AIChatExporter/tools/metadata_diff.py

"""What distinguishes an image ChatGPT refuses to serve from one it serves?

branch_check.py turned up something the earlier probing missed: of the images
that failed to download, only some are actually gone. The rest answer
/files/{id} with 200 and full metadata, and refuse only /download. Three
distinct states:

    gone     404 on /files/{id}                  — deleted, unrecoverable
    refused  200 on /files/{id}, 403 on download — exists, will not serve
    working  200 on both                         — fine

"refused" is the interesting one, because those files still exist and may be
recoverable. Since the metadata comes back for them, the discriminator can be
read straight off: fetch metadata for every file in each state and compare the
fields. A field that is constant within "refused" and different in "working"
is the cause.

Also re-checks /download now. If a file that was refused during the export
serves today, the failure was transient and a retry pass recovers it — a very
different fix from anything permanent.

Run from the project root:

    python tools/metadata_diff.py
"""

import json
import os
import re
import sys
from collections import defaultdict
from pathlib import Path

sys.path.insert(0, str(Path(__file__).resolve().parent.parent))

from dotenv import load_dotenv

load_dotenv()

from src.providers.chatgpt import BASE_URL, ChatGPTProvider  # noqa: E402

SAVED_RE = re.compile(r"!\[([^\]]*)\]\((media/[^)]+)\)")
DEAD_RE = re.compile(r"🖼️ \*\*Image attached\*\* — `([^`]+)`\s*\(([^)]*)\)")

WORKING_SAMPLE = 6


def collect(export_dir: Path) -> tuple[list[str], list[str]]:
    """(ids that failed to download, ids that downloaded fine)."""
    from src.providers.chatgpt import parse_asset_file_id

    failed: list[str] = []
    working: list[str] = []
    for md in export_dir.rglob("*.md"):
        try:
            text = md.read_text(encoding="utf-8", errors="replace")
        except OSError:
            continue
        for ref, _meta in DEAD_RE.findall(text):
            file_id = parse_asset_file_id(ref)
            if file_id:
                failed.append(file_id)
        for _source, rel in SAVED_RE.findall(text):
            stem = Path(rel).stem
            if stem.startswith("file"):
                working.append(stem)
    return failed, working


def probe(provider, file_id: str) -> tuple[str, dict]:
    """(state, metadata) for one file."""
    provider._pace()
    meta_resp = provider._session.request(
        "GET", f"{BASE_URL}/files/{file_id}", timeout=30
    )
    if meta_resp.status_code == 404:
        return "gone", {}
    if meta_resp.status_code != 200:
        return f"meta-{meta_resp.status_code}", {}

    try:
        meta = meta_resp.json()
    except Exception:  # noqa: BLE001 - diagnostic
        meta = {}

    provider._pace()
    dl_resp = provider._session.request(
        "GET", f"{BASE_URL}/files/{file_id}/download", timeout=30
    )
    state = "working" if dl_resp.status_code == 200 else f"refused-{dl_resp.status_code}"
    return state, meta


def main() -> None:
    export_dir = Path(os.getenv("EXPORT_DIR", "./exports")).expanduser()
    failed, working = collect(export_dir)
    if not failed:
        print(f"no failed images found under {export_dir}")
        return

    # Sample working files across the archive rather than all of them.
    step = max(1, len(working) // WORKING_SAMPLE)
    working_sample = working[::step][:WORKING_SAMPLE]

    provider = ChatGPTProvider()
    by_state: dict[str, list[tuple[str, dict]]] = defaultdict(list)

    print("=" * 78)
    print(f"Probing {len(failed)} failed + {len(working_sample)} working files")
    print("=" * 78)
    for file_id in failed + working_sample:
        state, meta = probe(provider, file_id)
        by_state[state].append((file_id, meta))
        print(f"  {file_id[:40]:<42} {state}")

    print()
    print("=" * 78)
    print("States")
    print("=" * 78)
    for state, entries in sorted(by_state.items()):
        print(f"  {state:<16} {len(entries)}")
    print()

    if any(s.startswith("refused") for s in by_state) is False:
        print("  No file is in the 'refused' state right now.")
        print("  → Every previously-failed file that still exists now serves.")
        print("    The export-time 403s were TRANSIENT; a retry pass recovers them.")
        print()

    print("=" * 78)
    print("Metadata field comparison")
    print("=" * 78)
    states = [s for s in by_state if by_state[s] and any(m for _i, m in by_state[s])]
    all_fields: set[str] = set()
    for state in states:
        for _fid, meta in by_state[state]:
            all_fields.update(meta.keys())

    for field in sorted(all_fields):
        line = f"  {field:<24}"
        distinct_per_state = []
        for state in sorted(states):
            values = {
                json.dumps(meta.get(field), default=str)[:28]
                for _fid, meta in by_state[state]
                if meta
            }
            shown = ", ".join(sorted(values)[:3])
            if len(values) > 3:
                shown += f" (+{len(values) - 3} more)"
            distinct_per_state.append((state, values, shown))
            line += f"  [{state}] {shown}"
        # Flag fields that cleanly separate the states.
        value_sets = [v for _s, v, _sh in distinct_per_state]
        if len(value_sets) > 1 and all(
            not (a & b) for i, a in enumerate(value_sets) for b in value_sets[i + 1:]
        ):
            line += "   ← DISCRIMINATOR"
        print(line)

    print()
    print("=" * 78)
    print("One full record per state")
    print("=" * 78)
    for state in sorted(states):
        fid, meta = next(((f, m) for f, m in by_state[state] if m), (None, None))
        if not meta:
            continue
        print(f"  --- {state} ({fid}) ---")
        for key, value in sorted(meta.items()):
            print(f"      {key:<24} {json.dumps(value, default=str)[:90]}")
        print()


if __name__ == "__main__":
    main()