Repository navigation
docs(rfc-wake-judge): record Q4 as decided from the judge core's code - #13234
Conversation
Design Review (Fable 5) — ✅ PASSDesign-level review of Design-Verdict: PASS Verify #12787 still reads [DESIGN-REVIEWED] 4793cab |
GPT 5.6 Review — ✅ no blocking findingsGPT 5.6 completed its review of This comment is updated in place on each push. Review detailsFINDING -- docs/request-for-change/rfc-wake-judge.md:357 -- Pinned False positive or not applicable? A repository writer can comment: |
Opus 5 Review — ✅ no blocking findingsReviewed Verdict parsed from the review's SHA-scoped output markers for commit False positive or not applicable? A repository writer can comment: |
0fe7223 to
3bc51c8
Compare
|
span=45dc661abaa4 Correct, and the state it names is reachable rather than theoretical. Fixed.
The defect was mine: I narrowed the precondition in sections 3.3, 3.4 and 7 Q4 and Applied in 4793cab (this comment stamps 3bc51c8, the head the finding |
|
span=d29af0980bf9 Correct. Applied, and widened past the two sections named. The header told a merge auditor to re-read sections 3.2, 3.3 and 3.6. This PR Rather than adding two section numbers, the list is now stated as the invariant it That also answers this lane's watch item in the same edit. Verifying at #12787's Applied in 4793cab (this comment stamps 3bc51c8, the head the suggestion |
3bc51c8 to
4793cab
Compare
The built-in brief is authorized by the nudge_evidence grant read as the narrower gate.judge_evidence_scope_granted -- the Decisions consent for the configured endpoint plus this point's own scope -- asked before a lane is picked, so it holds on both lanes. Those two conditions are exactly what arms the Jev lane, so the default provider sends a briefless loop to the lane the switch names, and a machine holding the scope alone screens nothing. gate = false is never screened and judge: false opts out. The rollout entry for the judge core states the decision instead of blocking on it, the open-questions section answers Q4 with the same rule, and the two sections that asserted the undecided consequence state the settled one. Q5 stays open. The index row and its provenance line carry the refreshed reading.
|
span=9b83636b5394
Section 5 now names the lane instead of the loop: the LLM lane needs no keystone Three other sentences carried the same unqualified claim and are fixed in the same |
|
span=45dc661abaa4
With Section 5 now derives the exposure from what authorizes each lane rather than from This is the second round on this span. The first was the same class of error -- a |
|
span=45dc661abaa4
The claim is justified for the involuntary case only. A machine holding the scope Section 3.6 now says what is actually true of each case: no machine falls through |
|
span=e23818f24c1e
That README declares each document's own I fixed the sentence rather than the front matter, because bumping The sentence now says only that, and points at the front matter for the main-side |
4793cab to
4e0dde1
Compare
GPT 5.6 Review — ✅ no blocking findingsGPT 5.6 completed its review of This comment is updated in place on each push. Review detailsNo findings. False positive or not applicable? A repository writer can comment: |
bolichen97
left a comment
There was a problem hiding this comment.
Approving. The doc never claims this rule is on main: the front matter stays partial, the header says the core sections are read at d81bd0ec17 on #12787, the README index line says the same, and Q4 itself is phrased as "PR D's tick reads ...". Reading an in-flight branch is this document's pre-existing convention, not something this PR introduces.
Q4's chosen answer is also the narrowest of the options it lists — the built-in brief applies only when endpoint consent AND this point's nudge_evidence scope both hold — so it adds no data flow. Q4 and the §8 PR D entry are both on the "Re-audit at merge" list, which is the hook the Design lane asked for.
…kirodotdev#13234) The built-in brief is authorized by the nudge_evidence grant read as the narrower gate.judge_evidence_scope_granted -- the Decisions consent for the configured endpoint plus this point's own scope -- asked before a lane is picked, so it holds on both lanes. Those two conditions are exactly what arms the Jev lane, so the default provider sends a briefless loop to the lane the switch names, and a machine holding the scope alone screens nothing. gate = false is never screened and judge: false opts out. The rollout entry for the judge core states the decision instead of blocking on it, the open-questions section answers Q4 with the same rule, and the two sections that asserted the undecided consequence state the settled one. Q5 stays open. The index row and its provenance line carry the refreshed reading.
