@eigenpal/cli 0.6.9 → 0.6.11
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 +6 -0
- package/README.md +2 -2
- package/dist/cli.js +1310 -1274
- package/dist/skill/SKILL.md +60 -57
- package/dist/skill/reference/cli/agents.md +143 -556
- package/dist/skill/reference/cli/init.md +1 -1
- package/dist/skill/reference/cli/runs.md +481 -0
- package/dist/skill/reference/cli/surface.md +135 -0
- package/dist/skill/reference/cli/workflow.md +35 -149
- package/dist/skill/reference/dataset-format.md +1 -1
- package/dist/skill/reference/debugging.md +23 -22
- package/dist/skill/reference/step-exec.md +3 -3
- package/dist/skill/reference/workflow-yaml.md +2 -2
- package/dist/templates/blank/README.md +1 -1
- package/dist/templates/pdf-extraction/README.md +1 -1
- package/dist/templates/text-classification/README.md +1 -1
- package/package.json +1 -1
|
@@ -10,7 +10,6 @@ Manage workflows: push, pull, run, evaluate.
|
|
|
10
10
|
- [Evaluators](#evaluators)
|
|
11
11
|
- [Dataset](#dataset)
|
|
12
12
|
- [Experiment](#experiment)
|
|
13
|
-
- [Execution](#execution)
|
|
14
13
|
- [Versions](#versions)
|
|
15
14
|
- [Step-type](#step-type)
|
|
16
15
|
- [Evaluator-type](#evaluator-type)
|
|
@@ -20,6 +19,7 @@ Manage workflows: push, pull, run, evaluate.
|
|
|
20
19
|
- [`eigenpal workflow pull [options] <workflow-id>`](#eigenpal-workflow-pull-options-workflow-id)
|
|
21
20
|
- [`eigenpal workflow push [options]`](#eigenpal-workflow-push-options)
|
|
22
21
|
- [`eigenpal workflow move [options] <workflow-id>`](#eigenpal-workflow-move-options-workflow-id)
|
|
22
|
+
- [`eigenpal workflow run [options] <workflow-id> [examples...]`](#eigenpal-workflow-run-options-workflow-id-examples)
|
|
23
23
|
- [`eigenpal workflow validate [options] [path]`](#eigenpal-workflow-validate-options-path)
|
|
24
24
|
- [`eigenpal workflow clear-local [options] [examples...]`](#eigenpal-workflow-clear-local-options-examples)
|
|
25
25
|
- [`eigenpal workflow evaluators pull [options] <workflow-id>`](#eigenpal-workflow-evaluators-pull-options-workflow-id)
|
|
@@ -40,12 +40,6 @@ Manage workflows: push, pull, run, evaluate.
|
|
|
40
40
|
- [`eigenpal workflow experiment|exp results [options] <workflow-id> [batchId]`](#eigenpal-workflow-experimentexp-results-options-workflow-id-batchid)
|
|
41
41
|
- [`eigenpal workflow experiment|exp compare|diff [options] <batchIdA> <batchIdB>`](#eigenpal-workflow-experimentexp-comparediff-options-batchida-batchidb)
|
|
42
42
|
- [`eigenpal workflow experiment|exp watch [options] <workflow-id> <batchId>`](#eigenpal-workflow-experimentexp-watch-options-workflow-id-batchid)
|
|
43
|
-
- [`eigenpal workflow execution|exec run [options] <workflow-id> [examples...]`](#eigenpal-workflow-executionexec-run-options-workflow-id-examples)
|
|
44
|
-
- [`eigenpal workflow execution|exec get [options] <executionId>`](#eigenpal-workflow-executionexec-get-options-executionid)
|
|
45
|
-
- [`eigenpal workflow execution|exec list|ls [options] <workflow-id>`](#eigenpal-workflow-executionexec-listls-options-workflow-id)
|
|
46
|
-
- [`eigenpal workflow execution|exec watch [options] <executionId>`](#eigenpal-workflow-executionexec-watch-options-executionid)
|
|
47
|
-
- [`eigenpal workflow execution|exec compare|diff [options] <executionA> <executionB>`](#eigenpal-workflow-executionexec-comparediff-options-executiona-executionb)
