timmy
b4be7049ea
Quality gates / quality (pull_request) Successful in 2m38s
Deterministic escalation only fired on a narrow set of literal phrases, so real reports like "there is blood when I wipe" or "I have tarry stools" reached the chat provider without the fixed medical guidance. Expanding the suite found 18 of 18 checked clinical phrasings missing. - domain: cover bleeding reported by wiping/toilet paper/anatomy/mixed-in phrasing, black-tarry-dark-red stool, reported temperature and high temperature, abdominal-scoped severe pain in every natural word order, and past-tense/slang inability to pass gas. Near-miss wording that must stay quiet (paper cut, blood pressure, black beans, dark red wine, a normal temperature, knee or back pain, passed gas, no gas in the car) is pinned. - domain: a symptom reported in any truthy shape (1, "yes", "true") now counts as reported. Reading only the literal boolean `true` silently cleared a symptom, which is the one direction this boundary may never fail in. - hermes-agent-service: the gateway ledger sanitizer used the same strict check, so a browser-supplied ledger entry could have its symptom cleared before the escalation check. - tests/escalation-regression.test.js: per-flag positive and negative language coverage, model output can neither set nor clear a symptom/urgency/discomfort/note, and the escalation copy is byte-identical for every flag and under a missing, throwing, or malicious provider. Registered in the default unit gate. - scripts/record_release_demo.mjs: the recording now types the new bleeding and tarry phrasing, and seeds a fictional ledger whose note says "stool was tarry yesterday", then asserts in the browser that exactly one new Timmy bubble carries the app's own copy and that the turn never reaches Hermes. Three new captions are required release gates. Boundary unchanged: no new inference, no diagnosis, no image claim. Escalation only ever gets broader on user-reported symptoms.
305 lines
19 KiB
Python
Executable File
305 lines
19 KiB
Python
Executable File
#!/usr/bin/env python3
|
||
"""Build a gated, reproducible Timmy review release from committed main."""
|
||
from __future__ import annotations
|
||
|
||
import datetime as dt
|
||
import hashlib
|
||
import json
|
||
import os
|
||
from pathlib import Path
|
||
import re
|
||
import shutil
|
||
import subprocess
|
||
import sys
|
||
import tarfile
|
||
import tempfile
|
||
import time
|
||
import urllib.request
|
||
|
||
ROOT = Path(__file__).resolve().parents[1]
|
||
OUT_ROOT = Path(os.environ.get("TIMMY_RELEASE_DIR", "/root/timmy-releases"))
|
||
PUBLIC_REPO = "https://forge.alexanderwhitestone.com/git/stackchain/timmy-talking-turd"
|
||
EXCLUDED_PREFIXES = ("video/", "research/source-pages/", "artifacts/")
|
||
EXCLUDED_SUFFIXES = (".gguf", ".bin", ".safetensors", ".onnx", ".pyc")
|
||
SECRET_PATTERNS = (
|
||
re.compile(r"-----BEGIN (?:RSA |EC |OPENSSH )?PRIVATE KEY-----"),
|
||
re.compile(r"(?i)(?:api[_-]?key|access[_-]?token|authorization)\s*[:=]\s*['\"](?!\.\.\.|top-secret|test-|example|placeholder)[A-Za-z0-9_./+:-]{16,}"),
|
||
)
