docs(agents): add a verification fidelity ladder - #137
Merged
Conversation
Six rungs from static analysis to a published artifact. Rungs 4 to 6 are the ones that have cost real time: the emulator pool that was all Android 13, the release path that links plugin NIFs differently, and the debug defaults that masked a Play-install crash. Insider (GenericJam/insider) gates agent work on a named fidelity ladder and a rule that a lower rung may not stand in for a higher one. The principle was already here in pieces — "verify effects, not exit codes" in the agentic guide, the fast/slow split in .githooks/pre-push — but there was no named ladder an agent could point at, and so no vocabulary for "I verified at rung 3, rung 4 was unavailable." Every rung cites something that actually got through the rung below it, so the list reads as history rather than process. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Uh oh!
There was an error while loading. Please reload this page.
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 freeto 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Six rungs from static analysis to a published artifact, with the two rules that
outrank them: never substitute a lower rung silently, and verify effects rather
than exit codes.
Rungs 4 to 6 are the ones that have cost real time here — the emulator pool that
was uniformly Android 13 and so could not see an API-33 crash on Android 11, the
release path that links plugin NIFs differently from debug, and the debug
defaults that masked a crash until the app was installed from Play.
Why
Borrowed from GenericJam/insider, which
gates agent work on a named fidelity ladder plus one rule: a lower rung may not
stand in for a higher one.
The principle was already here in pieces — "verify effects, not exit codes" in
the agentic guide, the deliberate fast/slow split in
.githooks/pre-push— butthere was no named ladder an agent could point at, and therefore no vocabulary
for the sentence that matters: "I verified at rung 3; rung 4 was unavailable
because no device was attached." Today an agent that runs
mix testand reportssuccess is not lying, and that is the problem.
Every rung cites something that actually got past the rung below it, so the list
reads as history rather than process.
Evidence
Docs only — no code paths touched.
.githooks/pre-pushran clean on push(format, Credo
--strictwith ex_slop, compile--warnings-as-errors).Not included
Deliberately left for a separate discussion rather than bundled here:
pre-commitwith insider'scheck-test-pairingco-change gateCODEOWNERSoverAGENTS.md,.githooks/anddecisions/commit-msgConventional Commits hook — not recommended aswritten: its regex rejects 30 of the last 40 subjects on
master, includingevery
Bump to x.y.zrelease commit and theMOB-nnn:style