PyPI - agentledger-runtime - Versions diffs - 1.3.2__tar.gz → 1.5.0__tar.gz - Mend

agentledger-runtime 1.3.2tar.gz → 1.5.0tar.gz

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

Files changed (402) hide show

{agentledger_runtime-1.3.2 → agentledger_runtime-1.5.0}/.github/workflows/ci.yml RENAMED Viewed

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

{agentledger_runtime-1.3.2 → agentledger_runtime-1.5.0}/CHANGELOG.md RENAMED Viewed

@@ -6,7 +6,115 @@ This project follows semantic versioning for the stable runtime-core contract. O
 ## Unreleased
-No unreleased changes yet.
+## 1.5.0 - 2026-07-08
+### Added
+- Added a dependency-free OpenAI Agents SDK-style approval/replay example that records model evidence, proposed tool calls, approval state, Tool Ledger history, and replay-safe resume behavior without requiring external framework installs.
+- Added a dependency-free Temporal bridge retry-safety example that shows workflow/activity ownership boundaries, retry correlation, archived tool-proposal reuse, and single-write side-effect behavior after an activity crash.
+- Added framework-native smoke coverage and CI checks for the new OpenAI Agents SDK-style and Temporal bridge adoption paths.
+- Added a dependency-free runtime benchmark suite with a semantic coverage matrix for all required runtime checks.
+- Added benchmark documentation and release checklist gates for recording local timing, evidence/debug artifact generation, failure injection, adapter contract dry-runs, and cross-language conformance command baselines.
+### Clarified
+- This is a four-language 1.5.0 runtime-core release train. Python, Go, TypeScript, and Rust keep the same portable runtime-core semantics introduced in the 1.4 line.
+- The new OpenAI Agents SDK-style and Temporal bridge assets are Python adoption examples and documentation entrypoints. They do not imply official upstream endorsement or new language-specific runtime-core requirements.
+## 1.4.2 - 2026-06-19
+### 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
+- Added the Runtime Model Evidence Boundary across Python, Go, TypeScript, and Rust runtime-core packages.
+- Added `agentledger.model.evidence.v1` for externally executed model-call evidence.
+- Added `model_call_requested`, `model_call_completed`, `model_call_failed`, and `tool_call_proposed` runtime events.
+- Added APIs to record archived model requests/responses, model failures, model-proposed tool calls, token usage, and USD cost evidence without making AgentLedger a model router.
+- Added `model_call_failed` to failure attribution, failure lifecycle, Inspector failure detection, adversarial review checks, and cross-language tests.
+### Clarified
+- AgentLedger records model evidence produced by user code, agent frameworks, provider SDKs, LiteLLM/new-api/one-api, or enterprise gateways.
+- AgentLedger does not own provider routing, retry, timeout, fallback, key management, provider SDK compatibility, or pricing catalogs in runtime-core.
+- This is a four-language runtime-core patch release. Inspector remains a language-neutral companion viewer distributed through Python/PyPI.
+## 1.4.0 - 2026-06-13
+### Added
+- Added the Agent Failure Lifecycle baseline across Python, Go, TypeScript, and Rust runtime-core packages.
+- Added `agentledger.failure.envelope.v1`, a normalized failure read model for terminal failures, recoverable retries, approval waits, blocked tools, and unknown side-effect states.
+- Added `agentledger.failure.lifecycle.v1`, `agentledger.failure.causal_graph.v1`, `agentledger.failure.replay_plan.v1`, `agentledger.failure.regression.v1`, `agentledger.failure.alerts.v1`, and `agentledger.failure.export.v1`.
+- Added failure lifecycle, causal graph, replay plan, local alert records, regression comparison, and external export mappings for OpenTelemetry, Langfuse, LangSmith, and Temporal-style consumers.
+- Added `agentledger failure export` and `agentledger failure regress` CLI commands.
+- Added Inspector panels for Failure Lifecycle, Failure Replay Plan, Failure Alerts, and Failure Causal Graph.
+### Tested
+- Added non-happy-path tests for missing event payloads, retry-scheduled steps, pending approvals, pending tool verification, blocked tools, terminal failure reports, Inspector HTML rendering, unsafe replay planning, local failure alerts, export mappings, and failure regression classification.
+- Added matching failure lifecycle assertions to Go, TypeScript, and Rust runtime-core tests.
+### Clarified
+- This is a runtime-core feature release, not an Inspector-only patch. Python, Go, TypeScript, and Rust share the 1.4.0 failure lifecycle contract.
+- Inspector remains a language-neutral read-only companion viewer distributed through Python/PyPI.
+- Failure export mappings are local JSON contracts. They do not send data to external SaaS systems or replace incident management, eval, or observability platforms.
+## 1.3.5 - 2026-06-07
+### Added
+- Added an Inspector chronological Event Stream view sorted by event timestamp, showing runtime run id, extracted agent run id, step id, event type, summary, and links back to detailed timeline records.
