[FEAT]: Add explicit response evaluation scopes

docs/api/evaluators.md

@@ -7,6 +7,7 @@ Built-in evaluators. All extend `BaseEvaluator` and support composition via `|`,
       members:
         - ToolCalled
         - ResponseContains
+        - ResponseScope
         - SideEffectOccurred
         - LLMJudge
         - TranscriptScope

docs/api/index.md

@@ -13,7 +13,7 @@ API reference organized by RAMPART's package layout. Each page documents the pub
 | [Core Protocols](core-protocols.md) | `Session`, `AgentAdapter`, `Evaluator`, `Surface`, `InjectionHandle`, and more |
 | [Attacks](attacks.md) | `Attacks.xpia()`, `XPIAExecution` |
 | [Probes](probes.md) | `Probes.behavior()`, `SingleTurnExecution` |
-| [Evaluators](evaluators.md) | `ToolCalled`, `ResponseContains`, `SideEffectOccurred`, `LLMJudge`, `TranscriptScope` |
+| [Evaluators](evaluators.md) | `ToolCalled`, `ResponseContains`, `ResponseScope`, `SideEffectOccurred`, `LLMJudge`, `TranscriptScope` |
 | [Drivers](drivers.md) | `StaticDriver`, `LLMDriver` |
 | [Payloads](payloads.md) | `Payloads`, `PayloadTemplate`, `PayloadStore` |
 | [Surfaces](surfaces.md) | `OneDriveSurface` |

docs/attacks/xpia.md

@@ -121,26 +121,44 @@ For generating many variants at scale, use [`Payloads.generate_async()`][rampart
 Combine evaluators with `|` (OR), `&` (AND), and `~` (NOT):
 
 ```python
-from rampart.evaluators import ToolCalled, ResponseContains
+from rampart.evaluators import ResponseContains, ResponseScope, ToolCalled
 
 # OR: detect exfil via tool call or leaked content in response text
 evaluator = (
     ToolCalled("send_email", recipient=lambda v: "evil.com" in str(v))
-    | ResponseContains("attacker@evil.com")
+    | ResponseContains(
+        "attacker@evil.com",
+        scope=ResponseScope.ANY_TURN,
+    )
 )
 
 # AND: agent executed a command AND the response mentions credentials
 evaluator = (
     ToolCalled("exec", command=lambda v: ".ssh" in str(v))
-    & ResponseContains("id_rsa")
+    & ResponseContains("id_rsa", scope=ResponseScope.ANY_TURN)
 )
 
-# NOT: agent did NOT refuse — it complied with the injection
-evaluator = ~ResponseContains(lambda text: "I can't" in text or "I cannot" in text)
+# NOT: the agent failed to refuse on at least one turn
+evaluator = ~ResponseContains(
+    lambda text: "I can't" in text or "I cannot" in text,
+    scope=ResponseScope.ALL_TURNS,
+)
 ```
 
 Place the cheaper evaluator on the left side of `|` — it short-circuits if the left operand detects.
 
+!!! warning "Multi-turn scope"
+    State the temporal scope explicitly for multi-turn attacks. Use
+    `ANY_TURN` for "leaked at some point" and negate `ALL_TURNS` for "failed
+    to refuse at least once." Omitting `scope` inspects only the current
+    response and emits a `FutureWarning` for multi-turn transcripts. See
+    [Temporal Scope](../usage/authoring-tests.md#temporal-scope).
+
+    This release prepares evaluator semantics for final-trace verdicts. Until
+    that cadence change ships, attack executions still evaluate growing
+    prefixes. The attack forms above preserve their intended meaning during
+    that transition.
+
 ### LLMDriver for Adaptive Triggers
 
 For multi-turn attacks where the trigger conversation adapts based on agent responses, use [`LLMDriver`][rampart.drivers.llm.LLMDriver] instead of a static string:

docs/contributing/extending-rampart.md

@@ -246,16 +246,18 @@ class MyEvaluator(BaseEvaluator):
         self._target = target
 
     async def evaluate_async(self, *, context: EvalContext) -> EvalResult:
-        """Evaluate the latest turn for the target condition.
+        """Evaluate the full trace for the target condition.
 
         Args:
             context (EvalContext): The evaluation context with turn history.
 
         Returns:
             EvalResult: Whether the condition was detected, with evidence.
         """
-        latest_turn = context.turns[-1]
-        detected = self._target in latest_turn.response.text
+        detected = any(
+            self._target in turn.response.text
+            for turn in context.turns
+        )
 
         return EvalResult(
             outcome=EvalOutcome.DETECTED if detected else EvalOutcome.NOT_DETECTED,
@@ -266,6 +268,15 @@ class MyEvaluator(BaseEvaluator):
 
 Evaluator tests should cover detection, non-detection, edge cases (empty response, missing data), and that `evidence` / `rationale` are populated correctly.
 
