Compare commits
1 Commits
fix/75
...
feat/131-v
| Author | SHA1 | Date | |
|---|---|---|---|
|
4dc6819079 |
@@ -7,7 +7,6 @@ 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",
|
||||
@@ -20,7 +19,4 @@ __all__ = [
|
||||
"format_result",
|
||||
"format_gateway_response",
|
||||
"get_urgency_emoji",
|
||||
"CrisisSessionTracker",
|
||||
"SessionState",
|
||||
"check_crisis_with_session",
|
||||
]
|
||||
|
||||
@@ -22,7 +22,6 @@ from .response import (
|
||||
get_system_prompt_modifier,
|
||||
CrisisResponse,
|
||||
)
|
||||
from .session_tracker import CrisisSessionTracker
|
||||
|
||||
|
||||
def check_crisis(text: str) -> dict:
|
||||
|
||||
@@ -1,259 +0,0 @@
|
||||
"""
|
||||
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(),
|
||||
},
|
||||
}
|
||||
@@ -808,7 +808,6 @@ 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');
|
||||
|
||||
@@ -1051,8 +1050,7 @@ Sovereignty and service always.`;
|
||||
}
|
||||
}, 1000);
|
||||
|
||||
// Focus the Call 988 link (always enabled) — disabled buttons cannot receive focus
|
||||
if (overlayCallLink) overlayCallLink.focus();
|
||||
overlayDismissBtn.focus();
|
||||
}
|
||||
|
||||
// Register focus trap on document (always listening, gated by class check)
|
||||
|
||||
@@ -1,68 +0,0 @@
|
||||
# The Door Fleet Work Orders Audit — issue #75
|
||||
|
||||
Generated: 2026-04-17T04:10:14Z
|
||||
Source issue: `TRIAGE: The Door - Fleet Work Orders (2026-04-09)`
|
||||
|
||||
## Source Snapshot
|
||||
|
||||
Issue #75 is a dated triage work-order sheet, not a normal feature request. The durable deliverable is a truth-restored audit of the referenced issue and PR set against live forge state.
|
||||
|
||||
## Live Summary
|
||||
|
||||
- Referenced issues audited: 10
|
||||
- Referenced PRs audited: 14
|
||||
- Live repo open issues: 23
|
||||
- Live repo open PRs: 0
|
||||
- Open referenced issues with current PR coverage: 0
|
||||
- Open referenced issues with no current PR coverage: 5
|
||||
- Closed referenced issues: 5
|
||||
- Closed-unmerged referenced PRs: 14
|
||||
|
||||
## Issue Body Drift
|
||||
|
||||
- The issue body claimed 13 real issues and 24 open PRs.
|
||||
- Live repo state now shows 23 open issues and 0 open PRs.
|
||||
- Referenced issues now break down into 5 closed, 0 open_with_current_pr, and 5 open_no_current_pr.
|
||||
- Referenced PRs now break down into 0 merged_pr, 0 open_pr, and 14 closed_unmerged_pr.
|
||||
|
||||
## Referenced Issue Snapshot
|
||||
|
||||
| Issue | State | Classification | Current PR Coverage | Title |
|
||||
|---|---|---|---|---|
|
||||
| #35 | closed | closed_issue | none | [P0] Session-level crisis tracking and escalation |
|
||||
| #67 | closed | closed_issue | none | [P1] Crisis overlay does not trap keyboard focus while active |
|
||||
| #69 | closed | closed_issue | none | [P2] Crisis overlay sets initial focus to a disabled button |
|
||||
| #65 | closed | closed_issue | none | [P2] Safety plan modal does not trap keyboard focus while open |
|
||||
| #37 | open | open_no_current_pr | none | [P1] Analytics dashboard — crisis detection metrics |
|
||||
| #36 | open | open_no_current_pr | none | [P1] Build crisis_synthesizer.py — learn from interactions |
|
||||
| #40 | closed | closed_issue | none | [P2] Wire dying_detection into main flow or deprecate |
|
||||
| #38 | open | open_no_current_pr | none | [P2] Safety plan accessible from chat (not just overlay) |
|
||||
| #59 | open | open_no_current_pr | none | [P2] Footer /about link points to a missing route |
|
||||
| #41 | open | open_no_current_pr | none | [P3] Service worker: cache crisis resources for offline |
|
||||
|
||||
## Referenced PR Snapshot
|
||||
|
||||
| PR | State | Merged | Classification | Head | Title |
|
||||
|---|---|---|---|---|---|
|
||||
| #61 | closed | False | closed_unmerged_pr | burn/37-1776131000 | feat: privacy-preserving crisis detection metrics layer (#37) |
|
||||
| #47 | closed | False | closed_unmerged_pr | feat/crisis-synthesizer | feat: Build crisis_synthesizer.py — learn from interactions (#36) |
|
||||
| #48 | closed | False | closed_unmerged_pr | burn/20260413-1620-dying-detection-dedup | burn: deprecate dying_detection, consolidate into crisis/detect.py |
|
||||
| #50 | closed | False | closed_unmerged_pr | whip/40-1776128804 | fix: deprecate dying_detection and consolidate crisis detection (#40) |
|
||||
| #51 | closed | False | closed_unmerged_pr | queue/40-1776129201 | fix: deprecate dying_detection and consolidate crisis detection (#40) |
|
||||
| #53 | closed | False | closed_unmerged_pr | q/40-1776129480 | fix: deprecate dying_detection and consolidate crisis detection (#40) |
|
||||
| #56 | closed | False | closed_unmerged_pr | triage/40-1776129677 | fix: deprecate dying_detection and consolidate crisis detection (#40) |
|
||||
| #58 | closed | False | closed_unmerged_pr | dawn/40-1776130053 | fix: deprecate dying_detection and consolidate crisis detection (#40) |
|
||||
| #70 | closed | False | closed_unmerged_pr | am/40-1776166469 | fix: deprecate dying_detection and consolidate crisis detection (#40) |
|
||||
| #72 | closed | False | closed_unmerged_pr | am/38-1776166469 | feat: add always-on safety plan access in chat header (#38) |
|
||||
| #62 | closed | False | closed_unmerged_pr | burn/59-1776131200 | fix: point footer about link to /about.html (#59) |
|
||||
| #71 | closed | False | closed_unmerged_pr | am/41-1776166469 | feat: cache offline crisis resources (refs #41) |
|
||||
| #46 | closed | False | closed_unmerged_pr | feat/compassion-router-wiring | feat: wire compassion router into chat flow (closes #34) |
|
||||
| #45 | closed | False | closed_unmerged_pr | feat/session-crisis-tracking | feat: Session-level crisis tracking and escalation (#35) |
