED_IDS="$FAILED_IDS $CANDIDATE_ID"
        continue
    fi

    # Inject transpiled calculateParams body into OptimizerV3.sol (UUPS-compatible).
    # Extract function body from OptimizerV3Push3.sol and replace content between
    # BEGIN/END markers in OptimizerV3.sol.
    python3 - "$TRANSPILER_OUT" "$OPTIMIZERV3_SOL" <<'PYEOF' || {
import sys

push3_path = sys.argv[1]
v3_path = sys.argv[2]

# Extract function body from OptimizerV3Push3.sol
# Find "function calculateParams" then extract everything between the opening { and
# the matching closing } at the same indent level (4 spaces / function level)
with open(push3_path) as f:
    push3 = f.read()

# Find body start: line after "function calculateParams...{"
fn_start = push3.find("function calculateParams")
if fn_start == -1:
    sys.exit("calculateParams not found in OptimizerV3Push3")
brace_start = push3.find("{", fn_start)
body_start = push3.index("\n", brace_start) + 1

# Find body end: the closing "    }" of the function (4-space indent, before contract close)
# Walk backwards from end to find the function-level closing brace
lines = push3[body_start:].split("\n")
body_lines = []
for line in lines:
    if line.strip() == "}" and (line.startswith("    }") or line == "}"):
        # This is the function-closing brace
        break
    body_lines.append(line)

body = "\n".join(body_lines)

# Now inject into OptimizerV3.sol between markers
with open(v3_path) as f:
    v3 = f.read()

begin_marker = "// ── BEGIN TRANSPILER OUTPUT"
end_marker = "// ── END TRANSPILER OUTPUT"
begin_idx = v3.find(begin_marker)
end_idx = v3.find(end_marker)
if begin_idx == -1 or end_idx == -1:
    sys.exit("markers not found in OptimizerV3.sol")

begin_line_end = v3.index("\n", begin_idx) + 1
# Keep the end marker line intact
with open(v3_path, "w") as f:
    f.write(v3[:begin_line_end])
    f.write(body + "\n")
    f.write(v3[end_idx:])

PYEOF
        log "WARNING: failed to inject calculateParams into OptimizerV3.sol for $CANDIDATE_ID — skipping"
        FAILED_IDS="$FAILED_IDS $CANDIDATE_ID"
        continue
    }

    # Compile (forge's incremental build skips unchanged files quickly)
    FORGE_EC=0
    (cd "$ONCHAIN_DIR" && forge build --silent) >/dev/null 2>&1 || FORGE_EC=$?

    if [ "$FORGE_EC" -ne 0 ]; then
        log "WARNING: forge build failed for $CANDIDATE_ID (exit $FORGE_EC) — skipping"
        FAILED_IDS="$FAILED_IDS $CANDIDATE_ID"
        continue
    fi

    # Extract bytecode from artifact (strip leading 0x if present)
    BYTECODE_HEX="$(python3 - "$ARTIFACT_PATH" <<'PYEOF'
import json, sys
with open(sys.argv[1]) as f:
    d = json.load(f)
bytecode = d["deployedBytecode"]["object"]
# Ensure 0x prefix
if not bytecode.startswith("0x"):
    bytecode = "0x" + bytecode
print(bytecode)
PYEOF
)" || { log "WARNING: failed to extract bytecode for $CANDIDATE_ID — skipping"; FAILED_IDS="$FAILED_IDS $CANDIDATE_ID"; continue; }

    if [ -z "$BYTECODE_HEX" ] || [ "$BYTECODE_HEX" = "0x" ]; then
        log "WARNING: empty bytecode for $CANDIDATE_ID — skipping"
        FAILED_IDS="$FAILED_IDS $CANDIDATE_ID"
        continue
    fi

    printf '%s\n' "$CANDIDATE_ID" >> "$IDS_FILE"
    printf '%s\n' "$BYTECODE_HEX" >> "$BYTECODES_FILE"
    COMPILED_COUNT=$((COMPILED_COUNT + 1))
    log "Compiled $CANDIDATE_ID"
done

if [ "$COMPILED_COUNT" -eq 0 ]; then
    fail2 "No candidates compiled successfully — aborting"
fi

log "Compiled $COMPILED_COUNT / ${#PUSH3_FILES[@]} candidates"

# =============================================================================
# Step 3 — Run FitnessEvaluator.t.sol (in-process revm, all candidates at once)
# =============================================================================

ATTACKS_DIR="${ATTACKS_DIR:-$DEFAULT_ATTACKS_DIR}"

log "Running FitnessEvaluator.t.sol (in-process revm, fork: $BASE_RPC_URL)…"

FORGE_TEST_EC=0
FORGE_OUTPUT="$(
    cd "$ONCHAIN_DIR"
    BASE_RPC_URL="$BASE_RPC_URL" \
    FITNESS_MANIFEST_DIR="$MANIFEST_DIR" \
    ATTACKS_DIR="$ATTACKS_DIR" \
    forge test \
        --match-contract FitnessEvaluator \
        --match-test testBatchEvaluate \
        -vv \
        --no-match-path "NOT_A_REAL_PATH" \
        2>&1
)" || FORGE_TEST_EC=$?

if [ "$FORGE_TEST_EC" -ne 0 ]; then
    # Surface forge output on failure for diagnosis
    printf '%s\n' "$FORGE_OUTPUT" >&2
    fail2 "forge test failed (exit $FORGE_TEST_EC)"
fi

# =============================================================================
# Step 4 — Extract and emit score JSON lines
#
# forge test -vv wraps console.log output with leading spaces and a "Logs:" header.
# We grep for lines containing the score JSON pattern and strip the indentation.
# =============================================================================

SCORES_JSONL="$(printf '%s\n' "$FORGE_OUTPUT" | grep -E '"candidate_id"' | sed 's/^[[:space:]]*//' || true)"

if [ -z "$SCORES_JSONL" ]; then
    printf '%s\n' "$FORGE_OUTPUT" >&2
    fail2 "No score lines found in forge test output"
fi

# Emit scores to stdout
printf '%s\n' "$SCORES_JSONL"

# Optionally write to output directory
if [ -n "$OUTPUT_DIR" ]; then
    mkdir -p "$OUTPUT_DIR"
    printf '%s\n' "$SCORES_JSONL" > "$OUTPUT_DIR/scores.jsonl"
    log "Scores written to $OUTPUT_DIR/scores.jsonl"
fi

# Warn about any candidates that were skipped (compile failures)
if [ -n "$FAILED_IDS" ]; then
    log "WARNING: the following candidates were skipped (compile failed): $FAILED_IDS"
    exit 1
fi

log "Done — scored $COMPILED_COUNT candidates"