| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| README.md | 2026-04-05 | 1.2 kB | |
| v1.0.0 source code.tar.gz | 2026-04-05 | 172.2 kB | |
| v1.0.0 source code.zip | 2026-04-05 | 225.5 kB | |
| Totals: 3 Items | 398.8 kB | 3 | |
What's new since 0.2.0
Features
- Structured output — optional
outputSchema(Zod) on any agent, with auto-retry on validation failure (#36, [#38]) - Task retry with exponential backoff —
maxRetries,retryDelayMs,retryBackoffper task (#37) - Observability —
onTracecallback emits structured spans for LLM calls, tool calls, tasks, and agent runs (#40) - Lifecycle hooks —
beforeRun/afterRunon AgentConfig for prompt rewriting and result post-processing (#45) - Human-in-the-loop —
onApprovalcallback between task execution rounds to gate the next batch (#46) - Loop detection — detects stuck agents repeating the same tool calls or text, with configurable
warn/terminate/ custom handler (#49) - Grok (xAI) adapter — first-class support with dedicated GrokAdapter (#44)
- Fallback tool-call extraction — local models that emit tool calls as plain text are now handled automatically (#47)
Testing & quality
- 340 tests, 71% line coverage across
src/(#53) - Coverage badge added to README (#55)
Full changelog
https://github.com/JackChen-me/open-multi-agent/compare/v0.2.0...v1.0.0