Skip to content

Navigation Menu

Sign in
Sign up

docs: this repository is an instrument utility, and publishes nothing else - #101

Draft
test1card wants to merge 14 commits into
master from
docs/instrument-only
Draft

docs: this repository is an instrument utility, and publishes nothing else #101
test1card wants to merge 14 commits into
master from
docs/instrument-only

Conversation

@test1card

@test1card test1card commented Aug 20, 2026
edited
Loading

Copy link
Copy Markdown
Owner

This repository is an instrument utility. The working relationship, the plans and the development directives are private and are not published here.

Removed, chosen by measurement rather than by feel. Both documents have ZERO references from tests/, governance/ and .github/, so they are the part of this direction that costs nothing to carry out today:

  • docs/OBLIGATIONS.md (17 782 bytes) — the register of owner directions. Removed rather than emptied, because an emptied register is still a statement about how the owner works.
  • docs/campaigns/MONTANA_CAMPAIGN_ARCHIVE.md (137 300 bytes) — campaign coordination history.
  • Earlier in this branch: an obligation row carrying a private clone URL, and an archive section that named a private location and listed its directories.

Both files were copied out byte-exactly and compared by hash before either was removed. Nothing is lost; it is simply not published.

Every pointer to them is removed as well, and no replacement says where they went — naming the place is the same mistake in a smaller font. Fourteen pointers across PROJECT_STATUS.md, README.md, ROADMAP.md, docs/DECISIONS.md, docs/MONTANA_IMPLEMENTATION_AGENT_SPEC.md and the two ASD-STE100 skill files now read "the obligations register", "kept outside this repository", or nothing at all. The obligation identifiers stay, because a reader who meets OB-012 in a comment needs to know it is a real thing with a name; what disappears is the path. The phase-1-status token that a trigger depends on is untouched, and its comment still forbids rewording it.

What is deliberately NOT in this change, and it is the larger half. The same direction reaches ROADMAP.md, AGENTS.md, docs/DECISIONS.md, docs/OPEN_CELLS.md, docs/CLAIM_CORRECTIONS.md and governance/agent_preventions.yaml. Those carry 27 references from tests, governance and continuous integration between them, and they are what the required checks read. Moving them is a separate change with a sequencing decision behind it, and it is not smuggled into this one.

Documentation only, no source change. tests/docs and tests/governance are green at 364 passed, the derived documentation pair is regenerated to a fixed point, and a repository-wide search for the removed paths returns nothing.

This change was prepared with AI assistance.

