docs: record the LazyVim profile and the auto-speak arming rule (Refs #36)

Neither setting did what it looked like it did, and the knowledge base had no
page for either, so both were invisible until the operator asked.

tools/neovim.md: the two entry points (vanilla `nvim`, `lazyvim` as an
NVIM_APPNAME profile), the fresh-box install, the base16 wallpaper-palette hook
with its SIGUSR1 contract, and the trap that matters — the official recipe
clones over ~/.config/nvim and destroys the vanilla quick-edit path.
tools/applications.md gets the editor row (Ghostty's row had lost its label)
and Neovim's verified version.

core/dankvoice.md gains the arming rule: arming is session-scoped, a silent
session start is a config state, and the two checks — `/say status` then
`pgrep -a pw-play` — prove the chain without blaming the endpoint.

kb-lint 0 violations, index-coverage 0 issues.

omp-docs/core/dankvoice.md

@@ -68,6 +68,19 @@ quick local speech, the package carries cloned-voice narration. The `tts`
 tool / `xd://tts` device reach frank-tts too, but produce files, not audio
 playback.
 
+## Arming auto-speak
+
+Arming is **session-scoped by design**: `/say on` arms the running session and
+is deliberately never persisted. A session that starts silent is a config
+state, not a fault — set `"auto": true` in `~/.omp/cache/dankvoice.json` (this
+fleet does) or export `DANKVOICE_AUTO=1` to start armed. Editing the settings
+file mid-session does nothing; the plugin reads it at startup.
+
+Two checks prove the chain, in order: `/say status` must report
+`auto-speak on` with a real endpoint (not `NO ENDPOINT`), and `pgrep -a pw-play`
+during a turn must show one player per spoken segment, `--target` set to the
+saved sink. Thinking narration rides the same arming (`thinking: true`).
+
 ## Limits
 
 * Auto-speak narrates thinking and the final message only — mid-turn tool