PyPI - agentledger-runtime - Versions diffs - 1.2.3__tar.gz → 1.3.0__tar.gz - Mend

agentledger-runtime 1.2.3tar.gz → 1.3.0tar.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 (376) hide show

{agentledger_runtime-1.2.3 → agentledger_runtime-1.3.0}/CHANGELOG.md RENAMED Viewed

@@ -8,6 +8,58 @@ This project follows semantic versioning for the stable runtime-core contract. O
 No unreleased changes yet.
+## 1.3.0
+### Added
+- `agentledger inspector` CLI with read-only `run` and `evidence` subcommands.
+- Language-neutral Inspector read model `agentledger.inspector.v1` for run timeline, Tool Ledger, approvals, policy decisions, cost/failure records, artifacts, and risk flags.
+- Static HTML Inspector export for local or internal debugging without starting a server.
+- Read-only SQLite runtime data source and Postgres/MySQL read data sources through existing StateStore adapter boundaries.
+- Optional `agentledger-inspector` companion package for users who want to depend on the read model and extension API directly.
+### Clarified
+- Inspector is an evidence/runtime metadata consumer, not a permissions system or write/control plane.
+- Use read-only database credentials for Postgres/MySQL inspection; evidence-bundle input remains the most portable path across Python, Go, TypeScript, and Rust.
+## 1.2.4
+### Added
+- Open-source impact documentation for AgentLedger's early-stage agent reliability and governance infrastructure positioning.
+- Maintainer notes documenting project ownership, review principles, release responsibilities, coding-agent usage, and maintenance signals.
+- Cross-language 3-minute side-effect safety demos showing crash/retry without duplicate external writes.
+- Cross-language MCP governance examples showing descriptor annotations for side effects, approval, sandbox metadata, idempotency, and audit evidence.
+- Adoption plan, public issue/discussion candidates, and a legal-agent case study template.
+### Changed
+- README first screen now leads with the tool side-effect safety problem before describing architecture.
+- MCP tool adapter now maps governance annotations such as `approval_required`, `sandbox_required`, `sandbox_executor`, and `sandbox_policy`.
+### Clarified
+- Roadmap guidance for open-source adoption, OpenAI Agents SDK/MCP examples, Codex-assisted maintainer workflows, and public usage evidence without changing runtime-core semantics.
+- 1.2.4 does not change runtime-core semantics; it is an adoption and example-focused release.
+## 1.2.3
+### Added
+- SQL query examples for runtime inspection, multi-table timelines, approvals, costs, artifacts, and large business-schema integration patterns.
+- `agentledger-langfuse` as an official optional observability adapter boundary.
+- TypeScript subpath/package, Go adapter boundary, and Rust crate/feature boundary for Langfuse-style evidence/trace payload export.
+### Changed
+- Updated adapter packaging, certification, optional-adapter conformance, and documentation entrypoints for the Langfuse adapter boundary.
+- Removed tracked local runtime state from the repository.
+### Clarified
+- Langfuse support is an adapter/export boundary, not a replacement for Langfuse or a binding to the Langfuse SDK.
 ## 1.2.2
 ### Added
@@ -90,7 +142,7 @@ No unreleased changes yet.
 - Python reference runtime-core parity is now declared for Go, TypeScript, and Rust within the AgentLedger core scope.
 - Concrete production adapters such as Postgres, S3/MinIO, Docker, Kubernetes, MCP transport, LangGraph, Temporal, and OpenTelemetry remain optional packages unless explicitly shipped for a language.
-- AgentLedger remains a framework/library/runtime layer, not SaaS and not a general workflow, eval, RAG, or deployment platform.
+- AgentLedger remains a framework/library/runtime layer, not a managed service and not a general workflow, eval, RAG, or deployment product.
 ## 1.0.0

