Repository navigation
[instructions] Split experimental ledger docs out of memory.md - #67685
Open
github-actions[bot] wants to merge 1 commit into
Open
github-actions[bot] wants to merge 1 commit into
github-actions[bot] wants to merge 1 commit into
Conversation
memory.md had grown to 407 lines, over the 400-line instruction-file cap, after recent repo-memory JSON-schema-validation changes (#67439). Extract the self-contained "standalone ledger (experimental)" section into a new ledger.md, replacing it with a short pointer. Update the cross-reference in memory-stateful-patterns.md to link directly to ledger.md instead of an anchor inside memory.md. debug-agentic-workflow.md is also over the cap (432 lines) after recent model/engine-misconfiguration diagnostics (#67488), but its checklist content is pinned inline by a regression test (.github/skills/agentic-workflows/tests/test_guidance.py) that also requires it mirrored in root debug.md, so it is left as a documented exception rather than split. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This was referenced Oct 11, 2026
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Instructions Janitor: sync memory/ledger docs
Scope: reviewed every commit touching
.github/aw/anddocs/since the lastinstructions-janitor sync (
eca67cf, #67162) through the current.github/aw-touchingtip (
9ded002, #67488). The latest published release is v0.89.21 (2026-09-23); this repohas had several incremental instruction syncs since then, so this pass picks up from the
last one rather than re-reviewing the full release window.
Files reviewed:
.github/aw/memory.md(touched by Add declarative JSON schema validation for memory #67439, repo-memory JSON-schema validation).github/aw/work-queue.md(touched by Make AW work queues auto-bootstrap and evolve workers durably #67322, Clarify why the ESLint factory cannot dispatch workers #67217, Use repository labels for work-queue Issue status #67223 — auto-bootstrap, Issuelabels, ESLint-factory dispatch clarification) — read in full, content is accurate and
within size budget; no changes needed
.github/aw/debug-agentic-workflow.mdand.github/aw/debug-security-review.md(touched by Make AW work queues auto-bootstrap and evolve workers durably #67322, Add model and engine misconfiguration diagnostics to agentic-workflows #67488) — read in full;
debug-security-review.md's work-queuereference already matches the auto-bootstrap behavior
.github/aw/create-agentic-workflow.md,.github/aw/github-agentic-workflows.md,.github/aw/network.md(touched by Strengthen workflow recommendation guidance #67468) — read in full, coherent and within budgetSize audit
.github/aw/memory.mdhad grown to 407 lines (over the 400-line cap) after #67439 addedJSON-schema validation docs. Fix: extracted the self-contained "standalone ledger
(experimental)" section into a new
.github/aw/ledger.md(68 lines), leaving a shortpointer in
memory.md(now 359 lines) and updating thememory-stateful-patterns.mdcross-reference to link
ledger.mddirectly instead of an in-file anchor..github/aw/debug-agentic-workflow.mdis also over the cap (432 lines) after #67488added the "Model and engine misconfiguration" checklist. I initially extracted that
section too, but reverted it:
.github/skills/agentic-workflows/tests/test_guidance.pyis a regression test (added by the same PR) that requires the full checklist text to
stay inline in
debug-agentic-workflow.mdand mirrored in rootdebug.md. Splitting itwould break that contract, so this file is left as a documented exception to the
400-line target.
Before/after line counts for edited files:
.github/aw/memory.md.github/aw/ledger.md.github/aw/memory-stateful-patterns.md.github/aw/debug-agentic-workflow.mdDuplication audit
No new duplication found; the ledger split removes the only duplicated ledger content
(previously inline in
memory.mdand cross-referenced frommemory-stateful-patterns.md).Verification
debug-agentic-workflow.mdhas a zero diff againstmain(git diffempty),so the
test_guidance.pyregression contract is unaffected..github/aw/*.mdsize audit (wc -l); only the documented exceptionabove remains over 400 lines.