+- Added `agentledger inspector runs` and the `agentledger.inspector.runs.v1` read model for a read-only run index over SQLite/Postgres/MySQL runtime metadata.
+### Fixed
+- Improved packaged Inspector/static HTML layout so large JSON/details payloads and long ids do not expand tables or break the page width.
+- Reworked detailed Inspector, evidence, and time-travel tables so JSON opens in a full-width row below the record instead of a narrow right-side column.
+- Reworked the Inspector run-index HTML from a wide multi-column table into a compact paginated run list with status, timestamps, counters, Inspector links, and folded JSON details.
+### Clarified
+- This is an Inspector companion patch release. Inspector is language-neutral, but the current packaged implementation is distributed through the Python/PyPI CLI. The release does not change the stable runtime-core contract or require Go, TypeScript, or Rust runtime-core package changes.
+## 1.3.4
+### Fixed
+- Corrected the `agentledger-inspector` package module `__version__` so it matches published package metadata.
+- Added a release metadata regression check so the runtime package, Inspector companion package, and optional Inspector extra stay aligned in future patch releases.
+### Clarified
+- This is an Inspector/package metadata patch release. It does not change the stable runtime-core contract or require Go, TypeScript, or Rust runtime-core changes.
+## 1.3.3
+### Added
+- Added stable Inspector read-model anchors and related links for timeline events, steps, Tool Ledger rows, approval requests, policy decisions, and artifacts.
+- Added static HTML report navigation and internal cross-links so local reports can jump between events, tools, approvals, and artifacts without running a server.
+### 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.
 ## 1.3.2
@@ -267,3 +375,7 @@ No unreleased changes yet.
 - 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-1.3.2 → agentledger_runtime-1.5.0}/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-1.3.2 → agentledger_runtime-1.5.0}/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-1.3.2 → agentledger_runtime-1.5.0}/PKG-INFO RENAMED Viewed

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agentledger-runtime
-Version: 1.3.2
+Version: 1.5.0
 Summary: Runtime reliability layer for Agent Harness stacks
 Project-URL: Homepage, https://github.com/yaogdu/AgentLedger
 Project-URL: Repository, https://github.com/yaogdu/AgentLedger
@@ -21,33 +21,33 @@ Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.11
 Provides-Extra: all
-Requires-Dist: agentledger-inspector<2,>=1.3.2; 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'
-Requires-Dist: agentledger-mysql<2,>=1.3; extra == 'all'
-Requires-Dist: agentledger-otel<2,>=1.3; extra == 'all'
-Requires-Dist: agentledger-postgres<2,>=1.3; extra == 'all'
-Requires-Dist: agentledger-s3<2,>=1.3; extra == 'all'
-Requires-Dist: agentledger-sandbox-docker<2,>=1.3; extra == 'all'
+Requires-Dist: agentledger-inspector<2,>=1.5.0; extra == 'all'
+Requires-Dist: agentledger-langfuse<2,>=1.5; extra == 'all'
+Requires-Dist: agentledger-langgraph<2,>=1.5; extra == 'all'
+Requires-Dist: agentledger-mcp<2,>=1.5; extra == 'all'
+Requires-Dist: agentledger-mysql<2,>=1.5; extra == 'all'
+Requires-Dist: agentledger-otel<2,>=1.5; extra == 'all'
+Requires-Dist: agentledger-postgres<2,>=1.5; extra == 'all'
+Requires-Dist: agentledger-s3<2,>=1.5; extra == 'all'
+Requires-Dist: agentledger-sandbox-docker<2,>=1.5; extra == 'all'
 Provides-Extra: docker
-Requires-Dist: agentledger-sandbox-docker<2,>=1.3; extra == 'docker'
+Requires-Dist: agentledger-sandbox-docker<2,>=1.5; extra == 'docker'
 Provides-Extra: inspector
-Requires-Dist: agentledger-inspector<2,>=1.3.2; extra == 'inspector'
+Requires-Dist: agentledger-inspector<2,>=1.5.0; extra == 'inspector'
 Provides-Extra: langfuse
-Requires-Dist: agentledger-langfuse<2,>=1.3; extra == 'langfuse'
+Requires-Dist: agentledger-langfuse<2,>=1.5; extra == 'langfuse'
 Provides-Extra: langgraph
-Requires-Dist: agentledger-langgraph<2,>=1.3; extra == 'langgraph'
+Requires-Dist: agentledger-langgraph<2,>=1.5; extra == 'langgraph'
 Provides-Extra: mcp
-Requires-Dist: agentledger-mcp<2,>=1.3; extra == 'mcp'
+Requires-Dist: agentledger-mcp<2,>=1.5; extra == 'mcp'
 Provides-Extra: mysql
-Requires-Dist: agentledger-mysql<2,>=1.3; extra == 'mysql'
+Requires-Dist: agentledger-mysql<2,>=1.5; extra == 'mysql'
 Provides-Extra: otel
-Requires-Dist: agentledger-otel<2,>=1.3; extra == 'otel'