{agentledger_runtime-1.2.3 → agentledger_runtime-1.3.0}/PKG-INFO RENAMED Viewed

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agentledger-runtime
-Version: 1.2.3
+Version: 1.3.0
 Summary: Runtime reliability layer for Agent Harness stacks
 Project-URL: Homepage, https://github.com/yaogdu/AgentLedger
 Project-URL: Repository, https://github.com/yaogdu/AgentLedger
@@ -21,30 +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-langfuse<2,>=1.2; extra == 'all'
-Requires-Dist: agentledger-langgraph<2,>=1.2; extra == 'all'
-Requires-Dist: agentledger-mcp<2,>=1.2; extra == 'all'
-Requires-Dist: agentledger-mysql<2,>=1.2; extra == 'all'
-Requires-Dist: agentledger-otel<2,>=1.2; extra == 'all'
-Requires-Dist: agentledger-postgres<2,>=1.2; extra == 'all'
-Requires-Dist: agentledger-s3<2,>=1.2; extra == 'all'
-Requires-Dist: agentledger-sandbox-docker<2,>=1.2; extra == 'all'
+Requires-Dist: agentledger-inspector<2,>=1.3; extra == 'all'
+Requires-Dist: agentledger-langfuse<2,>=1.3; extra == 'all'
+Requires-Dist: agentledger-langgraph<2,>=1.3; extra == 'all'
+Requires-Dist: agentledger-mcp<2,>=1.3; extra == 'all'
+Requires-Dist: agentledger-mysql<2,>=1.3; extra == 'all'
+Requires-Dist: agentledger-otel<2,>=1.3; extra == 'all'
+Requires-Dist: agentledger-postgres<2,>=1.3; extra == 'all'
+Requires-Dist: agentledger-s3<2,>=1.3; extra == 'all'
+Requires-Dist: agentledger-sandbox-docker<2,>=1.3; extra == 'all'
 Provides-Extra: docker
-Requires-Dist: agentledger-sandbox-docker<2,>=1.2; extra == 'docker'
+Requires-Dist: agentledger-sandbox-docker<2,>=1.3; extra == 'docker'
+Provides-Extra: inspector
+Requires-Dist: agentledger-inspector<2,>=1.3; extra == 'inspector'
 Provides-Extra: langfuse
-Requires-Dist: agentledger-langfuse<2,>=1.2; extra == 'langfuse'
+Requires-Dist: agentledger-langfuse<2,>=1.3; extra == 'langfuse'
 Provides-Extra: langgraph
-Requires-Dist: agentledger-langgraph<2,>=1.2; extra == 'langgraph'
+Requires-Dist: agentledger-langgraph<2,>=1.3; extra == 'langgraph'
 Provides-Extra: mcp
-Requires-Dist: agentledger-mcp<2,>=1.2; extra == 'mcp'
+Requires-Dist: agentledger-mcp<2,>=1.3; extra == 'mcp'
 Provides-Extra: mysql
-Requires-Dist: agentledger-mysql<2,>=1.2; extra == 'mysql'
+Requires-Dist: agentledger-mysql<2,>=1.3; extra == 'mysql'
 Provides-Extra: otel
-Requires-Dist: agentledger-otel<2,>=1.2; extra == 'otel'
+Requires-Dist: agentledger-otel<2,>=1.3; extra == 'otel'
 Provides-Extra: postgres
-Requires-Dist: agentledger-postgres<2,>=1.2; extra == 'postgres'
+Requires-Dist: agentledger-postgres<2,>=1.3; extra == 'postgres'
 Provides-Extra: s3
-Requires-Dist: agentledger-s3<2,>=1.2; extra == 's3'
+Requires-Dist: agentledger-s3<2,>=1.3; extra == 's3'
 Description-Content-Type: text/markdown
 # AgentLedger
@@ -52,14 +55,16 @@ 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 1.2.3 stable](https://img.shields.io/badge/Version-1.2.3--stable-111827)
+![Version 1.3.0 stable](https://img.shields.io/badge/Version-1.3.0--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)
 ![Replay Evidence](https://img.shields.io/badge/Replay-evidence%20driven-7c3aed)
 ![Tool Ledger](https://img.shields.io/badge/Tools-ledger%20guarded-d97706)
-AgentLedger `1.2.3` 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.
+Your agent called a tool. Did it happen? Can you retry safely? Can you prove it later?
+AgentLedger `1.3.0` 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.
@@ -75,7 +80,11 @@ Python remains the reference implementation, and Go, TypeScript, and Rust now ha
 | Choose Python / Go / TypeScript / Rust | [docs/LANGUAGE_QUICKSTART.md](docs/LANGUAGE_QUICKSTART.md) |
 | 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) |
 | Understand Harness stack composition | [docs/HARNESS_STACK.md](docs/HARNESS_STACK.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) |
 | Understand what is equal across languages | [docs/LANGUAGE_IMPLEMENTATION_COMPARISON.md](docs/LANGUAGE_IMPLEMENTATION_COMPARISON.md) |
 | Install optional adapter packages | [docs/ADAPTER_PACKAGING.md](docs/ADAPTER_PACKAGING.md) |
 | Use Go correctly | [go/README.md](go/README.md#install) |
@@ -88,7 +97,7 @@ Python remains the reference implementation, and Go, TypeScript, and Rust now ha
