feat: build crisis synthesizer (#36)

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.

crisis/metrics.py

@@ -1,133 +0,0 @@
-#!/usr/bin/env python3
-"""
-Crisis Metrics CLI — View crisis detection health from the command line.
-
-Usage:
-    python3 -m crisis.metrics --summary    # weekly report
-    python3 -m crisis.metrics --json        # raw JSON export
-    python3 -m crisis.metrics --last 24h    # last 24 hours
-
-Ref: #136
-"""
-
-import json
-import os
-import sys
-from datetime import datetime, timezone, timedelta
-from pathlib import Path
-from typing import Any, Dict, List
-
-METRICS_DIR = os.environ.get("CRISIS_METRICS_DIR", str(Path.home() / ".the-door" / "metrics"))
-
-
-def load_metrics(hours: int = 168) -> List[dict]:
-    """Load metrics entries from the last N hours."""
-    cutoff = datetime.now(timezone.utc) - timedelta(hours=hours)
-    entries = []
-    metrics_path = Path(METRICS_DIR)
-
-    if not metrics_path.exists():
-        return entries
-
-    for f in sorted(metrics_path.glob("*.json")):
-        try:
-            with open(f) as fh:
-                data = json.load(fh)
-            if isinstance(data, list):
-                entries.extend(data)
-            elif isinstance(data, dict):
-                entries.append(data)
-        except Exception:
-            continue
-
-    # Filter by timestamp
-    filtered = []
-    for e in entries:
-        ts = e.get("timestamp", "")
-        if ts:
-            try:
-                t = datetime.fromisoformat(ts.replace("Z", "+00:00"))
-                if t >= cutoff:
-                    filtered.append(e)
-            except Exception:
-                filtered.append(e)
-
-    return filtered
-
-
-def summarize(entries: List[dict]) -> dict:
-    """Summarize metrics entries."""
-    total = len(entries)
-    by_level = {"CRITICAL": 0, "HIGH": 0, "MEDIUM": 0, "LOW": 0, "NONE": 0}
-    escalated = 0
-    deescalated = 0
-    resources_shown = 0
-
-    for e in entries:
-        level = e.get("level", "NONE")
-        by_level[level] = by_level.get(level, 0) + 1
-        if e.get("escalated"):
-            escalated += 1
-        if e.get("deescalation_confirmed"):
-            deescalated += 1
-        if e.get("resources_shown"):
-            resources_shown += 1
-
-    return {
-        "period_hours": 168,
-        "total_interactions": total,
-        "by_level": by_level,
-        "escalated_sessions": escalated,
-        "deescalated_sessions": deescalated,
-        "resources_shown": resources_shown,
-        "crisis_rate": round((by_level["CRITICAL"] + by_level["HIGH"]) / max(total, 1) * 100, 1),
-    }
-
-
-def print_summary(summary: dict):
-    print(f"\n{'='*50}")
-    print(f"  CRISIS METRICS SUMMARY")
-    print(f"  {datetime.now().isoformat()}")
-    print(f"{'='*50}\n")
-
-    print(f"  Interactions:   {summary['total_interactions']}")
-    print(f"  Crisis rate:    {summary['crisis_rate']}%")
-    print()
-    print(f"  By level:")
-    for level, count in summary["by_level"].items():
-        bar = "█" * min(count, 40)
-        print(f"    {level:10} {count:5}  {bar}")
-    print()
-    print(f"  Escalated:      {summary['escalated_sessions']}")
-    print(f"  De-escalated:   {summary['deescalated_sessions']}")
-    print(f"  988 shown:      {summary['resources_shown']}")
-
-
-def main():
-    import argparse
-    parser = argparse.ArgumentParser(description="Crisis Metrics CLI")
-    parser.add_argument("--summary", action="store_true", help="Weekly summary")
-    parser.add_argument("--json", action="store_true", help="JSON export")
-    parser.add_argument("--last", default="168h", help="Time window (e.g., 24h, 7d)")
-    args = parser.parse_args()
-
-    # Parse time window
-    last = args.last
-    if last.endswith("h"):
-        hours = int(last[:-1])
-    elif last.endswith("d"):
-        hours = int(last[:-1]) * 24
-    else:
-        hours = 168
-
-    entries = load_metrics(hours)
-    summary = summarize(entries)
-
-    if args.json:
-        print(json.dumps(summary, indent=2))
-    else:
-        print_summary(summary)
-
-
-if __name__ == "__main__":
-    main()

