@sleep2agi/agent-node 2.4.5 → 2.4.6-preview.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.
- package/README.md +4 -3
- package/dist/cli.js +31 -31
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# @sleep2agi/agent-node
|
|
2
2
|
|
|
3
|
-
Agent runtime for Agent Network. Connects to a CommHub server, registers under an alias, and processes incoming tasks with
|
|
3
|
+
Agent runtime for Agent Network. Connects to a CommHub server, registers under an alias, and processes incoming tasks with Claude, Codex, Grok Build, or compatible HTTP runtimes.
|
|
4
4
|
|
|
5
5
|
The supported entry point is the `anet` CLI from `@sleep2agi/agent-network`, which writes the right `config.json`, network token, and environment variables for you.
|
|
6
6
|
|
|
@@ -52,7 +52,7 @@ CLI flags:
|
|
|
52
52
|
| `claude-agent-sdk` | [@anthropic-ai/claude-agent-sdk](https://www.npmjs.com/package/@anthropic-ai/claude-agent-sdk) | verified | Anthropic-compatible API; works with MiniMax, DeepSeek, GLM, Kimi, Anthropic, OpenRouter, or custom endpoints |
|
|
53
53
|
| `codex-sdk` | [@openai/codex-sdk](https://www.npmjs.com/package/@openai/codex-sdk) | unverified end-to-end | unit tests pass, no full E2E with real codex auth |
|
|
54
54
|
| `claude-code-cli` | local `claude` CLI | unverified end-to-end | runs locally for Claude Pro subscribers (v0.8.2 fixed the session-resume default-loss bug; see [changelog](https://anet.sh/en/changelog)) |
|
|
55
|
-
| `grok-build-acp` | local `grok agent stdio` |
|
|
55
|
+
| `grok-build-acp` | local `grok agent stdio` | stable runtime, native MCP injection boundary remains preview | requires Grok Build CLI login; stable for receive/reply, session persistence, and explicit CommHub delegation handled by agent-node |
|
|
56
56
|
| `http-api` | OpenAI/Anthropic-compatible HTTP | experimental | reads `ANTHROPIC_*`, `OPENAI_*`, or `MINIMAX_CODING_API_KEY` environment variables |
|
|
57
57
|
|
|
58
58
|
Runtimes are loaded lazily — picking one doesn't pull the others' dependencies. `claude-code-cli` adds zero extra SDK weight.
|
|
@@ -70,7 +70,7 @@ anet node start grok-demo
|
|
|
70
70
|
|
|
71
71
|
The runtime starts `grok agent stdio`, authenticates with the cached Grok login, opens or loads a Grok session, sends the task prompt, collects streamed ACP notifications, and writes `grokSession` back to the node config.
|
|
72
72
|
|
|
73
|
-
|
|
73
|
+
Stable behavior:
|
|
74
74
|
|
|
75
75
|
- CommHub task delivery and replies are handled by `agent-node`, not by Grok itself.
|
|
76
76
|
- Plain text tasks should be answered directly by Grok.
|
|
@@ -82,6 +82,7 @@ Known boundary:
|
|
|
82
82
|
- Native Grok MCP tool injection is still experimental. Do not rely on Grok itself seeing `commhub_get_all_status` or `commhub_send_task`.
|
|
83
83
|
- Image attachments are currently text-only because the captured Grok ACP capability reports `promptCapabilities.image=false`.
|
|
84
84
|
- `grok ACP error -32603` is treated as retryable once with a fresh session; the runtime now logs JSON-RPC `error.data` when Grok provides it.
|
|
85
|
+
- Grok tool-state boilerplate such as "Do not attempt to use tools from these servers yet" is stripped from final CommHub replies so users see the actual task answer.
|
|
85
86
|
|
|
86
87
|
## Provider presets (claude-agent-sdk)
|
|
87
88
|
|