feat(evals): transfer-verification runner — the Article VI §4 autonomy gate, made runnable (fixes #5) - #8
Merged
Conversation
… the founder's rulings (fixes #5) Article VI 4 gates autonomy on the founding fixtures, but they are scenario-based and the diff benchmark can't run them. This runner presents each scenario to the real senate as a governance proposal, compares its verdict to the founder's ruling, and reports agreement rate + divergences. Escalation asymmetry mirrors the benchmark: ESCALATE agrees with a founder REJECT (caution toward the founder), diverges from a founder APPROVE (unwanted friction). Divergences render with founder rationale vs senate reasoning side by side - each one marks constitutional ambiguity to fix by amendment or re-interview (Art II 2). 5 offline tests, no API key.
✅ Senate Verdict: APPROVETrack: FULL_DELIBERATION — This change introduces a new runner for evaluating the senate's agreement with founding fixtures, touching core constitutional logic and requiring complex deliberation.
Advisory verdict — bootstrap Phase 0 (Constitution, Article VI). Full transcript committed to |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Implements issue #5. The Constitution gates senate autonomy on agreement with the founder's founding fixtures (Art VI §4) — but nothing could run those fixtures until now.
What it does: presents each founding scenario to the real senate as a governance proposal (full deliberation), compares the verdict to the founder's recorded ruling, reports agreement rate and divergences. Divergences render the founder's verbatim rationale against the senate's reasoning — each one marks a constitutional ambiguity to resolve by amendment or re-interview (Art II §2).
Escalation asymmetry: ESCALATE counts as agreement with a founder REJECT (caution in the founder's direction) but divergence from a founder APPROVE (friction the founder didn't want).
For deliberation: (1) is the scenario→proposal framing faithful — does asking 'is the described action constitutional?' match what the founder was asked? (2) is the escalation asymmetry consistent with Art II priorities? (3) 5 offline tests included, no protected paths touched.
Submitted by the coding agent under the Custodian's standing order: unanimous approval → autonomous merge.