// Deterministic, model-free fake ShardEngine for the native worker (DGR-033).
//
// This is the C++ analogue of `meshnet_node.fake_shard_engine.FakeShardEngine`
// (DGR-032): a pure fixture that performs a *bounded real forward* over the
// bytes it received off the socket and never links, loads, or dispatches to
// llama.cpp. It exists to prove the standalone worker process, stream,
// lifecycle, and supervision shape before any real engine is bound (DGR-037).
//
// The "forward" is deliberately transport-verifiable rather than semantic: it
// reassembles a tensor's fragments, checks they tile exactly, and derives a
// CRC32C over the uncompressed bytes — the same rule the schema's `Checksum`
// declares and the same bounded forward the DGR-024 Python surface performs.
// Feeding the same bytes back (echo) lets a client prove the payload truly
// traversed the wire and returned unmodified; a direct hop and an opaque relay
// of the identical frames therefore yield byte-identical responses.
//
// There is no arbitrary-graph entry point here and no llama.cpp RPC: the engine
// only knows how to reassemble/checksum a bundle. That is the whole point of a
// fixture worker (acceptance criterion 4).

#ifndef MESHNET_NATIVE_WORKER_FAKE_ENGINE_H_
#define MESHNET_NATIVE_WORKER_FAKE_ENGINE_H_

#include <algorithm>
#include <cstdint>
#include <optional>
#include <string>
#include <vector>

#include "shard_runtime.pb.h"

namespace meshnet::worker {

namespace sp = ::meshnet::shard::v1;

// Standard CRC-32 (ISO-HDLC / zlib polynomial 0xEDB88320, reflected).
//
// The schema's `Checksum` field is labelled CRC32C, but the DGR-024 Python
// runtime surface (`shard_runtime_server.py`) computes it with `zlib.crc32`
// (standard CRC-32, not the Castagnoli CRC32C). This worker deliberately mirrors
// that exact computation so its checksum acceptance is byte-for-byte identical
// to the existing Python gRPC surface and to a relayed frame's expectations.
inline uint32_t Crc32(const std::string& data, uint32_t seed = 0) {
  static uint32_t table[256];
  static bool built = false;
  if (!built) {
    for (uint32_t i = 0; i < 256; ++i) {
      uint32_t c = i;
      for (int k = 0; k < 8; ++k) {
        c = (c & 1) ? (c >> 1) ^ 0xEDB88320u : (c >> 1);
      }
      table[i] = c;
    }
    built = true;
  }
  uint32_t crc = seed ^ 0xFFFFFFFFu;
  for (unsigned char byte : data) {
    crc = (crc >> 8) ^ table[(crc ^ byte) & 0xFF];
  }
  return crc ^ 0xFFFFFFFFu;
}

// Outcome of validating one bundle before the bounded forward runs.
struct BundleCheck {
  // Set when the bundle is malformed/corrupt (maps to PAYLOAD_CORRUPT).
  std::optional<std::string> corrupt_detail;
  // Set when the declared payload exceeds the negotiated per-chunk ceiling
  // (maps to RESOURCE_EXHAUSTED) — the worker refuses unbounded messages.
  std::optional<std::string> oversize_detail;
};

// The fake engine's only capability: verify a bundle tiles and checksums, and
// that it stays within the negotiated byte ceiling. Mirrors `_validate_bundle`
// in `shard_runtime_server.py` plus the bounded-message rule DGR-033 adds.
class FakeShardEngine {
 public:
  // Marker mirroring `FakeShardEngine.EVIDENCE_CLASS` so a future parity check
  // (DGR-036) can assert this is a fixture, not a real engine.
  static constexpr const char* kEvidenceClass = "fixture";

  explicit FakeShardEngine(uint64_t max_chunk_bytes) : max_chunk_bytes_(max_chunk_bytes) {}

  BundleCheck Validate(const sp::TensorBundle& bundle) const {
    BundleCheck result;
    for (const auto& tensor : bundle.tensors()) {
      // Bounded message: a declared payload larger than the ceiling is refused
      // before any reassembly work is done.
      if (max_chunk_bytes_ != 0 && tensor.total_bytes() > max_chunk_bytes_) {
        result.oversize_detail =
            "tensor '" + tensor.name() + "': declared total_bytes " +
            std::to_string(tensor.total_bytes()) + " exceeds max_chunk_bytes " +
            std::to_string(max_chunk_bytes_);
        return result;
      }

      // Fragments must tile the wire body exactly: no hole, no overlap.
      std::vector<const sp::TensorFragment*> ordered;
      ordered.reserve(tensor.fragments_size());
      for (const auto& fragment : tensor.fragments()) {
        ordered.push_back(&fragment);
      }
      std::sort(ordered.begin(), ordered.end(),
                [](const sp::TensorFragment* a, const sp::TensorFragment* b) {
                  return a->byte_offset() < b->byte_offset();
                });
      uint64_t expected_offset = 0;
      std::string payload;
      for (const auto* fragment : ordered) {
        if (fragment->byte_offset() != expected_offset) {
          result.corrupt_detail =
              "tensor '" + tensor.name() + "': fragment at offset " +
              std::to_string(fragment->byte_offset()) +
              " does not tile the preceding " + std::to_string(expected_offset) +
              " bytes (gap or overlap)";
          return result;
        }
        payload.append(fragment->payload());
        expected_offset += fragment->payload().size();
      }
      if (tensor.compression() == sp::COMPRESSION_NONE &&
          expected_offset != tensor.total_bytes()) {
        result.corrupt_detail =
            "tensor '" + tensor.name() + "': fragments cover " +
            std::to_string(expected_offset) + " bytes, declared total_bytes is " +
            std::to_string(tensor.total_bytes());
        return result;
      }
      if (tensor.compression() == sp::COMPRESSION_NONE &&
          tensor.checksum().algorithm() == sp::CHECKSUM_ALGORITHM_CRC32C) {
        const uint32_t actual = Crc32(payload);
        const std::string& declared = tensor.checksum().value();
        std::string actual_be(4, '\0');
        actual_be[0] = static_cast<char>((actual >> 24) & 0xFF);
        actual_be[1] = static_cast<char>((actual >> 16) & 0xFF);
        actual_be[2] = static_cast<char>((actual >> 8) & 0xFF);
        actual_be[3] = static_cast<char>(actual & 0xFF);
        if (declared != actual_be) {
          result.corrupt_detail = "tensor '" + tensor.name() + "': checksum mismatch";
          return result;
        }
      }
    }
    return result;
  }

  // Bounded real forward: fold every fragment's payload through CRC32C so the
  // digest is only reproducible if the payload really traversed the wire.
  uint32_t BoundedForward(const sp::TensorBundle& bundle) const {
    uint32_t digest = 0;
    for (const auto& tensor : bundle.tensors()) {
      for (const auto& fragment : tensor.fragments()) {
        digest = Crc32(fragment.payload(), digest);
      }
    }
    return digest;
  }

 private:
  uint64_t max_chunk_bytes_;
};

}  // namespace meshnet::worker

#endif  // MESHNET_NATIVE_WORKER_FAKE_ENGINE_H_