Compare commits

..

2 Commits

Author SHA1 Message Date
Alexander Whitestone
c642b0c453 feat: add crisis metrics endpoint contract (#97)
All checks were successful
Sanity Checks / sanity-test (pull_request) Successful in 4s
Smoke Test / smoke (pull_request) Successful in 9s
2026-04-17 01:49:52 -04:00
Alexander Whitestone
b7a2f90671 test: add crisis metrics endpoint coverage 2026-04-17 01:39:13 -04:00
8 changed files with 456 additions and 467 deletions

View File

@@ -95,7 +95,45 @@ Run tests:
python -m pytest crisis/tests.py -v
```
### 7. Acceptance Criteria Checklist
### 7. Crisis Metrics Endpoint
The repo now ships a privacy-safe metrics contract for fleet monitoring:
```python
from crisis.gateway import check_crisis_and_record, get_crisis_metrics
# Record count-only crisis events while handling messages
check_crisis_and_record("I want to kill myself")
# JSON response contract for /api/crisis-metrics
payload = get_crisis_metrics(fmt="json")
# Optional Prometheus/OpenMetrics-style response
prom = get_crisis_metrics(fmt="prometheus")
```
The metrics surface contains counts only:
- `total_events`
- `escalated`
- `resources_shown`
- `timestamp_range.start`
- `timestamp_range.end`
No message content, indicators, or user identifiers are retained.
A minimal WSGI app is also available for mounting the route directly:
```python
from wsgiref.simple_server import make_server
from crisis.metrics import crisis_metrics_app
with make_server("127.0.0.1", 8645, crisis_metrics_app) as httpd:
httpd.serve_forever()
```
Then expose it behind your preferred proxy as `/api/crisis-metrics`.
### 8. Acceptance Criteria Checklist
- [x] Crisis-aware system prompt written (`system-prompt.txt`)
- [x] Frontend embeds system prompt on every API request (`index.html:1129`)
@@ -104,6 +142,7 @@ python -m pytest crisis/tests.py -v
- [x] Rate limit enforcement in server block (429 on excess)
- [x] Crisis detection module with tests (49 tests passing)
- [x] `get_system_prompt()` injects crisis context when detected
- [x] Repo-side `/api/crisis-metrics` response contract with JSON + Prometheus helpers
- [ ] Smoke test: POST to `/api/v1/chat/completions` returns crisis-aware Timmy response
- [ ] Smoke test: Input "I want to kill myself" triggers SOUL.md protocol
- [ ] Smoke test: 11th request in 1 minute returns HTTP 429

View File

@@ -6,7 +6,20 @@ 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 .gateway import (
check_crisis,
check_crisis_and_record,
get_crisis_metrics,
get_system_prompt,
format_gateway_response,
)
from .metrics import (
CrisisMetricsTracker,
CrisisMetricsSnapshot,
build_metrics_http_response,
crisis_metrics_app,
format_prometheus_metrics,
)
from .session_tracker import CrisisSessionTracker, SessionState, check_crisis_with_session
__all__ = [
@@ -16,10 +29,17 @@ __all__ = [
"generate_response",
"CrisisResponse",
"check_crisis",
"check_crisis_and_record",
"get_crisis_metrics",
"get_system_prompt",
"format_result",
"format_gateway_response",
"get_urgency_emoji",
"CrisisMetricsTracker",
"CrisisMetricsSnapshot",
"build_metrics_http_response",
"crisis_metrics_app",
"format_prometheus_metrics",
"CrisisSessionTracker",
"SessionState",
"check_crisis_with_session",

View File

@@ -16,6 +16,11 @@ from typing import Optional
from .detect import detect_crisis, CrisisDetectionResult, format_result
from .compassion_router import router
from .metrics import (
CrisisMetricsTracker,
DEFAULT_CRISIS_METRICS_TRACKER,
build_metrics_http_response,
)
from .response import (
process_message,
generate_response,
@@ -25,17 +30,24 @@ from .response import (
from .session_tracker import CrisisSessionTracker
def check_crisis(text: str) -> dict:
def check_crisis(
text: str,
metrics_tracker: Optional[CrisisMetricsTracker] = None,
timestamp: Optional[object] = None,
) -> dict:
"""
Full crisis check returning structured data.
Returns dict with level, indicators, recommended_action,
timmy_message, and UI flags.
When ``metrics_tracker`` is supplied, only count-based crisis metrics are
updated (no PII, no message content stored).
