PyPI - agentledger-runtime - Versions diffs - 1.4.2__tar.gz → 1.5.2__tar.gz - Mend

agentledger-runtime 1.4.2tar.gz → 1.5.2tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (406) hide show

{agentledger_runtime-1.4.2 → agentledger_runtime-1.5.2}/.github/workflows/ci.yml RENAMED Viewed

@@ -114,6 +114,43 @@ jobs:
           go run ./cmd/agentledger-go conformance
           go run ./cmd/agentledger-go contract validate
+  benchmark:
+    name: Runtime benchmark gate
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+      - name: Set up Go
+        uses: actions/setup-go@v5
+        with:
+          go-version: "1.22"
+      - name: Set up Node
+        uses: actions/setup-node@v4
+        with:
+          node-version: "22"
+      - name: Set up Rust
+        uses: dtolnay/rust-toolchain@stable
+      - name: Run full runtime benchmark
+        run: |
+          PYTHONDONTWRITEBYTECODE=1 PYTHONPATH=src python scripts/benchmark_runtime.py --iterations 20 --output-dir benchmark-artifacts --command-timeout 180
+      - name: Upload benchmark report
+        uses: actions/upload-artifact@v4
+        with:
+          name: agentledger-benchmark
+          path: benchmark-artifacts/**
+          retention-days: 14
   python:
     name: Python ${{ matrix.python-version }}
     runs-on: ubuntu-latest
@@ -225,12 +262,16 @@ jobs:
           python -m json.tool /tmp/agentledger-example-mcp.json >/dev/null
           PYTHONDONTWRITEBYTECODE=1 PYTHONPATH=src python examples/openai_agents/basic_agent.py >/tmp/agentledger-example-openai-agents.json
           python -m json.tool /tmp/agentledger-example-openai-agents.json >/dev/null
+          PYTHONDONTWRITEBYTECODE=1 PYTHONPATH=src python examples/openai_agents/approval_replay.py >/tmp/agentledger-example-openai-approval-replay.json
+          python -m json.tool /tmp/agentledger-example-openai-approval-replay.json >/dev/null
           PYTHONDONTWRITEBYTECODE=1 PYTHONPATH=src python examples/sandbox/command_tool.py >/tmp/agentledger-example-sandbox.json
           python -m json.tool /tmp/agentledger-example-sandbox.json >/dev/null
           PYTHONDONTWRITEBYTECODE=1 PYTHONPATH=src python examples/tool_catalog/basic_catalog.py >/tmp/agentledger-example-tool-catalog.json
           python -m json.tool /tmp/agentledger-example-tool-catalog.json >/dev/null
           PYTHONDONTWRITEBYTECODE=1 PYTHONPATH=src python examples/semantic_kernel/basic_kernel.py >/tmp/agentledger-example-semantic-kernel.json
           python -m json.tool /tmp/agentledger-example-semantic-kernel.json >/dev/null
+          PYTHONDONTWRITEBYTECODE=1 PYTHONPATH=src python examples/temporal_bridge/demo.py >/tmp/agentledger-example-temporal-bridge.json
+          python -m json.tool /tmp/agentledger-example-temporal-bridge.json >/dev/null
           PYTHONDONTWRITEBYTECODE=1 PYTHONPATH=src python -m agentledger --root /tmp/agentledger-ci-worker-run worker-run examples/transient_retry >/tmp/agentledger-example-worker-run.json
           python -m json.tool /tmp/agentledger-example-worker-run.json >/dev/null

{agentledger_runtime-1.4.2 → agentledger_runtime-1.5.2}/CHANGELOG.md RENAMED Viewed

@@ -6,7 +6,55 @@ This project follows semantic versioning for the stable runtime-core contract. O
 ## Unreleased
-No unreleased changes.
+## 1.5.2 - 2026-07-19
+### Added
+- Added the normalized Oh My Pi / OMP runtime bridge across Python, Go, TypeScript, and Rust runtime-core packages.
+- Added `OmpSession`, `OmpTurn`, `OmpModelCall`, `OmpToolProposal`, `OmpToolExecution`, `OmpFailure`, and `OmpStateChange` records for translating external OMP runtime events into AgentLedger runs, steps, model evidence, Tool Ledger rows, failure lifecycle events, artifacts, and versioned state changes.
+- Added cross-language OMP bridge tests with no OMP dependency and no application-specific assumptions.
+- Added Python, Go, TypeScript, and Rust OMP bridge examples using synthetic runtime events.
+### Fixed
+- Hardened the release gate audit so the built-in OMP runtime bridge is included in Python parity coverage through the aggregate four-language parity gate.
+- Clarified the OpenAI Agents SDK approval/replay example boundary lint exception for approval-gated external API side effects that are not untrusted local sandbox execution.
+### Clarified
+- The OMP bridge is built into the current runtime packages as a generic runtime evidence adapter. A separate `agentledger-omp` package remains optional future packaging work, not a requirement for 1.5.2.
+- The bridge records domain-neutral runtime evidence only; applications built on OMP still own their memory, document, persona, workspace, account, and business semantics.
+- This is a four-language patch release. It extends the adapter surface without changing the stable v1.x runtime-core contract.
+## 1.5.1 - 2026-07-19
+### Added
+- Added the Oh My Pi / OMP runtime adapter design document, defining a generic OMP runtime event-to-AgentLedger evidence boundary.
+- Added OMP adapter roadmap entries covering runtime session, turn, model-call, tool-proposal, tool-execution, failure, artifact, and versioned state-change mapping.
+- Added Chinese documentation for the OMP adapter boundary and implementation phases.
+### Clarified
+- The OMP adapter is a runtime adapter, not an application-specific adapter. It must not encode private product paths, memory semantics, workspace rules, account/quota logic, or business-specific harness behavior.
+- Versioned document/state support should stay domain-neutral: AgentLedger can record refs, hashes, diffs, commit/rollback status, failure evidence, and causal links, while applications own the meaning of their files and state.
+- Aligned companion package metadata, package-level `__version__` values, and latest install/certification snippets to `1.5.1`.
+- This patch release does not change the stable v1.x runtime-core contract.
+## 1.5.0 - 2026-07-08
+### Added
+- Added a dependency-free OpenAI Agents SDK-style approval/replay example that records model evidence, proposed tool calls, approval state, Tool Ledger history, and replay-safe resume behavior without requiring external framework installs.
+- Added a dependency-free Temporal bridge retry-safety example that shows workflow/activity ownership boundaries, retry correlation, archived tool-proposal reuse, and single-write side-effect behavior after an activity crash.
+- Added framework-native smoke coverage and CI checks for the new OpenAI Agents SDK-style and Temporal bridge adoption paths.
+- Added a dependency-free runtime benchmark suite with a semantic coverage matrix for all required runtime checks.
+- Added benchmark documentation and release checklist gates for recording local timing, evidence/debug artifact generation, failure injection, adapter contract dry-runs, and cross-language conformance command baselines.
+### Clarified
+- This is a four-language 1.5.0 runtime-core release train. Python, Go, TypeScript, and Rust keep the same portable runtime-core semantics introduced in the 1.4 line.
+- The new OpenAI Agents SDK-style and Temporal bridge assets are Python adoption examples and documentation entrypoints. They do not imply official upstream endorsement or new language-specific runtime-core requirements.
 ## 1.4.2 - 2026-06-19
@@ -362,7 +410,3 @@ No unreleased changes.
 - Exact optional framework packages are not implemented.
 - Rust, TypeScript, and Go implementations are not started.
 - Production sandbox hardening requires external deployment policy.
----
-generated by codex cli

