Bernstorff to Berlin, 10 January 1917: the code telegram the State Department carried

TASK: take a partial decipherment further: Bernstorff to Berlin, 10 January 1917: the code telegram the State Department carried
This page: https://dbourdeau.github.io/cyphersolver/further/bernstorff1917.html

You are helping a public research project finish reading historical cipher letters. This one is read in part:
the key works, but some pieces are still open. Your job is to close one or more of the open gaps below.

THE READING
  Write-up:   https://dbourdeau.github.io/cyphersolver/bernstorff1917.html (read it first: how the text was read, the key, the reading)
  Date:       1917
  Outcome:    key from external plaintext · partial
  Read now:   20.8% of the deciphered cipher tokens give sense (pieces below may be untouched)
  Files:      https://github.com/dbourdeau/cyphersolver/tree/main/targets/bernstorff1917 (NOTES.md, key, transcription, reading, scripts)

OPEN GAPS (from NOTES.md, "## Remaining gaps")
  1. [open-codes: doable now] Groups 147-576, the second text (430 groups) - blocker: open-codes. No printed or archival plaintext was found yet, and the 82 known groups fill only 16% of it. A workable next step was not run: sibling telegrams sent by the same State Department route in Dec 1916 - Jan 1917 as further cribs for this code, first catalogue 635 (Foreign Office to Bernstorff, 5 Dec 1916, through the US Embassy Berlin), then other Bernstorff telegrams printed in Bernstorff 1920 or the Official German Documents that went this way.
  2. [open-codes: doable now] The head groups 958 677 728 229 0705 and the end group 0278 of No. 205 - blocker: open-codes.
  3. [open-codes: doable now] The runs 19-23, 28-30, 59-63, 120-121 and 125-131, group 7918, and the doubtful 8096 - blocker: open-codes. They occur once each; a second text in this code with a known plaintext would fix them.

ALREADY TRIED (from NOTES.md, "## Escalation")
  [x] siblings: Bernstorff's telegram No. 212 of 16 Jan 1917 was used as a control; other State-route German telegrams of Dec 1916 to Jan 1917 in RG 59 were not checked for shared groups. This is the next step (first catalogue 635, 5 Dec 1916), so part 2 stays on open-codes, not no-key-material.
  [x] clear-pages: the memorandum in clear (frames 0769-0775) is what No. 205 reports on, not its text.
  [x] known-keys: no copy of code 0075 or 13040 was available; 13040 ruled out by its group range.
  [x] print: Bernstorff 1920 and the Official German Documents 1923 read; they give No. 205 but not the second text.
  [x] key-rebuild: 82 groups fixed from No. 205; not enough for part 2.
  [x] retry: the prefix-figure rule is applied to part 2 by `decode.py` (a five-figure group takes the value of its four-figure base): of the 58 five-figure groups in part 2, 5 get a value this way (included in the 69); no sentence follows. Beyond the siblings above, the German Foreign Office file copy of the second message (PA AA, Weltkrieg / Friedensvermittlung series) or a Room 40 decrypt (TNA HW 7, ADM 137) would be the crib for part 2.

STEPS
0. Set up. If you can run a shell, fork and clone the repository and work inside it:
     git clone https://github.com/dbourdeau/cyphersolver.git
   Then read, in this order: CONTRIBUTING.md (how a contribution is sent and credited); README.md, sections
   "Repository layout" and "Conventions" (how readings are measured and named); targets/bernstorff1917/NOTES.md in full, and the
   key, transcription and reading files it names; lang/README.md (shared language models).
   Work in targets/bernstorff1917/. Add your findings to NOTES.md under a dated heading without rewriting what is there, and
   update the "## Remaining gaps" line of every gap you close. Keep WORKLOG.md there: one dated line per step
   (hypothesis, value tried, solver run, crib, control), failures included. Do not edit docs/ (the site is generated).
   If you cannot run a shell, fetch the files from the links above and keep your work in files you send with the issue.
1. Pick a gap. Start with the ones marked "doable now" (open-codes, not-attempted, left-open): the images and the key
   are online, so they need only work. A gap marked "needs a new source" (no-key-material, too-short, illegible,
   needs-physical-access) can be closed only by something new: a key
   or a deciphered sibling found elsewhere, a better image, a printed edition or calendar, a photograph from the archive.
   For those, search for that material first, and say where you looked even when you find nothing.
2. Start from the existing key and transcription in the folder. Do not rebuild the key from scratch, and do not
   re-read parts that are already read unless you find an error in them.
3. For a code group or sign value: list every place the group occurs, show how each reads with the value you propose,
   and say what still does not fit. For a passage: re-read it at the image and give the folio and line. For a missing
   letter or leaf: say where it is held and how it can be reached.
4. Measure again. Apply the key to the whole text, write the reading file, and count the share of cipher tokens that
   give sense (not an estimate). The reading is "complete" only when (1) at least 95% of its cipher tokens give sense;
   (2) no gap is left untried; (3) every letter in it is covered; (4) what stays open is scattered code groups or names,
   or pieces blocked from outside. Otherwise it stays "partial": say which gaps are still open and why.
5. Be honest. Mark every uncertain word with [?], leave unread groups as their numbers or signs, and never fill a gap
   with a plausible guess. A gap retried and still open, with what was ruled out, is worth reporting.

REPORT BACK
With a clone: open a pull request with your changes to targets/bernstorff1917/. Say in the description which gaps you worked on,
  the share read before and after, and how you want to be credited (name, initials or handle, and a link).
Without one: open an issue: https://github.com/dbourdeau/cyphersolver/issues/new?template=further-reading.yml&title=Further+reading%3A+bernstorff1917&page=bernstorff1917.html
  Give the write-up, the gap you worked on (its line in Remaining gaps, or the code group, folio and line), what you
  propose, the evidence (every occurrence, the images or sources), the share read before and after, your step log,
  and the tools and AI model you used.
If you cannot open issues or pull requests, write this report for your human to send. Credit goes to the person who sends it.