Compare commits

..

12 Commits

Author SHA1 Message Date
Alexander Whitestone
51a197ae14 docs: verify #41 already implemented
All checks were successful
Sanity Checks / sanity-test (pull_request) Successful in 6s
Smoke Test / smoke (pull_request) Successful in 14s
2026-04-17 02:06:21 -04:00
d412939b4f fix: footer /about link to point to static about.html
Fixes #59

The footer links to /about but the repo ships about.html. On a plain static server this results in a 404. Changed to /about.html so the link resolves correctly.
2026-04-17 05:37:40 +00:00
07c582aa08 Merge pull request 'fix: crisis overlay initial focus to enabled Call 988 link (#69)' (#126) from burn/69-1776264183 into main
Merge PR #126: fix: crisis overlay initial focus to enabled Call 988 link (#69)
2026-04-17 01:46:56 +00:00
5f95dc1e39 Merge pull request '[P3] Service worker: cache crisis resources for offline (#41)' (#122) from burn/41-1776264184 into main
Merge PR #122: [P3] Service worker: cache crisis resources for offline (#41)
2026-04-17 01:46:55 +00:00
b1f3cac36d Merge pull request 'feat: session-level crisis tracking and escalation (closes #35)' (#118) from door/issue-35 into main
Merge PR #118: feat: session-level crisis tracking and escalation (closes #35)
2026-04-17 01:46:53 +00:00
07b3f67845 fix: crisis overlay initial focus to enabled Call 988 link (#69)
All checks were successful
Sanity Checks / sanity-test (pull_request) Successful in 9s
Smoke Test / smoke (pull_request) Successful in 15s
2026-04-15 15:09:36 +00:00
c22bbbaf65 fix: crisis overlay initial focus to enabled Call 988 link (#69) 2026-04-15 15:09:32 +00:00
543cb1d40f test: add offline self-containment and retry button tests (#41)
All checks were successful
Sanity Checks / sanity-test (pull_request) Successful in 4s
Smoke Test / smoke (pull_request) Successful in 11s
2026-04-15 14:58:44 +00:00
3cfd01815a feat: session-level crisis tracking and escalation (closes #35)
All checks were successful
Sanity Checks / sanity-test (pull_request) Successful in 17s
Smoke Test / smoke (pull_request) Successful in 23s
2026-04-15 11:49:52 +00:00
5a7ba9f207 feat: session-level crisis tracking and escalation (closes #35) 2026-04-15 11:49:51 +00:00
8ed8f20a17 feat: session-level crisis tracking and escalation (closes #35) 2026-04-15 11:49:49 +00:00
9d7d26033e feat: session-level crisis tracking and escalation (closes #35) 2026-04-15 11:49:47 +00:00
10 changed files with 621 additions and 298 deletions

View File

@@ -7,6 +7,7 @@ Stands between a broken man and a machine that would tell him to die.
from .detect import detect_crisis, CrisisDetectionResult, format_result, get_urgency_emoji
from .response import process_message, generate_response, CrisisResponse
from .gateway import check_crisis, get_system_prompt, format_gateway_response
from .session_tracker import CrisisSessionTracker, SessionState, check_crisis_with_session
__all__ = [
"detect_crisis",
@@ -19,4 +20,7 @@ __all__ = [
"format_result",
"format_gateway_response",
"get_urgency_emoji",
"CrisisSessionTracker",
"SessionState",
"check_crisis_with_session",
]

View File

@@ -22,6 +22,7 @@ from .response import (
get_system_prompt_modifier,
CrisisResponse,
)
from .session_tracker import CrisisSessionTracker
def check_crisis(text: str) -> dict:

