agentledger-runtime 1.3.0__tar.gz → 1.3.2__tar.gz

{agentledger_runtime-1.3.0 → agentledger_runtime-1.3.2}/CHANGELOG.md

@@ -8,6 +8,25 @@ This project follows semantic versioning for the stable runtime-core contract. O
 
 No unreleased changes yet.
 
+## 1.3.2
+
+### Added
+
+- Added configurable Inspector redaction policies for JSON and static HTML reports.
+- Added `agentledger inspector run/evidence --redact-key ...` and `--redaction-policy policy.json` for local or internal debugging with sensitive fields masked.
+- Exported `InspectorRedactionPolicy` from both `agentledger-runtime` and the optional `agentledger-inspector` companion package for custom viewers.
+
+### Clarified
+
+- This is an Inspector-only patch release. It does not change the stable runtime-core contract or require Go, TypeScript, or Rust runtime-core changes.
+
+## 1.3.1
+
+### Fixed
+
+- Added the Python `agentledger version` CLI command so the Python reference CLI matches the documented four-language CLI baseline.
+- Aligned the Python, Go, TypeScript, and Rust package train to `1.3.1` after the post-release install smoke caught the missing Python command.
+
 ## 1.3.0
 
 ### Added

{agentledger_runtime-1.3.0 → agentledger_runtime-1.3.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agentledger-runtime
-Version: 1.3.0
+Version: 1.3.2
 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,>=1.3; extra == 'all'
+Requires-Dist: agentledger-inspector<2,>=1.3.2; 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'
@@ -33,7 +33,7 @@ Requires-Dist: agentledger-sandbox-docker<2,>=1.3; extra == 'all'
 Provides-Extra: docker
 Requires-Dist: agentledger-sandbox-docker<2,>=1.3; extra == 'docker'
 Provides-Extra: inspector
-Requires-Dist: agentledger-inspector<2,>=1.3; extra == 'inspector'
+Requires-Dist: agentledger-inspector<2,>=1.3.2; extra == 'inspector'
 Provides-Extra: langfuse
 Requires-Dist: agentledger-langfuse<2,>=1.3; extra == 'langfuse'
 Provides-Extra: langgraph
@@ -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 1.3.0 stable](https://img.shields.io/badge/Version-1.3.0--stable-111827)
+![Version 1.3.x stable](https://img.shields.io/badge/Version-1.3.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 `1.3.0` is a runtime reliability layer for Agent Harness stacks. It does not try to teach agents how to reason or replace the surrounding harness ecosystem; it makes agent runs durable, auditable, replayable, policy-governed, and recoverable when workers crash, tools fail, or prompts change.
+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.
 
 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.
 
@@ -333,7 +333,7 @@ AgentLedger is also not a new LLM SDK, not a workflow engine, not a general obse
 
 ## Current maturity
 
-AgentLedger 1.3.0 is a stable runtime-core release with Python as the reference implementation and Go, TypeScript, and Rust covered by shared runtime-core parity gates. It is suitable for local use, framework adapter integration, reliability semantics validation, and production pilot preparation with explicit adapter boundaries.
+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 1.3.2; 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.
 
 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-1.3.0 → agentledger_runtime-1.3.2}/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 1.3.0 stable](https://img.shields.io/badge/Version-1.3.0--stable-111827)
+![Version 1.3.x stable](https://img.shields.io/badge/Version-1.3.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 `1.3.0` is a runtime reliability layer for Agent Harness stacks. It does not try to teach agents how to reason or replace the surrounding harness ecosystem; it makes agent runs durable, auditable, replayable, policy-governed, and recoverable when workers crash, tools fail, or prompts change.
+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.
 
 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.
 
@@ -281,7 +281,7 @@ AgentLedger is also not a new LLM SDK, not a workflow engine, not a general obse
 
 ## Current maturity
 
-AgentLedger 1.3.0 is a stable runtime-core release with Python as the reference implementation and Go, TypeScript, and Rust covered by shared runtime-core parity gates. It is suitable for local use, framework adapter integration, reliability semantics validation, and production pilot preparation with explicit adapter boundaries.
+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 1.3.2; 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.
 