|
|
48
|
-
- [`eigenpal workflow execution|exec cancel [options] <executionId>`](#eigenpal-workflow-executionexec-cancel-options-executionid)
|
|
49
43
|
- [`eigenpal workflow versions list|ls [options] <workflow-id>`](#eigenpal-workflow-versions-listls-options-workflow-id)
|
|
50
44
|
- [`eigenpal workflow versions restore [options] <workflow-id> <versionId>`](#eigenpal-workflow-versions-restore-options-workflow-id-versionid)
|
|
51
45
|
- [`eigenpal workflow step-type list|ls [options]`](#eigenpal-workflow-step-type-listls-options)
|
|
@@ -84,13 +78,7 @@ workflow
|
|
|
84
78
|
│ ├── results <workflow-id> [batchId]
|
|
85
79
|
│ ├── compare|diff <batchIdA> <batchIdB>
|
|
86
80
|
│ └── watch <workflow-id> <batchId>
|
|
87
|
-
├──
|
|
88
|
-
│ ├── run <workflow-id> [examples...]
|
|
89
|
-
│ ├── get <executionId>
|
|
90
|
-
│ ├── list|ls <workflow-id>
|
|
91
|
-
│ ├── watch <executionId>
|
|
92
|
-
│ ├── compare|diff <executionA> <executionB>
|
|
93
|
-
│ └── cancel <executionId>
|
|
81
|
+
├── run <workflow-id> [examples...]
|
|
94
82
|
├── versions
|
|
95
83
|
│ ├── list|ls <workflow-id>
|
|
96
84
|
│ └── restore <workflow-id> <versionId>
|
|
@@ -110,14 +98,15 @@ workflow
|
|
|
110
98
|
|
|
111
99
|
### Core
|
|
112
100
|
|
|
113
|
-
| Command
|
|
114
|
-
|
|
|
115
|
-
| `eigenpal workflow list\|ls [options]`
|
|
116
|
-
| `eigenpal workflow pull [options] <workflow-id>`
|
|
117
|
-
| `eigenpal workflow push [options]`
|
|
118
|
-
| `eigenpal workflow move [options] <workflow-id>`
|
|
119
|
-
| `eigenpal workflow
|
|
120
|
-
| `eigenpal workflow
|
|
101
|
+
| Command | Description |
|
|
102
|
+
| ------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
|
103
|
+
| `eigenpal workflow list\|ls [options]` | List workflows the caller can read. |
|
|
104
|
+
| `eigenpal workflow pull [options] <workflow-id>` | Download the YAML definition of the workflow at its current version. |
|
|
105
|
+
| `eigenpal workflow push [options]` | Create or update a workflow from a YAML file. |
|
|
106
|
+
| `eigenpal workflow move [options] <workflow-id>` | Move a workflow to a folder path, creating folders as needed |
|
|
107
|
+
| `eigenpal workflow run [options] <workflow-id> [examples...]` | Run a saved workflow against local dataset examples. |
|
|
108
|
+
| `eigenpal workflow validate [options] [path]` | Local-only validation. Without [path]: runs the templated three-way check (./workflow.yaml + ./evaluators.yaml + ./dataset/). With [path] pointing at a YAML file: validates just that workflow.yaml. For per-noun targeting use `evaluators validate` or `dataset validate`. |
|
|
109
|
+
| `eigenpal workflow clear-local [options] [examples...]` | Delete local execution artifacts under ./dataset/examples/. Keeps the latest run per example by default. |
|
|
121
110
|
|
|
122
111
|
### Evaluators
|
|
123
112
|
|
|
@@ -152,17 +141,6 @@ workflow
|
|
|
152
141
|
| `eigenpal workflow experiment\|exp compare\|diff [options] <batchIdA> <batchIdB>` | Diff eval scores between two experiment batches. |
|
|
153
142
|
| `eigenpal workflow experiment\|exp watch [options] <workflow-id> <batchId>` | Poll until terminal, then auto-pull results — replaces `status --watch` + `results --out`. |
|
|
154
143
|
|
|
155
|
-
### Execution
|
|
156
|
-
|
|
157
|
-
| Command | Description |
|
|
158
|
-
