@laburen/delta-cli 0.2.0-canary.22 → 0.2.0-canary.23
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/dist/commands/agent-checks.js +10 -3
- package/dist/commands/agent-checks.js.map +1 -1
- package/dist/commands/agent-tools/add.js +2 -1
- package/dist/commands/agent-tools/add.js.map +1 -1
- package/dist/commands/agent-tools/remove.js +2 -1
- package/dist/commands/agent-tools/remove.js.map +1 -1
- package/dist/commands/agent-tools/shared.d.ts +14 -2
- package/dist/commands/agent-tools/shared.js +17 -0
- package/dist/commands/agent-tools/shared.js.map +1 -1
- package/dist/generated/schemas.js +4 -4
- package/dist/generated/schemas.js.map +1 -1
- package/docs/SKILL.md +1 -1
- package/docs/references/commands.md +1 -1
- package/docs/references/output-and-errors.md +1 -1
- package/package.json +2 -2
package/docs/SKILL.md
CHANGED
|
@@ -95,7 +95,7 @@ Both create a new version and neither activates it unless you ask. They differ i
|
|
|
95
95
|
- `agents update <agent_id> --config @patch.json` **edits**: it starts from the latest version and replaces only the config keys you send (`{"prompt":[{"type":"text","content":"New prompt"}]}` changes the prompt and keeps the model, tools and the rest). Each top-level key is replaced whole, with no deep merge: `{"knowledge":{"project_ids":[]}}` drops `knowledge.mode`. `--skills` and `--mcp-connections` replace the whole list and also create a version. With only `--name` or `--description` no version is created.
|
|
96
96
|
- `agents versions create <agent_id> --config @config.json` **writes the whole version**: a key you omit goes back to its default, and there are no skills or MCP connections unless you send them. Use it with a full config (start from `--skeleton`).
|
|
97
97
|
|
|
98
|
-
**Warning:** `agents update --config`, `agents tools add` and `agents
|
|
98
|
+
**Warning:** `agents update --config`, `agents tools add`, `agents tools remove` and `agents versions create` (when you send what you want it to keep) start from the **latest** version, not the active one. If the latest is an inactive draft, the new version carries the draft's changes, and the active version's tools are lost if only the active one had them. When that happens the response has a warning `includes_unpublished_changes` (`Warning: ...` on stderr) with `active_version_id` and `changed_fields_from_active` (what the new version changes compared with the active one, not with the draft), and the CLI prints `Compare every change against the active version with: laburen agents versions compare <agent_id> --from <active_version_id> --to <version_id>`. It also appears with `--activate`. There is no warning when the agent has no active version, when the latest is the active one, or when the new version equals the active one. Before activating a version, compare the active one against it with that command. Deleting the latest version frees its number, and the next version reuses it (the number is the highest that exists plus one).
|
|
99
99
|
|
|
100
100
|
When the new version stays inactive, both print `Created version <n> (not active). Activate it with: laburen agents versions activate <agent_id> <version_id>` on stderr, also with `--json`. Pass `--activate` to activate it right away.
|
|
101
101
|
|
|
@@ -123,7 +123,7 @@ Without `--json`, `compare` prints one difference per line, with the same rule a
|
|
|
123
123
|
|
|
124
124
|
Tools (reads the latest version, changes `config.tools`, and creates a new version; the new version is not active unless you pass `--activate`):
|
|
125
125
|
|
|
126
|
-
> **Warning:** `tools add` and `tools remove` start from the **latest** version, not the active one (so does `agents update --config`). If the latest version is a draft that is not active, the new version keeps the draft's
|
|
126
|
+
> **Warning:** `tools add` and `tools remove` start from the **latest** version, not the active one (so does `agents update --config`). If the latest version is a draft that is not active, the new version keeps the draft's changes and drops whatever only the active version had. The response then has the warning `includes_unpublished_changes`, and the CLI prints the ready command `laburen agents versions compare <agent_id> --from <active_version_id> --to <version_id>` to see every change against the active version (`active_version_id` and `changed_fields_from_active` are in the `--json` output). You can also check `laburen agents versions list <agent_id>` first; if the latest is not the active one, activate or delete the draft before you change tools.
|
|
127
127
|
|
|
128
128
|
```sh
|
|
129
129
|
laburen agents tools add <agent_id> --tool '{"type":"send_files"}'
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
- stdout: the data, and the error JSON (with `--json` or in non-interactive mode; see below).
