azaion/gps-denied-onboard
1
0
Fork 0
mirror of https://github.com/azaion/gps-denied-onboard.git synced 2026-06-21 22:01:13 +00:00
Code Issues Packages Projects Releases Wiki Activity
468 Commits 7 Branches 0 Tags
89606ccfdcbc34fc6bc2212c8d6c8f8d4b46f6a6
Commit Graph

8 Commits

Author SHA1 Message Date
Oleksandr Bezdieniezhnykh 235eb4549e [AZ-527] Consolidate _assert_engine_output_dim into c2-internal helper 
Closes cumulative review batches 49-51 Finding F1 (Medium /
Maintainability) -- the 7-way duplication of _assert_engine_output_dim
across c2_vpr secondary VPR strategy modules.

Add c2-internal helper assert_engine_output_dim(inference_runtime,
handle, preprocessor, descriptor_dim, *, output_key='embedding',
input_key='input') in src/gps_denied_onboard/components/c2_vpr/
_engine_dim_assertion.py. The helper runs a zero-init dry-run
inference at preprocessor.input_shape() and asserts the engine output
dict carries (1, descriptor_dim) under output_key. Raises
gps_denied_onboard.config.schema.ConfigError on mismatch (preserving
the prior error envelope and message wording byte-identically).

Migrate 7 strategy modules (ultra_vpr, net_vlad, mega_loc, mix_vpr,
sela_vpr, eigen_places, salad) to import the helper and delete the
local _assert_engine_output_dim definitions + their inline
'AZ-527 (planned)' comments. NetVLAD is the only call site that
overrides output_key='vlad_descriptor'; the other 6 explicitly pass
output_key=_OUTPUT_KEY + input_key=_ENGINE_INPUT_KEY (matching helper
defaults but documenting strategy contract at the call site).

Add tests/unit/c2_vpr/test_az527_engine_dim_assertion.py (14 tests,
AAA pattern, Protocol-conforming fakes) covering AC-1..AC-4: helper
signature; wrong shape raises ConfigError naming both dims; missing
output key raises ConfigError naming the missing key; AST-walk
regression guard for stray definitions outside the helper module
(modeled on AZ-526's test_ac4_az526_no_module_level_iso_ts_from_clock_outside_helper);
import-grep regression guard verifying all 7 strategy modules import
the helper.

AC-5 (existing AZ-337/338/339/340 AC-6 sub-tests pass unmodified) is
exercised transitively: c2_vpr/ full directory 230/230 PASS, no test
file modified outside the new test_az527_*. AC-6 (AZ-270 + AZ-507
layer lints) verified by tests/unit/test_az270_compose_root.py
8/8 PASS.

Code-review verdict: PASS (zero findings). Ruff clean.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-05-14 00:50:17 +03:00
Oleksandr Bezdieniezhnykh 87909cce9f [AZ-340] C2 SelaVPR + EigenPlaces + SALAD secondary VPR backbones 
Three new VprStrategy implementations for IT-12 comparative-study
(research binary only, gated OFF for airborne / operator-tooling per
ADR-002). All run via the C7 TensorRT runtime (or ONNX-RT fallback)
with their own concrete BackbonePreprocessor, single-stage L2
normalisation, and FaissBridge-delegated retrieval — same pattern as
AZ-339 (MegaLoc + MixVPR), parametrised in tests for compactness.

  * SelaVprStrategy   — D=512,  input 224x224
  * EigenPlacesStrategy — D=2048, input 480x480
  * SaladStrategy     — D=8448, input 322x322 (DINOv2-Large backbone;
                        heaviest in the C2 family — NFR-perf budget
                        relaxed to 120 ms p95 / 1200 MB GPU per task
                        spec)

The composition-root factory tables and KNOWN_STRATEGIES set were
already pre-wired at AZ-336 land time; module-layout.md already names
all three Internal entries and BUILD_VPR_* rows. No CMake change
required (env-flag gating).

54 unit tests (3 strategies * 18 cases) cover AC-1..AC-11 plus extras
(single-stage L2, NCHW FP16, constructor validation, FDR emission).
All pass; sibling c2_vpr suite + composition-root regression + AZ-526
iso-ts regression all green.

Code review verdict: PASS_WITH_WARNINGS. Two Low findings logged in
batch_51_review.md: F1 escalates `_assert_engine_output_dim`
duplication from 4-way to 7-way (already tracked by AZ-527 hygiene
PBI; will surface in cumulative review batches 49-51); F2 mirrors the
AZ-337 / 338 / 339 AC-10 spec-drift precedent (literal
ConfigurationError vs implemented ConfigError / StrategyNotAvailable).