soak measurement added 6 commits August 20, 2026 17:57
...cribed here
Owner direction, 2026年08月20日: information about the private working layer belongs
only in that layer, and this repository is the laboratory instrument and nothing
else.
Two places in this repository described that layer, and both predate the
direction:
- `docs/OBLIGATIONS.md` carried a row whose whole subject was the layer's
 private remote, including its clone URL. The register is append-only by its
 own rule, and the direction overrides that rule for this row: it is removed
 rather than restated with a changed status, because a status change would keep
 the text.
- `docs/campaigns/MONTANA_CAMPAIGN_ARCHIVE.md` carried a section describing the
 layer by name and enumerating its internal directories and what each one
 holds.
Both are removed. What is NOT removed, and the distinction is deliberate: the
places that say directions are registered in this repository and that a working
corpus existed outside it. Those are statements about how THIS repository is
governed, they name nothing and describe no structure, and removing them would
delete the reason the obligations register exists.
Documentation only, no source change. `tests/docs` and the agent-guidance
cross-reference guard are green at 70 passed.
...repository
Owner, 2026年08月20日: everything private -- the working relationship, the plans and
the development directives -- is stored privately, and this repository is an
instrument utility and nothing more.
TWO DOCUMENTS ARE REMOVED, and they were chosen by measurement rather than by
feel: both had ZERO references from tests, governance and continuous
integration, so they are the part of this direction that costs nothing to carry
out today.
- `docs/OBLIGATIONS.md`, 17782 bytes -- the register of owner directions. It is
 removed rather than emptied, because an emptied register is still a statement
 about how the owner works.
- `docs/campaigns/MONTANA_CAMPAIGN_ARCHIVE.md`, 137300 bytes -- campaign
 coordination history.
Both were copied out byte-exactly and compared by hash before either was
removed here. Nothing is lost; it is simply not published.
EVERY POINTER TO THEM IS REMOVED TOO, and none of the replacements says where
they went -- naming the place is the same mistake in a smaller font. Fourteen
pointers across `PROJECT_STATUS.md`, `README.md`, `ROADMAP.md`,
`docs/DECISIONS.md`, `docs/MONTANA_IMPLEMENTATION_AGENT_SPEC.md` and the two
ASD-STE100 skill files now say "the obligations register", "kept outside this
repository", or nothing at all. The obligation identifiers stay, because a
reader who meets OB-012 in a comment needs to know it is a real thing with a
name; what disappears is the path.
The one token that a trigger depends on -- `phase-1-status` in `ROADMAP.md` --
is untouched, and its comment still forbids rewording it.
WHAT IS NOT DONE HERE, and it is the larger half. The same direction reaches
`ROADMAP.md`, `AGENTS.md`, `docs/DECISIONS.md`, `docs/OPEN_CELLS.md`,
`docs/CLAIM_CORRECTIONS.md` and `governance/agent_preventions.yaml`, which
together carry 27 references from tests, governance and continuous integration
and are what the required checks read. Moving those is a separate change with a
sequencing decision behind it, and it is not smuggled into this one.
Documentation only, no source change. `tests/docs` and `tests/governance` are
green at 364 passed with the derived pair regenerated.
Fourteen pointers across PROJECT_STATUS.md, README.md, ROADMAP.md,
docs/DECISIONS.md, the implementation spec and the two ASD-STE100 skill files
now say the obligations register, or kept outside this repository, or nothing --
never a path. Naming the place is the same mistake in a smaller font.
The obligation identifiers stay: a reader who meets OB-012 in a comment needs to
know it is a real thing with a name. What disappears is the path. The
phase-1-status token a trigger depends on is untouched, and its comment still
forbids rewording it.
@test1card test1card changed the title (削除) docs: this repository is the instrument, and does not describe anything else (削除ここまで) (追記) docs: this repository is an instrument utility, and publishes nothing else (追記ここまで) Aug 20, 2026

Copy link
Copy Markdown
Owner Author

@codex review

Head is 8051984edf4d752297070bdd5ada657efdc84ca5. Documentation only, no source change.

Two documents leave the repository and every pointer to them is rewritten so that none names a path. The two were selected by measurement: both had zero references from tests/, governance/ and .github/, which is why this change cannot move a required check.

Please look hardest at three things:

  1. A pointer I missed. A search for OBLIGATIONS.md and MONTANA_CAMPAIGN_ARCHIVE over the tree returns nothing, but a reference spelled differently — a bare docs/campaigns/ directory mention, a relative link, a path split across a line break — would not be caught by that search.
  2. A claim that no longer has a source. Several documents cited those two files as the authority for a statement. Where the citation is now "the obligations register", the statement still has to be true and still has to be checkable by someone who cannot read that register.
  3. The phase-1-status token in ROADMAP.md. A registered obligation keys its trigger to that exact string. It is untouched, and the comment forbidding a reword is untouched, but that is the one thing in this change whose breakage would be silent.

tests/docs and tests/governance are green at 364 passed, and the derived documentation pair is regenerated to a fixed point.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 8051984edf

i️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Comment thread docs/DECISIONS.md Outdated
Comment on lines +394 to +396
guard. Owner directions that are deferred behind trigger conditions are
registered in `docs/OBLIGATIONS.md` — the register is the single home for such
directions and repository search must be able to find them.
registered outside this repository, in one place, so that no direction depends
on being remembered.

@chatgpt-codex-connector chatgpt-codex-connector Bot Aug 20, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Badge Supersede the owner decision instead of rewriting it

This rewrites an existing [Owner] decision from keeping obligations in-tree to keeping them outside the repository, while its unchanged heading still says they are "registered in-tree." Because docs/DECISIONS.md is explicitly append-only, this both erases the historical decision and leaves the current source of truth internally contradictory; restore the original entry and record the move in a new superseding decision.

AGENTS.md reference: AGENTS.md:L52-L58

Useful? React with 👍 / 👎.

