Function recompile

openkb/cli.py:1559–1712

Re-run the current compile pipeline on already-indexed documents. Recompiling re-runs the same ``compile_short_doc`` / ``compile_long_doc`` that ``openkb add`` uses, so pre-feature KBs gain the ``entities/`` layer and pages refresh to the current format. It does NOT re-run PageIndex or

(ctx, doc_name, all_docs, dry_run, yes, refresh_schema)

@click.pass_context
@_with_kb_lock(exclusive=True)
def recompile(ctx, doc_name, all_docs, dry_run, yes, refresh_schema):
    """Re-run the current compile pipeline on already-indexed documents.

    Recompiling re-runs the same ``compile_short_doc`` / ``compile_long_doc``
    that ``openkb add`` uses, so pre-feature KBs gain the ``entities/`` layer
    and pages refresh to the current format. It does NOT re-run PageIndex or
    re-convert raw files — it reuses the on-disk ``wiki/sources/`` and
    ``wiki/summaries/`` content (and the registry's PageIndex ``doc_id``).

    DOC_NAME recompiles one doc (resolved like ``openkb remove`` — filename,
    slug, or unique substring). ``--all`` recompiles every indexed doc.
    Exactly one of DOC_NAME or ``--all`` is required.

    Side effect: this regenerates summaries (short docs) and rewrites concept
    pages with the current logic — manual edits to those pages are overwritten.
    """
    from openkb.state import HashRegistry

    kb_dir = _find_kb_dir(ctx.obj.get("kb_dir_override"))
    if kb_dir is None:
        click.echo("No knowledge base found. Run `openkb init` first.")
        return

    if all_docs and doc_name:
        click.echo("Specify either a DOC_NAME or --all, not both.")
        return
    if not all_docs and not doc_name:
        click.echo("Specify a document name or pass --all to recompile every doc.")
        return

    openkb_dir = kb_dir / ".openkb"
    wiki_dir = kb_dir / "wiki"
    registry = HashRegistry(openkb_dir / "hashes.json")

    # Resolve the set of docs to recompile.
    if all_docs:
        entries = list(registry.all_entries().values())
        if not entries:
            click.echo("No documents indexed yet. Run `openkb add` first.")
            return
        targets = entries
    else:
        matches = _resolve_doc_identifier(registry, doc_name)
        if not matches:
            click.echo(f"No document matching '{doc_name}' found in the KB.")
            click.echo("Try `openkb list` to see indexed documents.")
            return
        if len(matches) > 1:
            click.echo(f"'{doc_name}' matches multiple documents:")
            for _, m in matches:
                click.echo(f"  - {m.get('name', '?')}  (doc_name: {m.get('doc_name', '?')})")
            click.echo("Use a more specific name or the exact doc_name slug.")
            return
        targets = [matches[0][1]]

    def _classify(meta: dict) -> str:
        return "long" if _is_long_doc(meta) else "short"