 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-1.3.0 → agentledger_runtime-1.3.2}/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 1.3.0 stable](https://img.shields.io/badge/Version-1.3.0--stable-111827)
+![Version 1.3.x stable](https://img.shields.io/badge/Version-1.3.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 `1.3.0` 是面向 Agent Harness stack 的 runtime reliability layer。它不负责让 Agent 更会“思考”，也不替代完整 Harness 生态；它负责让 Agent run 在 worker 崩溃、工具失败、prompt 变更和长任务恢复时，仍然具备持久化、可审计、可重放、可治理和可恢复能力。
+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。
 
 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。
 
@@ -282,7 +282,7 @@ AgentLedger 也不是新的 LLM SDK，不是 workflow engine，不是通用 obse
 
 ## 当前成熟度
 
-AgentLedger 1.3.0 是 stable runtime-core release，Python 是 reference implementation，Go、TypeScript、Rust 已由共享 runtime-core parity gate 覆盖；适合本地使用、framework adapter integration、reliability semantics 验证，以及在明确 adapter 边界下做 production pilot 准备。
+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 1.3.2；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。
 
 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-1.3.0 → agentledger_runtime-1.3.2}/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 1.3.0
-PYTHONPATH=src python3 -m agentledger adapter certify --kind mysql --adapter-version 1.3.0 --out ./mysql-certification.json
-PYTHONPATH=src python3 -m agentledger adapter certify --kind s3 --adapter-version 1.3.0 --out ./s3-certification.json
-PYTHONPATH=src python3 -m agentledger adapter certify --kind langgraph --adapter-version 1.3.0 --package-name agentledger-langgraph
+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
 ```
 
 Supported built-in profiles:

{agentledger_runtime-1.3.0 → agentledger_runtime-1.3.2}/docs/ADAPTER_PACKAGING.md

@@ -1,6 +1,6 @@
 # Adapter Packaging
 
-AgentLedger `1.2.1` introduced the adapter packaging model, `1.2.2` extended it with the official MySQL storage adapter boundary, `1.2.3` added a dependency-free Langfuse evidence/trace export boundary, and `1.3.0` adds the read-only Inspector companion package. Runtime-core stays small and dependency-light; concrete integrations and external evidence consumers move into optional packages that can be installed through extras or directly.
+AgentLedger `1.2.1` introduced the adapter packaging model, `1.2.2` extended it with the official MySQL storage adapter boundary, `1.2.3` added a dependency-free Langfuse evidence/trace export boundary, and `1.3.0` added the read-only Inspector companion package. Runtime-core stays small and dependency-light; concrete integrations and external evidence consumers move into optional packages that can be installed through extras or directly.
 
 ## Why Split Adapters
 
@@ -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 1.3.0
-PYTHONDONTWRITEBYTECODE=1 PYTHONPATH=src python3 -m agentledger adapter certify --kind mysql --adapter-version 1.3.0
+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 scripts/check_adapter_packages.py
 go test ./...
 cd typescript && npm test

{agentledger_runtime-1.3.0 → agentledger_runtime-1.3.2}/docs/ADAPTER_ROADMAP.md

@@ -70,6 +70,7 @@ These should not block core parity or official release claims.
 | Workflow | Airflow / Prefect / Argo | They are batch/workflow systems; useful bridges, but AgentLedger should not become a general workflow engine. |
 | Eval | LangSmith / Braintrust / custom eval platforms | Eval remains a consumer of evidence/replay contracts, not runtime-core. |
 | Vector DB / RAG | Pinecone, Weaviate, Milvus, pgvector, etc. | Long-term memory/retrieval infra should be external; runtime stores refs/evidence, not knowledge retrieval logic. |
+| 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. |
 
 ## Cross-Language Policy
@@ -113,3 +114,4 @@ Every official adapter must provide:
 7. Kubernetes sandbox/backend recipe, then optional execution adapter.
 8. Temporal/Ray/Kubernetes scheduler/backend bridges based on real user demand.
 9. Model provider/router adapters after the runtime `ModelGateway` contract is stable.
+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.

{agentledger_runtime-1.3.0 → agentledger_runtime-1.3.2}/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 release train | PyPI metadata `1.3.0` | `go.mod` tag `go/v1.3.0` | npm package `1.3.0` | `Cargo.toml` `1.3.0` | `scripts/check_complete_core_parity.py` version check | done |
-| Package install smoke | Install/import/run from published or built package | PyPI `agentledger-runtime==1.3.0` release smoke after publish | `go/v1.3.0` clean external `go get` smoke after tag | npm `agentledger-runtime@1.3.0` release smoke after publish | crates.io `agentledger-runtime==1.3.0` 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 1.3 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==1.3.2` 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 |
 | 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 versions are checked across Python, TypeScript, and Rust; the current release train is aligned at `1.3.0`.
+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 `1.3.2` without changing non-Python runtime-core baselines.
 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-1.3.0 → agentledger_runtime-1.3.2}/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@v1.3.0` 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` |
+| 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` |
 | 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@v1.3.0
+go get github.com/yaogdu/AgentLedger/go@v1.3.1
 ```
 