{agentledger_runtime-1.4.2 → agentledger_runtime-1.5.2}/PKG-INFO RENAMED Viewed

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agentledger-runtime
-Version: 1.4.2
+Version: 1.5.2
 Summary: Runtime reliability layer for Agent Harness stacks
 Project-URL: Homepage, https://github.com/yaogdu/AgentLedger
 Project-URL: Repository, https://github.com/yaogdu/AgentLedger
@@ -21,33 +21,33 @@ Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.11
 Provides-Extra: all
-Requires-Dist: agentledger-inspector<2,>=1.4.2; extra == 'all'
-Requires-Dist: agentledger-langfuse<2,>=1.4; extra == 'all'
-Requires-Dist: agentledger-langgraph<2,>=1.4; extra == 'all'
-Requires-Dist: agentledger-mcp<2,>=1.4; extra == 'all'
-Requires-Dist: agentledger-mysql<2,>=1.4; extra == 'all'
-Requires-Dist: agentledger-otel<2,>=1.4; extra == 'all'
-Requires-Dist: agentledger-postgres<2,>=1.4; extra == 'all'
-Requires-Dist: agentledger-s3<2,>=1.4; extra == 'all'
-Requires-Dist: agentledger-sandbox-docker<2,>=1.4; extra == 'all'
+Requires-Dist: agentledger-inspector<2,>=1.5.2; extra == 'all'
+Requires-Dist: agentledger-langfuse<2,>=1.5.2; extra == 'all'
+Requires-Dist: agentledger-langgraph<2,>=1.5.2; extra == 'all'
+Requires-Dist: agentledger-mcp<2,>=1.5.2; extra == 'all'
+Requires-Dist: agentledger-mysql<2,>=1.5.2; extra == 'all'
+Requires-Dist: agentledger-otel<2,>=1.5.2; extra == 'all'
+Requires-Dist: agentledger-postgres<2,>=1.5.2; extra == 'all'
+Requires-Dist: agentledger-s3<2,>=1.5.2; extra == 'all'
+Requires-Dist: agentledger-sandbox-docker<2,>=1.5.2; extra == 'all'
 Provides-Extra: docker
-Requires-Dist: agentledger-sandbox-docker<2,>=1.4; extra == 'docker'
+Requires-Dist: agentledger-sandbox-docker<2,>=1.5.2; extra == 'docker'
 Provides-Extra: inspector
-Requires-Dist: agentledger-inspector<2,>=1.4.2; extra == 'inspector'
+Requires-Dist: agentledger-inspector<2,>=1.5.2; extra == 'inspector'
 Provides-Extra: langfuse
-Requires-Dist: agentledger-langfuse<2,>=1.4; extra == 'langfuse'
+Requires-Dist: agentledger-langfuse<2,>=1.5.2; extra == 'langfuse'
 Provides-Extra: langgraph
-Requires-Dist: agentledger-langgraph<2,>=1.4; extra == 'langgraph'
+Requires-Dist: agentledger-langgraph<2,>=1.5.2; extra == 'langgraph'
 Provides-Extra: mcp
-Requires-Dist: agentledger-mcp<2,>=1.4; extra == 'mcp'
+Requires-Dist: agentledger-mcp<2,>=1.5.2; extra == 'mcp'
 Provides-Extra: mysql
-Requires-Dist: agentledger-mysql<2,>=1.4; extra == 'mysql'
+Requires-Dist: agentledger-mysql<2,>=1.5.2; extra == 'mysql'
 Provides-Extra: otel
-Requires-Dist: agentledger-otel<2,>=1.4; extra == 'otel'
+Requires-Dist: agentledger-otel<2,>=1.5.2; extra == 'otel'
 Provides-Extra: postgres
-Requires-Dist: agentledger-postgres<2,>=1.4; extra == 'postgres'
+Requires-Dist: agentledger-postgres<2,>=1.5.2; extra == 'postgres'
 Provides-Extra: s3
-Requires-Dist: agentledger-s3<2,>=1.4; extra == 's3'
+Requires-Dist: agentledger-s3<2,>=1.5.2; extra == 's3'
 Description-Content-Type: text/markdown
 # AgentLedger
@@ -55,7 +55,7 @@ Description-Content-Type: text/markdown
 [English](README.md) | [中文](README.zh-CN.md)
 ![Python 3.11+](https://img.shields.io/badge/Python-3.11%2B-3776AB?logo=python&logoColor=white)
-![Version 1.4.x stable](https://img.shields.io/badge/Version-1.4.x--stable-111827)
+![Version 1.5.x stable](https://img.shields.io/badge/Version-1.5.x--stable-111827)
 ![License Apache-2.0](https://img.shields.io/badge/License-Apache--2.0-0f766e)
 ![Runtime Durable](https://img.shields.io/badge/Runtime-durable%20execution-1f6feb)
 ![Storage SQLite/Postgres/MySQL](https://img.shields.io/badge/Storage-SQLite%20%7C%20Postgres%20%7C%20MySQL-b45309)
@@ -64,7 +64,7 @@ Description-Content-Type: text/markdown
 Your agent called a tool. Did it happen? Can you retry safely? Can you prove it later?
-AgentLedger `1.4.x` is a runtime reliability layer for Agent Harness stacks. It does not try to teach agents how to reason or replace the surrounding harness ecosystem; it makes agent runs durable, auditable, replayable, policy-governed, and recoverable when workers crash, tools fail, or prompts change.
+AgentLedger `1.5.x` is a runtime reliability layer for Agent Harness stacks. It does not try to teach agents how to reason or replace the surrounding harness ecosystem; it makes agent runs durable, auditable, replayable, policy-governed, and recoverable when workers crash, tools fail, or prompts change.
