@brainbase-labs/cli 0.48.0 → 0.50.0
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.
- package/README.md +29 -6
- package/dist/index.js +15688 -14778
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -27,6 +27,24 @@ brainbase benchmark list # list benchmarks for the linked agent
|
|
|
27
27
|
|
|
28
28
|
Run `brainbase help` to see every command.
|
|
29
29
|
|
|
30
|
+
## Agent surfaces
|
|
31
|
+
|
|
32
|
+
Manage Chat, Slack, Meetings, GitHub, Linear and Phone from the terminal:
|
|
33
|
+
|
|
34
|
+
```sh
|
|
35
|
+
brainbase agent connections --agent <id> --json
|
|
36
|
+
brainbase agent surface chat configure --agent <id> --models= --json
|
|
37
|
+
brainbase agent surface meeting configure --agent <id> --vision true
|
|
38
|
+
brainbase agent surface github connect --agent <id> --no-open
|
|
39
|
+
brainbase agent surface --help
|
|
40
|
+
```
|
|
41
|
+
|
|
42
|
+
Use `status` for effective settings and capabilities, and `configure` to
|
|
43
|
+
change only the supplied fields. GitHub/Linear setup prints portable browser
|
|
44
|
+
links and can resume with `wait --installation <id>`. Provider operations
|
|
45
|
+
require a login session. Phone purchases and all new disconnect commands
|
|
46
|
+
require `--yes`. See the [command reference](docs/reference/commands.mdx#connections).
|
|
47
|
+
|
|
30
48
|
## Link and pull in one step
|
|
31
49
|
|
|
32
50
|
A fresh checkout — a task sandbox, a CI job — can attach to an agent and pull it
|
|
@@ -98,18 +116,23 @@ this confirms admission or delivery, not task success.
|
|
|
98
116
|
|
|
99
117
|
## Renaming and labelling tasks
|
|
100
118
|
|
|
101
|
-
|
|
119
|
+
Label a task when you create it, find tasks by label, and change a task's
|
|
120
|
+
title, its labels or its model, including while it runs:
|
|
102
121
|
|
|
103
122
|
```sh
|
|
104
|
-
brainbase task
|
|
123
|
+
brainbase task create --message "Nightly smoke run" --metadata env=staging
|
|
124
|
+
brainbase task list --metadata env=staging
|
|
125
|
+
brainbase task update <task-id> --title "Nightly smoke run" --metadata env=prod
|
|
105
126
|
brainbase task update <task-id> --unset-metadata env --json
|
|
106
127
|
brainbase task update <task-id> --model claude-sonnet-5-5
|
|
128
|
+
brainbase task update <task-id> --clear-model
|
|
107
129
|
```
|
|
108
130
|
|
|
109
|
-
`--metadata` and `--unset-metadata` keep every label you do not name
|
|
110
|
-
|
|
111
|
-
`--model` switches the model the
|
|
112
|
-
running keeps its model.
|
|
131
|
+
`--metadata` and `--unset-metadata` keep every label you do not name, and
|
|
132
|
+
edits from several clients at once all survive. `--clear-metadata` removes them
|
|
133
|
+
all, and `--clear-title` removes the title. `--model` switches the model the
|
|
134
|
+
task's next turn runs on; a turn already running keeps its model.
|
|
135
|
+
`--clear-model` returns the task to its agent's default model. See
|
|
113
136
|
[the command reference](docs/reference/commands.mdx) for every flag.
|
|
114
137
|
|
|
115
138
|
## Benchmark management
|