Modern LLM applications employ runtime monitors to inspect tool calls, traces, streams, detector outputs and verifier inputs. This creates an interface‑reliability problem: a framework path may stay operational while policy‑relevant evidence never reaches the decision point. For instance, a regex detector returned a positive match, but the framework stranded the result before the block decision. This differs from jailbreaks or detector errors because the evidence is already recognized yet disconnected from enforcement. We study this repair‑boundary signature with canary contracts: parent/fixed confirmation units that embed a known payload on the changed evidence surface and record monitor visibility together with the downstream decision for action‑boundary cases. Applying the protocol to public framework repairs, we identified 18 evidence‑path failures across 11 LLM or agent safety project groups and four implementation ecosystems. Nine are established‑boundary repairs, eight are new‑surface policy‑coverage gaps, and one is a boundary‑only evidence case. Fourteen reach E1 enforcement boundaries: seven native action outcomes, six configured enforcement boundaries, and one synthetic‑consumer consequence. The remaining cases affect verifier, safety‑prompt or observability channels. The cases form carrier, adapter, authority and surface families, showing how ordinary application behavior can remain intact while a safety‑specific evidence path misses its decision. Exact revisions, deterministic outcomes, negative controls and a frozen prospective audit document the confirmation rule. Consequently, monitor assumptions need regression tests at schemas, streams, tools and adapters as frameworks evolve.
Review