 Most agent frameworks focus on planning, reasoning, and workflow logic. AgentLedger sits underneath or beside LangChain, LangGraph, CrewAI, AutoGen, OpenAI Agents SDK, LlamaIndex, Semantic Kernel, or custom agents to provide runtime guarantees around state, tools, evidence, replay, and recovery.
@@ -83,7 +83,9 @@ Python remains the reference implementation, and Go, TypeScript, and Rust now ha
 | Find runnable examples | [examples/README.md](examples/README.md), [go/examples/README.md](go/examples/README.md), [typescript/examples/README.md](typescript/examples/README.md), [rust/examples/README.md](rust/examples/README.md) |
 | Query runtime tables | [docs/QUERY_EXAMPLES.md](docs/QUERY_EXAMPLES.md) |
 | Inspect a run visually | [docs/INSPECTOR.md](docs/INSPECTOR.md) |
+| Run benchmark and coverage gates | [docs/BENCHMARKS.md](docs/BENCHMARKS.md) |
 | Understand Harness stack composition | [docs/HARNESS_STACK.md](docs/HARNESS_STACK.md) |
+| Plan an Oh My Pi / OMP runtime adapter | [docs/OMP_RUNTIME_ADAPTER_DESIGN.md](docs/OMP_RUNTIME_ADAPTER_DESIGN.md) |
 | Understand open-source impact | [docs/OPEN_SOURCE_IMPACT.md](docs/OPEN_SOURCE_IMPACT.md) |
 | Understand maintainer responsibilities | [docs/MAINTAINER_NOTES.md](docs/MAINTAINER_NOTES.md) |
 | Plan adoption work | [docs/ADOPTION.md](docs/ADOPTION.md) |
@@ -256,6 +258,7 @@ Temporal + LangGraph + AgentLedger is a valid production stack: Temporal runs th
 - Contributing guide: [CONTRIBUTING.md](CONTRIBUTING.md)
 - Community conduct: [CODE_OF_CONDUCT.md](CODE_OF_CONDUCT.md)
 - Release gates: [docs/RELEASE_CHECKLIST.md](docs/RELEASE_CHECKLIST.md)
+- Benchmark gates: [docs/BENCHMARKS.md](docs/BENCHMARKS.md)
 - Compatibility policy: [docs/VERSIONING.md](docs/VERSIONING.md)
 ## Quick start
@@ -350,7 +353,7 @@ AgentLedger is also not a new LLM SDK, not a workflow engine, not a general obse
 ## Current maturity
-AgentLedger 1.4.x is a stable runtime-core line with Python as the reference implementation and Go, TypeScript, and Rust covered by shared runtime-core parity gates. The four language runtimes share the same runtime-core failure semantics and model evidence boundary: failed steps, retry scheduling, cancellation, lease recovery, Tool Ledger unknown-state handling, cost/failure attribution, evidence, replay, normalized failure envelopes, failure lifecycle, causal graph, replay plan, regression report, alerts, failure export mappings, archived model request/response/failure evidence, and model-proposed tool-call records. The current runtime-core release is 1.4.2 across Python, Go, TypeScript, and Rust; Inspector remains a language-neutral companion viewer distributed through Python/PyPI. It is suitable for local use, framework adapter integration, reliability semantics validation, and production pilot preparation with explicit adapter boundaries.
+AgentLedger 1.5.x is a stable runtime-core line with Python as the reference implementation and Go, TypeScript, and Rust covered by shared runtime-core parity gates. The four language runtimes share the same runtime-core failure semantics, model evidence boundary, and normalized OMP runtime bridge: failed steps, retry scheduling, cancellation, lease recovery, Tool Ledger unknown-state handling, cost/failure attribution, evidence, replay, normalized failure envelopes, failure lifecycle, causal graph, replay plan, regression report, alerts, failure export mappings, archived model request/response/failure evidence, model-proposed tool-call records, and OMP session/turn/tool/state evidence mapping. The current runtime-core release is 1.5.2 across Python, Go, TypeScript, and Rust; Inspector remains a language-neutral companion viewer distributed through Python/PyPI. It is suitable for local use, framework adapter integration, reliability semantics validation, and production pilot preparation with explicit adapter boundaries.
 The runtime-core contract is stable; optional production adapters and external infrastructure hardening remain separately tracked. See [docs/MATURITY_MODEL.md](docs/MATURITY_MODEL.md), [docs/IMPLEMENTATION_STATUS.md](docs/IMPLEMENTATION_STATUS.md), and [docs/ROADMAP.md](docs/ROADMAP.md).
@@ -405,7 +408,3 @@ See [docs/RELEASE_CHECKLIST.md](docs/RELEASE_CHECKLIST.md) for the complete rele
 ## License
 Apache-2.0. See [LICENSE](LICENSE).
----
-generated by codex cli