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-05-14 00:32:38 +03:00
Oleksandr Bezdieniezhnykh 0d65ff4705 [AZ-339] C2 MegaLoc + MixVPR secondary VPR backbones 
Adds two research-only VprStrategy implementations for the IT-12
comparative-study matrix. MegaLocStrategy (D=2048, 322x322) and
MixVprStrategy (D=4096, 320x320), both via C7 TensorRT FP16 with
their own concrete BackbonePreprocessor. Single-stage global L2
normalisation; retrieval delegated to FaissBridge; FDR records +
structured logs identical to UltraVPR. BUILD_VPR_MEGALOC and
BUILD_VPR_MIXVPR ON for research/replay-cli only, OFF for airborne
and operator-tooling (fail-fast at composition root via existing
AZ-336 factory). Uses helpers.iso_ts_from_clock from day 1 — no
new timestamp helper duplicates introduced.

36 parametrised AC tests + 25 protocol-conformance + 18 helper
regression tests pass; 1690 / 1690 unit tests pass (excluding 1
pre-existing flaky cold-start subprocess test in c12). Verdict:
PASS_WITH_WARNINGS — one Medium follow-on (AZ-527 to consolidate
4-way _assert_engine_output_dim) + one Low AC wording drift.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-05-13 23:52:54 +03:00
Oleksandr Bezdieniezhnykh 3c4fd272f1 [AZ-337] C2 UltraVPR primary backbone VprStrategy 
UltraVPR is the Documentary Lead's PRIMARY backbone per
description.md § 1 and is wired by default
(config.c2_vpr.strategy = "ultra_vpr"). Runs on the C7 TensorRT
runtime (AZ-298) or ONNX-Runtime fallback (AZ-299); explicitly NOT
on the PyTorch FP16 runtime so a TRT engine compile bug can fall
back to NetVLAD without simultaneously breaking both strategies.

Production changes:
- c2_vpr/ultra_vpr.py - UltraVprStrategy + module-level create()
  factory. embed_query pipeline: preprocess -> runtime.infer ->
  single-stage L2 -> VprQuery. retrieve_topk delegates one-line to
  FaissBridge. Engine load + output-shape assertion happen at
  create() time (AC-6) so misconfiguration surfaces at startup,
  not 17 minutes into a flight. UltraVPR has D=512 fixed (NOT a
  config knob; AC-5 / AC-6 / AC-7 all assume 512). Single-stage L2
  (no intra-cluster step like NetVLAD; spy-test enforces this so a
  future refactor cannot silently regress recall).
- c2_vpr/_preprocessor_ultra_vpr.py - centre-crop using the camera
  calibration's principal point (cx, cy from intrinsics_3x3),
  falling back to geometric centre + WARN log when calibration is
  absent (AC-9). Resize -> (384, 384) -> ImageNet mean/std ->
  FP16 NCHW.
- No composition-root changes: UltraVPR consumes a pre-compiled
  .trt engine (no PyTorch nn.Module), so the strategy module does
  NOT expose MODEL_NAME / architecture_factory. The composition-
  root _register_strategy_architecture helper no-ops cleanly for
  this case (verified by test_create_does_not_register_pytorch_architecture).

Tests:
- tests/unit/c2_vpr/test_ultra_vpr.py - 29 tests covering all 12
  ACs + preprocessor contract + constructor validation + FDR
  record emission + single-stage L2 enforcement.

Full unit suite: 1637 passed / 80 env-skipped (+29 new tests).
Per-batch code review (batch_47_review.md): PASS_WITH_WARNINGS
(3 Low-severity findings; no Critical / High / Medium):
- F1: _iso_ts_from_clock is now the 7th copy (AZ-508 will close).
- F2: AZ-337 spec uses outdated C7 API names; affects upcoming
  AZ-339 / AZ-340. Spec-hygiene PBI recommended.
- F3: principal-point fallback uses (0, 0) zero-detection for
  missing calibration; safe but tightens when intrinsics become
  Optional.

Architectural notes:
- AZ-507 layering clean. Imports only InferenceRuntimeCut,
  DescriptorIndexCut, c2_vpr internals, _types, helpers,
  clock, fdr_client. Architecture lint test passes.
- Pattern parity with NetVLAD (B46) where semantics permit;
  UltraVPR-specific paths (single-stage L2, 'embedding' output
  key, TRT runtime, no architecture registry, principal-point
  crop) are clearly localised.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-05-13 22:43:17 +03:00
Oleksandr Bezdieniezhnykh af0dbe863a [AZ-338] [AZ-283] C2 NetVLAD mandatory simple-baseline VprStrategy 
NetVLAD is the C2 comparative baseline per the engine rule (every
production-default backbone ships with a simple-baseline alongside).
Runs on the C7 PyTorch FP16 runtime (NOT TRT) so a TRT engine compile
bug cannot simultaneously break NetVLAD AND UltraVPR.