|
||||
|
||||
## Recommended Next Actions
|
||||
|
||||
1. Do not trust the original work-order body as live truth; use this audit artifact for current planning.
|
||||
2. Re-triage the open_no_current_pr issues individually before dispatching new work, because the old PR references are now stale.
|
||||
3. Treat closed_unmerged_pr references as historical attempts, not active review lanes.
|
||||
4. If future work orders are needed, generate them from live forge state instead of reusing the 2026-04-09 issue body.
|
||||
5. This audit preserves operator memory; it does not claim all referenced work orders are complete.
|
||||
@@ -1,295 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
from urllib.request import Request, urlopen
|
||||
|
||||
API_BASE = "https://forge.alexanderwhitestone.com/api/v1"
|
||||
ORG = "Timmy_Foundation"
|
||||
DEFAULT_TOKEN_PATH = os.path.expanduser("~/.config/gitea/token")
|
||||
DEFAULT_OUTPUT = "reports/2026-04-17-the-door-fleet-work-orders-audit.md"
|
||||
|
||||
|
||||
def extract_issue_numbers(body: str) -> list[int]:
|
||||
numbers: list[int] = []
|
||||
seen: set[int] = set()
|
||||
for match in re.finditer(r"#(\d+)", body or ""):
|
||||
value = int(match.group(1))
|
||||
if value in seen:
|
||||
continue
|
||||
seen.add(value)
|
||||
numbers.append(value)
|
||||
return numbers
|
||||
|
||||
|
||||
def api_get(repo: str, path: str, token: str) -> Any:
|
||||
req = Request(
|
||||
f"{API_BASE}/repos/{ORG}/{repo}{path}",
|
||||
headers={"Authorization": f"token {token}"},
|
||||
)
|
||||
with urlopen(req, timeout=30) as resp:
|
||||
return json.loads(resp.read().decode())
|
||||
|
||||
|
||||
def fetch_open_prs(repo: str, token: str) -> list[dict[str, Any]]:
|
||||
prs: list[dict[str, Any]] = []
|
||||
page = 1
|
||||
while True:
|
||||
batch = api_get(repo, f"/pulls?state=open&limit=100&page={page}", token)
|
||||
if not batch:
|
||||
break
|
||||
prs.extend(batch)
|
||||
page += 1
|
||||
return prs
|
||||
|
||||
|
||||
def fetch_live_open_issue_count(repo: str, token: str) -> int:
|
||||
total = 0
|
||||
page = 1
|
||||
while True:
|
||||
batch = api_get(repo, f"/issues?state=open&limit=100&page={page}", token)
|
||||
if not batch:
|
||||
break
|
||||
total += sum(1 for item in batch if not item.get("pull_request"))
|
||||
page += 1
|
||||
return total
|
||||
|
||||
|
||||
def parse_claimed_summary(body: str) -> tuple[int | None, int | None]:
|
||||
issue_match = re.search(r"has\s+(\d+)\s+real issues", body or "", flags=re.IGNORECASE)
|
||||
pr_match = re.search(r"and\s+(\d+)\s+open PRs", body or "", flags=re.IGNORECASE)
|
||||
claimed_open_issues = int(issue_match.group(1)) if issue_match else None
|
||||
claimed_open_prs = int(pr_match.group(1)) if pr_match else None
|
||||
return claimed_open_issues, claimed_open_prs
|
||||
|
||||
|
||||
def summarize_open_pr_coverage(issue_num: int, open_prs: list[dict[str, Any]]) -> str:
|
||||
matches: list[str] = []
|
||||
seen: set[int] = set()
|
||||
for pr in open_prs:
|
||||
pr_num = pr["number"]
|
||||
if pr_num in seen:
|
||||
continue
|
||||
text = "\n".join(
|
||||
[
|
||||
pr.get("title") or "",
|
||||
pr.get("body") or "",
|
||||
(pr.get("head") or {}).get("ref") or "",
|
||||
]
|
||||
)
|
||||
if f"#{issue_num}" not in text:
|
||||
continue
|
||||
seen.add(pr_num)
|
||||
matches.append(f"open PR #{pr_num}")
|
||||
return ", ".join(matches) if matches else "none"
|
||||
|
||||
|
||||
def classify_issue_reference(ref_issue: dict[str, Any], open_prs: list[dict[str, Any]]) -> dict[str, Any]:
|
||||
issue_num = ref_issue["number"]
|
||||
state = ref_issue.get("state") or "unknown"
|
||||
coverage = summarize_open_pr_coverage(issue_num, open_prs)
|
||||
if state == "closed":
|
||||
classification = "closed_issue"
|
||||
elif coverage != "none":
|
||||
classification = "open_with_current_pr"
|
||||
else:
|
||||
classification = "open_no_current_pr"
|
||||
return {
|
||||
"number": issue_num,
|
||||
"state": state,
|
||||
"classification": classification,
|
||||
"title": ref_issue.get("title") or "",
|
||||
"current_pr_coverage": coverage,
|
||||
"url": ref_issue.get("html_url") or ref_issue.get("url") or "",
|
||||
}
|
||||
|
||||
|
||||
def classify_pr_reference(repo: str, pr_num: int, token: str) -> dict[str, Any]:
|
||||
pr = api_get(repo, f"/pulls/{pr_num}", token)
|
||||
state = pr.get("state") or "unknown"
|
||||
merged = bool(pr.get("merged"))
|
||||
if merged:
|
||||
classification = "merged_pr"
|
||||
elif state == "open":
|
||||
classification = "open_pr"
|
||||
else:
|
||||