| ------------------------------------------------------------------------------------- | ---------------------------------------------------------------- |
|
|
159
|
-
| `eigenpal workflow execution\|exec run [options] <workflow-id> [examples...]` | Run a saved workflow against local dataset examples. |
|
|
160
|
-
| `eigenpal workflow execution\|exec get [options] <executionId>` | Fetch a single execution payload. Optionally narrow to one step. |
|
|
161
|
-
| `eigenpal workflow execution\|exec list\|ls [options] <workflow-id>` | List recent executions for a workflow. |
|
|
162
|
-
| `eigenpal workflow execution\|exec watch [options] <executionId>` | Stream live execution status until terminal or 30-min detach. |
|
|
163
|
-
| `eigenpal workflow execution\|exec compare\|diff [options] <executionA> <executionB>` | Diff two executions side-by-side, per step. |
|
|
164
|
-
| `eigenpal workflow execution\|exec cancel [options] <executionId>` | Cancel an execution. Idempotent on already-terminal runs. |
|
|
165
|
-
|
|
166
144
|
### Versions
|
|
167
145
|
|
|
168
146
|
| Command | Description |
|
|
@@ -186,9 +164,9 @@ workflow
|
|
|
186
164
|
|
|
187
165
|
### Step
|
|
188
166
|
|
|
189
|
-
| Command | Description
|
|
190
|
-
| ---------------------------------------------- |
|
|
191
|
-
| `eigenpal workflow step exec [options] <type>` | DISABLED — local mimic runners removed pending server-side redesign (EIG-104). Use `workflow
|
|
167
|
+
| Command | Description |
|
|
168
|
+
| ---------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------- |
|
|
169
|
+
| `eigenpal workflow step exec [options] <type>` | DISABLED — local mimic runners removed pending server-side redesign (EIG-104). Use `workflow run` or `workflow experiment run` instead. |
|
|
192
170
|
|
|
193
171
|
## Details
|
|
194
172
|
|
|
@@ -256,6 +234,26 @@ Move a workflow to a folder path, creating folders as needed
|
|
|
256
234
|
| `--base-url <url>` | no | | Server base URL |
|
|
257
235
|
| `--json` | no | | Output the raw server response as JSON |
|
|
258
236
|
|
|
237
|
+
### `eigenpal workflow run [options] <workflow-id> [examples...]`
|
|
238
|
+
|
|
239
|
+
Run a saved workflow against local dataset examples.
|
|
240
|
+
|
|
241
|
+
### Arguments
|
|
242
|
+
|
|
243
|
+
| Name | Required | Variadic | Description |
|
|
244
|
+
| ------------- | -------- | -------- | ----------- |
|
|
245
|
+
| `workflow-id` | yes | no | |
|
|
246
|
+
| `examples` | no | yes | |
|
|
247
|
+
|
|
248
|
+
### Options
|
|
249
|
+
|
|
250
|
+
| Flag | Required | Default | Description |
|
|
251
|
+
| ------------------- | -------- | ------- | -------------------------------------------- |
|
|
252
|
+
| `--dir <dir>` | no | | Local eigenpal directory |
|
|
253
|
+
| `--concurrency <n>` | no | | Max examples to run in parallel (default: 3) |
|
|
254
|
+
| `--base-url <url>` | no | | Server base URL |
|
|
255
|
+
| `--json` | no | | Output the raw server response as JSON |
|
|
256
|
+
|
|
259
257
|
### `eigenpal workflow validate [options] [path]`
|
|
260
258
|
|
|
261
259
|
Local-only validation. Without [path]: runs the templated three-way check (./workflow.yaml + ./evaluators.yaml + ./dataset/). With [path] pointing at a YAML file: validates just that workflow.yaml. For per-noun targeting use `evaluators validate` or `dataset validate`.