{agentledger_runtime-1.4.2 → agentledger_runtime-1.5.2}/README.md RENAMED Viewed

@@ -3,7 +3,7 @@
 [English](README.md) | [中文](README.zh-CN.md)
 ![Python 3.11+](https://img.shields.io/badge/Python-3.11%2B-3776AB?logo=python&logoColor=white)
-![Version 1.4.x stable](https://img.shields.io/badge/Version-1.4.x--stable-111827)
+![Version 1.5.x stable](https://img.shields.io/badge/Version-1.5.x--stable-111827)
 ![License Apache-2.0](https://img.shields.io/badge/License-Apache--2.0-0f766e)
 ![Runtime Durable](https://img.shields.io/badge/Runtime-durable%20execution-1f6feb)
 ![Storage SQLite/Postgres/MySQL](https://img.shields.io/badge/Storage-SQLite%20%7C%20Postgres%20%7C%20MySQL-b45309)
@@ -12,7 +12,7 @@
 Your agent called a tool. Did it happen? Can you retry safely? Can you prove it later?
-AgentLedger `1.4.x` is a runtime reliability layer for Agent Harness stacks. It does not try to teach agents how to reason or replace the surrounding harness ecosystem; it makes agent runs durable, auditable, replayable, policy-governed, and recoverable when workers crash, tools fail, or prompts change.
+AgentLedger `1.5.x` is a runtime reliability layer for Agent Harness stacks. It does not try to teach agents how to reason or replace the surrounding harness ecosystem; it makes agent runs durable, auditable, replayable, policy-governed, and recoverable when workers crash, tools fail, or prompts change.
 Most agent frameworks focus on planning, reasoning, and workflow logic. AgentLedger sits underneath or beside LangChain, LangGraph, CrewAI, AutoGen, OpenAI Agents SDK, LlamaIndex, Semantic Kernel, or custom agents to provide runtime guarantees around state, tools, evidence, replay, and recovery.
@@ -31,7 +31,9 @@ Python remains the reference implementation, and Go, TypeScript, and Rust now ha
 | Find runnable examples | [examples/README.md](examples/README.md), [go/examples/README.md](go/examples/README.md), [typescript/examples/README.md](typescript/examples/README.md), [rust/examples/README.md](rust/examples/README.md) |
 | Query runtime tables | [docs/QUERY_EXAMPLES.md](docs/QUERY_EXAMPLES.md) |
 | Inspect a run visually | [docs/INSPECTOR.md](docs/INSPECTOR.md) |
+| Run benchmark and coverage gates | [docs/BENCHMARKS.md](docs/BENCHMARKS.md) |
 | Understand Harness stack composition | [docs/HARNESS_STACK.md](docs/HARNESS_STACK.md) |
+| Plan an Oh My Pi / OMP runtime adapter | [docs/OMP_RUNTIME_ADAPTER_DESIGN.md](docs/OMP_RUNTIME_ADAPTER_DESIGN.md) |
 | Understand open-source impact | [docs/OPEN_SOURCE_IMPACT.md](docs/OPEN_SOURCE_IMPACT.md) |
 | Understand maintainer responsibilities | [docs/MAINTAINER_NOTES.md](docs/MAINTAINER_NOTES.md) |
 | Plan adoption work | [docs/ADOPTION.md](docs/ADOPTION.md) |
@@ -204,6 +206,7 @@ Temporal + LangGraph + AgentLedger is a valid production stack: Temporal runs th
 - Contributing guide: [CONTRIBUTING.md](CONTRIBUTING.md)
 - Community conduct: [CODE_OF_CONDUCT.md](CODE_OF_CONDUCT.md)
 - Release gates: [docs/RELEASE_CHECKLIST.md](docs/RELEASE_CHECKLIST.md)
+- Benchmark gates: [docs/BENCHMARKS.md](docs/BENCHMARKS.md)
 - Compatibility policy: [docs/VERSIONING.md](docs/VERSIONING.md)
 ## Quick start
@@ -298,7 +301,7 @@ AgentLedger is also not a new LLM SDK, not a workflow engine, not a general obse
 ## Current maturity
-AgentLedger 1.4.x is a stable runtime-core line with Python as the reference implementation and Go, TypeScript, and Rust covered by shared runtime-core parity gates. The four language runtimes share the same runtime-core failure semantics and model evidence boundary: failed steps, retry scheduling, cancellation, lease recovery, Tool Ledger unknown-state handling, cost/failure attribution, evidence, replay, normalized failure envelopes, failure lifecycle, causal graph, replay plan, regression report, alerts, failure export mappings, archived model request/response/failure evidence, and model-proposed tool-call records. The current runtime-core release is 1.4.2 across Python, Go, TypeScript, and Rust; Inspector remains a language-neutral companion viewer distributed through Python/PyPI. It is suitable for local use, framework adapter integration, reliability semantics validation, and production pilot preparation with explicit adapter boundaries.
+AgentLedger 1.5.x is a stable runtime-core line with Python as the reference implementation and Go, TypeScript, and Rust covered by shared runtime-core parity gates. The four language runtimes share the same runtime-core failure semantics, model evidence boundary, and normalized OMP runtime bridge: failed steps, retry scheduling, cancellation, lease recovery, Tool Ledger unknown-state handling, cost/failure attribution, evidence, replay, normalized failure envelopes, failure lifecycle, causal graph, replay plan, regression report, alerts, failure export mappings, archived model request/response/failure evidence, model-proposed tool-call records, and OMP session/turn/tool/state evidence mapping. The current runtime-core release is 1.5.2 across Python, Go, TypeScript, and Rust; Inspector remains a language-neutral companion viewer distributed through Python/PyPI. It is suitable for local use, framework adapter integration, reliability semantics validation, and production pilot preparation with explicit adapter boundaries.
 The runtime-core contract is stable; optional production adapters and external infrastructure hardening remain separately tracked. See [docs/MATURITY_MODEL.md](docs/MATURITY_MODEL.md), [docs/IMPLEMENTATION_STATUS.md](docs/IMPLEMENTATION_STATUS.md), and [docs/ROADMAP.md](docs/ROADMAP.md).
@@ -353,7 +356,3 @@ See [docs/RELEASE_CHECKLIST.md](docs/RELEASE_CHECKLIST.md) for the complete rele
 ## License
 Apache-2.0. See [LICENSE](LICENSE).
----
-generated by codex cli

{agentledger_runtime-1.4.2 → agentledger_runtime-1.5.2}/README.zh-CN.md RENAMED Viewed