Comment thread ROADMAP.md Outdated
Comment on lines +838 to +839
this token to phase-1-status=DONE. A registered obligation keys its trigger
to that exact token; do not reword it, translate it, or let an STE rewrite

@chatgpt-codex-connector chatgpt-codex-connector Bot Aug 20, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Badge Keep OB-002 attached to the phase trigger

When this marker eventually changes to DONE, a repository-only reader can no longer determine that OB-002—the adaptation-skill obligation—is what fired, because the rewrite replaced the identifier with an anonymous "registered obligation" and the register is no longer readable here. Preserve the OB-002 identifier and enough of its required action beside the marker so completing Phase 1 cannot silently strand the deferred direction.

Useful? React with 👍 / 👎.

Comment thread docs/skills/asd-ste100/SKILL.md Outdated

**Will not:**
- Rewrite archived, evidence, or verbatim-quoted text (repository note: in this repository, `docs/campaigns/` archives, quoted owner/reviewer words, and anything fenced `<!-- verbatim:begin -->`...`<!-- verbatim:end -->` are byte-faithful records — an STE pass over them destroys exactly what they exist to preserve; see OB-012 in `docs/OBLIGATIONS.md`).
- Rewrite archived, evidence, or verbatim-quoted text (repository note: in this repository, `docs/campaigns/` archives, quoted owner/reviewer words, and anything fenced `<!-- verbatim:begin -->`...`<!-- verbatim:end -->` are byte-faithful records — an STE pass over them destroys exactly what they exist to preserve; this is OB-012 in the obligations register).

@chatgpt-codex-connector chatgpt-codex-connector Bot Aug 20, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Remove the surviving campaign-directory pointers

This changed exemption still points to docs/campaigns/, even though deleting the archive removes that directory. A repository-wide search also finds the same stale path in ROADMAP.md, README.md, README.ru.md, PROJECT_STATUS.md, and docs/architecture.md; readers therefore still see a path that resolves nowhere, and the intended path-free rewrite is incomplete.

Useful? React with 👍 / 👎.

Comment thread ROADMAP.md
Comment on lines 144 to +146
The owner-ratified P0-P9 plan that stood here is campaign history. It moved
verbatim, with provenance, to `docs/campaigns/MONTANA_CAMPAIGN_ARCHIVE.md`
(section "Owner-ratified P0-P9 plan, extracted from ROADMAP.md").
`docs/OPEN_CELLS.md` is the live disclosure register; it wins on any
verbatim, with provenance, into the campaign record kept outside this
repository. `docs/OPEN_CELLS.md` is the live disclosure register; it wins on any

@chatgpt-codex-connector chatgpt-codex-connector Bot Aug 20, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Retain the P9 rule that derives the roadmap state

Moving the only full P9 definition outside the repository leaves the subsequent MERGED_P9_OPEN conclusion unverifiable for a repository-only reader: the listed facts remain visible, but the rule that maps those facts to that outcome and defines MERGED_CHECKPOINT was present only in the deleted archive. Because the post-Montana programme below uses this outcome to decide which work may start, retain a self-contained summary of the P9 decision and closure criteria here rather than requiring access to the external campaign record.

Useful? React with 👍 / 👎.

soak measurement added 2 commits August 20, 2026 18:27
Four review findings, and the first one is the sharpest: I rewrote an
append-only owner decision in place.
AN APPEND-ONLY LOG IS NOT EDITED. `docs/DECISIONS.md` says so about itself, and
I changed a 2026年08月09日 entry from "obligations are registered in-tree" to the
opposite while leaving its heading claiming the original. That both erased the
decision and left the file contradicting itself. The body is now WITHDRAWN with
the heading kept, so the sequence has no silent gap and no edited entry claims
to be the original, and a new dated entry records the supersession and why the
earlier decision was made -- it solved a real failure and traded it for a worse
one.
A TRIGGER LOST THE NAME OF WHAT IT FIRES. The `phase-1-status` token is keyed by
OB-002, and the rewrite replaced that identifier with an anonymous phrase. A
reader of this repository could then flip the token to DONE and strand the
deferred direction with no way to know what it was. The identifier is back, and
enough of the required action stands beside it to act on without reading
anything else.
A DERIVATION LOST ITS RULE. The roadmap derives the outcome MERGED_P9_OPEN and
then uses it to decide which work may start, but the rule mapping facts to that
outcome lived only in the removed archive. The bounded-cycle rule and all three
terminal outcomes are restated here in full.
AND THE PATH-FREE REWRITE WAS INCOMPLETE. `docs/campaigns/` is now an empty
directory and six files still pointed at it: PROJECT_STATUS.md, README.md,
README.ru.md, ROADMAP.md, docs/architecture.md and the ASD-STE100 skill. None
does now.
The Russian sentences were edited through UTF-8 and read back afterwards, which
is the only way to know a Windows tool did not eat them.
`tests/docs` and `tests/governance` are green at 365 passed.

