agent-lifecycle-kit 2.5.0__tar.gz → 2.7.0__tar.gz

{agent_lifecycle_kit-2.5.0/src/agent_lifecycle_kit.egg-info → agent_lifecycle_kit-2.7.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agent-lifecycle-kit
-Version: 2.5.0
+Version: 2.7.0
 Summary: Provider-neutral lifecycle control layer that helps coding agents plan, execute, validate, and prove software tasks to completion.
 Author: Agent Lifecycle Kit contributors
 License: Apache-2.0
@@ -43,7 +43,7 @@ ALK provides a verifiable finish for external-agent work with proportionate cont
 ## Quick start
 Start with [install ALK and make the first run](docs/guides/install-and-first-run.md).
 
-It includes macOS, Linux and Windows instructions, Python 3.11-3.14, [PyPI](https://pypi.org/project/agent-lifecycle-kit/) installation with `python -m pip install agent-lifecycle-kit==2.5.0`, and common `agent-lifecycle version` errors.
+It includes macOS, Linux and Windows instructions, Python 3.11-3.14, [PyPI](https://pypi.org/project/agent-lifecycle-kit/) installation with `python -m pip install agent-lifecycle-kit==2.7.0`, and common `agent-lifecycle version` errors.
 
 For a quick start, run:
 
@@ -69,7 +69,7 @@ agent-lifecycle start --adapter <adapter-id> --file task.md
 - The [system architecture](docs/architecture/system-architecture.md) page explains how the project is organized, and [project comparison](docs/reference/project-comparison.md) shows how it differs from similar tools.
 - Multiple-agent boundaries, workflow configuration, model choice, prompts, timeouts and retries are described in [workflow customization and execution controls](docs/reference/workflow-customization.md).
 - Create a local project profile with `agent-lifecycle project profile init`; see [project workflow profile](docs/reference/project-workflow-profile.md). Explain the selected profile, plan constraints and adapter capability lineage with [effective configuration](docs/reference/effective-configuration.md), [structured result qualification](docs/reference/structured-result-qualification.md) and [adapter action evidence](docs/reference/adapter-action-evidence.md). Add optional project-owned architecture and dependency evidence with [external verification checks](docs/reference/external-verification-checks.md), run longer specialized adapter work through [bounded external tool jobs](docs/reference/external-tool-jobs.md), track bounded terminology with [project domain language](docs/reference/project-domain-language.md), coordinate several runs with the read-only [multi-run attention view](docs/reference/multi-run-attention-view.md), or use the optional [security analysis profile](docs/reference/security-analysis-profile.md) for untrusted findings and independently verified remediation.
-- For long sessions, use [context checkpoints and compaction recovery](docs/reference/context-checkpoints.md). They preserve a bounded local continuation package without changing plan authority.
+- For long sessions, use [context checkpoints and compaction recovery](docs/reference/context-checkpoints.md). They preserve a bounded local continuation package without changing plan authority. Measure phases and releases with [release accounting](docs/reference/release-accounting.md), and cross session boundaries with the bounded [phase-to-session handoff](docs/guides/phase-session-handoff.md).
 ## What it gives you
 - A finish-oriented lifecycle: plan, execute, review, and prove the result.
 - One process for different CLIs: adapter-specific commands stay outside the
@@ -196,7 +196,7 @@ Adapter installation and support-level details live in [Adapter install](docs/ad
 - Start: [English documentation](docs/README.md), [Русская документация](docs/ru/README.md), [Install](docs/guides/install-and-first-run.md), [Quickstart](docs/guides/quickstart.md), [Beginner and advanced workflows](docs/guides/beginner-and-advanced-workflows.md), [Commands by task](docs/guides/commands-by-task.md), [Research workflow](docs/guides/research-workflow.md), [Lifecycle task scenarios](docs/guides/lifecycle-cookbook.md), and [Code review workflows](docs/guides/code-review-workflows.md).
 - Planning and adapters: [Issue to specification drafts](docs/guides/issue-to-spec.md), [Adapter install](docs/adapters/install.md), and [Adapter support matrix](docs/adapters/support-matrix.md).
 - Reference: [System architecture](docs/architecture/system-architecture.md), [workflow customization and execution controls](docs/reference/workflow-customization.md), [execution strategy](docs/reference/execution-strategy.md), [CLI reference](docs/reference/cli.md), [External verification checks](docs/reference/external-verification-checks.md), [Bounded external tool jobs](docs/reference/external-tool-jobs.md), [Project domain language](docs/reference/project-domain-language.md), [Multi-run attention view](docs/reference/multi-run-attention-view.md), [Plan verification](docs/reference/plan-verification.md), [Research evidence](docs/reference/research-evidence.md), [Public locators and redaction](docs/reference/public-locators-and-redaction.md), [Finding-to-check adoption](docs/reference/finding-check-adoption.md), [Source of truth](docs/reference/source-of-truth.md), [Managed lifecycle runner](docs/reference/managed-lifecycle-runner.md), [Managed adapter sessions](docs/reference/managed-adapter-sessions.md), [Portable Agent Plugins](docs/reference/agent-plugins.md), [Plugin publication](docs/reference/plugin-publication.md), [Implementation audit](docs/reference/implementation-audit.md), [Plan completeness](docs/reference/plan-completeness.md), [Public contracts](docs/reference/public-contracts.md), and [Readiness diagnostics](docs/reference/readiness-diagnostics.md).
-- Quality and resources: [Reference-task evaluation](docs/reference/reference-task-evaluation.md), [model routing](docs/reference/model-routing.md), [quality-cost learning](docs/reference/quality-cost-learning.md), [performance and resource budgets](docs/reference/performance-and-resource-budgets.md), [lifecycle cost accounting](docs/reference/lifecycle-cost.md), [host-local token accounting](docs/reference/host-local-token-accounting.md), [process execution observability](docs/reference/process-execution-observability.md), [Usage export](docs/reference/usage-export.md), and [Evidence integrity](docs/reference/evidence-integrity.md).
+- Quality and resources: [Reference-task evaluation](docs/reference/reference-task-evaluation.md), [model routing](docs/reference/model-routing.md), [quality-cost learning](docs/reference/quality-cost-learning.md), [review efficiency](docs/reference/review-efficiency.md), [evidence independence](docs/reference/evidence-independence.md), [performance and resource budgets](docs/reference/performance-and-resource-budgets.md), [lifecycle cost accounting](docs/reference/lifecycle-cost.md), [host-local token accounting](docs/reference/host-local-token-accounting.md), [process execution observability](docs/reference/process-execution-observability.md), [Usage export](docs/reference/usage-export.md), and [Evidence integrity](docs/reference/evidence-integrity.md).
 - Profiles and operations: [Project workflow presets](docs/reference/workflow-presets.md), [Project workflow profile](docs/reference/project-workflow-profile.md), [Read-only status views](docs/reference/read-only-status-view.md), [Adapter progress bridge](docs/reference/automatic-progress-bridge.md), [Sandbox boundaries](docs/reference/sandbox-boundaries.md), [Import mappers](docs/reference/import-mappers.md), [Episode retrieval](docs/reference/episode-retrieval.md), [Runner migration](docs/guides/runner-migration-2.md), [Runner recovery records](docs/reference/runner-recovery.md), [Cross-check profile](docs/reference/cross-check-profile.md), [Review Mesh](docs/reference/review-mesh.md), [Risk-bound independent verification](docs/reference/risk-bound-independent-verification.md), [Bug Forensics profile](docs/reference/bug-forensics.md), and [Bug Forensics context budget](docs/reference/bug-forensics-context-budget.md).
 - Release assets: [Task templates](templates/tasks/README.md), [Neutrality scanning](docs/reference/neutrality.md), and [Release security](docs/security/release-security.md).
 Apache-2.0. See [LICENSE](LICENSE).