|
||
|
||
# Captions that must be proven on camera (via the demo's own receipt) for the release to pass.
|
||
DEMO_REQUIRED_CAPTIONS = (
|
||
"One clear photo action. Manual logging stays one tap away.",
|
||
"Nothing uploads until explicit consent",
|
||
"The suggestion stays provisional — nothing is applied or saved until you confirm it",
|
||
"Type 2 is hard or lumpy, so Timmy asks about soreness, hydration, blood, and black-or-tarry — never guessed from the photo",
|
||
"Vision worker offline — the AI and consent steps disappear instead of failing after upload",
|
||
"Every byte-bearing control the model names, in the running app: local ledger, consent-gated upload, portable export, full deletion",
|
||
"Delete all local data clears the ledger in this browser; there is no server copy of it to keep",
|
||
"Hermes Agent connected — free-text, contextual, and server-side",
|
||
"Urgent language is intercepted deterministically before Hermes",
|
||
"Bleeding reported as wiping still escalates, in the app’s own fixed words",
|
||
"Tarry and black stool wording escalates too: one red flag, one unchanging message",
|
||
"A tarry note already saved in the journal escalates the same way, before any provider call",
|
||
"An out-of-range answer fails closed: nothing is applied and no provider detail reaches you",
|
||
"A filled-in field that is out of range still fails closed, even when the other field came back blank",
|
||
"Reachable is not loaded: no AI control, no consent, and no upload until the pinned model is resident",
|
||
"Every pattern line names the confirmed logs behind it, and following one shows exactly those records",
|
||
"Two logs is not a pattern: the summary refuses to describe a trend it cannot support",
|
||
)
|
||
|
||
|
||
def run(args: list[str], cwd: Path, *, capture: bool = False, env: dict[str, str] | None = None) -> str:
|
||
print("+", " ".join(args), flush=True)
|
||
result = subprocess.run(args, cwd=cwd, check=True, text=True, env=env,
|
||
stdout=subprocess.PIPE if capture else None)
|
||
return result.stdout.strip() if capture else ""
|
||
|
||
|
||
def sha256(path: Path) -> str:
|
||
digest = hashlib.sha256()
|
||
with path.open("rb") as handle:
|
||
for chunk in iter(lambda: handle.read(1024 * 1024), b""):
|
||
digest.update(chunk)
|
||
return digest.hexdigest()
|
||
|
||
|
||
def tracked_files(tree: Path) -> list[str]:
|
||
names = run(["git", "ls-files"], tree, capture=True).splitlines()
|
||
return sorted(name for name in names if name and not name.startswith(EXCLUDED_PREFIXES)
|
||
and not name.endswith(EXCLUDED_SUFFIXES))
|
||
|
||
|
||
def scan_secrets(tree: Path, names: list[str]) -> None:
|
||
forbidden_names = [name for name in names if Path(name).name == ".env" or name.endswith((".pem", ".key", ".p12"))]
|
||
findings: list[str] = list(forbidden_names)
|
||
for name in names:
|
||
path = tree / name
|
||
if not path.is_file() or path.stat().st_size > 2_000_000:
|
||
continue
|
||
try:
|
||
text = path.read_text(encoding="utf-8")
|
||
except UnicodeDecodeError:
|
||
continue
|
||
for pattern in SECRET_PATTERNS:
|
||
if pattern.search(text):
|
||
findings.append(name)
|
||
break
|
||
if findings:
|
||
raise SystemExit("Secret scan failed: " + ", ".join(sorted(set(findings))))
|
||
|
||
|
||
def main() -> int:
|
||
branch = run(["git", "branch", "--show-current"], ROOT, capture=True)
|
||
if branch != "main":
|
||
raise SystemExit(f"Release must build from main, not {branch!r}")
|
||
status = run(["git", "status", "--porcelain"], ROOT, capture=True)
|
||
if status:
|
||
raise SystemExit("Release requires a clean committed tree")
|
||
release_delta = os.environ.get("TIMMY_RELEASE_DELTA",
|
||
"Verified rebuild of the current user-visible feature path — no new feature is claimed.").strip()
|
||
if not release_delta:
|
||
raise SystemExit("TIMMY_RELEASE_DELTA must not be empty")
|
||
commit = run(["git", "rev-parse", "HEAD"], ROOT, capture=True)
|
||
short = commit[:12]
|
||
commit_epoch = int(run(["git", "show", "-s", "--format=%ct", commit], ROOT, capture=True))
|
||
source_date = dt.datetime.fromtimestamp(commit_epoch, dt.timezone.utc)
|
||
release_date = dt.datetime.now(dt.timezone.utc).date().isoformat()
|
||
version = f"{release_date}-{short}"
|
||
release_dir = OUT_ROOT / version
|
||
if release_dir.exists():
|
||
shutil.rmtree(release_dir)
|
||
release_dir.mkdir(parents=True)
|
||
|
||
with tempfile.TemporaryDirectory(prefix="timmy-release-") as tmp:
|
||
tree = Path(tmp) / "source"
|
||
run(["git", "clone", "--quiet", "--no-local", str(ROOT), str(tree)], ROOT)
|
||
run(["git", "checkout", "--quiet", commit], tree)
|
||
run(["npm", "ci", "--ignore-scripts"], tree)
|
||
run(["npm", "test"], tree)