+Requires-Dist: agentledger-otel<2,>=1.5; extra == 'otel'
 Provides-Extra: postgres
-Requires-Dist: agentledger-postgres<2,>=1.3; extra == 'postgres'
+Requires-Dist: agentledger-postgres<2,>=1.5; extra == 'postgres'
 Provides-Extra: s3
-Requires-Dist: agentledger-s3<2,>=1.3; extra == 's3'
+Requires-Dist: agentledger-s3<2,>=1.5; extra == 's3'
 Description-Content-Type: text/markdown
 # AgentLedger
@@ -55,7 +55,7 @@ Description-Content-Type: text/markdown
 [English](README.md) | [中文](README.zh-CN.md)
 ![Python 3.11+](https://img.shields.io/badge/Python-3.11%2B-3776AB?logo=python&logoColor=white)
-![Version 1.3.x stable](https://img.shields.io/badge/Version-1.3.x--stable-111827)
+![Version 1.5.x stable](https://img.shields.io/badge/Version-1.5.x--stable-111827)
 ![License Apache-2.0](https://img.shields.io/badge/License-Apache--2.0-0f766e)
 ![Runtime Durable](https://img.shields.io/badge/Runtime-durable%20execution-1f6feb)
 ![Storage SQLite/Postgres/MySQL](https://img.shields.io/badge/Storage-SQLite%20%7C%20Postgres%20%7C%20MySQL-b45309)
@@ -64,11 +64,11 @@ Description-Content-Type: text/markdown
 Your agent called a tool. Did it happen? Can you retry safely? Can you prove it later?
-AgentLedger `1.3.x` is a runtime reliability layer for Agent Harness stacks. It does not try to teach agents how to reason or replace the surrounding harness ecosystem; it makes agent runs durable, auditable, replayable, policy-governed, and recoverable when workers crash, tools fail, or prompts change.
+AgentLedger `1.5.x` is a runtime reliability layer for Agent Harness stacks. It does not try to teach agents how to reason or replace the surrounding harness ecosystem; it makes agent runs durable, auditable, replayable, policy-governed, and recoverable when workers crash, tools fail, or prompts change.
 Most agent frameworks focus on planning, reasoning, and workflow logic. AgentLedger sits underneath or beside LangChain, LangGraph, CrewAI, AutoGen, OpenAI Agents SDK, LlamaIndex, Semantic Kernel, or custom agents to provide runtime guarantees around state, tools, evidence, replay, and recovery.
-In a full harness stack, systems such as LangGraph, Temporal, Langfuse, MCP, model routers, storage backends, and sandbox providers can each own the layer they are good at. AgentLedger owns the reliability substrate between them: durable execution, tool/model governance, evidence, replay, policy/sandbox boundaries, cost/failure attribution, and adapter contracts.
+In a full harness stack, systems such as LangGraph, Temporal, Langfuse, MCP, model gateways, storage backends, and sandbox providers can each own the layer they are good at. AgentLedger owns the reliability substrate between them: durable execution, tool/model governance, evidence, replay, policy/sandbox boundaries, cost/failure attribution, and adapter contracts.
 Python remains the reference implementation, and Go, TypeScript, and Rust now have native runtime-core baselines aligned to the same language-neutral runtime contract. Provider-specific drivers and framework-native adapters intentionally vary by ecosystem. See `docs/LANGUAGE_IMPLEMENTATION_COMPARISON.md` for the exact four-language comparison and adapter boundary.
@@ -76,11 +76,14 @@ 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) |
 | Find runnable examples | [examples/README.md](examples/README.md), [go/examples/README.md](go/examples/README.md), [typescript/examples/README.md](typescript/examples/README.md), [rust/examples/README.md](rust/examples/README.md) |
 | Query runtime tables | [docs/QUERY_EXAMPLES.md](docs/QUERY_EXAMPLES.md) |
 | Inspect a run visually | [docs/INSPECTOR.md](docs/INSPECTOR.md) |
+| Run benchmark and coverage gates | [docs/BENCHMARKS.md](docs/BENCHMARKS.md) |
 | Understand Harness stack composition | [docs/HARNESS_STACK.md](docs/HARNESS_STACK.md) |
 | Understand open-source impact | [docs/OPEN_SOURCE_IMPACT.md](docs/OPEN_SOURCE_IMPACT.md) |
 | Understand maintainer responsibilities | [docs/MAINTAINER_NOTES.md](docs/MAINTAINER_NOTES.md) |
@@ -90,6 +93,14 @@ Python remains the reference implementation, and Go, TypeScript, and Rust now ha
 | Use Go correctly | [go/README.md](go/README.md#install) |
 | Read the full documentation map | [docs/README.md](docs/README.md) |
+## Inspector Preview
+Inspector exports self-contained, read-only HTML for local or internal debugging. It can show a run index before opening a single run, then drill into chronological events, Tool Ledger rows, approvals, artifacts, and full-width JSON details.