{agent_lifecycle_kit-2.5.0 → agent_lifecycle_kit-2.7.0}/README.md

@@ -21,7 +21,7 @@ ALK provides a verifiable finish for external-agent work with proportionate cont
 ## Quick start
 Start with [install ALK and make the first run](docs/guides/install-and-first-run.md).
 
-It includes macOS, Linux and Windows instructions, Python 3.11-3.14, [PyPI](https://pypi.org/project/agent-lifecycle-kit/) installation with `python -m pip install agent-lifecycle-kit==2.5.0`, and common `agent-lifecycle version` errors.
+It includes macOS, Linux and Windows instructions, Python 3.11-3.14, [PyPI](https://pypi.org/project/agent-lifecycle-kit/) installation with `python -m pip install agent-lifecycle-kit==2.7.0`, and common `agent-lifecycle version` errors.
 
 For a quick start, run:
 
@@ -47,7 +47,7 @@ agent-lifecycle start --adapter <adapter-id> --file task.md
 - The [system architecture](docs/architecture/system-architecture.md) page explains how the project is organized, and [project comparison](docs/reference/project-comparison.md) shows how it differs from similar tools.
 - Multiple-agent boundaries, workflow configuration, model choice, prompts, timeouts and retries are described in [workflow customization and execution controls](docs/reference/workflow-customization.md).
 - Create a local project profile with `agent-lifecycle project profile init`; see [project workflow profile](docs/reference/project-workflow-profile.md). Explain the selected profile, plan constraints and adapter capability lineage with [effective configuration](docs/reference/effective-configuration.md), [structured result qualification](docs/reference/structured-result-qualification.md) and [adapter action evidence](docs/reference/adapter-action-evidence.md). Add optional project-owned architecture and dependency evidence with [external verification checks](docs/reference/external-verification-checks.md), run longer specialized adapter work through [bounded external tool jobs](docs/reference/external-tool-jobs.md), track bounded terminology with [project domain language](docs/reference/project-domain-language.md), coordinate several runs with the read-only [multi-run attention view](docs/reference/multi-run-attention-view.md), or use the optional [security analysis profile](docs/reference/security-analysis-profile.md) for untrusted findings and independently verified remediation.
-- For long sessions, use [context checkpoints and compaction recovery](docs/reference/context-checkpoints.md). They preserve a bounded local continuation package without changing plan authority.
+- For long sessions, use [context checkpoints and compaction recovery](docs/reference/context-checkpoints.md). They preserve a bounded local continuation package without changing plan authority. Measure phases and releases with [release accounting](docs/reference/release-accounting.md), and cross session boundaries with the bounded [phase-to-session handoff](docs/guides/phase-session-handoff.md).
 ## What it gives you
 - A finish-oriented lifecycle: plan, execute, review, and prove the result.
 - One process for different CLIs: adapter-specific commands stay outside the
@@ -174,7 +174,7 @@ Adapter installation and support-level details live in [Adapter install](docs/ad
 - Start: [English documentation](docs/README.md), [Русская документация](docs/ru/README.md), [Install](docs/guides/install-and-first-run.md), [Quickstart](docs/guides/quickstart.md), [Beginner and advanced workflows](docs/guides/beginner-and-advanced-workflows.md), [Commands by task](docs/guides/commands-by-task.md), [Research workflow](docs/guides/research-workflow.md), [Lifecycle task scenarios](docs/guides/lifecycle-cookbook.md), and [Code review workflows](docs/guides/code-review-workflows.md).
 - Planning and adapters: [Issue to specification drafts](docs/guides/issue-to-spec.md), [Adapter install](docs/adapters/install.md), and [Adapter support matrix](docs/adapters/support-matrix.md).