 | What is stable? | The v1.x runtime-core contract: durable execution, Tool Ledger, evidence/replay, policy/approval/sandbox boundaries, cost/failure reports, worker/conformance, and Python reference implementation with Go/TypeScript/Rust runtime-core parity gates. |
 | What is optional? | Postgres, MySQL, S3/MinIO, framework-native packages, OTLP collector transport, sandbox infrastructure, distributed deployment recipes, and real-service hardening. |
 | What is experimental? | Some concrete provider adapters, media/stream processing adapters, and real-service hardening paths. Go/TypeScript/Rust runtime-core baselines are native implementations covered by shared conformance. |
-| What is not in core? | Planning engines, full eval systems, RAG/vector memory, trace stores, hosted application products, and hosted sandbox infrastructure. |
+| What is not in core? | Planning engines, full eval systems, RAG/vector memory, trace stores, application administration backends, and sandbox infrastructure providers. |
 | How should other languages work? | This repo is contract-first. Python is the reference runtime; Go, Node/TypeScript, and Rust now have native runtime baselines under `go/`, `typescript/`, and `rust/`. Runtime-ready requires `contracts/agentledger.runtime.v1.json`, the shared semantic manifest `contracts/conformance/runtime_semantics.v1.json`, shared conformance fixtures, and per-language conformance commands. |
 ## Scope principle
@@ -164,10 +173,12 @@ The intended production shape is therefore not `AgentLedger instead of LangGraph
 ## Examples
-The repository includes small quickstarts plus a richer multi-language Travel Assistant demo that shows the same runtime ideas across Python, Go, Rust, and TypeScript.
+The repository includes cross-language 3-minute side-effect safety demos, MCP governance demos, small quickstarts, and a richer multi-language Travel Assistant demo that shows the same runtime ideas across Python, Go, Rust, and TypeScript.
-| Language | Demo | Run |
+| Goal | Demo | Run |
 | --- | --- | --- |
+| 3-minute side-effect safety | Python / Go / Rust / TypeScript | `PYTHONPATH=src python3 examples/three_minute_demo/demo.py`; `cd go && go run ./examples/three_minute_demo`; `cd rust && cargo run --example three_minute_demo`; `cd typescript && node examples/three_minute_demo/three_minute_demo.js` |
+| MCP tool governance | Python / Go / Rust / TypeScript | `PYTHONPATH=src python3 examples/mcp_governance/demo.py`; `cd go && go run ./examples/mcp_governance`; `cd rust && cargo run --example mcp_governance`; `cd typescript && node examples/mcp_governance/mcp_governance.js` |
 | Python | `examples/travel_assistant/demo.py` | `python3 examples/travel_assistant/demo.py` |
 | Go | `go/examples/travel_assistant/main.go` | `cd go && go run examples/travel_assistant/main.go` |
 | Rust | `rust/examples/travel_assistant.rs` | `cd rust && cargo run --example travel_assistant` |
@@ -322,7 +333,7 @@ AgentLedger is also not a new LLM SDK, not a workflow engine, not a general obse
 ## Current maturity
-AgentLedger 1.2.3 is a stable runtime-core release with Python as the reference implementation and Go, TypeScript, and Rust covered by shared runtime-core parity gates. It is suitable for local use, framework adapter integration, reliability semantics validation, and production pilot preparation with explicit adapter boundaries.
+AgentLedger 1.3.0 is a stable runtime-core release with Python as the reference implementation and Go, TypeScript, and Rust covered by shared runtime-core parity gates. 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).
@@ -331,6 +342,7 @@ The runtime-core contract is stable; optional production adapters and external i
 | Goal | Document |
 | --- | --- |
 | Use the runtime | [docs/USAGE.md](docs/USAGE.md) |
+| Inspect runtime evidence | [docs/INSPECTOR.md](docs/INSPECTOR.md) |
 | Understand architecture | [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md) |
 | Compare with adjacent tools | [docs/COMPARISONS.md](docs/COMPARISONS.md) |
 | Read implementation details | [docs/DESIGN_AND_IMPLEMENTATION.md](docs/DESIGN_AND_IMPLEMENTATION.md) |