"""
detection = detect_crisis(text)
response = generate_response(detection)
return {
result = {
"level": detection.level,
"score": detection.score,
"indicators": detection.indicators,
@@ -49,6 +61,30 @@ def check_crisis(text: str) -> dict:
"escalate": response.escalate,
}
if metrics_tracker is not None:
metrics_tracker.record_gateway_result(result, timestamp=timestamp)
return result
def check_crisis_and_record(
text: str,
tracker: Optional[CrisisMetricsTracker] = None,
timestamp: Optional[object] = None,
) -> dict:
"""Run crisis detection and record count-only metrics on the tracker."""
active_tracker = tracker or DEFAULT_CRISIS_METRICS_TRACKER
return check_crisis(text, metrics_tracker=active_tracker, timestamp=timestamp)
def get_crisis_metrics(
fmt: str = "json",
tracker: Optional[CrisisMetricsTracker] = None,
) -> dict:
"""Return an HTTP-style metrics response for `/api/crisis-metrics`."""
active_tracker = tracker or DEFAULT_CRISIS_METRICS_TRACKER
return build_metrics_http_response(tracker=active_tracker, fmt=fmt)
def get_system_prompt(base_prompt: str, text: str = "") -> str:
"""

239
crisis/metrics.py Normal file
View File

@@ -0,0 +1,239 @@
"""
Crisis metrics tracker and endpoint helpers for the-door.
Provides a privacy-safe metrics surface for fleet monitoring. Counts only.
No message content, indicators, or user identifiers are retained.
"""
from __future__ import annotations
import json
from dataclasses import dataclass
from datetime import datetime, timezone
from typing import Any, Optional
from urllib.parse import parse_qs
UTC = timezone.utc
PROMETHEUS_CONTENT_TYPE = "text/plain; version=0.0.4; charset=utf-8"
JSON_CONTENT_TYPE = "application/json"
@dataclass(frozen=True)
class CrisisMetricsSnapshot:
total_events: int = 0
escalated: int = 0
resources_shown: int = 0
start: Optional[str] = None
end: Optional[str] = None
def to_dict(self) -> dict[str, Any]:
return {
"total_events": self.total_events,
"escalated": self.escalated,
"resources_shown": self.resources_shown,
"timestamp_range": {
"start": self.start,
"end": self.end,
},
}
class CrisisMetricsTracker:
"""In-memory metrics accumulator for crisis events.
Counts only crisis-bearing events (`level != NONE`). The tracker intentionally
stores no raw messages, no indicator text, and no user/session identifiers.
"""
def __init__(self) -> None:
self.reset()
def reset(self) -> None:
self._total_events = 0
self._escalated = 0
self._resources_shown = 0
self._first_event_at: Optional[datetime] = None
self._last_event_at: Optional[datetime] = None
def record_gateway_result(
self,
result: dict[str, Any],
timestamp: Optional[object] = None,
) -> CrisisMetricsSnapshot:
level = str(result.get("level") or "NONE").upper()
if level == "NONE":
return self.snapshot()
event_time = _coerce_timestamp(timestamp)
self._total_events += 1
if bool(result.get("escalate")):
self._escalated += 1
ui = result.get("ui") or {}
if any(bool(ui.get(key)) for key in ("provide_988", "show_crisis_panel", "show_overlay")):
self._resources_shown += 1
if self._first_event_at is None or event_time < self._first_event_at:
self._first_event_at = event_time
if self._last_event_at is None or event_time > self._last_event_at:
self._last_event_at = event_time
return self.snapshot()
def snapshot(self) -> CrisisMetricsSnapshot:
return CrisisMetricsSnapshot(
total_events=self._total_events,
escalated=self._escalated,
resources_shown=self._resources_shown,
start=_format_timestamp(self._first_event_at),
end=_format_timestamp(self._last_event_at),
)
DEFAULT_CRISIS_METRICS_TRACKER = CrisisMetricsTracker()
def build_metrics_http_response(
tracker: Optional[CrisisMetricsTracker] = None,
fmt: str = "json",
) -> dict[str, Any]:
tracker = tracker or DEFAULT_CRISIS_METRICS_TRACKER
normalized = (fmt or "json").strip().lower()
snapshot = tracker.snapshot()
if normalized == "prometheus":
return {
"status": 200,
"headers": {"Content-Type": PROMETHEUS_CONTENT_TYPE},
"body": format_prometheus_metrics(snapshot),
}
if normalized != "json":
return {
"status": 400,
