human behavior: classifier gate, pacing, splitting, quiet hours, stable prompt prefix

2026-07-13 15:55:26 +02:00
parent 13b9569c07
commit ae870db181
15 changed files with 510 additions and 42 deletions
@@ -54,6 +54,14 @@ Decisions inside the set architecture. D-NNN, never renumbered.
  fact-level erasure ships with FDB-007 structured memory — stated in
  the user-facing confirmation, not hidden. (Superseded by D-014:
  erasure now covers facts, observations and episode traces.)
+- **D-016** — The reply/ignore classifier fails open (BEH-03): a
+  broken classifier must never mute the bot; the budget gate already
+  bounds spend. Its verdict gates BEFORE the main call, the
+  envelope's answer_needed still gates after — two independent nets.
+- **D-017** — All human-behavior knobs default to off/v3.0.0
+  semantics; behavior changes are config rollouts per deployment, not
+  code flips. The classifier's `factual` flag is the only coupling
+  (delay bypass) and defaults to false without a classifier.
 - **D-015** — Deploys are push-based from the dev machine
  (`git archive <tag> | ssh`), not pull-based: no deploy keys or git
  state on the hosts, the artifact is exactly the tag tree, untracked