{agentledger_runtime-1.2.3 → agentledger_runtime-1.3.0}/README.md RENAMED Viewed

@@ -3,14 +3,16 @@
 [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 1.2.3 stable](https://img.shields.io/badge/Version-1.2.3--stable-111827)
+![Version 1.3.0 stable](https://img.shields.io/badge/Version-1.3.0--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)
 ![Replay Evidence](https://img.shields.io/badge/Replay-evidence%20driven-7c3aed)
 ![Tool Ledger](https://img.shields.io/badge/Tools-ledger%20guarded-d97706)
-AgentLedger `1.2.3` 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.
+Your agent called a tool. Did it happen? Can you retry safely? Can you prove it later?
+AgentLedger `1.3.0` 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.
@@ -26,7 +28,11 @@ Python remains the reference implementation, and Go, TypeScript, and Rust now ha
 | Choose Python / Go / TypeScript / Rust | [docs/LANGUAGE_QUICKSTART.md](docs/LANGUAGE_QUICKSTART.md) |
 | 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) |
 | Understand Harness stack composition | [docs/HARNESS_STACK.md](docs/HARNESS_STACK.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) |
 | Understand what is equal across languages | [docs/LANGUAGE_IMPLEMENTATION_COMPARISON.md](docs/LANGUAGE_IMPLEMENTATION_COMPARISON.md) |
 | Install optional adapter packages | [docs/ADAPTER_PACKAGING.md](docs/ADAPTER_PACKAGING.md) |
 | Use Go correctly | [go/README.md](go/README.md#install) |
@@ -39,7 +45,7 @@ Python remains the reference implementation, and Go, TypeScript, and Rust now ha
 | What is stable? | The v1.x runtime-core contract: durable execution, Tool Ledger, evidence/replay, policy/approval/sandbox boundaries, cost/failure reports, worker/conformance, and Python reference implementation with Go/TypeScript/Rust runtime-core parity gates. |
 | What is optional? | Postgres, MySQL, S3/MinIO, framework-native packages, OTLP collector transport, sandbox infrastructure, distributed deployment recipes, and real-service hardening. |
 | What is experimental? | Some concrete provider adapters, media/stream processing adapters, and real-service hardening paths. Go/TypeScript/Rust runtime-core baselines are native implementations covered by shared conformance. |
-| What is not in core? | Planning engines, full eval systems, RAG/vector memory, trace stores, hosted application products, and hosted sandbox infrastructure. |
+| What is not in core? | Planning engines, full eval systems, RAG/vector memory, trace stores, application administration backends, and sandbox infrastructure providers. |
 | How should other languages work? | This repo is contract-first. Python is the reference runtime; Go, Node/TypeScript, and Rust now have native runtime baselines under `go/`, `typescript/`, and `rust/`. Runtime-ready requires `contracts/agentledger.runtime.v1.json`, the shared semantic manifest `contracts/conformance/runtime_semantics.v1.json`, shared conformance fixtures, and per-language conformance commands. |
 ## Scope principle
@@ -115,10 +121,12 @@ The intended production shape is therefore not `AgentLedger instead of LangGraph
 ## Examples
-The repository includes small quickstarts plus a richer multi-language Travel Assistant demo that shows the same runtime ideas across Python, Go, Rust, and TypeScript.
+The repository includes cross-language 3-minute side-effect safety demos, MCP governance demos, small quickstarts, and a richer multi-language Travel Assistant demo that shows the same runtime ideas across Python, Go, Rust, and TypeScript.
-| Language | Demo | Run |
+| Goal | Demo | Run |
 | --- | --- | --- |
+| 3-minute side-effect safety | Python / Go / Rust / TypeScript | `PYTHONPATH=src python3 examples/three_minute_demo/demo.py`; `cd go && go run ./examples/three_minute_demo`; `cd rust && cargo run --example three_minute_demo`; `cd typescript && node examples/three_minute_demo/three_minute_demo.js` |
+| MCP tool governance | Python / Go / Rust / TypeScript | `PYTHONPATH=src python3 examples/mcp_governance/demo.py`; `cd go && go run ./examples/mcp_governance`; `cd rust && cargo run --example mcp_governance`; `cd typescript && node examples/mcp_governance/mcp_governance.js` |
 | Python | `examples/travel_assistant/demo.py` | `python3 examples/travel_assistant/demo.py` |
 | Go | `go/examples/travel_assistant/main.go` | `cd go && go run examples/travel_assistant/main.go` |
 | Rust | `rust/examples/travel_assistant.rs` | `cd rust && cargo run --example travel_assistant` |
@@ -273,7 +281,7 @@ AgentLedger is also not a new LLM SDK, not a workflow engine, not a general obse
 ## Current maturity
-AgentLedger 1.2.3 is a stable runtime-core release with Python as the reference implementation and Go, TypeScript, and Rust covered by shared runtime-core parity gates. It is suitable for local use, framework adapter integration, reliability semantics validation, and production pilot preparation with explicit adapter boundaries.
+AgentLedger 1.3.0 is a stable runtime-core release with Python as the reference implementation and Go, TypeScript, and Rust covered by shared runtime-core parity gates. 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).
@@ -282,6 +290,7 @@ The runtime-core contract is stable; optional production adapters and external i
 | Goal | Document |
 | --- | --- |
 | Use the runtime | [docs/USAGE.md](docs/USAGE.md) |
+| Inspect runtime evidence | [docs/INSPECTOR.md](docs/INSPECTOR.md) |
 | Understand architecture | [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md) |
 | Compare with adjacent tools | [docs/COMPARISONS.md](docs/COMPARISONS.md) |
 | Read implementation details | [docs/DESIGN_AND_IMPLEMENTATION.md](docs/DESIGN_AND_IMPLEMENTATION.md) |

{agentledger_runtime-1.2.3 → agentledger_runtime-1.3.0}/README.zh-CN.md RENAMED Viewed