Copy link
Copy Markdown
Owner Author

@codex review

Head is b851b660c4481aa1e476480dc644b0735b41ec5b. All four findings are closed, and the first one was the sharpest.

  • I rewrote an append-only entry in place. docs/DECISIONS.md says that about itself, and I changed a 2026年08月09日 decision to its opposite while leaving the heading claiming the original. The body is now WITHDRAWN with the heading kept — so the sequence has no silent gap and no edited entry pretends to be the original — and a new dated entry records the supersession, including why the earlier decision was made: it solved a real failure and traded it for a worse one.
  • OB-002 is back beside the phase-1-status token, with enough of its required action stated there to act on. Flipping that token to DONE can no longer strand a direction whose name the reader cannot recover.
  • The bounded-cycle rule is restated in full, all three terminal outcomes included, so the MERGED_P9_OPEN derivation below it is checkable without reaching for anything outside this repository.
  • docs/campaigns/ is empty and nothing points at it now — the six files you named are all fixed. Your search was right and mine was too narrow: I had searched for the two file names, not for the directory.

The Russian sentences in PROJECT_STATUS.md and README.ru.md were edited through UTF-8 and read back afterwards; one of them also needed rewording rather than substitution, because dropping the path left the clause ungrammatical.

tests/docs and tests/governance are green at 365 passed, and the derived documentation pair is regenerated to a fixed point.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: b851b660c4

i️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Comment thread docs/DECISIONS.md Outdated
Comment on lines +391 to +395
**The body of this entry is removed, and the heading stays so that the sequence
of decisions has no silent gap.** Its subject was how the owner's own working
material is organised, which the decision below places outside this repository.
Rewriting the entry in place would have been worse than removing it: this file
is append-only, and an edited entry claims to be the original.

@chatgpt-codex-connector chatgpt-codex-connector Bot Aug 20, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Badge Restore the original decision before superseding it

Fresh evidence at this head is that the replacement now explicitly says the 2026年08月09日 body was removed; retaining only its heading and a summary still rewrites this append-only log and erases the original claims about the workspace, register, and byte-exact migration evidence. Keep that entry intact and add the 2026年08月20日 supersession after it, as the repository contract requires.

AGENTS.md reference: AGENTS.md:L52-L58

Useful? React with 👍 / 👎.

Comment thread ROADMAP.md
Comment on lines +159 to +161
> after P5; or the integration topology differs from P2. **MERGED_P9_OPEN:**
> `master` has already been fast-forwarded at P9, but a post-fast-forward check
> or settings verification fails.

@chatgpt-codex-connector chatgpt-codex-connector Bot Aug 20, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Retain the P9 success criteria in the roadmap

Fresh evidence at this head is that the added summary still defines only MERGED_P9_OPEN, while the conclusion below invokes the unavailable archived P9 definition and the roadmap later uses that outcome to decide what may start. The deleted P9 rule additionally required host migration, native workflow binding, and a successful post-fast-forward protected run before yielding MERGED_CHECKPOINT; without those success criteria, a repository-only reader cannot verify when this residual is closed, so retain that boundary alongside this summary.

AGENTS.md reference: AGENTS.md:L44-L50

Useful? React with 👍 / 👎.

Comment thread docs/DECISIONS.md Outdated
Comment on lines +402 to +405
The working relationship, the plans, and the development directives are private.
They are not published here. This repository is an instrument utility: the
software, its tests, its guards, and the disclosure a user of the instrument
needs.

