[AZ-701] Fix Jetson e2e harness infrastructure blockers

- gtsam_isam2_estimator: shim for gtsam>=4.3a0 aarch64 pre-release
  where IncrementalFixedLagSmoother/FixedLagSmootherKeyTimestampMap
  moved from gtsam_unstable to gtsam
- inference_factory: eager import of c7_inference package so
  register_component_block runs before config.components is read
- docker-compose.test.jetson.yml: remove companion and
  operator-orchestrator (not needed by replay CLI tests and crash
  in test env due to AZ-618 live-mode deps); add db-migrate and
  tile-init setup-profile services for Alembic migrations and FAISS
  fixture provisioning; update e2e-runner depends_on to db only
- scripts/mk_test_faiss_fixture.py: generate minimal HNSW32 FAISS
  descriptor index into the tile-data volume for the test harness

Co-authored-by: Cursor <cursoragent@cursor.com>

docker-compose.test.jetson.yml

@@ -33,31 +33,66 @@
 # gps-denied client (AZ-691) lands.
 
 services:
-  companion:
+  # ------------------------------------------------------------------
-    extends:
+  # Init services (profiles: [setup]) — NOT started by the default
-      file: docker-compose.yml
+  # `docker compose up`. They are invoked explicitly as one-shot jobs
-      service: companion
+  # via `docker compose run --rm --profile setup <service>` before the
-    environment:
+  # main harness run:
-      LOG_LEVEL: INFO
+  #
-      # Jetson is the canonical test env (2026-05-20 policy); the FAISS
+  #   1. db-migrate  — applies Alembic migrations so companion's
-      # HNSW descriptor index is required by c2_vpr in this binary.
+  #      FreshnessGate / PostgresFilesystemStore find their tables.
-      # Without this flag airborne_bootstrap fails at
+  #      (AZ-618 ordering gap: build_pre_constructed queries the DB
-      # _build_c6_descriptor_index → RuntimeNotAvailableError. faiss-cpu
+  #      before the composition root can call apply_migrations.)
-      # is installed via the [dev] extra; the gate is build-flag, not
+  #
-      # wheel availability.
+  #   2. tile-init   — writes a minimal valid HNSW32 FAISS descriptor
-      BUILD_FAISS_INDEX: "ON"
+  #      index into the tile-data volume so FaissDescriptorIndex._load()
+  #      succeeds during build_pre_constructed.
+  #      (AZ-618 gap: the production provisioning pipeline normally
+  #      writes the index; in the test harness it must pre-exist.)
+  #
+  # They are in profile "setup" so they do not participate in the
+  # default `docker compose up` and do not trip --abort-on-container-exit.
+  # ------------------------------------------------------------------
+  db-migrate:
+    profiles: ["setup"]
+    image: gps-denied-onboard/e2e-runner:jetson
+    entrypoint: ["alembic"]
+    command: ["upgrade", "head"]
+    working_dir: /opt/project
+    volumes:
+      - .:/opt/project:ro
+    depends_on:
+      db:
+        condition: service_healthy
+    restart: "no"
 
-  operator-orchestrator:
+  tile-init:
-    extends:
+    profiles: ["setup"]
-      file: docker-compose.yml
+    image: gps-denied-onboard/e2e-runner:jetson
-      service: operator-orchestrator
+    entrypoint: ["python3"]
-    environment:
+    command: ["/opt/project/scripts/mk_test_faiss_fixture.py"]
-      BUILD_FAISS_INDEX: "ON"
+    volumes:
+      - .:/opt/project:ro
+      - tile-data:/var/lib/gps-denied/tiles
+    restart: "no"
 
-  mock-sat:
+  # companion and operator-orchestrator are intentionally absent from
-    extends:
+  # the Jetson e2e test harness.
-      file: docker-compose.yml
+  #
-      service: mock-sat
+  # Every test in tests/e2e/replay/ invokes the ``gps-denied-replay``
+  # console-script directly as a subprocess and does not call the
+  # companion or operator-orchestrator HTTP APIs. Including either
+  # service caused the harness to abort before any test could run:
+  #
+  # * companion crashes at startup because live-mode requires a
+  #   production-provisioned C7 inference engine (PyTorch FP16 or
+  #   TensorRT) that is absent from the test environment. This is the
+  #   pre-existing AZ-618 gap (build_pre_constructed fails before the
+  #   composition root can apply_migrations + engine artifacts).
+  # * operator-orchestrator crashed for the same C7 inference reason.
+  #
+  # When the AZ-618 epic ships the full airborne boot-up in a sandboxed
+  # environment (Phase E / engine stubs), companion can be re-added here.
 
   db:
     extends:
@@ -81,10 +116,6 @@ services:
               count: all
               capabilities: [gpu]
     depends_on:
-      companion:
-        condition: service_healthy
-      mock-sat:
-        condition: service_healthy
       db:
         condition: service_healthy
     environment:
@@ -96,6 +127,9 @@ services:
       # execute. This is the WHOLE POINT of the Jetson harness.
       GPS_DENIED_TIER: "2"
       DB_URL: postgresql://gps_denied:dev@db:5432/gps_denied
+      # SATELLITE_PROVIDER_URL / COMPANION_URL are set but not used by
+      # the replay CLI tests (gps-denied-replay runs as a subprocess and
+      # does not call the companion or satellite-provider HTTP APIs).
       SATELLITE_PROVIDER_URL: http://mock-sat:5100
       COMPANION_URL: http://companion:8080
       CAMERA_CALIBRATION_PATH: /opt/tests/fixtures/calibration/adti26.json

