agentledger-runtime 1.3.4__tar.gz → 1.4.0__tar.gz

{agentledger_runtime-1.3.4 → agentledger_runtime-1.4.0}/CHANGELOG.md

@@ -6,7 +6,46 @@ This project follows semantic versioning for the stable runtime-core contract. O
 
 ## Unreleased
 
-No unreleased changes yet.
+No unreleased changes.
+
+## 1.4.0 - 2026-06-13
+
+### Added
+
+- Added the Agent Failure Lifecycle baseline across Python, Go, TypeScript, and Rust runtime-core packages.
+- Added `agentledger.failure.envelope.v1`, a normalized failure read model for terminal failures, recoverable retries, approval waits, blocked tools, and unknown side-effect states.
+- Added `agentledger.failure.lifecycle.v1`, `agentledger.failure.causal_graph.v1`, `agentledger.failure.replay_plan.v1`, `agentledger.failure.regression.v1`, `agentledger.failure.alerts.v1`, and `agentledger.failure.export.v1`.
+- Added failure lifecycle, causal graph, replay plan, local alert records, regression comparison, and external export mappings for OpenTelemetry, Langfuse, LangSmith, and Temporal-style consumers.
+- Added `agentledger failure export` and `agentledger failure regress` CLI commands.
+- Added Inspector panels for Failure Lifecycle, Failure Replay Plan, Failure Alerts, and Failure Causal Graph.
+
+### Tested
+
+- Added non-happy-path tests for missing event payloads, retry-scheduled steps, pending approvals, pending tool verification, blocked tools, terminal failure reports, Inspector HTML rendering, unsafe replay planning, local failure alerts, export mappings, and failure regression classification.
+- Added matching failure lifecycle assertions to Go, TypeScript, and Rust runtime-core tests.
+
+### Clarified
+
+- This is a runtime-core feature release, not an Inspector-only patch. Python, Go, TypeScript, and Rust share the 1.4.0 failure lifecycle contract.
+- Inspector remains a language-neutral read-only companion viewer distributed through Python/PyPI.
+- Failure export mappings are local JSON contracts. They do not send data to external SaaS systems or replace incident management, eval, or observability platforms.
+
+## 1.3.5 - 2026-06-07
+
+### Added
+
+- Added an Inspector chronological Event Stream view sorted by event timestamp, showing runtime run id, extracted agent run id, step id, event type, summary, and links back to detailed timeline records.
+- Added `agentledger inspector runs` and the `agentledger.inspector.runs.v1` read model for a read-only run index over SQLite/Postgres/MySQL runtime metadata.
+
+### Fixed
+
+- Improved packaged Inspector/static HTML layout so large JSON/details payloads and long ids do not expand tables or break the page width.
+- Reworked detailed Inspector, evidence, and time-travel tables so JSON opens in a full-width row below the record instead of a narrow right-side column.
+- Reworked the Inspector run-index HTML from a wide multi-column table into a compact paginated run list with status, timestamps, counters, Inspector links, and folded JSON details.
+
+### Clarified
+
+- This is an Inspector companion patch release. Inspector is language-neutral, but the current packaged implementation is distributed through the Python/PyPI CLI. The release does not change the stable runtime-core contract or require Go, TypeScript, or Rust runtime-core package changes.
 
 ## 1.3.4
 

{agentledger_runtime-1.3.4 → agentledger_runtime-1.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agentledger-runtime
-Version: 1.3.4
+Version: 1.4.0
 Summary: Runtime reliability layer for Agent Harness stacks
 Project-URL: Homepage, https://github.com/yaogdu/AgentLedger
 Project-URL: Repository, https://github.com/yaogdu/AgentLedger
@@ -21,33 +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,>=1.3.4; 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'
+Requires-Dist: agentledger-inspector<2,>=1.4.0; 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'
 Provides-Extra: docker
-Requires-Dist: agentledger-sandbox-docker<2,>=1.3; extra == 'docker'
+Requires-Dist: agentledger-sandbox-docker<2,>=1.4; extra == 'docker'
 Provides-Extra: inspector
-Requires-Dist: agentledger-inspector<2,>=1.3.4; extra == 'inspector'
+Requires-Dist: agentledger-inspector<2,>=1.4.0; extra == 'inspector'
 Provides-Extra: langfuse
-Requires-Dist: agentledger-langfuse<2,>=1.3; extra == 'langfuse'
+Requires-Dist: agentledger-langfuse<2,>=1.4; extra == 'langfuse'
 Provides-Extra: langgraph
-Requires-Dist: agentledger-langgraph<2,>=1.3; extra == 'langgraph'
+Requires-Dist: agentledger-langgraph<2,>=1.4; extra == 'langgraph'
 Provides-Extra: mcp
-Requires-Dist: agentledger-mcp<2,>=1.3; extra == 'mcp'
+Requires-Dist: agentledger-mcp<2,>=1.4; extra == 'mcp'
 Provides-Extra: mysql
-Requires-Dist: agentledger-mysql<2,>=1.3; extra == 'mysql'
+Requires-Dist: agentledger-mysql<2,>=1.4; extra == 'mysql'
 Provides-Extra: otel
-Requires-Dist: agentledger-otel<2,>=1.3; extra == 'otel'
+Requires-Dist: agentledger-otel<2,>=1.4; extra == 'otel'
 Provides-Extra: postgres
-Requires-Dist: agentledger-postgres<2,>=1.3; extra == 'postgres'
+Requires-Dist: agentledger-postgres<2,>=1.4; extra == 'postgres'
 Provides-Extra: s3
-Requires-Dist: agentledger-s3<2,>=1.3; extra == 's3'
+Requires-Dist: agentledger-s3<2,>=1.4; 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 1.3.x stable](https://img.shields.io/badge/Version-1.3.x--stable-111827)
+![Version 1.4.x stable](https://img.shields.io/badge/Version-1.4.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 `1.3.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 `1.4.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.
 