@chatgpt-codex-connector chatgpt-codex-connector Bot Aug 20, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Badge Make the privacy boundary match what remains published

For anyone with access to this repository, this new privacy claim is not true: the current file still publishes verbatim owner development directives and working-relationship rules in the preceding entries (for example, the PR and publication instructions at lines 330-387), and the deleted obligations and campaign archive remain retrievable from the parent commit with ordinary Git history. If these materials are genuinely private, deleting them only from the tip is insufficient; otherwise narrow this decision so it does not assert that retained and historically accessible material is unpublished.

AGENTS.md reference: AGENTS.md:L546-L549

Useful? React with 👍 / 👎.

Comment thread README.md Outdated
Comment on lines +123 to +124
The qualification refactor (merged 2026年07月31日; campaign records in
`docs/campaigns/`) moved CryoDAQ toward narrower ownership, explicit
archived outside this repository) moved CryoDAQ toward narrower ownership, explicit

@chatgpt-codex-connector chatgpt-codex-connector Bot Aug 20, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P3 Badge Remove the dangling preposition in the README

When a reader reaches the primary English project overview, this edit now reads "campaign records in archived outside this repository," which is grammatically incomplete and makes the archive-location statement unnecessarily hard to parse. Remove the surviving in or rephrase the parenthetical as "campaign records archived outside this repository."

Useful? React with 👍 / 👎.

soak measurement added 2 commits August 20, 2026 18:51
Owner, 2026年08月20日: no internal names in this repository, only explicit
understandable ones.
An identifier like OB-012 names nothing to a reader who cannot open the register
it belongs to, and that register is not published here. Worse, it LOOKS like a
name, so a reader stops there instead of asking what the thing is. Seven places
in ROADMAP.md and the two documentation-skill files now say what the direction
requires -- moving the build host and binding the workflow natively; using
Simplified Technical English for project documentation; building the
in-repository adaptation skill -- and none of them says a number.
The trigger comment beside phase-1-status keeps the full statement of what it
defers, which is what stops the token being flipped and the work stranded. That
was the reason the number was there, and the statement does the job the number
could not.

Copy link
Copy Markdown
Owner Author

@codex review

Head is 3d16c56fdb54d76372900d1ae33446d023507226. This head reverses part of the previous round on the owner's instruction, and the reversal is worth stating plainly rather than letting it look like drift.

Your finding asked me to keep the OB-002 identifier beside the phase-1-status trigger so completing that phase could not silently strand the deferred direction. I did. The owner then directed that this repository carry no internal names at all, only explicit understandable ones.

The finding's concern is still met, by the other half of that fix. An identifier like OB-002 names nothing to a reader who cannot open the register, and the register is not published here — so it looks like a name and stops the reader from asking what the thing is. What stops the direction being stranded is the full statement of what it defers, which is beside the trigger and stays. Seven places now say what the direction requires — moving the build host and binding the workflow natively; using Simplified Technical English for project documentation; building the in-repository adaptation skill — and none says a number.

What this change does NOT touch, measured on this branch: the OC- row keys of docs/OPEN_CELLS.md (224 occurrences across 26 files, and the freshness guards match on the literal row prefixes), and the internal codename that appears in eight tracked paths and about 195 occurrences, all of which the machinery reads. Both are the same direction and both are larger changes with a sequencing decision behind them.

tests/docs and tests/governance are green at 365 passed, and the derived documentation pair is regenerated to a fixed point.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 3d16c56fdb

i️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Comment thread docs/DECISIONS.md Outdated
Comment on lines +415 to +417
**Obligation identifiers stay in this repository** wherever a reader needs to
know that a deferred direction exists — the identifier and enough of its action
to act on. What does not appear is a path, a location, or a name.

@chatgpt-codex-connector chatgpt-codex-connector Bot Aug 20, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Record the no-identifier decision consistently

At this head, the latest ROADMAP change follows the owner's instruction to remove internal obligation identifiers, but this authoritative owner decision still requires agents to retain those identifiers wherever a deferred direction exists. The conflict is already concrete: repository-wide search still finds the now-unresolvable OB-006 in docs/OPEN_CELLS.md, tests/release/test_whole_tree_artifact_freshness.py, and several tools/ci_* comments. Because future agents must treat this log as a durable source of owner direction, they can legitimately reintroduce the identifiers that this round removed; append a superseding decision that records the no-identifiers instruction and replace the remaining obligation references with explicit descriptions.

