Merge pull request 'fix(reliability): safety-resilience' (#39) from improve/reliability-safety-resilience into main

fix(reliability): safety-resilience — crisis detection degradation paths

soul.el

@@ -5,13 +5,9 @@ import "stewardship.el"
 import "imprint.el"
 import "awareness.el"
 import "chat.el"
-import "safety.el"
 import "studio.el"
 import "elp-input.el"
 import "routes.el"
-import "safety.el"
-import "stewardship.el"
-import "imprint.el"
 
 cgi "neuron-soul" {
     dharma_id: "ntn-genesis@http://localhost:7770",
@@ -265,19 +261,31 @@ fn layered_cycle(raw_input: String) -> String {
     let screen_result: String = safety_screen(raw_input, history)
     let screen_action: String = json_get(screen_result, "action")
 
+    // ISSUE 4: safe-mode guard. If safety_screen returned an invalid/empty action
+    // (engram failure or internal error), refuse rather than pass unscreened input.
+    let valid_action: Bool = str_eq(screen_action, "hard_bell")
+        || str_eq(screen_action, "soft_bell")
+        || str_eq(screen_action, "pass")
+    if !valid_action {
+        println("[soul] layered_cycle: safety_screen invalid action -- safe mode refusal")
+        return safety_validate("", "hard_bell")
+    }
+
     // Hard bell: bypass all upper layers, log and escalate.
     // Intentionally does NOT update conversation_history or call auto_persist():
     // hard bell events are security-sensitive and must not appear in engram conversation
     // history where they could leak context to subsequent turns. They are persisted
     // separately by safety_log_bell() into the Episodic tier with restricted labels.
     //
+    // ISSUE 6: safety_log_bell already called inside safety_screen (line 140).
+    // Do NOT call it again here -- that would double-log every hard bell.
+    //
     // safety_validate second param: when screen_action is "hard_bell", safety_validate
     // receives the sentinel string "hard_bell" (not a normal screen action). The safety
     // layer contract requires it to return a fixed refusal regardless of the output arg.
     // On the normal path, safety_validate receives the original screen_action ("pass")
     // so it can apply action-specific post-output checks.
     if str_eq(screen_action, "hard_bell") {
-        safety_log_bell("hard", json_get(screen_result, "reason"), str_slice(raw_input, 0, 80))
         return safety_validate("", "hard_bell")
     }
 
@@ -312,6 +320,16 @@ fn layered_cycle(raw_input: String) -> String {
         json_get(steward_result, "redirect_to")
     }
 
+    // ISSUE 1: pre-LLM bell augmentation for layered_cycle path.
+    // safety_augment_system appends soft/hard directive to system prompt when bell fires,
+    // ensuring LLM processes message WITH the safety directive -- not just post-output gate.
+    // Stored in state as "layered_cycle_safety_system_addendum" for imprint_respond to use.
+    // TODO: wire directly when imprint_respond gains system_override param (imprint.el change).
+    // ISSUE 3 TODO: no semantic crisis detection. Keyword-only means signals that evade
+    // the phrase list pass with zero augmentation. Semantic layer = separate decision.
+    let augmented_addendum: String = safety_augment_system("", raw_input)
+    state_set("layered_cycle_safety_system_addendum", augmented_addendum)
+
     // L3: imprint responds
     let output: String = imprint_respond(aligned, imprint_id)