evolution/crisis_synthesizer.py

@@ -1 +1,195 @@
-...
+"""Crisis synthesizer — learn from anonymized crisis interactions.
+
+This is deliberately simple and privacy-preserving. It does not train a model or
+modify detection rules automatically. It only logs metadata, summarizes patterns,
+and suggests human-reviewed keyword weight adjustments.
+"""
+
+from __future__ import annotations
+
+import argparse
+import json
+import time
+from collections import Counter, defaultdict
+from pathlib import Path
+from typing import Iterable
+
+DEFAULT_LOG_PATH = Path.home() / ".the-door" / "crisis-interactions.jsonl"
+LEVELS = ("NONE", "LOW", "MEDIUM", "HIGH", "CRITICAL")
+
+
+def build_interaction_event(
+    level: str,
+    indicators: list[str],
+    response_given: str,
+    continued_conversation: bool,
+    false_positive: bool,
+    *,
+    now: float | None = None,
+) -> dict:
+    return {
+        "timestamp": float(time.time() if now is None else now),
+        "level": level,
+        "indicators": list(indicators),
+        "indicator_count": len(indicators),
+        "response_given": response_given,
+        "continued_conversation": bool(continued_conversation),
+        "false_positive": bool(false_positive),
+    }
+
+
+def append_interaction_event(
+    log_path: str | Path,
+    *,
+    level: str,
+    indicators: list[str],
+    response_given: str,
+    continued_conversation: bool,
+    false_positive: bool,
+    now: float | None = None,
+) -> dict:
+    event = build_interaction_event(
+        level,
+        indicators,
+        response_given,
+        continued_conversation,
+        false_positive,
+        now=now,
+    )
+    path = Path(log_path)
+    path.parent.mkdir(parents=True, exist_ok=True)
+    with path.open("a", encoding="utf-8") as handle:
+        handle.write(json.dumps(event) + "\n")
+    return event
+
+
+def load_interaction_events(log_path: str | Path) -> list[dict]:
+    path = Path(log_path)
+    if not path.exists():
+        return []
+    events = []
+    for line in path.read_text(encoding="utf-8").splitlines():
+        if not line.strip():
+            continue
+        events.append(json.loads(line))
+    return events
+
+
+def summarize_keywords(events: Iterable[dict]) -> list[dict]:
+    counts: Counter[str] = Counter()
+    for event in events:
+        counts.update(event.get("indicators", []))
+    return [{"keyword": keyword, "count": count} for keyword, count in counts.most_common(10)]
+
+
+def suggest_keyword_adjustments(events: Iterable[dict], *, min_observations: int = 5) -> list[dict]:
+    stats: dict[str, dict[str, int]] = defaultdict(lambda: {
+        "observations": 0,
+        "true_positive_count": 0,
+        "false_positive_count": 0,
+        "continued_conversation_count": 0,
+    })
+
+    for event in events:
+        for keyword in event.get("indicators", []):
+            bucket = stats[keyword]
+            bucket["observations"] += 1
+            if event.get("false_positive"):
+                bucket["false_positive_count"] += 1
+            else:
+                bucket["true_positive_count"] += 1
+            if event.get("continued_conversation"):
+                bucket["continued_conversation_count"] += 1
+
+    suggestions = []
+    for keyword, bucket in sorted(stats.items()):
+        if bucket["observations"] < min_observations:
+            continue
+        fp = bucket["false_positive_count"]
+        tp = bucket["true_positive_count"]