 - Reference: [System architecture](docs/architecture/system-architecture.md), [workflow customization and execution controls](docs/reference/workflow-customization.md), [execution strategy](docs/reference/execution-strategy.md), [CLI reference](docs/reference/cli.md), [External verification checks](docs/reference/external-verification-checks.md), [Bounded external tool jobs](docs/reference/external-tool-jobs.md), [Project domain language](docs/reference/project-domain-language.md), [Multi-run attention view](docs/reference/multi-run-attention-view.md), [Plan verification](docs/reference/plan-verification.md), [Research evidence](docs/reference/research-evidence.md), [Public locators and redaction](docs/reference/public-locators-and-redaction.md), [Finding-to-check adoption](docs/reference/finding-check-adoption.md), [Source of truth](docs/reference/source-of-truth.md), [Managed lifecycle runner](docs/reference/managed-lifecycle-runner.md), [Managed adapter sessions](docs/reference/managed-adapter-sessions.md), [Portable Agent Plugins](docs/reference/agent-plugins.md), [Plugin publication](docs/reference/plugin-publication.md), [Implementation audit](docs/reference/implementation-audit.md), [Plan completeness](docs/reference/plan-completeness.md), [Public contracts](docs/reference/public-contracts.md), and [Readiness diagnostics](docs/reference/readiness-diagnostics.md).
-- Quality and resources: [Reference-task evaluation](docs/reference/reference-task-evaluation.md), [model routing](docs/reference/model-routing.md), [quality-cost learning](docs/reference/quality-cost-learning.md), [performance and resource budgets](docs/reference/performance-and-resource-budgets.md), [lifecycle cost accounting](docs/reference/lifecycle-cost.md), [host-local token accounting](docs/reference/host-local-token-accounting.md), [process execution observability](docs/reference/process-execution-observability.md), [Usage export](docs/reference/usage-export.md), and [Evidence integrity](docs/reference/evidence-integrity.md).
+- Quality and resources: [Reference-task evaluation](docs/reference/reference-task-evaluation.md), [model routing](docs/reference/model-routing.md), [quality-cost learning](docs/reference/quality-cost-learning.md), [review efficiency](docs/reference/review-efficiency.md), [evidence independence](docs/reference/evidence-independence.md), [performance and resource budgets](docs/reference/performance-and-resource-budgets.md), [lifecycle cost accounting](docs/reference/lifecycle-cost.md), [host-local token accounting](docs/reference/host-local-token-accounting.md), [process execution observability](docs/reference/process-execution-observability.md), [Usage export](docs/reference/usage-export.md), and [Evidence integrity](docs/reference/evidence-integrity.md).
 - Profiles and operations: [Project workflow presets](docs/reference/workflow-presets.md), [Project workflow profile](docs/reference/project-workflow-profile.md), [Read-only status views](docs/reference/read-only-status-view.md), [Adapter progress bridge](docs/reference/automatic-progress-bridge.md), [Sandbox boundaries](docs/reference/sandbox-boundaries.md), [Import mappers](docs/reference/import-mappers.md), [Episode retrieval](docs/reference/episode-retrieval.md), [Runner migration](docs/guides/runner-migration-2.md), [Runner recovery records](docs/reference/runner-recovery.md), [Cross-check profile](docs/reference/cross-check-profile.md), [Review Mesh](docs/reference/review-mesh.md), [Risk-bound independent verification](docs/reference/risk-bound-independent-verification.md), [Bug Forensics profile](docs/reference/bug-forensics.md), and [Bug Forensics context budget](docs/reference/bug-forensics-context-budget.md).
 - Release assets: [Task templates](templates/tasks/README.md), [Neutrality scanning](docs/reference/neutrality.md), and [Release security](docs/security/release-security.md).
 Apache-2.0. See [LICENSE](LICENSE).

{agent_lifecycle_kit-2.5.0 → agent_lifecycle_kit-2.7.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "agent-lifecycle-kit"
-version = "2.5.0"
+version = "2.7.0"
 description = "Provider-neutral lifecycle control layer that helps coding agents plan, execute, validate, and prove software tasks to completion."
 readme = "README.md"
 requires-python = ">=3.11,<3.15"

{agent_lifecycle_kit-2.5.0 → agent_lifecycle_kit-2.7.0}/src/agent_lifecycle/_version.py

@@ -1,3 +1,3 @@
 """Package version."""
 
