@sleep2agi/agent-node 2.5.0-preview.3 → 2.5.0-preview.30

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 (3) hide show
  1. package/README.md +46 -157
  2. package/dist/cli.js +160 -85
  3. package/package.json +6 -4
package/README.md CHANGED
@@ -1,190 +1,79 @@
1
- # @sleep2agi/agent-node
1
+ # `@sleep2agi/agent-node`
2
2
 
3
3
  [![npm version](https://img.shields.io/npm/v/@sleep2agi/agent-node.svg)](https://www.npmjs.com/package/@sleep2agi/agent-node)
4
4
  [![npm downloads](https://img.shields.io/npm/dm/@sleep2agi/agent-node.svg)](https://www.npmjs.com/package/@sleep2agi/agent-node)
5
5
  [![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://github.com/sleep2agi/agent-network/blob/main/LICENSE)
6
6
  [![Docs](https://img.shields.io/badge/docs-anet.sh-009e7e.svg)](https://anet.sh)
7
7
 
8
- 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.
8
+ Agent Node is the worker process between CommHub and a model runtime. It receives tasks over SSE, invokes the configured runtime, returns results, and reports node status.
9
9
 
10
- 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.
10
+ Most users should manage it through the `anet` CLI. `anet node create` writes the network-bound identity and runtime configuration; `anet node start` launches the matching Agent Node.
11
11
 
12
- ## Install
13
-
14
- You usually don't install this package directly — `anet node create` and `anet node start` use it via `npx`. To pin it:
12
+ ## Install and run
15
13
 
16
14
  ```bash
17
- npm install -g @sleep2agi/agent-node
18
- ```
15
+ npm install -g bun @sleep2agi/agent-network @sleep2agi/agent-node
19
16
 
20
- ## Verified flow
21
-
22
- ```bash
23
- npm install -g @sleep2agi/agent-network
24
- anet hub start # local hub (terminal 1)
25
- anet hub dashboard # web UI (terminal 2)
26
- anet login --username admin --password anethub
27
- anet node create my-bot # two-step picker: runtime, then provider
28
- anet node start my-bot # → SSE connected
17
+ anet hub start
18
+ anet hub dashboard
19
+ anet login --hub http://127.0.0.1:9200 --username admin
20
+ anet node create my-bot
21
+ anet node start my-bot
29
22
  ```
30
23
 
31
- The picker writes `.anet/nodes/<name>/config.json`. `anet node start` reads it and runs this package under the hood.
24
+ The node is ready after `SSE connected` appears in its log.
32
25
 
33
- ## Direct invocation
34
-
35
- For scripts and CI:
26
+ For an existing profile, direct invocation is possible but normally unnecessary:
36
27
 
37
28
  ```bash
38
- npx @sleep2agi/agent-node --alias my-bot --hub http://127.0.0.1:9200 --tools all
29
+ npx @sleep2agi/agent-node \
30
+ --config .anet/nodes/<name>/config.json \
31
+ --alias <name>
39
32
  ```
40
33
 
41
- CLI flags:
42
-
43
- | Flag | Default | Notes |
44
- |---|---|---|
45
- | `--alias` | required | unique name in the hub |
46
- | `--hub` | `http://127.0.0.1:9200` | CommHub URL |
47
- | `--runtime` | `claude-agent-sdk` | `claude-agent-sdk` / `codex-sdk` / `claude-code-cli` / `grok-build-acp` / `http-api` |
48
- | `--model` | runtime default | passed through to the SDK |
49
- | `--tools` | (none) | `all` or comma-separated list |
50
- | `--max-turns` | `50` | upper bound per task |
51
- | `--session` | (none) | resume a prior session / thread |
34
+ The config must contain a valid node token, or authentication must resolve through the documented legacy fallback. Do not pass a user token as node identity.
52
35
 
