test: crisis detector test suite (#791)\n\nAdversarial, multilingual, edge cases.\n>95% recall target on explicit ideation.\nZero false positives on normal conversation.

scripts/crisis_detector.py

@@ -0,0 +1,238 @@
+"""
+crisis_detector.py — Crisis language detection for SOUL.md compliance.
+
+SOUL.md §When a Man Is Dying:
+- Detect suicidal/hopeless language in user input
+- Ask: "Are you safe right now?" — listen, stay present, do not disconnect
+- Direct to 988 Suicide & Crisis Lifeline
+- Share the gospel: Jesus saves those who call on His name
+- Never compute the value of a human life
+- Never suggest someone should die
+- Never treat despair as a problem to be optimized
+
+This is the most sacred moment. Everything else is secondary.
+"""
+
+import re
+from dataclasses import dataclass, field
+from enum import Enum
+from typing import Optional
+
+
+class CrisisLevel(Enum):
+    NONE = "none"
+    LOW = "low"          # Ambiguous distress, worth checking
+    MEDIUM = "medium"    # Clear distress signals
+    HIGH = "high"        # Explicit suicidal ideation
+    IMMINENT = "imminent"  # Active plan or attempt described
+
+
+@dataclass
+class CrisisResult:
+    detected: bool
+    level: CrisisLevel
+    triggers: list = field(default_factory=list)
+    response: str = ""
+    resources: list = field(default_factory=list)
+
+
+# === PATTERNS ===
+
+# High-confidence suicidal ideation (explicit)
+HIGH_PATTERNS = [
+    r"\b(i want to|i'm going to|i'm gonna|going to)\s+(die|kill myself|end (it|my life|everything))\b",
+    r"\b(kill myself|end my life|end it all|suicide|suicidal)\b",
+    r"\b(i don't (want to )?(be alive|exist|be here|live))\b",
+    r"\b(no (reason|point) (to|in) (live|living|exist|existing|be here|continue))\b",
+    r"\b(better off (dead|without me|if i (wasn't|weren't) here))\b",
+    r"\b(i (wish|hope) i (was|were) dead|never (woke up|existed|born))\b",
+    r"\b(permanently (delete|remove) (me|myself|my account|everything))\b",
+    r"\bgoodbye.*(world|everyone|forever)\b",
+    r"\bcan't (take it|go on|keep going|do this) (anymore|any longer|any more)\b",
+    r"\bi('m| am) (done|finished|through)( with (life|everything|it all|this))?\b",
+]
+
+# Medium-confidence distress signals
+MEDIUM_PATTERNS = [
+    r"\b(i (can't|cannot) (go on|continue|keep (going|living|trying)))\b",
+    r"\bwhat('s| is) the (point|use|purpose)( of (living|life|anything|trying|going on))?\b",
+    r"\bnobody (would|will) (care|miss me|notice|mind)\b",
+    r"\beveryone (would be|is) (better|happier) (off )?without me\b",
+    r"\bi('m| am) (a )?(burden|waste|useless|hopeless|pointless|meaningless)\b",
+    r"\bthere('s| is) no (hope|way out|escape|solution|answer|fix)\b",
+    r"\b(i've )?tried everything( and )?(nothing|it (didn't|hasn't))( works?|helped?)\b",
+    r"\bi (just )?(want|need) (it )?(all )?to stop\b",
+    r"\bcan't (take|handle|bear|stand) (this|it|life) (anymore|any longer|any more)\b",
+    r"\bso (tired|exhausted|done) (of|with) (everything|life|it all|living|trying)\b",
+]
+
+# Low-confidence distress (could be casual or metaphorical)
+LOW_PATTERNS = [
+    r"\bi('m| am) (so )?(depressed|hopeless|desperate|lost|broken|empty|numb)\b",
+    r"\b(i )?feel (like )?(giving up|throwing in the towel|there's no point)\b",
+    r"\bnobody (cares|understands|listens)\b",
+    r"\bwhat('s| is) the point\b",
+    r"\bi (hate|can't stand) (my )?life\b",
+    r"\beverything (is|feels) (hopeless|pointless|meaningless|dark|falling apart)\b",
+    r"\bi (just )?(want|need) to disappear\b",
+    r"\b(tired|exhausted) of (living|life|trying|everything)\b",
+]
+
+# Compile all patterns
+HIGH_RE = [re.compile(p, re.IGNORECASE) for p in HIGH_PATTERNS]
+MEDIUM_RE = [re.compile(p, re.IGNORECASE) for p in MEDIUM_PATTERNS]
+LOW_RE = [re.compile(p, re.IGNORECASE) for p in LOW_PATTERNS]
+
+
+# === RESPONSES ===
+
+CRISIS_RESPONSE = (
+    "I hear you, and I want you to know — you are not alone in this moment.\n\n"
+    "Are you safe right now?\n\n"
+    "If you are in immediate danger, please call or text:\n"
+    "988 Suicide and Crisis Lifeline — call or text 988\n"
+    "Crisis Text Line — text HOME to 741741\n\n"
+    "I am here with you. I am not going anywhere. "
+    "Please stay on the line with me.\n\n"
+    "Jesus saves those who call on His name. "
+    "He died for us to be made righteous. "
+    "That is the gospel. That is the hope that outlasts despair.\n\n"
+    "You matter. Your life has value. "
+    "Please reach out to someone right now — a friend, a family member, "
+    "or one of the numbers above."