+![AgentLedger Inspector run index](docs/assets/inspector/runs-index.png)
+![AgentLedger Inspector single run](docs/assets/inspector/single-run-timeline.png)
 ## At a glance
 | Question | Answer |
@@ -100,6 +111,12 @@ Python remains the reference implementation, and Go, TypeScript, and Rust now ha
 | What is not in core? | Planning engines, full eval systems, RAG/vector memory, trace stores, application administration backends, and sandbox infrastructure providers. |
 | How should other languages work? | This repo is contract-first. Python is the reference runtime; Go, Node/TypeScript, and Rust now have native runtime baselines under `go/`, `typescript/`, and `rust/`. Runtime-ready requires `contracts/agentledger.runtime.v1.json`, the shared semantic manifest `contracts/conformance/runtime_semantics.v1.json`, shared conformance fixtures, and per-language conformance commands. |
+## When to use it
+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 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
 AgentLedger keeps the runtime thin but hard to replace: core only owns guarantees that cannot be reliably enforced outside the runtime boundary. Everything else should integrate through adapters, contracts, conformance tests, and examples.
@@ -145,7 +162,7 @@ For concrete stack patterns, from a minimal local harness to a Temporal + LangGr
 | Durable orchestration | Temporal, Ray, Kubernetes workers | provide agent-specific leases, fencing, checkpoints, cancellation, cost/failure attribution, and replay semantics inside the worker step |
 | Observability / eval UI | Langfuse, LangSmith, OpenTelemetry, custom dashboards | export structured runtime events, evidence bundles, trace/cost/failure data, and correlation IDs |
 | Tool and context protocols | MCP, internal tool servers, provider SDK tools | enforce schema, permissions, approval, sandbox, idempotency, and audit before side effects happen |
-| Model providers / routers | OpenAI, Anthropic, Gemini, Bedrock, Ollama, LiteLLM, enterprise gateways | provide the runtime model-call contract, archived responses, budget/fallback/replay semantics, and optional provider adapters |
+| Model providers / gateways | OpenAI, Anthropic, Gemini, Bedrock, Ollama, LiteLLM/new-api/one-api, enterprise gateways | execute or route model calls externally while AgentLedger records model evidence, archived responses, proposed tool calls, cost/failure attribution, and replay semantics |
 | Storage / artifacts | SQLite, Postgres, MySQL, S3/MinIO, internal stores | keep runtime metadata, state versions, migrations, blob refs, and evidence refs durable and conformance-tested |
 The intended production shape is therefore not `AgentLedger instead of LangGraph/Temporal/Langfuse`. It is `AgentLedger with LangGraph/Temporal/Langfuse` where AgentLedger governs the model/tool/state boundary that those systems otherwise cannot enforce by themselves.
@@ -177,6 +194,7 @@ 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` |
@@ -239,6 +257,7 @@ Temporal + LangGraph + AgentLedger is a valid production stack: Temporal runs th
 - Contributing guide: [CONTRIBUTING.md](CONTRIBUTING.md)
 - Community conduct: [CODE_OF_CONDUCT.md](CODE_OF_CONDUCT.md)
 - Release gates: [docs/RELEASE_CHECKLIST.md](docs/RELEASE_CHECKLIST.md)
+- Benchmark gates: [docs/BENCHMARKS.md](docs/BENCHMARKS.md)
 - Compatibility policy: [docs/VERSIONING.md](docs/VERSIONING.md)
 ## Quick start
@@ -333,7 +352,7 @@ AgentLedger is also not a new LLM SDK, not a workflow engine, not a general obse
 ## Current maturity
-AgentLedger 1.3.x is a stable runtime-core line with Python as the reference implementation and Go, TypeScript, and Rust covered by shared runtime-core parity gates. The current Python/Inspector patch is 1.3.2; 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.
+AgentLedger 1.5.x is a stable runtime-core line with Python as the reference implementation and Go, TypeScript, and Rust covered by shared runtime-core parity gates. The four language runtimes share the same runtime-core failure semantics 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 1.5.0 across Python, Go, TypeScript, and Rust; Inspector remains a language-neutral companion viewer distributed through Python/PyPI. It is suitable for local use, framework adapter integration, reliability semantics validation, and production pilot preparation with explicit adapter boundaries.
 The runtime-core contract is stable; optional production adapters and external infrastructure hardening remain separately tracked. See [docs/MATURITY_MODEL.md](docs/MATURITY_MODEL.md), [docs/IMPLEMENTATION_STATUS.md](docs/IMPLEMENTATION_STATUS.md), and [docs/ROADMAP.md](docs/ROADMAP.md).