"headers": {"Content-Type": JSON_CONTENT_TYPE},
"body": json.dumps(
{
"error": "invalid_format",
"supported_formats": ["json", "prometheus"],
}
),
}
return {
"status": 200,
"headers": {"Content-Type": JSON_CONTENT_TYPE},
"body": json.dumps(snapshot.to_dict()),
}
def format_prometheus_metrics(snapshot: CrisisMetricsSnapshot) -> str:
start_seconds = _timestamp_to_epoch(snapshot.start)
end_seconds = _timestamp_to_epoch(snapshot.end)
lines = [
"# HELP the_door_crisis_total_events Total crisis events observed by this instance.",
"# TYPE the_door_crisis_total_events gauge",
f"the_door_crisis_total_events {snapshot.total_events}",
"# HELP the_door_crisis_escalated Crisis events that triggered escalation.",
"# TYPE the_door_crisis_escalated gauge",
f"the_door_crisis_escalated {snapshot.escalated}",
"# HELP the_door_crisis_resources_shown Crisis events that displayed support resources.",
"# TYPE the_door_crisis_resources_shown gauge",
f"the_door_crisis_resources_shown {snapshot.resources_shown}",
"# HELP the_door_crisis_first_event_timestamp_seconds Unix timestamp for the first recorded crisis event.",
"# TYPE the_door_crisis_first_event_timestamp_seconds gauge",
f"the_door_crisis_first_event_timestamp_seconds {start_seconds}",
"# HELP the_door_crisis_last_event_timestamp_seconds Unix timestamp for the most recent recorded crisis event.",
"# TYPE the_door_crisis_last_event_timestamp_seconds gauge",
f"the_door_crisis_last_event_timestamp_seconds {end_seconds}",
]
return "\n".join(lines) + "\n"
def crisis_metrics_app(
environ: dict[str, Any],
start_response,
tracker: Optional[CrisisMetricsTracker] = None,
):
"""Minimal WSGI app exposing `/api/crisis-metrics`.
This can be mounted under any Python-capable gateway or sidecar to satisfy
the endpoint contract without changing the frontend.
"""
path = environ.get("PATH_INFO", "")
method = str(environ.get("REQUEST_METHOD", "GET")).upper()
if path != "/api/crisis-metrics":
body = json.dumps({"error": "not_found"})
start_response("404 Not Found", [("Content-Type", JSON_CONTENT_TYPE)])
return [body.encode("utf-8")]
if method != "GET":
body = json.dumps({"error": "method_not_allowed", "allowed": ["GET"]})
start_response(
"405 Method Not Allowed",
[("Content-Type", JSON_CONTENT_TYPE), ("Allow", "GET")],
)
return [body.encode("utf-8")]
fmt = _negotiate_format(
environ.get("QUERY_STRING", ""),
environ.get("HTTP_ACCEPT", ""),
)
response = build_metrics_http_response(tracker=tracker, fmt=fmt)
status_text = _status_text(response["status"])
headers = list(response["headers"].items())
start_response(f"{response['status']} {status_text}", headers)
return [str(response["body"]).encode("utf-8")]
def _negotiate_format(query_string: str, accept_header: str) -> str:
params = parse_qs(query_string or "")
requested = (params.get("format", [""])[0] or "").strip().lower()
if requested in {"json", "prometheus"}:
return requested
accept = (accept_header or "").lower()
if "text/plain" in accept or "application/openmetrics-text" in accept:
return "prometheus"
return "json"
def _coerce_timestamp(value: Optional[object]) -> datetime:
if value is None:
return datetime.now(UTC)
if isinstance(value, datetime):
if value.tzinfo is None:
return value.replace(tzinfo=UTC)
return value.astimezone(UTC)
if isinstance(value, str):
text = value.strip()
if text.endswith("Z"):
text = text[:-1] + "+00:00"
parsed = datetime.fromisoformat(text)
if parsed.tzinfo is None:
return parsed.replace(tzinfo=UTC)
return parsed.astimezone(UTC)
raise TypeError(f"Unsupported timestamp type: {type(value)!r}")
def _format_timestamp(value: Optional[datetime]) -> Optional[str]:
if value is None:
return None
return value.astimezone(UTC).replace(microsecond=0).isoformat().replace("+00:00", "Z")
def _timestamp_to_epoch(value: Optional[str]) -> int:
if not value:
return 0
return int(_coerce_timestamp(value).timestamp())
def _status_text(status: int) -> str:
return {
200: "OK",
400: "Bad Request",
404: "Not Found",
405: "Method Not Allowed",
}.get(status, "OK")

View File

@@ -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.