-__version__ = "2.5.0"
+__version__ = "2.7.0"

{agent_lifecycle_kit-2.5.0 → agent_lifecycle_kit-2.7.0}/src/agent_lifecycle/audit/implementation.py

@@ -8,6 +8,11 @@ from typing import Any
 from agent_lifecycle.audit.ownership import build_ownership_report, report_has_category
 from agent_lifecycle.contracts import LifecycleError, canonical_digest, read_json_object
 from agent_lifecycle.contracts.paths import normalize_repo_path
+from agent_lifecycle.contracts.review_verdict import (
+    BLOCKING_REVIEW_SEVERITIES,
+    REVIEW_SEVERITY_RANK,
+    open_blocking_finding_ids,
+)
 from agent_lifecycle.planning.task_compatibility import (
     validate_task_plan_compatibility_receipt,
 )
@@ -22,7 +27,6 @@ from agent_lifecycle.workflow.sandbox_policy import validate_task_sandbox_eviden
 from agent_lifecycle.workflow.selectors import find_task
 from agent_lifecycle.workflow.state import load_state
 
-SEVERITY_RANK = {"BLOCKER": 0, "HIGH": 1, "MEDIUM": 2, "LOW": 3, "INFO": 4}
 IMPLEMENTATION_AUDIT_SCHEMA = "agent-implementation-audit-report.v1"
 FINAL_IMPLEMENTATION_AUDIT_SCHEMA = "agent-final-implementation-audit.v1"
 
@@ -609,14 +613,7 @@ def _has_blockers(payload: dict[str, Any]) -> bool:
 
 def _has_open_blocking_findings(payload: dict[str, Any]) -> bool:
     findings = payload.get("findings")
-    if not isinstance(findings, list):
-        return False
-    return any(
-        isinstance(item, dict)
-        and item.get("status") == "open"
-        and item.get("severity") in {"BLOCKER", "HIGH", "MEDIUM"}
-        for item in findings
-    )
+    return isinstance(findings, list) and bool(open_blocking_finding_ids(findings))
 
 
 def _add_finding(
@@ -639,12 +636,15 @@ def _add_finding(
         "context": context or {},
     }
     findings.append(finding)
-    if severity in {"BLOCKER", "HIGH", "MEDIUM"}:
+    if severity in BLOCKING_REVIEW_SEVERITIES:
         blockers.append({"code": code, "severity": severity, "message": message, "context": context or {}})
 
 
 def _sorted_findings(findings: list[dict[str, Any]]) -> list[dict[str, Any]]:
-    return sorted(findings, key=lambda item: (SEVERITY_RANK.get(str(item.get("severity")), 99), str(item.get("code"))))
+    return sorted(
+        findings,
+        key=lambda item: (REVIEW_SEVERITY_RANK.get(str(item.get("severity")), 99), str(item.get("code"))),
+    )
 
 
 def _verdict(findings: list[dict[str, Any]]) -> str:
@@ -652,7 +652,7 @@ def _verdict(findings: list[dict[str, Any]]) -> str:
         return "BLOCKED"
     if any(item.get("category") == "ownership" for item in findings):
         return "CONTRACT_CHANGE"
-    if any(item.get("severity") in {"HIGH", "MEDIUM"} for item in findings):
+    if any(item.get("severity") in BLOCKING_REVIEW_SEVERITIES for item in findings):
         return "REWORK"
     return "ACCEPTED"
 

{agent_lifecycle_kit-2.5.0 → agent_lifecycle_kit-2.7.0}/src/agent_lifecycle/cli/dispatch_observability.py

@@ -39,7 +39,9 @@ from agent_lifecycle.imports.security_findings import import_security_findings
 from agent_lifecycle.metrics import (
     build_lifecycle_cost_summary,
     build_lifecycle_recommendation_summary,
+    build_phase_resource_measurement,
     build_quality_cost_signals,
+    build_release_accounting,
     build_task_outcome_index,
     build_usage_export,
     generate_lifecycle_cost_report,
@@ -47,10 +49,19 @@ from agent_lifecycle.metrics import (
     recommend_lifecycle_mode,
     require_lifecycle_cost_pass,
     require_lifecycle_recommendation_pass,
+    require_phase_resource_measurement_pass,
+    require_release_accounting_pass,
     require_usage_export_pass,
     validate_lifecycle_cost_report,
+    validate_phase_resource_measurement,
+    validate_release_accounting,
     validate_usage_export,
 )
+from agent_lifecycle.metrics.audit_efficiency import (
+    build_audit_efficiency_report,
+    validate_audit_efficiency_input,
+    validate_audit_efficiency_report,
+)
 from agent_lifecycle.metrics.audit_optimization import (
     build_audit_optimization_report,
     render_audit_optimization_terminal,
@@ -497,6 +508,10 @@ def _dispatch_metrics(args: argparse.Namespace) -> dict[str, Any] | str:
             "liveCallsStarted": False,
             "productionPromotionClaimed": False,
         }
+    if args.metrics_command == "phase-resources":
+        return _dispatch_phase_resources(args)
+    if args.metrics_command == "release-accounting":
+        return _dispatch_release_accounting(args)
     if args.metrics_command == "usage-export":
         export = build_usage_export(
             artifact_paths=[Path(item) for item in args.artifact],
@@ -571,6 +586,8 @@ def _dispatch_metrics(args: argparse.Namespace) -> dict[str, Any] | str:
         return payload
     if args.metrics_command == "audit-report":
         return _dispatch_audit_report(args)
+    if args.metrics_command == "audit-efficiency":
+        return _dispatch_audit_efficiency(args)
     if args.metrics_command == "audit-proposal":
         report = read_json_object(Path(args.report), label="audit optimization report")
         raw_recommendation = report.get("recommendation")
@@ -593,6 +610,69 @@ def _dispatch_metrics(args: argparse.Namespace) -> dict[str, Any] | str:
     raise LifecycleError("command-not-implemented", "metrics command is not implemented")
 