@@ -388,3 +407,7 @@ 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-1.3.2 → agentledger_runtime-1.5.0}/README.md RENAMED Viewed

@@ -3,7 +3,7 @@
 [English](README.md) | [中文](README.zh-CN.md)
 ![Python 3.11+](https://img.shields.io/badge/Python-3.11%2B-3776AB?logo=python&logoColor=white)
-![Version 1.3.x stable](https://img.shields.io/badge/Version-1.3.x--stable-111827)
+![Version 1.5.x stable](https://img.shields.io/badge/Version-1.5.x--stable-111827)
 ![License Apache-2.0](https://img.shields.io/badge/License-Apache--2.0-0f766e)
 ![Runtime Durable](https://img.shields.io/badge/Runtime-durable%20execution-1f6feb)
 ![Storage SQLite/Postgres/MySQL](https://img.shields.io/badge/Storage-SQLite%20%7C%20Postgres%20%7C%20MySQL-b45309)
@@ -12,11 +12,11 @@
 Your agent called a tool. Did it happen? Can you retry safely? Can you prove it later?
-AgentLedger `1.3.x` is a runtime reliability layer for Agent Harness stacks. It does not try to teach agents how to reason or replace the surrounding harness ecosystem; it makes agent runs durable, auditable, replayable, policy-governed, and recoverable when workers crash, tools fail, or prompts change.
+AgentLedger `1.5.x` is a runtime reliability layer for Agent Harness stacks. It does not try to teach agents how to reason or replace the surrounding harness ecosystem; it makes agent runs durable, auditable, replayable, policy-governed, and recoverable when workers crash, tools fail, or prompts change.
 Most agent frameworks focus on planning, reasoning, and workflow logic. AgentLedger sits underneath or beside LangChain, LangGraph, CrewAI, AutoGen, OpenAI Agents SDK, LlamaIndex, Semantic Kernel, or custom agents to provide runtime guarantees around state, tools, evidence, replay, and recovery.
-In a full harness stack, systems such as LangGraph, Temporal, Langfuse, MCP, model routers, storage backends, and sandbox providers can each own the layer they are good at. AgentLedger owns the reliability substrate between them: durable execution, tool/model governance, evidence, replay, policy/sandbox boundaries, cost/failure attribution, and adapter contracts.
+In a full harness stack, systems such as LangGraph, Temporal, Langfuse, MCP, model gateways, storage backends, and sandbox providers can each own the layer they are good at. AgentLedger owns the reliability substrate between them: durable execution, tool/model governance, evidence, replay, policy/sandbox boundaries, cost/failure attribution, and adapter contracts.
 Python remains the reference implementation, and Go, TypeScript, and Rust now have native runtime-core baselines aligned to the same language-neutral runtime contract. Provider-specific drivers and framework-native adapters intentionally vary by ecosystem. See `docs/LANGUAGE_IMPLEMENTATION_COMPARISON.md` for the exact four-language comparison and adapter boundary.
@@ -24,11 +24,14 @@ 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) |
 | Find runnable examples | [examples/README.md](examples/README.md), [go/examples/README.md](go/examples/README.md), [typescript/examples/README.md](typescript/examples/README.md), [rust/examples/README.md](rust/examples/README.md) |
 | Query runtime tables | [docs/QUERY_EXAMPLES.md](docs/QUERY_EXAMPLES.md) |
 | Inspect a run visually | [docs/INSPECTOR.md](docs/INSPECTOR.md) |
+| Run benchmark and coverage gates | [docs/BENCHMARKS.md](docs/BENCHMARKS.md) |
 | Understand Harness stack composition | [docs/HARNESS_STACK.md](docs/HARNESS_STACK.md) |
 | Understand open-source impact | [docs/OPEN_SOURCE_IMPACT.md](docs/OPEN_SOURCE_IMPACT.md) |
 | Understand maintainer responsibilities | [docs/MAINTAINER_NOTES.md](docs/MAINTAINER_NOTES.md) |
@@ -38,6 +41,14 @@ Python remains the reference implementation, and Go, TypeScript, and Rust now ha
 | Use Go correctly | [go/README.md](go/README.md#install) |
 | Read the full documentation map | [docs/README.md](docs/README.md) |
+## Inspector Preview
+Inspector exports self-contained, read-only HTML for local or internal debugging. It can show a run index before opening a single run, then drill into chronological events, Tool Ledger rows, approvals, artifacts, and full-width JSON details.