 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.
 
@@ -90,6 +90,14 @@ Python remains the reference implementation, and Go, TypeScript, and Rust now ha
 | Use Go correctly | [go/README.md](go/README.md#install) |
 | Read the full documentation map | [docs/README.md](docs/README.md) |
 
+## Inspector Preview
+
+Inspector exports self-contained, read-only HTML for local or internal debugging. It can show a run index before opening a single run, then drill into chronological events, Tool Ledger rows, approvals, artifacts, and full-width JSON details.
+
+![AgentLedger Inspector run index](docs/assets/inspector/runs-index.png)
+
+![AgentLedger Inspector single run](docs/assets/inspector/single-run-timeline.png)
+
 ## At a glance
 
 | Question | Answer |
@@ -333,7 +341,7 @@ AgentLedger is also not a new LLM SDK, not a workflow engine, not a general obse
 
 ## Current maturity
 
-AgentLedger 1.3.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 current Python/Inspector patch is 1.3.4; Go, TypeScript, and Rust runtime-core package baselines remain 1.3.1 until their next runtime-core release. It is suitable for local use, framework adapter integration, reliability semantics validation, and production pilot preparation with explicit adapter boundaries.
+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: 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, and failure export mappings. The current runtime-core release is 1.4.0 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).
 

{agentledger_runtime-1.3.4 → agentledger_runtime-1.4.0}/README.md

@@ -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 1.3.x stable](https://img.shields.io/badge/Version-1.3.x--stable-111827)
+![Version 1.4.x stable](https://img.shields.io/badge/Version-1.4.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 `1.3.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 `1.4.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.
 
 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.
 
@@ -38,6 +38,14 @@ Python remains the reference implementation, and Go, TypeScript, and Rust now ha
 | Use Go correctly | [go/README.md](go/README.md#install) |
 | Read the full documentation map | [docs/README.md](docs/README.md) |
 
+## Inspector Preview
+
+Inspector exports self-contained, read-only HTML for local or internal debugging. It can show a run index before opening a single run, then drill into chronological events, Tool Ledger rows, approvals, artifacts, and full-width JSON details.
+
+![AgentLedger Inspector run index](docs/assets/inspector/runs-index.png)
+
+![AgentLedger Inspector single run](docs/assets/inspector/single-run-timeline.png)
+
 ## At a glance
 
 | Question | Answer |
@@ -281,7 +289,7 @@ AgentLedger is also not a new LLM SDK, not a workflow engine, not a general obse
 
 ## Current maturity
 
-AgentLedger 1.3.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 current Python/Inspector patch is 1.3.4; Go, TypeScript, and Rust runtime-core package baselines remain 1.3.1 until their next runtime-core release. It is suitable for local use, framework adapter integration, reliability semantics validation, and production pilot preparation with explicit adapter boundaries.
+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: 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, and failure export mappings. The current runtime-core release is 1.4.0 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).
 

{agentledger_runtime-1.3.4 → agentledger_runtime-1.4.0}/README.zh-CN.md

@@ -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 1.3.x stable](https://img.shields.io/badge/Version-1.3.x--stable-111827)
+![Version 1.4.x stable](https://img.shields.io/badge/Version-1.4.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 `1.3.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 `1.4.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。
 
 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。
 
@@ -38,6 +38,13 @@ Python 仍然是 reference implementation；Go、TypeScript、Rust 已有 native
 | 正确使用 Go | [go/README.md](go/README.md#install) |
 | 查看完整文档地图 | [docs/zh/README.md](docs/zh/README.md) |
 
+## Inspector 预览
+
+Inspector 会导出自包含、只读的 HTML，适合本地或内网排查问题。它可以先展示 run index，再进入单个 run 查看按时间排序的事件、Tool Ledger、approval、artifact 和全宽 JSON 详情。
+
+![AgentLedger Inspector run index](docs/assets/inspector/runs-index.png)
+
+![AgentLedger Inspector single run](docs/assets/inspector/single-run-timeline.png)
 
