llm-requests-mode
llm-requests-mode: *llm-requests*, every LLM request since the editor started, running first, with state, model, start time, how long it took and destination. dd on a row stops it; <CR> shows what it sent. Read-only; updates itself.
:llm-requests (<leader>aq) opens *llm-requests*: every request since the editor started, the running ones first, then the finished ones, newest first. Each row shows its state (streaming, retrying with the reason, awaiting review, ...), its model, the time it started, how long it took once it has finished, and where its answer is going (below main.rs:4, echo, register "a, a chat, a rewrite).
| Keys | Effect |
|---|---|
dd | Stop the request on this line, as <C-c> stops a chat's. An answer being written into a buffer keeps what arrived and ends with [interrupted]. |
<CR> | Show what the request on this line sent, every exchange of it, in *llm-inspect* beside the list. Works for any request of the run, finished or not. |
The list is read-only and keeps itself current: a request starting or finishing shows without a keystroke. :llm-stop (<leader>ak) stops the current buffer's request without opening the list. See llm-guide for retries and timeouts.