+![AgentLedger Inspector run index](docs/assets/inspector/runs-index.png)
+![AgentLedger Inspector single run](docs/assets/inspector/single-run-timeline.png)
 ## At a glance
 | Question | Answer |
@@ -48,6 +59,12 @@ Python remains the reference implementation, and Go, TypeScript, and Rust now ha
 | What is not in core? | Planning engines, full eval systems, RAG/vector memory, trace stores, application administration backends, and sandbox infrastructure providers. |
 | How should other languages work? | This repo is contract-first. Python is the reference runtime; Go, Node/TypeScript, and Rust now have native runtime baselines under `go/`, `typescript/`, and `rust/`. Runtime-ready requires `contracts/agentledger.runtime.v1.json`, the shared semantic manifest `contracts/conformance/runtime_semantics.v1.json`, shared conformance fixtures, and per-language conformance commands. |
+## When to use it
+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 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
 AgentLedger keeps the runtime thin but hard to replace: core only owns guarantees that cannot be reliably enforced outside the runtime boundary. Everything else should integrate through adapters, contracts, conformance tests, and examples.
@@ -93,7 +110,7 @@ For concrete stack patterns, from a minimal local harness to a Temporal + LangGr
 | Durable orchestration | Temporal, Ray, Kubernetes workers | provide agent-specific leases, fencing, checkpoints, cancellation, cost/failure attribution, and replay semantics inside the worker step |
 | Observability / eval UI | Langfuse, LangSmith, OpenTelemetry, custom dashboards | export structured runtime events, evidence bundles, trace/cost/failure data, and correlation IDs |
 | Tool and context protocols | MCP, internal tool servers, provider SDK tools | enforce schema, permissions, approval, sandbox, idempotency, and audit before side effects happen |
-| Model providers / routers | OpenAI, Anthropic, Gemini, Bedrock, Ollama, LiteLLM, enterprise gateways | provide the runtime model-call contract, archived responses, budget/fallback/replay semantics, and optional provider adapters |
+| Model providers / gateways | OpenAI, Anthropic, Gemini, Bedrock, Ollama, LiteLLM/new-api/one-api, enterprise gateways | execute or route model calls externally while AgentLedger records model evidence, archived responses, proposed tool calls, cost/failure attribution, and replay semantics |
 | Storage / artifacts | SQLite, Postgres, MySQL, S3/MinIO, internal stores | keep runtime metadata, state versions, migrations, blob refs, and evidence refs durable and conformance-tested |
 The intended production shape is therefore not `AgentLedger instead of LangGraph/Temporal/Langfuse`. It is `AgentLedger with LangGraph/Temporal/Langfuse` where AgentLedger governs the model/tool/state boundary that those systems otherwise cannot enforce by themselves.
@@ -125,6 +142,7 @@ 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` |
@@ -187,6 +205,7 @@ Temporal + LangGraph + AgentLedger is a valid production stack: Temporal runs th
 - Contributing guide: [CONTRIBUTING.md](CONTRIBUTING.md)
 - Community conduct: [CODE_OF_CONDUCT.md](CODE_OF_CONDUCT.md)
 - Release gates: [docs/RELEASE_CHECKLIST.md](docs/RELEASE_CHECKLIST.md)
+- Benchmark gates: [docs/BENCHMARKS.md](docs/BENCHMARKS.md)
 - Compatibility policy: [docs/VERSIONING.md](docs/VERSIONING.md)
 ## Quick start
@@ -281,7 +300,7 @@ AgentLedger is also not a new LLM SDK, not a workflow engine, not a general obse
 ## Current maturity
-AgentLedger 1.3.x is a stable runtime-core line with Python as the reference implementation and Go, TypeScript, and Rust covered by shared runtime-core parity gates. The current Python/Inspector patch is 1.3.2; 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.
+AgentLedger 1.5.x is a stable runtime-core line with Python as the reference implementation and Go, TypeScript, and Rust covered by shared runtime-core parity gates. The four language runtimes share the same runtime-core failure semantics 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 1.5.0 across Python, Go, TypeScript, and Rust; Inspector remains a language-neutral companion viewer distributed through Python/PyPI. It is suitable for local use, framework adapter integration, reliability semantics validation, and production pilot preparation with explicit adapter boundaries.
 The runtime-core contract is stable; optional production adapters and external infrastructure hardening remain separately tracked. See [docs/MATURITY_MODEL.md](docs/MATURITY_MODEL.md), [docs/IMPLEMENTATION_STATUS.md](docs/IMPLEMENTATION_STATUS.md), and [docs/ROADMAP.md](docs/ROADMAP.md).
