pi-multi-agent-skill 0.2.0 → 0.2.1
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/CHANGELOG.md
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
1
|
+
# Changelog
|
|
2
|
+
|
|
3
|
+
## [0.2.1] - 2026-11-04
|
|
4
|
+
|
|
5
|
+
### Added
|
|
6
|
+
|
|
7
|
+
- A standalone multi-agent usage report shows token counts and recorded costs by date, project, job, model and profile. The skill tells the agent when to run it.
|
|
8
|
+
|
|
9
|
+
### Fixed
|
|
10
|
+
|
|
11
|
+
- Forked sessions exclude usage from before their creation without reading parent sessions.
|
|
12
|
+
- Model breakdowns use the concrete response model when pi records it.
|
|
13
|
+
- Date cutoffs before the first usage record return empty reports instead of an invalid-range error.
|
|
14
|
+
|
|
15
|
+
## [0.2.0] - 2026-10-26
|
|
16
|
+
|
|
17
|
+
### Breaking Changes
|
|
18
|
+
|
|
19
|
+
- Environment variables use the `PI_MULTI_AGENT_` prefix, such as `PI_MULTI_AGENT_PI_BIN`. The old `MULTI_AGENT_` names are not read.
|
|
20
|
+
|
|
21
|
+
### Added
|
|
22
|
+
|
|
23
|
+
- `rm --all` deletes every job of the current project that is not running.
|
|
24
|
+
- Starting a job with a name already in use fails and reports the existing job's status and age.
|
|
25
|
+
- `run` and `resume` check that the pi program exists before starting a job.
|
|
26
|
+
- Agents run `pi-request-user-input` in non-interactive mode, so its tool fails instead of opening a dialog.
|
|
27
|
+
|
|
28
|
+
## [0.1.0] - 2026-10-12
|
|
29
|
+
|
|
30
|
+
### Added
|
|
31
|
+
|
|
32
|
+
- Initial release. The `multi-agent` skill and its CLI run pi agents as named foreground or background jobs that can be waited on, steered, aborted, resumed, and inspected.
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "pi-multi-agent-skill",
|
|
3
|
-
"version": "0.2.
|
|
3
|
+
"version": "0.2.1",
|
|
4
4
|
"description": "A minimal multi-agent skill+cli for pi. It adds no extension or tools, so it uses only a few dozen tokens of the context window until the main agent delegates, yet it gives the same controls as a subagent extension. Background agents keep running after the session closes, and any later session can collect their results.",
|
|
5
5
|
"license": "MIT",
|
|
6
6
|
"author": "Milan Glacier",
|
|
@@ -24,7 +24,8 @@
|
|
|
24
24
|
"skills/multi-agent/references/*.md",
|
|
25
25
|
"skills/multi-agent/scripts/*.py",
|
|
26
26
|
"README.md",
|
|
27
|
-
"LICENSE"
|
|
27
|
+
"LICENSE",
|
|
28
|
+
"CHANGELOG.md"
|
|
28
29
|
],
|
|
29
30
|
"pi": {
|
|
30
31
|
"skills": [
|
|
@@ -137,4 +137,5 @@ only when you need it:
|
|
|
137
137
|
model, tools and system prompt are chosen.
|
|
138
138
|
- `state.md`: where jobs and conversations are stored, and the agent's
|
|
139
139
|
environment.
|
|
140
|
+
- `usage.md`: token and cost report.
|
|
140
141
|
- `troubleshooting.md`: error messages and what to do about them.
|
|
@@ -0,0 +1,40 @@
|
|
|
1
|
+
# Usage report
|
|
2
|
+
|
|
3
|
+
`usage.py` shows token counts and the cost pi recorded for the multi-agent
|
|
4
|
+
sessions on this machine. Run it only when the user asks what the agents used
|
|
5
|
+
or cost.
|
|
6
|
+
|
|
7
|
+
```bash
|
|
8
|
+
python3 "$SKILL_DIR/scripts/usage.py" [VIEW] [OPTIONS]
|
|
9
|
+
```
|
|
10
|
+
|
|
11
|
+
The default `overview` view shows the all-time total, the token breakdown,
|
|
12
|
+
the top projects and models, and the last seven days. Start there; it answers
|
|
13
|
+
most questions.
|
|
14
|
+
|
|
15
|
+
| View | What it shows |
|
|
16
|
+
|---|---|
|
|
17
|
+
| `daily`, `weekly`, `monthly` | Totals per period, including empty periods. |
|
|
18
|
+
| `project` | Totals per project. |
|
|
19
|
+
| `session` | Totals per job, with its profile and models. |
|
|
20
|
+
| `model` | Totals per provider and model. |
|
|
21
|
+
| `profile` | Totals per profile. |
|
|
22
|
+
|
|
23
|
+
| Option | Meaning |
|
|
24
|
+
|---|---|
|
|
25
|
+
| `--since DATE`, `--until DATE` | Inclusive date range for every view. |
|
|
26
|
+
| `--days N`, `--weeks N`, `--months N` | Window for the time view; defaults 30, 12 and 12. |
|
|
27
|
+
| `--project TEXT` | Only projects whose path contains TEXT; repeatable. |
|
|
28
|
+
| `--all` | All time instead of the default window. |
|
|
29
|
+
| `--limit N` | Rows in a group view; `0` shows all. |
|
|
30
|
+
| `--timezone NAME` | IANA timezone for day boundaries; default local. |
|
|
31
|
+
| `--json` | One JSON object instead of tables. |
|
|
32
|
+
|
|
33
|
+
The report covers every project on the machine, not just the current one. Use
|
|
34
|
+
`--project` to narrow it. Costs come from pi; records without a recorded cost
|
|
35
|
+
are counted as unpriced. Running jobs appear with the usage recorded so far.
|
|
36
|
+
|
|
37
|
+
Group views print every row unless `--limit` is given, so pass `--limit 10`
|
|
38
|
+
and raise it only when the user asks for more. When you need to compare or
|
|
39
|
+
sum numbers, `--json` is easier than a wide table. Report only the numbers
|
|
40
|
+
the user asked for, not the whole output.
|