0.4.0

CHANGELOG.md

@@ -7,20 +7,29 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.4.0]
+
 ### Added
 
+- feat: add optional pi agent SDK support
 - Optional pi Agent SDK adapter for isolated LiteLLM runs, Docker execution, structured judging, cancellation, and turn limits.
 - Provider-specific runner option types with backwards-compatible Claude defaults.
 
 ### Changed
 
+- chore: upgrade @anthropic-ai/claude-agent-sdk to ^0.3.310 ([#31](https://github.com/MetaMask/agent-runner/pull/31))
 - Apply the `on-success` Docker cleanup policy uniformly: adapters keep the container unless the run completed with a successful result.
 - **Breaking for custom Claude-backed adapters:** the runner no longer injects `settingSources: []`. Add `defaultOptions: { settingSources: [] }` to custom adapters to preserve SDK-settings isolation. The built-in Claude adapter keeps this default.
 - Reject judge `queryOptions` for non-Claude adapters without `runStructured()` instead of forwarding provider-native options to the legacy Claude judge. Use a separate Claude runner for customized Claude judging.
 - Drop cumulative output from pi progress messages, coalesce adjacent queued updates for the same tool call, and omit heartbeats from judge transcripts.
 
 ### Fixed
 
+- chore: patch critical and high vulnerabilities and drop Node 20 ([#33](https://github.com/MetaMask/agent-runner/pull/33))
+- fix: propagate Langfuse trace names ([#32](https://github.com/MetaMask/agent-runner/pull/32))
+- fix: address pi adapter review findings
+- fix: make coverage deterministic and harden bridge message validation
+- fix: address PR #28 review findings
 - Scrub exact environment values of at least eight characters whose names match recognized sensitive fragments from pi messages and errors, Docker bridge execution errors, and judge inputs. Pi message telemetry receives scrubbed output; arbitrary names, short or encoded values, and task prompt telemetry are not covered by this heuristic.
 - Share sensitive-name fragments with key-based redaction, including wallet SRPs, mnemonics, and passphrases; preserve system error fields and aggregate causes when scrubbing.
 - Preserve explicitly mapped pi Docker working directories instead of replacing them with the container default.
@@ -78,7 +87,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - fix: cleanup unused publish docs ([#8](https://github.com/MetaMask/agent-runner/pull/8))
 
-[Unreleased]: https://github.com/MetaMask/agent-runner/compare/v0.3.1...HEAD
+[Unreleased]: https://github.com/MetaMask/agent-runner/compare/v0.4.0...HEAD
+[0.4.0]: https://github.com/MetaMask/agent-runner/compare/v0.3.1...v0.4.0
 [0.3.1]: https://github.com/MetaMask/agent-runner/compare/v0.3.0...v0.3.1
 [0.3.0]: https://github.com/MetaMask/agent-runner/compare/v0.2.0...v0.3.0
 [0.2.0]: https://github.com/MetaMask/agent-runner/compare/v0.1.0...v0.2.0

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@metamask/agent-runner",
-  "version": "0.3.1",
+  "version": "0.4.0",
   "description": "Reusable Claude Agent SDK runner with Langfuse telemetry lifecycle support.",
   "homepage": "https://github.com/MetaMask/agent-runner#readme",
   "bugs": {