 
+def _dispatch_phase_resources(args: argparse.Namespace) -> dict[str, Any]:
+    source = read_json_object(Path(args.input), label="phase resource input")
+    if source.get("schemaVersion") != "agent-phase-resource-input.v1":
+        raise LifecycleError("phase-resource-input-schema-invalid", "unsupported phase resource input schema")
+    raw_phases = source.get("phases")
+    if not isinstance(raw_phases, list) or not all(isinstance(item, dict) for item in raw_phases):
+        raise LifecycleError("invalid-phase-resource-measurement", "phases must be an array of objects")
+    phases: list[dict[str, Any]] = raw_phases
+    raw_lineage = source.get("lineage")
+    if raw_lineage is not None and not isinstance(raw_lineage, dict):
+        raise LifecycleError("invalid-phase-resource-measurement", "lineage must be an object")
+    raw_artifacts = source.get("sourceArtifacts")
+    if raw_artifacts is not None and (
+        not isinstance(raw_artifacts, list) or not all(isinstance(item, dict) for item in raw_artifacts)
+    ):
+        raise LifecycleError("invalid-phase-resource-measurement", "sourceArtifacts must be an array of objects")
+    measurement = build_phase_resource_measurement(
+        phases,
+        lineage=raw_lineage,
+        source_artifacts=raw_artifacts,
+    )
+    validation = require_phase_resource_measurement_pass(validate_phase_resource_measurement(measurement))
+    output_bytes = write_json_create(Path(args.out), measurement)
+    body = {
+        "schemaVersion": "agent-phase-resource-generation.v1",
+        "status": "PASS",
+        "outputPath": args.out,
+        "outputBytes": len(output_bytes),
+        "measurementDigest": measurement["measurementDigest"],
+        "validation": validation,
+        "liveCallsStarted": False,
+        "productionPromotionClaimed": False,
+    }
+    return {**body, "receiptDigest": canonical_digest(body)}
+
+
+def _dispatch_release_accounting(args: argparse.Namespace) -> dict[str, Any]:
+    declared_provenance = (
+        read_json_object(Path(args.provenance), label="release accounting provenance")
+        if args.provenance
+        else None
+    )
+    accounting = build_release_accounting(
+        args.release_id,
+        [Path(item) for item in args.artifact],
+        project_root=Path(args.project_root),
+        declared_provenance=declared_provenance,
+    )
+    validation = require_release_accounting_pass(validate_release_accounting(accounting))
+    output_bytes = write_json_create(Path(args.out), accounting)
+    body = {
+        "schemaVersion": "agent-release-accounting-generation.v1",
+        "status": "PASS",
+        "outputPath": args.out,
+        "outputBytes": len(output_bytes),
+        "accountingDigest": accounting["accountingDigest"],
+        "validation": validation,
+        "liveCallsStarted": False,
+        "productionPromotionClaimed": False,
+    }
+    return {**body, "receiptDigest": canonical_digest(body)}
+
+
 def _dispatch_audit_report(args: argparse.Namespace) -> dict[str, Any] | str:
     samples = _read_audit_samples(args.sample)
     candidates = _read_json_items(args.candidate_profile, label="candidate profile")
@@ -625,6 +705,40 @@ def _dispatch_audit_report(args: argparse.Namespace) -> dict[str, Any] | str:
     return report
 
 
+def _dispatch_audit_efficiency(args: argparse.Namespace) -> dict[str, Any]:
+    measurement = read_json_object(Path(args.input), label="audit efficiency input")
+    validation = validate_audit_efficiency_input(measurement)
+    if validation["status"] != "PASS":
+        raise LifecycleError(
+            "audit-efficiency-input-invalid",
+            "audit efficiency input validation failed",
+            {"validation": validation},
+        )
+
+    comparisons: list[dict[str, Any]] = []
+    for index, path in enumerate(args.comparison):
+        comparison = read_json_object(Path(path), label="audit efficiency comparison")
+        comparison_validation = validate_audit_efficiency_input(comparison)
+        if comparison_validation["status"] != "PASS":
+            raise LifecycleError(
+                "audit-efficiency-comparison-invalid",
+                "audit efficiency comparison validation failed",
+                {"index": index, "validation": comparison_validation},
+            )
+        comparisons.append(comparison)
+
+    report = build_audit_efficiency_report(measurement, comparison_measurements=comparisons)
+    report_validation = validate_audit_efficiency_report(report)
+    if report_validation["status"] != "PASS":
+        raise LifecycleError(
+            "audit-efficiency-report-invalid",
+            "audit efficiency report validation failed",
+            {"validation": report_validation},
+        )
+    write_json_create(Path(args.out), report)
+    return report
+
+
 def _read_audit_samples(paths: list[str]) -> list[dict[str, Any]]:
     samples: list[dict[str, Any]] = []
     for item in paths:

{agent_lifecycle_kit-2.5.0 → agent_lifecycle_kit-2.7.0}/src/agent_lifecycle/cli/dispatch_planning.py

@@ -6,6 +6,7 @@ import argparse
 from pathlib import Path
 from typing import Any
 