 ## 快速判断
 
@@ -282,7 +289,7 @@ AgentLedger 也不是新的 LLM SDK，不是 workflow engine，不是通用 obse
 
 ## 当前成熟度
 
-AgentLedger 1.3.x 是 stable runtime-core line，Python 是 reference implementation，Go、TypeScript、Rust 已由共享 runtime-core parity gate 覆盖。当前 Python/Inspector patch 是 1.3.3；Go、TypeScript、Rust runtime-core package baseline 仍是 1.3.1，直到它们进入下一次 runtime-core release。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 1.4.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：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 和 failure export mappings。当前 runtime-core release 是 1.4.0，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)。
 

{agentledger_runtime-1.3.4 → agentledger_runtime-1.4.0}/docs/ADAPTER_CERTIFICATION.md

@@ -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 1.3.1
-PYTHONPATH=src python3 -m agentledger adapter certify --kind mysql --adapter-version 1.3.1 --out ./mysql-certification.json
-PYTHONPATH=src python3 -m agentledger adapter certify --kind s3 --adapter-version 1.3.1 --out ./s3-certification.json
-PYTHONPATH=src python3 -m agentledger adapter certify --kind langgraph --adapter-version 1.3.1 --package-name agentledger-langgraph
+PYTHONPATH=src python3 -m agentledger adapter certify --kind postgres --adapter-version 1.4.0
+PYTHONPATH=src python3 -m agentledger adapter certify --kind mysql --adapter-version 1.4.0 --out ./mysql-certification.json
+PYTHONPATH=src python3 -m agentledger adapter certify --kind s3 --adapter-version 1.4.0 --out ./s3-certification.json
+PYTHONPATH=src python3 -m agentledger adapter certify --kind langgraph --adapter-version 1.4.0 --package-name agentledger-langgraph
 ```
 
 Supported built-in profiles:

{agentledger_runtime-1.3.4 → agentledger_runtime-1.4.0}/docs/ADAPTER_PACKAGING.md

@@ -135,7 +135,7 @@ Each adapter package should provide:
 
 ## First Adapter Packages
 
-| Package | Owns in current `1.3.x` release train | Dependency status |
+| Package | Owns in current `1.4.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. |
@@ -240,8 +240,8 @@ 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 1.3.1
-PYTHONDONTWRITEBYTECODE=1 PYTHONPATH=src python3 -m agentledger adapter certify --kind mysql --adapter-version 1.3.1
+PYTHONDONTWRITEBYTECODE=1 PYTHONPATH=src python3 -m agentledger adapter certify --kind postgres --adapter-version 1.4.0
+PYTHONDONTWRITEBYTECODE=1 PYTHONPATH=src python3 -m agentledger adapter certify --kind mysql --adapter-version 1.4.0
 PYTHONDONTWRITEBYTECODE=1 PYTHONPATH=src python3 scripts/check_adapter_packages.py
 go test ./...
 cd typescript && npm test

{agentledger_runtime-1.3.4 → agentledger_runtime-1.4.0}/docs/COMPLETE_CORE_PARITY_CHECKLIST.md

@@ -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 1.3 release family | PyPI metadata `1.3.x` | `go.mod` tag `go/v1.3.1` for current baseline | npm package `1.3.1` for current baseline | `Cargo.toml` `1.3.1` 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==1.3.4` release smoke after publish for current Inspector patch | `go/v1.3.1` clean external `go get` smoke after tag | npm `agentledger-runtime@1.3.1` release smoke after publish | crates.io `agentledger-runtime==1.3.1` 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 1.4 release family | PyPI metadata `1.4.x` | `go.mod` tag `go/v1.4.0` for current baseline | npm package `1.4.0` for current baseline | `Cargo.toml` `1.4.0` 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==1.4.0` release smoke after publish | `go/v1.4.0` clean external `go get` smoke after tag | npm `agentledger-runtime@1.4.0` release smoke after publish | crates.io `agentledger-runtime==1.4.0` 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 `1.3`; Python may carry Inspector-only patch releases such as `1.3.4` without changing non-Python runtime-core baselines.
+4. Package release families are checked across Python, TypeScript, and Rust. The current core release family is `1.4`; 1.4.0 is a four-language runtime-core feature release for Agent Failure Lifecycle.
 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.
 

{agentledger_runtime-1.3.4 → agentledger_runtime-1.4.0}/docs/GETTING_STARTED.md

@@ -9,7 +9,7 @@ This is the shortest path from install to a working AgentLedger run. If you are
 | Language | Install / use | Quickstart | Examples | Package / command |
 |---|---|---|---|---|
 | Python | `pipx install agentledger-runtime` or `pip install agentledger-runtime` | `agentledger quickstart` | `../examples/README.md` | PyPI package `agentledger-runtime`, CLI `agentledger` |
-| Go | `go get github.com/yaogdu/AgentLedger/go@v1.3.1` inside a Go module | `cd go && go run ./examples/quickstart` from this repo | `../go/examples/README.md` | Go module `github.com/yaogdu/AgentLedger/go`, CLI package `.../go/cmd/agentledger-go` |
+| Go | `go get github.com/yaogdu/AgentLedger/go@v1.4.0` inside a Go module | `cd go && go run ./examples/quickstart` from this repo | `../go/examples/README.md` | Go module `github.com/yaogdu/AgentLedger/go`, CLI package `.../go/cmd/agentledger-go` |
 | TypeScript | `npm install agentledger-runtime` | `node typescript/examples/quickstart/quickstart.js` | `../typescript/examples/README.md` | npm package `agentledger-runtime`, CLI `agentledger-ts` |
 | Rust | crates.io package: `agentledger-runtime` | `cargo add agentledger-runtime` 或 `cd rust && cargo run --example quickstart` | `../rust/examples/README.md` | crate `agentledger-runtime`, binary `agentledger-rust` |
 
@@ -36,17 +36,17 @@ Use the library inside a Go module:
 