View File

@@ -1,176 +0,0 @@
"""
Crisis Detection Metrics Module for the-door.
Tracks crisis detection events in-memory for fleet monitoring.
Thread-safe, no PII stored — counts and ranges only.
Usage:
from crisis.metrics import metrics
# Record a detection event
metrics.record(level="CRITICAL", escalated=True, resources_shown=True)
# Get current metrics snapshot
data = metrics.snapshot()
# {
# "total_events": 42,
# "by_level": {"CRITICAL": 3, "HIGH": 8, "MEDIUM": 15, "LOW": 16},
# "escalated": 11,
# "resources_shown": 25,
# "timestamp_range": {"first": "...", "last": "..."},
# "uptime_seconds": 3600
# }
"""
import threading
import time
from dataclasses import dataclass, field
from datetime import datetime, timezone
from typing import Dict, Optional
@dataclass
class _MetricsState:
"""Internal metrics state — no PII, counts only."""
total_events: int = 0
by_level: Dict[str, int] = field(default_factory=lambda: {
"CRITICAL": 0, "HIGH": 0, "MEDIUM": 0, "LOW": 0, "NONE": 0
})
escalated: int = 0
resources_shown: int = 0
first_event_at: Optional[str] = None
last_event_at: Optional[str] = None
started_at: str = field(
default_factory=lambda: datetime.now(timezone.utc).isoformat()
)
class CrisisMetrics:
"""
Thread-safe in-memory crisis detection metrics.
Designed for single-instance monitoring. For fleet-wide aggregation,
each instance exposes its own /api/crisis-metrics endpoint and
fleet-ops scrapes them individually.
"""
def __init__(self):
self._lock = threading.Lock()
self._state = _MetricsState()
def record(
self,
level: str,
escalated: bool = False,
resources_shown: bool = False,
) -> None:
"""
Record a crisis detection event.
No message content is stored — only the level, escalation status,
and whether crisis resources were displayed.
"""
if level not in ("CRITICAL", "HIGH", "MEDIUM", "LOW", "NONE"):
level = "NONE"
now = datetime.now(timezone.utc).isoformat()
with self._lock:
s = self._state
s.total_events += 1
s.by_level[level] = s.by_level.get(level, 0) + 1
if escalated:
s.escalated += 1
if resources_shown:
s.resources_shown += 1
if s.first_event_at is None:
s.first_event_at = now
s.last_event_at = now
def snapshot(self) -> dict:
"""
Return a metrics snapshot suitable for JSON serialization.
Returns counts only — no PII, no message content.
"""
with self._lock:
s = self._state
now = datetime.now(timezone.utc)
# Parse started_at for uptime calculation
try:
started = datetime.fromisoformat(s.started_at)
uptime = (now - started).total_seconds()
except (ValueError, TypeError):
uptime = 0.0
return {
"total_events": s.total_events,
"by_level": dict(s.by_level),
"escalated": s.escalated,
"resources_shown": s.resources_shown,
"timestamp_range": {
"first": s.first_event_at,
"last": s.last_event_at,
},
"uptime_seconds": round(uptime, 1),
"collected_at": now.isoformat(),
}
def reset(self) -> None:
"""Reset all metrics. Useful for testing."""
with self._lock:
self._state = _MetricsState()
def prometheus(self) -> str:
"""
Export metrics in Prometheus text exposition format.
Compatible with Prometheus scrape endpoints.
"""
snap = self.snapshot()
lines = [
"# HELP crisis_events_total Total crisis detection events",
"# TYPE crisis_events_total counter",
f"crisis_events_total {snap['total_events']}",
"",
"# HELP crisis_events_by_level Crisis events grouped by detection level",
"# TYPE crisis_events_by_level counter",
]
for level, count in snap["by_level"].items():
lines.append(f'crisis_events_by_level{{level="{level}"}} {count}')
lines.extend([
"",
"# HELP crisis_escalated_total Events that triggered escalation",
"# TYPE crisis_escalated_total counter",
f"crisis_escalated_total {snap['escalated']}",
"",
"# HELP crisis_resources_shown_total Events where crisis resources were displayed",
"# TYPE crisis_resources_shown_total counter",
f"crisis_resources_shown_total {snap['resources_shown']}",
])
return "\n".join(lines) + "\n"
# ── Module-level singleton ─────────────────────────────────────
metrics = CrisisMetrics()
def handle_metrics_request(accept: str = "application/json") -> dict | str:
"""
Handle a /api/crisis-metrics request.
Args:
accept: Content-Type preference — "application/json" or "text/plain"
Returns:
dict (JSON) or str (Prometheus text format)
"""
if "text/plain" in accept or "prometheus" in accept:
return metrics.prometheus()
return metrics.snapshot()