|
||
# The committed corpus hashes are an integrity receipt: verify them before anything is built.
|
||
run(["python3", "scripts/build_vision_corpus.py", "--verify"], tree)
|
||
server_env = dict(os.environ)
|
||
server_env.update({"HOST": "127.0.0.1", "PORT": "4173", "TIMMY_VISION_ENABLED": "false"})
|
||
server_log = (release_dir / "acceptance-server.log").open("w", encoding="utf-8")
|
||
server = subprocess.Popen(["node", "server.mjs"], cwd=tree, env=server_env,
|
||
stdout=server_log, stderr=subprocess.STDOUT, text=True)
|
||
try:
|
||
for _ in range(50):
|
||
if server.poll() is not None:
|
||
raise SystemExit("Acceptance server exited before readiness")
|
||
try:
|
||
urllib.request.urlopen("http://127.0.0.1:4173/", timeout=1).read(1)
|
||
break
|
||
except Exception:
|
||
time.sleep(0.1)
|
||
else:
|
||
raise SystemExit("Acceptance server did not become ready")
|
||
run(["npm", "run", "test:ui"], tree)
|
||
run(["npm", "run", "test:photo"], tree)
|
||
run(["npm", "run", "test:mobile-capture"], tree)
|
||
run(["npm", "run", "test:sleek"], tree)
|
||
run(["npm", "run", "test:manual-fallback"], tree)
|
||
run(["npm", "run", "test:provisional"], tree)
|
||
run(["npm", "run", "test:followup"], tree)
|
||
run(["npm", "run", "test:vision-refusal"], tree)
|
||
run(["npm", "run", "test:worker-readiness"], tree)
|
||
run(["npm", "run", "test:pattern-summary"], tree)
|
||
demo_raw = release_dir / f"timmy-talking-turd-{version}-demo.raw.webm"
|
||
caption_receipt = release_dir / f"timmy-talking-turd-{version}-demo-captions.json"
|
||
demo_env = dict(server_env)
|
||
demo_env["TIMMY_RELEASE_VERSION"] = version
|
||
demo_env["TIMMY_RELEASE_DEMO_DELTA"] = release_delta
|
||
demo_env["TIMMY_DEMO_CAPTIONS_OUT"] = str(caption_receipt)
|
||
run(["node", "scripts/record_release_demo.mjs", str(demo_raw)], tree, env=demo_env)
|
||
if not caption_receipt.exists():
|
||
raise SystemExit("Release demo produced no on-camera caption receipt")
|
||
recorded = json.loads(caption_receipt.read_text(encoding="utf-8"))
|
||
onscreen = [str(line) for line in (recorded.get("captions") or [])]
|
||
if recorded.get("releaseDelta") != release_delta or not any(release_delta in line for line in onscreen):
|
||
raise SystemExit("Release demo did not state the declared release delta on camera")
|
||
for required in DEMO_REQUIRED_CAPTIONS:
|
||
if not any(required in line for line in onscreen):
|
||
raise SystemExit(f"Release demo is missing a required on-camera caption: {required}")
|
||
finally:
|
||
server.terminate()
|
||
try:
|
||
server.wait(timeout=5)
|
||
except subprocess.TimeoutExpired:
|
||
server.kill()
|
||
server.wait(timeout=5)
|
||
server_log.close()
|
||
demo = release_dir / f"timmy-talking-turd-{version}-demo.mp4"
|
||
run(["ffmpeg", "-y", "-v", "error", "-i", str(demo_raw), "-vf", "scale=720:1280:flags=lanczos", "-an", "-c:v", "libx264", "-preset", "fast", "-crf", "20", "-pix_fmt", "yuv420p", "-movflags", "+faststart", str(demo)], tree)
|
||
demo_raw.unlink()
|
||
run(["ffmpeg", "-v", "error", "-i", str(demo), "-f", "null", "-"], tree)
|
||
