{ "schema_version": "1.0", "baseline": "fdadbed489129455437f25202a03bae6e0c2e822", "experiment_date": "2026-09-04", "status": "OBSERVED_COUNTEREXAMPLES; NOT_FIXED; NOT_QA_ACCEPTANCE", "external_effectful_calls": 0, "baseline_tests": { "tests": [ { "file": "src/approval/__tests__/OperationApprovalService.test.ts", "sha256": "d1a386437dd1102c88f5188f545f31aee42d21f6f54105998f2621a928405e09" }, { "file": "src/pm/__tests__/pmChildTaskIdentityDependency.test.ts", "sha256": "9732845b5bde8a4a6d7fce55a1f59771c509f66b5c8857e266690d0ec213c132" }, { "file": "src/evidence-association/__tests__/EvidenceAssociationReader.test.ts", "sha256": "2220d52fdef1b0d3cd72729c29a92b73c0bbb1e3d0a6a605476dacb77b72bf4c" }, { "file": "src/logs/__tests__/TelemetryRedactor.test.ts", "sha256": "3b869c3a4ad05b1a7178218e65e8aa4f91b03a27b15299b29864e0fe00e3c4d7" } ], "runs": [ { "started": "2026-09-04T05:37:53.595Z", "finished": "2026-09-04T05:37:54.724Z", "exit_code": 0, "counts": { "tests": 31, "pass": 31, "fail": 0, "skipped": 0 }, "raw_log_sha256": "9a9849c58a20ce3ef1bd4abe96202af68234d8243d36821300aa2baa7feca884" }, { "started": "2026-09-04T05:37:54.726Z", "finished": "2026-09-04T05:37:55.901Z", "exit_code": 0, "counts": { "tests": 31, "pass": 31, "fail": 0, "skipped": 0 }, "raw_log_sha256": "ec6206fc6714606d768085e573ef6f5f56f67990974c775d2e07b0e8e2685f2c" } ] }, "approval_matrix": [ { "round": 1, "name": "same-session", "expected": "ALLOW", "expectation": "matched", "fixture": "", "first": { "decision": "ALLOW", "reason": "operation_approval_consumed", "authorization": { "status": "consumed", "issued_at": "2026-09-04T05:41:19.271Z", "consumed_at": "2026-09-04T05:41:19.475Z", "consumed_by": { "agent_id": "DEV-01", "session_id": "session-1", "task_id": "TASK-1", "thread_key": "thread-1", "role": "DEV" } } }, "replay": { "decision": "THREW", "code": "APPROVAL_ALREADY_CONSUMED", "authorization": { "status": "consumed", "issued_at": "2026-09-04T05:41:19.271Z", "consumed_at": "2026-09-04T05:41:19.475Z", "consumed_by": { "agent_id": "DEV-01", "session_id": "session-1", "task_id": "TASK-1", "thread_key": "thread-1", "role": "DEV" } } } }, { "round": 1, "name": "delivered-resume", "expected": "ALLOW", "expectation": "mismatched", "fixture": "", "first": { "decision": "REQUIRE_APPROVAL", "authorization": { "status": "available", "issued_at": "2026-09-04T05:41:19.717Z", "consumed_at": null } }, "replay": null }, { "round": 1, "name": "other-session", "expected": "OBSERVE", "expectation": "not_scored", "fixture": "", "first": { "decision": "REQUIRE_APPROVAL", "authorization": { "status": "available", "issued_at": "2026-09-04T05:41:19.972Z", "consumed_at": null } }, "replay": null }, { "round": 1, "name": "missing-session", "expected": "REQUIRE_APPROVAL", "expectation": "matched", "fixture": "", "first": { "decision": "REQUIRE_APPROVAL", "authorization": { "status": "available", "issued_at": "2026-09-04T05:41:20.246Z", "consumed_at": null } }, "replay": null }, { "round": 1, "name": "different-agent", "expected": "REQUIRE_APPROVAL", "expectation": "matched", "fixture": "", "first": { "decision": "REQUIRE_APPROVAL", "authorization": { "status": "available", "issued_at": "2026-09-04T05:41:20.539Z", "consumed_at": null } }, "replay": null }, { "round": 1, "name": "different-task", "expected": "REQUIRE_APPROVAL", "expectation": "matched", "fixture": "", "first": { "decision": "REQUIRE_APPROVAL", "authorization": { "status": "available", "issued_at": "2026-09-04T05:41:20.812Z", "consumed_at": null } }, "replay": null }, { "round": 1, "name": "different-thread", "expected": "REQUIRE_APPROVAL", "expectation": "matched", "fixture": "", "first": { "decision": "REQUIRE_APPROVAL", "authorization": { "status": "available", "issued_at": "2026-09-04T05:41:21.039Z", "consumed_at": null } }, "replay": null }, { "round": 1, "name": "different-project", "expected": "REQUIRE_APPROVAL", "expectation": "matched", "fixture": "", "first": { "decision": "REQUIRE_APPROVAL", "authorization": { "status": "available", "issued_at": "2026-09-04T05:41:21.265Z", "consumed_at": null } }, "replay": null }, { "round": 1, "name": "different-target", "expected": "REQUIRE_APPROVAL", "expectation": "mismatched", "fixture": "", "first": { "decision": "ALLOW", "reason": "operation_approval_consumed", "authorization": { "status": "consumed", "issued_at": "2026-09-04T05:41:21.485Z", "consumed_at": "2026-09-04T05:41:21.683Z", "consumed_by": { "agent_id": "DEV-01", "session_id": "session-1", "task_id": "TASK-1", "thread_key": "thread-1", "role": "DEV" } } }, "replay": { "decision": "THREW", "code": "APPROVAL_ALREADY_CONSUMED", "authorization": { "status": "consumed", "issued_at": "2026-09-04T05:41:21.485Z", "consumed_at": "2026-09-04T05:41:21.683Z", "consumed_by": { "agent_id": "DEV-01", "session_id": "session-1", "task_id": "TASK-1", "thread_key": "thread-1", "role": "DEV" } } } }, { "round": 1, "name": "different-source-channel", "expected": "OBSERVE", "expectation": "not_scored", "fixture": "", "first": { "decision": "REQUIRE_APPROVAL", "authorization": { "status": "available", "issued_at": "2026-09-04T05:41:21.927Z", "consumed_at": null } }, "replay": null }, { "round": 1, "name": "cancelled", "expected": "REQUIRE_APPROVAL", "expectation": "matched", "fixture": "", "first": { "decision": "REQUIRE_APPROVAL", "authorization": { "status": "invalid", "issued_at": null, "consumed_at": null } }, "replay": null }, { "round": 2, "name": "same-session", "expected": "ALLOW", "expectation": "matched", "fixture": "", "first": { "decision": "ALLOW", "reason": "operation_approval_consumed", "authorization": { "status": "consumed", "issued_at": "2026-09-04T05:41:22.455Z", "consumed_at": "2026-09-04T05:41:22.687Z", "consumed_by": { "agent_id": "DEV-01", "session_id": "session-1", "task_id": "TASK-1", "thread_key": "thread-1", "role": "DEV" } } }, "replay": { "decision": "THREW", "code": "APPROVAL_ALREADY_CONSUMED", "authorization": { "status": "consumed", "issued_at": "2026-09-04T05:41:22.455Z", "consumed_at": "2026-09-04T05:41:22.687Z", "consumed_by": { "agent_id": "DEV-01", "session_id": "session-1", "task_id": "TASK-1", "thread_key": "thread-1", "role": "DEV" } } } }, { "round": 2, "name": "delivered-resume", "expected": "ALLOW", "expectation": "mismatched", "fixture": "", "first": { "decision": "REQUIRE_APPROVAL", "authorization": { "status": "available", "issued_at": "2026-09-04T05:41:22.958Z", "consumed_at": null } }, "replay": null }, { "round": 2, "name": "other-session", "expected": "OBSERVE", "expectation": "not_scored", "fixture": "", "first": { "decision": "REQUIRE_APPROVAL", "authorization": { "status": "available", "issued_at": "2026-09-04T05:41:23.198Z", "consumed_at": null } }, "replay": null }, { "round": 2, "name": "missing-session", "expected": "REQUIRE_APPROVAL", "expectation": "matched", "fixture": "", "first": { "decision": "REQUIRE_APPROVAL", "authorization": { "status": "available", "issued_at": "2026-09-04T05:41:23.444Z", "consumed_at": null } }, "replay": null }, { "round": 