@@ -3,7 +3,7 @@
 [English](README.md) | [中文](README.zh-CN.md)
 ![Python 3.11+](https://img.shields.io/badge/Python-3.11%2B-3776AB?logo=python&logoColor=white)
-![Version 1.4.x stable](https://img.shields.io/badge/Version-1.4.x--stable-111827)
+![Version 1.5.x stable](https://img.shields.io/badge/Version-1.5.x--stable-111827)
 ![License Apache-2.0](https://img.shields.io/badge/License-Apache--2.0-0f766e)
 ![Runtime Durable](https://img.shields.io/badge/Runtime-durable%20execution-1f6feb)
 ![Storage SQLite/Postgres/MySQL](https://img.shields.io/badge/Storage-SQLite%20%7C%20Postgres%20%7C%20MySQL-b45309)
@@ -12,7 +12,7 @@
 你的 Agent 调用了一个工具。它真的执行了吗？可以安全重试吗？之后能证明发生过什么吗？
-AgentLedger `1.4.x` 是面向 Agent Harness stack 的 runtime reliability layer。它不负责让 Agent 更会“思考”，也不替代完整 Harness 生态；它负责让 Agent run 在 worker 崩溃、工具失败、prompt 变更和长任务恢复时，仍然具备持久化、可审计、可重放、可治理和可恢复能力。
+AgentLedger `1.5.x` 是面向 Agent Harness stack 的 runtime reliability layer。它不负责让 Agent 更会“思考”，也不替代完整 Harness 生态；它负责让 Agent run 在 worker 崩溃、工具失败、prompt 变更和长任务恢复时，仍然具备持久化、可审计、可重放、可治理和可恢复能力。
 大多数 Agent 框架关注 planning、reasoning 和 workflow logic。AgentLedger 放在 LangChain、LangGraph、CrewAI、AutoGen、OpenAI Agents SDK、LlamaIndex、Semantic Kernel 或自定义 Agent 的下方或旁边，提供 state、tool、evidence、replay、recovery 相关的 runtime guarantees。
@@ -31,7 +31,9 @@ Python 仍然是 reference implementation；Go、TypeScript、Rust 已有 native
 | 找可运行示例 | [examples/README.md](examples/README.md)、[go/examples/README.md](go/examples/README.md)、[typescript/examples/README.md](typescript/examples/README.md)、[rust/examples/README.md](rust/examples/README.md) |
 | 查询 runtime 表 | [docs/zh/QUERY_EXAMPLES.md](docs/zh/QUERY_EXAMPLES.md) |
 | 可视化排查 run | [docs/zh/INSPECTOR.md](docs/zh/INSPECTOR.md) |
+| 运行 benchmark 和覆盖门禁 | [docs/zh/BENCHMARKS.md](docs/zh/BENCHMARKS.md) |
 | 理解 Harness stack 组合方式 | [docs/zh/HARNESS_STACK.md](docs/zh/HARNESS_STACK.md) |
+| 规划 Oh My Pi / OMP runtime adapter | [docs/zh/OMP_RUNTIME_ADAPTER_DESIGN.md](docs/zh/OMP_RUNTIME_ADAPTER_DESIGN.md) |
 | 理解开源生态价值 | [docs/zh/OPEN_SOURCE_IMPACT.md](docs/zh/OPEN_SOURCE_IMPACT.md) |
 | 理解维护者职责 | [docs/zh/MAINTAINER_NOTES.md](docs/zh/MAINTAINER_NOTES.md) |
 | 规划 adoption 工作 | [docs/zh/ADOPTION.md](docs/zh/ADOPTION.md) |
@@ -204,6 +206,7 @@ Temporal + LangGraph + AgentLedger 是合理的生产组合：Temporal 跑外层
 - 贡献方式：[CONTRIBUTING.md](CONTRIBUTING.md)
 - 社区行为：[CODE_OF_CONDUCT.md](CODE_OF_CONDUCT.md)
 - 发布检查：[docs/zh/RELEASE_CHECKLIST.md](docs/zh/RELEASE_CHECKLIST.md)
+- Benchmark 门禁：[docs/zh/BENCHMARKS.md](docs/zh/BENCHMARKS.md)
 - 兼容策略：[docs/VERSIONING.md](docs/VERSIONING.md)
 ## 快速开始
@@ -298,7 +301,7 @@ AgentLedger 也不是新的 LLM SDK，不是 workflow engine，不是通用 obse
 ## 当前成熟度
-AgentLedger 1.4.x 是 stable runtime-core line，Python 是 reference implementation，Go、TypeScript、Rust 已由共享 runtime-core parity gate 覆盖。四种语言 runtime 共享同一组 runtime-core failure semantics 和 model evidence boundary：failed step、retry scheduling、cancellation、lease recovery、Tool Ledger unknown-state handling、cost/failure attribution、evidence、replay、normalized failure envelope、failure lifecycle、causal graph、replay plan、regression report、alerts、failure export mappings、archived model request/response/failure evidence，以及 model-proposed tool-call records。当前 runtime-core release 是 1.4.2，并覆盖 Python、Go、TypeScript、Rust；Inspector 仍是 language-neutral companion viewer，通过 Python/PyPI 分发。适合本地使用、framework adapter integration、reliability semantics 验证，以及在明确 adapter 边界下做 production pilot 准备。
+AgentLedger 1.5.x 是 stable runtime-core line，Python 是 reference implementation，Go、TypeScript、Rust 已由共享 runtime-core parity gate 覆盖。四种语言 runtime 共享同一组 runtime-core failure semantics、model evidence boundary 和 normalized OMP runtime bridge：failed step、retry scheduling、cancellation、lease recovery、Tool Ledger unknown-state handling、cost/failure attribution、evidence、replay、normalized failure envelope、failure lifecycle、causal graph、replay plan、regression report、alerts、failure export mappings、archived model request/response/failure evidence、model-proposed tool-call records，以及 OMP session/turn/tool/state evidence mapping。当前 runtime-core release 是 1.5.2，并覆盖 Python、Go、TypeScript、Rust；Inspector 仍是 language-neutral companion viewer，通过 Python/PyPI 分发。适合本地使用、framework adapter integration、reliability semantics 验证，以及在明确 adapter 边界下做 production pilot 准备。
 runtime-core contract 已稳定；optional production adapter 和外部基础设施加固仍按独立阶段推进。详见 [docs/MATURITY_MODEL.md](docs/MATURITY_MODEL.md)、[docs/zh/IMPLEMENTATION_STATUS.md](docs/zh/IMPLEMENTATION_STATUS.md) 和 [docs/zh/ROADMAP.md](docs/zh/ROADMAP.md)。
@@ -353,7 +356,3 @@ cd ../rust && cargo run --quiet -- conformance
 ## License
 Apache-2.0. See [LICENSE](LICENSE)。
----
-generated by codex cli