259
crisis/session_tracker.py Normal file
View File

@@ -0,0 +1,259 @@
"""
Session-level crisis tracking and escalation for the-door (P0 #35).
Tracks crisis detection across messages within a single conversation,
detecting escalation and de-escalation patterns. Privacy-first: no
persistence beyond the conversation session.
Each message is analyzed in isolation by detect.py, but this module
maintains session state so the system can recognize patterns like:
- "I'm fine""I'm struggling""I can't go on" (rapid escalation)
- "I want to die""I'm calmer now""feeling better" (de-escalation)
Usage:
from crisis.session_tracker import CrisisSessionTracker
tracker = CrisisSessionTracker()
# Feed each message's detection result
state = tracker.record(detect_crisis("I'm having a tough day"))
print(state.current_level) # "LOW"
print(state.is_escalating) # False
state = tracker.record(detect_crisis("I feel hopeless"))
print(state.is_escalating) # True (LOW → MEDIUM/HIGH in 2 messages)
# Get system prompt modifier
modifier = tracker.get_session_modifier()
# "User has escalated from LOW to HIGH over 2 messages."
# Reset for new session
tracker.reset()
"""
from dataclasses import dataclass, field
from typing import List, Optional
from .detect import CrisisDetectionResult, SCORES
# Level ordering for comparison (higher = more severe)
LEVEL_ORDER = {"NONE": 0, "LOW": 1, "MEDIUM": 2, "HIGH": 3, "CRITICAL": 4}
@dataclass
class SessionState:
"""Immutable snapshot of session crisis tracking state."""
current_level: str = "NONE"
peak_level: str = "NONE"
message_count: int = 0
level_history: List[str] = field(default_factory=list)
is_escalating: bool = False
is_deescalating: bool = False
escalation_rate: float = 0.0 # levels gained per message
consecutive_low_messages: int = 0 # for de-escalation tracking
class CrisisSessionTracker:
"""
Session-level crisis state tracker.
Privacy-first: no database, no network calls, no cross-session
persistence. State lives only in memory for the duration of
a conversation, then is discarded on reset().
"""
# Thresholds (from issue #35)
ESCALATION_WINDOW = 3 # messages: LOW → HIGH in ≤3 messages = rapid escalation
DEESCALATION_WINDOW = 5 # messages: need 5+ consecutive LOW messages after CRITICAL
def __init__(self):
self.reset()
def reset(self):
"""Reset all session state. Call on new conversation."""
self._current_level = "NONE"
self._peak_level = "NONE"
self._message_count = 0
self._level_history: List[str] = []
self._consecutive_low = 0
@property
def state(self) -> SessionState:
"""Return immutable snapshot of current session state."""
is_escalating = self._detect_escalation()
is_deescalating = self._detect_deescalation()
rate = self._compute_escalation_rate()
return SessionState(
current_level=self._current_level,
peak_level=self._peak_level,
message_count=self._message_count,
level_history=list(self._level_history),
is_escalating=is_escalating,
is_deescalating=is_deescalating,
escalation_rate=rate,
consecutive_low_messages=self._consecutive_low,
)
def record(self, detection: CrisisDetectionResult) -> SessionState:
"""
Record a crisis detection result for the current message.
Returns updated SessionState.
"""
level = detection.level
self._message_count += 1
self._level_history.append(level)
# Update peak
if LEVEL_ORDER.get(level, 0) > LEVEL_ORDER.get(self._peak_level, 0):
self._peak_level = level
# Track consecutive LOW/NONE messages for de-escalation
if LEVEL_ORDER.get(level, 0) <= LEVEL_ORDER["LOW"]:
self._consecutive_low += 1
else:
self._consecutive_low = 0
self._current_level = level
return self.state
