mirror of
https://github.com/multica-ai/multica.git
synced 2026-08-13 03:15:34 +02:00
cd9f4147a5
Discovers the effort levels each Kimi model advertises, exposes them through the
existing per-model catalog, and applies an explicitly selected level over ACP
`session/set_config_option` before the prompt is sent.
Per-model efforts come from `kimi provider list --json`, not from a `session/new`
snapshot: that snapshot only ever describes the one model the session was created
with, so using it would leak one model's levels onto the rest of the catalog.
Effort selection is gated on Kimi CLI >= 0.29.0. Kimi 0.28.1 reports the same
supportEfforts as 0.33.0 but its ACP implements only an on/off toggle, answering
set_config_option("max") with success while confirming "on" — so the catalog alone
cannot tell whether the installed CLI can act on what it advertises. The gate reads
agentInfo.version from the ACP initialize response that discovery already makes, so
it costs no extra process. Below the floor, and on any build reporting no parsable
version, model discovery and task execution are unaffected and only the Thinking
control is hidden; Kimi is deliberately not added to the global MinVersions map.
Applying a level never blocks a task: a failed, unconfirmed, or mismatched
set_config_option logs a warning and sends the prompt anyway.
Closes #6059