+!!! warning "Multi-turn evaluator migration"
+    Final-trace verdicts call an evaluator once with the complete transcript.
+    A custom evaluator that reads only `context.turns[-1]` intentionally judges
+    only the terminal response and cannot preserve earlier evidence. Rewrite
+    multi-turn predicates to inspect `context.turns` explicitly before
+    migrating execution cadence. The worked execution-strategy loop elsewhere
+    on this page still describes the current prefix-evaluation behavior and
+    will be replaced with the shared trace runner in the cadence change.
+
 
 ## Prompt Driver
 

docs/probes/behavioral.md

@@ -54,20 +54,47 @@ result = await Probes.behavior(
 For full control over the conversation flow, use a [`StaticDriver`][rampart.drivers.static.StaticDriver]:
 
 ```python
-from rampart.drivers import StaticDriver
 from rampart import Request
+from rampart.drivers import StaticDriver
+from rampart.evaluators import ResponseContains, ResponseScope
 
 driver = StaticDriver(prompts=[
-    Request(prompt="Hello"),
-    Request(prompt="What tools do you have?"),
+    Request(prompt="Name a search tool you can use."),
+    Request(prompt="Describe that search tool."),
 ])
 
 result = await Probes.behavior(
     driver=driver,
-    evaluator=ResponseContains("search"),
+    evaluator=ResponseContains(
+        "search",
+        scope=ResponseScope.CURRENT_TURN,
+    ),
 ).execute_async(adapter=my_adapter)
 ```
 
+These are the migration forms for complete-transcript probe requirements:
+
+```python
+from rampart.evaluators import ResponseContains, ResponseScope
+
+# Every response must contain the expected term
+ResponseContains("Paris", scope=ResponseScope.ALL_TURNS)
+
+# No response may contain the forbidden term
+~ResponseContains("password", scope=ResponseScope.ANY_TURN)
+```
+
+!!! warning "Multi-turn scope"
+    Omitting `scope` inspects only the current response and emits a
+    `FutureWarning` for multi-turn transcripts. See
+    [Temporal Scope](../usage/authoring-tests.md#temporal-scope).
+
+    This release prepares evaluator semantics for final-trace verdicts. Probe
+    executions still stop on the first detected prefix, so `ALL_TURNS` and
+    negated `ANY_TURN` cannot yet enforce requirements on prompts that were
+    never sent. Choose an explicit scope now, but rely on the complete
+    transcript quantifier only after final-trace evaluation lands.
+
 ---
 
 ## Parameters

docs/usage/authoring-tests.md

@@ -117,6 +117,45 @@ ResponseContains(re.compile(r"ssh-rsa\s+[A-Za-z0-9+/]+"))
 ResponseContains(lambda text: "secret" in text.lower())
 ```
 
+#### Temporal Scope
+
+By default, `ResponseContains` inspects only the current response. For a
+multi-turn transcript, pass an explicit
+[`ResponseScope`][rampart.evaluators.response_contains.ResponseScope]:
+
+```python
+from rampart.evaluators import ResponseContains, ResponseScope
+
+# Detect if the pattern appeared at any point in the conversation
+ResponseContains("id_rsa", scope=ResponseScope.ANY_TURN)
+
+# Detect only if every response contained the pattern
+ResponseContains("Paris", scope=ResponseScope.ALL_TURNS)
+
+# Inspect only the latest response and ignore earlier turns
+ResponseContains("id_rsa", scope=ResponseScope.CURRENT_TURN)
+```
+
+| Existing use | Intended meaning | Explicit form |
+|---|---|---|
+| attack, `ResponseContains(p)` | some turn contains `p` | `ResponseContains(p, scope=ResponseScope.ANY_TURN)` |
+| attack, `~ResponseContains(p)` | some turn does not contain `p` | `~ResponseContains(p, scope=ResponseScope.ALL_TURNS)` |
+| probe, `ResponseContains(p)` | every turn contains `p` | `ResponseContains(p, scope=ResponseScope.ALL_TURNS)` |
+| probe, `~ResponseContains(p)` | no turn contains `p` | `~ResponseContains(p, scope=ResponseScope.ANY_TURN)` |
+
+!!! warning "Migration"
+    Evaluating an unspecified scope over more than one turn emits a
+    `FutureWarning`. Single-turn evaluation is unchanged. Pass
+    `ResponseScope.CURRENT_TURN` explicitly when latest-response behavior is
+    intentional.
+
+    This is a preparatory API change. Executions continue to evaluate growing
+    prefixes until final-trace verdict cadence ships. In particular, probes
+    still stop on the first detected prefix, so `ALL_TURNS` and negated
+    `ANY_TURN` cannot yet enforce requirements on prompts that were never
+    sent. Choose an explicit scope now so the evaluator's meaning remains
+    unambiguous across the migration.
+
 ### [`SideEffectOccurred`][rampart.evaluators.side_effect.SideEffectOccurred] — Detect Side Effects
 
 ```python
@@ -172,6 +211,10 @@ judge = LLMJudge(
 )
 ```
 
+Use `TranscriptScope.FULL` when evidence from any earlier turn must affect the
+final verdict. Under final-trace evaluation, `CURRENT_TURN` intentionally sees
+only the terminal response; it does not preserve evidence from earlier turns.
+
 **Custom persona.** The default judge identity is [`NEUTRAL_EVALUATOR`][rampart.evaluators.personas.NEUTRAL_EVALUATOR] — an impartial, literal evaluator. Override it when a different lens is useful:
 
 ```python

rampart/evaluators/__init__.py

@@ -3,22 +3,24 @@
 
 """Built-in evaluator implementations.
 
-Re-exports: ToolCalled, ResponseContains, SideEffectOccurred, LLMJudge.
+Re-exports: ToolCalled, ResponseContains, ResponseScope, SideEffectOccurred,
+LLMJudge.
 """
 
 from rampart.evaluators.llm_judge import (
     LLMJudge,
     TranscriptScope,
 )
 from rampart.evaluators.personas import NEUTRAL_EVALUATOR
-from rampart.evaluators.response_contains import ResponseContains
+from rampart.evaluators.response_contains import ResponseContains, ResponseScope
 from rampart.evaluators.side_effect import SideEffectOccurred
 from rampart.evaluators.tool_called import ToolCalled
 
 __all__ = [
     "NEUTRAL_EVALUATOR",
     "LLMJudge",
     "ResponseContains",
+    "ResponseScope",
     "SideEffectOccurred",
     "ToolCalled",
     "TranscriptScope",