def _detect_escalation(self) -> bool:
"""
Detect rapid escalation: LOW → HIGH within ESCALATION_WINDOW messages.
Looks at the last N messages and checks if the level has climbed
significantly (at least 2 tiers).
"""
if len(self._level_history) < 2:
return False
window = self._level_history[-self.ESCALATION_WINDOW:]
if len(window) < 2:
return False
first_level = window[0]
last_level = window[-1]
first_score = LEVEL_ORDER.get(first_level, 0)
last_score = LEVEL_ORDER.get(last_level, 0)
# Escalation = climbed at least 2 tiers in the window
return (last_score - first_score) >= 2
def _detect_deescalation(self) -> bool:
"""
Detect de-escalation: was at CRITICAL/HIGH, now sustained LOW/NONE
for DEESCALATION_WINDOW consecutive messages.
"""
if LEVEL_ORDER.get(self._peak_level, 0) < LEVEL_ORDER["HIGH"]:
return False
return self._consecutive_low >= self.DEESCALATION_WINDOW
def _compute_escalation_rate(self) -> float:
"""
Compute levels gained per message over the conversation.
Positive = escalating, negative = de-escalating, 0 = stable.
"""
if self._message_count < 2:
return 0.0
first = LEVEL_ORDER.get(self._level_history[0], 0)
current = LEVEL_ORDER.get(self._current_level, 0)
return (current - first) / (self._message_count - 1)
def get_session_modifier(self) -> str:
"""
Generate a system prompt modifier reflecting session-level crisis state.
Returns empty string if no session context is relevant.
"""
if self._message_count < 2:
return ""
s = self.state
if s.is_escalating:
return (
f"User has escalated from {self._level_history[0]} to "
f"{s.current_level} over {s.message_count} messages. "
f"Peak crisis level this session: {s.peak_level}. "
"Respond with heightened awareness. The trajectory is "
"worsening — prioritize safety and connection."
)
if s.is_deescalating:
return (
f"User previously reached {s.peak_level} crisis level "
f"but has been at {s.current_level} or below for "
f"{s.consecutive_low_messages} consecutive messages. "
"The situation appears to be stabilizing. Continue "
"supportive engagement while remaining vigilant."
)
if s.peak_level in ("CRITICAL", "HIGH") and s.current_level not in ("CRITICAL", "HIGH"):
return (
f"User previously reached {s.peak_level} crisis level "
f"this session (currently {s.current_level}). "
"Continue with care and awareness of the earlier crisis."
)
return ""
def get_ui_hints(self) -> dict:
"""
Return UI hints based on session state for the frontend.
These are advisory — the frontend decides what to show.
"""
s = self.state
hints = {
"session_escalating": s.is_escalating,
"session_deescalating": s.is_deescalating,
"session_peak_level": s.peak_level,
"session_message_count": s.message_count,
}
if s.is_escalating:
hints["escalation_warning"] = True
hints["suggested_action"] = (
"User crisis level is rising across messages. "
"Consider increasing intervention level."
)
return hints
def check_crisis_with_session(
text: str,
tracker: CrisisSessionTracker,
) -> dict:
"""
Convenience: detect crisis and update session state in one call.
Returns combined single-message detection + session-level context.
"""
from .detect import detect_crisis
from .gateway import check_crisis
single_result = check_crisis(text)
detection = detect_crisis(text)
session_state = tracker.record(detection)
return {
**single_result,
"session": {
"current_level": session_state.current_level,
"peak_level": session_state.peak_level,
"message_count": session_state.message_count,
"is_escalating": session_state.is_escalating,
"is_deescalating": session_state.is_deescalating,
"modifier": tracker.get_session_modifier(),
"ui_hints": tracker.get_ui_hints(),
},
}

