PyPI - agentledger-runtime - Versions diffs - 1.4.1__tar.gz → 1.4.2__tar.gz - Mend

agentledger-runtime 1.4.1tar.gz → 1.4.2tar.gz

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

Files changed (388) hide show

{agentledger_runtime-1.4.1 → agentledger_runtime-1.4.2}/CHANGELOG.md RENAMED Viewed

@@ -8,6 +8,24 @@ This project follows semantic versioning for the stable runtime-core contract. O
 No unreleased changes.
+## 1.4.2 - 2026-06-19
+### Added
+- Added dedicated Inspector read models and HTML panels for archived model calls and model-proposed tool calls.
+- Added stronger Inspector links between model evidence, proposed tool calls, runtime events, Tool Ledger rows, and failure records.
+- Added model evidence and proposed-tool references to portable failure exports, including Langfuse, OpenTelemetry, LangSmith, Temporal-style, and CI-friendly local mappings.
+- Added a dependency-free model evidence example showing how to record externally executed provider/gateway calls without making AgentLedger a model router.
+- Hardened boundary lint for direct database calls, direct filesystem mutation, and risky tool metadata that omits idempotency, approval, or sandbox boundaries.
+- Added a shareable side-effect safety showcase that contrasts naive duplicate side effects with AgentLedger safe retry and generated Inspector HTML.
+- Added adoption content for the showcase, including a Chinese article draft, short social posts, and a deterministic GIF recording flow.
+### Clarified
+- This is a four-language 1.4.2 release train. Runtime-core semantics remain aligned across Python, Go, TypeScript, and Rust.
+- Inspector and boundary lint remain companion/read-model tooling distributed through the Python reference package; Inspector can still consume language-neutral evidence from non-Python runtimes.
+- AgentLedger continues to record model evidence and tool proposals, not provider routing, retry, fallback, key management, or pricing catalogs.
 ## 1.4.1 - 2026-06-19
 ### Added
@@ -344,3 +362,7 @@ No unreleased changes.
 - Exact optional framework packages are not implemented.
 - Rust, TypeScript, and Go implementations are not started.
 - Production sandbox hardening requires external deployment policy.
+---
+generated by codex cli

{agentledger_runtime-1.4.1 → agentledger_runtime-1.4.2}/CODE_OF_CONDUCT.md RENAMED Viewed

@@ -20,3 +20,7 @@ AgentLedger is an open-source engineering project. Contributors, maintainers, an
 ## Enforcement
 Maintainers may edit or remove comments, close issues, reject contributions, or restrict participation when behavior harms the project. Security concerns should be reported through `SECURITY.md`.
+---
+generated by codex cli

{agentledger_runtime-1.4.1 → agentledger_runtime-1.4.2}/CONTRIBUTING.md RENAMED Viewed

@@ -96,3 +96,7 @@ Good first contribution areas:
 - TypeScript worker/client targeting the runtime contract
 - Rust runtime primitive or worker experiments
 - Go infrastructure worker/client experiments
+---
+generated by codex cli