probe = json.loads(run(["ffprobe", "-v", "error", "-print_format", "json", "-show_streams", "-show_format", str(demo)], tree, capture=True))
|
||
video_streams = [stream for stream in probe.get("streams", []) if stream.get("codec_type") == "video"]
|
||
if len(video_streams) != 1 or video_streams[0].get("codec_name") != "h264" or video_streams[0].get("pix_fmt") != "yuv420p" or video_streams[0].get("width") != 720 or video_streams[0].get("height") != 1280:
|
||
raise SystemExit("Release demo media probe failed")
|
||
contact_sheet = release_dir / f"timmy-talking-turd-{version}-demo-contact-sheet.jpg"
|
||
# Span the whole recording: a fixed 1/2 fps sheet only covered the first 24s of a longer demo.
|
||
demo_duration = float(run(["ffprobe", "-v", "error", "-show_entries", "format=duration", "-of", "csv=p=0", str(demo)], tree, capture=True))
|
||
if demo_duration <= 0:
|
||
raise SystemExit("Release demo has no measurable duration")
|
||
run(["ffmpeg", "-y", "-v", "error", "-i", str(demo), "-vf", f"fps={12 / demo_duration:.6f},scale=180:-1,tile=4x3:padding=4:margin=4", "-frames:v", "1", str(contact_sheet)], tree)
|
||
if not contact_sheet.exists() or contact_sheet.stat().st_size == 0:
|
||
raise SystemExit("Release demo contact sheet was not produced")
|
||
run(["npm", "audit", "--audit-level=high"], tree)
|
||
for file in ("app.js", "server.mjs", "service-worker.js", "src/analysis.js", "src/domain.js", "src/draft.js", "src/suggestion.js", "src/followup.js", "src/vision-readiness.js", "src/hermes-agent-service.js", "src/vision-config.js", "src/vision-service.js", "src/vision-corpus.js", "src/summary.js", "scripts/record_worker_benchmark.mjs", "tests/staging.acceptance.mjs", "tests/vision-refusal.acceptance.mjs", "tests/worker-readiness.acceptance.mjs", "tests/pattern-summary.acceptance.mjs"):
|
||
run(["node", "--check", file], tree)
|
||
run(["bash", "-n", "scripts/bootstrap_selfhost_smolvlm.sh"], tree)
|
||
run(["bash", "-n", "scripts/run_selfhost_smolvlm.sh"], tree)
|
||
run(["bash", "-n", "scripts/worker_ready.sh"], tree)
|
||
run(["bash", "-n", "deploy/worker/entrypoint.sh"], tree)
|
||
run(["bash", "-n", "deploy/worker/build_image.sh"], tree)
|
||
run(["bash", "-n", "deploy/worker/run_worker_container.sh"], tree)
|
||
run(["python3", "-m", "py_compile", "scripts/ingest_training_photo.py", "scripts/build_release.py", "scripts/build_vision_corpus.py"], tree)
|
||
run(["git", "diff", "--check", commit], tree)
|
||
|
||
names = tracked_files(tree)
|
||
scan_secrets(tree, names)
|
||
if any(name.startswith(EXCLUDED_PREFIXES) or name.endswith(EXCLUDED_SUFFIXES) for name in names):
|
||
raise SystemExit("Release allowlist included a forbidden artifact")
|
||
|
||
package_root = Path(tmp) / f"timmy-talking-turd-{version}"
|
||
for name in names:
|
||
src = tree / name
|
||
dst = package_root / name
|
||
dst.parent.mkdir(parents=True, exist_ok=True)
|
||
shutil.copy2(src, dst)
|
||
|
||
notes = (
|
||
f"# Timmy review release {version}\n\n"
|
||
f"- Source commit: [{commit}]({PUBLIC_REPO}/commit/{commit})\n"
|
||
f"- Build date (UTC): {release_date}\n"
|
||
f"- Release delta: {release_delta}\n"
|
||
"- Sleek three-destination shell with one dominant photo action and quiet manual fallback\n"