|
|
@@ -628,118 +626,6 @@ Poll until terminal, then auto-pull results — replaces `status --watch` + `res
|
|
|
628
626
|
| `--no-pull` | no | | Skip auto-pulling results on terminal (just watch) |
|
|
629
627
|
| `--base-url <url>` | no | | Server base URL |
|
|
630
628
|
|
|
631
|
-
### `eigenpal workflow execution|exec run [options] <workflow-id> [examples...]`
|
|
632
|
-
|
|
633
|
-
Run a saved workflow against local dataset examples.
|
|
634
|
-
|
|
635
|
-
### Arguments
|
|
636
|
-
|
|
637
|
-
| Name | Required | Variadic | Description |
|
|
638
|
-
| ------------- | -------- | -------- | ----------- |
|
|
639
|
-
| `workflow-id` | yes | no | |
|
|
640
|
-
| `examples` | no | yes | |
|
|
641
|
-
|
|
642
|
-
### Options
|
|
643
|
-
|
|
644
|
-
| Flag | Required | Default | Description |
|
|
645
|
-
| ------------------- | -------- | ------- | -------------------------------------------- |
|
|
646
|
-
| `--dir <dir>` | no | | Local eigenpal directory |
|
|
647
|
-
| `--concurrency <n>` | no | | Max examples to run in parallel (default: 3) |
|
|
648
|
-
| `--base-url <url>` | no | | Server base URL |
|
|
649
|
-
| `--json` | no | | Output the raw server response as JSON |
|
|
650
|
-
|
|
651
|
-
### `eigenpal workflow execution|exec get [options] <executionId>`
|
|
652
|
-
|
|
653
|
-
Fetch a single execution payload. Optionally narrow to one step.
|
|
654
|
-
|
|
655
|
-
### Arguments
|
|
656
|
-
|
|
657
|
-
| Name | Required | Variadic | Description |
|
|
658
|
-
| ------------- | -------- | -------- | ----------- |
|
|
659
|
-
| `executionId` | yes | no | |
|
|
660
|
-
|
|
661
|
-
### Options
|
|
662
|
-
|
|
663
|
-
| Flag | Required | Default | Description |
|
|
664
|
-
| ------------------- | -------- | ------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
|
665
|
-
| `--step <name>` | no | | Show only this step (or comma-separated list) |
|
|
666
|
-
| `--include <kinds>` | no | `"input,output,error,duration"` | Comma-separated subset of input,output,error,duration. `input` projects the resolved templated config (= what the processor actually received). `inputRef` returns the minimal predecessor-id reference instead. |
|
|
667
|
-
| `--base-url <url>` | no | | Server base URL |
|
|
668
|
-
| `--json` | no | | Output the raw server response as JSON |
|
|
669
|
-
|
|
670
|
-
### `eigenpal workflow execution|exec list|ls [options] <workflow-id>`
|
|
671
|
-
|
|
672
|
-
List recent executions for a workflow.