@@ -3,14 +3,16 @@
 [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 1.2.3 stable](https://img.shields.io/badge/Version-1.2.3--stable-111827)
+![Version 1.3.0 stable](https://img.shields.io/badge/Version-1.3.0--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)
 ![Replay Evidence](https://img.shields.io/badge/Replay-evidence%20driven-7c3aed)
 ![Tool Ledger](https://img.shields.io/badge/Tools-ledger%20guarded-d97706)
-AgentLedger `1.2.3` 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。
+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 `1.3.0` 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。
@@ -26,7 +28,11 @@ Python 仍然是 reference implementation；Go、TypeScript、Rust 已有 native
 | 选择 Python / Go / TypeScript / Rust | [docs/zh/LANGUAGE_QUICKSTART.md](docs/zh/LANGUAGE_QUICKSTART.md) |
 | 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) |
 | 理解 Harness stack 组合方式 | [docs/zh/HARNESS_STACK.md](docs/zh/HARNESS_STACK.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) |
 | 理解四语言哪些对齐、哪些不对齐 | [docs/zh/LANGUAGE_IMPLEMENTATION_COMPARISON.md](docs/zh/LANGUAGE_IMPLEMENTATION_COMPARISON.md) |
 | 安装 optional adapter packages | [docs/zh/ADAPTER_PACKAGING.md](docs/zh/ADAPTER_PACKAGING.md) |
 | 正确使用 Go | [go/README.md](go/README.md#install) |
@@ -116,10 +122,12 @@ AgentLedger 本身不是完整 Agent Harness。它的设计目标是和 Harness
 ## 示例
-仓库里既有最小 quickstart，也有一个更完整的多语言 Travel Assistant demo，用来展示 Python、Go、Rust、TypeScript 下相同的 runtime 思路。
+仓库里包含四语言 3-minute side-effect safety demo、MCP governance demo、最小 quickstart，以及一个更完整的多语言 Travel Assistant demo，用来展示 Python、Go、Rust、TypeScript 下相同的 runtime 思路。
-| 语言 | Demo | 运行方式 |
+| 目标 | Demo | 运行方式 |
 | --- | --- | --- |
+| 3 分钟副作用安全 demo | Python / Go / Rust / TypeScript | `PYTHONPATH=src python3 examples/three_minute_demo/demo.py`; `cd go && go run ./examples/three_minute_demo`; `cd rust && cargo run --example three_minute_demo`; `cd typescript && node examples/three_minute_demo/three_minute_demo.js` |
+| MCP tool governance | Python / Go / Rust / TypeScript | `PYTHONPATH=src python3 examples/mcp_governance/demo.py`; `cd go && go run ./examples/mcp_governance`; `cd rust && cargo run --example mcp_governance`; `cd typescript && node examples/mcp_governance/mcp_governance.js` |
 | Python | `examples/travel_assistant/demo.py` | `python3 examples/travel_assistant/demo.py` |
 | Go | `go/examples/travel_assistant/main.go` | `cd go && go run examples/travel_assistant/main.go` |
 | Rust | `rust/examples/travel_assistant.rs` | `cd rust && cargo run --example travel_assistant` |
@@ -274,7 +282,7 @@ AgentLedger 也不是新的 LLM SDK，不是 workflow engine，不是通用 obse
 ## 当前成熟度
-AgentLedger 1.2.0 是 stable runtime-core release，Python 是 reference implementation，Go、TypeScript、Rust 已由共享 runtime-core parity gate 覆盖；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 1.3.0 是 stable runtime-core release，Python 是 reference implementation，Go、TypeScript、Rust 已由共享 runtime-core parity gate 覆盖；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)。
@@ -283,6 +291,7 @@ runtime-core contract 已稳定；optional production adapter 和外部基础设
 | 目标 | 文档 |
 | --- | --- |
 | 学会使用 runtime | [docs/zh/USAGE.md](docs/zh/USAGE.md) |
+| 查看 runtime evidence | [docs/zh/INSPECTOR.md](docs/zh/INSPECTOR.md) |
 | 理解整体架构 | [docs/zh/ARCHITECTURE.md](docs/zh/ARCHITECTURE.md) |
 | 对比相邻工具 | [docs/zh/COMPARISONS.md](docs/zh/COMPARISONS.md) |
 | 阅读实现细节 | [docs/zh/DESIGN_AND_IMPLEMENTATION.md](docs/zh/DESIGN_AND_IMPLEMENTATION.md) |

{agentledger_runtime-1.2.3 → agentledger_runtime-1.3.0}/docs/ADAPTER_CERTIFICATION.md RENAMED Viewed