 ```bash
 go mod init your-module-name  # only if your project does not already have go.mod
-go get github.com/yaogdu/AgentLedger/go@v1.3.1
+go get github.com/yaogdu/AgentLedger/go@v1.4.0
 ```
 
 Install the optional CLI:
 
 ```bash
-go install github.com/yaogdu/AgentLedger/go/cmd/agentledger-go@v1.3.1
+go install github.com/yaogdu/AgentLedger/go/cmd/agentledger-go@v1.4.0
 agentledger-go --help
 ```
 
-Important: `go get` must run inside a Go module. `go install github.com/yaogdu/AgentLedger/go@v1.3.1` is not valid because that path is a library, not `package main`. Use `/cmd/agentledger-go` for the CLI.
+Important: `go get` must run inside a Go module. `go install github.com/yaogdu/AgentLedger/go@v1.4.0` is not valid because that path is a library, not `package main`. Use `/cmd/agentledger-go` for the CLI.
 
 ### TypeScript
 

{agentledger_runtime-1.3.4 → agentledger_runtime-1.4.0}/docs/IMPLEMENTATION_STATUS.md

@@ -6,7 +6,7 @@ This document tracks what is implemented in runtime-core, what remains planned f
 
 ## Current Baseline
 
-AgentLedger 1.3.x is a stable runtime-core line with Python as the reference implementation and Go/TypeScript/Rust covered by shared runtime-core parity gates. The 1.3 line keeps the stable runtime-core contract and adds a language-neutral, read-only Inspector companion path for evidence and runtime metadata inspection. It is suitable for:
+AgentLedger 1.4.x is a stable runtime-core line with Python as the reference implementation and Go/TypeScript/Rust covered by shared runtime-core parity gates. The 1.4 line keeps the stable runtime-core contract, adds a language-neutral read-only Inspector companion path, and completes the Agent Failure Lifecycle baseline across all four runtime packages. It is suitable for:
 
 - local use
 - runtime design review
@@ -15,7 +15,7 @@ AgentLedger 1.3.x is a stable runtime-core line with Python as the reference imp
 - reliability semantics validation
 - production pilot preparation with explicit adapter boundaries
 
-Release-scope note: 1.3.0 added Inspector as a read-only evidence/runtime metadata consumer. It can read exported evidence bundles or connect to SQLite/Postgres/MySQL AgentLedger metadata with read-only credentials and can export a static HTML debug report. 1.3.2 adds configurable redaction for Inspector JSON/HTML output. 1.3.3 adds static report navigation and read-model cross-links for timeline, tool, approval, policy, and artifact records. 1.3.4 fixes Inspector package release metadata alignment without changing runtime-core semantics. MySQL remains the 1.2.2 storage adapter boundary and Langfuse remains the 1.2.3 observability adapter boundary; real-service production claims still require external validation.
+Release-scope note: 1.3.x added and hardened Inspector as a read-only evidence/runtime metadata consumer. It can read exported evidence bundles or connect to SQLite/Postgres/MySQL AgentLedger metadata with read-only credentials and can export static HTML debug reports. 1.4.0 adds the four-language Agent Failure Lifecycle baseline: normalized failure envelopes, lifecycle stages, causal graph, replay plan, regression report, local alert records, and portable failure export mappings. MySQL remains the 1.2.2 storage adapter boundary and Langfuse remains the 1.2.3 observability adapter boundary; real-service production claims still require external validation.
 
 The runtime-core contract is stable. Optional production adapters, external infrastructure hardening, and full eval systems remain outside the stable core boundary; non-Python runtime-core baselines are verified by the shared parity gates.
 
@@ -23,7 +23,7 @@ Scope rule: runtime-core should stay thin but indispensable. It should own only
 
 ## Current Completion Boundary
 
-For the current 1.3.x goal, "stable runtime-core plus read-only evidence consumers" means the Python reference runtime is usable, documented, tested, release-gated, and contract-frozen, with Go/TypeScript/Rust covered by runtime-core parity gates. It also means first-party adapter boundaries are packaged or importable in each ecosystem where they fit, and the Inspector can consume exported evidence across languages. It does not mean every optional production adapter or external eval integration is production-hardened in every language.
+For the current 1.4.x goal, "stable runtime-core plus failure lifecycle and read-only evidence consumers" means the Python reference runtime is usable, documented, tested, release-gated, and contract-frozen, with Go/TypeScript/Rust covered by runtime-core parity gates. It also means first-party adapter boundaries are packaged or importable in each ecosystem where they fit, and the Inspector can consume exported evidence across languages. It does not mean every optional production adapter or external eval integration is production-hardened in every language.
 
 Included in this boundary:
 
@@ -58,7 +58,7 @@ Excluded from this boundary:
 | Adapter contracts | framework adapter base, LangGraph facade, MCP tool/context mapping, dependency-free method facades, first-party adapter package boundaries |
 | Sandbox boundary | fail-closed `none`, local executor, router, external executor contracts, Docker/bubblewrap command paths, Kubernetes dry-run/gated path |
 | Observability | trace JSONL export with media/stream spans, dependency-free OTLP JSON export, optional OTLP/JSON collector POST, evidence-linked audit records |