|
||
"- Manual fallback: vision-offline logging stays one action away with an in-session draft and explicit start over\n"
|
||
"- Smart free-text Timmy chat backed by authenticated server-side Hermes session continuity\n"
|
||
"- Agent safety: exact-origin HttpOnly session, bounded text-only ledger context, no browser credentials or session IDs\n"
|
||
"- Vision profiles: hosted and self-hosted SmolVLM2 bootstrap\n"
|
||
"- AI suggestions stay provisional: suggested, confirmed, and corrected states are distinct and screen-reader described; correcting one clears the AI-confirmed state without losing user context\n"
|
||
"- Hard-stool follow-up: a Bristol 1-2 entry asks user-reported questions (difficulty passing, soreness, visible blood, truly black/tarry versus dark brown, hydration); mild reports get non-diagnostic self-care, and a confirmed red-flag answer lands on the same deterministic escalation path as manual logging\n"
|
||
"- Vision corpus: a committed CC0 synthetic corpus (stool, non-stool, blur, glare, empty bowl, malformed response) proves every reply is schema-valid or fails closed; a schema-valid reply with unreadable fields abstains instead of erroring, and unparsable or out-of-range replies return plain copy with nothing applied — including a reply that fills in one field and leaves the other blank, where an out-of-range value still fails closed instead of being reported as an unreadable photo (issue #73)\n"
|
||
"- Self-hosted worker container: a digest-pinned image that builds the pinned llama.cpp revision, mounts hash-verified weights read-only, runs unprivileged with no credential, and is published on loopback only (issue #15)\n"
|
||
"- Post-load readiness: the app offers AI only once the pinned model is actually loaded, so a reachable-but-unloaded worker falls back to manual logging in one tap instead of failing after the upload (issue #15)\n"
|
||
"- Target-GPU benchmark: scripts/record_worker_benchmark.mjs records cold start, warm latency, and VRAM on the target GPU and refuses to write a receipt it did not measure; no GPU measurement is bundled with this release\n"
|
||
"- Explainable pattern summaries (issue #34): the home insight card reports confirmed-log counts and form groupings per window, every line names the exact confirmed records behind it, following a citation opens those records, and a window below the minimum says it is too sparse instead of describing a trend; no line explains a cause, rules on food, or offers a health verdict\n"
|
||
"- Safety: suggestions are observable-field assistance, never diagnosis; user confirmation is required\n"
|
||
"- Known limitation: open-weight VLM acceptance is proven, Bristol accuracy is not clinically validated\n"
|
||
"- Package excludes model weights, medical-image corpora, raw research pages, generated screenshots, and video production assets\n"
|
||
)
|
||
(package_root / "RELEASE-NOTES.md").write_text(notes, encoding="utf-8")
|
||
|
||
archive = release_dir / f"timmy-talking-turd-{version}.tar.gz"
|
||
with archive.open("wb") as raw:
|
||
import gzip
|
||
