mirror of
https://github.com/azaion/gps-denied-onboard.git
synced 2026-06-21 07:01:14 +00:00
a06b107fc3
Wraps HttpTileUploader (AZ-319) with two bounded retry budgets: - In-call (per-batch) — re-invokes inner on PARTIAL outcome up to `max_in_call_retries` times with capped exponential backoff (`min(base ** attempt_number, cap)`). On exhaustion: surfaces an operator hint via `next_retry_at_s = now + backoff_cap_s`. - Per-tile (cross-call) — atomically increments c6's `tiles.upload_attempts` counter for every rejection; once a tile hits `max_per_tile_attempts` it is forward-only transitioned to `voting_status = upload_giveup` (excluded from `pending_uploads`). Each transition emits FDR `kind="c11.upload.giveup"` plus an ERROR log. C6 contract changes (AZ-303 v1.3.0): - VotingStatus.UPLOAD_GIVEUP added (forward-only from PENDING/TRUSTED). - TileMetadataStore.increment_upload_attempts(tile_id) -> int added with NotImplementedError default for backwards-compat. - Migration 0003_c11_upload_attempts: additive column + widened ck_tiles_voting_status (preserves IS NULL clause). C11 wiring: - C11RetryConfig + disable_retry_decorator on C11Config. - build_tile_uploader wraps in decorator by default; bypass flag returns the bare HttpTileUploader. New `clock` keyword. Cross-component isolation honoured (AZ-507): the decorator declares `_RetryMetadataStoreLike` Protocol cut over c6's TileMetadataStore and references `UPLOAD_GIVEUP` via a local string constant — no c6 imports. Tests: 13 decorator + 1 conformance + 2 factory bypass + AC-6 enum update + alembic head bump + AZ-272 schema fixture. 238 passed across c11/c6/fdr suites; pre-existing perf microbenches unrelated. Code review: PASS_WITH_WARNINGS (5 Low/Informational findings, docs-level or downstream-CI-blocked). See _docs/03_implementation/reviews/batch_41_review.md. Co-authored-by: Cursor <cursoragent@cursor.com>
180 lines
7.4 KiB
Python
180 lines
7.4 KiB
Python
"""C11 TileManager config block (AZ-316, AZ-319, AZ-320).
|
|
|
|
Registered into ``config.components['c11_tile_manager']`` by the
|
|
package ``__init__.py``. Three composition-root factories read this
|
|
block:
|
|
|
|
* :func:`gps_denied_onboard.runtime_root.c11_factory.build_tile_uploader`
|
|
reads the ``upload_*`` fields, ``companion_id``, and the AZ-320
|
|
``retry`` block (``disable_retry_decorator`` + the per-tile / per-call
|
|
retry knobs) to drive AZ-319 + the optional AZ-320 decorator.
|
|
* :func:`gps_denied_onboard.runtime_root.c11_factory.build_tile_downloader`
|
|
reads the ``satellite_provider_url``, ``service_api_key``, and
|
|
``download_*`` fields to drive AZ-316.
|
|
|
|
All defaults are conservative no-op values so unit tests / replay
|
|
runs that do not exercise C11 keep working without YAML; the factory
|
|
raises :class:`ConfigError` when an empty production-required field
|
|
(``service_api_key``, ``companion_id``, etc.) is observed in operator
|
|
wiring.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from dataclasses import dataclass, field
|
|
|
|
from gps_denied_onboard.config.schema import ConfigError
|
|
|
|
__all__ = ["C11Config", "C11RetryConfig"]
|
|
|
|
|
|
_DEFAULT_BATCH_SIZE: int = 25
|
|
_DEFAULT_HTTP_TIMEOUT_S: float = 30.0
|
|
_DEFAULT_MAX_RETRY_AFTER_S: int = 600
|
|
_MAX_BATCH_SIZE: int = 200
|
|
_DEFAULT_DOWNLOAD_RESOLUTION_FLOOR: float = 0.5
|
|
_DEFAULT_DOWNLOAD_MAX_5XX_RETRIES: int = 4
|
|
_MIN_DOWNLOAD_RETRIES: int = 1
|
|
_MAX_DOWNLOAD_RETRIES: int = 16
|
|
_DEFAULT_MAX_IN_CALL_RETRIES: int = 3
|
|
_DEFAULT_MAX_PER_TILE_ATTEMPTS: int = 5
|
|
_DEFAULT_RETRY_BACKOFF_BASE_S: float = 2.0
|
|
_DEFAULT_RETRY_BACKOFF_CAP_S: float = 60.0
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class C11RetryConfig:
|
|
"""C11 ``IdempotentRetryTileUploader`` knobs (AZ-320).