|
|
673
|
-
|
|
674
|
-
### Arguments
|
|
675
|
-
|
|
676
|
-
| Name | Required | Variadic | Description |
|
|
677
|
-
| ------------- | -------- | -------- | ----------- |
|
|
678
|
-
| `workflow-id` | yes | no | |
|
|
679
|
-
|
|
680
|
-
### Options
|
|
681
|
-
|
|
682
|
-
| Flag | Required | Default | Description |
|
|
683
|
-
| ------------------- | -------- | ------- | ---------------------------------------------------------------- |
|
|
684
|
-
| `--status <status>` | no | | Filter by status: pending\|running\|completed\|failed\|cancelled |
|
|
685
|
-
| `--limit <n>` | no | `50` | Page size |
|
|
686
|
-
| `--offset <n>` | no | `0` | Page offset |
|
|
687
|
-
| `--base-url <url>` | no | | Server base URL |
|
|
688
|
-
| `--json` | no | | Output the raw server response as JSON |
|
|
689
|
-
|
|
690
|
-
### `eigenpal workflow execution|exec watch [options] <executionId>`
|
|
691
|
-
|
|
692
|
-
Stream live execution status until terminal or 30-min detach.
|
|
693
|
-
|
|
694
|
-
### Arguments
|
|
695
|
-
|
|
696
|
-
| Name | Required | Variadic | Description |
|
|
697
|
-
| ------------- | -------- | -------- | ----------- |
|
|
698
|
-
| `executionId` | yes | no | |
|
|
699
|
-
|
|
700
|
-
### Options
|
|
701
|
-
|
|
702
|
-
| Flag | Required | Default | Description |
|
|
703
|
-
| ---------------------- | -------- | ------- | ---------------------------------------------- |
|
|
704
|
-
| `--max-wait <seconds>` | no | `1800` | Detach after N seconds (default 1800 = 30 min) |
|
|
705
|
-
| `--base-url <url>` | no | | Server base URL |
|
|
706
|
-
|
|
707
|
-
### `eigenpal workflow execution|exec compare|diff [options] <executionA> <executionB>`
|
|
708
|
-
|
|
709
|
-
Diff two executions side-by-side, per step.
|
|
710
|
-
|
|
711
|
-
### Arguments
|
|
712
|
-
|
|
713
|
-
| Name | Required | Variadic | Description |
|
|
714
|
-
| ------------ | -------- | -------- | ----------- |
|
|
715
|
-
| `executionA` | yes | no | |
|
|
716
|
-
| `executionB` | yes | no | |
|
|
717
|
-
|
|
718
|
-
### Options
|
|
719
|
-
|
|
720
|
-
| Flag | Required | Default | Description |
|
|
721
|
-
| ------------------ | -------- | ------- | ------------------------------- |
|
|
722
|
-
| `--step <name>` | no | | Restrict comparison to one step |
|
|
723
|
-
| `--base-url <url>` | no | | Server base URL |
|
|
724
|
-
|
|
725
|
-
### `eigenpal workflow execution|exec cancel [options] <executionId>`
|
|
726
|
-
|
|
727
|
-
Cancel an execution. Idempotent on already-terminal runs.
|
|
728
|
-
|
|
729
|
-
### Arguments
|
|
730
|
-
|
|
731
|
-
| Name | Required | Variadic | Description |
|
|
732
|
-
| ------------- | -------- | -------- | ----------- |
|
|
733
|
-
| `executionId` | yes | no | |
|
|
734
|
-
|
|
735
|
-
### Options
|
|
736
|
-
|
|
737
|
-
| Flag | Required | Default | Description |
|
|
738
|
-
| ------------------ | -------- | ------- | --------------------------------------------------------------------- |
|
|
739
|
-
| `--yes` | no | | Required for non-TTY shells (CI, pipes). Acts immediately, no prompt. |
|
|
740
|
-
| `--base-url <url>` | no | | Server base URL |
|
|
741
|
-
| `--json` | no | | Output the raw server response as JSON |
|
|
742
|
-
|
|
743
629
|
### `eigenpal workflow versions list|ls [options] <workflow-id>`
|
|
744
630
|
|
|
745
631
|
List historical workflow versions, newest first.