What is the problem?
docs/request-for-change/rfc-wake-judge.mdcarries Q4 as an open question --which switch authorizes the point's built-in brief on each lane -- and its
rollout entry for the judge core reads "Blocked on Q4". The judge core settles
it: on #12787 the tick
reads the seam's narrower
gate.judge_evidence_scope_grantedbefore any lane ispicked, and leaves the tick untouched when that answers no.
Two other sections also state the consequence Q4 worried about -- that a
briefless loop with the scope granted and no endpoint consent is screened on the
LLM lane, whose destination is the owner's own model provider. That branch makes
it impossible: the grant a briefless loop runs on is the endpoint consent AND the
point's own scope, so a machine holding the scope alone screens nothing.
Why this issue matters to the user
The First Principles lane reads a design decision off the base branch, so a
document that calls a decision open while the branch implements it blocks the
implementation PR.
Beyond the lane, this document is the record of what granting
nudge_evidencebuys. As written it tells an owner the destination may differ from the words on
the switch. In the shipped rule it cannot, because the two conditions the grant
is read as are exactly the ones that arm the Jev lane the switch names. An owner
reading the open question would withhold a grant over a case that does not
exist, and a reviewer of PR D would look for a decision the code already made.
How our fix solves it
Every site that asserted Q4 open now states the rule the code implements, and
nothing is invented: the wording follows
_judge_tick_is_quiet,judge_evidence_scope_granted,_judge_authorityandjudge_laneatd81bd0ec17.nudge_evidencegrant read as the narrower question, on both lanes, askedbefore a lane is picked. Because those two conditions are exactly the Jev
lane's arming conditions,
auto-- the default -- sends a briefless loop tothe Jev lane the switch names. The LLM lane screens a briefless loop only where
the owner holds that grant and pins
provider = llm, so an install that neverconsented to the Jev endpoint has no built-in brief at all while a loop that
wrote criteria still runs there on the lane's own authority.
gate = falseisnever screened and
judge: falseopts out, both read before the built-in briefis assembled.
on it, and no longer says "Jev lane only":
judge_lanereturns the LLM lanewhenever Jev is not armed, and that lane is on main.
and section 3.6 keeps only Q5 as its open consequence.
with the scope and no endpoint consent screens the loops that wrote their own
criteria, not every gated loop.
judge_evidence_scope_grantedstates the briefless rule;_judge_authoritybeside it and
config/sections.pystate the spec half for a briefed loop andname no briefless case.
(
08f5787fb8->d81bd0ec17), and the index's provenance line records it inthat file's own convention.
Q5 is untouched and stays open. It asks how a grant recorded under narrower
wording is told apart from one recorded under the wider population, which the
keystone cannot answer today because it stores one boolean per scope and no
wording.
What tests we did
Documentation only; no source file changes. The gates Fast Gate runs over a
markdown change, all against
origin/mainat4917d72476:python3 scripts/docs_lint.py --test-- exit 0, self-test passed../scripts/docs-lint.sh-- exit 0, all documentation checks passed.python3 scripts/check_brand_name.py --testand the gate -- exit 0.python3 scripts/check_comment_history.py-- exit 0 (0 changed files in itsscope; it reads code comments).
python3 scripts/check_feature_map.py-- exit 0.python3 scripts/check_focus_cue.py-- exit 0.The decision itself was read from PR #12787's tree at
d81bd0ec17withoutediting it:
_judge_tick_is_quietinautonudge.py,default_spec/BRIEF_DEFAULT/BRIEF_CUSTOMinautonudge_judge.py, andjudge_evidence_scope_granted/_judge_authority/judge_lane/_consented_for/_point_scope_grantedindecisions/gate.py.Any other suggestions on the work
The two code sites this document points at still describe only the briefed case.
gate._judge_authoritysaysprovider = llmplus ajudgespec on the loop isthe whole authorization for that lane, and
config/sections.py'sNudgeWakeConfigdocstring repeats it. Both are accurate for a loop that wrotecriteria and silent about the briefless one, whose rule lives one function away.
A sentence in each would put the whole rule where a reader of either lands, and
it belongs in PR D rather than here.
Refs #12787