Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -501,7 +501,7 @@ Runtime Intelligence boundary:
- `collection_mode` starts as `single_result_export`; EdgeEnv owns telemetry history accumulation and comparability-first regression.
- Missing device telemetry remains explicit in `missing_fields` instead of being fabricated.
- `runtime_telemetry.coverage` records expected / observed / missing telemetry fields, with `comparability_owner: edgeenv` and `missing_telemetry_is_failure: false`.
- `runtime_telemetry.history_seed` uses `inferedge-runtime-telemetry-history-seed-v1`, keeps `registry_owner: edgeenv`, `decision_owner: lab`, `production_monitoring: false`, and exposes a `single_result_to_history` replay point that mirrors the Runtime telemetry timestamp, sequence id, latency values, operation flags, power mode, and telemetry source for EdgeEnv accumulation. It also carries a compact `run_config` snapshot so EdgeEnv can keep replay/comparability evidence with the seed without turning Runtime into a registry.
- `runtime_telemetry.history_seed` uses `inferedge-runtime-telemetry-history-seed-v1`, keeps `registry_owner: edgeenv`, `decision_owner: lab`, `production_monitoring: false`, and exposes a `single_result_to_history` replay point that mirrors the Runtime telemetry timestamp, sequence id, latency values, operation flags, power mode, and telemetry source for EdgeEnv accumulation. It also carries a compact `run_config` snapshot, including input/preprocess and Jetson clocks markers, so EdgeEnv can keep replay/comparability evidence with the seed without turning Runtime into a registry.
- EdgeEnv validates and preserves this seed as `runtime_telemetry_history_seed`; Lab may display the preserved marker in a Runtime Intelligence risk report, but Runtime does not own the registry or deployment decision.
- Runtime exports telemetry evidence only. AIGuard may turn it into deterministic anomaly evidence, and Lab remains the deployment decision owner.

Expand Down
4 changes: 4 additions & 0 deletions scripts/smoke_default.sh
Original file line number Diff line number Diff line change
Expand Up @@ -128,7 +128,9 @@ assert history_seed["run_config"]["warmup"] == data["run_config"]["warmup"], his
assert history_seed["run_config"]["runs"] == data["run_config"]["runs"], history_seed
assert history_seed["run_config"]["timeout_ms"] == data["run_config"]["timeout_ms"], history_seed
assert history_seed["run_config"]["input_mode"] == health["input_mode"], history_seed
assert history_seed["run_config"]["input_preprocess"] == health["input_preprocess"], history_seed
assert history_seed["run_config"]["power_mode"] == telemetry["power_mode"], history_seed
assert history_seed["run_config"]["jetson_clocks"] == data["run_config"]["jetson_clocks"], history_seed
assert history_seed["points"][0]["telemetry_timestamp"] == telemetry["telemetry_timestamp"], history_seed
assert history_seed["points"][0]["execution_sequence_id"] == telemetry["execution_sequence_id"], history_seed
assert history_seed["points"][0]["mean_ms"] == telemetry["latency"]["mean_ms"], history_seed
Expand Down Expand Up @@ -218,7 +220,9 @@ assert history_seed["run_config"]["batch"] == data["run_config"]["batch"], histo
assert history_seed["run_config"]["runs"] == data["run_config"]["runs"], history_seed
assert history_seed["run_config"]["timeout_ms"] == data["run_config"]["timeout_ms"], history_seed
assert history_seed["run_config"]["input_mode"] == health["input_mode"], history_seed
assert history_seed["run_config"]["input_preprocess"] == health["input_preprocess"], history_seed
assert history_seed["run_config"]["power_mode"] == telemetry["power_mode"], history_seed
assert history_seed["run_config"]["jetson_clocks"] == data["run_config"]["jetson_clocks"], history_seed
assert history_seed["points"][0]["p99_ms"] == telemetry["latency"]["p99_ms"], history_seed
assert history_seed["points"][0]["deadline_missed"] == telemetry["operation"]["deadline_missed"], history_seed
assert "runtime_telemetry_recorded" in events, events
Expand Down
5 changes: 5 additions & 0 deletions tests/test_agent_runtime_result_contract.py
Original file line number Diff line number Diff line change
Expand Up @@ -242,7 +242,12 @@ def test_runtime_output_records_optional_agent_block_when_manifest_is_provided(s
self.assertEqual(history_seed["run_config"]["runs"], result["run_config"]["runs"])
self.assertEqual(history_seed["run_config"]["timeout_ms"], result["run_config"]["timeout_ms"])
self.assertEqual(history_seed["run_config"]["input_mode"], result["runtime_health_snapshot"]["input_mode"])
self.assertEqual(
history_seed["run_config"]["input_preprocess"],
result["runtime_health_snapshot"]["input_preprocess"],
)
self.assertEqual(history_seed["run_config"]["power_mode"], telemetry["power_mode"])
self.assertEqual(history_seed["run_config"]["jetson_clocks"], result["run_config"]["jetson_clocks"])
point = history_seed["points"][0]
self.assertEqual(point["execution_sequence_id"], telemetry["execution_sequence_id"])
self.assertEqual(point["telemetry_timestamp"], telemetry["telemetry_timestamp"])
Expand Down
Loading