+from agent_lifecycle.cli.plan_lock_commands import create_reviewed_plan_lock
 from agent_lifecycle.compiler import compile_small_model_packets, compile_task_packets
 from agent_lifecycle.contracts import (
     LifecycleError,
@@ -93,6 +94,12 @@ def _dispatch_specification(args: argparse.Namespace) -> dict[str, Any]:
 
 
 def _dispatch_plan(args: argparse.Namespace) -> dict[str, Any]:
+    if args.plan_command == "lock-create":
+        return create_reviewed_plan_lock(
+            manifest_path=args.manifest,
+            review_path=args.review,
+            repository_root=Path(args.repository_root),
+        )
     if args.plan_command == "check":
         manifest = read_json_object(Path(args.manifest), label="plan manifest")
         lock = read_json_object(Path(args.lock), label="plan lock") if args.lock else None

{agent_lifecycle_kit-2.5.0 → agent_lifecycle_kit-2.7.0}/src/agent_lifecycle/cli/metrics_parser.py

@@ -22,6 +22,15 @@ def add_metrics_parser(subparsers: argparse._SubParsersAction[argparse.ArgumentP
     cost_report.add_argument("--project-root", default=".")
     cost_report.add_argument("--out", required=True)
     cost_report.add_argument("--summary-out")
+    phase_resources = metrics_sub.add_parser("phase-resources", help="build a bounded phase resource measurement")
+    phase_resources.add_argument("--input", required=True)
+    phase_resources.add_argument("--out", required=True)
+    release_accounting = metrics_sub.add_parser("release-accounting", help="build release resource accounting")
+    release_accounting.add_argument("--release-id", required=True)
+    release_accounting.add_argument("--artifact", action="append", required=True)
+    release_accounting.add_argument("--project-root", default=".")
+    release_accounting.add_argument("--provenance")
+    release_accounting.add_argument("--out", required=True)
     usage_export = metrics_sub.add_parser("usage-export")
     usage_export.add_argument("--artifact", action="append", default=[])
     usage_export.add_argument("--project-root", default=".")
@@ -68,6 +77,13 @@ def add_metrics_parser(subparsers: argparse._SubParsersAction[argparse.ArgumentP
     audit_report.add_argument("--current-profile")
     audit_report.add_argument("--out", required=True)
     audit_report.add_argument("--terminal", action="store_true")
+    audit_efficiency = metrics_sub.add_parser(
+        "audit-efficiency",
+        help="report quality-preserving audit efficiency from explicit accounting inputs",
+    )
+    audit_efficiency.add_argument("--input", required=True)
+    audit_efficiency.add_argument("--comparison", action="append", default=[])
+    audit_efficiency.add_argument("--out", required=True)
     audit_proposal = metrics_sub.add_parser("audit-proposal", help="create an explicit audit optimization proposal")
     audit_proposal.add_argument("--report", required=True)
     audit_proposal.add_argument("--out", required=True)

agent_lifecycle_kit-2.7.0/src/agent_lifecycle/cli/plan_lock_commands.py

@@ -0,0 +1,96 @@
+"""Reviewed plan-lock creation command."""
+
+from __future__ import annotations
+
+from pathlib import Path, PurePosixPath
+from typing import Any
+
+from agent_lifecycle.contracts import (
+    LifecycleError,
+    canonical_digest,
+    load_json_object,
+    sha256_hex,
+    write_json_create,
+)
+from agent_lifecycle.contracts.canonical import MAX_JSON_INPUT_BYTES
+from agent_lifecycle.contracts.paths import normalize_repo_path, read_stable_repository_file
+from agent_lifecycle.freeze.package_integrity import (
+    build_reviewed_plan_lock_v2,
+    verify_plan_package_integrity,
+)
+
+PLAN_LOCK_CREATION_RECEIPT = "agent-plan-lock-creation-receipt.v1"
+
+
+def create_reviewed_plan_lock(
+    *,
+    manifest_path: str,
+    review_path: str,
+    repository_root: Path,
+) -> dict[str, Any]:
+    """Create and verify the canonical lock for one reviewed frozen plan."""
+
+    root = repository_root.resolve(strict=True)
+    manifest_rel, manifest_data = _read_repository_json(root, manifest_path, label="plan manifest")
+    manifest = load_json_object(manifest_data, label="plan manifest")
+    package_value = manifest.get("package")
+    package = package_value if isinstance(package_value, dict) else {}
+    raw_plan_root = package.get("planArtifactRoot")
+    if not isinstance(raw_plan_root, str):
+        raise LifecycleError("invalid-plan-manifest", "package.planArtifactRoot is required")
+    plan_root = normalize_repo_path(raw_plan_root, label="package.planArtifactRoot")
+    expected_manifest = f"{plan_root}/plan.manifest.json"
+    if manifest_rel != expected_manifest:
+        raise LifecycleError("plan-manifest-path-mismatch", "manifest path does not match package.planArtifactRoot")
+
+    review_rel, review_data = _read_repository_json(root, review_path, label="plan review")
+    review = load_json_object(review_data, label="plan review")
+    lock = build_reviewed_plan_lock_v2(
+        manifest,
+        review,
+        review_path=review_rel,
+        review_sha256=sha256_hex(review_data),
+        repository_root=root,
+    )
+    # Reject malformed or drifting package bytes before creating the
+    # no-replace authority artifact. The second check still detects drift.
+    verify_plan_package_integrity(manifest, lock, repository_root=root)
+    lock_rel = f"{plan_root}/plan.lock.json"
+    lock_path = root.joinpath(*PurePosixPath(lock_rel).parts)
+    try:
+        write_json_create(lock_path, lock)
+    except FileExistsError as exc:
+        raise LifecycleError("plan-lock-exists", "canonical plan lock already exists", {"path": lock_rel}) from exc
+    except OSError as exc:
+        raise LifecycleError(
+            "plan-lock-write-failed",
+            "canonical plan lock could not be created",
+            {"path": lock_rel},
+        ) from exc
+    verification = verify_plan_package_integrity(manifest, lock, repository_root=root)
+    body = {
+        "schemaVersion": PLAN_LOCK_CREATION_RECEIPT,
+        "status": "PASS",
+        "packageId": package.get("id"),
+        "planRevision": manifest.get("planRevision"),
+        "manifestPath": manifest_rel,
+        "manifestHash": canonical_digest(manifest),
+        "reviewPath": review_rel,
+        "reviewId": review.get("reviewId"),
+        "reviewedPlanHash": review.get("reviewedPlanHash"),
+        "lockPath": lock_rel,
+        "lockSchemaVersion": lock.get("schemaVersion"),
+        "planFilesHash": lock.get("planFilesHash"),
+        "filesystemVerified": verification.get("filesystemVerified") is True,
+        "productionPromotionClaimed": False,
+    }
+    return {**body, "receiptDigest": canonical_digest(body)}
+
+
+def _read_repository_json(root: Path, raw_path: str, *, label: str) -> tuple[str, bytes]:
+    relative = normalize_repo_path(raw_path, label=f"{label} path")
+    data = read_stable_repository_file(root, relative, max_bytes=MAX_JSON_INPUT_BYTES, label=label)
+    return relative, data
+
+
+__all__ = ["PLAN_LOCK_CREATION_RECEIPT", "create_reviewed_plan_lock"]