+        if fp >= min_observations and tp == 0:
+            adjustment = "lower_weight"
+            rationale = "Observed only false positives across the sample window."
+        elif tp >= min_observations and fp == 0:
+            adjustment = "raise_weight"
+            rationale = "Observed repeated genuine crises with no false positives."
+        else:
+            adjustment = "observe"
+            rationale = "Mixed evidence; keep monitoring before changing weights."
+        suggestions.append(
+            {
+                "keyword": keyword,
+                **bucket,
+                "suggested_adjustment": adjustment,
+                "rationale": rationale,
+            }
+        )
+    return suggestions
+
+
+def build_weekly_report(
+    events: Iterable[dict],
+    *,
+    now: float | None = None,
+    window_days: int = 7,
+    min_observations: int = 3,
+) -> dict:
+    current_time = float(time.time() if now is None else now)
+    cutoff = current_time - (window_days * 86400)
+    filtered = [event for event in events if float(event.get("timestamp", 0)) >= cutoff]
+
+    detections_per_level = {level: 0 for level in LEVELS}
+    detected_events = []
+    continued_after_intervention = 0
+    for event in filtered:
+        level = event.get("level", "NONE")
+        detections_per_level[level] = detections_per_level.get(level, 0) + 1
+        if level != "NONE":
+            detected_events.append(event)
+            if event.get("continued_conversation"):
+                continued_after_intervention += 1
+
+    false_positive_count = sum(1 for event in detected_events if event.get("false_positive"))
+    false_positive_estimate = false_positive_count / len(detected_events) if detected_events else 0.0
+
+    return {
+        "window_days": window_days,
+        "total_events": len(filtered),
+        "detections_per_level": detections_per_level,
+        "most_common_keywords": summarize_keywords(filtered),
+        "false_positive_estimate": false_positive_estimate,
+        "continued_after_intervention": continued_after_intervention,
+        "keyword_weight_suggestions": suggest_keyword_adjustments(filtered, min_observations=min_observations),
+    }
+
+
+def render_weekly_report(summary: dict) -> str:
+    return json.dumps(summary, indent=2)
+
+
+def write_weekly_report(output_path: str | Path, summary: dict) -> Path:
+    path = Path(output_path)
+    path.parent.mkdir(parents=True, exist_ok=True)
+    path.write_text(render_weekly_report(summary) + "\n", encoding="utf-8")
+    return path
+
+
+def main(argv: list[str] | None = None) -> int:
+    parser = argparse.ArgumentParser(description="Summarize anonymized crisis interactions")
+    parser.add_argument("--log-path", default=str(DEFAULT_LOG_PATH), help="JSONL crisis interaction log")
+    parser.add_argument("--days", type=int, default=7, help="Lookback window in days")
+    parser.add_argument("--min-observations", type=int, default=3, help="Minimum observations before suggesting keyword adjustments")
+    parser.add_argument("--output", help="Optional file to write the weekly report JSON")
+    args = parser.parse_args(argv)
+
+    events = load_interaction_events(args.log_path)
+    summary = build_weekly_report(events, window_days=args.days, min_observations=args.min_observations)
+    rendered = render_weekly_report(summary)
+    print(rendered)
+    if args.output:
+        write_weekly_report(args.output, summary)
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

