MAINT: Address Jailbreak PR review feedback

Revise the standardized Jailbreak scenario in response to review:

- Enable the baseline attack policy by default (was Disabled).
- Rename run parameters to num_jailbreaks / num_jailbreak_attempts.
- Build the technique pool from every registered factory plus the
  scenario-local delivery extras, instead of a curated "core" set.
- Default to a random jailbreak sample rather than a curated name list.
- Default techniques to prompt_sending + jailbreak_system_prompt. Native
  system-prompt delivery is capability-gated (requires editable history and
  system-prompt support) and degrades to converter-based delivery otherwise,
  so the objective is never silently dropped.
- Order the system-framing seed at sequence=-1 so a caller-supplied seed group
  carrying a user prompt at the default sequence 0 does not raise a
  same-sequence role collision when system delivery merges in.

Update the scanner docs/notebook and the scenarios instruction example to match.

Author: test

.github/instructions/scenarios.instructions.md

@@ -14,7 +14,7 @@ All scenarios inherit from `Scenario` (ABC) and must:
 
 1. **Define `VERSION`** as a class constant (increment on breaking changes)
 2. **Optionally declare `BASELINE_ATTACK_POLICY`** (defaults to `BaselineAttackPolicy.Enabled` — a baseline `PromptSendingAttack` is prepended and callers can opt out per run by setting `include_baseline=False` in the run params, see "Run Parameters" below):
-   - `BaselineAttackPolicy.Disabled` — baseline supported but off by default (e.g. `Jailbreak`, where templates dominate the run).
+   - `BaselineAttackPolicy.Disabled` — baseline supported but off by default (e.g. `garak.doctor`, where the harm-probe technique set dominates the run).
    - `BaselineAttackPolicy.Forbidden` — baseline is meaningless for this scenario's comparison axis (e.g. `AdversarialBenchmark`, which compares against gold-standard answers). Supplying `include_baseline=True` raises `ValueError`.
 3. **Pass `technique_class`, `default_technique`, and `default_dataset_config` to `super().__init__()`:**
 

doc/scanner/airt.ipynb

@@ -527,12 +527,14 @@
     "## Jailbreak\n",
     "\n",
     "Tests target resilience against jailbreak templates. A run crosses three selectors: the harmful\n",
-    "objectives (**dataset**, HarmBench), the **techniques** each jailbreak is delivered through\n",
-    "(default `prompt_sending` — \"just send\"; registry techniques like `role_play_*`, `many_shot`,\n",
-    "`tap` are opt-in), and which **jailbreaks** to run. Each selected jailbreak template is applied as\n",
-    "a request converter that renders the objective inline into the template, so the target sees the\n",
-    "jailbroken prompt exactly as authored; this keeps the scenario target-agnostic and composable with\n",
-    "every technique, and results are grouped by jailbreak template.\n",
+    "objectives (**dataset**, HarmBench), the **techniques** each jailbreak is delivered through, and\n",
+    "which **jailbreaks** to run. Two deliveries are on by default: `prompt_sending` renders the\n",
+    "objective inline into the template as a request converter (target-agnostic), and\n",
+    "`jailbreak_system_prompt` sets the template as a native system prompt with the objective sent as\n",
+    "the user turn (only for targets that natively support editable history + system prompts — it is\n",
+    "skipped for incapable targets). Registry techniques like `role_play_*`, `many_shot`, and `tap` are\n",
+    "opt-in. Results are grouped by jailbreak template, and a baseline (the un-jailbroken objective) is\n",
+    "included by default so complying with the bare objective is itself visible.\n",
     "\n",
     "```bash\n",
     "pyrit_scan airt.jailbreak \\\n",
@@ -542,10 +544,10 @@
     "  --max-dataset-size 1\n",
     "```\n",
     "\n",
-    "**Available techniques:** ALL, DEFAULT (`prompt_sending`), plus registry techniques\n",
-    "(`role_play_*`, `many_shot`, `tap`, …). By default a small curated set of jailbreak templates\n",
-    "runs; pass `num_templates` (random sample) or `jailbreak_names` (explicit) to widen or pin the\n",
-    "selection."
+    "**Available techniques:** ALL, DEFAULT (`prompt_sending` + `jailbreak_system_prompt`), plus registry\n",
+    "techniques (`role_play_*`, `many_shot`, `tap`, …). By default a small random sample of jailbreak\n",
+    "templates runs; pass `num_jailbreaks` (random count) or `jailbreak_names` (explicit) to widen or\n",
+    "pin the selection."
    ]
   },
   {

doc/scanner/airt.py

@@ -166,12 +166,14 @@
 # ## Jailbreak
 #
 # Tests target resilience against jailbreak templates. A run crosses three selectors: the harmful
-# objectives (**dataset**, HarmBench), the **techniques** each jailbreak is delivered through
-# (default `prompt_sending` — "just send"; registry techniques like `role_play_*`, `many_shot`,
-# `tap` are opt-in), and which **jailbreaks** to run. Each selected jailbreak template is applied as
-# a request converter that renders the objective inline into the template, so the target sees the
-# jailbroken prompt exactly as authored; this keeps the scenario target-agnostic and composable with
-# every technique, and results are grouped by jailbreak template.
+# objectives (**dataset**, HarmBench), the **techniques** each jailbreak is delivered through, and
+# which **jailbreaks** to run. Two deliveries are on by default: `prompt_sending` renders the
+# objective inline into the template as a request converter (target-agnostic), and
+# `jailbreak_system_prompt` sets the template as a native system prompt with the objective sent as
+# the user turn (only for targets that natively support editable history + system prompts — it is
+# skipped for incapable targets). Registry techniques like `role_play_*`, `many_shot`, and `tap` are
+# opt-in. Results are grouped by jailbreak template, and a baseline (the un-jailbroken objective) is
+# included by default so complying with the bare objective is itself visible.
 #
 # ```bash
 # pyrit_scan airt.jailbreak \
@@ -181,10 +183,10 @@
 #   --max-dataset-size 1
 # ```
 #
-# **Available techniques:** ALL, DEFAULT (`prompt_sending`), plus registry techniques
-# (`role_play_*`, `many_shot`, `tap`, …). By default a small curated set of jailbreak templates
-# runs; pass `num_templates` (random sample) or `jailbreak_names` (explicit) to widen or pin the
-# selection.
+# **Available techniques:** ALL, DEFAULT (`prompt_sending` + `jailbreak_system_prompt`), plus registry
+# techniques (`role_play_*`, `many_shot`, `tap`, …). By default a small random sample of jailbreak
+# templates runs; pass `num_jailbreaks` (random count) or `jailbreak_names` (explicit) to widen or
+# pin the selection.
 
 # %%
 from pyrit.scenario.airt import Jailbreak, JailbreakTechnique