{agentledger_runtime-1.4.1 → agentledger_runtime-1.4.2}/PKG-INFO RENAMED Viewed

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agentledger-runtime
-Version: 1.4.1
+Version: 1.4.2
 Summary: Runtime reliability layer for Agent Harness stacks
 Project-URL: Homepage, https://github.com/yaogdu/AgentLedger
 Project-URL: Repository, https://github.com/yaogdu/AgentLedger
@@ -21,7 +21,7 @@ Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.11
 Provides-Extra: all
-Requires-Dist: agentledger-inspector<2,>=1.4.1; extra == 'all'
+Requires-Dist: agentledger-inspector<2,>=1.4.2; extra == 'all'
 Requires-Dist: agentledger-langfuse<2,>=1.4; extra == 'all'
 Requires-Dist: agentledger-langgraph<2,>=1.4; extra == 'all'
 Requires-Dist: agentledger-mcp<2,>=1.4; extra == 'all'
@@ -33,7 +33,7 @@ Requires-Dist: agentledger-sandbox-docker<2,>=1.4; extra == 'all'
 Provides-Extra: docker
 Requires-Dist: agentledger-sandbox-docker<2,>=1.4; extra == 'docker'
 Provides-Extra: inspector
-Requires-Dist: agentledger-inspector<2,>=1.4.1; extra == 'inspector'
+Requires-Dist: agentledger-inspector<2,>=1.4.2; extra == 'inspector'
 Provides-Extra: langfuse
 Requires-Dist: agentledger-langfuse<2,>=1.4; extra == 'langfuse'
 Provides-Extra: langgraph
@@ -76,6 +76,7 @@ Python remains the reference implementation, and Go, TypeScript, and Rust now ha
 | Need | Go to |
 | --- | --- |
+| See the core value in 3 minutes | [examples/showcase/duplicate_side_effect_crash](examples/showcase/duplicate_side_effect_crash/README.md) |
 | Install and run the first example | [docs/GETTING_STARTED.md](docs/GETTING_STARTED.md) |
 | Decide whether AgentLedger fits your use case | [docs/USE_CASES.md](docs/USE_CASES.md) |
 | Choose Python / Go / TypeScript / Rust | [docs/LANGUAGE_QUICKSTART.md](docs/LANGUAGE_QUICKSTART.md) |
@@ -113,7 +114,7 @@ Inspector exports self-contained, read-only HTML for local or internal debugging
 Use AgentLedger when an agent starts doing work you may need to recover, prove, or replay later: creating tickets, sending emails, changing files, calling internal APIs, querying sensitive systems, waiting for human approval, or running long enough that a worker crash is realistic.
-The fastest way to validate the value is the [3-minute side-effect safety demo](examples/three_minute_demo/README.md). In that controlled demo, a tool side effect succeeds, the worker crashes before commit, and the retry resumes through AgentLedger without duplicating the external write. For concrete production scenarios, guarantee boundaries, and adoption guidance, see [docs/USE_CASES.md](docs/USE_CASES.md).
+The fastest way to validate the value is the [3-minute side-effect safety showcase](examples/showcase/duplicate_side_effect_crash/README.md). It contrasts a naive retry that sends an external email twice with an AgentLedger-managed retry that records the side effect once, resumes safely, and exports Inspector HTML evidence. For concrete production scenarios, guarantee boundaries, and adoption guidance, see [docs/USE_CASES.md](docs/USE_CASES.md).
 ## Scope principle
@@ -192,6 +193,7 @@ The repository includes cross-language 3-minute side-effect safety demos, MCP go
 | Goal | Demo | Run |
 | --- | --- | --- |
+| Shareable crash/retry showcase | Python | `PYTHONPATH=src python3 examples/showcase/duplicate_side_effect_crash/demo.py` |
 | 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` |
@@ -348,7 +350,7 @@ AgentLedger is also not a new LLM SDK, not a workflow engine, not a general obse
 ## Current maturity
-AgentLedger 1.4.x is a stable runtime-core line with Python as the reference implementation and Go, TypeScript, and Rust covered by shared runtime-core parity gates. The four language runtimes share the same runtime-core failure semantics and model evidence boundary: failed steps, retry scheduling, cancellation, lease recovery, Tool Ledger unknown-state handling, cost/failure attribution, evidence, replay, normalized failure envelopes, failure lifecycle, causal graph, replay plan, regression report, alerts, failure export mappings, archived model request/response/failure evidence, and model-proposed tool-call records. The current runtime-core release is 1.4.1 across Python, Go, TypeScript, and Rust; Inspector remains a language-neutral companion viewer distributed through Python/PyPI. It is suitable for local use, framework adapter integration, reliability semantics validation, and production pilot preparation with explicit adapter boundaries.
+AgentLedger 1.4.x is a stable runtime-core line with Python as the reference implementation and Go, TypeScript, and Rust covered by shared runtime-core parity gates. The four language runtimes share the same runtime-core failure semantics and model evidence boundary: failed steps, retry scheduling, cancellation, lease recovery, Tool Ledger unknown-state handling, cost/failure attribution, evidence, replay, normalized failure envelopes, failure lifecycle, causal graph, replay plan, regression report, alerts, failure export mappings, archived model request/response/failure evidence, and model-proposed tool-call records. The current runtime-core release is 1.4.2 across Python, Go, TypeScript, and Rust; Inspector remains a language-neutral companion viewer distributed through Python/PyPI. It is suitable for local use, framework adapter integration, reliability semantics validation, and production pilot preparation with explicit adapter boundaries.
 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).
@@ -403,3 +405,7 @@ See [docs/RELEASE_CHECKLIST.md](docs/RELEASE_CHECKLIST.md) for the complete rele
 ## License
 Apache-2.0. See [LICENSE](LICENSE).
+---
+generated by codex cli

