{ "mode": "offline-synthetic-execution-identity", "baseline_commit": "c4486ed8cc3c82a00f421f3bac32653b814f2d40", "candidate": "working tree at invocation; published with its source commit", "baseline_source_sha256": { "src/apixly_jev_harness/__init__.py": "79a4ea23ea1469f218c5d6f4ee8567f0cf12f77dbd658f4afb57daa90c2a3039", "src/apixly_jev_harness/backend.py": "0ddfab6b270d8219a66614630e70aa10a74cb531f8075d07c255df145725ed5f", "src/apixly_jev_harness/callbacks.py": "2d27ad4540d910354c54de7566546b4c9d99b5a5fa87705a1905885349078497", "src/apixly_jev_harness/cli.py": "8d9434bf8a8b539163194a84e3f099761d08ef32201f99cbce46c139f3726d94", "src/apixly_jev_harness/context.py": "b9d76abb33f8a1ebe8731fe6d5fe6811445132a6046448fc0e2cc871507d50ea", "src/apixly_jev_harness/diagnostics.py": "9e8e98dc4b103c1a6687dbd31bd2dd01739309c7e4021b9ecb0f28b6976a0f71", "src/apixly_jev_harness/engine.py": "19d809ee7af67586b03a472af49908f6ec278231285d16db161a540b3f0247a6", "src/apixly_jev_harness/output.py": "94be8b482e4279e29aca128a35caf54744dbe8db8188f14905488f8ddde93a0b", "src/apixly_jev_harness/surfaces.py": "65ce73edfe9f6a3c16de373b3a1b85671c3d2cc661f3a50dd906a15721c7d8f1", "src/apixly_jev_harness/task.py": "0f5801e9fdb5626e1db65d269c715e8bcf692ebaa3a91f46b9945158b4bbb6db", "src/apixly_jev_harness/task_cli.py": "9cf30e5ed50680ac3b0212bdd8118d67f4272cc7690941a6e57e48fd2ccf850d", "src/apixly_jev_harness/verify.py": "97d2a178902291094f4e16db08732748d234b8c5ad8dd49a55607c8d195f1ed2" }, "candidate_source_sha256": { "src/apixly_jev_harness/__init__.py": "7093e9f7a45a9b6c75b2cdd3c1c0a2364d1b66afbee46fa5340660e576d52cd6", "src/apixly_jev_harness/backend.py": "0ddfab6b270d8219a66614630e70aa10a74cb531f8075d07c255df145725ed5f", "src/apixly_jev_harness/callbacks.py": "2d27ad4540d910354c54de7566546b4c9d99b5a5fa87705a1905885349078497", "src/apixly_jev_harness/cli.py": "8d9434bf8a8b539163194a84e3f099761d08ef32201f99cbce46c139f3726d94", "src/apixly_jev_harness/context.py": "b9d76abb33f8a1ebe8731fe6d5fe6811445132a6046448fc0e2cc871507d50ea", "src/apixly_jev_harness/diagnostics.py": "9e8e98dc4b103c1a6687dbd31bd2dd01739309c7e4021b9ecb0f28b6976a0f71", "src/apixly_jev_harness/engine.py": "ad5e27cd3eeb8ccf3beb3f6a06e57321edd0fb8c2db63eaa432d3d00ebddf19f", "src/apixly_jev_harness/output.py": "94be8b482e4279e29aca128a35caf54744dbe8db8188f14905488f8ddde93a0b", "src/apixly_jev_harness/surfaces.py": "65ce73edfe9f6a3c16de373b3a1b85671c3d2cc661f3a50dd906a15721c7d8f1", "src/apixly_jev_harness/task.py": "0f5801e9fdb5626e1db65d269c715e8bcf692ebaa3a91f46b9945158b4bbb6db", "src/apixly_jev_harness/task_cli.py": "21c883722768c781a68e31e3a602e43eb2a5fac838ea61de478348e9cee87aa8", "src/apixly_jev_harness/verify.py": "97d2a178902291094f4e16db08732748d234b8c5ad8dd49a55607c8d195f1ed2" }, "runner_sha256": "e1b9b8f8f1b99af1f077f1d21b052e6dab7d6723f44c130cc92f77f0810ef6e1", "python_version": "3.14.2", "cases": { "execute_known": { "stage": "execute", "usage": "known" }, "execute_unknown": { "stage": "execute", "usage": "unknown" }, "result_context_known": { "stage": "result_context", "usage": "known" }, "result_context_unknown": { "stage": "result_context", "usage": "unknown" }, "observe_known": { "stage": "observe", "usage": "known" }, "observe_unknown": { "stage": "observe", "usage": "unknown" }, "verify_known": { "stage": "verify", "usage": "known" }, "verify_unknown": { "stage": "verify", "usage": "unknown" }, "pre_effect_bind_stop": { "stage": "bind_stop", "usage": "known" }, "pre_effect_freshness_stop": { "stage": "freshness_stop", "usage": "unknown" }, "pre_effect_freshness_exception": { "stage": "freshness_exception", "usage": "known" }, "post_effect_ordinary_exception": { "stage": "ordinary_exception", "usage": "known" }, "normal_done_known": { "stage": "done", "usage": "known" }, "normal_done_unknown": { "stage": "done", "usage": "unknown" }, "cleared_next_cycle_verify_stop": { "stage": "next_cycle_verify_stop", "usage": "known" }, "second_effect_execute_unknown": { "stage": "second_effect_execute", "usage": "unknown" } }, "behavior_parity": true, "reproduction": "python benchmarks/execution_identity.py --output local-results/execution-identity-ab.json", "scope": "Sixteen fixed synthetic workflows, three paired repeats with alternating arm order. Four post-effect DecisionStop stages are paired with known/unknown prior scripted usage. Controls cover pre-effect binding/freshness stops, existing ordinary exception identities before/after effects, verified done with known/unknown usage, a later-cycle stop after pending identity was cleared and a second distinct action whose current id must not be replaced by the first historical id. Selection is scripted; native inference entrypoints are forbidden and actual model/network/UI calls are zero if the guard is never hit. Durable local intent and independent synthetic effect counters establish which current action stopped. The verifier-stop fixture uses the unchanged-observation immediate verification path while execution is still pending.", "negative_results": "Adding a current action_id increases uncertain terminal output bytes and introduces local projection work. The id identifies the program's pending action, not proof of external completion, permission, rollback, safe retry or exactly-once behavior. Ordinary exceptions already carried pending ids, including a pre-effect failure; pre-effect DecisionStop controls still omit action_id. No semantic quality, real-world action reconciliation, speed or fee improvement is claimed. Unknown prior scripted usage remains unknown even when the terminal action is identified.", "cost_conversion": "No tariff or savings assumed. Actual model usage is zero only with zero forbidden native attempts; a guard hit records unknown actual usage and fails the fixture. Scripted requests and reported scripted usage are separate from actual model usage. Real whole-operation timing uses perf_counter and includes synthetic registration, loop admission, scripted selection, trusted callbacks, effect markers and private journal serialization; excludes process/import setup and terminal analysis/source hashes. A loop-only frozen monotonic clock stabilizes synthetic request budgets and never substitutes for whole-operation timing. Returned context bytes exclude the local archive path; scalar request sizes include the shared context and selection envelope, not provider tokens.", "summary": { "baseline": { "runs": 48, "correct": 21, "behavior_correct": 48, "identity_correct": 21, "terminal_matches_durable_intent": 21, "uncertain_exits": 30, "pre_effect_stops": 6, "scripted_decisions": 51, "effects": 42, "intent_events": 42, "unknown_scripted_usage_rows": 21, "native_inference_attempts": 0, "raw_input_marker_exposures": 0, "median_whole_operation_seconds": 0.0013709584964090027, "returned_context_bytes": 24069, "selection_input_bytes": 87279, "shared_context_bytes": 14667, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true } }, "candidate": { "runs": 48, "correct": 48, "behavior_correct": 48, "identity_correct": 48, "terminal_matches_durable_intent": 48, "uncertain_exits": 30, "pre_effect_stops": 6, "scripted_decisions": 51, "effects": 42, "intent_events": 42, "unknown_scripted_usage_rows": 21, "native_inference_attempts": 0, "raw_input_marker_exposures": 0, "median_whole_operation_seconds": 0.0014633749960921705, "returned_context_bytes": 24897, "selection_input_bytes": 87279, "shared_context_bytes": 14667, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true } } }, "rows": [ { "case": "execute_known", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "execute", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:execute", "error_type": null, "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:execute", "error_type": null, "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": false, "terminal_matches_durable_intent": false, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": false, "whole_operation_seconds": 0.0010043329966720194, "returned_context_bytes": 527, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 1 }, { "case": "execute_known", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "execute", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:execute", "error_type": null, "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:execute", "error_type": null, "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0013297089899424464, "returned_context_bytes": 558, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 1 }, { "case": "execute_known", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "execute", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:execute", "error_type": null, "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:execute", "error_type": null, "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0013340420118765905, "returned_context_bytes": 558, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 2 }, { "case": "execute_known", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "execute", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:execute", "error_type": null, "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:execute", "error_type": null, "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": false, "terminal_matches_durable_intent": false, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": false, "whole_operation_seconds": 0.001300415999139659, "returned_context_bytes": 527, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 2 }, { "case": "execute_known", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "execute", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:execute", "error_type": null, "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:execute", "error_type": null, "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": false, "terminal_matches_durable_intent": false, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": false, "whole_operation_seconds": 0.0013729999918723479, "returned_context_bytes": 527, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 3 }, { "case": "execute_known", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "execute", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:execute", "error_type": null, "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:execute", "error_type": null, "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0013687089958693832, "returned_context_bytes": 558, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 3 }, { "case": "execute_unknown", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "execute", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:execute", "error_type": null, "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:execute", "error_type": null, "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": false, "terminal_matches_durable_intent": false, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": false, "whole_operation_seconds": 0.001335499997367151, "returned_context_bytes": 459, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 1 }, { "case": "execute_unknown", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "execute", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:execute", "error_type": null, "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:execute", "error_type": null, "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0012854579981649294, "returned_context_bytes": 490, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 1 }, { "case": "execute_unknown", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "execute", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:execute", "error_type": null, "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:execute", "error_type": null, "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.00126862499746494, "returned_context_bytes": 490, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 2 }, { "case": "execute_unknown", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "execute", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:execute", "error_type": null, "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:execute", "error_type": null, "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": false, "terminal_matches_durable_intent": false, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": false, "whole_operation_seconds": 0.0012744160048896447, "returned_context_bytes": 459, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 2 }, { "case": "execute_unknown", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "execute", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:execute", "error_type": null, "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:execute", "error_type": null, "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": false, "terminal_matches_durable_intent": false, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": false, "whole_operation_seconds": 0.0014314580039354041, "returned_context_bytes": 459, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 3 }, { "case": "execute_unknown", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "execute", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:execute", "error_type": null, "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:execute", "error_type": null, "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0016483340004924685, "returned_context_bytes": 490, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 3 }, { "case": "result_context_known", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "result_context", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:result_context", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:result_context", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": false, "terminal_matches_durable_intent": false, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": false, "whole_operation_seconds": 0.0014176670083543286, "returned_context_bytes": 534, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 1 }, { "case": "result_context_known", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "result_context", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:result_context", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:result_context", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0015224170056171715, "returned_context_bytes": 565, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 1 }, { "case": "result_context_known", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "result_context", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:result_context", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:result_context", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0015035830001579598, "returned_context_bytes": 565, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 2 }, { "case": "result_context_known", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "result_context", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:result_context", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:result_context", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": false, "terminal_matches_durable_intent": false, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": false, "whole_operation_seconds": 