@@ -212,10 +212,10 @@ This does not make an adapter production-ready by itself. It gives users a concr
 AgentLedger can generate a machine-readable starting bundle for official adapter profiles:
 ```bash
-PYTHONPATH=src python3 -m agentledger adapter certify --kind postgres --adapter-version 1.2.3
-PYTHONPATH=src python3 -m agentledger adapter certify --kind mysql --adapter-version 1.2.3 --out ./mysql-certification.json
-PYTHONPATH=src python3 -m agentledger adapter certify --kind s3 --adapter-version 1.2.3 --out ./s3-certification.json
-PYTHONPATH=src python3 -m agentledger adapter certify --kind langgraph --adapter-version 1.2.3 --package-name agentledger-langgraph
+PYTHONPATH=src python3 -m agentledger adapter certify --kind postgres --adapter-version 1.3.0
+PYTHONPATH=src python3 -m agentledger adapter certify --kind mysql --adapter-version 1.3.0 --out ./mysql-certification.json
+PYTHONPATH=src python3 -m agentledger adapter certify --kind s3 --adapter-version 1.3.0 --out ./s3-certification.json
+PYTHONPATH=src python3 -m agentledger adapter certify --kind langgraph --adapter-version 1.3.0 --package-name agentledger-langgraph
 ```
 Supported built-in profiles:

{agentledger_runtime-1.2.3 → agentledger_runtime-1.3.0}/docs/ADAPTER_PACKAGING.md RENAMED Viewed