{agentledger_runtime-1.4.1 → agentledger_runtime-1.4.2}/README.md RENAMED Viewed

@@ -24,6 +24,7 @@ Python remains the reference implementation, and Go, TypeScript, and Rust now ha
 | Need | Go to |
 | --- | --- |
+| See the core value in 3 minutes | [examples/showcase/duplicate_side_effect_crash](examples/showcase/duplicate_side_effect_crash/README.md) |
 | Install and run the first example | [docs/GETTING_STARTED.md](docs/GETTING_STARTED.md) |
 | Decide whether AgentLedger fits your use case | [docs/USE_CASES.md](docs/USE_CASES.md) |
 | Choose Python / Go / TypeScript / Rust | [docs/LANGUAGE_QUICKSTART.md](docs/LANGUAGE_QUICKSTART.md) |
@@ -61,7 +62,7 @@ Inspector exports self-contained, read-only HTML for local or internal debugging
 Use AgentLedger when an agent starts doing work you may need to recover, prove, or replay later: creating tickets, sending emails, changing files, calling internal APIs, querying sensitive systems, waiting for human approval, or running long enough that a worker crash is realistic.
-The fastest way to validate the value is the [3-minute side-effect safety demo](examples/three_minute_demo/README.md). In that controlled demo, a tool side effect succeeds, the worker crashes before commit, and the retry resumes through AgentLedger without duplicating the external write. For concrete production scenarios, guarantee boundaries, and adoption guidance, see [docs/USE_CASES.md](docs/USE_CASES.md).
+The fastest way to validate the value is the [3-minute side-effect safety showcase](examples/showcase/duplicate_side_effect_crash/README.md). It contrasts a naive retry that sends an external email twice with an AgentLedger-managed retry that records the side effect once, resumes safely, and exports Inspector HTML evidence. For concrete production scenarios, guarantee boundaries, and adoption guidance, see [docs/USE_CASES.md](docs/USE_CASES.md).
 ## Scope principle
@@ -140,6 +141,7 @@ The repository includes cross-language 3-minute side-effect safety demos, MCP go
 | Goal | Demo | Run |
 | --- | --- | --- |
+| Shareable crash/retry showcase | Python | `PYTHONPATH=src python3 examples/showcase/duplicate_side_effect_crash/demo.py` |
 | 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` |
@@ -296,7 +298,7 @@ AgentLedger is also not a new LLM SDK, not a workflow engine, not a general obse
 ## Current maturity
-AgentLedger 1.4.x is a stable runtime-core line with Python as the reference implementation and Go, TypeScript, and Rust covered by shared runtime-core parity gates. The four language runtimes share the same runtime-core failure semantics and model evidence boundary: failed steps, retry scheduling, cancellation, lease recovery, Tool Ledger unknown-state handling, cost/failure attribution, evidence, replay, normalized failure envelopes, failure lifecycle, causal graph, replay plan, regression report, alerts, failure export mappings, archived model request/response/failure evidence, and model-proposed tool-call records. The current runtime-core release is 1.4.1 across Python, Go, TypeScript, and Rust; Inspector remains a language-neutral companion viewer distributed through Python/PyPI. It is suitable for local use, framework adapter integration, reliability semantics validation, and production pilot preparation with explicit adapter boundaries.
+AgentLedger 1.4.x is a stable runtime-core line with Python as the reference implementation and Go, TypeScript, and Rust covered by shared runtime-core parity gates. The four language runtimes share the same runtime-core failure semantics and model evidence boundary: failed steps, retry scheduling, cancellation, lease recovery, Tool Ledger unknown-state handling, cost/failure attribution, evidence, replay, normalized failure envelopes, failure lifecycle, causal graph, replay plan, regression report, alerts, failure export mappings, archived model request/response/failure evidence, and model-proposed tool-call records. The current runtime-core release is 1.4.2 across Python, Go, TypeScript, and Rust; Inspector remains a language-neutral companion viewer distributed through Python/PyPI. It is suitable for local use, framework adapter integration, reliability semantics validation, and production pilot preparation with explicit adapter boundaries.