Production changes:
- c2_vpr/net_vlad.py — NetVladStrategy + module-level create() factory.
  Constructor wires InferenceRuntimeCut + DescriptorIndexCut +
  NetVladBackbonePreprocessor + DescriptorNormaliser + FaissBridge.
  embed_query pipeline: preprocess -> runtime.infer -> dual-stage
  normalisation (intra-cluster THEN global L2) -> VprQuery.
  retrieve_topk delegates one-line to FaissBridge.
- c2_vpr/_net_vlad_architecture.py — Arandjelovic et al. 2016 NetVLAD
  layer over torchvision VGG16 features + optional Linear PCA
  projection to descriptor_dim (default 4096; published Pittsburgh
  reference uses K*D=64*512=32768 raw + Linear(32768, 4096) PCA).
- c2_vpr/_preprocessor_net_vlad.py — OpenCV-based image preprocessor:
  decode -> centre-crop square -> resize (480, 480) -> ImageNet
  normalisation -> FP16 NCHW. Calibration is not consumed (NetVLAD
  is calibration-agnostic per published preprocessing chain).
- c2_vpr/inference_runtime_cut.py — NEW AZ-507 consumer-side cut
  mirroring C7 InferenceRuntime; lets c2_vpr stay AZ-507-clean.
- c2_vpr/config.py — added netvlad_descriptor_dim: int = 4096 knob.
- helpers/descriptor_normaliser.py — added intra_cluster_normalise
  (DescriptorNormaliser v1.0.0 -> v1.1.0; backward-compatible add).
- runtime_root/vpr_factory.py — added _register_strategy_architecture
  helper that binds (MODEL_NAME, architecture_factory(descriptor_dim))
  to C7's architecture registry before delegating to the strategy's
  create() factory. Keeps the c7 import at L4, preserves AZ-507.
- fdr_client/records.py — registered vpr.embed_query,
  vpr.backbone_error, vpr.preprocess_error record kinds.

Tests:
- tests/unit/c2_vpr/test_net_vlad.py — 31 tests covering all 11 ACs +
  preprocessor contract + architecture factory + constructor
  validation + FDR record emission.
- tests/unit/test_az283_descriptor_normaliser.py — +8 tests for the
  new intra_cluster_normalise.
- tests/unit/test_az272_fdr_record_schema.py — +3 fixture payloads.

Full unit suite: 1608 passed / 80 env-skipped (+43 new tests).
Per-batch code review (batch_46_review.md): PASS_WITH_WARNINGS
(4 Low-severity hygiene findings; no Critical/High/Medium).

Architectural notes:
- The spec implied c2_vpr.net_vlad.create() registers the architecture
  with C7. That violates AZ-507 (no cross-component imports). Resolved
  by exposing MODEL_NAME + architecture_factory(descriptor_dim) on the
  strategy module and having the composition root perform the C7 bind.
- C7 PyTorch runtime API names in the spec (forward, load_engine)
  were outdated; aligned implementation with the live v1.0.0 Protocol
  (infer, compile_engine + deserialize_engine). Spec hygiene flagged
  in review F2.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-05-13 22:30:29 +03:00
Oleksandr Bezdieniezhnykh 88f6ae6dce [AZ-341] C2 FAISS HNSW retrieve wiring (FaissBridge + AZ-507 cut) 
Shared retrieve_topk plumbing for every concrete C2 VprStrategy:
- FaissBridge centralises the c6 search_topk → VprResult pipeline,
  the defended-in-depth INV-4 check (exactly k, distance-ascending),
  the WARN-threshold check on distances[0], optional per-frame DEBUG
  log, and one `vpr.retrieve_topk` FDR record per call with latency
  measurement.
- DescriptorIndexCut Protocol — consumer-side structural cut of c6
  DescriptorIndex.search_topk (AZ-507); keeps c2_vpr c6-import-free.
- C2VprConfig gains warn_top1_threshold + debug_per_frame_distances
  knobs with validators.
- KNOWN_PAYLOAD_KEYS registers vpr.retrieve_topk for the FDR record
  schema with payload {frame_id, backbone_label, top10_distances,
  latency_us}; companion fixture added to the AZ-272 roundtrip suite.
- 22 unit tests cover AC-1..AC-11 + NFR-perf microbench (p95 ≤ 0.5 ms)
  + constructor and retrieve-argument validation.

Verdict: PASS_WITH_WARNINGS (2 Low findings — duplicated ISO-ts
helper across c2/c5/c11/c12, captured in AZ-508 hygiene PBI;
spec-listed but unused `normaliser` parameter dropped — INV-3 makes
the embedding L2-normalised at the strategy's `embed_query`).