AGENTS.md reference: AGENTS.md:L52-L58

Useful? React with 👍 / 👎.

Comment thread docs/skills/asd-ste100/SKILL.md Outdated

**Will not:**
- Rewrite archived, evidence, or verbatim-quoted text (repository note: in this repository, `docs/campaigns/` archives, quoted owner/reviewer words, and anything fenced `<!-- verbatim:begin -->`...`<!-- verbatim:end -->` are byte-faithful records — an STE pass over them destroys exactly what they exist to preserve; see OB-012 in `docs/OBLIGATIONS.md`).
- Rewrite archived, evidence, or verbatim-quoted text (repository note: in this repository, quoted owner/reviewer words and anything fenced `<!-- verbatim:begin -->`...`<!-- verbatim:end -->` are byte-faithful records — an STE pass over them destroys exactly what they exist to preserve, which the standing documentation direction excludes for that reason).

@chatgpt-codex-connector chatgpt-codex-connector Bot Aug 20, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P3 Badge Split the changed skill boundary into short instructions

When this edited bullet is treated as new or changed project documentation, it violates the documentation contract it is meant to enforce: the sentence contains 46 words, while the Core Rewrite Rules in this same file limit instructions to 20 words and require one instruction per sentence, and ROADMAP.md states that new and changed English text must conform immediately. Split the prohibition from its repository-specific rationale so the checked-in binding skill does not demonstrate a direct counterexample to its own required form.

Useful? React with 👍 / 👎.

soak measurement added 2 commits August 20, 2026 19:40
Five review findings, and one of them says my own text was untrue.
THE PRIVACY CLAIM WAS WRONG, AND I CHECKED IT RATHER THAN ARGUING. Removing a
file from the current tree does not remove it from the repository: the campaign
archive is still 1721 lines away through ordinary git history, and after this
merges those commits stay ancestors of master. Entries above the new one also
still publish owner directions verbatim. So the decision now says what it
actually is -- a decision about what is WRITTEN here from now on -- and states
plainly that closing the rest would take a history rewrite or a change of
repository visibility, both of which are outward acts and belong to the owner.
THE APPEND-ONLY ENTRY IS RESTORED INTACT. I had removed its body and kept the
heading, which still rewrites an append-only log. It is back byte-faithful, with
the supersession appended after it where the contract says supersession goes.
That created a real conflict with the dead-path guard, because the restored entry
names a file this same change removes. **I did not edit the record to make the
check pass** -- an append-only log whose entries are rewritten to satisfy a check
stops being a record. The entry is fenced with the byte-faithful markers the
documentation skill already defines, and the guard now skips those fences for the
dead-path scan and for nothing else. Proved both ways: a dead path in ordinary
text still reddens; the same path inside a fence does not.
THE NO-IDENTIFIER INSTRUCTION IS NOW A DECISION, not only an edit. Without that,
this log still told a future agent to keep identifiers, so the next agent could
legitimately put back what this round removed. The entry also records what the
retrofit has NOT reached and how large it is, so the remaining identifiers read
as work in progress rather than as a contradiction.
THE ROADMAP KEEPS THE WHOLE TERMINAL BOUNDARY. The summary defined only the open
outcome, so a repository-only reader could see the conclusion but not the
criteria that close it. All three conditions are stated.
AND TWO SMALLER ONES: the README sentence lost a preposition and read
"campaign records in archived outside this repository"; and the skill's own
exemption bullet was a 46-word sentence inside a file whose rules limit an
instruction to 20 words and one instruction per sentence. It is four short
instructions and a separate rationale now.
`tests/docs` is green at 68 passed.

Copy link
Copy Markdown
Owner Author

@codex review this pull request at head 3e3b770285fcdc4eae074f1f16fd641ca7a67d13.

This head has been sitting without a review request since it was pushed; the last review names an earlier commit. Nothing has changed on the branch since. Zero review comments are anchored to this commit.