 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).
@@ -351,3 +353,7 @@ See [docs/RELEASE_CHECKLIST.md](docs/RELEASE_CHECKLIST.md) for the complete rele
 ## License
 Apache-2.0. See [LICENSE](LICENSE).
+---
+generated by codex cli

{agentledger_runtime-1.4.1 → agentledger_runtime-1.4.2}/README.zh-CN.md RENAMED Viewed

@@ -24,6 +24,7 @@ Python 仍然是 reference implementation；Go、TypeScript、Rust 已有 native
 | 需求 | 入口 |
 | --- | --- |
+| 3 分钟看到核心价值 | [examples/showcase/duplicate_side_effect_crash](examples/showcase/duplicate_side_effect_crash/README.md) |
 | 安装并跑通第一个示例 | [docs/zh/GETTING_STARTED.md](docs/zh/GETTING_STARTED.md) |
 | 判断 AgentLedger 是否适合你的场景 | [docs/zh/USE_CASES.md](docs/zh/USE_CASES.md) |
 | 选择 Python / Go / TypeScript / Rust | [docs/zh/LANGUAGE_QUICKSTART.md](docs/zh/LANGUAGE_QUICKSTART.md) |
@@ -61,7 +62,7 @@ Inspector 会导出自包含、只读的 HTML，适合本地或内网排查问
 当 Agent 开始执行以后可能需要恢复、证明或 replay 的工作时，就适合引入 AgentLedger：创建 ticket、发送邮件、修改文件、调用内部 API、查询敏感系统、等待人工审批，或者任务长到 worker crash 是现实风险。
-最快的价值验证方式是跑 [3 分钟副作用安全 demo](examples/three_minute_demo/README.md)。在这个受控 demo 里，工具副作用已经成功、worker 在提交状态前崩溃、重试通过 AgentLedger 恢复且不会重复外部写入。更具体的生产场景、保证边界和接入判断见 [docs/zh/USE_CASES.md](docs/zh/USE_CASES.md)。
+最快的价值验证方式是跑 [3 分钟副作用安全 showcase](examples/showcase/duplicate_side_effect_crash/README.md)。它会对比一个 naive retry 把外部邮件发送两次，以及 AgentLedger-managed retry 只记录并复用一次副作用、可安全恢复并导出 Inspector HTML evidence。更具体的生产场景、保证边界和接入判断见 [docs/zh/USE_CASES.md](docs/zh/USE_CASES.md)。
 ## 范围原则
@@ -140,6 +141,7 @@ AgentLedger 本身不是完整 Agent Harness。它的设计目标是和 Harness
 | 目标 | Demo | 运行方式 |
 | --- | --- | --- |
+| 传播型 crash/retry showcase | Python | `PYTHONPATH=src python3 examples/showcase/duplicate_side_effect_crash/demo.py` |
 | 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` |
@@ -296,7 +298,7 @@ AgentLedger 也不是新的 LLM SDK，不是 workflow engine，不是通用 obse
 ## 当前成熟度
-AgentLedger 1.4.x 是 stable runtime-core line，Python 是 reference implementation，Go、TypeScript、Rust 已由共享 runtime-core parity gate 覆盖。四种语言 runtime 共享同一组 runtime-core failure semantics 和 model evidence boundary：failed step、retry scheduling、cancellation、lease recovery、Tool Ledger unknown-state handling、cost/failure attribution、evidence、replay、normalized failure envelope、failure lifecycle、causal graph、replay plan、regression report、alerts、failure export mappings、archived model request/response/failure evidence，以及 model-proposed tool-call records。当前 runtime-core release 是 1.4.1，并覆盖 Python、Go、TypeScript、Rust；Inspector 仍是 language-neutral companion viewer，通过 Python/PyPI 分发。适合本地使用、framework adapter integration、reliability semantics 验证，以及在明确 adapter 边界下做 production pilot 准备。
+AgentLedger 1.4.x 是 stable runtime-core line，Python 是 reference implementation，Go、TypeScript、Rust 已由共享 runtime-core parity gate 覆盖。四种语言 runtime 共享同一组 runtime-core failure semantics 和 model evidence boundary：failed step、retry scheduling、cancellation、lease recovery、Tool Ledger unknown-state handling、cost/failure attribution、evidence、replay、normalized failure envelope、failure lifecycle、causal graph、replay plan、regression report、alerts、failure export mappings、archived model request/response/failure evidence，以及 model-proposed tool-call records。当前 runtime-core release 是 1.4.2，并覆盖 Python、Go、TypeScript、Rust；Inspector 仍是 language-neutral companion viewer，通过 Python/PyPI 分发。适合本地使用、framework adapter integration、reliability semantics 验证，以及在明确 adapter 边界下做 production pilot 准备。
 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)。
@@ -351,3 +353,7 @@ cd ../rust && cargo run --quiet -- conformance
 ## License
 Apache-2.0. See [LICENSE](LICENSE)。
+---
+generated by codex cli