classification = "closed_unmerged_pr"
|
||||
return {
|
||||
"number": pr_num,
|
||||
"state": state,
|
||||
"merged": merged,
|
||||
"classification": classification,
|
||||
"title": pr.get("title") or "",
|
||||
"head": (pr.get("head") or {}).get("ref") or "",
|
||||
"url": pr.get("html_url") or pr.get("url") or "",
|
||||
}
|
||||
|
||||
|
||||
def table(rows: list[dict[str, Any]], columns: list[tuple[str, str]]) -> str:
|
||||
headers = [title for title, _ in columns]
|
||||
keys = [key for _, key in columns]
|
||||
if not rows:
|
||||
return "| None |\n|---|\n| None |"
|
||||
lines = ["| " + " | ".join(headers) + " |", "|" + "|".join(["---"] * len(headers)) + "|"]
|
||||
for row in rows:
|
||||
values: list[str] = []
|
||||
for key in keys:
|
||||
value = row.get(key, "")
|
||||
if key == "number" and value != "":
|
||||
value = f"#{value}"
|
||||
values.append(str(value).replace("\n", " "))
|
||||
lines.append("| " + " | ".join(values) + " |")
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def render_report(
|
||||
*,
|
||||
source_issue: int,
|
||||
source_title: str,
|
||||
generated_at: str,
|
||||
claimed_open_issues: int | None,
|
||||
claimed_open_prs: int | None,
|
||||
live_open_issues: int,
|
||||
live_open_prs: int,
|
||||
issue_rows: list[dict[str, Any]],
|
||||
pr_rows: list[dict[str, Any]],
|
||||
) -> str:
|
||||
open_with_current_pr = [row for row in issue_rows if row["classification"] == "open_with_current_pr"]
|
||||
open_no_current_pr = [row for row in issue_rows if row["classification"] == "open_no_current_pr"]
|
||||
closed_issues = [row for row in issue_rows if row["classification"] == "closed_issue"]
|
||||
merged_prs = [row for row in pr_rows if row["classification"] == "merged_pr"]
|
||||
open_pr_refs = [row for row in pr_rows if row["classification"] == "open_pr"]
|
||||
closed_unmerged_prs = [row for row in pr_rows if row["classification"] == "closed_unmerged_pr"]
|
||||
|
||||
drift_lines = [
|
||||
f"- The issue body claimed {claimed_open_issues if claimed_open_issues is not None else 'unknown'} real issues and {claimed_open_prs if claimed_open_prs is not None else 'unknown'} open PRs.",
|
||||
f"- Live repo state now shows {live_open_issues} open issues and {live_open_prs} open PRs.",
|
||||
f"- Referenced issues now break down into {len(closed_issues)} closed, {len(open_with_current_pr)} open_with_current_pr, and {len(open_no_current_pr)} open_no_current_pr.",
|
||||
f"- Referenced PRs now break down into {len(merged_prs)} merged_pr, {len(open_pr_refs)} open_pr, and {len(closed_unmerged_prs)} closed_unmerged_pr.",
|
||||
]
|
||||
|
||||
return "\n".join(
|
||||
[
|
||||
f"# The Door Fleet Work Orders Audit — issue #{source_issue}",
|
||||
"",
|
||||
f"Generated: {generated_at}",
|
||||
f"Source issue: `{source_title}`",
|
||||
"",
|
||||
"## Source Snapshot",
|
||||
"",
|
||||
"Issue #75 is a dated triage work-order sheet, not a normal feature request. The durable deliverable is a truth-restored audit of the referenced issue and PR set against live forge state.",
|
||||
"",
|
||||
"## Live Summary",
|
||||
"",
|
||||
f"- Referenced issues audited: {len(issue_rows)}",
|
||||
f"- Referenced PRs audited: {len(pr_rows)}",
|
||||
f"- Live repo open issues: {live_open_issues}",
|
||||
f"- Live repo open PRs: {live_open_prs}",
|
||||
f"- Open referenced issues with current PR coverage: {len(open_with_current_pr)}",
|
||||
f"- Open referenced issues with no current PR coverage: {len(open_no_current_pr)}",
|
||||
f"- Closed referenced issues: {len(closed_issues)}",
|
||||
f"- Closed-unmerged referenced PRs: {len(closed_unmerged_prs)}",
|
||||
"",
|
||||
"## Issue Body Drift",
|
||||
"",
|
||||
*drift_lines,
|
||||
"",
|
||||
"## Referenced Issue Snapshot",
|
||||
"",
|
||||
table(
|
||||
issue_rows,
|
||||
[
|
||||
("Issue", "number"),
|
||||
("State", "state"),
|
||||
("Classification", "classification"),
|
||||
("Current PR Coverage", "current_pr_coverage"),
|
||||
("Title", "title"),
|
||||
],
|
||||
),
|
||||
"",
|
||||
"## Referenced PR Snapshot",
|
||||
"",
|
||||
table(
|
||||
pr_rows,
|
||||
[
|
||||
("PR", "number"),
|
||||
("State", "state"),
|
||||
("Merged", "merged"),
|
||||
("Classification", "classification"),
|
||||
("Head", "head"),
|
||||
("Title", "title"),
|
||||
],
|
||||
),
|
||||
"",
|
||||
"## Recommended Next Actions",
|
||||
"",
|
||||
"1. Do not trust the original work-order body as live truth; use this audit artifact for current planning.",
|
||||
"2. Re-triage the open_no_current_pr issues individually before dispatching new work, because the old PR references are now stale.",