{agent_lifecycle_kit-2.5.0 → agent_lifecycle_kit-2.7.0}/src/agent_lifecycle/cli/planning_parsers.py

@@ -17,6 +17,13 @@ def _add_plan_parser(subparsers: argparse._SubParsersAction[argparse.ArgumentPar
     plan_check.add_argument("--lock")
     plan_check.add_argument("--require-completeness", action="store_true")
     plan_check.add_argument("--completeness-profile")
+    lock_create = plan_sub.add_parser(
+        "lock-create",
+        help="create the canonical lock for an independently reviewed plan",
+    )
+    lock_create.add_argument("--manifest", required=True)
+    lock_create.add_argument("--review", required=True)
+    lock_create.add_argument("--repository-root", default=".")
     verify = plan_sub.add_parser("verify", help="compose read-only plan checks")
     verify.add_argument("--manifest", required=True)
     verify.add_argument("--package-root")

{agent_lifecycle_kit-2.5.0 → agent_lifecycle_kit-2.7.0}/src/agent_lifecycle/contracts/audit_optimization_schemas.py

@@ -14,9 +14,69 @@ AUDIT_OPTIMIZATION_REPORT_SCHEMA = "agent-audit-optimization-report.v1"
 AUDIT_OPTIMIZATION_PROPOSAL_SCHEMA = "agent-audit-optimization-proposal.v1"
 AUDIT_OPTIMIZATION_APPLIED_PROFILE_SCHEMA = "agent-audit-optimization-applied-profile.v1"
 AUDIT_OPTIMIZATION_APPLY_RESULT_SCHEMA = "agent-audit-optimization-apply-result.v1"
+AUDIT_EFFICIENCY_INPUT_SCHEMA = "agent-audit-efficiency-input.v1"
+AUDIT_EFFICIENCY_REPORT_SCHEMA = "agent-audit-efficiency-report.v1"
 