{agentledger_runtime-1.4.2 → agentledger_runtime-1.5.2}/docs/ADAPTER_PACKAGING.md RENAMED Viewed

@@ -135,7 +135,7 @@ Each adapter package should provide:
 ## First Adapter Packages
-| Package | Owns in current `1.4.x` release train | Dependency status |
+| Package | Owns in current `1.5.x` release train | Dependency status |
 | --- | --- | --- |
 | `agentledger-postgres` | `PostgresStore`, `PostgresStoreConfig`, migration/conformance helpers | Requires `psycopg[binary]`; production rollout still needs real-service drills. |
 | `agentledger-mysql` | `MySQLStore`, `MySQLStoreConfig`, migration/conformance helpers | Requires `pymysql`; production rollout still needs real-service drills. |

{agentledger_runtime-1.4.2 → agentledger_runtime-1.5.2}/docs/ADAPTER_ROADMAP.md RENAMED Viewed

@@ -47,6 +47,7 @@ These are valuable but should follow the Priority 1 adapters or remain thinner f
 | Area | Adapter | Reason | Notes |
 | --- | --- | --- | --- |
 | Framework | LangChain Runnable | Broad usage, relatively generic callable boundary. | Keep thin; avoid depending on LangChain internals. |
+| Runtime | Oh My Pi / OMP | OMP is a runtime boundary that can emit session, turn, model, tool, failure, artifact, and state-change evidence into AgentLedger without making AgentLedger application-specific. | Built-in normalized bridge is implemented across Python, Go, TypeScript, and Rust in 1.5.2; package as `agentledger-omp` only if the bridge grows beyond a thin translation layer. |
 | Framework | CrewAI | Common for role-based teams, but AgentLedger should not inherit its orchestration model. | Wrap run/kickoff surfaces only. |
 | Framework | AutoGen | Useful for multi-agent conversations; APIs vary by generation. | Use adapter certification before claiming stability. |
 | Framework | OpenAI Agents SDK | Useful for OpenAI-native teams. | Keep aligned with official SDK surface; avoid duplicating SDK semantics. |
@@ -110,13 +111,10 @@ Every official adapter must provide:
 3. Docker sandbox adapter across Python, Go, TypeScript, and Rust.
 4. OpenTelemetry transport adapter across Python, Go, TypeScript, and Rust.
 5. LangGraph official Python adapter package and certification examples.
-6. LangChain / CrewAI / AutoGen / OpenAI Agents SDK / LlamaIndex / Semantic Kernel facades where ecosystems are stable.
-7. Kubernetes sandbox/backend recipe, then optional execution adapter.
-8. Temporal/Ray/Kubernetes scheduler/backend bridges based on real user demand.
-9. Add model evidence examples for OpenAI-compatible endpoints, Anthropic-style calls, and enterprise gateways without making AgentLedger a model router.
-10. Evaluate only, without implementation commitment, whether a Routing Advisor / Capability Router evidence boundary is useful for WisePick-style services. If later adopted, it should record externally supplied route suggestions, preserve replay by reusing stored routing evidence, and send feedback only after new real executions.
-11. Add eval adapter/export packages for mature open-source eval tools only when the boundary is evidence/replay conversion: Langfuse datasets/scores, Phoenix experiments, promptfoo test cases, DeepEval cases, Ragas rows, OpenAI Evals samples, and CI report inputs. Do not build dataset/scorer/experiment management inside AgentLedger.
----
-generated by codex cli
+6. Harden the built-in Oh My Pi / OMP runtime bridge with additional redaction/evidence-completeness fixtures, then create optional packages only if a separate package boundary becomes useful.
+7. LangChain / CrewAI / AutoGen / OpenAI Agents SDK / LlamaIndex / Semantic Kernel facades where ecosystems are stable.
+8. Kubernetes sandbox/backend recipe, then optional execution adapter.
+9. Temporal/Ray/Kubernetes scheduler/backend bridges based on real user demand.
+10. Add model evidence examples for OpenAI-compatible endpoints, Anthropic-style calls, and enterprise gateways without making AgentLedger a model router.
+11. Evaluate only, without implementation commitment, whether a Routing Advisor / Capability Router evidence boundary is useful for WisePick-style services. If later adopted, it should record externally supplied route suggestions, preserve replay by reusing stored routing evidence, and send feedback only after new real executions.
+12. Add eval adapter/export packages for mature open-source eval tools only when the boundary is evidence/replay conversion: Langfuse datasets/scores, Phoenix experiments, promptfoo test cases, DeepEval cases, Ragas rows, OpenAI Evals samples, and CI report inputs. Do not build dataset/scorer/experiment management inside AgentLedger.

{agentledger_runtime-1.4.2 → agentledger_runtime-1.5.2}/docs/ADOPTION.md RENAMED Viewed