|
||||
"3. Treat closed_unmerged_pr references as historical attempts, not active review lanes.",
|
||||
"4. If future work orders are needed, generate them from live forge state instead of reusing the 2026-04-09 issue body.",
|
||||
"5. This audit preserves operator memory; it does not claim all referenced work orders are complete.",
|
||||
]
|
||||
) + "\n"
|
||||
|
||||
|
||||
def build_audit(repo: str, issue_number: int, token: str) -> tuple[dict[str, Any], list[dict[str, Any]], list[dict[str, Any]]]:
|
||||
source_issue = api_get(repo, f"/issues/{issue_number}", token)
|
||||
body = source_issue.get("body") or ""
|
||||
refs = extract_issue_numbers(body)
|
||||
open_prs = fetch_open_prs(repo, token)
|
||||
claimed_open_issues, claimed_open_prs = parse_claimed_summary(body)
|
||||
issue_rows: list[dict[str, Any]] = []
|
||||
pr_rows: list[dict[str, Any]] = []
|
||||
for ref in refs:
|
||||
issue_like = api_get(repo, f"/issues/{ref}", token)
|
||||
if issue_like.get("pull_request"):
|
||||
pr_rows.append(classify_pr_reference(repo, ref, token))
|
||||
else:
|
||||
issue_rows.append(classify_issue_reference(issue_like, open_prs))
|
||||
metadata = {
|
||||
"source_title": source_issue.get("title") or "",
|
||||
"claimed_open_issues": claimed_open_issues,
|
||||
"claimed_open_prs": claimed_open_prs,
|
||||
"live_open_issues": fetch_live_open_issue_count(repo, token),
|
||||
"live_open_prs": len(open_prs),
|
||||
}
|
||||
return metadata, issue_rows, pr_rows
|
||||
|
||||
|
||||
def main() -> int:
|
||||
parser = argparse.ArgumentParser(description="Audit The Door fleet work orders issue against live forge state.")
|
||||
parser.add_argument("--repo", default="the-door")
|
||||
parser.add_argument("--issue", type=int, default=75)
|
||||
parser.add_argument("--token-file", default=DEFAULT_TOKEN_PATH)
|
||||
parser.add_argument("--output", default=DEFAULT_OUTPUT)
|
||||
args = parser.parse_args()
|
||||
|
||||
token = Path(args.token_file).read_text(encoding="utf-8").strip()
|
||||
generated_at = datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ")
|
||||
metadata, issue_rows, pr_rows = build_audit(args.repo, args.issue, token)
|
||||
report = render_report(
|
||||
source_issue=args.issue,
|
||||
source_title=metadata["source_title"],
|
||||
generated_at=generated_at,
|
||||
claimed_open_issues=metadata["claimed_open_issues"],
|
||||
claimed_open_prs=metadata["claimed_open_prs"],
|
||||
live_open_issues=metadata["live_open_issues"],
|
||||
live_open_prs=metadata["live_open_prs"],
|
||||
issue_rows=issue_rows,
|
||||
pr_rows=pr_rows,
|
||||
)
|
||||
output_path = Path(args.output)
|
||||
output_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
output_path.write_text(report, encoding="utf-8")
|
||||
print(output_path)
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -52,34 +52,6 @@ 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()
|
||||
|
||||
@@ -1,100 +0,0 @@
|
||||
import importlib.util
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
ROOT = Path(__file__).resolve().parents[1]
|
||||
SCRIPT_PATH = ROOT / "scripts" / "fleet_work_orders_audit.py"
|
||||
REPORT_PATH = ROOT / "reports" / "2026-04-17-the-door-fleet-work-orders-audit.md"
|
||||
|
||||
|
||||
def _load_module():
|
||||
assert SCRIPT_PATH.exists(), f"missing {SCRIPT_PATH.relative_to(ROOT)}"
|
||||
spec = importlib.util.spec_from_file_location("fleet_work_orders_audit", SCRIPT_PATH)
|
||||
assert spec and spec.loader
|
||||
module = importlib.util.module_from_spec(spec)
|
||||
spec.loader.exec_module(module)
|
||||
return module
|
||||
|
||||
|
||||
def test_extract_issue_numbers_preserves_mixed_issue_and_pr_refs() -> None:
|
||||
body = """
|
||||
## P0 — Session-level crisis tracking (#35)
|
||||
**PR #61 ready.**
|
||||
## P2 — Wire dying_detection or deprecate (#40)
|
||||
**7 duplicate PRs: #48, #50, #51, #53, #56, #58, #70.**
|
||||
"""
|
||||
|
||||
mod = _load_module()
|
||||
|
||||
assert mod.extract_issue_numbers(body) == [35, 61, 40, 48, 50, 51, 53, 56, 58, 70]
|
||||
|
||||
|
||||
def test_render_report_calls_out_issue_body_drift() -> None:
|
||||
issue_rows = [
|
||||
{
|
||||
"number": 35,
|
||||
"state": "closed",
|
||||
"classification": "closed_issue",
|
||||
"title": "session tracking",
|
||||
"current_pr_coverage": "none",
|
||||
},
|
||||
{
|
||||
"number": 38,
|
||||
"state": "open",
|
||||
"classification": "open_no_current_pr",
|
||||
"title": "safety plan",
|
||||
"current_pr_coverage": "none",
|
||||
},