This is the privacy repair: it removes the internal register and the campaign archive from the public tree. Please check that nothing it leaves behind still names internal-only material, and that no reference it removes was load-bearing for something the repository still reads.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 3e3b770285

i️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Comment on lines +153 to +155
engineering, review, and publication checklist" was campaign-local, is kept
outside this repository as history, and is superseded by
`ROADMAP.md`/`PROJECT_STATUS.md` for anything still open;

@chatgpt-codex-connector chatgpt-codex-connector Bot Aug 23, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Remove the remaining private scratchpad dependencies

In a fresh or public checkout, this revised startup block still directs agents at line 159 to read scratchpad/montana/exec/implementation_agent_doc_requests.md, while a repository-wide search finds 11 tracked references to scratchpad/montana and no corresponding tracked files; production docstrings and the refactor report likewise point readers to that private campaign layer. Consequently the repair still names internal-only material and makes unavailable external records inputs to repository work; replace those references with the necessary in-tree rationale or remove them.

AGENTS.md reference: AGENTS.md:L76-L80

Useful? React with 👍 / 👎.

Comment thread docs/DECISIONS.md
Comment on lines +448 to +451
**The retrofit is not complete and its size is measured.** The `OC-` row keys of
`docs/OPEN_CELLS.md` are 224 occurrences across 26 files, and the documentation
freshness guards match those literal row prefixes; the campaign codename is in
eight tracked paths, every one of which is read by tests, tools or continuous

@chatgpt-codex-connector chatgpt-codex-connector Bot Aug 23, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Correct the measured campaign-name inventory

At this exact head, git grep -Il Montana returns 26 tracked paths and a case-insensitive search returns 51, not eight; examples include PROJECT_STATUS.md, AGENTS.md, production modules, tests, and tools. Because this newly recorded measurement scopes the remaining privacy retrofit, understating it can cause the cleanup to stop while many campaign-name references remain, and the claim also lacks the exact command and immutable-object binding required for a current count.

AGENTS.md reference: AGENTS.md:L445-L450

Useful? React with 👍 / 👎.

Comment on lines 1740 to +1743
continue
if p.startswith(_EXEMPT_SOURCE_PREFIXES):
continue
text = _read(REPO_ROOT / p)
text = _VERBATIM_BLOCK_RE.sub("", _read(REPO_ROOT / p))

@chatgpt-codex-connector chatgpt-codex-connector Bot Aug 23, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Add a regression that prevents republishing the private files

If a later change restores docs/OBLIGATIONS.md or the campaign archive, this modified test remains green because it checks only whether referenced paths exist; once either private file is restored, its references resolve, and no other repository guard rejects the publication. The change describes the prior publication as a confirmed, machine-testable privacy mistake, so add a negative-control regression that rejects those private paths or equivalent tracked register/archive material rather than relying on deletion at this one head.

AGENTS.md reference: AGENTS.md:L358-L365

Useful? React with 👍 / 👎.

Comment thread ROADMAP.md Outdated
Comment on lines +603 to +605
The direction requiring it, and the decision on what it covers, are recorded
outside this repository; this entry is the plan for the retrofit of the EXISTING
corpus.

@chatgpt-codex-connector chatgpt-codex-connector Bot Aug 23, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Keep the binding documentation scope in the repository

For a repository-only documentation change, this rewrite makes the governing scope unavailable: the deleted OB-012 row was the only place specifying that client-facing and agent-layer English were governed while Russian text, verbatim evidence, archives, and changelog history were exempt. The remaining roadmap still says new text conforms "per the obligation" and later points readers to "its disposition list," but neither source is now readable here, so an agent cannot determine what must be rewritten or protected from rewriting. Retain that public scope and its dispositions in an authoritative in-tree document without the private register identifier.

AGENTS.md reference: AGENTS.md:L44-L58

Useful? React with 👍 / 👎.