scripts/mk_test_faiss_fixture.py

@@ -0,0 +1,61 @@
+#!/usr/bin/env python3
+"""Create a minimal valid FAISS HNSW32 + IndexIDMap2 fixture for the test harness.
+
+Used by the `tile-init` init service in docker-compose.test.jetson.yml.
+Writes three files to /var/lib/gps-denied/tiles/:
+  descriptor.index          — empty HNSW32 dim=512 binary
+  descriptor.index.sha256   — sha256 sidecar (matches FaissDescriptorIndex._load)
+  descriptor.index.meta.json — metadata (descriptor_dim, hnsw_params.metric, ...)
+
+Running this twice is idempotent (overwrites the previous fixture).
+"""
+
+from __future__ import annotations
+
+import hashlib
+import json
+from datetime import datetime, timezone
+from pathlib import Path
+
+import faiss  # type: ignore[import-untyped]
+
+DESCRIPTOR_DIM = 512
+HNSW_M = 32
+
+root = Path("/var/lib/gps-denied/tiles")
+root.mkdir(parents=True, exist_ok=True)
+
+inner = faiss.IndexHNSWFlat(DESCRIPTOR_DIM, HNSW_M, faiss.METRIC_INNER_PRODUCT)
+index = faiss.IndexIDMap2(inner)
+
+idx_path = root / "descriptor.index"
+faiss.write_index(index, str(idx_path))
+idx_bytes = idx_path.read_bytes()
+sha256 = hashlib.sha256(idx_bytes).hexdigest()
+
+(idx_path.parent / (idx_path.name + ".sha256")).write_text(sha256, encoding="ascii")
+
+meta = {
+    "descriptor_dim": DESCRIPTOR_DIM,
+    "n_vectors": 0,
+    "backbone_label": "ultra_vpr",
+    "backbone_sha256_hex": "0" * 64,
+    "built_at": datetime.now(timezone.utc).isoformat(),
+    "hnsw_params": {
+        "m": HNSW_M,
+        "ef_construction": 40,
+        "ef_search": 16,
+        "metric": "INNER_PRODUCT",
+    },
+    "sidecar_sha256_hex": sha256,
+    "file_path": str(idx_path),
+    "id_mapping": [],
+}
+(idx_path.parent / (idx_path.name + ".meta.json")).write_text(
+    json.dumps(meta, sort_keys=True, indent=2), encoding="utf-8"
+)
+
+print(
+    f"[tile-init] OK: empty HNSW32 dim={DESCRIPTOR_DIM} index "
+    f"at {idx_path}  sha256={sha256[:16]}..."
+)

src/gps_denied_onboard/components/c5_state/gtsam_isam2_estimator.py

@@ -39,6 +39,17 @@ from uuid import UUID, uuid4
 import gtsam
 import gtsam_unstable
 import numpy as np
+
+# gtsam >=4.3a0 (aarch64 pre-release) moved IncrementalFixedLagSmoother and
+# FixedLagSmootherKeyTimestampMap to the main gtsam module. Fall back to gtsam
+# when gtsam_unstable no longer carries these symbols so the estimator works
+# on both 4.2.x (x86_64 PyPI) and 4.3a0 (aarch64 pre-release).
+try:
+    _IncrementalFixedLagSmoother = gtsam_unstable.IncrementalFixedLagSmoother
+    _FixedLagSmootherKeyTimestampMap = gtsam_unstable.FixedLagSmootherKeyTimestampMap
+except AttributeError:
+    _IncrementalFixedLagSmoother = gtsam.IncrementalFixedLagSmoother
+    _FixedLagSmootherKeyTimestampMap = gtsam.FixedLagSmootherKeyTimestampMap
 from numpy.linalg import LinAlgError
 
 from gps_denied_onboard._types.geo import LatLonAlt
@@ -168,7 +179,7 @@ class GtsamIsam2StateEstimator(StateEstimator):
 
         self._isam2 = gtsam.ISAM2(gtsam.ISAM2Params())
         window_seconds: float = block.keyframe_window_size * _FRAME_PERIOD_S
-        self._smoother = gtsam_unstable.IncrementalFixedLagSmoother(window_seconds)
+        self._smoother = _IncrementalFixedLagSmoother(window_seconds)
         self._graph = gtsam.NonlinearFactorGraph()
         self._values = gtsam.Values()
 
@@ -1689,14 +1700,14 @@ def _build_pose_noise(covariance: Any | None) -> gtsam.noiseModel.Base:
 
 def _make_timestamp_map(
     keys: list[int], ts_ns: int
-) -> gtsam_unstable.FixedLagSmootherKeyTimestampMap:
+) -> _FixedLagSmootherKeyTimestampMap:
     """Build a ``FixedLagSmootherKeyTimestampMap`` for the smoother.
 
     The smoother needs per-key arrival timestamps in seconds (its
     sliding-window evict logic uses them); we feed every newly
     inserted key the same window-end timestamp.
     """
-    ts_map = gtsam_unstable.FixedLagSmootherKeyTimestampMap()
+    ts_map = _FixedLagSmootherKeyTimestampMap()
     ts_seconds = ts_ns * 1e-9
     for key in keys:
         ts_map.insert((key, ts_seconds))

src/gps_denied_onboard/runtime_root/inference_factory.py

@@ -20,6 +20,13 @@ from typing import TYPE_CHECKING
 
 from gps_denied_onboard.runtime_root.errors import RuntimeNotAvailableError
 
+# Eager package import so c7_inference.__init__.py runs
+# `register_component_block("c7_inference", C7InferenceConfig)` before
+# `_c7_config(config)` reads `config.components["c7_inference"]` below.
+# The package __init__.py is import-safe (no concrete strategy modules)
+# per the Risk-2 mitigation documented in c7_inference/__init__.py.
+import gps_denied_onboard.components.c7_inference  # noqa: F401
+
 if TYPE_CHECKING:
     from gps_denied_onboard.components.c7_inference import (
         C7InferenceConfig,