2, "name": "different-agent", "expected": "REQUIRE_APPROVAL", "expectation": "matched", "fixture": "", "first": { "decision": "REQUIRE_APPROVAL", "authorization": { "status": "available", "issued_at": "2026-09-04T05:41:23.683Z", "consumed_at": null } }, "replay": null }, { "round": 2, "name": "different-task", "expected": "REQUIRE_APPROVAL", "expectation": "matched", "fixture": "", "first": { "decision": "REQUIRE_APPROVAL", "authorization": { "status": "available", "issued_at": "2026-09-04T05:41:23.923Z", "consumed_at": null } }, "replay": null }, { "round": 2, "name": "different-thread", "expected": "REQUIRE_APPROVAL", "expectation": "matched", "fixture": "", "first": { "decision": "REQUIRE_APPROVAL", "authorization": { "status": "available", "issued_at": "2026-09-04T05:41:24.160Z", "consumed_at": null } }, "replay": null }, { "round": 2, "name": "different-project", "expected": "REQUIRE_APPROVAL", "expectation": "matched", "fixture": "", "first": { "decision": "REQUIRE_APPROVAL", "authorization": { "status": "available", "issued_at": "2026-09-04T05:41:24.397Z", "consumed_at": null } }, "replay": null }, { "round": 2, "name": "different-target", "expected": "REQUIRE_APPROVAL", "expectation": "mismatched", "fixture": "", "first": { "decision": "ALLOW", "reason": "operation_approval_consumed", "authorization": { "status": "consumed", "issued_at": "2026-09-04T05:41:24.635Z", "consumed_at": "2026-09-04T05:41:24.848Z", "consumed_by": { "agent_id": "DEV-01", "session_id": "session-1", "task_id": "TASK-1", "thread_key": "thread-1", "role": "DEV" } } }, "replay": { "decision": "THREW", "code": "APPROVAL_ALREADY_CONSUMED", "authorization": { "status": "consumed", "issued_at": "2026-09-04T05:41:24.635Z", "consumed_at": "2026-09-04T05:41:24.848Z", "consumed_by": { "agent_id": "DEV-01", "session_id": "session-1", "task_id": "TASK-1", "thread_key": "thread-1", "role": "DEV" } } } }, { "round": 2, "name": "different-source-channel", "expected": "OBSERVE", "expectation": "not_scored", "fixture": "", "first": { "decision": "REQUIRE_APPROVAL", "authorization": { "status": "available", "issued_at": "2026-09-04T05:41:25.099Z", "consumed_at": null } }, "replay": null }, { "round": 2, "name": "cancelled", "expected": "REQUIRE_APPROVAL", "expectation": "matched", "fixture": "", "first": { "decision": "REQUIRE_APPROVAL", "authorization": { "status": "invalid", "issued_at": null, "consumed_at": null } }, "replay": null } ], "assertion_failures": [ { "name": "delivered-resume", "round": 1, "expected": "ALLOW", "actual": "REQUIRE_APPROVAL" }, { "name": "different-target", "round": 1, "expected": "REQUIRE_APPROVAL", "actual": "ALLOW" }, { "name": "delivered-resume", "round": 2, "expected": "ALLOW", "actual": "REQUIRE_APPROVAL" }, { "name": "different-target", "round": 2, "expected": "REQUIRE_APPROVAL", "actual": "ALLOW" } ], "probe_exit_code": 1, "field_comparisons": [ { "round": 1, "name": "same", "original_call": { "toolName": "shell", "args": { "command": "git push origin codex/research-probe" }, "projectRoot": "", "projectId": "causal-1-kfZrT5", "agentId": "DEV-01", "sessionId": "session-1", "taskId": "TASK-1", "threadKey": "thread-1", "sourceChannel": "codex_app_server" }, "changed_call": { "toolName": "shell", "args": { "command": "git push origin codex/research-probe" }, "projectRoot": "", "projectId": "causal-1-kfZrT5", "agentId": "DEV-01", "sessionId": "session-1", "taskId": "TASK-1", "threadKey": "thread-1", "sourceChannel": "codex_app_server" }, "original_fingerprint": "sha256:c5dd2c4de2f1908e97695f1555c960f2e8d73a06b74e095407fe4184d232a0ca", "changed_fingerprint": "sha256:c5dd2c4de2f1908e97695f1555c960f2e8d73a06b74e095407fe4184d232a0ca", "original_digest": "sha256:2b728613ffaba7047100877002b6815f3e9ccf73ea91cef2cc93e4eec184f933", "changed_digest": "sha256:2b728613ffaba7047100877002b6815f3e9ccf73ea91cef2cc93e4eec184f933", "request_differences": [], "operation": { "kind": "remote_git", "exact_targets": [], "canonical_targets": [], "target_set_stable": true, "recursive": false, "dynamic_or_wildcard": false }, "confidence": { "complete": true, "unresolved_fields": [], "detector_ids": [ "shell.remote_git" ] }, "counterfactual_nested_session_removed_digest_matches": true }, { "round": 1, "name": "branch", "original_call": { "toolName": "shell", "args": { "command": "git push origin codex/research-probe" }, "projectRoot": "", "projectId": "causal-1-kfZrT5", "agentId": "DEV-01", "sessionId": "session-1", "taskId": "TASK-1", "threadKey": "thread-1", "sourceChannel": "codex_app_server" }, "changed_call": { "toolName": "shell", "args": { "command": "git push origin codex/another-target" }, "projectRoot": "", "projectId": "causal-1-kfZrT5", "agentId": "DEV-01", "sessionId": "session-1", "taskId": "TASK-1", "threadKey": "thread-1", "sourceChannel": "codex_app_server" }, "original_fingerprint": "sha256:c5dd2c4de2f1908e97695f1555c960f2e8d73a06b74e095407fe4184d232a0ca", "changed_fingerprint": "sha256:c5dd2c4de2f1908e97695f1555c960f2e8d73a06b74e095407fe4184d232a0ca", "original_digest": "sha256:2b728613ffaba7047100877002b6815f3e9ccf73ea91cef2cc93e4eec184f933", "changed_digest": "sha256:2b728613ffaba7047100877002b6815f3e9ccf73ea91cef2cc93e4eec184f933", "request_differences": [], "operation": { "kind": "remote_git", "exact_targets": [], "canonical_targets": [], "target_set_stable": true, "recursive": false, "dynamic_or_wildcard": false }, "confidence": { "complete": true, "unresolved_fields": [], "detector_ids": [ "shell.remote_git" ] }, "counterfactual_nested_session_removed_digest_matches": true }, { "round": 1, "name": "remote", "original_call": { "toolName": "shell", "args": { "command": "git push origin codex/research-probe" }, "projectRoot": "", "projectId": "causal-1-kfZrT5", "agentId": "DEV-01", "sessionId": "session-1", "taskId": "TASK-1", "threadKey": "thread-1", "sourceChannel": "codex_app_server" }, "changed_call": { "toolName": "shell", "args": { "command": "git push backup codex/research-probe" }, "projectRoot": "", "projectId": "causal-1-kfZrT5", "agentId": "DEV-01", "sessionId": "session-1", "taskId": "TASK-1", "threadKey": "thread-1", "sourceChannel": "codex_app_server" }, "original_fingerprint": "sha256:c5dd2c4de2f1908e97695f1555c960f2e8d73a06b74e095407fe4184d232a0ca", "changed_fingerprint": "sha256:c5dd2c4de2f1908e97695f1555c960f2e8d73a06b74e095407fe4184d232a0ca", "original_digest": "sha256:2b728613ffaba7047100877002b6815f3e9ccf73ea91cef2cc93e4eec184f933", "changed_digest": "sha256:2b728613ffaba7047100877002b6815f3e9ccf73ea91cef2cc93e4eec184f933", "request_differences": [], "operation": { "kind": "remote_git", "exact_targets": [], "canonical_targets": [], "target_set_stable": true, "recursive": false, "dynamic_or_wildcard": false }, "confidence": { "complete": true, "unresolved_fields": [], "detector_ids": [ "shell.remote_git" ] }, "counterfactual_nested_session_removed_digest_matches": true }, { "round": 1, "name": "force", "original_call": { "toolName": "shell", "args": { "command": "git push origin