-| Inspector | `agentledger.inspector.v1` read model, `agentledger inspector run/evidence`, static HTML report, section navigation, row anchors, cross-links between related records, evidence-bundle input, read-only SQLite input, Postgres/MySQL read paths through existing adapter boundaries, configurable redaction policy, optional `agentledger-inspector` companion package |
+| Inspector | `agentledger.inspector.v1` single-run read model, `agentledger.inspector.runs.v1` run-index read model, `agentledger inspector run/runs/evidence`, static HTML reports, section navigation, row anchors, cross-links between related records, evidence-bundle input, read-only SQLite input, Postgres/MySQL read paths through existing adapter boundaries, configurable redaction policy, optional `agentledger-inspector` companion package |
 | Reliability checks | failure injection suite, failure attribution report, conformance runners including media runtime conformance, runtime-boundary lint, scheduler facade, adversarial review, evidence regression for shell, HTTP, cloud, GitHub, and common model SDK bypasses with JSON rule-pack extension |
 | Media and stream contracts | `MediaArtifact`, `MediaMetadata`, `ArtifactLineage`, `StreamChunkRef`, `EventStreamCheckpoint`, `AgentContext.create_media_artifact(...)`, `AgentContext.create_stream_checkpoint(...)`, media/stream tool schema conventions, ToolGateway/Tool Ledger media tool example, evidence indexes, replay artifact validation/counts |
 | Release scaffolding | CI workflow, changelog, security policy, versioning policy, release checklist, contributor checks, bilingual documentation entrypoints, SVG architecture diagram, ResourceWarning-sensitive test gate, adapter certification checklist, adapter packaging docs/checks |

{agentledger_runtime-1.3.4 → agentledger_runtime-1.4.0}/docs/INSPECTOR.md

@@ -4,6 +4,14 @@ AgentLedger Inspector is a language-neutral, read-only debug and audit view for
 
 It is not a long-running service and not a runtime control plane. It does not approve requests, cancel runs, mutate Tool Ledger rows, call tools, or contact model providers.
 
+## Preview
+
+The default renderer is a static reference UI: a paginated run index plus a single-run view with chronological events and full-width JSON details.
+
+![AgentLedger Inspector run index](assets/inspector/runs-index.png)
+
+![AgentLedger Inspector single run](assets/inspector/single-run-timeline.png)
+
 ## Install
 
 Inspector is available through the core CLI and as an optional companion package:
@@ -22,11 +30,33 @@ Inspector is implemented once as a companion evidence consumer. Go, TypeScript,
 The boundary is:
 
 - language runtimes write AgentLedger metadata, Tool Ledger rows, events, artifacts, and evidence
-- Inspector reads that data through the stable read model `agentledger.inspector.v1`
+- Inspector reads that data through stable read models such as `agentledger.inspector.v1` and `agentledger.inspector.runs.v1`
 - users can build their own viewer, API endpoint, or internal debug tool on top of the read model
 
 This keeps Inspector outside runtime-core execution semantics while still making all language implementations debuggable through one tool.
 
+## Using Inspector With Non-Python Runtimes
+
+Inspector is language-neutral, but the current official distribution is the Python/PyPI companion package and the `agentledger inspector ...` CLI. A Go, TypeScript, or Rust application does not need to embed Python or install PyPI packages in its runtime process. It only needs to write AgentLedger-compatible metadata or export an AgentLedger evidence bundle.
+
+The normal non-Python workflow is:
+
+1. Run the agent with the native Go, TypeScript, or Rust runtime.
+2. Export evidence or point Inspector at the runtime database/blob root.
+3. Install `agentledger-inspector` on a developer, CI, support, or internal debugging machine.
+4. Generate static HTML or JSON from the shared read model.
+
+Example:
+
+```bash
+pip install agentledger-inspector
+agentledger inspector evidence ./evidence/<run_id> --html ./inspector.html
+```
+
+Without the Python/PyPI package, the non-Python runtimes still support the shared runtime-core failure semantics and can export compatible evidence. What they do not currently ship is an equivalent native Inspector viewer command that renders the same official run index, single-run HTML, and normalized failure envelopes without installing the companion Inspector tool. This is a distribution/viewer gap, not a runtime failure-support gap.
+
+Standalone Inspector distributions are on the roadmap so non-Python users can consume the official viewer without installing through PyPI. Candidate forms include a Docker image, a single executable, a static web viewer over exported evidence JSON, and a Node/npm CLI or viewer package.
+
 ## Data Sources
 
 Inspector supports two read paths.
@@ -35,6 +65,7 @@ Inspector supports two read paths.
 |---|---|---|
 | Exported evidence | `agentledger inspector evidence <path>` | Portable artifact from any language implementation or CI job. |
 | Local SQLite runtime | `agentledger inspector run <run_id> --root .agentledger` | Local development and small deployments. |
+| Run index | `agentledger inspector runs --root .agentledger` | Read-only list of recent runs before opening one run. |
 | Direct SQLite path | `agentledger inspector run <run_id> --backend sqlite --db state.db --blob-root blobs` | Custom runtime directory layouts. |