|
|
|
|
* ``max_in_call_retries`` — bounded loop count for partial-success
|
|
re-invocations of the wrapped uploader within a single call.
|
|
* ``max_per_tile_attempts`` — terminal threshold per tile across
|
|
ALL calls; exceeding the threshold moves the tile to
|
|
:class:`VotingStatus.UPLOAD_GIVEUP` (a human-decision boundary —
|
|
automated promotion back to ``PENDING`` is forbidden).
|
|
* ``backoff_base_s`` — base of the exponential backoff used between
|
|
in-call retries (``base ** retries_used``).
|
|
* ``backoff_cap_s`` — upper bound on each individual backoff sleep;
|
|
also used as the operator hint for ``next_retry_at_s`` when the
|
|
in-call budget is exhausted.
|
|
"""
|
|
|
|
max_in_call_retries: int = _DEFAULT_MAX_IN_CALL_RETRIES
|
|
max_per_tile_attempts: int = _DEFAULT_MAX_PER_TILE_ATTEMPTS
|
|
backoff_base_s: float = _DEFAULT_RETRY_BACKOFF_BASE_S
|
|
backoff_cap_s: float = _DEFAULT_RETRY_BACKOFF_CAP_S
|
|
|
|
def __post_init__(self) -> None:
|
|
if self.max_in_call_retries < 0:
|
|
raise ConfigError(
|
|
"C11RetryConfig.max_in_call_retries must be >= 0; "
|
|
f"got {self.max_in_call_retries}"
|
|
)
|
|
if self.max_per_tile_attempts <= 0:
|
|
raise ConfigError(
|
|
"C11RetryConfig.max_per_tile_attempts must be > 0; "
|
|
f"got {self.max_per_tile_attempts}"
|
|
)
|
|
if self.backoff_base_s <= 0:
|
|
raise ConfigError(
|
|
"C11RetryConfig.backoff_base_s must be > 0; "
|
|
f"got {self.backoff_base_s}"
|
|
)
|
|
if self.backoff_cap_s <= 0:
|
|
raise ConfigError(
|
|
"C11RetryConfig.backoff_cap_s must be > 0; "
|
|
f"got {self.backoff_cap_s}"
|
|
)
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class C11Config:
|
|
"""Per-component config for C11 tile manager (upload + download paths).
|
|
|
|
Upload-side fields (AZ-319):
|
|
|
|
* ``satellite_provider_ingest_url`` — base URL for the upload
|
|
endpoint; ``HttpTileUploader`` appends
|
|
``/api/satellite/tiles/ingest``. Empty → upload factory raises
|
|
:class:`ConfigError`.
|
|
* ``upload_batch_size`` — tiles per multipart POST.
|
|
* ``upload_http_timeout_s`` — per-request timeout (seconds).
|
|
* ``upload_max_retry_after_s`` — cumulative 429 ``Retry-After``
|
|
cap before :class:`RateLimitedError`.
|
|
* ``companion_id`` — stable per-companion id for D-PROJ-2 voting.
|
|
|
|
Download-side fields (AZ-316):
|
|
|
|
* ``satellite_provider_url`` — base URL for the GET surface;
|
|
``HttpTileDownloader`` appends per-tile / list paths.