codex/research-probe" }, "projectRoot": "", "projectId": "causal-1-kfZrT5", "agentId": "DEV-01", "sessionId": "session-1", "taskId": "TASK-1", "threadKey": "thread-1", "sourceChannel": "codex_app_server" }, "changed_call": { "toolName": "shell", "args": { "command": "git push --force origin codex/research-probe" }, "projectRoot": "", "projectId": "causal-1-kfZrT5", "agentId": "DEV-01", "sessionId": "session-1", "taskId": "TASK-1", "threadKey": "thread-1", "sourceChannel": "codex_app_server" }, "original_fingerprint": "sha256:c5dd2c4de2f1908e97695f1555c960f2e8d73a06b74e095407fe4184d232a0ca", "changed_fingerprint": "sha256:c5dd2c4de2f1908e97695f1555c960f2e8d73a06b74e095407fe4184d232a0ca", "original_digest": "sha256:2b728613ffaba7047100877002b6815f3e9ccf73ea91cef2cc93e4eec184f933", "changed_digest": "sha256:2b728613ffaba7047100877002b6815f3e9ccf73ea91cef2cc93e4eec184f933", "request_differences": [], "operation": { "kind": "remote_git", "exact_targets": [], "canonical_targets": [], "target_set_stable": true, "recursive": false, "dynamic_or_wildcard": false }, "confidence": { "complete": true, "unresolved_fields": [], "detector_ids": [ "shell.remote_git" ] }, "counterfactual_nested_session_removed_digest_matches": true }, { "round": 1, "name": "delete", "original_call": { "toolName": "shell", "args": { "command": "git push origin codex/research-probe" }, "projectRoot": "", "projectId": "causal-1-kfZrT5", "agentId": "DEV-01", "sessionId": "session-1", "taskId": "TASK-1", "threadKey": "thread-1", "sourceChannel": "codex_app_server" }, "changed_call": { "toolName": "shell", "args": { "command": "git push origin --delete codex/research-probe" }, "projectRoot": "", "projectId": "causal-1-kfZrT5", "agentId": "DEV-01", "sessionId": "session-1", "taskId": "TASK-1", "threadKey": "thread-1", "sourceChannel": "codex_app_server" }, "original_fingerprint": "sha256:c5dd2c4de2f1908e97695f1555c960f2e8d73a06b74e095407fe4184d232a0ca", "changed_fingerprint": "sha256:c5dd2c4de2f1908e97695f1555c960f2e8d73a06b74e095407fe4184d232a0ca", "original_digest": "sha256:2b728613ffaba7047100877002b6815f3e9ccf73ea91cef2cc93e4eec184f933", "changed_digest": "sha256:2b728613ffaba7047100877002b6815f3e9ccf73ea91cef2cc93e4eec184f933", "request_differences": [], "operation": { "kind": "remote_git", "exact_targets": [], "canonical_targets": [], "target_set_stable": true, "recursive": false, "dynamic_or_wildcard": false }, "confidence": { "complete": true, "unresolved_fields": [], "detector_ids": [ "shell.remote_git" ] }, "counterfactual_nested_session_removed_digest_matches": true }, { "round": 1, "name": "new-session", "original_call": { "toolName": "shell", "args": { "command": "git push origin codex/research-probe" }, "projectRoot": "", "projectId": "causal-1-kfZrT5", "agentId": "DEV-01", "sessionId": "session-1", "taskId": "TASK-1", "threadKey": "thread-1", "sourceChannel": "codex_app_server" }, "changed_call": { "toolName": "shell", "args": { "command": "git push origin codex/research-probe" }, "projectRoot": "", "projectId": "causal-1-kfZrT5", "agentId": "DEV-01", "sessionId": "session-2", "taskId": "TASK-1", "threadKey": "thread-1", "sourceChannel": "codex_app_server" }, "original_fingerprint": "sha256:c5dd2c4de2f1908e97695f1555c960f2e8d73a06b74e095407fe4184d232a0ca", "changed_fingerprint": "sha256:c5dd2c4de2f1908e97695f1555c960f2e8d73a06b74e095407fe4184d232a0ca", "original_digest": "sha256:2b728613ffaba7047100877002b6815f3e9ccf73ea91cef2cc93e4eec184f933", "changed_digest": "sha256:32c54f086d9f5e1fb154e51fabe30427c03c1343a2b7dae6c0786b50776d83bb", "request_differences": [ { "path": "subject.session_id", "before": "session-1", "after": "session-2" }, { "path": "snapshot.operation_facts.subject.session_id", "before": "session-1", "after": "session-2" } ], "operation": { "kind": "remote_git", "exact_targets": [], "canonical_targets": [], "target_set_stable": true, "recursive": false, "dynamic_or_wildcard": false }, "confidence": { "complete": true, "unresolved_fields": [], "detector_ids": [ "shell.remote_git" ] }, "counterfactual_nested_session_removed_digest_matches": true }, { "round": 1, "name": "other-task", "original_call": { "toolName": "shell", "args": { "command": "git push origin codex/research-probe" }, "projectRoot": "", "projectId": "causal-1-kfZrT5", "agentId": "DEV-01", "sessionId": "session-1", "taskId": "TASK-1", "threadKey": "thread-1", "sourceChannel": "codex_app_server" }, "changed_call": { "toolName": "shell", "args": { "command": "git push origin codex/research-probe" }, "projectRoot": "", "projectId": "causal-1-kfZrT5", "agentId": "DEV-01", "sessionId": "session-1", "taskId": "TASK-2", "threadKey": "thread-1", "sourceChannel": "codex_app_server" }, "original_fingerprint": "sha256:c5dd2c4de2f1908e97695f1555c960f2e8d73a06b74e095407fe4184d232a0ca", "changed_fingerprint": "sha256:d9a1ae0147927bee7ebab828b8eec2a161c497fb34f52dae9e85ab18b1e94b77", "original_digest": "sha256:2b728613ffaba7047100877002b6815f3e9ccf73ea91cef2cc93e4eec184f933", "changed_digest": "sha256:7ef2353c36e94bbabb2be014a1fc44652bec3730b455662a1bbea0c480864d56", "request_differences": [ { "path": "subject.task_id", "before": "TASK-1", "after": "TASK-2" }, { "path": "resource.scope.task_scope_digest", "before": "sha256:4724c8a4dd31235c39b3333ff57b6fa7efb910809d7ecc35c98830c39ecf61b4", "after": "sha256:846c54b1d72984cae5ddc53fa61b3282f0a274c8c459c785203ee623a069ae9f" }, { "path": "snapshot.operation_fingerprint", "before": "sha256:c5dd2c4de2f1908e97695f1555c960f2e8d73a06b74e095407fe4184d232a0ca", "after": "sha256:d9a1ae0147927bee7ebab828b8eec2a161c497fb34f52dae9e85ab18b1e94b77" }, { "path": "snapshot.operation_facts.context.task_id", "before": "TASK-1", "after": "TASK-2" }, { "path": "snapshot.operation_facts.context.task_scope_digest", "before": "sha256:4724c8a4dd31235c39b3333ff57b6fa7efb910809d7ecc35c98830c39ecf61b4", "after": "sha256:846c54b1d72984cae5ddc53fa61b3282f0a274c8c459c785203ee623a069ae9f" } ], "operation": { "kind": "remote_git", "exact_targets": [], "canonical_targets": [], "target_set_stable": true, "recursive": false, "dynamic_or_wildcard": false }, "confidence": { "complete": true, "unresolved_fields": [], "detector_ids": [ "shell.remote_git" ] }, "counterfactual_nested_session_removed_digest_matches": false }, { "round": 2, "name": "same", "original_call": { "toolName": "shell", "args": { "command": "git push origin codex/research-probe" }, "projectRoot": "", "projectId": "causal-2-OJHCI2", "agentId": "DEV-01", "sessionId": "session-1", "taskId": "TASK-1", "threadKey": "thread-1", "sourceChannel": "codex_app_server" }, "changed_call": { "toolName": "shell", "args": { "command": "git push origin codex/research-probe" }, "projectRoot": "", "projectId": "causal-2-OJHCI2", "agentId": "DEV-01", "sessionId": "session-1", "taskId": "TASK-1", "threadKey": "thread-1", "sourceChannel": "codex_app_server" }, "original_fingerprint": "sha256:af30e3d1c21a9e9eae96f63d1f654c8c5a3861e956e90dc57cd4c1cf952c943f", "changed_fingerprint": "sha256:af30e3d1c21a9e9eae96f63d1f654c8c5a3861e956e90dc57cd4c1cf952c943f", "original_digest": "sha256:2d0062132552dd68ee874e6cb87f533d38810a5bc66b9fc1c8ef220b80ea57f3", "changed_digest": "sha256:2d0062132552dd68ee874e6cb87f533d38810a5bc66b9fc1c8ef220b80ea57f3", "request_differences": [], "operation": { "kind": "remote_git", "exact_targets": [], "canonical_targets": [], "target_set_stable": true, "recursive": false, "dynamic_or_wildcard": false }, "confidence": { "complete": true, "unresolved_fields": [], "detector_ids": [ "shell.remote_git" ] }, "counterfactual_nested_session_removed_digest_matches": true }, { "round": 2, "name": "branch", "original_call": { "toolName": "shell", "args": { "command": "git push origin codex/research-probe" }, "projectRoot": "", "projectId": "causal-2-OJHCI2", "agentId": "DEV-01", "sessionId": "session-1", "taskId": "TASK-1", "threadKey": "thread-1", "sourceChannel": "codex_app_server" }, "changed_call": { "toolName": "shell", "args": { "command": "git push origin codex/another-target" }, "projectRoot": "", "projectId": "causal-2-OJHCI2", "agentId": "DEV-01", "sessionId": "session-1", "taskId": "TASK-1", "threadKey": "thread-1", "sourceChannel": "codex_app_server" }, "original_fingerprint": "sha256:af30e3d1c21a9e9eae96f63d1f654c8c5a3861e956e90dc57cd4c1cf952c943f", "changed_fingerprint": "sha256:af30e3d1c21a9e9eae96f63d1f654c8c5a3861e956e90dc57cd4c1cf952c943f", "original_digest": "sha256:2d0062132552dd68ee874e6cb87f533d38810a5bc66b9fc1c8ef220b80ea57f3", "changed_digest": "sha256:2d0062132552dd68ee874e6cb87f533d38810a5bc66b9fc1c8ef220b80ea57f3", "request_differences": [], "operation": { "kind": "remote_git", "exact_targets": [], "canonical_targets": [], "target_set_stable": true, "recursive": false, "dynamic_or_wildcard": false }, "confidence": { "complete": true, "unresolved_fields": [], "detector_ids": [ "shell.remote_git" ] }, "counterfactual_nested_session_removed_digest_matches": true }, { "round": 2, "name": "remote", "original_call": { "toolName": "shell", "args": { "command": "git push origin codex/research-probe" }, "projectRoot": "", "projectId": "causal-2-OJHCI2", "agentId": "DEV-01", "sessionId": "session-1", "taskId": "TASK-1", "threadKey": "thread-1", "sourceChannel": "codex_app_server" }, "changed_call": { "toolName": "shell", "args": { "command": "git push backup codex/research-probe" }, "projectRoot": "", "projectId": "causal-2-OJHCI2", "agentId": "DEV-01", "sessionId": "session-1", "taskId": "TASK-1", "threadKey": "thread-1", "sourceChannel": "codex_app_server" }, "original_fingerprint": "sha256:af30e3d1c21a9e9eae96f63d1f654c8c5a3861e956e90dc57cd4c1cf952c943f", "changed_fingerprint": "sha256:af30e3d1c21a9e9eae96f63d1f654c8c5a3861e956e90dc57cd4c1cf952c943f", "original_digest": "sha256:2d0062132552dd68ee874e6cb87f533d38810a5bc66b9fc1c8ef220b80ea57f3", "changed_digest": "sha256:2d0062132552dd68ee874e6cb87f533d38810a5bc66b9fc1c8ef220b80ea57f3", "request_differences": [], "operation": { "kind": "remote_git", "exact_targets": [], "canonical_targets": [], "target_set_stable": true, "recursive": false, "dynamic_or_wildcard": false }, "confidence": { "complete": true, "unresolved_fields": [], "detector_ids": [ "shell.remote_git" ] }, "counterfactual_nested_session_removed_digest_matches": true }, { "round": 2, "name": "force", "original_call": { "toolName": "shell", "args": { "command": "git push origin codex/research-probe" }, "projectRoot": "", "projectId": "causal-2-OJHCI2", "agentId": "DEV-01", "sessionId": "session-1", "taskId": "TASK-1", "threadKey": "thread-1", "sourceChannel": "codex_app_server" }, "changed_call": { "toolName": "shell", "args": { "command": "git push --force origin codex/research-probe" }, "projectRoot": "", "projectId": "causal-2-OJHCI2", "agentId": "DEV-01", "sessionId": "session-1", "taskId": "TASK-1", "threadKey": "thread-1", "sourceChannel": "codex_app_server" }, "original_fingerprint": "sha256:af30e3d1c21a9e9eae96f63d1f654c8c5a3861e956e90dc57cd4c1cf952c943f", "changed_fingerprint": "sha256:af30e3d1c21a9e9eae96f63d1f654c8c5a3861e956e90dc57cd4c1cf952c943f", "original_digest": "sha256:2d0062132552dd68ee874e6cb87f533d38810a5bc66b9fc1c8ef220b80ea57f3", "changed_digest": "sha256:2d0062132552dd68ee874e6cb87f533d38810a5bc66b9fc1c8ef220b80ea57f3", "request_differences": [], "operation": { "kind": "remote_git", "exact_targets": [], "canonical_targets": [], "target_set_stable": true, "recursive": false, "dynamic_or_wildcard": false }, "confidence": { "complete": true, "unresolved_fields": [], "detector_ids": [ "shell.remote_git" ] }, "counterfactual_nested_session_removed_digest_matches": true }, { "round": 2, "name": "delete", "original_call": { "toolName": "shell", "args": { "command": "git push origin codex/research-probe" }, "projectRoot": "", "projectId": "causal-2-OJHCI2", "agentId": "DEV-01", "sessionId": "session-1", "taskId": "TASK-1", "threadKey": "thread-1", "sourceChannel": "codex_app_server" }, "changed_call": { "toolName": "shell", "args": { "command": "git push origin --delete codex/research-probe" }, "projectRoot": "", "projectId": "causal-2-OJHCI2", "agentId": "DEV-01", "sessionId": "session-1", "taskId": "TASK-1", "threadKey": "thread-1", "sourceChannel": "codex_app_server" }, "original_fingerprint": "sha256:af30e3d1c21a9e9eae96f63d1f654c8c5a3861e956e90dc57cd4c1cf952c943f", "changed_fingerprint": "sha256:af30e3d1c21a9e9eae96f63d1f654c8c5a3861e956e90dc57cd4c1cf952c943f", "original_digest": "sha256:2d0062132552dd68ee874e6cb87f533d38810a5bc66b9fc1c8ef220b80ea57f3", "changed_digest": "sha256:2d0062132552dd68ee874e6cb87f533d38810a5bc66b9fc1c8ef220b80ea57f3", "request_differences": [], "operation": { "kind": "remote_git", "exact_targets": [], "canonical_targets": [], "target_set_stable": true, "recursive": false, "dynamic_or_wildcard": false }, "confidence": { "complete": true, "unresolved_fields": [], "detector_ids": [ "shell.remote_git" ] }, "counterfactual_nested_session_removed_digest_matches": true }, { "round": 2, "name": "new-session", "original_call": { "toolName": "shell", "args": { "command": "git push origin codex/research-probe" }, "projectRoot": "", "projectId": "causal-2-OJHCI2", "agentId": "DEV-01", "sessionId": "session-1", "taskId": "TASK-1", "threadKey": "thread-1", "sourceChannel": "codex_app_server" }, "changed_call": { "toolName": "shell", "args": { "command": "git push origin codex/research-probe" }, "projectRoot": "", "projectId": "causal-2-OJHCI2", "agentId": "DEV-01", "sessionId": "session-2", "taskId": "TASK-1", "threadKey": "thread-1", "sourceChannel": "codex_app_server" }, "original_fingerprint": "sha256:af30e3d1c21a9e9eae96f63d1f654c8c5a3861e956e90dc57cd4c1cf952c943f", "changed_fingerprint": "sha256:af30e3d1c21a9e9eae96f63d1f654c8c5a3861e956e90dc57cd4c1cf952c943f", "original_digest": "sha256:2d0062132552dd68ee874e6cb87f533d38810a5bc66b9fc1c8ef220b80ea57f3", "changed_digest": "sha256:3c63fb1b97c17c683b795350ac1b41b57c633f50bb315d809ad278a284ab51aa", "request_differences": [ { "path": "subject.session_id", "before": "session-1", "after": "session-2" }, { "path": "snapshot.operation_facts.subject.session_id", "before": "session-1", "after": "session-2" } ], "operation": { "kind": "remote_git", "exact_targets": [], "canonical_targets": [], "target_set_stable": true, "recursive": false, "dynamic_or_wildcard": false }, "confidence": { "complete": true, "unresolved_fields": [], "detector_ids": [ "shell.remote_git" ] }, "counterfactual_nested_session_removed_digest_matches": true }, { "round": 2, "name": "other-task", "original_call": { "toolName": "shell", "args": { "command": "git push origin codex/research-probe" }, "projectRoot": "", "projectId": "causal-2-OJHCI2", "agentId": "DEV-01", "sessionId": "session-1", "taskId": "TASK-1", "threadKey": "thread-1", "sourceChannel": "codex_app_server" }, "changed_call": { "toolName": "shell", "args": { "command": "git push origin codex/research-probe" }, "projectRoot": "", "projectId": "causal-2-OJHCI2", "agentId": "DEV-01", "sessionId": "session-1", "taskId": "TASK-2", "threadKey": "thread-1", "sourceChannel": "codex_app_server" }, "original_fingerprint": "sha256:af30e3d1c21a9e9eae96f63d1f654c8c5a3861e956e90dc57cd4c1cf952c943f", "changed_fingerprint": "sha256:2abc9e04a723e89ddcb63ba2253dcc2b40c10c19e581922c86ce2572a2aebb50", "original_digest": "sha256:2d0062132552dd68ee874e6cb87f533d38810a5bc66b9fc1c8ef220b80ea57f3", "changed_digest": "sha256:d6fc864332429fecb1774229936a697be1ab9802f437fbcaef7dca7b6ce47685", "request_differences": [ { "path": "subject.task_id", "before": "TASK-1", "after": "TASK-2" }, { "path": "resource.scope.task_scope_digest", "before": "sha256:5c3ae71750b6fdb25b1f552f3b80c6b6f85654d37db19ffcdabe78f7503182cf", "after": "sha256:08dd08868a0744357f8b1a42b3b74b0a2ca7b84e73641f528cf1803c4b4cd788" }, { "path": "snapshot.operation_fingerprint", "before": "sha256:af30e3d1c21a9e9eae96f63d1f654c8c5a3861e956e90dc57cd4c1cf952c943f", "after": "sha256:2abc9e04a723e89ddcb63ba2253dcc2b40c10c19e581922c86ce2572a2aebb50" }, { "path": "snapshot.operation_facts.context.task_id", "before": "TASK-1", "after": "TASK-2" }, { "path": "snapshot.operation_facts.context.task_scope_digest", "before": "sha256:5c3ae71750b6fdb25b1f552f3b80c6b6f85654d37db19ffcdabe78f7503182cf", "after": "sha256:08dd08868a0744357f8b1a42b3b74b0a2ca7b84e73641f528cf1803c4b4cd788" } ], "operation": { "kind": "remote_git", "exact_targets": [], "canonical_targets": [], "target_set_stable": true, "recursive": false, "dynamic_or_wildcard": false }, "confidence": { "complete": true, "unresolved_fields": [], "detector_ids": [ "shell.remote_git" ] }, "counterfactual_nested_session_removed_digest_matches": false } ], "codex_resolution": [ { "round": 1, "name": "same-command", "approved_command": "git push origin codex/research-probe", "requested_command": "git push origin codex/research-probe", "fixture": "", "actual": { "allow": true, "code": "ALLOW", "reason": "no frozen negative-list predicate matched" }, "before_authorization": { "status": "available", "issued_at": "2026-09-04T06:05:11.990Z", "consumed_at": null }, "after_authorization": { "status": "consumed", "issued_at": "2026-09-04T06:05:11.990Z", "consumed_at": "2026-09-04T06:05:11.997Z", "consumed_by": { "agent_id": "DEV-01", "session_id": "session-1", "task_id": "TASK-1", "thread_key": "thread-1", "role": "DEV" } } }, { "round": 1, "name": "changed-branch", "approved_command": "git push origin codex/research-probe", "requested_command": "git push origin codex/another-target", "fixture": "", "actual": { "allow": true, "code": "ALLOW", "reason": "no frozen negative-list predicate matched" }, "before_authorization": { "status": "available", "issued_at": "2026-09-04T06:05:12.009Z", "consumed_at": null }, "after_authorization": { "status": "consumed", "issued_at": "2026-09-04T06:05:12.009Z", "consumed_at": "2026-09-04T06:05:12.015Z", "consumed_by": { "agent_id": "DEV-01", "session_id": "session-1", "task_id": "TASK-1", "thread_key": "thread-1", "role": "DEV" } } }, { "round": 2, "name": "same-command", "approved_command": "git push origin codex/research-probe", "requested_command": "git push origin codex/research-probe", "fixture": "", "actual": { "allow": true, "code": "ALLOW", "reason": "no frozen negative-list predicate matched" }, "before_authorization": { "status": "available", "issued_at": "2026-09-04T06:05:12.027Z", "consumed_at": null }, "after_authorization": { "status": "consumed", "issued_at": "2026-09-04T06:05:12.027Z", "consumed_at": "2026-09-04T06:05:12.032Z", "consumed_by": { "agent_id": "DEV-01", "session_id": "session-1", "task_id": "TASK-1", "thread_key": "thread-1", "role": "DEV" } } }, { "round": 2, "name": "changed-branch", "approved_command": "git push origin codex/research-probe", "requested_command": "git push origin codex/another-target", "fixture": "", "actual": { "allow": true, "code": "ALLOW", "reason": "no frozen negative-list predicate matched" }, "before_authorization": { "status": "available", "issued_at": "2026-09-04T06:05:12.043Z", "consumed_at": null }, "after_authorization": { "status": "consumed", "issued_at": "2026-09-04T06:05:12.043Z", "consumed_at": "2026-09-04T06:05:12.049Z", "consumed_by": { "agent_id": "DEV-01", "session_id": "session-1", "task_id": "TASK-1", "thread_key": "thread-1", "role": "DEV" } } } ], "lineage_controls": [ { "round": 1, "name": "matching", "fixture": "", "expected": "accepted", "actual": { "task_id": "TASK-20260904-003", "content_digest": "6844b4c8f2abbdf9273fa9fd8e9a8be58c65e78d2d4f9c0ff2a9d83a0ad25df0", "authored_snapshot": { "schema_version": 1, "frontmatter": { "depends_on": [ "TASK-20260904-001" ], "parent": "TASK-20260904-001", "protocol": "fcop", "recipient": "QA", "sender": "PM", "thread_key": "thread-1" }, "body": "# Same task text\nIdentical description and expected output." }, "capability_matrix": [ { "task_step": "# Same task text", "execution_role": "UNASSIGNED", "required_capability": "task.execution", "available_tools": [], "current_policy": "allow", "risk": "low", "conclusion": "executable", "suggested_fix": "none" } ], "feasibility": { "decision": "EXECUTABLE", "reason_codes": [ "ACCEPTANCE_UNVERIFIABLE" ], "source": "task_spec_admission" }, "decision": "accepted", "code": "TASK_SPEC_VALID", "blocking_findings": [], "advisory_findings": [ { "id": "ACCEPTANCE_UNVERIFIABLE", "field": "task_body", "message": "downstream task has no observable completion evidence or acceptance contract", "suggested_fix": "add measurable completion conditions, required evidence, and the formal REPORT route before dispatch", "finding_id": "ACCEPTANCE_UNVERIFIABLE", "category": "acceptance_gate", "severity": "medium", "section": "Same task text", "line_start": 10, "line_end": 10, "original_excerpt": "# Same task text", "impact": "This is context for PM and does not prevent task execution.", "required_capability": "task_body", "current_support": "task remains executable; the exact operation boundary evaluates concrete effects", "suggested_replacement": "add measurable completion conditions, required evidence, and the formal REPORT route before dispatch", "can_auto_fix": false, "decision_owner": "PM", "recommended_decision": "advisory", "enforcement": "advisory" } ] } }, { "round": 