"measurement":"ai-service-plane first increment (Requirement 6): repo-facts + verify (2 passes) + agree for the 46-candidate validation set, executed by the ax-backed reconciler on google/ax + Agent Substrate (kind, gVisor) on the 7 GB host",
"definition":"declared sites whose candidate pass a or pass b flagged; reference = 16 agreed + fuxa, froxlor validateIpAddresses, unleash found in one pass"
},
"declared_sites_covered_by_candidates":{
"plane":19,
"of":20,
"definition":"agree's metric declared_sites_matched: candidates whose site falls on a declared site, flagged or not (winml has no candidate)"
"reading":"Detection is lower, not only agreement: plane passes flagged 17 of 20 declared sites in at least one pass against the reference's 19 (budibase read and fuxa getDaqValue were flagged by neither plane pass), and two-pass agreement moved the three froxlor sites (pass b only) into 'disputed'; unleash moved the other way. Cost fell 17% (62% of prompt tokens were cache hits). By the pre-registered rule the increment is NOT MET and the design is revisited before task 9.",
"dev_token_report":{
"transcript":"the whole development session (c09e30b2), not the increment alone",
"egress gateway not deployed; deny-by-default per-actor policy",
"gateway dials the address the actor dialled",
"workspace clone before the actor was running",
"32 KB env limit on inlined inputs",
"63-byte template name limit"
],
"correction":"2026-09-30: the first version of this record read agree's declared_sites_matched (coverage by candidates, 19) as 'found in either pass' and concluded detection was unchanged; recounted from agreed.json rows it is 17 vs the reference's 19."