with gzip.GzipFile(filename="", mode="wb", fileobj=raw, mtime=commit_epoch) as gz:
|
||
with tarfile.open(fileobj=gz, mode="w") as tar:
|
||
for path in sorted(package_root.rglob("*")):
|
||
arcname = path.relative_to(package_root.parent)
|
||
info = tar.gettarinfo(str(path), arcname=str(arcname))
|
||
info.uid = info.gid = 0
|
||
info.uname = info.gname = ""
|
||
info.mtime = commit_epoch
|
||
if path.is_file():
|
||
with path.open("rb") as handle:
|
||
tar.addfile(info, handle)
|
||
else:
|
||
tar.addfile(info)
|
||
|
||
digest = sha256(archive)
|
||
demo_digest = sha256(demo)
|
||
manifest = {
|
||
"schema_version": 1,
|
||
"project": "Timmy the Talking Turd",
|
||
"version": version,
|
||
"commit": commit,
|
||
"release_delta": release_delta,
|
||
"source_date_utc": source_date.isoformat(),
|
||
"built_at_utc": dt.datetime.now(dt.timezone.utc).isoformat(),
|
||
"artifact": archive.name,
|
||
"bytes": archive.stat().st_size,
|
||
"sha256": digest,
|
||
"feature_demo": {
|
||
"artifact": demo.name,
|
||
"bytes": demo.stat().st_size,
|
||
"sha256": demo_digest,
|
||
"width": 720,
|
||
"height": 1280,
|
||
"codec": "h264",
|
||
"pixel_format": "yuv420p",
|
||
"recorded_from_working_app": True,
|
||
"fixture_data": "synthetic-Type-4, deterministic vision suggestion reviewed, confirmed, and corrected to Type 2, user-reported hard-stool follow-up with non-diagnostic self-care and a confirmed black/tarry red flag, the CC0 synthetic vision corpus replaying a non-stool refusal, an unreadable-fields abstention, an out-of-range fail-closed reply, and a blank-plus-out-of-range fail-closed reply, offline vision status, fictional multi-day sample logs driving the explainable pattern summary and its citation sheet, a sparse fictional window showing the insufficient-data copy, and deterministic Hermes chat response",
|
||
},
|
||
"gates": {
|
||
"unit_security": "passed",
|
||
"mobile_green_path": "passed",
|
||
"photo_first_acceptance": "passed",
|
||
"sleek_hermes_chat_acceptance": "passed",
|
||
"manual_fallback_draft_recovery": "passed",
|
||
"provisional_suggestion_state": "passed",
|
||
"hard_stool_followup": "passed",
|
||
"vision_corpus_refusal": "passed",
|
||
"worker_container_receipts": "passed",
|
||
"worker_post_load_readiness": "passed",
|
||
"longitudinal_pattern_summary": "passed",
|
||
"dependency_audit_high": "passed",
|
||
"syntax": "passed",
|
||
"secret_scan": "passed",
|
||
"forbidden_artifacts": "passed",
|
||
"feature_demo_full_decode": "passed",
|
||
"feature_demo_media_probe": "passed",
|
||
"release_delta_visible_on_camera": "passed",
|
||
},
|
||
}
|
||
manifest_path = release_dir / "manifest.json"
|
||
manifest_path.write_text(json.dumps(manifest, indent=2) + "\n", encoding="utf-8")
|
||
(release_dir / "SHA256SUMS").write_text(f"{digest} {archive.name}\n{demo_digest} {demo.name}\n", encoding="utf-8")
|
||
print(json.dumps({"release_dir": str(release_dir), "archive": str(archive), "feature_demo": str(demo), "manifest": str(manifest_path), "sha256": digest, "feature_demo_sha256": demo_digest}, indent=2))
|
||
return 0
|
||
|
||
|
||
if __name__ == "__main__":
|
||
sys.exit(main())
|