|
||||
]
|
||||
pr_rows = [
|
||||
{
|
||||
"number": 61,
|
||||
"state": "closed",
|
||||
"merged": False,
|
||||
"classification": "closed_unmerged_pr",
|
||||
"title": "metrics layer",
|
||||
"head": "burn/37-123",
|
||||
}
|
||||
]
|
||||
|
||||
mod = _load_module()
|
||||
|
||||
report = mod.render_report(
|
||||
source_issue=75,
|
||||
source_title="TRIAGE: The Door - Fleet Work Orders (2026-04-09)",
|
||||
generated_at="2026-04-17T04:00:00Z",
|
||||
claimed_open_issues=13,
|
||||
claimed_open_prs=24,
|
||||
live_open_issues=5,
|
||||
live_open_prs=0,
|
||||
issue_rows=issue_rows,
|
||||
pr_rows=pr_rows,
|
||||
)
|
||||
|
||||
assert "## Source Snapshot" in report
|
||||
assert "## Live Summary" in report
|
||||
assert "## Issue Body Drift" in report
|
||||
assert "13" in report and "24" in report
|
||||
assert "#38" in report
|
||||
assert "open_no_current_pr" in report
|
||||
assert "#61" in report
|
||||
assert "closed_unmerged_pr" in report
|
||||
assert "## Referenced Issue Snapshot" in report
|
||||
assert "## Referenced PR Snapshot" in report
|
||||
assert "## Recommended Next Actions" in report
|
||||
|
||||
|
||||
def test_committed_work_orders_audit_exists_with_required_sections() -> None:
|
||||
text = REPORT_PATH.read_text(encoding="utf-8")
|
||||
|
||||
required = [
|
||||
"# The Door Fleet Work Orders Audit — issue #75",
|
||||
"## Source Snapshot",
|
||||
"## Live Summary",
|
||||
"## Issue Body Drift",
|
||||
"## Referenced Issue Snapshot",
|
||||
"## Referenced PR Snapshot",
|
||||
"## Recommended Next Actions",
|
||||
]
|
||||
missing = [item for item in required if item not in text]
|
||||
assert not missing, missing
|
||||
@@ -50,22 +50,6 @@ 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()
|
||||
|
||||
@@ -1,277 +0,0 @@
|
||||
"""
|
||||
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()
|
||||
134
tests/test_voice_analysis.py
Normal file
134
tests/test_voice_analysis.py
Normal file
@@ -0,0 +1,134 @@
|
||||
"""Tests for voice message distress analysis (#131)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import pytest
|
||||
|
||||
from voice_analysis import (
|
||||
VoiceAnalysisResult,
|
||||
compute_speech_rate,
|
||||
compute_distress_score,
|
||||
DISTRESS_THRESHOLDS,
|
||||
NORMAL_SPEECH_RATE,
|
||||
NORMAL_PITCH_VAR,
|
||||
)
|
||||
|
||||
|
||||
class TestDistressScore:
|
||||
"""Distress score computation from paralinguistic features."""
|
||||
|
||||
def test_normal_speech_no_distress(self):
|
||||
score, signals = compute_distress_score(
|
||||
speech_rate=140, # normal
|
||||
pitch_variability=50, # normal
|
||||
silence_ratio=0.15, # normal
|
||||
volume_db=-20, # normal
|
||||
)
|
||||
assert score < 0.1
|
||||
assert not signals
|
||||
|
||||
def test_slow_speech_detected(self):
|
||||
score, signals = compute_distress_score(
|
||||
speech_rate=60, # very slow
|
||||
pitch_variability=50,
|
||||
silence_ratio=0.15,
|
||||
volume_db=-20,
|
||||
)
|
||||
assert score > 0.1
|
||||
assert any("slow" in s for s in signals)
|
||||
|
||||
def test_monotone_detected(self):
|
||||
score, signals = compute_distress_score(
|
||||
speech_rate=140,
|
||||
pitch_variability=10, # very monotone
|
||||
silence_ratio=0.15,
|
||||
volume_db=-20,
|
||||
)
|
||||
assert score > 0.1
|
||||
assert any("monotone" in s for s in signals)
|
||||
|
||||
def test_long_pauses_detected(self):
|
||||
score, signals = compute_distress_score(
|
||||
speech_rate=140,
|
||||
pitch_variability=50,
|
||||
silence_ratio=0.50, # very quiet
|
||||
volume_db=-20,
|
||||
)
|
||||
assert score > 0.1
|
||||
assert any("pause" in s for s in signals)
|
||||
|
||||
def test_quiet_voice_detected(self):
|
||||
score, signals = compute_distress_score(
|
||||
speech_rate=140,
|
||||
pitch_variability=50,
|
||||
silence_ratio=0.15,
|
||||
volume_db=-45, # very quiet
|
||||
)
|
||||
assert score > 0.1
|
||||
assert any("quiet" in s for s in signals)
|
||||
|
||||
def test_multiple_signals_compound(self):
|
||||
score, signals = compute_distress_score(
|
||||
speech_rate=50, # very slow
|
||||
pitch_variability=5, # very monotone
|
||||
silence_ratio=0.55, # long pauses
|
||||
volume_db=-50, # very quiet
|
||||
)
|
||||
assert score > 0.5
|
||||
assert len(signals) >= 3
|
||||
|
||||
def test_max_score_is_1(self):
|
||||
score, _ = compute_distress_score(
|
||||
speech_rate=0,
|
||||
pitch_variability=0,
|
||||
silence_ratio=1.0,
|
||||
volume_db=-100,
|
||||
)
|
||||
assert score <= 1.0
|
||||
|
||||
|
||||
class TestSpeechRate:
|
||||
"""Speech rate computation."""
