#pragma once
/// TRACES: GR-004 | SR-001
//
// Gallery ↔ embedder binding.
//
// A gallery is only valid for the embedder that built it. Cosine similarities
// between embeddings from two different models are meaningless but *look*
// plausible — nothing crashes, nothing is obviously wrong, and every number
// measured downstream is quietly garbage. So the embedder's identity is stamped
// into the gallery at build time and checked by every consumer at load time.
//
// ── What identifies an embedder ───────────────────────────────────────────────
// Two fields, carried together:
//
//   model_name    basename of the model file, e.g. "LVFace-B_Glint360K.onnx"
//   model_sha256  hex SHA-256 of that file's bytes
//
// The hash is what *decides*; the name is what a human *reads*. Neither alone is
// enough:
//
//   • A name alone is a promise, not a fact. Models get re-exported, re-quantised
//     and overwritten in place under an unchanged filename — which is precisely
//     the case where the weights differ and nothing else does. A name-only stamp
//     is blind to exactly the failure it exists to catch.
//   • A hash alone is correct but unreadable: "expected 3f2a… got 9c1b…" tells an
//     operator nothing about what to do next.
//
// SHA-256 over the file bytes is derived from the artefact rather than asserted
// about it, is stable across machines and filesystems, and needs no registry to
// be kept up to date. Cost is ~0.1 s for a 250 MB ONNX, paid once per process
// (results are memoised on path+mtime+size), which is noise next to model load.
//
// ── Degraded and legacy cases ─────────────────────────────────────────────────
// A TRT-backend deployment may run from a prebuilt .engine with the source .onnx
// absent, so the hash cannot be computed. Then the name is compared alone and the
// result is reported as a *weak* match — believed, not proven.
//
// Galleries built before GR-004 carry no stamp at all. They warn loudly rather
// than fail, because the state is unknown rather than known-bad, and because
// hard-failing every pre-existing gallery would make the check something people
// route around rather than trust. Set require_stamp (or SAE_REQUIRE_GALLERY_STAMP=1)
// to promote "unknown" to a hard error — that is the mode measurement work runs in.
//
// A *mismatch* is always fatal, in every mode, with no bypass.

#include <cstdint>
#include <string>

struct EmbedderStamp {
    std::string model_name;      // basename of the model file
    std::string model_sha256;    // lowercase hex SHA-256 of the file's bytes ("" = unavailable)
    int32_t     embed_dim{512};

    bool empty() const { return model_name.empty() && model_sha256.empty(); }

    // "LVFace-B_Glint360K.onnx (sha256 3f2a1c4d…)" — for error messages.
    std::string describe() const;
};

// Identify the model at `model_path`. Missing/unreadable file → name filled from
// the path, hash left empty (the weak-match path). Empty path → empty stamp.
EmbedderStamp make_embedder_stamp(const std::string& model_path);

enum class StampVerdict {
    match,             // hashes agree — binding proven
    weak_match,        // names agree, no hash on one side — believed, unproven
    unstamped,         // gallery predates GR-004 / was written without a stamp
    unknown_embedder,  // gallery is stamped but the loaded embedder can't be identified
    mismatch,          // proven different models — always fatal
};

struct StampCheck {
    StampVerdict verdict{StampVerdict::match};
    std::string  message;      // human-readable, names BOTH sides

    // A mismatch is fatal unconditionally. The three "cannot prove it" verdicts
    // are fatal only in strict mode.
    bool fatal(bool require_stamp) const {
        return verdict == StampVerdict::mismatch ||
               (require_stamp && verdict != StampVerdict::match);
    }
};

// Pure comparison — no file I/O, no model loading. This is the unit under test.
// `gallery_desc`/`embedder_desc` are only used to make the message locatable
// (a gallery path, a dump path, "the embedder being loaded", …).
StampCheck compare_embedder_stamps(const EmbedderStamp& built_with,
                                   const EmbedderStamp& loading_with,
                                   const std::string&   gallery_desc  = "gallery",
                                   const std::string&   embedder_desc = "embedder");

// Apply the comparison: throw std::runtime_error on a fatal verdict, otherwise
// log to stderr. `require_stamp` is OR-ed with SAE_REQUIRE_GALLERY_STAMP.
void enforce_embedder_stamp(const EmbedderStamp& built_with,
                            const EmbedderStamp& loading_with,
                            const std::string&   gallery_desc,
                            const std::string&   embedder_desc,
                            bool                 require_stamp);

// Convenience for the common consumer shape: "I loaded this gallery and I am
// about to embed with this model file." Hashes the model, then enforces.
struct ActorGallery;
void verify_gallery_embedder(const ActorGallery& gallery,
                             const std::string&  gallery_path,
                             const std::string&  arcface_model_path,
                             bool                require_stamp);

// SAE_REQUIRE_GALLERY_STAMP=1 → treat an unprovable binding as fatal.
bool require_gallery_stamp_from_env();

// Lowercase hex SHA-256. Exposed so a test can pin the digest against the
// published vectors, which is what guarantees the C++ and Python (hashlib)
// stamps of the same file agree.
std::string sha256_hex(const std::string& bytes);
std::string sha256_file_hex(const std::string& path);   // "" if unreadable