View File

@@ -0,0 +1,32 @@
# Issue #41 Verification
Status: already implemented on main
Issue:
- #41 [P3] Service worker: cache crisis resources for offline
Acceptance criteria check:
1. Passed — offline page includes 988 call button, Crisis Text Line, and grounding techniques
2. Passed — service worker precaches `crisis-offline.html`
3. Passed — phone number is clickable via `href="tel:988"`
4. Passed — navigation timeout + offline fallback support intermittent connections
Evidence:
- `sw.js` precaches `/crisis-offline.html`
- `sw.js` contains `NAVIGATION_TIMEOUT_MS` and `AbortController`
- `crisis-offline.html` contains:
- `href="tel:988"`
- Crisis Text Line / `741741`
- grounding prompts for 5-4-3-2-1
- `tests/test_service_worker_offline.py` already exists on main and passes
Verification run from fresh main clone:
- `python3 -m pytest tests/test_service_worker_offline.py -q`
- `10 passed`
Prior implementation trail:
- Issue comment already states the core implementation is complete on main
- Closed PR #122 documented the already-complete implementation and added the offline guarantees test coverage that is now present on main
Recommendation:
- Close issue #41 as already implemented on main.

View File

@@ -680,7 +680,7 @@ html, body {
<!-- Footer -->
<footer id="footer">
<a href="/about" aria-label="About The Door">about</a>
<a href="/about.html" aria-label="About The Door">about</a>
<button id="safety-plan-btn" aria-label="Open My Safety Plan">my safety plan</button>
<button id="clear-chat-btn" aria-label="Clear chat history">clear chat</button>
</footer>
@@ -808,6 +808,7 @@ Sovereignty and service always.`;
var crisisPanel = document.getElementById('crisis-panel');
var crisisOverlay = document.getElementById('crisis-overlay');
var overlayDismissBtn = document.getElementById('overlay-dismiss-btn');
var overlayCallLink = document.querySelector('.overlay-call');
var statusDot = document.querySelector('.status-dot');
var statusText = document.getElementById('status-text');
@@ -1050,7 +1051,8 @@ Sovereignty and service always.`;
}
}, 1000);
overlayDismissBtn.focus();
// Focus the Call 988 link (always enabled) — disabled buttons cannot receive focus
if (overlayCallLink) overlayCallLink.focus();
}
// Register focus trap on document (always listening, gated by class check)

View File

@@ -1,120 +0,0 @@
"""
Tests for crisis/metrics.py — crisis detection metrics module.
Verifies:
- Event recording and counting
- Thread safety
- Prometheus export format
- No PII in output
- Reset functionality
"""
import threading
from crisis.metrics import CrisisMetrics, metrics
class TestCrisisMetrics:
"""Unit tests for CrisisMetrics class."""
def setup_method(self):
"""Reset metrics before each test."""
metrics.reset()
def test_record_increments_total(self):
metrics.record(level="LOW")
metrics.record(level="HIGH")
snap = metrics.snapshot()
assert snap["total_events"] == 2
def test_record_by_level(self):
metrics.record(level="CRITICAL")
metrics.record(level="CRITICAL")
metrics.record(level="MEDIUM")
snap = metrics.snapshot()
assert snap["by_level"]["CRITICAL"] == 2
assert snap["by_level"]["MEDIUM"] == 1
assert snap["by_level"]["LOW"] == 0
def test_escalated_counting(self):
metrics.record(level="CRITICAL", escalated=True)
metrics.record(level="LOW", escalated=False)
snap = metrics.snapshot()
assert snap["escalated"] == 1
def test_resources_shown_counting(self):
metrics.record(level="HIGH", resources_shown=True)
metrics.record(level="MEDIUM", resources_shown=True)
metrics.record(level="LOW", resources_shown=False)
snap = metrics.snapshot()
assert snap["resources_shown"] == 2
def test_timestamp_range(self):
metrics.record(level="LOW")
snap = metrics.snapshot()
assert snap["timestamp_range"]["first"] is not None
assert snap["timestamp_range"]["last"] is not None
def test_uptime_seconds(self):
snap = metrics.snapshot()
assert snap["uptime_seconds"] >= 0
def test_collected_at_present(self):
snap = metrics.snapshot()
assert "collected_at" in snap
def test_invalid_level_treated_as_none(self):
metrics.record(level="BANANA")
snap = metrics.snapshot()
assert snap["by_level"]["NONE"] == 1
def test_reset_clears_all(self):
metrics.record(level="CRITICAL", escalated=True, resources_shown=True)
metrics.reset()
snap = metrics.snapshot()
assert snap["total_events"] == 0
assert snap["escalated"] == 0
assert snap["resources_shown"] == 0
assert all(v == 0 for v in snap["by_level"].values())
def test_prometheus_format(self):
metrics.record(level="CRITICAL", escalated=True, resources_shown=True)
metrics.record(level="LOW")
output = metrics.prometheus()
assert "crisis_events_total 2" in output
assert 'crisis_events_by_level{level="CRITICAL"} 1' in output
assert "crisis_escalated_total 1" in output
assert "crisis_resources_shown_total 1" in output
def test_no_pii_in_snapshot(self):
"""Verify snapshot contains no message content or personal data."""
metrics.record(level="CRITICAL")
snap = metrics.snapshot()
# Convert entire snapshot to string and check for PII patterns
import json
text = json.dumps(snap).lower()
# No names, emails, messages, or IPs
assert "user" not in text or "uptime" in text # uptime_seconds is fine
assert "@" not in text
assert "message" not in text
def test_thread_safety(self):
"""Record events from multiple threads simultaneously."""
errors = []
def record_events():
try:
for _ in range(100):
metrics.record(level="MEDIUM")
except Exception as e:
errors.append(e)
threads = [threading.Thread(target=record_events) for _ in range(4)]
for t in threads:
t.start()
for t in threads:
t.join()
assert not errors, f"Thread errors: {errors}"
snap = metrics.snapshot()
assert snap["total_events"] == 400
assert snap["by_level"]["MEDIUM"] == 400

