AiFailure
Why an AI call (com.siddharth.kmp.llmchat.AiProvider.complete or on-device OnDeviceLlm.generate) didn't produce text. Lives in :result — a zero-dependency module both the cloud (:llm-chat) and on-device (:ai) seams already sit downstream of conceptually — so neither invents its own error type and callers handling both seams share one when.
Entries
Link copied to clipboard
The key was rejected (401/403).
Link copied to clipboard
The provider is throttling (429).
Link copied to clipboard
On-device only: the model isn't downloaded/resident yet.
Link copied to clipboard
On-device only: this platform/backend can't run inference at all.
Link copied to clipboard
The call completed but the model returned no usable text.
Companion properties
Link copied to clipboard
Returns an immutable kotlin.enums.EnumEntries list containing the constants of this enum type, in the order they're declared.