|
|
@@ -839,7 +725,7 @@ Fetch the JSON Schema for one evaluator type. Pipe through `jq` to inspect speci
|
|
|
839
725
|
|
|
840
726
|
### `eigenpal workflow step exec [options] <type>`
|
|
841
727
|
|
|
842
|
-
DISABLED — local mimic runners removed pending server-side redesign (EIG-104). Use `workflow
|
|
728
|
+
DISABLED — local mimic runners removed pending server-side redesign (EIG-104). Use `workflow run` or `workflow experiment run` instead.
|
|
843
729
|
|
|
844
730
|
### Arguments
|
|
845
731
|
|
|
@@ -270,7 +270,7 @@ Pretty mode prints labelled `Inputs` / `Expected` / `Metadata` sections;
|
|
|
270
270
|
|
|
271
271
|
```bash
|
|
272
272
|
# 1. Look at what the workflow actually returned for the example
|
|
273
|
-
eigenpal
|
|
273
|
+
eigenpal runs get exec_… --json | jq '.run.output.data' > /tmp/correct.json
|
|
274
274
|
|
|
275
275
|
# 2. Patch the example's expected output in place. PATCH semantics:
|
|
276
276
|
# every flag you omit is left alone.
|
|
@@ -3,15 +3,15 @@
|
|
|
3
3
|
Three tools cover most cases:
|
|
4
4
|
|
|
5
5
|
```bash
|
|
6
|
-
eigenpal
|
|
7
|
-
eigenpal
|
|
8
|
-
eigenpal
|
|
6
|
+
eigenpal runs get <exec-id> # full payload, step-by-step
|
|
7
|
+
eigenpal runs watch <exec-id> # live status; 2s during transition / 5s steady
|
|
8
|
+
eigenpal runs compare <a> <b> # side-by-side diff of two runs
|
|
9
9
|
```
|
|
10
10
|
|
|
11
11
|
## 1. Reproduce the failure
|
|
12
12
|
|
|
13
13
|
```bash
|
|
14
|
-
eigenpal workflow
|
|
14
|
+
eigenpal workflow run <workflow-id> <example-name>
|
|
15
15
|
```
|
|
16
16
|
|
|
17
17
|
`<workflow-id>` is either a `wf_…` id or a slug (the YAML's `name:`
|
|
@@ -25,14 +25,14 @@ historical execution, skip the rerun and pull the recorded execution
|
|
|
25
25
|
directly:
|
|
26
26
|
|
|
27
27
|
```bash
|
|
28
|
-
eigenpal
|
|
29
|
-
eigenpal
|
|
28
|
+
eigenpal runs list <workflow-id> --type workflow --status failed --limit 5
|
|
29
|
+
eigenpal runs get exec_…
|
|
30
30
|
```
|
|
31
31
|
|
|
32
32
|
## 2. Pull the full execution
|
|
33
33
|
|
|
34
34
|
```bash
|
|
35
|
-
eigenpal
|
|
35
|
+
eigenpal runs get <exec-id>
|
|
36
36
|
```
|
|
37
37
|
|
|
38
38
|
The payload includes:
|
|
@@ -61,20 +61,21 @@ The payload includes:
|
|
|
61
61
|
Quick triage with `jq`:
|
|
62
62
|
|
|
63
63
|
```bash
|
|
64
|
-
eigenpal
|
|
65
|
-
| jq '.stepExecutions[] | { step: .stepName, status, error }'
|
|
64
|
+
eigenpal runs get <exec-id> --json \
|
|
65
|
+
| jq '.run.stepExecutions[] | { step: .stepName, status, error }'
|
|
66
66
|
```
|
|
67
67
|
|
|
68
68
|
Narrow to a single step:
|
|
69
69
|
|
|
70
70
|
```bash
|
|
71
|
-
eigenpal
|
|
71
|
+
eigenpal runs get <exec-id> --include input,output,error --json \
|
|
72
|
+
| jq '.run.stepExecutions[] | select(.stepName == "extract")'
|
|
72
73
|
```
|
|
73
74
|
|
|
74
75
|
Drill into one field:
|
|
75
76
|
|
|
76
77
|
```bash
|
|
77
|
-
eigenpal
|
|
78
|
+
eigenpal runs get <exec-id> --json | jq '.run.stepExecutions[2].output.totalAmount'
|
|
78
79
|
```
|
|
79
80
|
|
|
80
81
|
## 3. Common failure modes
|
|
@@ -151,7 +152,7 @@ path are created automatically.