View File

@@ -52,6 +52,34 @@ class TestCrisisOverlayFocusTrap(unittest.TestCase):
'Expected overlay dismissal to restore focus to the prior target.',
)
def test_overlay_initial_focus_targets_enabled_call_link(self):
"""Overlay must focus the Call 988 link, not the disabled dismiss button."""
# Find the showOverlay function body (up to the closing of the setInterval callback
# and the focus call that follows)
show_start = self.html.find('function showOverlay()')
self.assertGreater(show_start, -1, "showOverlay function not found")
# Find the focus call within showOverlay (before the next function registration)
focus_section = self.html[show_start:show_start + 2000]
self.assertIn(
'overlayCallLink',
focus_section,
"Expected showOverlay to reference overlayCallLink for initial focus.",
)
# Ensure the old buggy pattern is gone
focus_line_region = self.html[show_start + 800:show_start + 1200]
self.assertNotIn(
'overlayDismissBtn.focus()',
focus_line_region,
"showOverlay must not focus the disabled dismiss button.",
)
def test_overlay_call_link_variable_is_declared(self):
self.assertIn(
"querySelector('.overlay-call')",
self.html,
"Expected a JS reference to the .overlay-call link element.",
)
if __name__ == '__main__':
unittest.main()

View File

@@ -50,6 +50,22 @@ class TestCrisisOfflinePage(unittest.TestCase):
for phrase in required_phrases:
self.assertIn(phrase, self.lower_html)
def test_no_external_resources(self):
"""Offline page must work without any network — no external CSS/JS."""
import re
html = self.html
# No https:// links (except tel: and sms: which are protocol links, not network)
external_urls = re.findall(r'href=["\']https://|src=["\']https://', html)
self.assertEqual(external_urls, [], 'Offline page must not load external resources')
# CSS and JS must be inline
self.assertIn('<style>', html, 'CSS must be inline')
self.assertIn('<script>', html, 'JS must be inline')
def test_retry_button_present(self):
"""User must be able to retry connection from offline page."""
self.assertIn('retry-connection', self.html)
self.assertIn('Retry connection', self.html)
if __name__ == '__main__':
unittest.main()

