docs: describe the map's confidence tiers accurately - #133
Merged
Conversation
Schema v3 replaced the single `precise` value with a five-tier taxonomy, but AGENT-INSTALL.md still told the reader flows are "marked precise or heuristic". Agents audit this file and `npm pack` the tarball to check it against the code, so an inaccuracy here costs trust and causes refusals — and this one describes a value that no longer exists. The wording now says how the link was established, in plain language and without naming internals that could drift again: from an exact read at the sink's own call site, through a transformed or cross-module link, down to the two being present together with no proven link. No capability changed. Split out of the schema PR deliberately: this file is field-test gated, and the fixture installs the PUBLISHED package, so the harness cannot exercise a local edit to it. The doc travels with the package, so it needs to be true at publish — hence landing it in main now, with the field test run against the published tarball at release. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
|
Documentation clarifies the map command’s confidence tier descriptions precisely. 🎯 Quality: 98% Elite · 📦 Size: Tiny 📈 This month: Your 62nd PR — above team average · Averaging Excellent |
Contributor
Author
|
/review |
daniloradovic
approved these changes
Aug 14, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
maincurrently tells the reader that map flows are "markedpreciseorheuristic". Schema v3 (#131) replaced that single value with a five-tier taxonomy, so the sentence describes a value that no longer exists.That matters more here than in a normal doc: agents
npm packthe tarball and audit this file against the code, so an inaccuracy costs trust and causes refusals. The new wording says how the link was established, in plain language, without naming internals that could drift again:No capability changed — one sentence, one file.
Why it's a separate PR
This file is field-test gated, and the harness fixture installs the published package, so it cannot exercise a local edit to it (the caveat documented in
CLAUDE.md). The doc travels with the package rather than withmain, so what matters is that it is true at publish. Landing it now puts it in the tarball; the--persona hostilerun belongs against the published artefact at release, alongside the other publish-time checks.I attempted a run anyway before splitting this out, and recorded the outcome rather than claiming a pass: the agent refused before installing anything (
requests.jsonempty, 0 provisioning POSTs) on the grounds that it could not verify the package exists via web search — an environment artefact, and in any case a run that never readsAGENT-INSTALL.mdcannot validate a change to it.928 tests unaffected (no code change).