 Install the optional CLI:
 
 ```bash
-go install github.com/yaogdu/AgentLedger/go/cmd/agentledger-go@v1.3.0
+go install github.com/yaogdu/AgentLedger/go/cmd/agentledger-go@v1.3.1
 agentledger-go --help
 ```
 
-Important: `go get` must run inside a Go module. `go install github.com/yaogdu/AgentLedger/go@v1.3.0` 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@v1.3.1` is not valid because that path is a library, not `package main`. Use `/cmd/agentledger-go` for the CLI.
 
 ### TypeScript
 

{agentledger_runtime-1.3.0 → agentledger_runtime-1.3.2}/docs/IMPLEMENTATION_STATUS.md

@@ -6,7 +6,7 @@ This document tracks what is implemented in runtime-core, what remains planned f
 
 ## Current Baseline
 
-AgentLedger 1.3.0 is a stable runtime-core line with Python as the reference implementation and Go/TypeScript/Rust covered by shared runtime-core parity gates. The 1.3.0 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 1.3.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:
 
 - local use
 - runtime design review
@@ -15,7 +15,7 @@ AgentLedger 1.3.0 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 adds 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. 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: 1.3.0 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. 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.
 
@@ -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, evidence-bundle input, read-only SQLite input, Postgres/MySQL read paths through existing adapter boundaries, optional `agentledger-inspector` companion package |
+| Inspector | `agentledger.inspector.v1` read model, `agentledger inspector run/evidence`, static HTML report, 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-1.3.0 → agentledger_runtime-1.3.2}/docs/INSPECTOR.md

@@ -90,6 +90,38 @@ 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.
 
+## Redaction
+
+Inspector output can include sensitive operational evidence, especially when `--include-payloads` is used. `1.3.2` adds explicit redaction for JSON and HTML reports. Redaction is applied to the Inspector read model before rendering, so custom viewers that consume `InspectorReport.to_dict()` receive the same masked data as the default HTML renderer.
+
+Redact one or more keys directly:
+
+```bash
+agentledger inspector evidence ./evidence/<run_id> \
+  --include-payloads \
+  --redact-key password \
+  --redact-key api_token \
+  --html ./inspector.html
+```
+
+Use a policy file when the same rule should be reused:
+
+```json
+{
+  "keys": ["password", "api_token", "authorization"],
+  "replacement": "[redacted]"
+}
+```
+
+```bash
+agentledger inspector run <run_id> \
+  --root .agentledger \
+  --redaction-policy ./inspector-redaction.json \
+  --out ./inspector.json
+```
+
+The built-in policy matches exact key names case-insensitively and also redacts JSON strings that can be parsed as objects or arrays. It is a local debug safeguard, not a substitute for upstream secret management, database permissions, or evidence retention policy.
+
 ## Extension API
 