Tests: 1565 passed / 80 skipped (was 1543; +22 new tests).
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-05-13 21:45:40 +03:00
Oleksandr Bezdieniezhnykh 3665acef66 [AZ-336] C2 VprStrategy: Protocol + DTOs + factory + composition 
Foundational scaffolding for every concrete C2 backbone (UltraVPR,
NetVLAD, MegaLoc, MixVPR, SelaVPR, EigenPlaces, SALAD — AZ-337..AZ-340)
and the C2.5 ReRanker consumer side. No backbone is implemented here.

* VprStrategy Protocol (embed_query / retrieve_topk / descriptor_dim)
  + BackbonePreprocessor C2-internal Protocol (NOT in Public API per
  description.md § 6).
* DTOs in L1 _types/vpr.py — VprQuery, VprCandidate, VprResult; all
  frozen + slots; tuple-not-list for VprResult.candidates so the
  immutability invariant truly holds.
* Error family: VprError + VprBackboneError + VprPreprocessError +
  IndexUnavailableError; same-named but namespace-distinct from
  c6_tile_cache.IndexUnavailableError (the c2 family is the closed
  envelope C5 / C2.5 consume; concrete strategies rewrap the C6 form).
* C2VprConfig (strategy enum + backbone_weights_path + faiss_index_path)
  with strict validation at load; registered into Config.components on
  c2_vpr import.
* build_vpr_strategy factory with 7-strategy resolution table, lazy
  import, BUILD_VPR_<variant> gating, ImportError→
  StrategyNotAvailableError mapping, and pre-flight descriptor_dim
  match against DescriptorIndex.descriptor_dim() — mismatch fires
  ConfigError at startup, NOT at first frame.

Contract change vs the v1.0.0 draft: factory takes descriptor_index:
DescriptorIndex (not tile_store: TileStore) because descriptor_dim()
lives on DescriptorIndex per C6's Public API. The contract markdown
is updated to match.

Architecture: VprCandidate.tile_id is a plain (zoom, lat, lon) tuple,
keeping _types/ (L1) free of any c6_tile_cache (L3) import per
module-layout.md. Consumers reconstruct TileId at the C6 boundary.

Excluded per task spec:
* Concrete backbones (AZ-337..AZ-340).
* FAISS HNSW retrieve wiring (AZ-341).
* DescriptorNormaliser helper (AZ-283, already shipped).
* AC-9 single-thread binding — deferred per task spec Risk 4 until the
  generic compose_root thread-binding registry is in place (today
  each factory owns its own, e.g. fc_factory).

Tests: 45 ACs + NFRs in tests/unit/c2_vpr/test_protocol_conformance.py
covering AC-1..AC-8, the error family, the config validation, the
factory NFR (p99 ≤ 50 ms). The legacy smoke test is removed. Full
sweep 973 passed, 2 skipped (CI-only cmake / actionlint).

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-05-12 05:25:35 +03:00
Oleksandr Bezdieniezhnykh b12db61444 [AZ-263] Bootstrap: repo skeleton + Docker + CI + Alembic + Tier-1 tests 
Implements the AZ-263 / E-BOOT initial structure task:

- Python src/-layout package `gps_denied_onboard/` with per-component
  interface stubs (14 components), type-only DTOs under `_types/`,
  shared helpers under `helpers/` (R14 LightGlue ownership), structured
  JSON logging, runtime composition root with env-var fail-fast gate,
  healthcheck module shared by Docker and CI smoke.
- CMake top-level + `cmake/{build_options,dependencies,strategies}.cmake`
  with the BUILD_* per-binary flags (ADR-002) and pinned external git
  refs for OKVIS2 / VINS-Mono / GTSAM / FAISS / OpenCV >=4.12.0.
- Three Dockerfiles (companion-tier1, operator-tooling,
  mock-suite-sat-service) + two compose files (dev + Tier-1 test).
- Four GitHub Actions workflows: ci.yml (lint/unit/integration/dual
  binary build/SBOM diff/security), ci-tier2.yml (self-hosted Jetson
  AC-bound NFTs), release.yml, cve-rescan.yml.
- Two CI gate scripts: `ci/sbom_diff.py` (deployment SBOM subset +
  R02 exclusion), `ci/opencv_pin_gate.py` (>=4.12.0 enforcement,
  D-CROSS-CVE-1).
- Alembic-driven Postgres 16 initial migration `0001_initial.py`
  mirroring satellite-provider tiles + flights + sector_classifications
  + manifests + engine_cache_entries (data_model.md s 2).
- Tier-1 test scaffolding: 95 passing unit tests covering every AC,
  per-component smoke tests, structured logging JSON output check,
  env-var gate check, healthcheck import check. Two CI-gated tests
  (cmake configure, actionlint) skip locally with explicit reasons.
- Batch report + code review report under `_docs/03_implementation/`.

Verdict: PASS_WITH_WARNINGS (two Low findings, both informational).
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-05-11 01:00:28 +03:00