|
|
6
6
|
- stderr: notices, the login URL, the version notice, and errors for humans. The exception is a command whose stdout is the content: `agents run` without `--json` writes all its errors to stderr (as JSON in non-interactive mode), including usage errors such as a missing `<agent_id>`, so stdout keeps only the text of the turn; and `agents follow-ups run` without `--json`, when the result has `error`, prints the card on stdout and the error on stderr (with `--json`, stdout has only the `FollowUpRun`, which already carries `error`).
|
|
7
|
-
- `Warning: <message>` on stderr for each item of `warnings` in an API response, read from the top-level `warnings` and from a nested `version.warnings` (as in `agents create` and `agents update`) (also with `--json`, where stdout stays the untouched JSON). Without `--json`, the card on stdout does not repeat those `warnings`: each one is shown once, on stderr; use `--json` to read their other fields (such as `code`).
|
|
7
|
+
- `Warning: <message>` on stderr for each item of `warnings` in an API response, read from the top-level `warnings` and from a nested `version.warnings` (as in `agents create` and `agents update`) (also with `--json`, where stdout stays the untouched JSON). Without `--json`, the card on stdout does not repeat those `warnings`: each one is shown once, on stderr; use `--json` to read their other fields (such as `code`). A warning `includes_unpublished_changes` (in `agents update`, `agents versions create` and `agents tools add|remove`) is followed by a line on stderr with the command that compares the active version against the new one: `Compare every change against the active version with: laburen agents versions compare <agent_id> --from <active_version_id> --to <version_id>`; its `active_version_id` and `changed_fields_from_active` fields are in the `--json` output.
|
|
8
8
|
|
|
9
9
|
Without `--json`, lists print as a table and single items as `key: value` lines (an empty `changed_fields` shows as `changed_fields: []`; an empty `warnings` list and empty objects are hidden). Lists of agents, versions, skills and the like show a few columns and cut long text to the width of a terminal (the ID column is never cut, and piped output is not cut); `get` or `--json` shows every field. In a `get` card, nested objects are indented under their key; in a table cell they are one-line JSON. Lists of strings appear as `a,b` in a table cell; in a card they go one `- item` per line under their key, also with a single item, so a list never looks like a single value. `agents follow-ups run` prints the `reason` and `messages` of `agent` with their real line breaks, indented under their field (a one-line text stays on the line of its field); control characters and terminal sequences are escaped as everywhere else. `versions compare` prints one difference per line with one rule for every resource: a string longer than 120 characters, or a list of only text blocks (the prompt), shows its first 60 characters: `"<first 60 chars>…" (N chars)`; any other list or object is summarized as `<list, N items>` or `<object, N keys>` only when its JSON is longer than 120 characters, and a shorter one is printed whole (`[{"skill_id":"…","strategy":"pin"}] → […"latest"]`). When both values are objects and one of them is that long, the line names the top-level keys that changed instead (`tree: changed SKILL.md; added references/b.md; removed references/a.md`), up to 5 keys per group and then `(+N more)`. When both values are non-empty lists and one of them is that long, the line names the items that changed, were added or were removed (`tools: changed tool_b, tool_d; added tool_x`), with the same limit: each item is named by its `id` (or `skill_id`, `connection_id`, `name`, `type`) when every item has one and none repeats, and by its position otherwise (`changed [1]; added [2]`); same items in another order show as `same items, reordered`. Use `--json` for the full values. `--json` is never changed by any of this. Table columns follow the order in which keys appear, including columns that are `null` in every row. Control characters in values from the server (`\n`, `\t`, `ESC`...) are printed escaped (`\n`, `\x1b`), never raw: in tables, cards, errors, `next` lines and the labels of the questions. An empty list prints `No results.`
|
|
10
10
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@laburen/delta-cli",
|
|
3
|
-
"version": "0.2.0-canary.
|
|
3
|
+
"version": "0.2.0-canary.23",
|
|
4
4
|
"description": "Laburen CLI to manage agents from the terminal",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"license": "MIT",
|
|
@@ -27,7 +27,7 @@
|
|
|
27
27
|
},
|
|
28
28
|
"dependencies": {
|
|
29
29
|
"@clack/prompts": "1.8.1",
|
|
30
|
-
"@laburen/delta-sdk": "1.5.0-canary.
|
|
30
|
+
"@laburen/delta-sdk": "1.5.0-canary.23",
|
|
31
31
|
"@vercel/detect-agent": "1.2.7",
|
|
32
32
|
"commander": "14.0.3",
|
|
33
33
|
"picocolors": "1.1.1"
|