mirror of
https://github.com/azaion/gps-denied-onboard.git
synced 2026-06-22 17:41:13 +00:00
1d18e25cf4
Extend the AZ-701 replay_api POST /replay endpoint so AZ-897 (now in ../ui repo) can drive the AZ-894 CSV-replay path. The endpoint keeps full back-compat for tlog clients and adds: - (video, tlog) OR (video, csv) multipart with strict XOR enforced at the API boundary (AC-2 / AC-3 → 400 multipart_missing_field) - validate_csv_kind: rejects malformed CSV schema at boundary by scanning the header line for AZ-896 required tokens; messages point at csv_replay_format.md (AC-4) - ReplayInputs DTO: tlog_path / csv_path are now Path | None with XOR re-enforced in __post_init__ for internal callers - JobStorage reserves both input.tlog and input.csv paths; handler writes exactly one - SubprocessReplayRunner.run dispatches --imu vs --tlog argv (AC-1) - _maybe_render_report dispatches load_csv_ground_truth vs load_tlog_ground_truth; CsvGpsFix and TlogGpsFix have field-compatible shapes for the GroundTruthRow adapter (AC-6) - GET /static/example-csv serves the AZ-896 reference CSV; honours REPLAY_API_EXAMPLE_CSV_PATH env, falls back to source-checkout layout, returns 503 with example_csv_unavailable when neither resolves to a readable file. No auth required (AC-5) Tests: 27/27 unit tests green: - 18 pre-existing tlog-path tests unchanged (AC-7) - 9 new tests covering ACs 1-6 + validate_csv_kind isolation Deferred (NOT silently fixed; reported to user as end-of-turn notes for scope discipline): - gps-denied-render-map only consumes binary tlog truth today, so CSV-path jobs return map_html_url=None. Extending render-map to dispatch on truth-file extension is AZ-700 follow-up territory. - ReportContext.tlog_path field is now overloaded as the "ground-truth source path"; the rendered report still labels the line "Tlog: <csv_path>" which is cosmetically misleading for CSV runs. Field rename + label fix is AZ-699 follow-up. Bookkeeping: AZ-959 spec moved todo/ → done/, dep-table preamble fifth bump documents what landed + what's deferred, state.md records batch 5 complete and what comes next. Co-authored-by: Cursor <cursoragent@cursor.com>
98 lines
2.9 KiB
Python
98 lines
2.9 KiB
Python
"""AZ-701 — per-job temp-file lifecycle.
|
|
|
|
One ``StorageRoot`` rooted at ``REPLAY_API_STORAGE_ROOT``.
|
|
Each job allocates a subdirectory ``<root>/<job_id>/`` containing
|
|
the uploaded ``tlog`` + ``video`` + ``calibration`` plus the
|
|
estimator's outputs (``emissions.jsonl``, the AZ-699 report, the
|
|
AZ-700 map).
|
|
|
|
The directory is deleted on job completion (``release_job``) and on
|
|
service shutdown (``cleanup_all``). The service deliberately does
|
|
NOT keep finished-job artefacts forever — invariant 2 in the
|
|
contract.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import logging
|
|
import shutil
|
|
from dataclasses import dataclass
|
|
from pathlib import Path
|
|
|
|
__all__ = ["JobStorage", "StorageRoot"]
|
|
|
|
|
|
_LOGGER = logging.getLogger("gps_denied_onboard.replay_api.storage")
|
|
|
|
|
|
@dataclass(frozen=True, slots=True)
|
|
class JobStorage:
|
|
"""The per-job paths the handler hands to the runner.
|
|
|
|
Both ``tlog_path`` and ``csv_path`` are reserved on disk; the
|
|
handler writes to exactly one and leaves the other unused. The
|
|
``ReplayInputs`` DTO carries ``None`` for the branch that wasn't
|
|
written so downstream consumers know which clock source applies.
|
|
"""
|
|
|
|
root: Path
|
|
tlog_path: Path
|
|
csv_path: Path
|
|
video_path: Path
|
|
calibration_path: Path
|
|
output_dir: Path
|
|
|
|
|
|
class StorageRoot:
|
|
"""Parent of per-job storage directories.
|
|
|
|
The class is intentionally thin — the registry calls
|
|
``allocate_job`` at submit-time and ``release_job`` at terminal
|
|
transitions; nothing else owns mutation rights.
|
|
"""
|
|
|
|
def __init__(self, root: Path) -> None:
|
|
self._root = root
|
|
self._root.mkdir(parents=True, exist_ok=True)
|
|
|
|
@property
|
|
def root(self) -> Path:
|
|
return self._root
|
|
|
|
def allocate_job(self, job_id: str) -> JobStorage:
|
|
job_root = self._root / job_id
|
|
job_root.mkdir(parents=True, exist_ok=False)
|
|
output_dir = job_root / "output"
|
|
output_dir.mkdir(parents=True, exist_ok=True)
|
|
return JobStorage(
|
|
root=job_root,
|
|
tlog_path=job_root / "input.tlog",
|
|
csv_path=job_root / "input.csv",
|
|
video_path=job_root / "input.mp4",
|
|
calibration_path=job_root / "calibration.json",
|
|
output_dir=output_dir,
|
|
)
|
|
|
|
def release_job(self, job_id: str) -> None:
|
|
target = self._root / job_id
|
|
if not target.exists():
|
|
return
|
|
try:
|
|
shutil.rmtree(target)
|
|
except OSError as exc:
|
|
_LOGGER.warning(
|
|
"failed to delete per-job storage %s: %s", target, exc
|
|
)
|
|
|
|
def cleanup_all(self) -> None:
|
|
for child in self._root.iterdir():
|
|
if child.is_dir():
|
|
try:
|
|
shutil.rmtree(child)
|
|
except OSError as exc:
|
|
_LOGGER.warning(
|
|
"failed to delete per-job storage %s: %s",
|
|
child,
|
|
exc,
|
|
)
|