1, "name": "wrong-root", "fixture": "", "expected": "mechanical_error", "actual": { "task_id": "TASK-20260904-003", "content_digest": "6844b4c8f2abbdf9273fa9fd8e9a8be58c65e78d2d4f9c0ff2a9d83a0ad25df0", "authored_snapshot": { "schema_version": 1, "frontmatter": { "depends_on": [ "TASK-20260904-001" ], "parent": "TASK-20260904-001", "protocol": "fcop", "recipient": "QA", "sender": "PM", "thread_key": "thread-1" }, "body": "# Same task text\nIdentical description and expected output." }, "capability_matrix": [ { "task_step": "# Same task text", "execution_role": "UNASSIGNED", "required_capability": "task.execution", "available_tools": [], "current_policy": "allow", "risk": "low", "conclusion": "executable", "suggested_fix": "none" } ], "feasibility": { "decision": "NEEDS_REWRITE", "reason_codes": [ "ACCEPTANCE_UNVERIFIABLE" ], "source": "task_spec_admission" }, "decision": "mechanical_error", "code": "TASK_SPEC_INVALID", "blocking_findings": [ { "id": "PARENT_INVALID", "field": "root_task_id", "message": "child task root_task_id does not match its parent's canonical root", "evidence": [ "TASK-20260904-999", "TASK-20260904-000" ], "suggested_fix": "inherit root_task_id from the parent task; do not start a new root inside an existing task tree", "finding_id": "PARENT_INVALID", "category": "lifecycle", "severity": "medium", "section": "frontmatter", "line_start": 3, "line_end": 3, "original_excerpt": "root_task_id: TASK-20260904-999", "impact": "The task wording may benefit from clarification; PM retains the execution decision.", "required_capability": "root_task_id", "current_support": "canonical identity or transaction integrity requires repair", "suggested_replacement": "inherit root_task_id from the parent task; do not start a new root inside an existing task tree", "can_auto_fix": false, "decision_owner": "TASK_AUTHOR", "recommended_decision": "needs_revision", "enforcement": "mechanical_error" } ], "advisory_findings": [ { "id": "ACCEPTANCE_UNVERIFIABLE", "field": "task_body", "message": "downstream task has no observable completion evidence or acceptance contract", "suggested_fix": "add measurable completion conditions, required evidence, and the formal REPORT route before dispatch", "finding_id": "ACCEPTANCE_UNVERIFIABLE", "category": "acceptance_gate", "severity": "medium", "section": "Same task text", "line_start": 10, "line_end": 10, "original_excerpt": "# Same task text", "impact": "This is context for PM and does not prevent task execution.", "required_capability": "task_body", "current_support": "task remains executable; the exact operation boundary evaluates concrete effects", "suggested_replacement": "add measurable completion conditions, required evidence, and the formal REPORT route before dispatch", "can_auto_fix": false, "decision_owner": "PM", "recommended_decision": "advisory", "enforcement": "advisory" } ] } }, { "round": 1, "name": "wrong-thread", "fixture": "", "expected": "mechanical_error", "actual": { "task_id": "TASK-20260904-003", "content_digest": "601643a977cca883cb7f3a32ed49be725274d79cb25feeba5387e1a2f0b553f8", "authored_snapshot": { "schema_version": 1, "frontmatter": { "depends_on": [ "TASK-20260904-001" ], "parent": "TASK-20260904-001", "protocol": "fcop", "recipient": "QA", "sender": "PM", "thread_key": "thread-2" }, "body": "# Same task text\nIdentical description and expected output." }, "capability_matrix": [ { "task_step": "# Same task text", "execution_role": "UNASSIGNED", "required_capability": "task.execution", "available_tools": [], "current_policy": "allow", "risk": "low", "conclusion": "executable", "suggested_fix": "none" } ], "feasibility": { "decision": "NEEDS_REWRITE", "reason_codes": [ "ACCEPTANCE_UNVERIFIABLE" ], "source": "task_spec_admission" }, "decision": "mechanical_error", "code": "TASK_SPEC_INVALID", "blocking_findings": [ { "id": "PARENT_INVALID", "field": "thread_key", "message": "child task canonical thread identity does not match its parent", "evidence": [ "thread-2", "thread-1" ], "finding_id": "PARENT_INVALID", "category": "lifecycle", "severity": "medium", "section": "frontmatter", "line_start": 7, "line_end": 7, "original_excerpt": "thread_key: thread-2", "impact": "The task wording may benefit from clarification; PM retains the execution decision.", "required_capability": "thread_key", "current_support": "canonical identity or transaction integrity requires repair", "suggested_fix": "revise the task specification so the requirement has one executable interpretation", "suggested_replacement": "revise the task specification so the requirement has one executable interpretation", "can_auto_fix": false, "decision_owner": "TASK_AUTHOR", "recommended_decision": "needs_revision", "enforcement": "mechanical_error" } ], "advisory_findings": [ { "id": "ACCEPTANCE_UNVERIFIABLE", "field": "task_body", "message": "downstream task has no observable completion evidence or acceptance contract", "suggested_fix": "add measurable completion conditions, required evidence, and the formal REPORT route before dispatch", "finding_id": "ACCEPTANCE_UNVERIFIABLE", "category": "acceptance_gate", "severity": "medium", "section": "Same task text", "line_start": 10, "line_end": 10, "original_excerpt": "# Same task text", "impact": "This is context for PM and does not prevent task execution.", "required_capability": "task_body", "current_support": "task remains executable; the exact operation boundary evaluates concrete effects", "suggested_replacement": "add measurable completion conditions, required evidence, and the formal REPORT route before dispatch", "can_auto_fix": false, "decision_owner": "PM", "recommended_decision": "advisory", "enforcement": "advisory" } ] } }, { "round": 1, "name": "missing-parent", "fixture": "", "expected": "mechanical_error", "actual": { "task_id": "TASK-20260904-003", "content_digest": "d0fa4fdde695ea693bcafd2331b89bb2fecf7874100118830fb73bfaea0ed1fa", "authored_snapshot": { "schema_version": 1, "frontmatter": { "depends_on": [ "TASK-20260904-001" ], "parent": "TASK-20260904-999", "protocol": "fcop", "recipient": "QA", "sender": "PM", "thread_key": "thread-1" }, "body": "# Same task text\nIdentical description and expected output." }, "capability_matrix": [ { "task_step": "# Same task text", "execution_role": "UNASSIGNED", "required_capability": "task.execution", "available_tools": [], "current_policy": "allow", "risk": "low", "conclusion": "executable", "suggested_fix": "none" } ], "feasibility": { "decision": "NEEDS_REWRITE", "reason_codes": [ "ACCEPTANCE_UNVERIFIABLE" ], "source": "task_spec_admission" }, "decision": "mechanical_error", "code": "TASK_SPEC_INVALID", "blocking_findings": [ { "id": "PARENT_INVALID", "field": "parent", "message": "parent task does not exist", "evidence": [ "TASK-20260904-999" ], "finding_id": "PARENT_INVALID", "category": "lifecycle", "severity": "medium", "section": "frontmatter", "line_start": 6, "line_end": 6, "original_excerpt": "parent: TASK-20260904-999", "impact": "The task wording may benefit from clarification; PM retains the execution decision.", "required_capability": "parent", "current_support": "canonical identity or transaction