|
|
|
151
152
|
## 4. Compare two executions
|
|
152
153
|
|
|
153
154
|
```bash
|
|
154
|
-
eigenpal
|
|
155
|
+
eigenpal runs compare <exec-a> <exec-b>
|
|
155
156
|
```
|
|
156
157
|
|
|
157
158
|
Output: per-step status / Δ duration / output diff. Useful for spotting
|
|
@@ -160,17 +161,17 @@ regressions between revisions of a workflow.
|
|
|
160
161
|
For a freer-form diff, dump both and compare with `jq`:
|
|
161
162
|
|
|
162
163
|
```bash
|
|
163
|
-
eigenpal
|
|
164
|
-
eigenpal
|
|
164
|
+
eigenpal runs get <exec-a> > a.json
|
|
165
|
+
eigenpal runs get <exec-b> > b.json
|
|
165
166
|
diff <(jq -S . a.json) <(jq -S . b.json)
|
|
166
167
|
```
|
|
167
168
|
|
|
168
169
|
## 5. Cancel a long-running execution
|
|
169
170
|
|
|
170
171
|
```bash
|
|
171
|
-
eigenpal
|
|
172
|
-
eigenpal
|
|
173
|
-
eigenpal
|
|
172
|
+
eigenpal runs cancel <exec-id> # TTY: silent
|
|
173
|
+
eigenpal runs cancel <exec-id> --yes # CI / pipes
|
|
174
|
+
eigenpal runs cancel <exec-id> --json # raw server payload
|
|
174
175
|
```
|
|
175
176
|
|
|
176
177
|
The worker finishes the current step, then stops — the cancellation
|
|
@@ -274,7 +275,7 @@ The terminal `--watch` output looks like:
|
|
|
274
275
|
✗ 7/7 did not pass
|
|
275
276
|
|
|
276
277
|
invoice-2025-001 [failed] template_resolution_failed at step `parse`: …
|
|
277
|
-
eigenpal
|
|
278
|
+
eigenpal runs get exec_…
|
|
278
279
|
…
|
|
279
280
|
|
|
280
281
|
ℹ step-level errors live on `stepExecutions[].error` — see reference/debugging.md.
|
|
@@ -287,11 +288,11 @@ detail (which step failed, what input it received, what output it
|
|
|
287
288
|
returned before erroring) follow the suggested command:
|
|
288
289
|
|
|
289
290
|
```bash
|
|
290
|
-
eigenpal
|
|
291
|
-
eigenpal
|
|
292
|
-
eigenpal
|
|
291
|
+
eigenpal runs get exec_… # full payload
|
|
292
|
+
eigenpal runs get exec_… --include input,output,error --json | jq '.run.stepExecutions[] | select(.stepName == "<name>")'
|
|
293
|
+
eigenpal runs get exec_… --json | jq -r '.run.stepExecutions[0].error'
|
|
293
294
|
```
|
|
294
295
|
|
|
295
|
-
For per-execution live view, `eigenpal
|
|
296
|
+
For per-execution live view, `eigenpal runs watch <exec-id>` does
|
|
296
297
|
adaptive polling (2 s while transitioning, 5 s when steady) and prints
|
|
297
298
|
ASCII status badges that work in any terminal.