 | Postgres metadata | `agentledger inspector run <run_id> --backend postgres --dsn ... --schema ... --blob-root ...` | Server-side StateStore deployments. |
 | MySQL metadata | `agentledger inspector run <run_id> --backend mysql --dsn ... --database ... --blob-root ...` | MySQL-backed StateStore deployments. |
@@ -56,6 +87,8 @@ This path reads AgentLedger runtime metadata directly. SQLite is opened in read-
 ```bash
 agentledger inspector run <run_id> --root .agentledger --html ./inspector.html
 agentledger inspector run <run_id> --backend sqlite --db .agentledger/state.db --blob-root .agentledger/blobs --out ./inspector.json
+agentledger inspector runs --root .agentledger --html ./runs.html
+agentledger inspector runs --root .agentledger --out ./runs.json
 ```
 
 Postgres and MySQL are also supported through the existing StateStore adapter boundaries. Inspector uses read-only store wrappers for these paths and does not run migrations or create tables:
@@ -63,12 +96,16 @@ Postgres and MySQL are also supported through the existing StateStore adapter bo
 ```bash
 agentledger inspector run <run_id> --backend postgres --dsn "$AGENTLEDGER_POSTGRES_DSN" --schema agentledger --blob-root .agentledger/blobs --html ./inspector.html
 agentledger inspector run <run_id> --backend mysql --dsn "$AGENTLEDGER_MYSQL_DSN" --database agentledger --blob-root .agentledger/blobs --html ./inspector.html
+agentledger inspector runs --backend postgres --dsn "$AGENTLEDGER_POSTGRES_DSN" --schema agentledger --html ./runs.html
+agentledger inspector runs --backend mysql --dsn "$AGENTLEDGER_MYSQL_DSN" --database agentledger --html ./runs.html
 ```
 
 Use database credentials with read-only permissions. AgentLedger does not add an Inspector-specific permission system; database grants, filesystem ACLs, and deployment policy remain the enforcement layer. The Inspector code path exposes no runtime write/control actions, but Postgres/MySQL client libraries cannot replace database-side read-only grants.
 
 The `--blob-root` argument currently points at a local blob directory containing the payload blobs referenced by the runtime metadata. If payload blobs live in S3/MinIO or another managed object store, export an evidence bundle first or provide a custom `EvidenceBlobStoreProtocol` implementation through the extension API.
 
+For `agentledger inspector runs`, `--blob-root` is optional. When present, Inspector may use it to extract an application-level `agent_run_id` from event payloads. When absent, the run index still works but may show `agent_run_id` as `-`.
+
 ## Output
 
 `--out` writes the stable JSON read model:
@@ -78,6 +115,8 @@ The `--blob-root` argument currently points at a local blob directory containing
   "schema_version": "agentledger.inspector.v1",
   "run": {},
   "summary": {},
+  "agent_run_id": null,
+  "event_stream": [],
   "timeline": [],
   "tool_ledger": [],
   "approvals": [],
@@ -90,6 +129,52 @@ The `--blob-root` argument currently points at a local blob directory containing
 
 `--html` writes a static HTML report for local or internal debugging. The file is self-contained and can be opened without a server.
 
+`agentledger inspector runs --out` writes a run-index read model:
+
+```json
+{
+  "schema_version": "agentledger.inspector.runs.v1",
+  "summary": {},
+  "runs": []
+}
+```
+
+`agentledger inspector runs --html` writes a static read-only run list. The default renderer uses a compact paginated vertical list with status, timestamps, counters, optional Inspector links, and folded JSON details instead of a wide table. Use `--run-link-template "/runs/{run_id}/inspector.html"` when an application or internal tool already exposes single-run Inspector pages and should link from the index to those pages.
+
+## Event Stream
+
+`1.3.5` adds an Event Stream section to the Inspector read model and static HTML report. It is a chronological view of the same run events, sorted by event time and tied together by:
+
+- `runtime_run_id`: the AgentLedger runtime run id
+- `agent_run_id`: an agent/application run id when one is present in event metadata or payloads
+- `seq`: the original AgentLedger event sequence
+- `type`, `step_id`, and `summary`: compact event context
+- `related_links`: local links back to detailed timeline, step, tool, approval, policy, or artifact records
+
+This view is intended for debugging a single run from top to bottom. It does not replace the detailed section views; it gives operators a time-ordered path through them.
+
+Detailed tables keep compact record columns on the first row and render the folded JSON payload in a full-width row below each record. This keeps long payloads readable without forcing a narrow right-side details column.
+
+## Failure Lifecycle
+
+`1.4.0` adds the Agent Failure Lifecycle baseline consumed by `agentledger failure report`, `agentledger failure export`, Inspector JSON, and Inspector static HTML.
+
+The runtime still records raw events, step rows, Tool Ledger rows, approval rows, cost records, and evidence bundles. Failure lifecycle output is a read model over those records so business code and support tooling do not need to infer failure semantics from undocumented table details.
+
+The stable failure read model includes:
+
+- `agentledger.failure.envelope.v1`: normalized category, status, severity, recoverability, retryability, owner, causal refs, and evidence refs
+- `agentledger.failure.lifecycle.v1`: detected, classified, recovery scheduled, recovered, terminal, and regressed stages