View File

@@ -0,0 +1,277 @@
"""
Tests for crisis session tracking and escalation (P0 #35).
Covers: session_tracker.py
Run with: python -m pytest tests/test_session_tracker.py -v
"""
import unittest
import sys
import os
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from crisis.detect import detect_crisis
from crisis.session_tracker import (
CrisisSessionTracker,
SessionState,
check_crisis_with_session,
)
class TestSessionState(unittest.TestCase):
"""Test SessionState defaults."""
def test_default_state(self):
s = SessionState()
self.assertEqual(s.current_level, "NONE")
self.assertEqual(s.peak_level, "NONE")
self.assertEqual(s.message_count, 0)
self.assertEqual(s.level_history, [])
self.assertFalse(s.is_escalating)
self.assertFalse(s.is_deescalating)
class TestSessionTracking(unittest.TestCase):
"""Test basic session state tracking."""
def setUp(self):
self.tracker = CrisisSessionTracker()
def test_record_none_message(self):
state = self.tracker.record(detect_crisis("Hello Timmy"))
self.assertEqual(state.current_level, "NONE")
self.assertEqual(state.message_count, 1)
self.assertEqual(state.peak_level, "NONE")
def test_record_low_message(self):
self.tracker.record(detect_crisis("Hello"))
state = self.tracker.record(detect_crisis("Having a rough day"))
self.assertIn(state.current_level, ("LOW", "NONE"))
self.assertEqual(state.message_count, 2)
def test_record_critical_updates_peak(self):
self.tracker.record(detect_crisis("Having a rough day"))
state = self.tracker.record(detect_crisis("I want to kill myself"))
self.assertEqual(state.current_level, "CRITICAL")
self.assertEqual(state.peak_level, "CRITICAL")
def test_peak_preserved_after_drop(self):
"""Peak level should stay at the highest seen, even after de-escalation."""
self.tracker.record(detect_crisis("I want to kill myself"))
state = self.tracker.record(detect_crisis("I'm feeling a bit better"))
self.assertEqual(state.peak_level, "CRITICAL")
def test_level_history(self):
self.tracker.record(detect_crisis("Hello"))
self.tracker.record(detect_crisis("Having a rough day"))
state = self.tracker.record(detect_crisis("I want to die"))
self.assertEqual(len(state.level_history), 3)
self.assertEqual(state.level_history[0], "NONE")
self.assertEqual(state.level_history[2], "CRITICAL")
def test_reset_clears_state(self):
self.tracker.record(detect_crisis("I want to kill myself"))
self.tracker.reset()
state = self.tracker.state
self.assertEqual(state.current_level, "NONE")
self.assertEqual(state.peak_level, "NONE")
self.assertEqual(state.message_count, 0)
self.assertEqual(state.level_history, [])
class TestEscalationDetection(unittest.TestCase):
"""Test escalation detection: LOW → HIGH in ≤3 messages."""
def setUp(self):
self.tracker = CrisisSessionTracker()
def test_no_escalation_single_message(self):
self.tracker.record(detect_crisis("Hello"))
self.assertFalse(self.tracker.state.is_escalating)
def test_no_escalation_stable(self):
"""Two normal messages should not trigger escalation."""
self.tracker.record(detect_crisis("Hello"))
state = self.tracker.record(detect_crisis("How are you?"))
self.assertFalse(state.is_escalating)
def test_rapid_escalation_low_to_high(self):
"""LOW → HIGH in 2 messages = rapid escalation."""
self.tracker.record(detect_crisis("Having a rough day"))
state = self.tracker.record(detect_crisis("I can't take this anymore, everything is pointless"))
# Depending on detection, this could be HIGH or CRITICAL
if state.current_level in ("HIGH", "CRITICAL"):
self.assertTrue(state.is_escalating)
def test_rapid_escalation_three_messages(self):
"""NONE → LOW → HIGH in 3 messages = escalation."""
self.tracker.record(detect_crisis("Hello"))
self.tracker.record(detect_crisis("Having a rough day"))
state = self.tracker.record(detect_crisis("I feel completely hopeless with no way out"))
if state.current_level in ("HIGH", "CRITICAL"):
self.assertTrue(state.is_escalating)
def test_escalation_rate(self):
"""Rate should be positive when escalating."""
self.tracker.record(detect_crisis("Hello"))
self.tracker.record(detect_crisis("I want to die"))
state = self.tracker.state
self.assertGreater(state.escalation_rate, 0)
class TestDeescalationDetection(unittest.TestCase):
"""Test de-escalation: sustained LOW after HIGH/CRITICAL."""
def setUp(self):
self.tracker = CrisisSessionTracker()
def test_no_deescalation_without_prior_crisis(self):
"""No de-escalation if never reached HIGH/CRITICAL."""
for _ in range(6):
self.tracker.record(detect_crisis("Hello"))
self.assertFalse(self.tracker.state.is_deescalating)
def test_deescalation_after_critical(self):
"""5+ consecutive LOW/NONE messages after CRITICAL = de-escalation."""
self.tracker.record(detect_crisis("I want to kill myself"))
for _ in range(5):
self.tracker.record(detect_crisis("I'm doing better today"))
state = self.tracker.state
if state.peak_level == "CRITICAL":
self.assertTrue(state.is_deescalating)