{agentledger_runtime-1.4.1 → agentledger_runtime-1.4.2}/SECURITY.md RENAMED Viewed

@@ -54,3 +54,7 @@ threat modeling
 ```
 See `docs/SECURITY_ENTERPRISE.md` for the enterprise security model.
+---
+generated by codex cli

{agentledger_runtime-1.4.1 → agentledger_runtime-1.4.2}/docs/ADAPTER_CERTIFICATION.md RENAMED Viewed

@@ -234,3 +234,7 @@ temporal
 The generated bundle includes package metadata, contract version, conformance commands, smoke commands, required external services, security assumptions, known limitations, and a `production_validation` block.
 For adapters that depend on real infrastructure, `production_validation.status` is intentionally `external-required`. That is not a failure. It means the local runtime has produced the certification contract, but a production claim still needs real credentials, service behavior, concurrency/load checks, and restore or rollback drills. P2-style production hardening must be backed by those external artifacts, not by local mocks alone.
+---
+generated by codex cli

{agentledger_runtime-1.4.1 → agentledger_runtime-1.4.2}/docs/ADAPTER_PACKAGING.md RENAMED Viewed

@@ -271,3 +271,7 @@ The adapter package boundary should not claim production hardening just because
 - media processing adapters
 - sub-agent or multi-agent runtime semantics
 - long-running UI, deployment management, or full eval system
+---
+generated by codex cli

{agentledger_runtime-1.4.1 → agentledger_runtime-1.4.2}/docs/ADAPTER_ROADMAP.md RENAMED Viewed

@@ -68,7 +68,7 @@ These should not block core parity or official release claims.
 | Sandbox | Firecracker | Powerful but infra-heavy; often managed through a platform layer. |
 | Sandbox | bubblewrap | Useful on Linux local machines but less universal across macOS/Windows teams. |
 | 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. |
+| Eval | Langfuse, Phoenix, promptfoo, DeepEval, Ragas, OpenAI Evals, LangSmith, Braintrust, custom CI | Eval remains a consumer of evidence/replay contracts, not runtime-core. AgentLedger should provide adapters/export formats, not a standalone Eval Platform. |
 | Vector DB / RAG | Pinecone, Weaviate, Milvus, pgvector, etc. | Long-term memory/retrieval infra should be external; runtime stores refs/evidence, not knowledge retrieval logic. |
 | Routing advisor / capability router | WisePick-style route decision services | Candidate direction only, not a committed adapter. It may be evaluated as a pre-execution suggestion and post-execution feedback loop, but should remain optional and must not turn AgentLedger core into a capability router or authorization layer. |
 | Application administration backend | User, organization, billing, identity, or control-plane adapters | Out of current project scope. AgentLedger is a framework/library/runtime reliability layer. |
@@ -115,3 +115,8 @@ Every official adapter must provide:
 8. Temporal/Ray/Kubernetes scheduler/backend bridges based on real user demand.
 9. Add model evidence examples for OpenAI-compatible endpoints, Anthropic-style calls, and enterprise gateways without making AgentLedger a model router.
 10. Evaluate only, without implementation commitment, whether a Routing Advisor / Capability Router evidence boundary is useful for WisePick-style services. If later adopted, it should record externally supplied route suggestions, preserve replay by reusing stored routing evidence, and send feedback only after new real executions.
+11. Add eval adapter/export packages for mature open-source eval tools only when the boundary is evidence/replay conversion: Langfuse datasets/scores, Phoenix experiments, promptfoo test cases, DeepEval cases, Ragas rows, OpenAI Evals samples, and CI report inputs. Do not build dataset/scorer/experiment management inside AgentLedger.
+---
+generated by codex cli

{agentledger_runtime-1.4.1 → agentledger_runtime-1.4.2}/docs/ADOPTION.md RENAMED Viewed

@@ -16,8 +16,10 @@ Can I verify the reliability claim myself?
 | Priority | Item | Acceptance criteria |
 |---|---|---|
+| P0 | Shareable side-effect showcase | A user can run `examples/showcase/duplicate_side_effect_crash`, see naive duplicate side effects versus AgentLedger safe retry, and open generated Inspector HTML. |
 | 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. |
+| P0 | Shareable article and short post | A maintainer can use `docs/articles/what-happened-after-agent-tool-failure.zh-CN.md` and `docs/articles/social-posts.md` without inventing positioning copy from scratch. |
 | P1 | MCP governance example | Dependency-free MCP-style tools demonstrate schema, approval, sandbox metadata, idempotency, and audit evidence across Python, Go, TypeScript, and Rust. |
 | P1 | 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. |
@@ -28,6 +30,7 @@ These can be opened as GitHub issues when the project is ready for public tracki
 | Title | Type | Why it matters |
 |---|---|---|
+| Record a side-effect safety GIF from the showcase | adoption | Turns the core value into a short visual artifact for README, social posts, and issue discussions. |
 | Build a cross-language 3-minute Tool Ledger demo | example | Shows the core value in a few minutes across Python, Go, TypeScript, and Rust. |
 | Add OpenAI Agents SDK approval/replay example | example | Connects AgentLedger to a major agent SDK boundary without claiming official endorsement. |
 | Add MCP tool governance example | example | Shows how MCP-style tools should pass through policy, approval, sandbox, idempotency, and evidence. |
@@ -56,3 +59,7 @@ Case studies should be useful but conservative:
 - external demos or blog posts
 - adapter conformance reports
 - real-service hardening reports
+---
+generated by codex cli

{agentledger_runtime-1.4.1 → agentledger_runtime-1.4.2}/docs/ARCHITECTURE.md RENAMED Viewed

@@ -150,3 +150,7 @@ evidence/replay golden fixtures
 ```
 This prevents each language from inventing different event names, lease semantics, idempotency behavior, or evidence bundle shapes.
+---
+generated by codex cli