@@ -21,6 +21,8 @@ Can I verify the reliability claim myself?
 | P0 | README first-screen pain point | The first screen explains the tool side-effect problem before listing architecture. |
 | P0 | Shareable article and short post | A maintainer can use `docs/articles/what-happened-after-agent-tool-failure.zh-CN.md` and `docs/articles/social-posts.md` without inventing positioning copy from scratch. |
 | P1 | MCP governance example | Dependency-free MCP-style tools demonstrate schema, approval, sandbox metadata, idempotency, and audit evidence across Python, Go, TypeScript, and Rust. |
+| P1 | OpenAI Agents SDK-style approval/replay example | A dependency-free SDK-style runner demonstrates model evidence, proposed tool calls, approval, Tool Ledger, evidence export, Inspector, and replay. |
+| P1 | Temporal bridge retry safety example | A dependency-free workflow/activity facade demonstrates backend retry while AgentLedger prevents duplicate node-internal side effects. |
 | P1 | Public issue/discussion list | The next adoption tasks are easy to open as GitHub issues or discussions. |
 | P1 | Case study template | A real integration can be documented without exposing private data. |
@@ -32,10 +34,10 @@ These can be opened as GitHub issues when the project is ready for public tracki
 |---|---|---|
 | Record a side-effect safety GIF from the showcase | adoption | Turns the core value into a short visual artifact for README, social posts, and issue discussions. |
 | Build a cross-language 3-minute Tool Ledger demo | example | Shows the core value in a few minutes across Python, Go, TypeScript, and Rust. |
-| Add OpenAI Agents SDK approval/replay example | example | Connects AgentLedger to a major agent SDK boundary without claiming official endorsement. |
+| Add OpenAI Agents SDK approval/replay example | example | Connects AgentLedger to a major agent SDK boundary without claiming official endorsement. Implemented as `examples/openai_agents/approval_replay.py`. |
 | Add MCP tool governance example | example | Shows how MCP-style tools should pass through policy, approval, sandbox, idempotency, and evidence. |
 | Prototype AgentLedger Inspector | debug tool | Makes run timelines, Tool Ledger, approvals, replay, and failures visible. |
-| Add Temporal bridge example | integration | Clarifies Temporal owns workflow lifecycle while AgentLedger owns node-internal reliability. |
+| Add Temporal bridge example | integration | Clarifies Temporal owns workflow lifecycle while AgentLedger owns node-internal reliability. Implemented as `examples/temporal_bridge/demo.py`. |
 | Add tool-injection risk scanner | security | Detects risky tool schemas, missing approval/sandbox, and runtime-boundary bypass patterns. |
 | Publish legal-agent case study | case study | Shows a realistic audit/evidence use case without private data. |

agentledger_runtime-1.5.2/docs/BENCHMARKS.md ADDED Viewed

@@ -0,0 +1,111 @@
+# Benchmarks
+AgentLedger benchmarks are release-quality gates, not marketing numbers. They verify that the runtime still covers the full semantic surface while also recording same-machine timing for representative local paths.
+The default benchmark is dependency-free for runtime scenarios:
+- SQLite `StateStore`
+- `LocalBlobStore`
+- no model provider calls
+- no real database, object store, Docker daemon, or cloud service
+- optional local CLI timing for Python, Go, TypeScript, and Rust conformance commands
+## Run
+From the repository root:
+```bash
+PYTHONDONTWRITEBYTECODE=1 PYTHONPATH=src python3 scripts/benchmark_runtime.py --iterations 20 --output-dir /tmp/agentledger-benchmark
+```
+For a fast Python-only smoke while editing:
+```bash
+PYTHONDONTWRITEBYTECODE=1 PYTHONPATH=src python3 scripts/benchmark_runtime.py --iterations 1 --skip-language-commands --output-dir /tmp/agentledger-benchmark-smoke
+```
+The command writes:
+- `benchmark.json`: machine-readable result, samples, coverage matrix, validation failures, and command output tails.
+- `benchmark.md`: human-readable report for release review.
+- `run-*/`: isolated runtime/evidence/static HTML artifacts for that invocation.
+- `execution_claim`: `release_gate` for the default full command, or `local_runtime_smoke` when language commands are skipped.
+- `warnings`: explicit caveats for dry-run, synthetic, or skipped validation paths.
+## Coverage
+The benchmark reads `contracts/conformance/runtime_semantics.v1.json` and reports every required semantic check in `coverage_matrix`.
+Current required coverage includes:
+- durable run, persistence, replay, and evidence export
+- local blob store
+- tool schema validation
+- worker/service and scheduler behavior
+- Tool Ledger idempotent retry
+- policy, approval, and sandbox fail-closed behavior
+- cost and failure attribution
+- media artifact and stream checkpoint evidence
+- evidence consumers, trace, OTLP JSON, Inspector HTML, and time-travel HTML
+- ops readiness, storage schema helpers, and non-destructive retention/backup checks
+- MCP and framework adapter contracts
+- boundary lint
+- adversarial review and evidence regression checks
+- failure injection
+- shadow/repro harness primitives
+- optional and official adapter certification/dry-run boundaries
+When language commands are enabled, Go, TypeScript, and Rust conformance CLIs must report the shared manifest ids. A full successful run should show:
+```text
+required_check_count = 27
+covered_check_count = 27
+not_run_count = 0
+by_status.measured_and_language_conformance = 27
+```
+The coverage matrix also includes `verification_depths`:
+- `executable_local` / `executable_local_fault`: real local runtime execution.
+- `negative_runtime_path`: an intentionally failing runtime boundary such as invalid tool input, approval pause, sandbox fail-closed, or budget denial.
+- `read_model_local`: evidence, replay, failure, cost, Inspector, scheduler, retention, or backup read models over persisted local data.
+- `synthetic_probe`: deliberately generated failure/lint fixtures.
+- `contract_dry_run` / `static_helper`: adapter contracts, DDL helpers, or static surfaces that do not prove a live external service.
+- `language_conformance`: Python, Go, TypeScript, or Rust CLI conformance reported the shared semantic check id.
+## Interpreting Results
+Use the timing numbers for same-machine regression tracking only. They are not a portable performance claim across laptops, CI runners, operating systems, or Python versions.
+The benchmark intentionally measures several non-happy-path behaviors:
+- crash after a side effect, followed by safe retry
+- exactly-once external side-effect count through Tool Ledger idempotency
+- invalid tool input rejected before execution
+- approval pause and resume
+- required sandbox fail-closed path
+- model call evidence, model failure evidence, tool-call proposal evidence, and model cost attribution
+- budget exhaustion that blocks tool execution before a side effect can run
+- failure injection for retry exhaustion, stale lease fencing, cancellation fencing, and side-effect idempotency
+- boundary lint detecting a deliberately unsafe direct shell call
+Some adapter-related checks are contract/dry-run checks by design. Postgres, MySQL, S3, Docker, Langfuse, OTLP collectors, and Temporal require separate service-backed validation before production claims.
+By default, the full release gate fails if a language conformance command fails, times out, or is skipped because a toolchain is missing. Use `--allow-language-skips` only for local investigation, not for release evidence.
+## Release Use
+For runtime-core or cross-language releases, run:
+```bash
+PYTHONDONTWRITEBYTECODE=1 PYTHONPATH=src python3 scripts/benchmark_runtime.py --iterations 20 --output-dir /tmp/agentledger-benchmark
+python3.11 scripts/check_language_parity.py
+```
+Attach or summarize `benchmark.md` in release notes when the release changes runtime semantics, failure handling, Inspector/debug output, evidence consumers, adapters, or language parity.
+The GitHub Actions workflow also runs the full benchmark in the `Runtime benchmark gate` job on `main` pushes and pull requests. That job uploads an artifact named `agentledger-benchmark` containing `benchmark.json`, `benchmark.md`, and the isolated `run-*/` evidence/debug artifacts. Use the latest successful CI artifact as release evidence, and keep separate service-backed validation for Postgres, MySQL, S3, Docker, Langfuse, OTLP collectors, Temporal, or other production adapter claims.
+---
+generated by codex cli