|
|
@@ -20,7 +20,7 @@ Until EIG-104 lands, single-step iteration goes through the queue:
|
|
|
20
20
|
|
|
21
21
|
```bash
|
|
22
22
|
# Run the whole workflow once with a specific example.
|
|
23
|
-
eigenpal workflow
|
|
23
|
+
eigenpal workflow run <workflow-id>
|
|
24
24
|
|
|
25
25
|
# Or iterate on one example via the experiment surface.
|
|
26
26
|
eigenpal workflow experiment run <workflow-id> --example-id <name>
|
|
@@ -36,7 +36,7 @@ To inspect what a step actually produced (input / output / resolved
|
|
|
36
36
|
config), use:
|
|
37
37
|
|
|
38
38
|
```bash
|
|
39
|
-
eigenpal
|
|
39
|
+
eigenpal runs get <executionId> --json --include input,output,config
|
|
40
40
|
```
|
|
41
41
|
|
|
42
42
|
The server returns `inputData` / `outputData` / `resolvedConfig` per
|
|
@@ -47,7 +47,7 @@ names (`input` / `output` / `config`).
|
|
|
47
47
|
|
|
48
48
|
| Code | When |
|
|
49
49
|
| --- | --- |
|
|
50
|
-
| 2 | Always — the command is disabled and redirects to `workflow
|
|
50
|
+
| 2 | Always — the command is disabled and redirects to `workflow run` / `experiment run`. |
|
|
51
51
|
|
|
52
52
|
## When this comes back
|
|
53
53
|
|
|
@@ -38,11 +38,11 @@ folder.
|
|
|
38
38
|
|
|
39
39
|
Required. Each entry is an object that adds an invocation surface:
|
|
40
40
|
|
|
41
|
-
- `{ type: api }` — the workflow can be called via REST or the CLI's `workflow
|
|
41
|
+
- `{ type: api }` — the workflow can be called via REST or the CLI's `workflow run`
|
|
42
42
|
- `{ type: manual }` — the workflow can be started manually
|
|
43
43
|
- `{ type: email, whitelist?: ... }` — inbound email
|
|
44
44
|
|
|
45
|
-
If `{ type: api }` is missing, `eigenpal workflow
|
|
45
|
+
If `{ type: api }` is missing, `eigenpal workflow run` rejects with a
|
|
46
46
|
403 / "Workflow does not have API trigger enabled."
|
|
47
47
|
|
|
48
48
|
### `inputs`
|
|
@@ -8,7 +8,7 @@ then run:
|
|
|
8
8
|
eigenpal workflow validate
|
|
9
9
|
|
|
10
10
|
# Run an example end-to-end against the configured base URL
|
|
11
|
-
eigenpal workflow
|
|
11
|
+
eigenpal workflow run __NAME__ sample
|
|
12
12
|
```
|
|
13
13
|
|
|
14
14
|
Add more examples under `dataset/examples/<name>/`. Each example needs an
|
|
@@ -9,7 +9,7 @@ fixed JSON schema.
|
|
|
9
9
|
|
|
10
10
|
1. Drop a sample PDF at `dataset/examples/sample-invoice/input/document/<filename>`.
|
|
11
11
|
2. Adjust the `extract.with.schema` to the fields your documents actually carry.
|
|
12
|
-
3. Run an example: `eigenpal workflow
|
|
12
|
+
3. Run an example: `eigenpal workflow run __NAME__ sample-invoice`.
|
|
13
13
|
4. When the output looks right, push: `eigenpal workflow push --file workflow.yaml`.
|
|
14
14
|
|
|
15
15
|
## Extending
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
# __NAME__
|
|
2
2
|
|
|
3
3
|
A text classification workflow scaffolded by `eigenpal init workflow`. Two examples
|
|
4
|
-
are pre-seeded so you can immediately run `eigenpal workflow
|
|
4
|
+
are pre-seeded so you can immediately run `eigenpal workflow run __NAME__` and see
|
|
5
5
|
end-to-end behavior.
|
|
6
6
|
|
|
7
7
|
The eval config asserts on the `label` path only — confidence/rationale are
|