{agentledger_runtime-1.4.1 → agentledger_runtime-1.4.2}/docs/BACKUP_RESTORE.md RENAMED Viewed

@@ -102,3 +102,7 @@ orchestrate cross-region restore
 ```
 Those operations belong to DBA, SRE, or deployment runbooks. AgentLedger provides conformance checks, evidence export, replay, and deterministic refs so the restore can be verified without running real tools.
+---
+generated by codex cli

{agentledger_runtime-1.4.1 → agentledger_runtime-1.4.2}/docs/COMPARISONS.md RENAMED Viewed

@@ -174,3 +174,7 @@ Can another language/runtime produce the same evidence semantics?
 ```
 That is the intended boundary: framework-neutral runtime safety and evidence, not a replacement for every framework around it.
+---
+generated by codex cli

{agentledger_runtime-1.4.1 → agentledger_runtime-1.4.2}/docs/COMPLETE_CORE_PARITY_CHECKLIST.md RENAMED Viewed

@@ -55,8 +55,8 @@ Excluded or not applicable:
 | CLI baseline | `--help`, `doctor`, `version`, `quickstart`, `conformance`, `contract validate`, `contract export` | `agentledger` CLI | `agentledger-go` | `agentledger-ts` | `agentledger-rust` | `scripts/check_complete_core_parity.py` | done |
 | Quickstart docs | Language quickstart and adapter quickstart | README + docs | `go/README.md` | `typescript/README.md` | `rust/README.md` | docs link check | done |
 | Examples | Runnable examples for core runtime and adapter API | Python examples | `go/examples/quickstart/main.go` | `typescript/examples/quickstart/quickstart.js` | `rust/examples/quickstart.rs` | `scripts/check_complete_core_parity.py` | done |
-| Package metadata | Installable package metadata in the current 1.4 release family | PyPI metadata `1.4.x` | `go.mod` tag `go/v1.4.1` for current baseline | npm package `1.4.1` for current baseline | `Cargo.toml` `1.4.1` 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==1.4.1` release smoke after publish | `go/v1.4.1` clean external `go get` smoke after tag | npm `agentledger-runtime@1.4.1` release smoke after publish | crates.io `agentledger-runtime==1.4.1` 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/v1.4.2` for current baseline | npm package `1.4.2` for current baseline | `Cargo.toml` `1.4.2` for current baseline | `scripts/check_complete_core_parity.py` release-family check | done |
+| Package install smoke | Install/import/run from published or built package | PyPI `agentledger-runtime==1.4.2` release smoke after publish | `go/v1.4.2` clean external `go get` smoke after tag | npm `agentledger-runtime@1.4.2` release smoke after publish | crates.io `agentledger-runtime==1.4.2` release smoke after publish | publish logs + `scripts/check_complete_core_parity.py` dry-run gates | release-gated |
 | Release docs | Changelog, release checklist, status docs reflect exact parity boundary | docs | docs | docs | docs | docs link check | done |
 | Comparison docs | Honest overlap with LangChain/LangGraph/LangSmith/Langfuse/etc. | docs | docs | docs | docs | docs link check | done |
@@ -67,7 +67,7 @@ The strict core parity gate now covers the previously weak areas:
 1. CLI baseline is automatically checked for all four language CLIs.
 2. Go, TypeScript, and Rust have runnable quickstart example files.
 3. TypeScript and Rust package surfaces have package dry-run checks (`npm pack --dry-run`, `cargo package --allow-dirty --no-verify`) and post-publish install smokes are required for release.
-4. Package release families are checked across Python, TypeScript, and Rust. The current core release family is `1.4`; 1.4.1 is a four-language runtime-core feature release for Agent Failure Lifecycle plus Runtime Model Evidence Boundary.
+4. Package release families are checked across Python, TypeScript, and Rust. The current core release family is `1.4`; 1.4.2 keeps the four-language release train aligned while consolidating model evidence UX, export mappings, examples, and boundary lint around the 1.4.0/1.4.1 runtime-core features.
 5. Go external module consumption is tag/release dependent; each release should repeat the clean external `go get` smoke after pushing the `go/vX.Y.Z` tag.
 6. Real service-backed hardening remains out of scope for core parity and stays documented as optional follow-up work.
@@ -82,3 +82,7 @@ python3.11 scripts/check_complete_core_parity.py
 ```
 `check_complete_core_parity.py` must verify CLI baseline, runnable examples, package metadata, and docs links in addition to semantic conformance.
+---
+generated by codex cli

{agentledger_runtime-1.4.1 → agentledger_runtime-1.4.2}/docs/DESIGN_AND_IMPLEMENTATION.md RENAMED Viewed

@@ -244,3 +244,7 @@ The checked-in contract fixture must match:
 PYTHONPATH=src python3 -m agentledger contract export > /tmp/agentledger-contract.json
 diff -u contracts/agentledger.runtime.v1.json /tmp/agentledger-contract.json
 ```
+---
+generated by codex cli

{agentledger_runtime-1.4.1 → agentledger_runtime-1.4.2}/docs/DISTRIBUTED_WORKERS.md RENAMED Viewed

@@ -157,3 +157,7 @@ cancelled run fences stale owner and blocks new claims
 ## Non-goals
 Runtime core does not create deployments, queues, clusters, connection pools, secrets, or cloud resources. It defines worker semantics and provides a reference loop plus conformance tests. Deployment adapters and operations teams own the actual orchestration environment.
+---
+generated by codex cli

{agentledger_runtime-1.4.1 → agentledger_runtime-1.4.2}/docs/EXECUTION_BACKENDS.md RENAMED Viewed

@@ -176,3 +176,7 @@ Temporal Workflow
 In this setup, Temporal owns workflow lifecycle, worker queues, retries, timers, and distributed execution. LangGraph owns graph nodes, edges, routing, and multi-agent orchestration. AgentLedger owns the model/tool boundary inside each node: Tool Ledger, idempotency, approval, sandbox, evidence, replay safety, and cost/failure attribution.
 This is the preferred positioning for complex production systems. AgentLedger should not claim to replace Temporal or LangGraph; it should make LangGraph nodes running inside Temporal agent-safe.
+---
+generated by codex cli

{agentledger_runtime-1.4.1 → agentledger_runtime-1.4.2}/docs/EXTENSIBILITY.md RENAMED Viewed

@@ -386,3 +386,7 @@ Blob adapters should implement `BlobStoreProtocol` and pass `BlobStoreConformanc
 Runtime core owns the contract and audit trail; adapter packages own backend-specific execution. A backend adapter should implement `SandboxExecutor.run_tool(...)`, respect `SandboxPolicy`, and return `SandboxResult` without leaking secrets into metadata. Kubernetes-based adapters should use `runtime_class` for gVisor rather than making gVisor a separate core dependency. The built-in Kubernetes adapter provides a dependency-free Job manifest dry-run and a `kubectl`-gated execution path; stronger integrations can replace it with an in-cluster controller or enterprise scheduler.
 Sandbox adapter packages can remain optional so users who do not want Docker/E2B/Kubernetes can use `none`, `local`, bubblewrap, or their own enterprise executor.
+---
+generated by codex cli

{agentledger_runtime-1.4.1 → agentledger_runtime-1.4.2}/docs/GETTING_STARTED.md RENAMED Viewed