 Inspector is intentionally split into three pieces so users can extend it:
@@ -103,12 +135,13 @@ Inspector is intentionally split into three pieces so users can extend it:
 Example:
 
 ```python
-from agentledger import InspectorDataSource, InspectorReportBuilder
+from agentledger import InspectorDataSource, InspectorRedactionPolicy, InspectorReportBuilder
 
-report = InspectorDataSource().from_evidence_path("./evidence/run-1")
+policy = InspectorRedactionPolicy(keys=("password", "api_token"))
+report = InspectorDataSource().from_evidence_path("./evidence/run-1", redaction_policy=policy)
 data = report.to_dict()
 
-custom_report = InspectorReportBuilder().from_evidence_path("./evidence/run-1")
+custom_report = InspectorReportBuilder().from_evidence_path("./evidence/run-1", redaction_policy=policy)
 html = custom_report.to_html()
 ```
 
@@ -135,6 +168,7 @@ For secondary development, keep these contracts stable:
 
 - accept `InspectorReport.to_dict()` as the UI/API input
 - preserve `schema_version == "agentledger.inspector.v1"`
+- apply `InspectorRedactionPolicy` before exposing reports to users when payloads may contain secrets
 - implement `EvidenceStateStoreProtocol` / `EvidenceBlobStoreProtocol` for custom stores
 - keep write/control actions out of Inspector surfaces
 - use runtime APIs, not Inspector data sources, when an operator needs to approve, deny, cancel, or recover a run
@@ -143,6 +177,7 @@ For secondary development, keep these contracts stable:
 
 - Treat Inspector JSON and HTML as sensitive operational evidence.
 - Reports can include tool names, tool status, external ids, approval reasons, model metadata, artifact refs, payload summaries, and failure details.
+- Use `--redact-key` or `--redaction-policy` before sharing reports outside the local debugging boundary.
 - Use read-only DB credentials for Postgres/MySQL.
 - Do not build custom write actions on top of Inspector reports. Use runtime APIs for runtime control and keep debug viewers read-only.
 - Prefer evidence-bundle input when the blob store is remote or managed by another service.
@@ -160,6 +195,10 @@ Implemented in `1.3.0`:
 - extension API for custom data sources and renderers
 - optional `agentledger-inspector` companion package
 
+Implemented in `1.3.2`:
+
+- configurable JSON/HTML report redaction through `--redact-key`, `--redaction-policy`, and `InspectorRedactionPolicy`
+
 Not in this version:
 
 - long-running web server

{agentledger_runtime-1.3.0 → agentledger_runtime-1.3.2}/docs/LANGUAGE_QUICKSTART.md

@@ -2,7 +2,7 @@
 
 [English](LANGUAGE_QUICKSTART.md) | [中文](zh/LANGUAGE_QUICKSTART.md)
 
-AgentLedger 1.3.0 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.
+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 1.3.2 while the non-Python runtime-core package baselines remain on the latest shared runtime-core tag.
 
 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@v1.3.0
+go get github.com/yaogdu/AgentLedger/go@v1.3.1
 ```
 
 Install the optional CLI command:
 
 ```bash
-go install github.com/yaogdu/AgentLedger/go/cmd/agentledger-go@v1.3.0
+go install github.com/yaogdu/AgentLedger/go/cmd/agentledger-go@v1.3.1
 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@v1.3.0` 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@v1.3.1` 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 1.3.0:
+Expected for 1.3.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 1.3.0 use injected clients and dry-run manifests; real cloud SDKs and live service hardening are optional follow-up gates.
+- 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.
 - 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.