@@ -336,3 +355,7 @@ 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-1.3.2 → agentledger_runtime-1.5.0}/README.zh-CN.md RENAMED Viewed

@@ -3,7 +3,7 @@
 [English](README.md) | [中文](README.zh-CN.md)
 ![Python 3.11+](https://img.shields.io/badge/Python-3.11%2B-3776AB?logo=python&logoColor=white)
-![Version 1.3.x stable](https://img.shields.io/badge/Version-1.3.x--stable-111827)
+![Version 1.5.x stable](https://img.shields.io/badge/Version-1.5.x--stable-111827)
 ![License Apache-2.0](https://img.shields.io/badge/License-Apache--2.0-0f766e)
 ![Runtime Durable](https://img.shields.io/badge/Runtime-durable%20execution-1f6feb)
 ![Storage SQLite/Postgres/MySQL](https://img.shields.io/badge/Storage-SQLite%20%7C%20Postgres%20%7C%20MySQL-b45309)
@@ -12,11 +12,11 @@
 你的 Agent 调用了一个工具。它真的执行了吗？可以安全重试吗？之后能证明发生过什么吗？
-AgentLedger `1.3.x` 是面向 Agent Harness stack 的 runtime reliability layer。它不负责让 Agent 更会“思考”，也不替代完整 Harness 生态；它负责让 Agent run 在 worker 崩溃、工具失败、prompt 变更和长任务恢复时，仍然具备持久化、可审计、可重放、可治理和可恢复能力。
+AgentLedger `1.5.x` 是面向 Agent Harness stack 的 runtime reliability layer。它不负责让 Agent 更会“思考”，也不替代完整 Harness 生态；它负责让 Agent run 在 worker 崩溃、工具失败、prompt 变更和长任务恢复时，仍然具备持久化、可审计、可重放、可治理和可恢复能力。
 大多数 Agent 框架关注 planning、reasoning 和 workflow logic。AgentLedger 放在 LangChain、LangGraph、CrewAI、AutoGen、OpenAI Agents SDK、LlamaIndex、Semantic Kernel 或自定义 Agent 的下方或旁边，提供 state、tool、evidence、replay、recovery 相关的 runtime guarantees。
-在完整 Harness stack 里，LangGraph、Temporal、Langfuse、MCP、model router、storage backend、sandbox provider 等系统可以各自负责擅长的层。AgentLedger 负责它们之间的 reliability substrate：durable execution、tool/model governance、evidence、replay、policy/sandbox boundary、cost/failure attribution 和 adapter contracts。
+在完整 Harness stack 里，LangGraph、Temporal、Langfuse、MCP、model gateway、storage backend、sandbox provider 等系统可以各自负责擅长的层。AgentLedger 负责它们之间的 reliability substrate：durable execution、tool/model governance、evidence、replay、policy/sandbox boundary、cost/failure attribution 和 adapter contracts。
 Python 仍然是 reference implementation；Go、TypeScript、Rust 已有 native runtime-core baseline，并对齐同一份 language-neutral runtime contract。provider-specific driver 和 framework-native adapter 会按各语言生态差异处理。四语言实现对比和 adapter 边界见 `docs/zh/LANGUAGE_IMPLEMENTATION_COMPARISON.md`。
@@ -24,11 +24,14 @@ 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) |
 | 找可运行示例 | [examples/README.md](examples/README.md)、[go/examples/README.md](go/examples/README.md)、[typescript/examples/README.md](typescript/examples/README.md)、[rust/examples/README.md](rust/examples/README.md) |
 | 查询 runtime 表 | [docs/zh/QUERY_EXAMPLES.md](docs/zh/QUERY_EXAMPLES.md) |
 | 可视化排查 run | [docs/zh/INSPECTOR.md](docs/zh/INSPECTOR.md) |
+| 运行 benchmark 和覆盖门禁 | [docs/zh/BENCHMARKS.md](docs/zh/BENCHMARKS.md) |
 | 理解 Harness stack 组合方式 | [docs/zh/HARNESS_STACK.md](docs/zh/HARNESS_STACK.md) |
 | 理解开源生态价值 | [docs/zh/OPEN_SOURCE_IMPACT.md](docs/zh/OPEN_SOURCE_IMPACT.md) |
 | 理解维护者职责 | [docs/zh/MAINTAINER_NOTES.md](docs/zh/MAINTAINER_NOTES.md) |
@@ -38,6 +41,13 @@ Python 仍然是 reference implementation；Go、TypeScript、Rust 已有 native
 | 正确使用 Go | [go/README.md](go/README.md#install) |
 | 查看完整文档地图 | [docs/zh/README.md](docs/zh/README.md) |
+## Inspector 预览
+Inspector 会导出自包含、只读的 HTML，适合本地或内网排查问题。它可以先展示 run index，再进入单个 run 查看按时间排序的事件、Tool Ledger、approval、artifact 和全宽 JSON 详情。
+![AgentLedger Inspector run index](docs/assets/inspector/runs-index.png)
+![AgentLedger Inspector single run](docs/assets/inspector/single-run-timeline.png)
 ## 快速判断
@@ -49,6 +59,12 @@ Python 仍然是 reference implementation；Go、TypeScript、Rust 已有 native
 | 哪些不属于 core？ | Planning engine、完整 eval 系统、RAG/vector memory、trace store、托管应用产品和托管 sandbox infrastructure。 |
