@zenera/neo 1.1.3 → 1.1.5

package/README.md

@@ -124,8 +124,9 @@ of surfacing three turns into a run as a confused model.
 
 ## What it gives you
 
-- **Agents** — an instruction, a model, tools, skills, plus handoffs and fork.
-  There is no hidden orchestration layer.
+- **Agents** — an instruction, a model, tools, skills, who it may hand the work
+  to, and how it splits into parallel branches. There is no hidden orchestration
+  layer.
 - **Models** — OpenAI, Anthropic, Google/Vertex and OpenRouter behind one
   interface, each through its own SDK, plus any OpenAI-compatible endpoint.
   Named providers and model aliases resolve from config or from the host.
@@ -135,9 +136,10 @@ of surfacing three turns into a run as a confused model.
   permanently occupying the prompt, optionally owning their own tools.
 - **Memory** — pluggable `MemoryStore`s, with scopes deciding what is private to
   an agent and what is shared.
-- **Trajectory** — an append-only log of everything that happened. Provider
-  messages are a projection of it, and compaction _covers_ nodes rather than
-  deleting them, so the audit trail survives context pressure.
+- **Trajectory** — an append-only log of everything that happened. What is sent
+  to a provider is derived from it, and compaction _covers_ nodes rather than
+  deleting them, so the full record survives even when older turns have to be
+  pushed out of the context window.
 - **Inspection** — `renderReportHtml` turns any run into one self-contained HTML
   file: the graph, every request, every token.
 

package/dist/project/config.js

@@ -212,7 +212,7 @@ const sandbox = z
     /**
      * Whether the model credentials reach the sandbox. On by default,
      * because the scaffolded image installs `zen` itself and an agent that
-     * cannot run `zen models` inside its own sandbox is a surprise.
+     * cannot run `zen check` inside its own sandbox is a surprise.
      *
      * Turning it off is the honest answer for a project whose agents write
      * code they then execute: the container runs whatever the model wrote,

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@zenera/neo",
-    "version": "1.1.3",
+    "version": "1.1.5",
     "description": "A multi-agent runtime for Node.js: agents, models, tools, skills, memory and an append-only trajectory.",
     "keywords": [
         "agents",