@fastino-ai/pioneer-cli 0.2.11 → 0.3.0

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 +22 -60
  2. package/dist/index.js +94 -134
  3. package/package.json +3 -13
package/README.md CHANGED
@@ -11,6 +11,21 @@ Command-line interface for the Pioneer AI training platform.
11
11
  ╚═╝ ╚═╝ ╚═════╝ ╚═╝ ╚═══╝╚══════╝╚══════╝╚═╝ ╚═╝
12
12
  ```
13
13
 
14
+ ## What's new in 0.3.0 (security release)
15
+
16
+ The `pioneer agent` interactive chat command and its WebSocket runtime have
17
+ been **removed** in this release for security reasons. The agent shipped with
18
+ local tool execution (shell, filesystem write/read, URL fetching) and a sandbox
19
+ surface that we are no longer comfortable shipping in a CLI binary.
20
+
21
+ If you need conversational workflows for training jobs, datasets, or model
22
+ deployment, use the Pioneer web app at <https://app.pioneer.ai/> instead. All
23
+ non-agent commands in this CLI (auth, dataset, job, model, telemetry) continue
24
+ to work unchanged.
25
+
26
+ Running `pioneer agent` (or any `agent` subcommand) now prints a clear
27
+ deprecation message and exits.
28
+
14
29
  ## Installation
15
30
 
16
31
  ### npm
@@ -51,18 +66,12 @@ pioneer auth login # Enter API key interactively
51
66
  pioneer auth logout # Clear stored API key
52
67
  pioneer auth status # Check if logged in
53
68
 
54
- # Agent
55
- pioneer agent # Interactive chat (default)
56
- pioneer agent --mode research # Research mode (Pro subscription required)
57
-
58
69
  # Training Jobs
59
70
  pioneer job list
60
71
  pioneer job get <id>
61
72
  pioneer job logs <id>
62
73
  pioneer job delete <id>
63
- # To create a training job, use the agent it will help you pick a base model
64
- # and datasets conversationally:
65
- pioneer agent
74
+ # To create a training job, use the Pioneer web app at https://app.pioneer.ai/.
66
75
 
67
76
  # Models
68
77
  pioneer model base-models # List available base models (tabular)
@@ -95,62 +104,15 @@ pioneer model_endpoints list
95
104
  pioneer model_artifacts list
96
105
  ```
97
106
 
98
- ## Agent command
99
-
100
- `agent` starts in interactive mode by default (standard workflow). For the only explicit alternate mode:
101
- - `--mode research`: Pro mode with deeper research response style.
102
- - `agent resume`: list recent conversations and resume a selected session.
103
- - `agent sessions`: explicit alias for listing sessions and resuming one.
104
-
105
- ```bash
106
- # Interactive (default)
107
- pioneer agent
108
-
109
- # Standard mode is the default:
110
- pioneer agent
111
-
112
- # Research mode (Pro subscription required)
113
- pioneer agent --mode research
114
-
115
- # Open a session list and pick one to continue
116
- pioneer agent resume
117
-
118
- # Equivalent: explicit sessions command
119
- pioneer agent sessions
120
-
121
- # Resume a specific conversation id
122
- pioneer agent resume 4f2a...
123
- ```
124
-
125
- When you start any of these commands, the CLI opens a conversational prompt and keeps accepting follow-up messages in the same session.
126
-
127
- Interactive **standard** mode uses the same WebSocket agent as the Pioneer app’s sidebar: Felix tools plus **local** CLI tools (**bash**, **read_file**, **write_file**, **edit_file**, **list_directory**, **search_files**, and **`browse_url`** — HTTP GET for public pages with HTML stripped; no JavaScript). Full **Browser Use** (driving your open Pioneer UI with click/type/navigate against the live DOM) remains **web-only**; the CLI surfaces a clear hint if those tools appear.
128
-
129
107
  ## End-to-End Example
130
108
 
131
- This example shows the complete workflow from running jobs to using agent support.
109
+ ### Step 1: Create a Training Job
132
110
 
133
- ### Step 1: Start a planning session
134
- Use `agent` for quick iteration while preparing jobs and reviewing results.
135
-
136
- ### Step 2: Open the interactive helper
137
-
138
- ```bash
139
- # Open a short interactive helper session
140
- pioneer agent
141
- ```
142
-
143
- ### Step 3: Create a Training Job
144
-
145
- Use `pioneer agent` to create a training job. The agent will guide you through
146
- picking a base model, selecting datasets, and configuring hyperparameters
147
- without needing to remember flags or dataset IDs:
148
-
149
- ```bash
150
- pioneer agent
151
- ```
111
+ Use the Pioneer web app at <https://app.pioneer.ai/> to create a training job.
112
+ The web app will guide you through picking a base model, selecting datasets,
113
+ and configuring hyperparameters.
152
114
 
153
- ### Step 4: Monitor Training Progress
115
+ ### Step 2: Monitor Training Progress
154
116
 
155
117
  ```bash
156
118
  # List all training jobs
@@ -163,7 +125,7 @@ pioneer job get <job-id>
163
125
  pioneer job logs <job-id>
164
126
  ```
165
127
 
166
- ### Step 5: Use Your Trained Model
128
+ ### Step 3: Use Your Trained Model
167
129
 
168
130
  Once training completes:
169
131