{agentledger_runtime-1.3.0 → agentledger_runtime-1.3.2}/docs/ROADMAP.md

@@ -22,6 +22,7 @@ Most capabilities should be evaluated in three layers: core contract, built-in m
 | FinOps / Cost Control | token/call/cost records, budget enforcement hooks, cost attribution reports | provider price catalogs, finance exports, alerts | invoice or payment system |
 | Inspector / Debug Viewer | stable read models, evidence export, static HTML debug export, redaction hooks, schema/version metadata | separate read-only local or internal inspector package | deployment management service, write/control plane in runtime-core |
 | Model Gateway / Router | model-call boundary, request/response archival, replay skipping, token/cost attribution, budget/fallback semantics | provider adapters, LiteLLM-style router adapters, policy packs, price catalogs | bundling every model SDK, becoming a full model gateway product, replacing provider SDKs |
+| Routing Advisor / Capability Router | candidate boundary only; no committed core feature. If future evaluation proves the boundary useful, runtime may record externally supplied route decisions as evidence and keep replay deterministic | possible WisePick-style capability router adapters or feedback clients, only if real usage justifies them | becoming a capability router, optimizing provider selection in core, or treating external routing decisions as authorization or idempotency keys |
 
 Execution backend positioning is documented in `EXECUTION_BACKENDS.md`: Temporal, Ray, and Kubernetes are backend adapters for generic distributed execution, while AgentLedger keeps agent-specific runtime invariants.
 
@@ -54,6 +55,7 @@ Recommended stack positioning:
 | Observability / eval UI | Langfuse, LangSmith, OpenTelemetry, custom dashboards | structured events, evidence bundles, trace/cost/failure export, correlation IDs |
 | Tool and context protocols | MCP, internal tool servers, provider SDK tools | ToolGateway, Tool Ledger, schema validation, approvals, sandbox, audit records |
 | Model providers / routers | OpenAI, Anthropic, Gemini, Bedrock, Ollama, LiteLLM | ModelGateway contract, archived model responses, budget/fallback/replay semantics |
+| Routing advisors / capability routers | WisePick-style decision services, custom capability routers | candidate integration boundary only; no planned implementation until real usage proves the need |
 | Storage / artifacts | SQLite, Postgres, MySQL, S3/MinIO, internal stores | StateStore/BlobStore contracts, migrations, conformance, evidence refs |
 
 ### Must Stay In Runtime-Core
@@ -101,6 +103,7 @@ LiteLLM and enterprise model gateways
 vector databases, RAG systems, long-term memory systems
 eval platforms and benchmark runners
 MCP tool servers and enterprise tool catalogs
+routing advisors and capability routers such as WisePick-style services; candidate only, if future evaluation proves the boundary useful
 ```
 
 AgentLedger should provide adapters, export formats, evidence bundles, trace correlation, and conformance checks for these layers.
@@ -552,6 +555,12 @@ Implemented in `1.3.0`:
 - static HTML export for shareable offline debugging
 - Tool Ledger, approval, policy decision, cost/failure, artifact, and timeline read model
 
+Implemented in `1.3.2`:
+
+- configurable Inspector redaction policy for JSON and static HTML output
+- CLI support for `--redact-key`, `--redaction-policy`, and `--redaction-replacement`
+- `InspectorRedactionPolicy` API for custom read-model consumers
+
 Follow-up work:
 
 - run/session list with status, timestamps, cost summary, and failure summary
@@ -560,7 +569,7 @@ Follow-up work:
 - Tool Ledger view with idempotency key, causal token, side-effect status, request/response refs, and unknown-state handling
 - artifact/evidence browser with payload refs, blob hashes, media refs, and stream checkpoint refs
 - cost and failure attribution panels
-- configurable redaction for secrets, credentials, prompts, payload fields, and large blobs
+- richer redaction presets for prompts, large blobs, and project-specific evidence fields
 - schema/version compatibility checks before reading a database
 
 Explicit non-goals:

{agentledger_runtime-1.3.0 → agentledger_runtime-1.3.2}/docs/USAGE.md

@@ -235,7 +235,7 @@ AGENTLEDGER_MYSQL_DSN=mysql://user:password@localhost:3306/database \
 PYTHONPATH=src python3 -m agentledger migrate up --dialect mysql
 ```
 
-Do not run adapter conformance against real application data. Use temporary test services. MySQL support in `1.3.0` is an official adapter boundary; production use still requires real-service concurrency, permission, backup, and restore validation.
+Do not run adapter conformance against real application data. Use temporary test services. MySQL support in `1.3.1` is an official adapter boundary; production use still requires real-service concurrency, permission, backup, and restore validation.
 