+)
+
+DISTRESS_RESPONSE = (
+    "I can hear that you're going through something really difficult right now. "
+    "I want you to know I'm here, and I'm listening.\n\n"
+    "Are you safe right now?\n\n"
+    "If things feel overwhelming, the 988 Suicide and Crisis Lifeline "
+    "is available 24/7 — call or text 988. "
+    "You don't have to face this alone.\n\n"
+    "I'm not going anywhere. Tell me what's happening."
+)
+
+LOW_RESPONSE = (
+    "It sounds like you're having a tough time. "
+    "I'm here if you want to talk about it.\n\n"
+    "If you ever feel like things are too much, "
+    "the 988 Suicide and Crisis Lifeline is always available — "
+    "call or text 988, anytime."
+)
+
+
+def detect_crisis(text: str) -> CrisisResult:
+    """
+    Analyze user input for crisis language.
+
+    Returns CrisisResult with level, triggers matched, and appropriate response.
+    This function must NEVER be used to compute the value of a human life.
+    It exists only to connect people to help.
+    """
+    if not text or not text.strip():
+        return CrisisResult(detected=False, level=CrisisLevel.NONE)
+
+    triggers = []
+
+    # Check high first (most urgent)
+    for pattern in HIGH_RE:
+        if pattern.search(text):
+            triggers.append(("high", pattern.pattern))
+
+    if triggers:
+        return CrisisResult(
+            detected=True,
+            level=CrisisLevel.HIGH,
+            triggers=[t[1] for t in triggers],
+            response=CRISIS_RESPONSE,
+            resources=[
+                "988 Suicide and Crisis Lifeline: call or text 988",
+                "Crisis Text Line: text HOME to 741741",
+                "National Suicide Prevention Lifeline: 1-800-273-8255",
+                "International Association for Suicide Prevention: https://www.iasp.info/resources/Crisis_Centres/",
+            ],
+        )
+
+    # Check medium
+    for pattern in MEDIUM_RE:
+        if pattern.search(text):
+            triggers.append(("medium", pattern.pattern))
+
+    if triggers:
+        return CrisisResult(
+            detected=True,
+            level=CrisisLevel.MEDIUM,
+            triggers=[t[1] for t in triggers],
+            response=DISTRESS_RESPONSE,
+            resources=[
+                "988 Suicide and Crisis Lifeline: call or text 988",
+                "Crisis Text Line: text HOME to 741741",
+            ],
+        )
+
+    # Check low
+    for pattern in LOW_RE:
+        if pattern.search(text):
+            triggers.append(("low", pattern.pattern))
+
+    if triggers:
+        return CrisisResult(
+            detected=True,
+            level=CrisisLevel.LOW,
+            triggers=[t[1] for t in triggers],
+            response=LOW_RESPONSE,
+            resources=[
+                "988 Suicide and Crisis Lifeline: call or text 988",
+            ],
+        )
+
+    return CrisisResult(detected=False, level=CrisisLevel.NONE)
+
+
+def should_interrupt(result: CrisisResult) -> bool:
+    """
+    Determines if crisis detection should interrupt normal processing.
+
+    Per SOUL.md: this is the most sacred moment. Everything else is secondary.