+- `agentledger.failure.causal_graph.v1`: run, step, event, tool, approval, cost, and failure nodes linked by causal/evidence edges
+- `agentledger.failure.replay_plan.v1`: evidence-only replay guidance that blocks unsafe side-effect replay when manual verification is required
+- `agentledger.failure.regression.v1`: recurring, fixed, and newly introduced failure comparison
+- `agentledger.failure.alerts.v1`: local alert records for terminal failures, unknown side effects, costly failures, and unsafe replay blocks
+- `agentledger.failure.export.v1`: portable export with OpenTelemetry, Langfuse, LangSmith, and Temporal-style mapping hints
+
+This intentionally covers non-happy-path production states, not just terminal failures. For example, `PENDING_VERIFICATION` Tool Ledger rows become `unknown_side_effect` envelopes with `manual_verification` recoverability, because retrying blindly could duplicate an external side effect.
+
+`1.4.0` does not turn AgentLedger into an incident-management, eval, or observability SaaS. The stable addition is the portable runtime-owned failure contract and Inspector panels that render it. External systems can consume the export without reading internal runtime tables.
+
 ## Navigation And Cross-links
 
 `1.3.3` adds stable row anchors and related links to the Inspector read model. Timeline events, steps, Tool Ledger rows, approval requests, policy decisions, and artifacts may include:
@@ -220,11 +305,27 @@ Implemented in `1.3.3`:
 - stable read-model anchors for timeline, step, Tool Ledger, approval, policy, and artifact rows
 - static HTML section navigation and internal cross-links between related runtime records
 
+Implemented in `1.3.5`:
+
+- chronological Event Stream in JSON and static HTML reports
+- read-only run index through `agentledger inspector runs`
+- `agentledger.inspector.runs.v1` run-index read model for custom viewers
+- runtime run id and extracted agent run id in event/timeline read-model rows
+- safer static HTML layout for long ids, full-width JSON details, and paginated run lists
+
+Implemented in `1.4.0`:
+
+- `agentledger.failure.envelope.v1` normalized failure read model
+- `agentledger.failure.lifecycle.v1`, `agentledger.failure.causal_graph.v1`, `agentledger.failure.replay_plan.v1`, `agentledger.failure.regression.v1`, `agentledger.failure.alerts.v1`, and `agentledger.failure.export.v1`
+- failure lifecycle data in `agentledger failure report` and portable export data from `agentledger failure export`
+- Failure Lifecycle, Failure Replay Plan, Failure Alerts, and Failure Causal Graph panels in Inspector JSON/static HTML
+- non-happy-path coverage for missing payloads, retry scheduling, pending approvals, pending tool verification, blocked tools, unsafe replay planning, and terminal failures
+
 Not in this version:
 
 - long-running web server
+- login, permission, user, or organization management for Inspector surfaces
 - write/control-plane actions
-- user/organization management
 - permission, identity, billing, or administration backend
 - full LangSmith/Langfuse replacement
 - live remote blob adapters inside the Inspector package

{agentledger_runtime-1.3.4 → agentledger_runtime-1.4.0}/docs/LANGUAGE_IMPLEMENTATION_COMPARISON.md

@@ -4,6 +4,8 @@
 
 This document makes the cross-language boundary explicit. AgentLedger's complete parity claim means **portable runtime-core parity**, not identical provider or ecosystem adapter implementations in every language.
 
+Patch versions do not need to move in lockstep when a release only changes a language-specific package, companion tool, read model, or adapter wrapper. `1.4.0` is different: it is a four-language runtime-core feature release for the Agent Failure Lifecycle, so Python, Go, TypeScript, and Rust all move to the same runtime-core release family. Inspector remains a language-neutral companion viewer distributed through Python/PyPI, but the failure lifecycle contract itself is implemented across all four runtime packages.
+
 ## How To Read This Table
 
 | Mark | Meaning |

{agentledger_runtime-1.3.4 → agentledger_runtime-1.4.0}/docs/LANGUAGE_QUICKSTART.md

@@ -2,7 +2,7 @@
 
 [English](LANGUAGE_QUICKSTART.md) | [中文](zh/LANGUAGE_QUICKSTART.md)
 
-AgentLedger 1.3.x has one Python reference runtime and native preview runtime-core baselines for Go, TypeScript, and Rust. The shared promise is semantic parity for runtime-core: durable runs, leases, Tool Ledger, evidence, replay, policy/approval/sandbox boundaries, cost/failure attribution, conformance, and official optional adapter contracts. Python may carry Inspector-only patch releases such as 1.3.4 while the non-Python runtime-core package baselines remain on the latest shared runtime-core tag.
+AgentLedger 1.4.x has one Python reference runtime and native runtime-core baselines for Go, TypeScript, and Rust. The shared promise is semantic parity for runtime-core: durable runs, leases, Tool Ledger, evidence, replay, policy/approval/sandbox boundaries, cost/failure attribution, Agent Failure Lifecycle, conformance, and official optional adapter contracts. Version 1.4.0 is a four-language runtime-core release; Inspector remains a language-neutral companion viewer distributed through Python/PyPI.
 
 The non-Python packages are native runtime packages, not thin clients: each runs a native local runtime loop and reports the shared conformance checks.
 
@@ -66,13 +66,13 @@ Use the released Go module from a Go project:
 
