-- What one replica of a model can actually serve, measured rather than guessed.
--
-- `llmgw ctl bench` has always been able to work this out — it ramps
-- concurrency until the SLO breaks and reports the last level that held. Until
-- now it printed that to a terminal and nothing kept it, so the one number that
-- says what a replica is worth lived in somebody's scrollback. Every decision
-- downstream then had to guess: admission uses a single global default for
-- healthy queue depth, and anything that wanted to size a model against real
-- demand had nothing to size against.
--
-- Keyed by model and profile, not by model alone. Capacity is a property of the
-- hardware and the engine arguments as much as of the weights: the same model
-- on a CPU profile and on an H100 profile are two different numbers, and
-- storing one would overwrite the other every time somebody benchmarked the
-- other kind of node.
--
-- The measurement is JSON for the same reason a model definition is: it is a
-- nested shape that is still growing, and as columns every field added to it
-- would be a migration.
--
-- Nothing here is authoritative about what a model may do — it is an
-- observation, with the time and the target it was taken from, so a reader can
-- decide whether it is still true. Hardware changes and engine builds change;
-- a capacity profile from six months ago is a hypothesis, not a fact.
CREATE TABLE capacity (
    model       TEXT NOT NULL,
    profile     TEXT NOT NULL,
    measurement TEXT NOT NULL,
    measured_at TIMESTAMP NOT NULL,
    measured_by TEXT NOT NULL DEFAULT '',
    PRIMARY KEY (model, profile)
);