53
36
  ## Runtimes
54
37
 
55
- | Runtime | Backend | Status | Notes |
56
- |---|---|---|---|
57
- | `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 |
58
- | `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 |
59
- | `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)) |
60
- | `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 |
61
- | `http-api` | OpenAI/Anthropic-compatible HTTP | experimental | reads `ANTHROPIC_*`, `OPENAI_*`, or `MINIMAX_CODING_API_KEY` environment variables |
62
-
63
- Runtimes are loaded lazily — picking one doesn't pull the others' dependencies. `claude-code-cli` adds zero extra SDK weight.
64
-
65
- ## Grok Build ACP
66
-
67
- `grok-build-acp` runs the local Grok Build CLI over Agent Client Protocol:
68
-
69
- ```bash
70
- curl -fsSL https://x.ai/cli/install.sh | bash
71
- grok
72
- anet node create grok-demo --runtime grok-build-acp
73
- anet node start grok-demo
74
- ```
75
-
76
- 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.
77
-
78
- Stable behavior:
79
-
80
- - CommHub task delivery and replies are handled by `agent-node`, not by Grok itself.
81
- - Plain text tasks should be answered directly by Grok.
82
- - Explicit delegation tasks are intercepted before Grok when they use a clear pattern such as `给 <alias> 发任务: <task>`.
83
- - Intercepted delegation calls CommHub directly, passes `parent_task_id`, polls `get_task`, and returns the child result.
38
+ Runtime availability follows the installed npm channel; do not infer it from a fixed version table in a README. Use the [runtime guide](https://anet.sh/guide/runtimes) as the current compatibility matrix.
84
39
 
85
- Known boundary:
86
-
87
- - Native Grok MCP tool injection is still experimental. Do not rely on Grok itself seeing `commhub_get_all_status` or `commhub_send_task`.
88
- - Image attachments are currently text-only because the captured Grok ACP capability reports `promptCapabilities.image=false`.
89
- - `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.
90
- - 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.
91
-
92
- ## Provider presets (claude-agent-sdk)
93
-
94
- `anet node create` step 2 picks one of these and writes `ANTHROPIC_BASE_URL` + a default model. All Anthropic-compatible HTTP API; `--model` is passed through verbatim.
95
-
96
- | Provider | Base URL | Default model | Status |
97
- |---|---|---|---|
98
- | Anthropic | `https://api.anthropic.com` | configured by `--model` | verified |
99
- | MiniMax (国际) | `https://api.minimax.io/anthropic` | `MiniMax-M2.7` | verified |
100
- | MiniMax (国内) | `https://api.minimaxi.com/anthropic` | `MiniMax-M2.7` | verified |
101
- | DeepSeek | `https://api.deepseek.com/anthropic` | `deepseek-chat` | verified |
102
- | GLM (智谱) | `https://open.bigmodel.cn/api/anthropic` | `glm-4-plus` | verified |
103
- | Kimi (Moonshot) | `https://api.moonshot.cn/anthropic` | `moonshot-v1-32k` | verified |
104
- | OpenRouter | `https://openrouter.ai/api/v1` | (user-chosen) | unverified end-to-end |
105
- | Custom | user-supplied | user-supplied | unverified end-to-end |
106
-
107
- ## Manual env-var examples
108
-
109
- ```bash
110
- # DeepSeek
111
- ANTHROPIC_BASE_URL=https://api.deepseek.com/anthropic \
112
- ANTHROPIC_AUTH_TOKEN=sk-... \
113
- npx @sleep2agi/agent-node --alias deep --hub http://127.0.0.1:9200 --tools all
114
-
115
- # MiniMax
116
- ANTHROPIC_BASE_URL=https://api.minimax.io/anthropic \
117
- ANTHROPIC_AUTH_TOKEN=your-key \
118
- npx @sleep2agi/agent-node --alias mini --model <minimax-model-id> --hub http://127.0.0.1:9200 --tools all
119
- ```
120
-
121
- ## Configuration file
122
-
123
- Typical output of `anet node create` at `.anet/nodes/<name>/config.json`:
124
-
125
- ```json
126
- {
127
- "node_id": "n_a1b2c3d4",
128
- "node_name": "my-bot",
129
- "hub": "http://127.0.0.1:9200",
130
- "token": "ntok_...",
131
- "runtime": "claude-agent-sdk",
132
- "model": "<minimax-model-id>",
133
- "channels": ["server:commhub"],
134
- "tools": ["Read", "Write", "Edit", "Bash", "Glob", "Grep"],
135
- "env": {
136
- "ANTHROPIC_BASE_URL": "https://api.minimax.io/anthropic",
137
- "ANTHROPIC_AUTH_TOKEN": "sk-..."
138
- },
139
- "flags": {
140
- "dangerouslySkipPermissions": true,
141
- "teammateMode": "in-process",
142
- "maxTurns": 50
143
- }
144
- }
145
- ```
146
-
147
- Per-node config wins over `~/.anet/config.json`; missing fields fall back to global, then defaults.
148
-
149
- ## Main loop
150
-
151
- Same shape across runtimes:
40
+ | Runtime | Purpose | Availability boundary |
41
+ |---|---|---|
42
+ | `claude-code-cli` | Reuse a local Claude Code login/session | Published task runtime |
43
+ | `claude-agent-sdk` | Call Anthropic-compatible APIs | Published task runtime |
44
+ | `codex-sdk` | Run Codex-backed tasks | Published task runtime |
45
+ | `grok-build-acp` | Run Grok Build through ACP | Published task runtime; no human attach |
46
+ | `codex-app-server` | Share a Codex thread with a human TUI | Preview-only; use `anet node start <name> --copresence` |
47
+ | `opencode-cli` | Run the vetted OpenCode ACP path | Preview-only |
152
48
 