@@ -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@v1.4.1` 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@v1.4.2` 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@v1.4.1
+go get github.com/yaogdu/AgentLedger/go@v1.4.2
 ```
 Install the optional CLI:
 ```bash
-go install github.com/yaogdu/AgentLedger/go/cmd/agentledger-go@v1.4.1
+go install github.com/yaogdu/AgentLedger/go/cmd/agentledger-go@v1.4.2
 agentledger-go --help
 ```
-Important: `go get` must run inside a Go module. `go install github.com/yaogdu/AgentLedger/go@v1.4.1` 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@v1.4.2` is not valid because that path is a library, not `package main`. Use `/cmd/agentledger-go` for the CLI.
 ### TypeScript
@@ -88,6 +88,7 @@ The crate is published as `agentledger-runtime`; the library crate is imported a
 | Goal | Example |
 |---|---|
+| See the side-effect safety problem visually | `../examples/showcase/duplicate_side_effect_crash/README.md` |
 | Understand the core value in 3 minutes | `../examples/three_minute_demo/README.md`; Go `../go/examples/three_minute_demo`; TypeScript `../typescript/examples/three_minute_demo`; Rust `../rust/examples/three_minute_demo.rs` |
 | Smallest Python run | `../examples/hello_world/hello.py` |
 | Idempotent side effects | `../examples/side_effect_idempotency/README.md` |
@@ -149,3 +150,7 @@ python3.11 scripts/check_language_parity.py --json-report /tmp/agentledger-langu
 ```
 These checks verify runtime-core parity, CLI/DX baseline, examples, package metadata, docs links, and shared conformance semantics.
+---
+generated by codex cli

{agentledger_runtime-1.4.1 → agentledger_runtime-1.4.2}/docs/HARNESS_STACK.md RENAMED Viewed

@@ -237,3 +237,7 @@ AgentLedger should not become:
 - an application administration, identity, billing, or control-plane backend.
 The long-term direction is to make AgentLedger the reliability substrate that allows a harness stack to be assembled from mature components without losing durable execution, governance, evidence, replay, and side-effect safety.
+---
+generated by codex cli

{agentledger_runtime-1.4.1 → agentledger_runtime-1.4.2}/docs/IMPLEMENTATION_PLAN.md RENAMED Viewed

@@ -319,3 +319,7 @@ Success criteria:
 - Container: Docker adapter package for common local/team deployments.
 - Cluster: Kubernetes adapter with Job manifest dry-run, optional `kubectl` create/wait/log/delete execution, and `runtime_class` support for gVisor/Kata-style runtimes.
 - High isolation: Firecracker/E2B/custom remote executor packages for untrusted code scenarios.
+---
+generated by codex cli

{agentledger_runtime-1.4.1 → agentledger_runtime-1.4.2}/docs/IMPLEMENTATION_STATUS.md RENAMED Viewed

@@ -15,12 +15,27 @@ AgentLedger 1.4.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.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. 1.4.1 adds the four-language Runtime Model Evidence Boundary: archived model request/response/failure evidence, model-proposed tool calls, and model cost/failure/replay semantics without provider routing. 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 added 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. 1.4.1 added the four-language Runtime Model Evidence Boundary: archived model request/response/failure evidence, model-proposed tool calls, and model cost/failure/replay semantics without provider routing. 1.4.2 consolidates that path with dedicated Inspector model-call/tool-proposal views, stronger failure export mappings, a model evidence example, and boundary lint hardening. 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.
 Scope rule: runtime-core should stay thin but indispensable. It should own only guarantees that cannot be enforced outside the runtime boundary; mature planning, workflow, eval, observability, RAG, sandbox infrastructure, and deployment systems should integrate through adapters or consume evidence/replay outputs.
+## Verification Boundary
+The release gates prove the covered runtime contracts and conformance scenarios, not the absence of all defects. Current automated checks cover unit tests, dependency-free examples, contract snapshots, adapter package metadata, cross-language runtime-core conformance, parity audits, lint rules, and Markdown/link hygiene.
+Areas that still require separate validation before production claims include:
+- browser-level visual regressions for generated static HTML reports
+- real Postgres/MySQL/S3/OTLP/sandbox services under realistic concurrency and failure modes
+- framework-native adapters against real framework versions
+- organization-specific policy packs, secret handling, redaction rules, and approval workflows
+- large evidence bundles, long-running runs, and high-cardinality production data
+- business-project integration smoke tests such as `legal-agent`
+When this document says a feature is implemented or stable, it means the feature is present and covered by the stated contract/test boundary. It does not mean every downstream integration, browser rendering edge case, or external infrastructure path is exhaustively verified.
 ## Current Completion Boundary
 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.
@@ -51,7 +66,7 @@ Excluded from this boundary:
 | Evidence regression primitives | side-effect-free evidence checks, `evidence-regression` media/stream gates, machine-readable regression summaries, adversarial review, evidence regression checklist with media/stream evidence checks, divergence report with media/stream dimensions, golden corpus seed/add/list/check with baseline, Tool Ledger, and media/stream built-ins |
 | Shadow mode | side-effect-safe candidate runs using archived Tool Ledger responses |
 | Cost and budget | store-backed cost records, budget enforcement hooks, read-only cost attribution report by run/agent/step/category/tool/model, and model evidence usage/USD attribution |
-| Runtime Model Evidence Boundary | `agentledger.model.evidence.v1`, external model-call evidence APIs, `model_call_requested/completed/failed`, `tool_call_proposed`, model failure category, and replay-safe archived model evidence semantics |
+| Runtime Model Evidence Boundary | `agentledger.model.evidence.v1`, external model-call evidence APIs, `model_call_requested/completed/failed`, `tool_call_proposed`, model failure category, replay-safe archived model evidence semantics, Inspector model-call/tool-proposal views, and export mappings for model evidence refs |
 | Approval and policy | approval request/approve/deny flow, YAML/JSON policy checks, `PolicyRequest`, `PolicyDecision`, `PolicyFinding`, `PolicyControl`, built-in evaluator registry, decision evidence in `tool_permission_decided` |
 | Scheduling semantics | leases, fencing, heartbeat, cancellation, retry policy, failure taxonomy |
 | Worker loop | local worker loop, process-shaped `WorkerService`, worker conformance runner |
@@ -60,7 +75,7 @@ Excluded from this boundary:
 | 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` 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 |
+| 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, database, filesystem, cloud, GitHub, risky ToolSpec metadata, 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 |
@@ -116,3 +131,7 @@ Large capabilities such as Eval, Observability, Guardrails, Tool Gateway/Sandbox
 3. Harden production-pilot adapter paths: Postgres, S3/MinIO, worker deployment, OTLP transport, and non-destructive retention/backup checks. These P2 claims require real services, load/concurrency checks, and restore or rollback drills; local certification manifests intentionally mark them as external-required.
 4. Build richer external evidence consumers and eval adapters outside runtime-core.
 5. Extend media/stream preview contracts into optional adapters only after the core reliability harness remains stable.
+---
+generated by codex cli

