brainclaw 0.19.10 → 0.19.12
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 +3 -0
- package/dist/cli.js +1 -0
- package/dist/commands/bootstrap.js +17 -1
- package/dist/commands/env.js +7 -1
- package/dist/commands/init.js +1 -0
- package/dist/commands/mcp.js +76 -3
- package/dist/commands/version.js +3 -1
- package/dist/commands/whoami.js +11 -1
- package/dist/core/bootstrap.js +416 -60
- package/dist/core/brainclaw-version.js +303 -62
- package/dist/core/schema.js +28 -0
- package/docs/cli.md +15 -1
- package/docs/integrations/mcp.md +29 -7
- package/docs/mcp-schema-changelog.md +6 -0
- package/docs/quickstart.md +22 -1
- package/package.json +1 -1
package/docs/quickstart.md
CHANGED
|
@@ -39,6 +39,7 @@ After the workspace is initialized, the nominal flow is:
|
|
|
39
39
|
|
|
40
40
|
```text
|
|
41
41
|
bclaw_session_start -> open a session and return current board/context
|
|
42
|
+
bclaw_get_execution_context -> inspect local tooling and notice package updates
|
|
42
43
|
bclaw_get_context -> fetch fresh prompt-ready context for the target path
|
|
43
44
|
bclaw_list_plans -> inspect active work
|
|
44
45
|
bclaw_claim -> claim scope before editing
|
|
@@ -48,6 +49,8 @@ bclaw_session_end -> close session cleanly and hand work off
|
|
|
48
49
|
|
|
49
50
|
Use native agent files such as `AGENTS.md`, `CLAUDE.md`, or Cursor rules as local workflow guidance, not as the only source of live state.
|
|
50
51
|
|
|
52
|
+
Unless the project overrides `brainclaw_update_source`, `bclaw_get_execution_context` checks the public npm `latest` channel so the agent can notice when a newer Brainclaw release is available.
|
|
53
|
+
|
|
51
54
|
## Path 2: CLI-Oriented Agent Or Fallback Workflow
|
|
52
55
|
|
|
53
56
|
Use this path when the agent does not have a good MCP integration yet, or when a human needs to drive the workflow directly.
|
|
@@ -103,10 +106,28 @@ brainclaw bootstrap --interview --audience cli
|
|
|
103
106
|
brainclaw bootstrap --interview --audience ide_chat
|
|
104
107
|
```
|
|
105
108
|
|
|
109
|
+
Use the returned question IDs to prepare a small JSON answers file when the interview needs to confirm durable memory:
|
|
110
|
+
|
|
111
|
+
```json
|
|
112
|
+
[
|
|
113
|
+
{
|
|
114
|
+
"question_id": "biq_example",
|
|
115
|
+
"response_items": ["Use agents sequentially in one checkout."],
|
|
116
|
+
"suggestions": []
|
|
117
|
+
}
|
|
118
|
+
]
|
|
119
|
+
```
|
|
120
|
+
|
|
121
|
+
Preview the enriched import proposal:
|
|
122
|
+
|
|
123
|
+
```bash
|
|
124
|
+
brainclaw bootstrap --answers-file ./bootstrap-answers.json --json
|
|
125
|
+
```
|
|
126
|
+
|
|
106
127
|
### Apply or rollback managed imports
|
|
107
128
|
|
|
108
129
|
```bash
|
|
109
|
-
brainclaw bootstrap --apply
|
|
130
|
+
brainclaw bootstrap --answers-file ./bootstrap-answers.json --apply
|
|
110
131
|
brainclaw bootstrap --uninstall
|
|
111
132
|
```
|
|
112
133
|
|