|
|
* ``service_api_key`` — bearer token for authenticated GETs;
|
|
logged ONLY redacted (``Bearer ***``). Empty → download factory
|
|
raises :class:`ConfigError`.
|
|
* ``download_http_timeout_s`` — per-request timeout (seconds).
|
|
* ``download_max_5xx_retries`` — exponential-backoff cap before
|
|
:class:`SatelliteProviderError`.
|
|
* ``download_max_retry_after_s`` — cumulative 429 ``Retry-After``
|
|
cap before :class:`RateLimitedError`.
|
|
* ``download_resolution_floor_m_per_px`` — RESTRICT-SAT-4 lower
|
|
bound for the C11 boundary check; defaults to 0.5 m/px.
|
|
"""
|
|
|
|
satellite_provider_ingest_url: str = ""
|
|
upload_batch_size: int = _DEFAULT_BATCH_SIZE
|
|
upload_http_timeout_s: float = _DEFAULT_HTTP_TIMEOUT_S
|
|
upload_max_retry_after_s: int = _DEFAULT_MAX_RETRY_AFTER_S
|
|
companion_id: str = ""
|
|
|
|
satellite_provider_url: str = ""
|
|
service_api_key: str = ""
|
|
download_http_timeout_s: float = _DEFAULT_HTTP_TIMEOUT_S
|
|
download_max_5xx_retries: int = _DEFAULT_DOWNLOAD_MAX_5XX_RETRIES
|
|
download_max_retry_after_s: int = _DEFAULT_MAX_RETRY_AFTER_S
|
|
download_resolution_floor_m_per_px: float = _DEFAULT_DOWNLOAD_RESOLUTION_FLOOR
|
|
|
|
disable_retry_decorator: bool = False
|
|
retry: C11RetryConfig = field(default_factory=C11RetryConfig)
|
|
|
|
def __post_init__(self) -> None:
|
|
if not 1 <= self.upload_batch_size <= _MAX_BATCH_SIZE:
|
|
raise ConfigError(
|
|
"C11Config.upload_batch_size must be in "
|
|
f"[1, {_MAX_BATCH_SIZE}]; got {self.upload_batch_size}"
|
|
)
|
|
if self.upload_http_timeout_s <= 0:
|
|
raise ConfigError(
|
|
"C11Config.upload_http_timeout_s must be > 0; "
|
|
f"got {self.upload_http_timeout_s}"
|
|
)
|
|
if self.upload_max_retry_after_s <= 0:
|
|
raise ConfigError(
|
|
"C11Config.upload_max_retry_after_s must be > 0; "
|
|
f"got {self.upload_max_retry_after_s}"
|
|
)
|
|
if self.download_http_timeout_s <= 0:
|
|
raise ConfigError(
|
|
"C11Config.download_http_timeout_s must be > 0; "
|
|
f"got {self.download_http_timeout_s}"
|
|
)
|
|
if not _MIN_DOWNLOAD_RETRIES <= self.download_max_5xx_retries <= _MAX_DOWNLOAD_RETRIES:
|
|
raise ConfigError(
|
|
"C11Config.download_max_5xx_retries must be in "
|
|
f"[{_MIN_DOWNLOAD_RETRIES}, {_MAX_DOWNLOAD_RETRIES}]; "
|
|
f"got {self.download_max_5xx_retries}"
|
|
)
|
|
if self.download_max_retry_after_s <= 0:
|
|
raise ConfigError(
|
|
"C11Config.download_max_retry_after_s must be > 0; "
|
|
f"got {self.download_max_retry_after_s}"
|
|
)
|
|
if self.download_resolution_floor_m_per_px <= 0:
|
|
raise ConfigError(
|
|
"C11Config.download_resolution_floor_m_per_px must be > 0; "
|
|
f"got {self.download_resolution_floor_m_per_px}"
|
|
)
|
|
if not isinstance(self.retry, C11RetryConfig):
|
|
raise ConfigError(
|
|
"C11Config.retry must be a C11RetryConfig; got "
|
|
f"{type(self.retry).__name__}"
|
|
)
|