Close first librarian promote round-trip + add --accept flag

scripts/librarian_promote.py gains a --accept flag that copies the
generated draft to the suggested docs/research/ target in the same
invocation. This is explicit per-invocation opt-in, not auto-apply:
the operator types --accept knowingly, the cp is still a deliberate
acceptance decision, just expressed in one command instead of two.

docs/research/option-a-bench-result.md is the first promoted note,
generated by gemini from
docs/archive/option-a-bench-result-2026-05-07.md and accepted
verbatim. Spot-check verified that cited file:line locations match
current source (traversal.pyx:473-475 and
inference_server.py:226-228 carry the cited code), the Last-verified
header reflects today's date and HEAD, and the durable conclusion
(sync-blocking policy boundary as the structural ceiling, not IPC
plumbing) is preserved.

This closes the end-to-end loop the librarian was designed for:
oversize check surfaced docs/performance.md, the routing pass split
durable analysis into the archive entry, the promote dispatcher
turned the archive entry into a research draft, and the human
accept step landed it as a tracked research note. Took one LLM call.

Removes the now-resolved ignore-list entry for
docs/research/option-a-bench-result.md (the file exists; the
forward reference is real).

scripts/librarian.sh exits 0 against the working tree.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

docs/plans/librarian.md

@@ -193,6 +193,10 @@ shells out to the LLM CLI selected by `LIBRARIAN_LLM`
 `runs/tmp/librarian-promote-<timestamp>-draft.md` for human review;
 the script never writes into `docs/research/` itself. `--show-prompt`
 prints the assembled prompt for inspection without calling the LLM.
+`--accept` is an explicit per-invocation opt-in that copies the draft
+to the suggested target as part of the same command — still
+propose-only by design (the operator chooses acceptance knowingly,
+not auto-applied).
 
 Refuses to run if:
 - the path is not under `docs/archive/`,
@@ -202,6 +206,20 @@ Refuses to run if:
 If the LLM judges the archive non-promotable, it is instructed to
 return a single line `SKIP: <reason>` instead of a draft.
 
+### First successful round-trip (2026-05-08)
+
+Smoke test against `docs/archive/option-a-bench-result-2026-05-07.md`
+with `LIBRARIAN_LLM=gemini` produced a draft that passed spot-check:
+`Last verified` header used today's date and the current commit
+(`8bbed31`); cited file paths and line numbers were verified as
+real (`traversal.pyx:473-475`, `inference_server.py:226-228`); code
+snippets matched current source; durable conclusion (sync-blocking
+policy boundary as the structural ceiling) preserved; ~60 lines of
+prose, no bullet soup. Accepted verbatim as
+`docs/research/option-a-bench-result.md`. The whole loop —
+oversize finding → extracted archive → LLM draft → human accept —
+closed without touching the LLM's output.
+
 ## Stage 2 remaining
 
 - MEMORY.md drift fixup mode (read drift report, propose one-line