|
||||
|
||||
def test_normal_rate(self):
|
||||
# 100 words in 60 seconds = 100 wpm
|
||||
segments = [{"start": 0.0, "end": 60.0, "text": "x"}]
|
||||
wpm = compute_speech_rate("word " * 100, segments)
|
||||
assert abs(wpm - 100) < 5
|
||||
|
||||
def test_empty_transcript(self):
|
||||
assert compute_speech_rate("", []) == 0.0
|
||||
|
||||
def test_no_segments(self):
|
||||
assert compute_speech_rate("hello world", []) == 0.0
|
||||
|
||||
|
||||
class TestDistressThresholds:
|
||||
"""Threshold configuration."""
|
||||
|
||||
def test_thresholds_ordered(self):
|
||||
assert DISTRESS_THRESHOLDS["low"] < DISTRESS_THRESHOLDS["medium"]
|
||||
assert DISTRESS_THRESHOLDS["medium"] < DISTRESS_THRESHOLDS["high"]
|
||||
|
||||
def test_low_is_03(self):
|
||||
assert DISTRESS_THRESHOLDS["low"] == 0.3
|
||||
|
||||
def test_high_is_10(self):
|
||||
assert DISTRESS_THRESHOLDS["high"] == 1.0
|
||||
|
||||
|
||||
class TestVoiceAnalysisResult:
|
||||
"""Result data structure."""
|
||||
|
||||
def test_creation(self):
|
||||
result = VoiceAnalysisResult(
|
||||
transcript="hello", speech_rate_wpm=120.0,
|
||||
pitch_mean_hz=150.0, pitch_variability=40.0,
|
||||
silence_ratio=0.2, volume_db=-20.0,
|
||||
volume_variability=5.0, duration_seconds=10.0,
|
||||
distress_score=0.1, distress_level="low",
|
||||
distress_signals=[],
|
||||
)
|
||||
assert result.transcript == "hello"
|
||||
assert result.distress_level == "low"
|
||||
assert not result.distress_signals
|
||||
356
voice_analysis.py
Normal file
356
voice_analysis.py
Normal file
@@ -0,0 +1,356 @@
|
||||
"""Voice message distress analysis — paralinguistic features (#131).
|
||||
|
||||
Analyzes audio (OGG/MP3/WAV) for distress signals using audio
|
||||
features extracted without a neural model — pure DSP analysis.
|
||||
|
||||
Signals detected:
|
||||
- Speech rate (words per minute from timestamps)
|
||||
- Pitch variability (F0 std deviation — monotone = depression indicator)
|
||||
- Silence ratio (long pauses)
|
||||
- Volume dynamics (drops, tremor proxy)
|
||||
|
||||
Uses whisper for transcription + word timestamps. All other features
|
||||
are computed from raw audio via librosa.
|
||||
|
||||
Refs: #131 — Epic #102 (Multimodal Crisis Detection)
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import subprocess
|
||||
import tempfile
|
||||
from dataclasses import dataclass, asdict
|
||||
from pathlib import Path
|
||||
from typing import Optional, List, Dict, Any
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
@dataclass
|
||||
class VoiceAnalysisResult:
|
||||
"""Result of voice message paralinguistic analysis."""
|
||||
transcript: str
|
||||
speech_rate_wpm: float # words per minute
|
||||
pitch_mean_hz: float # mean F0 in Hz
|
||||
pitch_variability: float # F0 standard deviation (low = monotone)
|
||||
silence_ratio: float # fraction of audio that is silence (0-1)
|
||||
volume_db: float # mean volume in dB
|
||||
volume_variability: float # volume std deviation
|
||||
duration_seconds: float # total audio duration
|
||||
distress_score: float # 0-1 composite score
|
||||
distress_level: str # "low", "medium", "high"
|
||||
distress_signals: List[str] # list of detected signals
|
||||
|
||||
|
||||
# Distress thresholds
|
||||
DISTRESS_THRESHOLDS = {
|
||||
"low": 0.3,
|
||||
"medium": 0.7,
|
||||
"high": 1.0,
|
||||
}
|
||||
|
||||
# Paralinguistic distress indicators
|
||||
# These are heuristic — the model learns what "normal" looks like
|
||||
# and flags deviations.
|
||||
NORMAL_SPEECH_RATE = (100, 180) # words per minute
|
||||
NORMAL_PITCH_VAR = (20, 80) # F0 std deviation in Hz
|
||||
NORMAL_SILENCE_RATIO = (0.05, 0.35) # fraction of silence
|
||||
NORMAL_VOLUME_DB = (-30, -10) # dB range
|
||||
|
||||
|
||||
def _ensure_whisper():
|
||||
"""Check if whisper is available."""
|
||||
try:
|
||||
result = subprocess.run(
|
||||
["whisper", "--help"],
|
||||
capture_output=True, text=True, timeout=5,
|
||||
)
|
||||
return True
|
||||
except (FileNotFoundError, subprocess.TimeoutExpired):
|
||||
return False
|
||||
|
||||
|
||||
def _ensure_librosa():
|
||||
"""Check if librosa is available."""
|
||||
try:
|
||||
import librosa
|
||||
return True
|
||||
except ImportError:
|
||||
return False
|
||||
|
||||
|
||||
def transcribe_with_timestamps(audio_path: str) -> Dict[str, Any]:
|
||||
"""Transcribe audio using whisper and extract word-level timestamps.
|
||||
|
||||
Returns dict with 'text' and 'segments' (list of {start, end, text}).
|
||||
Falls back to subprocess whisper if Python whisper not available.
