bot: queued AI query interface + librarian AI review of results

Two connected features.

1) AI query interface (via the comm layer). communication_subroutine gains an
AI_QUERY_Q, a submit_ai_query() in-process entry point, and an authed
POST /ai_query endpoint ({prompt, channel_id, request_type?, username?}). The
prompt is queued and answered asynchronously by a new tasks.loop worker in the
always-loaded AI cog (Events), which calls handle_response - so it runs on
whichever backend $gadaj_teraz currently selects (GPT or Claude) - and posts the
answer to the requested channel, chunked to Discord's limit. request_type "NONE"
(default) is a clean one-shot: no persona system prompt, no memory write. The
worker starts before the OpenAI guard in cog_load, so it also runs on a
Claude-only box; cog_unload cancels it.

2) Librarian AI review. New command $wyszukaj_z_recenzja mirrors
$wyszukaj_linki_do_dokumentow but sets ai_review=True on the QueryControl, which
rides the round-trip and is matched back by UUID. When the hits return,
check_data_q sends the raw list as before, then - if flagged - hands the same
list (already in Crossref-relevance order) plus the search phrase to the AI
queue for a weighted re-rank and per-source review, delivered to the same
channel. QueryControl gains an ai_review flag (default False, so the orphan path
and all existing callers are unaffected).

Confirmed separately (and noted in the docs): the DOI list the AI receives is
pre-sorted by Crossref relevance - the librarian pipeline only filters (drops
title-less items) and splits (in-db / not-in-db), never re-sorts, and relies on
insertion-ordered dicts (Py 3.7+).

Verified: /ai_query auth (401/200/400/open), submit_ai_query and the queued
dict shape, and the QueryControl flag - via a Flask test client and
tests/integration/test_ai_query_endpoint.py (5 tests, all pass; integration
suite 11 passed, the 3 failures are the pre-existing /clear_pr_pls musician
tests fixed on a separate branch). Full first-party compile clean.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

docs/deployment/DOCKER_PROXMOX.md

@@ -20,6 +20,7 @@ The three talk to each other over HTTP on the Proxmox LAN. Direction of calls:
    bot  --(/query)-------------------------------->  librarian
 musician --(/prepped_tracks)-------------------->    bot
 librarian --(/conjurer results)----------------->    bot
+  *    --(/ai_query)----------------------------->    bot   (see 1c-ter)
 ```
 
 Everything is configured through `CONJURER_*` environment variables (see the
@@ -117,6 +118,23 @@ generation (`imaginuje sobie:`) and personal assistants stay on OpenAI whatever
 the switch says (Anthropic has no equivalent) and degrade quietly if OpenAI is
 not configured, so a Claude-only box still boots.
 
+### 1c-ter. AI query interface + librarian AI review
+
+The bot exposes a queued AI interface on its comm layer: `POST /ai_query` with
+`{"prompt": ..., "channel_id": <discord channel id>, "request_type"?: "NONE"}`
+(same `X-Conjurer-Api-Key` auth as the other endpoints). The prompt is queued and
+answered asynchronously by whatever backend `$gadaj_teraz` currently selects
+(GPT or Claude), and the answer is posted to `channel_id`. `request_type: "NONE"`
+(the default) keeps it a clean one-shot that doesn't touch the bar's
+conversation memory.
+
+The first consumer of this is the librarian command **`$wyszukaj_z_recenzja`**:
+it works like `$wyszukaj_linki_do_dokumentow`, but when the DOI hits come back
+the list (already sorted by Crossref relevance) plus the search phrase are handed
+to the AI for a weighted-relevance re-rank and a short source review, delivered
+to the same channel right after the raw results. No extra config — it uses the
+active AI backend.
+
 ### 1d. Configure and launch
 
 ```bash