{agentledger_runtime-1.4.2 → agentledger_runtime-1.5.2}/docs/COMPLETE_CORE_PARITY_CHECKLIST.md RENAMED Viewed

@@ -55,8 +55,8 @@ Excluded or not applicable:
 | CLI baseline | `--help`, `doctor`, `version`, `quickstart`, `conformance`, `contract validate`, `contract export` | `agentledger` CLI | `agentledger-go` | `agentledger-ts` | `agentledger-rust` | `scripts/check_complete_core_parity.py` | done |
 | Quickstart docs | Language quickstart and adapter quickstart | README + docs | `go/README.md` | `typescript/README.md` | `rust/README.md` | docs link check | done |
 | Examples | Runnable examples for core runtime and adapter API | Python examples | `go/examples/quickstart/main.go` | `typescript/examples/quickstart/quickstart.js` | `rust/examples/quickstart.rs` | `scripts/check_complete_core_parity.py` | done |
-| Package metadata | Installable package metadata in the current 1.4 release family | PyPI metadata `1.4.x` | `go.mod` tag `go/v1.4.2` for current baseline | npm package `1.4.2` for current baseline | `Cargo.toml` `1.4.2` for current baseline | `scripts/check_complete_core_parity.py` release-family check | done |
-| Package install smoke | Install/import/run from published or built package | PyPI `agentledger-runtime==1.4.2` release smoke after publish | `go/v1.4.2` clean external `go get` smoke after tag | npm `agentledger-runtime@1.4.2` release smoke after publish | crates.io `agentledger-runtime==1.4.2` release smoke after publish | publish logs + `scripts/check_complete_core_parity.py` dry-run gates | release-gated |
+| Package metadata | Installable package metadata in the current 1.5 release family | PyPI metadata `1.5.x` | `go.mod` tag `go/v1.5.2` for current baseline | npm package `1.5.2` for current baseline | `Cargo.toml` `1.5.2` for current baseline | `scripts/check_complete_core_parity.py` release-family check | done |
+| Package install smoke | Install/import/run from published or built package | PyPI `agentledger-runtime==1.5.2` release smoke after publish | `go/v1.5.2` clean external `go get` smoke after tag | npm `agentledger-runtime@1.5.2` release smoke after publish | crates.io `agentledger-runtime==1.5.2` release smoke after publish | publish logs + `scripts/check_complete_core_parity.py` dry-run gates | release-gated |
 | Release docs | Changelog, release checklist, status docs reflect exact parity boundary | docs | docs | docs | docs | docs link check | done |
 | Comparison docs | Honest overlap with LangChain/LangGraph/LangSmith/Langfuse/etc. | docs | docs | docs | docs | docs link check | done |
@@ -67,7 +67,7 @@ The strict core parity gate now covers the previously weak areas:
 1. CLI baseline is automatically checked for all four language CLIs.
 2. Go, TypeScript, and Rust have runnable quickstart example files.
 3. TypeScript and Rust package surfaces have package dry-run checks (`npm pack --dry-run`, `cargo package --allow-dirty --no-verify`) and post-publish install smokes are required for release.
-4. Package release families are checked across Python, TypeScript, and Rust. The current core release family is `1.4`; 1.4.2 keeps the four-language release train aligned while consolidating model evidence UX, export mappings, examples, and boundary lint around the 1.4.0/1.4.1 runtime-core features.
+4. Package release families are checked across Python, TypeScript, and Rust. The current core release family is `1.5`; `1.5.2` is the latest aligned patch in that family, while `1.5.0` introduced the framework/Temporal adoption examples, smoke coverage, and benchmark gates.
 5. Go external module consumption is tag/release dependent; each release should repeat the clean external `go get` smoke after pushing the `go/vX.Y.Z` tag.
 6. Real service-backed hardening remains out of scope for core parity and stays documented as optional follow-up work.
@@ -82,7 +82,3 @@ python3.11 scripts/check_complete_core_parity.py
 ```
 `check_complete_core_parity.py` must verify CLI baseline, runnable examples, package metadata, and docs links in addition to semantic conformance.
----
-generated by codex cli

{agentledger_runtime-1.4.2 → agentledger_runtime-1.5.2}/docs/EXECUTION_BACKENDS.md RENAMED Viewed

@@ -82,6 +82,8 @@ AgentLedger is unnecessary for some Temporal workflows. If an agent node has no
 AgentLedger becomes valuable when agent nodes call models and tools, write external systems, need permissions or sandboxing, require evidence bundles, or must replay without repeating real side effects.
+See `../examples/temporal_bridge/README.md` for a dependency-free bridge example that simulates a Temporal-style activity retry after a worker crash. The example does not require a Temporal server; it demonstrates the contract boundary and shows how workflow/activity ids can be carried as runtime evidence metadata.
 ## Temporal Adapter Shape
 A Temporal integration should usually look like this:

agentledger-runtime 1.4.2__tar.gz → 1.5.2__tar.gz

agentledger-runtime 1.4.2tar.gz → 1.5.2tar.gz