|
||||
"""
|
||||
try:
|
||||
import whisper
|
||||
model = whisper.load_model("base")
|
||||
result = model.transcribe(audio_path, word_timestamps=True)
|
||||
return {
|
||||
"text": result["text"],
|
||||
"segments": [
|
||||
{"start": s["start"], "end": s["end"], "text": s["text"]}
|
||||
for s in result.get("segments", [])
|
||||
],
|
||||
}
|
||||
except ImportError:
|
||||
pass
|
||||
|
||||
# Fallback: subprocess whisper
|
||||
with tempfile.NamedTemporaryFile(suffix=".json", delete=False) as f:
|
||||
json_out = f.name
|
||||
|
||||
try:
|
||||
subprocess.run(
|
||||
["whisper", audio_path, "--model", "base", "--output_format", "json",
|
||||
"--output_dir", os.path.dirname(json_out)],
|
||||
capture_output=True, text=True, timeout=120,
|
||||
)
|
||||
|
||||
# Whisper outputs to <filename>.json in output_dir
|
||||
base = Path(audio_path).stem
|
||||
whisper_out = Path(os.path.dirname(json_out)) / f"{base}.json"
|
||||
|
||||
if whisper_out.exists():
|
||||
with open(whisper_out) as f:
|
||||
data = json.load(f)
|
||||
os.unlink(whisper_out)
|
||||
return {
|
||||
"text": data.get("text", ""),
|
||||
"segments": [
|
||||
{"start": s["start"], "end": s["end"], "text": s["text"]}
|
||||
for s in data.get("segments", [])
|
||||
],
|
||||
}
|
||||
except Exception as e:
|
||||
logger.warning("Whisper transcription failed: %s", e)
|
||||
finally:
|
||||
if os.path.exists(json_out):
|
||||
os.unlink(json_out)
|
||||
|
||||
return {"text": "", "segments": []}
|
||||
|
||||
|
||||
def extract_audio_features(audio_path: str) -> Dict[str, float]:
|
||||
"""Extract paralinguistic features from raw audio using librosa.
|
||||
|
||||
Returns dict with pitch, volume, and silence metrics.
|
||||
"""
|
||||
try:
|
||||
import librosa
|
||||
import numpy as np
|
||||
except ImportError:
|
||||
logger.warning("librosa not available — returning defaults")
|
||||
return {
|
||||
"pitch_mean_hz": 0.0, "pitch_variability": 0.0,
|
||||
"silence_ratio": 0.0, "volume_db": 0.0, "volume_variability": 0.0,
|
||||
"duration_seconds": 0.0,
|
||||
}
|
||||
|
||||
try:
|
||||
y, sr = librosa.load(audio_path, sr=None)
|
||||
except Exception as e:
|
||||
logger.warning("Failed to load audio %s: %s", audio_path, e)
|
||||
return {
|
||||
"pitch_mean_hz": 0.0, "pitch_variability": 0.0,
|
||||
"silence_ratio": 0.0, "volume_db": 0.0, "volume_variability": 0.0,
|
||||
"duration_seconds": 0.0,
|
||||
}
|
||||
|
||||
duration = len(y) / sr
|
||||
|
||||
# Pitch (F0) estimation using pyin
|
||||
try:
|
||||
f0, voiced_flag, _ = librosa.pyin(y, fmin=50, fmax=500, sr=sr)
|
||||
f0_voiced = f0[~np.isnan(f0)]
|
||||
if len(f0_voiced) > 0:
|
||||
pitch_mean = float(np.mean(f0_voiced))
|
||||
pitch_var = float(np.std(f0_voiced))
|
||||
else:
|
||||
pitch_mean = 0.0
|
||||
pitch_var = 0.0
|
||||
except Exception:
|
||||
pitch_mean = 0.0
|
||||
pitch_var = 0.0
|
||||
|
||||
# Volume (RMS energy)
|
||||
rms = librosa.feature.rms(y=y)[0]
|
||||
volume_db = float(librosa.amplitude_to_db(rms, ref=np.max).mean())
|
||||
volume_var = float(librosa.amplitude_to_db(rms, ref=np.max).std())
|
||||
|
||||
# Silence ratio
|
||||
try:
|
||||
intervals = librosa.effects.split(y, top_db=30)
|
||||
speech_samples = sum(end - start for start, end in intervals)
|
||||
silence_ratio = 1.0 - (speech_samples / len(y)) if len(y) > 0 else 0.0
|
||||
except Exception:
|
||||
silence_ratio = 0.0
|
||||
|
||||
return {
|
||||
"pitch_mean_hz": round(pitch_mean, 1),
|
||||
"pitch_variability": round(pitch_var, 1),
|
||||
"silence_ratio": round(silence_ratio, 3),
|
||||
"volume_db": round(volume_db, 1),
|
||||
"volume_variability": round(volume_var, 1),
|
||||
"duration_seconds": round(duration, 2),
|
||||
}
|
||||
|
||||
|
||||
def compute_speech_rate(transcript: str, segments: List[dict]) -> float:
|
||||
"""Compute words per minute from transcript and timestamps."""
|
||||
words = len(transcript.split())
|
||||
if words == 0:
|
||||
return 0.0
|
||||
|
||||
if not segments:
|
||||
return 0.0
|
||||
|
||||
total_duration = max(s["end"] for s in segments) - min(s["start"] for s in segments)
|
||||
if total_duration <= 0:
|
||||
return 0.0
|
||||
|
||||
wpm = words / (total_duration / 60.0)
|
||||
return round(wpm, 1)
|
||||
|
||||
|
||||
def compute_distress_score(
|
||||
speech_rate: float,
|
||||
pitch_variability: float,
|
||||
silence_ratio: float,
|
||||
volume_db: float,
|
||||
) -> tuple[float, List[str]]:
|
||||
"""Compute composite distress score from paralinguistic features.
|
||||
|
||||
Returns (score, signals) where score is 0-1 and signals is a list
|
||||
of detected distress indicators.