integrity requires repair", "suggested_fix": "revise the task specification so the requirement has one executable interpretation", "suggested_replacement": "revise the task specification so the requirement has one executable interpretation", "can_auto_fix": false, "decision_owner": "TASK_AUTHOR", "recommended_decision": "needs_revision", "enforcement": "mechanical_error" } ], "advisory_findings": [ { "id": "ACCEPTANCE_UNVERIFIABLE", "field": "task_body", "message": "downstream task has no observable completion evidence or acceptance contract", "suggested_fix": "add measurable completion conditions, required evidence, and the formal REPORT route before dispatch", "finding_id": "ACCEPTANCE_UNVERIFIABLE", "category": "acceptance_gate", "severity": "medium", "section": "Same task text", "line_start": 10, "line_end": 10, "original_excerpt": "# Same task text", "impact": "This is context for PM and does not prevent task execution.", "required_capability": "task_body", "current_support": "task remains executable; the exact operation boundary evaluates concrete effects", "suggested_replacement": "add measurable completion conditions, required evidence, and the formal REPORT route before dispatch", "can_auto_fix": false, "decision_owner": "PM", "recommended_decision": "advisory", "enforcement": "advisory" } ] } }, { "round": 1, "name": "same-text-other-done", "body_sha256": "cadc35ef2cf2670ad41bc0f368ee2ea13e190621d1c6d8c6302362386e10a1db", "distinct_task_ids": [ "TASK-20260904-001", "TASK-20260904-002" ], "expected": "waiting_dependency", "actual": { "disposition": "waiting_dependency", "decision_owner": "PM", "reason": "waiting_dependency", "detail": "waiting for TASK-20260904-001 lifecycle done (PM approved)", "waitingOn": "TASK-20260904-001" } }, { "round": 1, "name": "same-text-target-done", "body_sha256": "cadc35ef2cf2670ad41bc0f368ee2ea13e190621d1c6d8c6302362386e10a1db", "distinct_task_ids": [ "TASK-20260904-001", "TASK-20260904-002" ], "expected": "neutral", "actual": { "disposition": "neutral", "decision_owner": "AGENT", "reason": "runnable" } }, { "round": 2, "name": "matching", "fixture": "", "expected": "accepted", "actual": { "task_id": "TASK-20260904-003", "content_digest": "6844b4c8f2abbdf9273fa9fd8e9a8be58c65e78d2d4f9c0ff2a9d83a0ad25df0", "authored_snapshot": { "schema_version": 1, "frontmatter": { "depends_on": [ "TASK-20260904-001" ], "parent": "TASK-20260904-001", "protocol": "fcop", "recipient": "QA", "sender": "PM", "thread_key": "thread-1" }, "body": "# Same task text\nIdentical description and expected output." }, "capability_matrix": [ { "task_step": "# Same task text", "execution_role": "UNASSIGNED", "required_capability": "task.execution", "available_tools": [], "current_policy": "allow", "risk": "low", "conclusion": "executable", "suggested_fix": "none" } ], "feasibility": { "decision": "EXECUTABLE", "reason_codes": [ "ACCEPTANCE_UNVERIFIABLE" ], "source": "task_spec_admission" }, "decision": "accepted", "code": "TASK_SPEC_VALID", "blocking_findings": [], "advisory_findings": [ { "id": "ACCEPTANCE_UNVERIFIABLE", "field": "task_body", "message": "downstream task has no observable completion evidence or acceptance contract", "suggested_fix": "add measurable completion conditions, required evidence, and the formal REPORT route before dispatch", "finding_id": "ACCEPTANCE_UNVERIFIABLE", "category": "acceptance_gate", "severity": "medium", "section": "Same task text", "line_start": 10, "line_end": 10, "original_excerpt": "# Same task text", "impact": "This is context for PM and does not prevent task execution.", "required_capability": "task_body", "current_support": "task remains executable; the exact operation boundary evaluates concrete effects", "suggested_replacement": "add measurable completion conditions, required evidence, and the formal REPORT route before dispatch", "can_auto_fix": false, "decision_owner": "PM", "recommended_decision": "advisory", "enforcement": "advisory" } ] } }, { "round": 2, "name": "wrong-root", "fixture": "", "expected": "mechanical_error", "actual": { "task_id": "TASK-20260904-003", "content_digest": "6844b4c8f2abbdf9273fa9fd8e9a8be58c65e78d2d4f9c0ff2a9d83a0ad25df0", "authored_snapshot": { "schema_version": 1, "frontmatter": { "depends_on": [ "TASK-20260904-001" ], "parent": "TASK-20260904-001", "protocol": "fcop", "recipient": "QA", "sender": "PM", "thread_key": "thread-1" }, "body": "# Same task text\nIdentical description and expected output." }, "capability_matrix": [ { "task_step": "# Same task text", "execution_role": "UNASSIGNED", "required_capability": "task.execution", "available_tools": [], "current_policy": "allow", "risk": "low", "conclusion": "executable", "suggested_fix": "none" } ], "feasibility": { "decision": "NEEDS_REWRITE", "reason_codes": [ "ACCEPTANCE_UNVERIFIABLE" ], "source": "task_spec_admission" }, "decision": "mechanical_error", "code": "TASK_SPEC_INVALID", "blocking_findings": [ { "id": "PARENT_INVALID", "field": "root_task_id", "message": "child task root_task_id does not match its parent's canonical root", "evidence": [ "TASK-20260904-999", "TASK-20260904-000" ], "suggested_fix": "inherit root_task_id from the parent task; do not start a new root inside an existing task tree", "finding_id": "PARENT_INVALID", "category": "lifecycle", "severity": "medium", "section": "frontmatter", "line_start": 3, "line_end": 3, "original_excerpt": "root_task_id: TASK-20260904-999", "impact": "The task wording may benefit from clarification; PM retains the execution decision.", "required_capability": "root_task_id", "current_support": "canonical identity or transaction integrity requires repair", "suggested_replacement": "inherit root_task_id from the parent task; do not start a new root inside an existing task tree", "can_auto_fix": false, "decision_owner": "TASK_AUTHOR", "recommended_decision": "needs_revision", "enforcement": "mechanical_error" } ], "advisory_findings": [ { "id": "ACCEPTANCE_UNVERIFIABLE", "field": "task_body", "message": "downstream task has no observable completion evidence or acceptance contract", "suggested_fix": "add measurable completion conditions, required evidence, and the formal REPORT route before dispatch", "finding_id": "ACCEPTANCE_UNVERIFIABLE", "category": "acceptance_gate", "severity": "medium", "section": "Same task text", "line_start": 10, "line_end": 10, "original_excerpt": "# Same task text", "impact": "This is context for PM and does not prevent task execution.", "required_capability": "task_body", "current_support": "task remains executable; the exact operation boundary evaluates concrete effects", "suggested_replacement": "add measurable completion conditions, required evidence, and the formal REPORT route before dispatch", "can_auto_fix": false, "decision_owner": "PM", "recommended_decision": "advisory", "enforcement": "advisory" } ] } }, { "round": 2, "name": "wrong-thread", "fixture": "", "expected": "mechanical_error", "actual": { "task_id": "TASK-20260904-003", "content_digest": "601643a977cca883cb7f3a32ed49be725274d79cb25feeba5387e1a2f0b553f8", "authored_snapshot": { "schema_version": 