`teach_model` called `seed_model_env(entry, "", value)` — no served name — so the
pod registered the entry under its `path`. For an ordinary model that is merely
untidy. For an ADAPTER it is fatal: a LoRA's path IS its base, so diogene-alpha
registered as cyankiwi/Qwen3.8-27B-AWQ-INT4 and collapsed into the base.

Measured on the live pod before the fix:

    taught https://…:22143 about 'diogene-alpha' (cyankiwi/Qwen3.8-27B-AWQ-INT4)
    catalogue: […, 'qwen38-awq']      diogene-alpha listed: False
    HTTP 404: Model 'diogene-alpha' is not available.

Taught successfully, still 404 — and the version of this where the base answers
under the adapter's name would have been silent.

With the name carried, the same pod registered it and served it. Verified by
repetition rather than by eye: each name is byte-identical across two runs at
temperature 0 and the two differ from each other, so they are backed by
different weights.

    diogene-alpha  sha 77f7db98ab19 ×2   (reasons, then answers)
    qwen38-awq     sha 4767ec4fcf00 ×2   (answers directly)

One pod, one copy of the weights, the adapter selected per request by name.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PxYHWbCAjjjD7A1rhFKtaW