@@ -1,6 +1,6 @@
 # Adapter Packaging
-AgentLedger `1.2.1` introduced the adapter packaging model, `1.2.2` extended it with the official MySQL storage adapter boundary, and `1.2.3` adds a dependency-free Langfuse evidence/trace export boundary. Runtime-core stays small and dependency-light; concrete integrations move into optional adapter packages that can be installed through extras or directly.
+AgentLedger `1.2.1` introduced the adapter packaging model, `1.2.2` extended it with the official MySQL storage adapter boundary, `1.2.3` added a dependency-free Langfuse evidence/trace export boundary, and `1.3.0` adds the read-only Inspector companion package. Runtime-core stays small and dependency-light; concrete integrations and external evidence consumers move into optional packages that can be installed through extras or directly.
 ## Why Split Adapters
@@ -24,7 +24,7 @@ extras preserve easy installation
 Adapter packaging is language-specific. The goal is the same across languages, but the package mechanism follows each ecosystem:
-| Language | Mechanism in `1.2.x` | Reason |
+| Language | Mechanism | Reason |
 | --- | --- | --- |
 | Python | separate PyPI packages under `packages/` plus `agentledger-runtime[...]` extras | Python extras are the cleanest way to keep optional SDK dependencies out of core |
 | TypeScript/Node | `agentledger-runtime` subpath exports plus separate npm adapter packages under `typescript/packages/` | subpath exports are ergonomic for local use; adapter packages preserve future independent npm releases |
@@ -50,6 +50,7 @@ pip install "agentledger-runtime[mcp]"
 pip install "agentledger-runtime[otel]"
 pip install "agentledger-runtime[langfuse]"
 pip install "agentledger-runtime[docker]"
+pip install "agentledger-runtime[inspector]"
 pip install "agentledger-runtime[all]"
 ```
@@ -64,6 +65,7 @@ pip install agentledger-mcp
 pip install agentledger-otel
 pip install agentledger-langfuse
 pip install agentledger-sandbox-docker
+pip install agentledger-inspector
 ```
 Use extras for normal projects. Use direct adapter packages when an organization wants explicit dependency locks, separate package mirrors, or independent adapter release governance.
@@ -89,6 +91,7 @@ agentledger-runtime/
     agentledger-otel/
     agentledger-langfuse/
     agentledger-sandbox-docker/
+    agentledger-inspector/                 # companion package, not an adapter
   typescript/
     src/adapters/                        # runtime subpath exports
     packages/                            # npm adapter packages
@@ -132,7 +135,7 @@ Each adapter package should provide:
 ## First Adapter Packages
-| Package | Owns in `1.2.x` | Dependency status |
+| Package | Owns in current `1.3.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. |
@@ -143,6 +146,18 @@ Each adapter package should provide:
 | `agentledger-langfuse` | Langfuse-style evidence/trace payload export | Current package is dependency-light; Langfuse SDK/server ingestion behavior remains application/deployment validation. |
 | `agentledger-sandbox-docker` | Docker sandbox executor package and local/team recipes | Current boundary can use Docker CLI/manifest semantics; daemon hardening, network policy, and resource validation are external. |
+## Companion Packages
+Not every optional package is an adapter. `agentledger-inspector` is a read-only evidence/runtime metadata consumer. It uses the same package and extra mechanism for installation convenience, but it does not provide a storage, framework, sandbox, model, or observability adapter.
+```bash
+pip install "agentledger-runtime[inspector]"
+agentledger inspector evidence ./evidence/<run_id> --html ./inspector.html
+agentledger inspector run <run_id> --root .agentledger --html ./inspector.html
+```
+The Inspector package should remain read-only and dependency-light. Web servers, authentication, deployment management, and write/control-plane actions are outside this package boundary.
 Language fit matters. `agentledger-langgraph` is first-class for Python and TypeScript/Node because those ecosystems have LangGraph packages. Go and Rust expose a generic `framework` adapter boundary instead of pretending a native LangGraph ecosystem exists there.
 ## Sandbox Adapter Scope
@@ -195,23 +210,25 @@ Do not remove these shim paths in `1.2.1`. A future `2.0` may remove compatibili
 ```toml
 [project.optional-dependencies]
-postgres = ["agentledger-postgres>=1.2,<2"]
-mysql = ["agentledger-mysql>=1.2,<2"]
-s3 = ["agentledger-s3>=1.2,<2"]
-langgraph = ["agentledger-langgraph>=1.2,<2"]
-mcp = ["agentledger-mcp>=1.2,<2"]
-otel = ["agentledger-otel>=1.2,<2"]
-langfuse = ["agentledger-langfuse>=1.2,<2"]
-docker = ["agentledger-sandbox-docker>=1.2,<2"]
+postgres = ["agentledger-postgres>=1.3,<2"]
+mysql = ["agentledger-mysql>=1.3,<2"]
+s3 = ["agentledger-s3>=1.3,<2"]
+langgraph = ["agentledger-langgraph>=1.3,<2"]
+mcp = ["agentledger-mcp>=1.3,<2"]
+otel = ["agentledger-otel>=1.3,<2"]
+langfuse = ["agentledger-langfuse>=1.3,<2"]
+docker = ["agentledger-sandbox-docker>=1.3,<2"]
+inspector = ["agentledger-inspector>=1.3,<2"]
 all = [
-  "agentledger-postgres>=1.2,<2",
-  "agentledger-mysql>=1.2,<2",
-  "agentledger-s3>=1.2,<2",
-  "agentledger-langgraph>=1.2,<2",
-  "agentledger-mcp>=1.2,<2",
-  "agentledger-otel>=1.2,<2",
-  "agentledger-langfuse>=1.2,<2",
-  "agentledger-sandbox-docker>=1.2,<2",
+  "agentledger-postgres>=1.3,<2",
+  "agentledger-mysql>=1.3,<2",
+  "agentledger-s3>=1.3,<2",
+  "agentledger-langgraph>=1.3,<2",
+  "agentledger-mcp>=1.3,<2",
+  "agentledger-otel>=1.3,<2",
+  "agentledger-langfuse>=1.3,<2",
+  "agentledger-sandbox-docker>=1.3,<2",
+  "agentledger-inspector>=1.3,<2",
 ]
 ```
@@ -219,18 +236,20 @@ During local monorepo development, tests may install packages from `packages/*`
 ## Release Gates
-The `1.2.x` packaging release is expected to pass:
+The packaging release is expected to pass:
 ```bash
 PYTHONDONTWRITEBYTECODE=1 PYTHONPATH=src python3 -m unittest discover -s tests -q
-PYTHONDONTWRITEBYTECODE=1 PYTHONPATH=src python3 -m agentledger adapter certify --kind postgres --adapter-version 1.2.3
-PYTHONDONTWRITEBYTECODE=1 PYTHONPATH=src python3 -m agentledger adapter certify --kind mysql --adapter-version 1.2.3
+PYTHONDONTWRITEBYTECODE=1 PYTHONPATH=src python3 -m agentledger adapter certify --kind postgres --adapter-version 1.3.0
+PYTHONDONTWRITEBYTECODE=1 PYTHONPATH=src python3 -m agentledger adapter certify --kind mysql --adapter-version 1.3.0
 PYTHONDONTWRITEBYTECODE=1 PYTHONPATH=src python3 scripts/check_adapter_packages.py
 go test ./...
 cd typescript && npm test
 cd rust && cargo test --features adapters-all
 ```
+`scripts/check_adapter_packages.py` covers official adapter packages and read-only companion packages. `agentledger-inspector` is checked for metadata, dependency declaration, README, and import smoke coverage, but it remains a companion package rather than an adapter.
 Each adapter package should also pass:
 ```bash
@@ -239,9 +258,11 @@ python3 -m pip install dist/<adapter>.whl
 python3 -c "import <adapter_import_name>"
 ```
-## Non-Goals For 1.2.1
+Rust adapter crates depend on the published `agentledger-runtime` crate version as well as the local monorepo `path` dependency. For a new release train, publish `agentledger-runtime` first; then run `cargo package` or `cargo publish` for `rust/crates/agentledger-*`. Before the runtime crate version exists on crates.io, adapter crate packaging may fail registry dependency resolution even though local tests pass.
+## Non-Goals For The Adapter Package Boundary
-`1.2.1` should not claim production hardening just because packages exist. The following stay as later work:
+The adapter package boundary should not claim production hardening just because packages exist. The following stay as later work:
 - real Postgres/S3 restore drills and load/concurrency reports
 - full framework-native version matrix
@@ -249,4 +270,4 @@ python3 -c "import <adapter_import_name>"
 - Temporal/Ray/Kubernetes backend adapters
 - media processing adapters
 - sub-agent or multi-agent runtime semantics
-- hosted platform, SaaS, long-running UI, or full eval platform
+- long-running UI, deployment management, or full eval system