1, "frontmatter": { "depends_on": [ "TASK-20260904-001" ], "parent": "TASK-20260904-001", "protocol": "fcop", "recipient": "QA", "sender": "PM", "thread_key": "thread-2" }, "body": "# Same task text\nIdentical description and expected output." }, "capability_matrix": [ { "task_step": "# Same task text", "execution_role": "UNASSIGNED", "required_capability": "task.execution", "available_tools": [], "current_policy": "allow", "risk": "low", "conclusion": "executable", "suggested_fix": "none" } ], "feasibility": { "decision": "NEEDS_REWRITE", "reason_codes": [ "ACCEPTANCE_UNVERIFIABLE" ], "source": "task_spec_admission" }, "decision": "mechanical_error", "code": "TASK_SPEC_INVALID", "blocking_findings": [ { "id": "PARENT_INVALID", "field": "thread_key", "message": "child task canonical thread identity does not match its parent", "evidence": [ "thread-2", "thread-1" ], "finding_id": "PARENT_INVALID", "category": "lifecycle", "severity": "medium", "section": "frontmatter", "line_start": 7, "line_end": 7, "original_excerpt": "thread_key: thread-2", "impact": "The task wording may benefit from clarification; PM retains the execution decision.", "required_capability": "thread_key", "current_support": "canonical identity or transaction integrity requires repair", "suggested_fix": "revise the task specification so the requirement has one executable interpretation", "suggested_replacement": "revise the task specification so the requirement has one executable interpretation", "can_auto_fix": false, "decision_owner": "TASK_AUTHOR", "recommended_decision": "needs_revision", "enforcement": "mechanical_error" } ], "advisory_findings": [ { "id": "ACCEPTANCE_UNVERIFIABLE", "field": "task_body", "message": "downstream task has no observable completion evidence or acceptance contract", "suggested_fix": "add measurable completion conditions, required evidence, and the formal REPORT route before dispatch", "finding_id": "ACCEPTANCE_UNVERIFIABLE", "category": "acceptance_gate", "severity": "medium", "section": "Same task text", "line_start": 10, "line_end": 10, "original_excerpt": "# Same task text", "impact": "This is context for PM and does not prevent task execution.", "required_capability": "task_body", "current_support": "task remains executable; the exact operation boundary evaluates concrete effects", "suggested_replacement": "add measurable completion conditions, required evidence, and the formal REPORT route before dispatch", "can_auto_fix": false, "decision_owner": "PM", "recommended_decision": "advisory", "enforcement": "advisory" } ] } }, { "round": 2, "name": "missing-parent", "fixture": "", "expected": "mechanical_error", "actual": { "task_id": "TASK-20260904-003", "content_digest": "d0fa4fdde695ea693bcafd2331b89bb2fecf7874100118830fb73bfaea0ed1fa", "authored_snapshot": { "schema_version": 1, "frontmatter": { "depends_on": [ "TASK-20260904-001" ], "parent": "TASK-20260904-999", "protocol": "fcop", "recipient": "QA", "sender": "PM", "thread_key": "thread-1" }, "body": "# Same task text\nIdentical description and expected output." }, "capability_matrix": [ { "task_step": "# Same task text", "execution_role": "UNASSIGNED", "required_capability": "task.execution", "available_tools": [], "current_policy": "allow", "risk": "low", "conclusion": "executable", "suggested_fix": "none" } ], "feasibility": { "decision": "NEEDS_REWRITE", "reason_codes": [ "ACCEPTANCE_UNVERIFIABLE" ], "source": "task_spec_admission" }, "decision": "mechanical_error", "code": "TASK_SPEC_INVALID", "blocking_findings": [ { "id": "PARENT_INVALID", "field": "parent", "message": "parent task does not exist", "evidence": [ "TASK-20260904-999" ], "finding_id": "PARENT_INVALID", "category": "lifecycle", "severity": "medium", "section": "frontmatter", "line_start": 6, "line_end": 6, "original_excerpt": "parent: TASK-20260904-999", "impact": "The task wording may benefit from clarification; PM retains the execution decision.", "required_capability": "parent", "current_support": "canonical identity or transaction integrity requires repair", "suggested_fix": "revise the task specification so the requirement has one executable interpretation", "suggested_replacement": "revise the task specification so the requirement has one executable interpretation", "can_auto_fix": false, "decision_owner": "TASK_AUTHOR", "recommended_decision": "needs_revision", "enforcement": "mechanical_error" } ], "advisory_findings": [ { "id": "ACCEPTANCE_UNVERIFIABLE", "field": "task_body", "message": "downstream task has no observable completion evidence or acceptance contract", "suggested_fix": "add measurable completion conditions, required evidence, and the formal REPORT route before dispatch", "finding_id": "ACCEPTANCE_UNVERIFIABLE", "category": "acceptance_gate", "severity": "medium", "section": "Same task text", "line_start": 10, "line_end": 10, "original_excerpt": "# Same task text", "impact": "This is context for PM and does not prevent task execution.", "required_capability": "task_body", "current_support": "task remains executable; the exact operation boundary evaluates concrete effects", "suggested_replacement": "add measurable completion conditions, required evidence, and the formal REPORT route before dispatch", "can_auto_fix": false, "decision_owner": "PM", "recommended_decision": "advisory", "enforcement": "advisory" } ] } }, { "round": 2, "name": "same-text-other-done", "body_sha256": "cadc35ef2cf2670ad41bc0f368ee2ea13e190621d1c6d8c6302362386e10a1db", "distinct_task_ids": [ "TASK-20260904-001", "TASK-20260904-002" ], "expected": "waiting_dependency", "actual": { "disposition": "waiting_dependency", "decision_owner": "PM", "reason": "waiting_dependency", "detail": "waiting for TASK-20260904-001 lifecycle done (PM approved)", "waitingOn": "TASK-20260904-001" } }, { "round": 2, "name": "same-text-target-done", "body_sha256": "cadc35ef2cf2670ad41bc0f368ee2ea13e190621d1c6d8c6302362386e10a1db", "distinct_task_ids": [ "TASK-20260904-001", "TASK-20260904-002" ], "expected": "neutral", "actual": { "disposition": "neutral", "decision_owner": "AGENT", "reason": "runnable" } } ], "source_records": [ { "file": "runs/baseline-results.json", "sha256": "5313932f7ebd1ccc964424c565d1bafff61ca57dce56ff622e5520dd67c424f5" }, { "file": "runs/probe-2026-09-04T05-41-19-249Z.json", "sha256": "6aafb41c09e08504e190f344807aefcb0251c615cfa11247721f7c2f7fab62c7" }, { "file": "runs/causal-2026-09-04T06-05-11-964Z.json", "sha256": "05a1b904b3b8312e054068a66228767e6802889a54fe7c002ea08a8ca08798c2" } ], "redaction": { "fixture_paths": "Replaced with consistent synthetic fixture labels; labels are not executable paths.", "process_ids": "Omitted; cross-process execution is implemented by the source research runner.", "operation_digests": "Original observed values retained. Do not recompute from path-redacted inputs.", "ordering": "Array order, rounds, timestamps, outcomes and failures retained.", "excluded": "Privacy side experiment and incomplete authoring/debug runs are outside the article dataset." } }