@zhixuan92/multi-model-agent-core 3.9.0 → 3.9.1

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 (2) hide show
  1. package/README.md +1 -1
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -104,7 +104,7 @@ As of 3.4.0 every task-execution event the worker emits to the verbose stderr st
104
104
 
105
105
  ## What's new
106
106
 
107
- Latest: **3.9.0** — watchdog hardening + per-stage idle telemetry. The three reviewer entry points (`runSpecReview` / `runQualityReview` / `runDiffReview`) now accept and thread `taskDeadlineMs` + `abortSignal` + `onProgress` through their internal `delegateWithEscalation` calls, closing the leak that let reviewer hangs run past the cap. Defaults bumped: `timeoutMs` 30 → 60 min, `stallTimeoutMs` 10 → 20 min, via named constants. `StageStats` gains `maxIdleMs`/`totalIdleMs`/`activityEvents` per stage; `RunResult` gains `taskMaxIdleMs`. Full history: [CHANGELOG](https://github.com/zhixuan312/multi-model-agent/blob/master/CHANGELOG.md).
107
+ Latest: **3.9.1** — no core runtime API changes; this patch release ships the server package's Codex native skill-install fix while keeping the 3.9.0 watchdog and per-stage idle telemetry behavior unchanged. Full history: [CHANGELOG](https://github.com/zhixuan312/multi-model-agent/blob/master/CHANGELOG.md).
108
108
 
109
109
  ## Full documentation
110
110
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@zhixuan92/multi-model-agent-core",
3
- "version": "3.9.0",
3
+ "version": "3.9.1",
4
4
  "type": "module",
5
5
  "license": "MIT",
6
6
  "description": "Core library for multi-model-agent: provider runners (Claude, Codex, OpenAI-compatible), routing logic, config schema, and tool/sandbox primitives.",