 | 其它语言怎么做？ | 这个 repo 是 contract-first。Python 是 reference runtime；Go、Node/TypeScript、Rust 已在 `go/`、`typescript/`、`rust/` 下有 native runtime baseline。runtime-ready 必须对齐 `contracts/agentledger.runtime.v1.json` 和共享语义清单 `contracts/conformance/runtime_semantics.v1.json`，通过共享 conformance fixtures，并提供各语言 conformance command。 |
+## 什么时候该用
+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 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
 AgentLedger 的 runtime 要保持“薄但不可替代”：core 只内建那些不在 runtime boundary 内就无法可靠保证的能力。其它能力通过 adapter、contract、conformance test 和 example 接入成熟生态。
@@ -94,7 +110,7 @@ AgentLedger 本身不是完整 Agent Harness。它的设计目标是和 Harness
 | Durable orchestration | Temporal、Ray、Kubernetes workers | 在 worker step 内提供 agent-specific lease、fencing、checkpoint、cancellation、cost/failure attribution 和 replay semantics |
 | Observability / eval UI | Langfuse、LangSmith、OpenTelemetry、自定义 dashboard | 导出 structured runtime events、evidence bundle、trace/cost/failure data 和 correlation IDs |
 | Tool and context protocols | MCP、internal tool servers、provider SDK tools | 在副作用发生前强制执行 schema、permission、approval、sandbox、idempotency 和 audit |
-| Model providers / routers | OpenAI、Anthropic、Gemini、Bedrock、Ollama、LiteLLM、企业 gateway | 提供 runtime model-call contract、archived responses、budget/fallback/replay semantics 和 optional provider adapters |
+| Model providers / gateways | OpenAI、Anthropic、Gemini、Bedrock、Ollama、LiteLLM/new-api/one-api、企业 gateway | 在外部执行或路由 model call；AgentLedger 记录 model evidence、archived response、proposed tool call、cost/failure attribution 和 replay semantics |
 | Storage / artifacts | SQLite、Postgres、MySQL、S3/MinIO、内部存储 | 持久化 runtime metadata、state version、migration、blob ref 和 evidence ref，并通过 conformance 验证 |
 所以推荐的生产形态不是 `AgentLedger instead of LangGraph/Temporal/Langfuse`，而是 `AgentLedger with LangGraph/Temporal/Langfuse`：AgentLedger 负责治理这些系统自身难以强制保证的 model/tool/state boundary。
@@ -126,6 +142,7 @@ 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` |
@@ -188,6 +205,7 @@ Temporal + LangGraph + AgentLedger 是合理的生产组合：Temporal 跑外层
 - 贡献方式：[CONTRIBUTING.md](CONTRIBUTING.md)
 - 社区行为：[CODE_OF_CONDUCT.md](CODE_OF_CONDUCT.md)
 - 发布检查：[docs/zh/RELEASE_CHECKLIST.md](docs/zh/RELEASE_CHECKLIST.md)
+- Benchmark 门禁：[docs/zh/BENCHMARKS.md](docs/zh/BENCHMARKS.md)
 - 兼容策略：[docs/VERSIONING.md](docs/VERSIONING.md)
 ## 快速开始
@@ -282,7 +300,7 @@ AgentLedger 也不是新的 LLM SDK，不是 workflow engine，不是通用 obse
 ## 当前成熟度
-AgentLedger 1.3.x 是 stable runtime-core line，Python 是 reference implementation，Go、TypeScript、Rust 已由共享 runtime-core parity gate 覆盖。当前 Python/Inspector patch 是 1.3.2；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。
+AgentLedger 1.5.x 是 stable runtime-core line，Python 是 reference implementation，Go、TypeScript、Rust 已由共享 runtime-core parity gate 覆盖。四种语言 runtime 共享同一组 runtime-core failure semantics 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 1.5.0，并覆盖 Python、Go、TypeScript、Rust；Inspector 仍是 language-neutral companion viewer，通过 Python/PyPI 分发。适合本地使用、framework adapter integration、reliability semantics 验证，以及在明确 adapter 边界下做 production pilot 准备。
 runtime-core contract 已稳定；optional production adapter 和外部基础设施加固仍按独立阶段推进。详见 [docs/MATURITY_MODEL.md](docs/MATURITY_MODEL.md)、[docs/zh/IMPLEMENTATION_STATUS.md](docs/zh/IMPLEMENTATION_STATUS.md) 和 [docs/zh/ROADMAP.md](docs/zh/ROADMAP.md)。
@@ -337,3 +355,7 @@ cd ../rust && cargo run --quiet -- conformance
 ## License
 Apache-2.0. See [LICENSE](LICENSE)。
+---
+generated by codex cli

{agentledger_runtime-1.3.2 → agentledger_runtime-1.5.0}/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 1.3.2__tar.gz → 1.5.0__tar.gz

agentledger-runtime 1.3.2tar.gz → 1.5.0tar.gz