 
 AUDIT_OPTIMIZATION_SCHEMAS: dict[str, dict[str, Any]] = {
+    AUDIT_EFFICIENCY_INPUT_SCHEMA: open_object_schema(
+        AUDIT_EFFICIENCY_INPUT_SCHEMA,
+        required=[
+            "schemaVersion",
+            "releaseId",
+            "sourceRevision",
+            "sourceLineageDigest",
+            "qualityFloor",
+            "views",
+            "outcomes",
+            "totals",
+            "productionPromotionClaimed",
+            "inputDigest",
+        ],
+        properties={
+            "releaseId": {"type": "string", "minLength": 1},
+            "sourceRevision": {"type": "string", "minLength": 1},
+            "sourceLineageDigest": {"type": "string", "minLength": 64, "maxLength": 64},
+            "qualityFloor": {"type": "string", "minLength": 1},
+            "views": {"type": "object"},
+            "outcomes": {"type": "object"},
+            "totals": {"type": "object"},
+            "productionPromotionClaimed": {"const": False},
+            "inputDigest": {"type": "string", "minLength": 64, "maxLength": 64},
+        },
+    ),
+    AUDIT_EFFICIENCY_REPORT_SCHEMA: open_object_schema(
+        AUDIT_EFFICIENCY_REPORT_SCHEMA,
+        required=[
+            "schemaVersion",
+            "status",
+            "releaseId",
+            "qualityFloor",
+            "qualityFloorPreserved",
+            "metrics",
+            "comparison",
+            "advisoryOnly",
+            "autoApply",
+            "blockers",
+            "inputDigest",
+            "productionPromotionClaimed",
+            "reportDigest",
+        ],
+        properties={
+            "status": {"enum": ["PASS", "NO_COMPARISON", "FAIL"]},
+            "releaseId": {"type": ["string", "null"]},
+            "qualityFloor": {"type": ["string", "null"]},
+            "qualityFloorPreserved": {"const": True},
+            "metrics": {"type": "object"},
+            "comparison": {"type": "object"},
+            "advisoryOnly": {"const": True},
+            "autoApply": {"const": False},
+            "blockers": {"type": "array", "items": {"type": "object"}},
+            "inputDigest": {"type": ["string", "null"]},
+            "productionPromotionClaimed": {"const": False},
+            "reportDigest": {"type": "string", "minLength": 64, "maxLength": 64},
+        },
+    ),
     AUDIT_OPTIMIZATION_SAMPLE_SCHEMA: open_object_schema(
         AUDIT_OPTIMIZATION_SAMPLE_SCHEMA,
         required=[
@@ -42,6 +102,7 @@ AUDIT_OPTIMIZATION_SCHEMAS: dict[str, dict[str, Any]] = {
         properties={
             "sampleId": {"type": "string", "minLength": 1},
             "lineage": {"type": "object"},
+            "statisticalProvenance": {"type": "object"},
             "request": {"type": "object"},
             "review": {"type": "object"},
             "attempts": {"type": "object"},
@@ -61,7 +122,16 @@ AUDIT_OPTIMIZATION_SCHEMAS: dict[str, dict[str, Any]] = {
     ),
     AUDIT_OPTIMIZATION_SAMPLE_BATCH_SCHEMA: open_object_schema(
         AUDIT_OPTIMIZATION_SAMPLE_BATCH_SCHEMA,
-        required=["schemaVersion", "status", "sampleCount", "samples", "sourceCount", "blockers", "productionPromotionClaimed", "batchDigest"],
+        required=[
+            "schemaVersion",
+            "status",
+            "sampleCount",
+            "samples",
+            "sourceCount",
+            "blockers",
+            "productionPromotionClaimed",
+            "batchDigest",
+        ],
         properties={
             "status": {"enum": ["PASS", "FAIL"]},
             "sampleCount": {"type": "integer", "minimum": 0},
@@ -74,7 +144,16 @@ AUDIT_OPTIMIZATION_SCHEMAS: dict[str, dict[str, Any]] = {
     ),
     AUDIT_OPTIMIZATION_STATISTICS_SCHEMA: open_object_schema(
         AUDIT_OPTIMIZATION_STATISTICS_SCHEMA,
-        required=["schemaVersion", "status", "sampleCount", "confidence", "minimumSample", "signals", "blockers", "statisticsDigest"],
+        required=[
+            "schemaVersion",
+            "status",
+            "sampleCount",
+            "confidence",
+            "minimumSample",
+            "signals",
+            "blockers",
+            "statisticsDigest",
+        ],
         properties={
             "status": {"enum": ["PASS", "NO_RECOMMENDATION", "FAIL"]},
             "sampleCount": {"type": "integer", "minimum": 0},
@@ -121,7 +200,16 @@ AUDIT_OPTIMIZATION_SCHEMAS: dict[str, dict[str, Any]] = {
     ),
     AUDIT_OPTIMIZATION_REPORT_SCHEMA: open_object_schema(
         AUDIT_OPTIMIZATION_REPORT_SCHEMA,
-        required=["schemaVersion", "status", "statistics", "evaluation", "recommendation", "nextAction", "productionPromotionClaimed", "reportDigest"],
+        required=[
+            "schemaVersion",
+            "status",
+            "statistics",
+            "evaluation",
+            "recommendation",
+            "nextAction",
+            "productionPromotionClaimed",
+            "reportDigest",
+        ],
         properties={
             "status": {"enum": ["PASS", "NO_RECOMMENDATION", "FAIL"]},
             "statistics": {"type": "object"},
@@ -134,7 +222,18 @@ AUDIT_OPTIMIZATION_SCHEMAS: dict[str, dict[str, Any]] = {
     ),
     AUDIT_OPTIMIZATION_PROPOSAL_SCHEMA: open_object_schema(
         AUDIT_OPTIMIZATION_PROPOSAL_SCHEMA,
-        required=["schemaVersion", "status", "proposalId", "sourceRecommendationDigest", "approvalRequired", "applyAllowed", "candidateChanges", "rollback", "productionPromotionClaimed", "proposalDigest"],
+        required=[
+            "schemaVersion",
+            "status",
+            "proposalId",
+            "sourceRecommendationDigest",
+            "approvalRequired",
+            "applyAllowed",
+            "candidateChanges",
+            "rollback",
+            "productionPromotionClaimed",
+            "proposalDigest",
+        ],
         properties={
             "status": {"enum": ["PASS", "FAIL"]},
             "proposalId": {"type": "string", "minLength": 1},
@@ -201,6 +300,8 @@ AUDIT_OPTIMIZATION_SCHEMAS: dict[str, dict[str, Any]] = {
 
 
 __all__ = [
+    "AUDIT_EFFICIENCY_INPUT_SCHEMA",
+    "AUDIT_EFFICIENCY_REPORT_SCHEMA",
     "AUDIT_OPTIMIZATION_APPLIED_PROFILE_SCHEMA",
     "AUDIT_OPTIMIZATION_APPLY_RESULT_SCHEMA",
     "AUDIT_OPTIMIZATION_PROPOSAL_SCHEMA",