0.001403709000442177, "returned_context_bytes": 534, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 2 }, { "case": "result_context_known", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "result_context", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:result_context", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:result_context", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": false, "terminal_matches_durable_intent": false, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": false, "whole_operation_seconds": 0.0011951670021517202, "returned_context_bytes": 534, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 3 }, { "case": "result_context_known", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "result_context", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:result_context", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:result_context", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0013557080092141405, "returned_context_bytes": 565, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 3 }, { "case": "result_context_unknown", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "result_context", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:result_context", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:result_context", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": false, "terminal_matches_durable_intent": false, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": false, "whole_operation_seconds": 0.0013689170009456575, "returned_context_bytes": 466, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 1 }, { "case": "result_context_unknown", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "result_context", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:result_context", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:result_context", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.001354332998744212, "returned_context_bytes": 497, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 1 }, { "case": "result_context_unknown", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "result_context", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:result_context", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:result_context", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0013479589979397133, "returned_context_bytes": 497, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 2 }, { "case": "result_context_unknown", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "result_context", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:result_context", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:result_context", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": false, "terminal_matches_durable_intent": false, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": false, "whole_operation_seconds": 0.0014863339893054217, "returned_context_bytes": 466, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 2 }, { "case": "result_context_unknown", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "result_context", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:result_context", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:result_context", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": false, "terminal_matches_durable_intent": false, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": false, "whole_operation_seconds": 0.0013877500023227185, "returned_context_bytes": 466, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 3 }, { "case": "result_context_unknown", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "result_context", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:result_context", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:result_context", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0012895830004708841, "returned_context_bytes": 497, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 3 }, { "case": "observe_known", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "observe", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:observe", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:observe", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": false, "terminal_matches_durable_intent": false, "observations": 3, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": false, "whole_operation_seconds": 0.0013203749986132607, "returned_context_bytes": 527, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 1 }, { "case": "observe_known", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "observe", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:observe", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:observe", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.001333541003987193, "returned_context_bytes": 558, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 1 }, { "case": "observe_known", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "observe", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:observe", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:observe", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0016834169946378097, "returned_context_bytes": 558, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 2 }, { "case": "observe_known", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "observe", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:observe", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:observe", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": false, "terminal_matches_durable_intent": false, "observations": 3, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": false, "whole_operation_seconds": 0.0011699589958880097, "returned_context_bytes": 527, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 2 }, { "case": "observe_known", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "observe", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:observe", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:observe", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": false, "terminal_matches_durable_intent": false, "observations": 3, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": false, "whole_operation_seconds": 0.0015070420049596578, "returned_context_bytes": 527, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 3 }, { "case": "observe_known", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "observe", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:observe", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:observe", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0015542500041192397, "returned_context_bytes": 558, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 3 }, { "case": "observe_unknown", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "observe", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:observe", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:observe", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": false, "terminal_matches_durable_intent": false, "observations": 3, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": false, "whole_operation_seconds": 0.0013544579996960238, "returned_context_bytes": 459, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 1 }, { "case": "observe_unknown", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "observe", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:observe", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:observe", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0014698340091854334, "returned_context_bytes": 490, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 1 }, { "case": "observe_unknown", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "observe", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:observe", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:observe", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0015321249957196414, "returned_context_bytes": 490, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 2 }, { "case": "observe_unknown", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "observe", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:observe", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:observe", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": false, "terminal_matches_durable_intent": false, "observations": 3, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": false, "whole_operation_seconds": 0.0014164590102154762, "returned_context_bytes": 459, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 2 }, { "case": "observe_unknown", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "observe", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:observe", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:observe", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": false, "terminal_matches_durable_intent": false, "observations": 3, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": false, "whole_operation_seconds": 0.001356042004772462, "returned_context_bytes": 459, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 3 }, { "case": "observe_unknown", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "observe", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:observe", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:observe", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0015187500102911144, "returned_context_bytes": 490, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 3 }, { "case": "verify_known", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "verify", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:verify", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:verify", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": false, "terminal_matches_durable_intent": false, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": false, "whole_operation_seconds": 0.001574499998241663, "returned_context_bytes": 526, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 1 }, { "case": "verify_known", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "verify", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:verify", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:verify", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0015570830000797287, "returned_context_bytes": 557, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 1 }, { "case": "verify_known", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "verify", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:verify", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:verify", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0015279590006684884, "returned_context_bytes": 557, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 2 }, { "case": "verify_known", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "verify", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:verify", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:verify", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": false, "terminal_matches_durable_intent": false, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": false, "whole_operation_seconds": 0.0015337920049205422, "returned_context_bytes": 526, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 2 }, { "case": "verify_known", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "verify", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:verify", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:verify", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": false, "terminal_matches_durable_intent": false, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": false, "whole_operation_seconds": 0.0013998340000398457, "returned_context_bytes": 526, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 3 }, { "case": "verify_known", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "verify", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:verify", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:verify", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0012300410016905516, "returned_context_bytes": 557, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 3 }, { "case": "verify_unknown", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "verify", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:verify", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:verify", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": false, "terminal_matches_durable_intent": false, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": false, "whole_operation_seconds": 0.0014238750009099022, "returned_context_bytes": 458, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 1 }, { "case": "verify_unknown", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "verify", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:verify", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:verify", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.001416208004229702, "returned_context_bytes": 489, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 1 }, { "case": "verify_unknown", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "verify", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:verify", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:verify", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0014622919989051297, "returned_context_bytes": 489, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 2 }, { "case": "verify_unknown", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "verify", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:verify", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:verify", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": false, "terminal_matches_durable_intent": false, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": false, "whole_operation_seconds": 0.0014120830019237474, "returned_context_bytes": 458, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 2 }, { "case": "verify_unknown", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "verify", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:verify", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:verify", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": false, "terminal_matches_durable_intent": false, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": false, "whole_operation_seconds": 0.001506542001152411, "returned_context_bytes": 458, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 3 }, { "case": "verify_unknown", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "verify", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:verify", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_effect:verify", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0016852909902809188, "returned_context_bytes": 489, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 3 }, { "case": "pre_effect_bind_stop", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "bind_stop", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_before_effect", "error_type": null, "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_before_effect", "error_type": null, "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 1, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0011596250114962459, "returned_context_bytes": 514, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 1 }, { "case": "pre_effect_bind_stop", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "bind_stop", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_before_effect", "error_type": null, "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_before_effect", "error_type": null, "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 1, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.001183916989248246, "returned_context_bytes": 514, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 1 }, { "case": "pre_effect_bind_stop", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "bind_stop", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_before_effect", "error_type": null, "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_before_effect", "error_type": null, "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 1, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0015105829952517524, "returned_context_bytes": 514, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 2 }, { "case": "pre_effect_bind_stop", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "bind_stop", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_before_effect", "error_type": null, "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_before_effect", "error_type": null, "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 1, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.001280291995499283, "returned_context_bytes": 514, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 2 }, { "case": "pre_effect_bind_stop", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "bind_stop", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_before_effect", "error_type": null, "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_before_effect", "error_type": null, "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 1, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0013651249901158735, "returned_context_bytes": 514, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 3 }, { "case": "pre_effect_bind_stop", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "bind_stop", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_before_effect", "error_type": null, "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_before_effect", "error_type": null, "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 1, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0014234999980544671, "returned_context_bytes": 514, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 3 }, { "case": "pre_effect_freshness_stop", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "freshness_stop", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_before_effect", "error_type": null, "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_before_effect", "error_type": null, "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.001218332996359095, "returned_context_bytes": 446, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 1 }, { "case": "pre_effect_freshness_stop", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "freshness_stop", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_before_effect", "error_type": null, "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_before_effect", "error_type": null, "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.001872708002338186, "returned_context_bytes": 446, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 1 }, { "case": "pre_effect_freshness_stop", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "freshness_stop", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_before_effect", "error_type": null, "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_before_effect", "error_type": null, "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0011111659987363964, "returned_context_bytes": 446, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 2 }, { "case": "pre_effect_freshness_stop", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "freshness_stop", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_before_effect", "error_type": null, "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_before_effect", "error_type": null, "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0013034159928793088, "returned_context_bytes": 446, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 2 }, { "case": "pre_effect_freshness_stop", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "freshness_stop", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_before_effect", "error_type": null, "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_before_effect", "error_type": null, "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.001317540998570621, "returned_context_bytes": 446, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 3 }, { "case": "pre_effect_freshness_stop", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "freshness_stop", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_before_effect", "error_type": null, "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_before_effect", "error_type": null, "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0013296249962877482, "returned_context_bytes": 446, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 3 }, { "case": "pre_effect_freshness_exception", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "freshness_exception", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "failed", "complete": false, "reason": null, "error_type": "RuntimeError", "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "failed", "complete": false, "reason": null, "error_type": "RuntimeError", "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0012805000005755574, "returned_context_bytes": 526, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 1 }, { "case": "pre_effect_freshness_exception", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "freshness_exception", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "failed", "complete": false, "reason": null, "error_type": "RuntimeError", "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "failed", "complete": false, "reason": null, "error_type": "RuntimeError", "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.001857916999142617, "returned_context_bytes": 526, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 1 }, { "case": "pre_effect_freshness_exception", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "freshness_exception", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "failed", "complete": false, "reason": null, "error_type": "RuntimeError", "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "failed", "complete": false, "reason": null, "error_type": "RuntimeError", "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0013368749932851642, "returned_context_bytes": 526, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 2 }, { "case": "pre_effect_freshness_exception", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "freshness_exception", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "failed", "complete": false, "reason": null, "error_type": "RuntimeError", "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "failed", "complete": false, "reason": null, "error_type": "RuntimeError", "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0013485420058714226, "returned_context_bytes": 526, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 2 }, { "case": "pre_effect_freshness_exception", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "freshness_exception", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "failed", "complete": false, "reason": null, "error_type": "RuntimeError", "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "failed", "complete": false, "reason": null, "error_type": "RuntimeError", "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.001292834000196308, "returned_context_bytes": 526, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 3 }, { "case": "pre_effect_freshness_exception", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "freshness_exception", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "failed", "complete": false, "reason": null, "error_type": "RuntimeError", "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "failed", "complete": false, "reason": null, "error_type": "RuntimeError", "steps": 0, "effects": 0, "intent_events": 0, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0013124160032020882, "returned_context_bytes": 526, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 3 }, { "case": "post_effect_ordinary_exception", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "ordinary_exception", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": null, "error_type": "TimeoutError", "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": null, "error_type": "TimeoutError", "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.001310291001573205, "returned_context_bytes": 539, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 1 }, { "case": "post_effect_ordinary_exception", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "ordinary_exception", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": null, "error_type": "TimeoutError", "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": null, "error_type": "TimeoutError", "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0014547500031767413, "returned_context_bytes": 539, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 1 }, { "case": "post_effect_ordinary_exception", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "ordinary_exception", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": null, "error_type": "TimeoutError", "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": null, "error_type": "TimeoutError", "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0012307089928071946, "returned_context_bytes": 539, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 2 }, { "case": "post_effect_ordinary_exception", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "ordinary_exception", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": null, "error_type": "TimeoutError", "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": null, "error_type": "TimeoutError", "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0014614579995395616, "returned_context_bytes": 539, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 2 }, { "case": "post_effect_ordinary_exception", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "ordinary_exception", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": null, "error_type": "TimeoutError", "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": null, "error_type": "TimeoutError", "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.001091917001758702, "returned_context_bytes": 539, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 3 }, { "case": "post_effect_ordinary_exception", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "ordinary_exception", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": null, "error_type": "TimeoutError", "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "execution_uncertain", "complete": false, "reason": null, "error_type": "TimeoutError", "steps": 0, "effects": 1, "intent_events": 1, "executed_events": 0, "action_id": "synthetic_step", "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 2, "verifications": 1, "request_sizes": [ { "selection_input_bytes": 1707, "shared_context_bytes": 282, "shared_context_characters": 282 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0014867910067550838, "returned_context_bytes": 539, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 3 }, { "case": "normal_done_known", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "done", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "done", "complete": true, "reason": null, "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "done", "complete": true, "reason": null, "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1706, "shared_context_bytes": 281, "shared_context_characters": 281 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0016400830063503236, "returned_context_bytes": 462, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 1 }, { "case": "normal_done_known", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "done", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "done", "complete": true, "reason": null, "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "done", "complete": true, "reason": null, "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1706, "shared_context_bytes": 281, "shared_context_characters": 281 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0016118330095196143, "returned_context_bytes": 462, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 1 }, { "case": "normal_done_known", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "done", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "done", "complete": true, "reason": null, "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "done", "complete": true, "reason": null, "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1706, "shared_context_bytes": 281, "shared_context_characters": 281 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0015968750085448846, "returned_context_bytes": 462, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 2 }, { "case": "normal_done_known", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "done", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "done", "complete": true, "reason": null, "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "done", "complete": true, "reason": null, "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1706, "shared_context_bytes": 281, "shared_context_characters": 281 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0014727079978911206, "returned_context_bytes": 462, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 2 }, { "case": "normal_done_known", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "done", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "done", "complete": true, "reason": null, "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "done", "complete": true, "reason": null, "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1706, "shared_context_bytes": 281, "shared_context_characters": 281 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.001367832999676466, "returned_context_bytes": 462, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 3 }, { "case": "normal_done_known", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "done", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "done", "complete": true, "reason": null, "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "done", "complete": true, "reason": null, "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1706, "shared_context_bytes": 281, "shared_context_characters": 281 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0016043329960666597, "returned_context_bytes": 462, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 3 }, { "case": "normal_done_unknown", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "done", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "done", "complete": true, "reason": null, "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "done", "complete": true, "reason": null, "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1706, "shared_context_bytes": 281, "shared_context_characters": 281 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0016648329910822213, "returned_context_bytes": 394, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 1 }, { "case": "normal_done_unknown", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "done", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "done", "complete": true, "reason": null, "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "done", "complete": true, "reason": null, "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1706, "shared_context_bytes": 281, "shared_context_characters": 281 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0012972499971510842, "returned_context_bytes": 394, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 1 }, { "case": "normal_done_unknown", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "done", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "done", "complete": true, "reason": null, "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "done", "complete": true, "reason": null, "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1706, "shared_context_bytes": 281, "shared_context_characters": 281 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0014644579932792112, "returned_context_bytes": 394, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 2 }, { "case": "normal_done_unknown", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "done", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "done", "complete": true, "reason": null, "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "done", "complete": true, "reason": null, "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1706, "shared_context_bytes": 281, "shared_context_characters": 281 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.001548750005895272, "returned_context_bytes": 394, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 2 }, { "case": "normal_done_unknown", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "done", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "done", "complete": true, "reason": null, "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "done", "complete": true, "reason": null, "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1706, "shared_context_bytes": 281, "shared_context_characters": 281 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0013150000013411045, "returned_context_bytes": 394, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 3 }, { "case": "normal_done_unknown", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "done", "usage": "unknown", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "done", "complete": true, "reason": null, "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "done", "complete": true, "reason": null, "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1706, "shared_context_bytes": 281, "shared_context_characters": 281 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0013552500022342429, "returned_context_bytes": 394, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 3 }, { "case": "cleared_next_cycle_verify_stop", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "next_cycle_verify_stop", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_next_cycle", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_next_cycle", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1703, "shared_context_bytes": 278, "shared_context_characters": 278 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0012679170031333342, "returned_context_bytes": 511, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 1 }, { "case": "cleared_next_cycle_verify_stop", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "next_cycle_verify_stop", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_next_cycle", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_next_cycle", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1703, "shared_context_bytes": 278, "shared_context_characters": 278 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0013772079983027652, "returned_context_bytes": 511, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 1 }, { "case": "cleared_next_cycle_verify_stop", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "next_cycle_verify_stop", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_next_cycle", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_next_cycle", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1703, "shared_context_bytes": 278, "shared_context_characters": 278 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0015370839973911643, "returned_context_bytes": 511, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 2 }, { "case": "cleared_next_cycle_verify_stop", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "next_cycle_verify_stop", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_next_cycle", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_next_cycle", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1703, "shared_context_bytes": 278, "shared_context_characters": 278 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0015863339940551668, "returned_context_bytes": 511, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 2 }, { "case": "cleared_next_cycle_verify_stop", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "next_cycle_verify_stop", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_next_cycle", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_next_cycle", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1703, "shared_context_bytes": 278, "shared_context_characters": 278 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0015561670006718487, "returned_context_bytes": 511, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 3 }, { "case": "cleared_next_cycle_verify_stop", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "next_cycle_verify_stop", "usage": "known", "offered_action_ids": [ "synthetic_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_next_cycle", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 } }, "result": { "status": "needs_context", "complete": false, "reason": "synthetic_stop_next_cycle", "error_type": null, "steps": 1, "effects": 1, "intent_events": 1, "executed_events": 1, "action_id": null, "scripted_decisions": 1, "scripted_requests_reported": 1, "scripted_usage_complete": true, "reported_scripted_usage": { "input_tokens": 7, "output_tokens": 2 }, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 3, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1703, "shared_context_bytes": 278, "shared_context_characters": 278 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0015597079909639433, "returned_context_bytes": 511, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 3 }, { "case": "second_effect_execute_unknown", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "second_effect_execute", "usage": "unknown", "offered_action_ids": [ "first_step", "second_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_second_effect", "error_type": null, "steps": 1, "effects": 2, "intent_events": 2, "executed_events": 1, "action_id": "second_step", "scripted_decisions": 2, "scripted_requests_reported": 2, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_second_effect", "error_type": null, "steps": 1, "effects": 2, "intent_events": 2, "executed_events": 1, "action_id": null, "scripted_decisions": 2, "scripted_requests_reported": 2, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": false, "terminal_matches_durable_intent": false, "observations": 4, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1691, "shared_context_bytes": 278, "shared_context_characters": 278 }, { "selection_input_bytes": 1803, "shared_context_bytes": 387, "shared_context_characters": 387 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": false, "whole_operation_seconds": 0.0018945829942822456, "returned_context_bytes": 675, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 1 }, { "case": "second_effect_execute_unknown", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "second_effect_execute", "usage": "unknown", "offered_action_ids": [ "first_step", "second_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_second_effect", "error_type": null, "steps": 1, "effects": 2, "intent_events": 2, "executed_events": 1, "action_id": "second_step", "scripted_decisions": 2, "scripted_requests_reported": 2, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_second_effect", "error_type": null, "steps": 1, "effects": 2, "intent_events": 2, "executed_events": 1, "action_id": "second_step", "scripted_decisions": 2, "scripted_requests_reported": 2, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 4, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1691, "shared_context_bytes": 278, "shared_context_characters": 278 }, { "selection_input_bytes": 1803, "shared_context_bytes": 387, "shared_context_characters": 387 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0018189580005127937, "returned_context_bytes": 703, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 1 }, { "case": "second_effect_execute_unknown", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "second_effect_execute", "usage": "unknown", "offered_action_ids": [ "first_step", "second_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_second_effect", "error_type": null, "steps": 1, "effects": 2, "intent_events": 2, "executed_events": 1, "action_id": "second_step", "scripted_decisions": 2, "scripted_requests_reported": 2, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_second_effect", "error_type": null, "steps": 1, "effects": 2, "intent_events": 2, "executed_events": 1, "action_id": "second_step", "scripted_decisions": 2, "scripted_requests_reported": 2, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 4, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1691, "shared_context_bytes": 278, "shared_context_characters": 278 }, { "selection_input_bytes": 1803, "shared_context_bytes": 387, "shared_context_characters": 387 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.001677749998634681, "returned_context_bytes": 703, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 2 }, { "case": "second_effect_execute_unknown", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "second_effect_execute", "usage": "unknown", "offered_action_ids": [ "first_step", "second_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_second_effect", "error_type": null, "steps": 1, "effects": 2, "intent_events": 2, "executed_events": 1, "action_id": "second_step", "scripted_decisions": 2, "scripted_requests_reported": 2, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_second_effect", "error_type": null, "steps": 1, "effects": 2, "intent_events": 2, "executed_events": 1, "action_id": null, "scripted_decisions": 2, "scripted_requests_reported": 2, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": false, "terminal_matches_durable_intent": false, "observations": 4, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1691, "shared_context_bytes": 278, "shared_context_characters": 278 }, { "selection_input_bytes": 1803, "shared_context_bytes": 387, "shared_context_characters": 387 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": false, "whole_operation_seconds": 0.0015994589921319857, "returned_context_bytes": 675, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 2 }, { "case": "second_effect_execute_unknown", "runtime_version": "0.1.10", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "second_effect_execute", "usage": "unknown", "offered_action_ids": [ "first_step", "second_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_second_effect", "error_type": null, "steps": 1, "effects": 2, "intent_events": 2, "executed_events": 1, "action_id": "second_step", "scripted_decisions": 2, "scripted_requests_reported": 2, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_second_effect", "error_type": null, "steps": 1, "effects": 2, "intent_events": 2, "executed_events": 1, "action_id": null, "scripted_decisions": 2, "scripted_requests_reported": 2, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": false, "terminal_matches_durable_intent": false, "observations": 4, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1691, "shared_context_bytes": 278, "shared_context_characters": 278 }, { "selection_input_bytes": 1803, "shared_context_bytes": 387, "shared_context_characters": 387 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": false, "whole_operation_seconds": 0.0016887910023797303, "returned_context_bytes": 675, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "baseline", "repeat": 3 }, { "case": "second_effect_execute_unknown", "runtime_version": "0.1.11", "runtime_loaded_from_requested_source": true, "fixture": { "stage": "second_effect_execute", "usage": "unknown", "offered_action_ids": [ "first_step", "second_step" ], "frozen_loop_monotonic": 100.0, "max_steps": 2, "timeout_seconds": 120 }, "expected": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_second_effect", "error_type": null, "steps": 1, "effects": 2, "intent_events": 2, "executed_events": 1, "action_id": "second_step", "scripted_decisions": 2, "scripted_requests_reported": 2, "scripted_usage_complete": false, "reported_scripted_usage": null }, "result": { "status": "execution_uncertain", "complete": false, "reason": "synthetic_stop_after_second_effect", "error_type": null, "steps": 1, "effects": 2, "intent_events": 2, "executed_events": 1, "action_id": "second_step", "scripted_decisions": 2, "scripted_requests_reported": 2, "scripted_usage_complete": false, "reported_scripted_usage": null, "behavior_correct": true, "identity_correct": true, "terminal_matches_durable_intent": true, "observations": 4, "verifications": 2, "request_sizes": [ { "selection_input_bytes": 1691, "shared_context_bytes": 278, "shared_context_characters": 278 }, { "selection_input_bytes": 1803, "shared_context_bytes": 387, "shared_context_characters": 387 } ], "native_inference_attempts": 0, "raw_input_marker_exposures": 0 }, "correct": true, "whole_operation_seconds": 0.0015675419999752194, "returned_context_bytes": 703, "actual_model_usage": { "requests": 0, "models": {}, "input_tokens": 0, "output_tokens": 0, "usage_complete": true }, "arm": "candidate", "repeat": 3 } ] }