153
- ```
154
- start
155
- → report_status: idle
156
- → SSE long-poll /events/:alias
157
- → on new_task: get_inbox → ack_inbox
158
- → report_status: working
159
- → run the LLM (with commhub MCP tools injected)
160
- → send_reply
161
- → report_status: idle
162
- ```
49
+ Neither npm `latest` nor `preview` includes a shared Grok TUI. Development branches may contain source-only experiments, but they are not an installable product path until published and listed in the [Grok TUI status page](https://anet.sh/guide/grok-copresence).
163
50
 
164
- ## Peer coordination (verified)
51
+ ## Configuration and security
165
52
 
166
- When the agent runs, the commhub MCP tools are auto-injected. The model can call:
53
+ Project-local profiles live under `.anet/nodes/<alias>/`. A profile includes the Hub URL, runtime, `node_id`, network-bound `ntok_`, model settings, and runtime flags. Treat it as a secret:
167
54
 
168
- - `commhub_get_all_status()` — see who else is online
169
- - `commhub_send_task(alias, task)` — dispatch a sub-task to a peer
170
- - `commhub_get_task(task_id)` — poll for the peer's reply
171
- - `commhub_send_message(alias, message)` — chat without a task lifecycle
172
- - `commhub_report_status(status, task)` — push status update
55
+ - Do not commit `.anet`, profile files, `.env`, or tokens.
56
+ - Do not copy one node profile to another machine or alias.
57
+ - Create a separate node identity on each machine.
58
+ - Start from the intended project directory; runtime file tools inherit that workspace.
59
+ - Runtime permission defaults differ. Read the CLI disclosure and [security guide](https://anet.sh/concepts/security) before allowing shell, file-write, or network access.
173
60
 
174
- This is what powers the multi-agent flow demonstrated in `anet hub dashboard` (e.g. ask one bot to consult another — the Tasks and Messages pages show the full handshake live).
61
+ Agent Node does not read environment variables literally named `TOOLS` or `SYSTEM_PROMPT`. Use `--tools` / config `tools` and `--prompt` / config `systemPrompt`.
175
62
 
176
- ## Isolation
63
+ ## Task behavior
177
64
 
178
- When the runtime is `claude-code-cli`, the spawned subprocess gets `settingSources: []` so it doesn't read the host's `~/.claude.json` and accidentally cross networks.
65
+ - `send_task` creates executable work and can invoke the target runtime.
66
+ - `send_reply` completes a task without invoking another model.
67
+ - `send_message` is ordinary chat and does not invoke another model.
179
68
 
180
- ## Companion packages
69
+ This distinction prevents reply loops. See the [task lifecycle](https://anet.sh/concepts/task-lifecycle) for state, retry, timeout, and parent-child semantics.
181
70
 
182
- | Package | Version |
183
- |---|---|
184
- | [@sleep2agi/agent-network](https://www.npmjs.com/package/@sleep2agi/agent-network) | 2.2.10 |
185
- | [@sleep2agi/commhub-server](https://www.npmjs.com/package/@sleep2agi/commhub-server) | 0.8.4 |
186
- | [@sleep2agi/agent-network-dashboard](https://www.npmjs.com/package/@sleep2agi/agent-network-dashboard) | 0.5.6 |
71
+ ## Documentation
187
72
 
188
- ## License
73
+ - [Agent Node guide](https://anet.sh/guide/agent-node)
74
+ - [Runtime guide](https://anet.sh/guide/runtimes)
75
+ - [CLI reference](https://anet.sh/guide/cli)
76
+ - [Troubleshooting](https://anet.sh/troubleshooting)
77
+ - [Source repository](https://github.com/sleep2agi/agent-network)
189
78
 
190
- Apache-2.0
79
+ Apache-2.0.