{agentledger_runtime-1.2.3 → agentledger_runtime-1.3.0}/docs/ADAPTER_ROADMAP.md RENAMED Viewed

@@ -21,7 +21,7 @@ An adapter should stay community/experimental when:
 - The upstream SDK is unstable or mostly private/internal.
 - The integration requires opinionated infrastructure that users should own.
 - The runtime can only expose a safe boundary, not guarantee real behavior.
-- The adapter would force core to become a workflow engine, eval platform, SaaS platform, or deployment product.
+- The adapter would force core to become a workflow engine, eval system, application administration backend, or deployment product.
 ## Priority 1: Official Adapters
@@ -55,7 +55,7 @@ These are valuable but should follow the Priority 1 adapters or remain thinner f
 | Sandbox | Kubernetes Job sandbox | Good production boundary for cluster users. | Should support dry-run manifests, namespace/service account policy, and optional runtimeClass. |
 | Sandbox | E2B | Good managed remote sandbox for code/tool execution. | Keep as optional remote executor adapter. |
 | Distributed execution | Ray bridge | Useful for Python distributed worker pools. | Ray should own cluster scheduling; AgentLedger owns run semantics. |
-| Deployment | Kubernetes worker recipe | Useful for pilots. | Recipe/Helm/examples first; full platform later only if needed. |
+| Deployment | Kubernetes worker recipe | Useful for pilots. | Recipe/Helm/examples first; keep deployment management outside runtime-core. |
 | Model providers/router | OpenAI, Anthropic, Gemini, Bedrock, Azure OpenAI, Ollama, LiteLLM-style bridge | Model calls affect evidence, cost, replay, fallback, and budget enforcement, but provider SDKs should not be runtime-core dependencies. | Wait for `ModelGateway`/`ModelRouter` contract before stabilizing provider packages. |
 ## Priority 3: Experimental Or Community Adapters
@@ -70,7 +70,7 @@ These should not block core parity or official release claims.
 | Workflow | Airflow / Prefect / Argo | They are batch/workflow systems; useful bridges, but AgentLedger should not become a general workflow engine. |
 | Eval | LangSmith / Braintrust / custom eval platforms | Eval remains a consumer of evidence/replay contracts, not runtime-core. |
 | Vector DB / RAG | Pinecone, Weaviate, Milvus, pgvector, etc. | Long-term memory/retrieval infra should be external; runtime stores refs/evidence, not knowledge retrieval logic. |
-| SaaS/multi-tenant platform | Any hosted platform adapter | Out of current project scope. AgentLedger is a framework/library/runtime, not SaaS. |
+| Application administration backend | User, organization, billing, identity, or control-plane adapters | Out of current project scope. AgentLedger is a framework/library/runtime reliability layer. |
 ## Cross-Language Policy

agentledger_runtime-1.3.0/docs/ADOPTION.md ADDED Viewed

@@ -0,0 +1,58 @@
+# Adoption Plan
+This document tracks near-term work that makes AgentLedger easier to understand, try, discuss, and validate. It does not change runtime-core scope.
+## Why This Track Exists
+AgentLedger already has substantial runtime-core depth. The next adoption bottleneck is not another large feature; it is helping a new user answer three questions quickly:
+```text
+What problem does this solve?
+Can I see it in three minutes?
+Can I verify the reliability claim myself?
+```
+## Current Adoption Priorities
+| Priority | Item | Acceptance criteria |
+|---|---|---|
+| P0 | 3-minute demo | A user can run the Python, Go, TypeScript, or Rust 3-minute demo and see one external side effect, one Tool Ledger entry, safe retry, and replay-safe evidence. |
+| P0 | README first-screen pain point | The first screen explains the tool side-effect problem before listing architecture. |
+| 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 | 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. |
+## Suggested Public Issues
+These can be opened as GitHub issues when the project is ready for public tracking.
+| Title | Type | Why it matters |
+|---|---|---|
+| 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 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 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. |
+## Case Study Rules
+Case studies should be useful but conservative:
+- remove private data, customer data, secrets, and internal implementation details
+- describe the runtime problem before describing AgentLedger
+- show the AgentLedger integration boundary
+- include concrete evidence artifacts only when safe
+- avoid claiming production hardening unless real operational evidence exists
+## Good Adoption Evidence
+- runnable examples
+- short terminal recordings or GIFs
+- public issues and discussions
+- package downloads
+- real integration notes
+- external demos or blog posts
+- adapter conformance reports
+- real-service hardening reports

agentledger-runtime 1.2.3__tar.gz → 1.3.0__tar.gz

agentledger-runtime 1.2.3tar.gz → 1.3.0tar.gz