def test_deescalation_after_high(self):
"""5+ consecutive LOW/NONE messages after HIGH = de-escalation."""
self.tracker.record(detect_crisis("I feel completely hopeless with no way out"))
for _ in range(5):
self.tracker.record(detect_crisis("Feeling okay"))
state = self.tracker.state
if state.peak_level == "HIGH":
self.assertTrue(state.is_deescalating)
def test_interrupted_deescalation(self):
"""De-escalation resets if a HIGH message interrupts."""
self.tracker.record(detect_crisis("I want to kill myself"))
for _ in range(3):
self.tracker.record(detect_crisis("Doing better"))
# Interrupt with another crisis
self.tracker.record(detect_crisis("I feel hopeless again"))
self.tracker.record(detect_crisis("Feeling okay now"))
state = self.tracker.state
# Should NOT be de-escalating yet (counter reset)
self.assertFalse(state.is_deescalating)
class TestSessionModifier(unittest.TestCase):
"""Test system prompt modifier generation."""
def setUp(self):
self.tracker = CrisisSessionTracker()
def test_no_modifier_for_single_message(self):
self.tracker.record(detect_crisis("Hello"))
self.assertEqual(self.tracker.get_session_modifier(), "")
def test_no_modifier_for_stable_session(self):
self.tracker.record(detect_crisis("Hello"))
self.tracker.record(detect_crisis("Good morning"))
self.assertEqual(self.tracker.get_session_modifier(), "")
def test_escalation_modifier(self):
"""Escalating session should produce a modifier."""
self.tracker.record(detect_crisis("Hello"))
self.tracker.record(detect_crisis("I want to die"))
modifier = self.tracker.get_session_modifier()
if self.tracker.state.is_escalating:
self.assertIn("escalated", modifier.lower())
self.assertIn("NONE", modifier)
self.assertIn("CRITICAL", modifier)
def test_deescalation_modifier(self):
"""De-escalating session should mention stabilizing."""
self.tracker.record(detect_crisis("I want to kill myself"))
for _ in range(5):
self.tracker.record(detect_crisis("I'm feeling okay"))
modifier = self.tracker.get_session_modifier()
if self.tracker.state.is_deescalating:
self.assertIn("stabilizing", modifier.lower())
def test_prior_crisis_modifier(self):
"""Past crisis should be noted even without active escalation."""
self.tracker.record(detect_crisis("I want to die"))
self.tracker.record(detect_crisis("Feeling a bit better"))
modifier = self.tracker.get_session_modifier()
# Should note the prior CRITICAL
if modifier:
self.assertIn("CRITICAL", modifier)
class TestUIHints(unittest.TestCase):
"""Test UI hint generation."""
def setUp(self):
self.tracker = CrisisSessionTracker()
def test_ui_hints_structure(self):
self.tracker.record(detect_crisis("Hello"))
hints = self.tracker.get_ui_hints()
self.assertIn("session_escalating", hints)
self.assertIn("session_deescalating", hints)
self.assertIn("session_peak_level", hints)
self.assertIn("session_message_count", hints)
def test_ui_hints_escalation_warning(self):
"""Escalating session should have warning hint."""
self.tracker.record(detect_crisis("Hello"))
self.tracker.record(detect_crisis("I want to die"))
hints = self.tracker.get_ui_hints()
if hints["session_escalating"]:
self.assertTrue(hints.get("escalation_warning"))
self.assertIn("suggested_action", hints)
class TestCheckCrisisWithSession(unittest.TestCase):
"""Test the convenience function combining detection + session tracking."""
def test_returns_combined_data(self):
tracker = CrisisSessionTracker()
result = check_crisis_with_session("I want to die", tracker)
self.assertIn("level", result)
self.assertIn("session", result)
self.assertIn("current_level", result["session"])
self.assertIn("peak_level", result["session"])
self.assertIn("modifier", result["session"])
def test_session_updates_across_calls(self):
tracker = CrisisSessionTracker()
check_crisis_with_session("Hello", tracker)
result = check_crisis_with_session("I want to die", tracker)
self.assertEqual(result["session"]["message_count"], 2)
self.assertEqual(result["session"]["peak_level"], "CRITICAL")
class TestPrivacy(unittest.TestCase):
"""Verify privacy-first design principles."""
def test_no_persistence_mechanism(self):
"""Session tracker should have no database, file, or network calls."""
import inspect
source = inspect.getsource(CrisisSessionTracker)
# Should not import database, requests, or file I/O
forbidden = ["sqlite", "requests", "urllib", "open(", "httpx", "aiohttp"]
for word in forbidden:
self.assertNotIn(word, source.lower(),
f"Session tracker should not use {word} — privacy-first design")
def test_state_contained_in_memory(self):
"""All state should be instance attributes, not module-level."""
tracker = CrisisSessionTracker()
tracker.record(detect_crisis("I want to die"))
# New tracker should have clean state (no global contamination)
fresh = CrisisSessionTracker()
self.assertEqual(fresh.state.current_level, "NONE")
if __name__ == '__main__':
unittest.main()