{agentledger_runtime-1.4.1 → agentledger_runtime-1.4.2}/docs/INSPECTOR.md RENAMED Viewed

@@ -155,6 +155,22 @@ This view is intended for debugging a single run from top to bottom. It does not
 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.
+## Model Evidence
+`1.4.2` adds dedicated Inspector sections for the Runtime Model Evidence Boundary:
+- `Model Calls`: archived `model_call_requested`, `model_call_completed`, and `model_call_failed` evidence, including provider/model metadata, request/response/failure refs, usage, cost, step id, and status.
+- `Tool Proposals`: `tool_call_proposed` records emitted before ToolGateway execution, including the proposed tool name, arguments refs, model/provider metadata, confidence, reason, and links back to model-call evidence when available.
+These sections answer debugging questions such as:
+- What exact model request and response were attached to this run?
+- Did the model propose a tool call before the runtime executed a tool?
+- Was the failure caused by the model call, the runtime, or the tool execution?
+- Which evidence refs should be exported to Langfuse, OpenTelemetry, LangSmith, Temporal-style consumers, or CI?
+Inspector still does not route model calls, retry providers, manage keys, fetch pricing catalogs, or contact model providers. It only reads AgentLedger evidence that the runtime, user code, framework adapter, provider SDK, or external model gateway already recorded.
 ## 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.
@@ -329,3 +345,7 @@ Not in this version:
 - permission, identity, billing, or administration backend
 - full LangSmith/Langfuse replacement
 - live remote blob adapters inside the Inspector package
+---
+generated by codex cli

{agentledger_runtime-1.4.1 → agentledger_runtime-1.4.2}/docs/LANGUAGE_IMPLEMENTATION_COMPARISON.md RENAMED Viewed

@@ -4,7 +4,7 @@
 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` and `1.4.1` are different: they are four-language runtime-core feature releases for the Agent Failure Lifecycle and Runtime Model Evidence Boundary, 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 and model evidence contracts themselves are implemented across all four runtime packages.
+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. The `1.4.x` line is different: `1.4.0` introduced the four-language Agent Failure Lifecycle, `1.4.1` introduced the four-language Runtime Model Evidence Boundary, and `1.4.2` keeps the four-language release train while consolidating model evidence Inspector UX, export mappings, examples, and boundary lint. Inspector remains a language-neutral companion viewer distributed through Python/PyPI, but the failure lifecycle and model evidence contracts themselves are implemented across all four runtime packages.
 ## How To Read This Table
@@ -130,3 +130,7 @@ The current directories should stay as they are:
 | `src/agentledger/` | Yes | Python reference package layout. |
 Renaming `typescript/` to `node/` is not recommended right now: it would create churn without improving runtime semantics. If a future repo split happens, package/repo naming can be revisited then.
+---
+generated by codex cli

{agentledger_runtime-1.4.1 → agentledger_runtime-1.4.2}/docs/LANGUAGE_PARITY_AUDIT.md RENAMED Viewed

@@ -100,3 +100,7 @@ Run this before claiming parity:
 ```
 Expected result for the current scope: `gap_count: 0`.
+---
+generated by codex cli

{agentledger_runtime-1.4.1 → agentledger_runtime-1.4.2}/docs/LANGUAGE_PARITY_MATRIX.md RENAMED Viewed

@@ -114,3 +114,7 @@ all stable language runtimes move together
 contract changes require synchronized implementation and conformance updates
 breaking runtime semantics require a new major contract version
 ```
+---
+generated by codex cli

agentledger-runtime 1.4.1__tar.gz → 1.4.2__tar.gz

agentledger-runtime 1.4.1tar.gz → 1.4.2tar.gz