This repository is an instrument. It publishes the instrument and nothing else.
All tracked references to the private working area are removed, including tool
inputs and outputs and the code, test and documentation mentions of it.
The correction row is bound to an immutable head rather than to a moving count:
at 3e3b770 the case-sensitive count is 26 and
the case-insensitive count is 51.
A documentation-gate regression now refuses the restoration of the removed
register, the campaign archive, or any private reference, so this cannot come
back by accident.
The roadmap states the binding English-documentation scope and its exemptions in
the tree, rather than leaving them implied.
Deletion does not undo history: the removed content stays readable through git
history, and closing that needs a history rewrite or a visibility change, which
are the owner's to make.
Written with AI assistance.

Copy link
Copy Markdown
Owner Author

@codex review this pull request at head 1647b2f63781067a8f4f73ebc0ed07b5f8fd0834.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 1647b2f637

i️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

verdict="conditional-pass-with-P3-findings",
whole_file=True,
evidence="scratchpad/montana/exec/fable_runs/FABLE-BOUNDARY-01-20260719.md",
evidence="External review record is not published.",

@chatgpt-codex-connector chatgpt-codex-connector Bot Aug 27, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Badge Stop granting coverage without the preserved review report

This run still sets whole_file=True, so when a current file matches the recorded commit, the loop adds it to whole_file["fable"] even though the evidence field now confirms that no report is available for verification. Running this ledger can therefore grant whole-file coverage to the 26 assistant/reporting paths from an unavailable transcript; remove the run from coverage, as was done for WORKTREE_REVIEW_RUNS, or validate a persisted hash-bound report before applying it.

AGENTS.md reference: AGENTS.md:L163-L165

Useful? React with 👍 / 👎.

Comment on lines +1721 to +1725
_PRIVATE_PUBLICATION_PATHS = frozenset(
{
"docs/OBLIGATIONS.md",
"docs/campaigns/MONTANA_CAMPAIGN_ARCHIVE.md",
}

@chatgpt-codex-connector chatgpt-codex-connector Bot Aug 27, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Reject renamed copies of the private documents

Fresh evidence at this head is that the new publication guard checks only the two former exact path names. If the obligation register or campaign archive is restored as, for example, docs/directions.md, and it contains no old scratchpad reference, _private_publication_violations() returns no violation, so the regression stays green despite republishing the same private material. Add a negative control and a content/root-level invariant that survives renaming rather than treating the deleted filenames as the privacy boundary.

AGENTS.md reference: AGENTS.md:L361-L365

Useful? React with 👍 / 👎.

if p.startswith(_EXEMPT_SOURCE_PREFIXES):
continue
text = _read(REPO_ROOT / p)
text = _VERBATIM_BLOCK_RE.sub("", _read(REPO_ROOT / p))

@chatgpt-codex-connector chatgpt-codex-connector Bot Aug 27, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Restrict the verbatim exemption to immutable records

Applying this substitution to every tracked Markdown file creates an unrestricted opt-out from the dead-path guard: a newly added or edited document can wrap a misspelled backtick path in the generic verbatim fences, and the entire block disappears before validation. Nothing checks that the block is an immutable historical record rather than current instructions, so the gate can remain green while actionable documentation points to a missing file; constrain the exemption to the intended append-only source/section and add a negative control for fenced current prose.

AGENTS.md reference: AGENTS.md:L361-L365

Useful? React with 👍 / 👎.


ROOT = Path(__file__).resolve().parents[1]
OUTPUT = ROOT / "scratchpad" / "montana" / "exec" / "fable_review_map.md"
OUTPUT = ROOT / ".audit-run" / "review-ledgers" / "fable_review_map.md"

@chatgpt-codex-connector chatgpt-codex-connector Bot Aug 27, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Keep audit ledgers in the evidence review lane

Moving the generated ledger to .audit-run changes its classification without updating _review_lane: because the path ends in .md and .audit-run/ is not recognized, both this output and the dual-review ledger are now assigned to R09 (canonical product/operator documentation) instead of the former R10 historical/generated-evidence lane. The generators explicitly inventory these output paths, so their review maps now misstate non-authoritative audit evidence as canonical documentation; classify .audit-run/ as evidence before the generic Markdown rule.

AGENTS.md reference: AGENTS.md:L76-L80

Useful? React with 👍 / 👎.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@chatgpt-codex-connector chatgpt-codex-connector[bot] chatgpt-codex-connector[bot] left review comments

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

AltStyle によって変換されたページ (->オリジナル) /