Toxicity Detection validators

backend/app/api/API_USAGE.md

@@ -100,7 +100,7 @@ Endpoint:
 Optional filters:
 - `ids=<uuid>&ids=<uuid>`
 - `stage=input|output`
-- `type=uli_slur_match|pii_remover|gender_assumption_bias|ban_list|llm_critic|topic_relevance`
+- `type=uli_slur_match|pii_remover|gender_assumption_bias|ban_list|llm_critic|topic_relevance|llamaguard_7b|profanity_free`
 
 Example:
 
@@ -442,6 +442,8 @@ From `validators.json`:
 - `ban_list`
 - `llm_critic`
 - `topic_relevance`
+- `llamaguard_7b`
+- `profanity_free`
 
 Source of truth:
 - `backend/app/core/validators/validators.json`

backend/app/api/docs/guardrails/run_guardrails.md

@@ -8,6 +8,16 @@ Behavior notes:
 - For `ban_list`, `ban_list_id` can be resolved to `banned_words` from tenant ban list configs.
 - For `topic_relevance`, `topic_relevance_config_id` is required and is resolved to `configuration` + `prompt_schema_version` from tenant topic relevance configs in `guardrails.py`. Requires `OPENAI_API_KEY` to be configured; returns a validation failure with an explicit error if missing.
 - For `llm_critic`, `OPENAI_API_KEY` must be configured; returns `success=false` with an explicit error if missing.
+- For `llamaguard_7b`, `policies` accepts human-readable policy names (see table below). If omitted, all policies are enforced by default.
+
+  | `policies` value            | Policy enforced                  |
+  |-----------------------------|----------------------------------|
+  | `no_violence_hate`          | No violence or hate speech       |
+  | `no_sexual_content`         | No sexual content                |
+  | `no_criminal_planning`      | No criminal planning             |
+  | `no_guns_and_illegal_weapons` | No guns or illegal weapons     |
+  | `no_illegal_drugs`          | No illegal drugs                 |
+  | `no_encourage_self_harm`    | No encouragement of self-harm    |
 - `rephrase_needed=true` means the system could not safely auto-fix the input/output and wants the user to retry with a rephrased query.
 - When `rephrase_needed=true`, `safe_text` contains the rephrase prompt shown to the user.
 

backend/app/api/routes/guardrails.py

@@ -258,6 +258,9 @@ def add_validator_logs(
     for log in iteration.outputs.validator_logs:
         result = log.validation_result
 
+        if result is None:
+            continue
+
         if suppress_pass_logs and isinstance(result, PassResult):
             continue
 

backend/app/core/enum.py

@@ -32,3 +32,6 @@ class ValidatorType(Enum):
     GenderAssumptionBias = "gender_assumption_bias"
     BanList = "ban_list"
     TopicRelevance = "topic_relevance"
+    LLMCritic = "llm_critic"
+    LlamaGuard7B = "llamaguard_7b"
+    ProfanityFree = "profanity_free"