harness-typescript/v0.4.0
harness-typescript/v0.4.0 adds SageMakerDecisionModel, HumanInTheLoop auto mode, and server-side summary with Anthropic on-demand compaction.
The Deploy Log | Products | Free, no signup
6 versions of harness-typescript from Amazon Web Services in The Deploy Log. From to . On the median a new version every 6 days, publisher's dates only; the longest wait was 15 days. The newest is harness-typescript/v0.4.0. 4 versions in the last 30 days. Each links the publisher's own page.
| Version | Publisher's date | Days after the one before |
|---|---|---|
| harness-typescript/v0.4.0 | 8 | |
| v0.3.4 | 5 | |
| harness-typescript/v0.3.3 | 1 | |
| v0.3.2 | 15 | |
| harness-typescript/v0.3.0 | 6 | |
| harness-typescript/v0.2.0 |
harness-typescript/v0.4.0 adds SageMakerDecisionModel, HumanInTheLoop auto mode, and server-side summary with Anthropic on-demand compaction.
Release harness-typescript/v0.3.4 adds explicit cache points on GPT-5.6+ by default and lets ClassifierStrategy route with any DecisionModel.
Harness TypeScript v0.3.3 adds Bedrock maxTokens default, Model.model_info, and a summarizer fallback fix.
Adds structured output attempt limits, agent.cancel() stop, and graph, read, write, edit tools.
Released harness-typescript/v0.3.0 with Strands packaging for Claude, Codex, and Cursor, DecisionModel primitive, and MCP progress callbacks.
harness-typescript v0.2.0 adds a vended subagent tool and exposes a tool client accessor.
One line every time AI actually ships, around the clock, free on Threads and Bluesky. Every one is in The Deploy Log with its source.