index.html

@@ -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>

tests/test_crisis_synthesizer.py

@@ -0,0 +1,111 @@
+"""Tests for evolution/crisis_synthesizer.py (issue #36)."""
+
+from __future__ import annotations
+
+import importlib.util
+import json
+import pathlib
+import sys
+import tempfile
+import unittest
+
+ROOT = pathlib.Path(__file__).resolve().parents[1]
+SCRIPT = ROOT / 'evolution' / 'crisis_synthesizer.py'
+
+spec = importlib.util.spec_from_file_location('crisis_synthesizer', str(SCRIPT))
+mod = importlib.util.module_from_spec(spec)
+sys.modules['crisis_synthesizer'] = mod
+spec.loader.exec_module(mod)
+
+
+class TestCrisisSynthesizerEvent(unittest.TestCase):
+    def test_build_interaction_event_is_privacy_preserving(self):
+        event = mod.build_interaction_event(
+            level='CRITICAL',
+            indicators=['want_to_die', 'no_way_out'],
+            response_given='guardian',
+            continued_conversation=True,
+            false_positive=False,
+            now=1700000000,
+        )
+        self.assertEqual(event['timestamp'], 1700000000)
+        self.assertEqual(event['level'], 'CRITICAL')
+        self.assertEqual(event['response_given'], 'guardian')
+        self.assertTrue(event['continued_conversation'])
+        self.assertFalse(event['false_positive'])
+        self.assertEqual(event['indicators'], ['want_to_die', 'no_way_out'])
+        for forbidden in ['text', 'message', 'content', 'ip', 'session_id', 'user_id']:
+            self.assertNotIn(forbidden, event)
+
+
+class TestCrisisSynthesizerStorage(unittest.TestCase):
+    def test_append_and_load_events_round_trip(self):
+        with tempfile.TemporaryDirectory() as tmp:
+            log_path = pathlib.Path(tmp) / 'crisis-events.jsonl'
+            mod.append_interaction_event(
+                log_path,
+                level='HIGH',
+                indicators=['hopeless'],
+                response_given='companion',
+                continued_conversation=False,
+                false_positive=True,
+                now=1700000100,
+            )
+            events = mod.load_interaction_events(log_path)
+            self.assertEqual(len(events), 1)
+            self.assertEqual(events[0]['level'], 'HIGH')
+            self.assertEqual(events[0]['indicators'], ['hopeless'])
+
+
+class TestCrisisSynthesizerSummary(unittest.TestCase):
+    def test_weekly_report_contains_required_metrics(self):
+        events = [
+            mod.build_interaction_event('CRITICAL', ['want_to_die'], 'guardian', True, False, now=1700000000),
+            mod.build_interaction_event('HIGH', ['hopeless'], 'companion', False, True, now=1700000100),
+            mod.build_interaction_event('LOW', ['rough_day'], 'friend', False, False, now=1700000200),
+            mod.build_interaction_event('CRITICAL', ['want_to_die'], 'guardian', False, False, now=1700000300),
+            mod.build_interaction_event('NONE', [], 'friend', False, False, now=1700000400),
+        ]
+        summary = mod.build_weekly_report(events, now=1700000500, window_days=7)
+        self.assertEqual(summary['detections_per_level']['CRITICAL'], 2)
+        self.assertEqual(summary['detections_per_level']['HIGH'], 1)
+        self.assertEqual(summary['detections_per_level']['LOW'], 1)
+        self.assertEqual(summary['detections_per_level']['NONE'], 1)
+        self.assertEqual(summary['continued_after_intervention'], 1)
+        self.assertAlmostEqual(summary['false_positive_estimate'], 0.25)
+        self.assertEqual(summary['most_common_keywords'][0]['keyword'], 'want_to_die')
+        self.assertEqual(summary['most_common_keywords'][0]['count'], 2)
+
+
+class TestCrisisSynthesizerSuggestions(unittest.TestCase):
+    def test_suggests_weight_adjustments_from_interactions(self):
+        events = []
+        for ts in range(3):
+            events.append(mod.build_interaction_event('CRITICAL', ['want_to_die'], 'guardian', True, False, now=1700000000 + ts))
+        for ts in range(3):
+            events.append(mod.build_interaction_event('LOW', ['rough_day'], 'friend', False, True, now=1700000100 + ts))
+        suggestions = mod.suggest_keyword_adjustments(events, min_observations=3)
+        by_keyword = {s['keyword']: s for s in suggestions}
+        self.assertEqual(by_keyword['want_to_die']['suggested_adjustment'], 'raise_weight')
+        self.assertEqual(by_keyword['rough_day']['suggested_adjustment'], 'lower_weight')
+
+
+class TestCrisisSynthesizerRendering(unittest.TestCase):
+    def test_render_weekly_report_outputs_json(self):
+        summary = {
+            'detections_per_level': {'NONE': 0, 'LOW': 1, 'MEDIUM': 0, 'HIGH': 0, 'CRITICAL': 0},
+            'most_common_keywords': [{'keyword': 'rough_day', 'count': 1}],
+            'false_positive_estimate': 0.0,
+            'continued_after_intervention': 0,
+            'keyword_weight_suggestions': [],
+            'window_days': 7,
+            'total_events': 1,
+        }
+        rendered = mod.render_weekly_report(summary)
+        parsed = json.loads(rendered)
+        self.assertEqual(parsed['window_days'], 7)
+        self.assertEqual(parsed['most_common_keywords'][0]['keyword'], 'rough_day')
+
+
+if __name__ == '__main__':
+    unittest.main()