registry.py

"""
registry.py -- SINGLE SOURCE OF TRUTH for the GENOMIC specialists.

The Carbon analogue of agents/modmind/registry.py. Each entry is one mini
specialist trained on PURE domain data from HuggingFaceBio/carbon-pretraining-corpus
(the same corpus the 500M / 3B / 8B Carbon models were pretrained on).

The pitch: 4 dense ~80M DNA/RNA specialists (~320M total) + a zero-param
orchestrator < Carbon-500M on parameter count, while keeping per-domain
specialization crisp (one model never sees another domain's bases).

All specialists share ONE tokenizer (genomics/tokenizer.json), a Carbon-style
6-mer + single-base "length-max" vocab, so their latents live in the same space
and the RecursiveLink bridge / orchestrator can compare them directly.

To add a domain: add ONE entry here, then
    python genomics/build_tokenizer.py            # (only once; shared vocab)
    python genomics/train_specialist.py --domain <name>
"""

# Carbon corpus subsets -> mini specialists.
#   `config`  : the dataset config (subset) name on the Hub
#   `field`   : which column holds the sequence string (eukaryote uses `sequence`,
#               the evo2 subsets use `text`)
#   `molecule`: DNA or RNA -- metadata only (same ACGT/ACGU vocab, U folded to T)
#   `position`: chain slot (context-doubling order in the V2 config)
DATASET = "HuggingFaceBio/carbon-pretraining-corpus"

SPECIALISTS = {
    "eukaryote":   dict(config="eukaryote_generator_10B_subset", field="sequence",
                        molecule="DNA", vocab=4105, position=0),
    "prokaryote":  dict(config="prokaryote_evo2",                field="text",
                        molecule="DNA", vocab=4105, position=1),
    "mrna":        dict(config="mrna_evo2",                      field="text",
                        molecule="RNA", vocab=4105, position=2),
    "mrna_splice": dict(config="mrna_splice_evo2",              field="text",
                        molecule="RNA", vocab=4105, position=3),
}

# The specialists we are actively training (the genomic "foundation" set).
ACTIVE = ["eukaryote", "prokaryote", "mrna", "mrna_splice"]


def spec(name):
    if name not in SPECIALISTS:
        raise KeyError(f"unknown genomic specialist {name!r}; add it to "
                       f"registry.SPECIALISTS. known: {list(SPECIALISTS)}")
    return SPECIALISTS[name]


def text_of(name_or_spec, ex):
    """Extract the raw sequence string from a streamed example."""
    s = name_or_spec if isinstance(name_or_spec, dict) else spec(name_or_spec)
    return ex.get(s["field"], "") or ""