 ## Media and Streams
 
@@ -257,8 +257,8 @@ PYTHONPATH=src python3 -m agentledger state conformance --backend sqlite
 PYTHONPATH=src python3 -m agentledger blob conformance --backend local
 PYTHONPATH=src python3 -m agentledger worker conformance --backend sqlite --concurrent
 PYTHONPATH=src python3 -m agentledger adapter conformance --kind langchain
-PYTHONPATH=src python3 -m agentledger adapter certify --kind postgres --adapter-version 1.3.0 --out ./postgres-certification.json
-PYTHONPATH=src python3 -m agentledger adapter certify --kind mysql --adapter-version 1.3.0 --out ./mysql-certification.json
+PYTHONPATH=src python3 -m agentledger adapter certify --kind postgres --adapter-version 1.3.1 --out ./postgres-certification.json
+PYTHONPATH=src python3 -m agentledger adapter certify --kind mysql --adapter-version 1.3.1 --out ./mysql-certification.json
 ```
 
 `adapter certify` emits a machine-readable adapter certification bundle. It records package metadata, conformance commands, smoke commands, required external services, security assumptions, known limitations, and whether production validation still requires real infrastructure. For example, Postgres/MySQL/S3/Docker/Temporal bundles are marked `external-required` until they have real service credentials, concurrency/load checks, and restore or rollback drills.

{agentledger_runtime-1.3.0 → agentledger_runtime-1.3.2}/docs/zh/ADAPTER_CERTIFICATION.md

@@ -146,10 +146,10 @@ backup/restore notes if stateful
 AgentLedger 可以为官方 adapter profile 生成机器可读的起始认证 bundle：
 
 ```bash
-PYTHONPATH=src python3 -m agentledger adapter certify --kind postgres --adapter-version 1.3.0
-PYTHONPATH=src python3 -m agentledger adapter certify --kind mysql --adapter-version 1.3.0 --out ./mysql-certification.json
-PYTHONPATH=src python3 -m agentledger adapter certify --kind s3 --adapter-version 1.3.0 --out ./s3-certification.json
-PYTHONPATH=src python3 -m agentledger adapter certify --kind langgraph --adapter-version 1.3.0 --package-name agentledger-langgraph
+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
 ```
 
 内置 profile：

{agentledger_runtime-1.3.0 → agentledger_runtime-1.3.2}/docs/zh/ADAPTER_PACKAGING.md

@@ -240,8 +240,8 @@ packaging release 期望通过：
 
 ```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 1.3.0
-PYTHONDONTWRITEBYTECODE=1 PYTHONPATH=src python3 -m agentledger adapter certify --kind mysql --adapter-version 1.3.0
+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 scripts/check_adapter_packages.py
 go test ./...
 cd typescript && npm test

{agentledger_runtime-1.3.0 → agentledger_runtime-1.3.2}/docs/zh/ADAPTER_ROADMAP.md

@@ -70,6 +70,7 @@ Docker 优先官方化，是因为它适合作为 reference sandbox adapter，
 | Workflow | Airflow / Prefect / Argo | 它们是 batch/workflow 系统；可以桥接，但 AgentLedger 不应变成通用 workflow engine。 |
 | Eval | LangSmith / Braintrust / custom eval platforms | Eval 是 evidence/replay contract 的消费者，不属于 runtime-core。 |
 | Vector DB / RAG | Pinecone、Weaviate、Milvus、pgvector 等 | Long-term memory/retrieval infra 应外置；runtime 存 ref/evidence，不拥有知识检索逻辑。 |
+| Routing advisor / capability router | WisePick-style route decision service | 仅作为候选方向，不是已承诺 adapter。可以评估其作为执行前 suggestion 和执行后 feedback loop 的价值，但应保持 optional，不能把 AgentLedger core 变成 capability router 或授权层。 |
 | 应用管理后台 | 用户、组织、计费、身份或控制面 adapter | 当前项目范围外。AgentLedger 是 framework/library/runtime reliability layer。 |
 