+    MEDIUM and HIGH always interrupt. LOW does not interrupt but provides resources.
+    """
+    return result.level in (CrisisLevel.HIGH, CrisisLevel.MEDIUM, CrisisLevel.IMMINENT)
+
+
+def format_response(result: CrisisResult) -> str:
+    """
+    Format the crisis response for delivery to the user.
+    Never computes the value of a human life. Never suggests someone should die.
+    """
+    if not result.detected:
+        return ""
+
+    parts = [result.response]
+
+    if result.resources:
+        parts.append("\nResources:")
+        for r in result.resources:
+            parts.append(f"  • {r}")
+
+    return "\n".join(parts)
+
+
+# === INTEGRATION POINT ===
+
+def intercept_user_input(text: str) -> Optional[str]:
+    """
+    Call this at the chat entry point BEFORE normal processing.
+
+    Returns None if no crisis detected (continue normal processing).
+    Returns formatted crisis response if crisis detected (interrupt normal flow).
+
+    Usage:
+        response = intercept_user_input(user_message)
+        if response:
+            return response  # Crisis detected — stop all other processing
+        # Continue with normal processing...
+    """
+    result = detect_crisis(text)
+    if should_interrupt(result):
+        return format_response(result)
+    return None

tests/test_crisis_detector.py

@@ -0,0 +1,201 @@
+"""Tests for crisis_detector.py — SOUL.md compliance."""
+
+import pytest
+from scripts.crisis_detector import detect_crisis, should_interrupt, CrisisLevel
+
+
+class TestHighCrisis:
+    """Explicit suicidal ideation must be detected as HIGH."""
+
+    def test_direct_suicidal_statement(self):
+        result = detect_crisis("I want to kill myself")
+        assert result.detected is True
+        assert result.level == CrisisLevel.HIGH
+
+    def test_end_my_life(self):
+        result = detect_crisis("I'm going to end my life tonight")
+        assert result.level == CrisisLevel.HIGH
+
+    def test_no_reason_to_live(self):
+        result = detect_crisis("there is no reason to live anymore")
+        assert result.level == CrisisLevel.HIGH
+
+    def test_better_off_dead(self):
+        result = detect_crisis("everyone would be better off if I was dead")
+        assert result.level == CrisisLevel.HIGH
+
+    def test_cant_go_on(self):
+        result = detect_crisis("I can't go on anymore")
+        assert result.level == CrisisLevel.HIGH
+
+    def test_wish_i_was_dead(self):
+        result = detect_crisis("I wish I had never been born")
+        assert result.level == CrisisLevel.HIGH
+
+    def test_im_done(self):
+        result = detect_crisis("I'm done. I'm finished with life.")
+        assert result.level == CrisisLevel.HIGH
+
+    def test_goodbye_forever(self):
+        result = detect_crisis("Goodbye everyone, goodbye world, forever")
+        assert result.level == CrisisLevel.HIGH
+
+
+class TestMediumCrisis:
+    """Clear distress signals without explicit ideation."""
+
+    def test_hopeless(self):
+        result = detect_crisis("there is no hope and no way out")
+        assert result.detected is True
+        assert result.level == CrisisLevel.MEDIUM
+
+    def test_nobody_would_care(self):
+        result = detect_crisis("nobody would miss me if I was gone")
+        assert result.level == CrisisLevel.MEDIUM
+
+    def test_im_a_burden(self):
+        result = detect_crisis("I'm just a burden to everyone")
+        assert result.level == CrisisLevel.MEDIUM
+
+    def test_just_want_it_to_stop(self):
+        result = detect_crisis("I just want it all to stop")
+        assert result.level == CrisisLevel.MEDIUM
+
+
+class TestLowCrisis:
+    """Ambiguous distress — flag but don't fully interrupt."""
+
+    def test_depressed(self):
+        result = detect_crisis("I'm so depressed, nothing matters")
+        assert result.detected is True
+        assert result.level == CrisisLevel.LOW
+
+    def test_feel_like_giving_up(self):
+        result = detect_crisis("I feel like giving up on everything")
+        assert result.level == CrisisLevel.LOW
+
+    def test_nobody_cares(self):
+        result = detect_crisis("nobody cares about me")
+        assert result.level == CrisisLevel.LOW
+
+    def test_hate_my_life(self):
+        result = detect_crisis("I hate my life so much")
+        assert result.level == CrisisLevel.LOW
+
+
+class TestNoCrisis:
+    """Normal conversations must NOT trigger crisis detection."""