|
||||
"""
|
||||
signals = []
|
||||
scores = []
|
||||
|
||||
# Speech rate: very slow (<80) or very fast (>200) is concerning
|
||||
if speech_rate > 0:
|
||||
if speech_rate < NORMAL_SPEECH_RATE[0]:
|
||||
signals.append(f"very_slow_speech ({speech_rate:.0f} wpm)")
|
||||
scores.append(min(1.0, (NORMAL_SPEECH_RATE[0] - speech_rate) / 50))
|
||||
elif speech_rate > NORMAL_SPEECH_RATE[1]:
|
||||
signals.append(f"very_fast_speech ({speech_rate:.0f} wpm)")
|
||||
scores.append(min(1.0, (speech_rate - NORMAL_SPEECH_RATE[1]) / 80))
|
||||
else:
|
||||
scores.append(0.0)
|
||||
|
||||
# Pitch variability: low = monotone (depression indicator)
|
||||
if pitch_variability > 0:
|
||||
if pitch_variability < NORMAL_PITCH_VAR[0]:
|
||||
signals.append(f"monotone_voice (F0_var={pitch_variability:.0f}Hz)")
|
||||
scores.append(min(1.0, (NORMAL_PITCH_VAR[0] - pitch_variability) / NORMAL_PITCH_VAR[0]))
|
||||
else:
|
||||
scores.append(0.0)
|
||||
|
||||
# Silence ratio: high = long pauses
|
||||
if silence_ratio > NORMAL_SILENCE_RATIO[1]:
|
||||
signals.append(f"long_pauses (silence={silence_ratio:.0%})")
|
||||
scores.append(min(1.0, (silence_ratio - NORMAL_SILENCE_RATIO[1]) / 0.4))
|
||||
else:
|
||||
scores.append(0.0)
|
||||
|
||||
# Volume: very quiet
|
||||
if volume_db < NORMAL_VOLUME_DB[0]:
|
||||
signals.append(f"very_quiet ({volume_db:.0f}dB)")
|
||||
scores.append(min(1.0, abs(volume_db - NORMAL_VOLUME_DB[0]) / 20))
|
||||
else:
|
||||
scores.append(0.0)
|
||||
|
||||
# Composite: max of individual signals (not average — one severe signal is enough)
|
||||
if scores:
|
||||
score = max(scores)
|
||||
else:
|
||||
score = 0.0
|
||||
|
||||
return round(score, 3), signals
|
||||
|
||||
|
||||
def analyze_voice_message(audio_path: str) -> VoiceAnalysisResult:
|
||||
"""Analyze a voice message for distress signals.
|
||||
|
||||
Args:
|
||||
audio_path: Path to audio file (OGG, MP3, WAV).
|
||||
|
||||
Returns:
|
||||
VoiceAnalysisResult with all paralinguistic features.
|
||||
"""
|
||||
# Step 1: Transcribe with timestamps
|
||||
transcription = transcribe_with_timestamps(audio_path)
|
||||
transcript = transcription["text"]
|
||||
segments = transcription["segments"]
|
||||
|
||||
# Step 2: Extract audio features
|
||||
features = extract_audio_features(audio_path)
|
||||
|
||||
# Step 3: Compute speech rate
|
||||
wpm = compute_speech_rate(transcript, segments)
|
||||
|
||||
# Step 4: Compute distress score
|
||||
distress_score, distress_signals = compute_distress_score(
|
||||
speech_rate=wpm,
|
||||
pitch_variability=features["pitch_variability"],
|
||||
silence_ratio=features["silence_ratio"],
|
||||
volume_db=features["volume_db"],
|
||||
)
|
||||
|
||||
# Determine level
|
||||
if distress_score >= DISTRESS_THRESHOLDS["high"]:
|
||||
level = "high"
|
||||
elif distress_score >= DISTRESS_THRESHOLDS["medium"]:
|
||||
level = "medium"
|
||||
else:
|
||||
level = "low"
|
||||
|
||||
return VoiceAnalysisResult(
|
||||
transcript=transcript,
|
||||
speech_rate_wpm=wpm,
|
||||
pitch_mean_hz=features["pitch_mean_hz"],
|
||||
pitch_variability=features["pitch_variability"],
|
||||
silence_ratio=features["silence_ratio"],
|
||||
volume_db=features["volume_db"],
|
||||
volume_variability=features["volume_variability"],
|
||||
duration_seconds=features["duration_seconds"],
|
||||
distress_score=distress_score,
|
||||
distress_level=level,
|
||||
distress_signals=distress_signals,
|
||||
)
|
||||
|
||||
|
||||
def main():
|
||||
import argparse
|
||||
p = argparse.ArgumentParser(description="Voice message distress analysis")
|
||||
p.add_argument("audio", help="Path to audio file")
|
||||
p.add_argument("--json", action="store_true")
|
||||
a = p.parse_args()
|
||||
|
||||
if not os.path.exists(a.audio):
|
||||
print(f"File not found: {a.audio}", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
result = analyze_voice_message(a.audio)
|
||||
|
||||
if a.json:
|
||||
print(json.dumps(asdict(result), indent=2))
|
||||
else:
|
||||
print(f"Transcript: {result.transcript[:100]}...")
|
||||
print(f"Speech rate: {result.speech_rate_wpm} wpm")
|
||||
print(f"Pitch: {result.pitch_mean_hz} Hz (variability: {result.pitch_variability})")
|
||||
print(f"Silence: {result.silence_ratio:.0%}")
|
||||
print(f"Volume: {result.volume_db} dB")
|
||||
print(f"Distress: {result.distress_score:.2f} ({result.distress_level})")
|
||||
if result.distress_signals:
|
||||
print(f"Signals: {', '.join(result.distress_signals)}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in New Issue
Block a user