NeuroSploit

mirror of https://github.com/CyberSecurityUP/NeuroSploit.git synced 2026-09-29 20:41:51 +02:00

Files

T

CyberSecurityUPandClaude Opus 5 7661b5eb4e fix(wiring): resolve the last two placebos — pomdp belief gate + harness-owned inbox

pomdp.rs was dead (belief.rs was on the path, pomdp wasn't). Now
pomdp::may_assert runs as an anti-hallucination gate over the belief WorldModel:
a finding asserted confirmed while the belief about it is diffuse or weak is
held for review. Advisory — never deletes.

inbox.rs was unused (mail.tm happened via agent prompt instructions). Now when
temp-email is enabled the HARNESS creates the mail.tm inbox via crate::inbox and
hands the agent that exact address, so the inbox is one we own and record rather
than an unrecorded one the agent conjures. Best-effort; falls back to the old
prompt path on failure.

Every module is now on a real runtime path. 381 tests.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

2026-09-19 18:20:14 -03:00

app

feat(typesafe): confirmation-loop agent + --typesafe flag (on/off/auto) for A/B

2026-09-19 18:15:10 -03:00

crates/harness

fix(wiring): resolve the last two placebos — pomdp belief gate + harness-owned inbox

2026-09-19 18:20:14 -03:00

templates

feat(budget,provenance): reasoning budget modes and JOASNSCOPE provenance

2026-09-14 01:14:03 -03:00

.gitignore

chore: remove test artifacts, ignore scan debris (#35 )