Interface
What other programs can rely on from lnk model.
lnk model
The commands of lnk model other programs read, each with its output
and who reads it.
lnk model runtime list --json
[{"name", "base_url", "models": ["..."], "added"?, "state"}], one
entry per runtime found at a default port, and one per address lnk model runtime add remembers, answering or not: name then the one it
was given, and added true. An address added at a runtime's default
port keeps that runtime's name while it answers, added true too.
state is running for one answering with models, no_models for one
answering with none, and not_answering for an added address nothing
answers at, its models empty: it's listed until lnk model runtime remove forgets it.
--start
With --start, it lists after starting an installed Ollama that isn't
running. Read by lnk agent start (--start: offers the models here,
Ollama's too when it was stopped).
lnk model serve --json
One line, {"url", "description"}, once it listens on a 127.0.0.1
port; it stops when its stdin closes. Exit status 2: no runtime here
serves the model named.
Its owner
Its stdin is how it follows its owner: the program that started it holds the other end, so when that program ends, however it ends, stdin closes. The port then closes at once, so a new connection is refused. A request it had already taken is still answered, for up to 10 seconds, and then the server ends.
A memory engine's model
lnk agent memory serve reads it for a memory engine's model, and
passes <url> to the engine as $LNK_MEMORY_MODEL, empty when serving fails
or when no line comes within 10 s.
Link Memory's --embed
Link Memory with --embed <model>, run outside a sandbox, reads it and
calls <url>/v1/embeddings while it serves; when serving fails it searches by
words and says lnk model install <model>.
lnk model list --fit --json
A list of model names, as lnk model list --json writes them, holding
the one model that suits this machine, or none where no local model
does. Read by lnk agent start, which offers to install it when no
model runs here.
lnk model install <model> --yes
Exit status 0 once the model is pulled and Ollama lists it. Read by
lnk agent start, which installs the local model picked.