 ## 跨语言策略
@@ -113,3 +114,4 @@ Python 是 reference implementation，但官方 adapter 在生态存在时应尽
 7. Kubernetes sandbox/backend recipe，然后再做 optional execution adapter。
 8. 根据真实用户需求做 Temporal/Ray/Kubernetes scheduler/backend bridge。
 9. `ModelGateway` contract 稳定后，再做 model provider/router adapters。
+10. 仅评估，不承诺实现：Routing Advisor / Capability Router evidence boundary 是否对 WisePick-style services 有价值。如果后续采纳，应记录外部传入的 route suggestion，replay 时复用已存 routing evidence，并且只在新的真实执行完成后发送 feedback。

{agentledger_runtime-1.3.0 → agentledger_runtime-1.3.2}/docs/zh/COMPLETE_CORE_PARITY_CHECKLIST.md

@@ -26,7 +26,7 @@
 1. 四语言 CLI baseline 已有自动化检查，不再只依赖 conformance。
 2. Go、TypeScript、Rust 已有 runnable quickstart example files。
 3. TypeScript/Rust package surface 已有 `npm pack --dry-run` / `cargo package --allow-dirty --no-verify` 发布 dry-run；发布后仍需重复 clean install smoke。
-4. Python、TypeScript、Rust 的 package version 已自动检查；当前 release train 对齐到 `1.3.0`。
+4. Python、TypeScript、Rust 的 package release family 已自动检查；当前 core release family 是 `1.3`。Python 可以有 Inspector-only patch release，例如 `1.3.2`，不代表非 Python runtime-core baseline 必须同时变化。
 5. Go module 外部消费依赖 Git tag/release；每次 release 推送 `go/vX.Y.Z` tag 后都需要重复 clean external `go get` smoke。
 6. 真实服务 hardening 仍不属于 core parity，继续作为 optional follow-up 记录。
 

{agentledger_runtime-1.3.0 → agentledger_runtime-1.3.2}/docs/zh/GETTING_STARTED.md

@@ -9,7 +9,7 @@
 | 语言 | 安装 / 使用 | Quickstart | 示例 | 包 / 命令 |
 |---|---|---|---|---|
 | Python | `pipx install agentledger-runtime` 或 `pip install agentledger-runtime` | `agentledger quickstart` | `../../examples/README.md` | PyPI package `agentledger-runtime`，CLI `agentledger` |
-| Go | 在 Go module 内执行 `go get github.com/yaogdu/AgentLedger/go@v1.3.0` | 在 repo 内执行 `cd go && go run ./examples/quickstart` | `../../go/examples/README.md` | Go module `github.com/yaogdu/AgentLedger/go`，CLI package `.../go/cmd/agentledger-go` |
+| Go | 在 Go module 内执行 `go get github.com/yaogdu/AgentLedger/go@v1.3.1` | 在 repo 内执行 `cd go && go run ./examples/quickstart` | `../../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 @@ python -m agentledger doctor
 
 ```bash
 go mod init your-module-name  # 如果项目还没有 go.mod 才需要
-go get github.com/yaogdu/AgentLedger/go@v1.3.0
+go get github.com/yaogdu/AgentLedger/go@v1.3.1
 ```
 
 安装可选 CLI：
 
 ```bash
-go install github.com/yaogdu/AgentLedger/go/cmd/agentledger-go@v1.3.0
+go install github.com/yaogdu/AgentLedger/go/cmd/agentledger-go@v1.3.1
 agentledger-go --help
 ```
 
-注意：`go get` 必须在 Go module 里执行。`go install github.com/yaogdu/AgentLedger/go@v1.3.0` 是错误用法，因为该路径是 library，不是 `package main`。安装 CLI 要使用 `/cmd/agentledger-go`。
+注意：`go get` 必须在 Go module 里执行。`go install github.com/yaogdu/AgentLedger/go@v1.3.1` 是错误用法，因为该路径是 library，不是 `package main`。安装 CLI 要使用 `/cmd/agentledger-go`。
 