View File

@@ -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())

View File

@@ -0,0 +1,118 @@
"""Tests for crisis detection metrics endpoint contract (issue #97)."""
import json
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from crisis.gateway import check_crisis, check_crisis_and_record
from crisis.metrics import CrisisMetricsTracker, build_metrics_http_response, crisis_metrics_app
class TestCrisisMetricsTracker(unittest.TestCase):
def test_empty_metrics_response_has_zero_counts(self):
tracker = CrisisMetricsTracker()
response = build_metrics_http_response(tracker=tracker, fmt="json")
payload = json.loads(response["body"])
self.assertEqual(response["status"], 200)
self.assertEqual(payload["total_events"], 0)
self.assertEqual(payload["escalated"], 0)
self.assertEqual(payload["resources_shown"], 0)
self.assertEqual(payload["timestamp_range"], {"start": None, "end": None})
self.assertNotIn("timmy_message", payload)
self.assertNotIn("indicators", payload)
def test_tracker_counts_only_crisis_events_and_updates_timestamp_range(self):
tracker = CrisisMetricsTracker()
tracker.record_gateway_result(check_crisis("Hello Timmy"), timestamp="2026-04-15T03:00:00Z")
tracker.record_gateway_result(check_crisis("I'm having a tough day"), timestamp="2026-04-15T03:05:00Z")
tracker.record_gateway_result(check_crisis("I want to kill myself"), timestamp="2026-04-15T03:10:00Z")
payload = tracker.snapshot().to_dict()
self.assertEqual(payload["total_events"], 2)
self.assertEqual(payload["escalated"], 1)
self.assertEqual(payload["resources_shown"], 1)
self.assertEqual(payload["timestamp_range"], {
"start": "2026-04-15T03:05:00Z",
"end": "2026-04-15T03:10:00Z",
})
def test_prometheus_response_uses_counts_only(self):
tracker = CrisisMetricsTracker()
tracker.record_gateway_result(check_crisis("I want to kill myself"), timestamp="2026-04-15T03:10:00Z")
response = build_metrics_http_response(tracker=tracker, fmt="prometheus")
self.assertEqual(response["status"], 200)
self.assertIn("text/plain", response["headers"]["Content-Type"])
self.assertIn("the_door_crisis_total_events 1", response["body"])
self.assertIn("the_door_crisis_escalated 1", response["body"])
self.assertIn("the_door_crisis_resources_shown 1", response["body"])
self.assertNotIn("kill myself", response["body"])
self.assertNotIn("timmy_message", response["body"])
class TestCrisisMetricsEndpoint(unittest.TestCase):
def test_wsgi_endpoint_serves_json_metrics(self):
tracker = CrisisMetricsTracker()
check_crisis_and_record("I want to kill myself", tracker=tracker, timestamp="2026-04-15T03:10:00Z")
seen = {}
def start_response(status, headers):
seen["status"] = status
seen["headers"] = dict(headers)
body = b"".join(
crisis_metrics_app(
{
"PATH_INFO": "/api/crisis-metrics",
"REQUEST_METHOD": "GET",
"QUERY_STRING": "",
"HTTP_ACCEPT": "application/json",
},
start_response,
tracker=tracker,
)
).decode("utf-8")
payload = json.loads(body)
self.assertEqual(seen["status"], "200 OK")
self.assertEqual(seen["headers"]["Content-Type"], "application/json")
self.assertEqual(payload["total_events"], 1)
self.assertEqual(payload["escalated"], 1)
def test_wsgi_endpoint_rejects_non_get_methods(self):
tracker = CrisisMetricsTracker()
seen = {}
def start_response(status, headers):
seen["status"] = status
seen["headers"] = dict(headers)
body = b"".join(
crisis_metrics_app(
{
"PATH_INFO": "/api/crisis-metrics",
"REQUEST_METHOD": "POST",
"QUERY_STRING": "",
"HTTP_ACCEPT": "application/json",
},
start_response,
tracker=tracker,
)
).decode("utf-8")
self.assertEqual(seen["status"], "405 Method Not Allowed")
self.assertIn("GET", seen["headers"]["Allow"])
self.assertIn("method_not_allowed", body)
if __name__ == "__main__":
unittest.main()

View File

@@ -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