Test complete guidance delivery through process pipes - #296
Draft
nahiyankhan wants to merge 1 commit into
Draft
Conversation
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Category: infrastructure
User Impact: Strengthens evidence that guidance survives the CLI process boundary without adding truncation or changing runtime behavior.
Problem: Existing pipe regression coverage relied on output size and a final marker, which cannot detect missing content in the middle. Process delivery also needs to remain distinct from host receipt and model use.
Solution: Add 15 fixture-based tests that compare complete output or accepted material contents, including large Unicode packets, aggregate pulls, full menus, slow pipe readers, marker-shaped content, and explicit material outcomes. Document the tested boundary without claiming that every authored input survives loading/rendering or that the host/model received and used it.
Validation:
pnpm run quality:all: passed initially and again through the pre-push hook, including 241 tests across 19 files, package installation/import checks, release checks, workspace builds, and package validation.pnpm check:terminologyandgit diff origin/main...HEAD --check: passed.Changeset: patch documentation note added. No runtime, dependency, starter, output-format, or size-policy changes. Independent of the split Pass 1 fixes.
ghost Review: Not run: this slice changes tests and delivery-boundary documentation only; it changes no generation/review implementation or visual surface. Package validation passed in the full gate.
File changes
packages/ghost/test/producer-delivery.test.ts: seven subprocess tests compare complete Markdown/JSON content, full menu entries, cover/fallback/Skeleton content, explicit misses, and collision-safe material framing. Slow readers exercise pipe backpressure; expectations do not call the production formatter.packages/ghost/test/material-delivery.test.ts: eight embedded tests check UTF-8 byte boundaries, complete large bundled text, explicit unavailable/reference states, shared-material carriers, and whole-text-or-rejection inspection behavior under existing limits.packages/ghost/README.md: distinguish producer-output evidence from host transport and model application; do not substitute summaries for required content..changeset/document-delivery-evidence.md: release note for the delivery-boundary documentation.Screenshots/Demos: N/A; no visual changes.