@withgauge/cli 0.6.0 → 0.8.0

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 +33 -17
  2. package/dist/index.js +3993 -1951
  3. package/package.json +2 -2
package/README.md CHANGED
@@ -1,12 +1,13 @@
1
1
  # @withgauge/cli
2
2
 
3
- `gauge` — the [Gauge](https://agents.withgauge.com) command-line interface. Manage
4
- your prompts, repositories, and agent runs, and watch runs live from your
5
- terminal.
3
+ `gauge` — the [Gauge](https://agents.withgauge.com) command-line interface.
4
+ Manage your eval sets, Agent Preference prompts, run presets, and agent runs,
5
+ and watch runs live from your terminal.
6
6
 
7
7
  ```sh
8
8
  npm install -g @withgauge/cli
9
- gauge auth login # opens your browser to authorize this machine
9
+ gauge onboard # sign in, create a workspace, seed starter measurements
10
+ gauge auth login # (or just sign in)
10
11
  gauge orgs use <org> # set your default organization
11
12
  ```
12
13
 
@@ -15,30 +16,45 @@ Requires Node.js ≥ 22.12.
15
16
  ## Usage
16
17
 
17
18
  ```sh
18
- gauge prompts list # your prompts
19
- gauge runs list --status running # recent & active runs
19
+ gauge status # the org at a glance
20
+ gauge evals list # judged agent-experience measurements
21
+ gauge preference list # Agent Preference prompts and measurements
22
+ gauge presets list # run configurations (repo × persona × agents × skills × MCP)
23
+ gauge models list # supported model × harness × provider targets
24
+ gauge evals attach <id> --preset <presetId> # schedule a preset on an eval (prints the bill first)
25
+ gauge evals run <id> # launch now (ORG-funded, credit-gated)
20
26
  gauge runs watch <run-id> # follow a run as the agent works
21
- gauge runs fork <run-id> --prompt "Try a different approach"
22
- gauge repos list # your repository catalog
23
27
  gauge stats rankings -o json # brand rankings (share of voice) as JSON
24
- gauge query fields --dataset installs # discover a dataset's dimensions/metrics
25
28
  gauge query -d ecosystem -m installs,install_rate -o json # a flexible report
26
29
  ```
27
30
 
28
31
  Run `gauge --help` (or `gauge <command> --help`) for the full command set:
29
- prompts, schedules, repos, runs, stats, query, brands, tags, topics, provider
30
- keys, billing, and more.
32
+ evals, preference, presets, models, personas, skills, mcp, cycles, repos, runs,
33
+ experiments, batches, brands, tags, actions, impl, dashboards, members, org,
34
+ provider keys, billing, usage, stats, query, and more.
35
+
36
+ **Run presets** are the unit of configuration: an eval set or preference
37
+ prompt runs whatever presets are attached to it, every cycle. `gauge presets
38
+ create --name api-main --repo https://github.com/acme/api --agent
39
+ claude-code:claude-opus-4-8 --skill acme-cli@1.2.0` authors one;
40
+ `gauge evals attach` / `gauge preference attach` schedules it. Attaching
41
+ spends money on a schedule, so `attach` and `run` print the per-cycle run
42
+ arithmetic and ask before acting (`--yes` skips the prompt for scripts).
43
+
44
+ Use `gauge models list` before pinning models. It reads the organization's live
45
+ catalog and shows every selectable logical model with its harness, provider,
46
+ and effective capabilities. Open harnesses use `--agent pi:<model>` and
47
+ `--agent opencode:<model>` just like the frontier harnesses.
31
48
 
32
49
  `gauge query` builds flexible reports over your event warehouse (a GA4
33
- `run_report` analog): pick a `--dataset`, group by `--dimensions`, and aggregate
34
- `--metrics`, or pass a whole spec with `--json` (the agent-friendly surface).
35
- `gauge query datasets` / `gauge query fields --dataset <name>` list what you can
36
- ask for.
50
+ `run_report` analog): pick a `--dataset`, group by `--dimensions` (including
51
+ `run_preset`), and aggregate `--metrics`, or pass a whole spec with `--json`.
52
+ `gauge query datasets` / `gauge query fields --dataset <name>` list what you
53
+ can ask for.
37
54
 
38
55
  To launch runs declaratively, `gauge apply -f <spec>.json`. Discover the spec
39
56
  format without leaving the terminal: `gauge apply --example` prints a starter
40
- spec (`gauge apply --example > battery.json`), and `gauge apply --schema` prints
41
- its JSON Schema.
57
+ spec and `gauge apply --schema` prints its JSON Schema.
42
58
 
43
59
  Every read supports `-o json` for scripting. `GAUGE_API_TOKEN` overrides
44
60
  stored credentials (useful in CI). Exit codes: `0` ok · `1` error ·