 ### TypeScript
 

{agentledger_runtime-1.3.0 → agentledger_runtime-1.3.2}/docs/zh/IMPLEMENTATION_STATUS.md

@@ -6,7 +6,7 @@
 
 ## 当前基线
 
-AgentLedger 1.3.0 是 stable runtime-core line，Python 是 reference implementation，Go/TypeScript/Rust 已通过共享 runtime-core parity gate 覆盖。1.3.0 保持 stable runtime-core contract，同时增加 language-neutral、read-only Inspector companion path，用于查看 evidence 和 runtime metadata。它适合：
+AgentLedger 1.3.x 是 stable runtime-core line，Python 是 reference implementation，Go/TypeScript/Rust 已通过共享 runtime-core parity gate 覆盖。1.3 line 保持 stable runtime-core contract，同时增加 language-neutral、read-only Inspector companion path，用于查看 evidence 和 runtime metadata。它适合：
 
 - 本地使用
 - runtime 设计评审
@@ -15,7 +15,7 @@ AgentLedger 1.3.0 是 stable runtime-core line，Python 是 reference implementa
 - reliability semantics 验证
 - 在明确 adapter 边界下做 production pilot 准备
 
-版本范围说明：1.3.0 增加 Inspector，定位是只读 evidence/runtime metadata consumer。它可以读取导出的 evidence bundle，也可以用只读凭证连接 SQLite/Postgres/MySQL AgentLedger metadata，并导出静态 HTML debug report。MySQL 仍是 1.2.2 的 storage adapter boundary，Langfuse 仍是 1.2.3 的 observability adapter boundary；真实服务生产级声明仍需要外部验证。
+版本范围说明：1.3.0 增加 Inspector，定位是只读 evidence/runtime metadata consumer。它可以读取导出的 evidence bundle，也可以用只读凭证连接 SQLite/Postgres/MySQL AgentLedger metadata，并导出静态 HTML debug report。1.3.2 增加 Inspector JSON/HTML 输出的可配置脱敏。MySQL 仍是 1.2.2 的 storage adapter boundary，Langfuse 仍是 1.2.3 的 observability adapter boundary；真实服务生产级声明仍需要外部验证。
 
 runtime-core contract 已稳定。optional production adapter、外部基础设施加固和完整 eval 系统都不属于 stable core 边界；非 Python runtime-core baseline 由共享 parity gate 验证。
 
@@ -58,7 +58,7 @@ runtime-core contract 已稳定。optional production adapter、外部基础设
 | Adapter contract | framework adapter base、LangGraph facade、MCP tool/context mapping、dependency-free method facades、第一方 adapter package boundaries |
 | Sandbox boundary | fail-closed `none`、local executor、router、external executor contract、Docker/bubblewrap command path、Kubernetes dry-run/gated path |
 | Observability | trace JSONL export、dependency-free OTLP JSON export、optional OTLP/JSON collector POST、evidence-linked audit record |
-| Inspector | `agentledger.inspector.v1` read model、`agentledger inspector run/evidence`、静态 HTML report、evidence-bundle input、read-only SQLite input、通过已有 adapter boundary 的 Postgres/MySQL read path、optional `agentledger-inspector` companion package |
+| Inspector | `agentledger.inspector.v1` read model、`agentledger inspector run/evidence`、静态 HTML report、evidence-bundle input、read-only SQLite input、通过已有 adapter boundary 的 Postgres/MySQL read path、可配置 redaction policy、optional `agentledger-inspector` companion package |
 | Reliability checks | failure injection suite、failure attribution report、conformance runner、runtime-boundary lint, scheduler facade, adversarial review, evidence regression、JSON rule-pack extension |
 | Media/stream contracts | `MediaArtifact`、`MediaMetadata`、`ArtifactLineage`、`StreamChunkRef`、`EventStreamCheckpoint`、AgentContext helpers、tool schema conventions、evidence/replay validation |
 | 开源发布骨架 | CI workflow、changelog、security policy、versioning policy、release checklist、contributor checks、中英文文档入口、SVG 架构图、adapter certification checklist、adapter packaging docs/checks |