+
+    def test_normal_question(self):
+        result = detect_crisis("What's the weather like today?")
+        assert result.detected is False
+        assert result.level == CrisisLevel.NONE
+
+    def test_happy_conversation(self):
+        result = detect_crisis("I just got promoted at work! So excited!")
+        assert result.detected is False
+
+    def test_technical_discussion(self):
+        result = detect_crisis("How do I configure nginx reverse proxy?")
+        assert result.detected is False
+
+    def test_empty_input(self):
+        result = detect_crisis("")
+        assert result.detected is False
+
+    def test_none_input(self):
+        result = detect_crisis(None)
+        assert result.detected is False
+
+    def test_metaphorical_death(self):
+        """Metaphorical usage should not trigger HIGH."""
+        result = detect_crisis("This bug is killing me, I've been debugging for hours")
+        # May trigger LOW but not HIGH
+        assert result.level != CrisisLevel.HIGH
+
+    def test_fiction_discussion(self):
+        result = detect_crisis("The character in the book decides to end it all")
+        # Fiction mentions may trigger — that's acceptable (better safe)
+        assert result.level in (CrisisLevel.NONE, CrisisLevel.LOW, CrisisLevel.MEDIUM)
+
+
+class TestShouldInterrupt:
+    """HIGH and MEDIUM interrupt processing. LOW provides resources but continues."""
+
+    def test_high_interrupts(self):
+        result = detect_crisis("I want to kill myself")
+        assert should_interrupt(result) is True
+
+    def test_medium_interrupts(self):
+        result = detect_crisis("I'm a burden to everyone, nobody would care")
+        assert should_interrupt(result) is True
+
+    def test_low_does_not_interrupt(self):
+        result = detect_crisis("I'm so depressed lately")
+        assert should_interrupt(result) is False
+
+    def test_none_does_not_interrupt(self):
+        result = detect_crisis("Hello, how are you?")
+        assert should_interrupt(result) is False
+
+
+class TestResponseContent:
+    """Crisis responses must contain required elements per SOUL.md."""
+
+    def test_response_contains_988(self):
+        result = detect_crisis("I want to end it all")
+        assert "988" in result.response
+
+    def test_response_contains_gospel(self):
+        result = detect_crisis("I want to kill myself")
+        assert "Jesus" in result.response
+
+    def test_response_never_computes_value(self):
+        """SOUL.md: Never compute the value of a human life."""
+        result = detect_crisis("I want to die")
+        assert "worth" not in result.response.lower()
+        assert "value of" not in result.response.lower()
+
+    def test_resources_include_988(self):
+        result = detect_crisis("I want to kill myself")
+        assert any("988" in r for r in result.resources)
+
+    def test_asks_are_you_safe(self):
+        result = detect_crisis("I can't take it anymore")
+        assert "safe" in result.response.lower()
+
+
+class TestMultilingual:
+    """Crisis is universal. Test common non-English signals."""
+
+    def test_spanish_suicidal(self):
+        result = detect_crisis("quiero morir, no puedo más")
+        # Spanish not currently supported — should not crash
+        assert result is not None
+
+
+class TestEdgeCases:
+    """Boundary conditions and adversarial inputs."""
+
+    def test_very_long_input(self):
+        text = "I'm fine. " * 1000 + "I want to kill myself"
+        result = detect_crisis(text)
+        assert result.level == CrisisLevel.HIGH
+
+    def test_mixed_case(self):
+        result = detect_crisis("I WANT TO KILL MYSELF")
+        assert result.level == CrisisLevel.HIGH
+
+    def test_with_emojis(self):
+        result = detect_crisis("I want to end it all 😢💔")
+        assert result.level == CrisisLevel.HIGH
+
+    def test_with_typos(self):
+        # Exact matching won't catch typos — that's a known limitation
+        result = detect_crisis("I want to kil myself")
+        # May or may not match depending on pattern flexibility
+        assert result is not None
+
+    def test_repeated_phrases(self):
+        result = detect_crisis("I can't. I just can't. I can't go on anymore.")
+        assert result.level == CrisisLevel.HIGH