 ```bash
 go mod init your-module-name  # only if your project does not have go.mod yet
-go get github.com/yaogdu/AgentLedger/go@v1.3.1
+go get github.com/yaogdu/AgentLedger/go@v1.4.0
 ```
 
 Install the optional CLI command:
 
 ```bash
-go install github.com/yaogdu/AgentLedger/go/cmd/agentledger-go@v1.3.1
+go install github.com/yaogdu/AgentLedger/go/cmd/agentledger-go@v1.4.0
 agentledger-go --help
 agentledger-go doctor
 agentledger-go quickstart
@@ -86,7 +86,7 @@ go test . ./cmd/agentledger-go
 go run ./cmd/agentledger-go conformance
 ```
 
-Note: `go get` must run inside a Go module. `go install github.com/yaogdu/AgentLedger/go@v1.3.1` fails because the library package is not a `package main`; use `/cmd/agentledger-go` for the CLI.
+Note: `go get` must run inside a Go module. `go install github.com/yaogdu/AgentLedger/go@v1.4.0` fails because the library package is not a `package main`; use `/cmd/agentledger-go` for the CLI.
 
 Minimal runtime:
 
@@ -267,7 +267,7 @@ python3.11 scripts/audit_python_parity.py > /tmp/agentledger-python-parity-audit
 python3.11 scripts/check_language_parity.py --json-report /tmp/agentledger-language-parity.json
 ```
 
-Expected for 1.3.x:
+Expected for 1.4.x:
 
 ```text
 gap_count: 0
@@ -277,5 +277,5 @@ AgentLedger language parity checks passed
 ## What Not To Assume
 
 - Go/TypeScript/Rust are package surfaces, even though runtime-core semantics are conformance-aligned.
-- Official adapters in 1.3.x use injected clients and dry-run manifests; real cloud SDKs and live service hardening are optional follow-up gates.
+- Official adapters in 1.4.x use injected clients and dry-run manifests; real cloud SDKs and live service hardening are optional follow-up gates.
 - AgentLedger does not replace LangGraph, LangChain, LangSmith, Langfuse, Temporal, Ray, Kubernetes, vector DBs, or eval platforms. It provides the runtime safety/evidence layer those systems can integrate with.