@eigenpal/cli 0.23.6 → 0.23.7
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 +17 -0
- package/dist/cli.js +1148 -1341
- package/dist/docs-bundle.json +23 -23
- package/dist/skill/SKILL.md +0 -1
- package/dist/skill/reference/cli/surface.md +1 -3
- package/dist/skill/reference/cli/workflow.md +1 -30
- package/dist/skill/reference/dataset-format.md +10 -10
- package/dist/skill/reference/debugging.md +1 -1
- package/dist/skill/reference/evaluators.md +9 -9
- package/dist/skill/reference/step-types.md +44 -44
- package/dist/skill/reference/workflow-yaml.md +3 -110
- package/package.json +2 -1
- package/dist/skill/reference/step-exec.md +0 -62
package/dist/skill/SKILL.md
CHANGED
|
@@ -570,7 +570,6 @@ Workflow and eval references:
|
|
|
570
570
|
|
|
571
571
|
- [`reference/workflow-yaml.md`](reference/workflow-yaml.md)
|
|
572
572
|
- [`reference/step-types.md`](reference/step-types.md)
|
|
573
|
-
- [`reference/step-exec.md`](reference/step-exec.md)
|
|
574
573
|
- [`reference/dataset-format.md`](reference/dataset-format.md)
|
|
575
574
|
- [`reference/evaluators.md`](reference/evaluators.md)
|
|
576
575
|
- [`reference/debugging.md`](reference/debugging.md)
|
|
@@ -15,7 +15,6 @@ Manage workflows: push, pull, and evaluate.
|
|
|
15
15
|
- [Versions](#versions)
|
|
16
16
|
- [Step-type](#step-type)
|
|
17
17
|
- [Evaluator-type](#evaluator-type)
|
|
18
|
-
- [Step](#step)
|
|
19
18
|
- [Details](#details)
|
|
20
19
|
- [`eigenpal workflow list|ls [options]`](#eigenpal-workflow-listls-options)
|
|
21
20
|
- [`eigenpal workflow get [options] <workflow-id>`](#eigenpal-workflow-get-options-workflow-id)
|
|
@@ -72,7 +71,6 @@ Manage workflows: push, pull, and evaluate.
|
|
|
72
71
|
- [`eigenpal workflow step-type get [options] <type>`](#eigenpal-workflow-step-type-get-options-type)
|
|
73
72
|
- [`eigenpal workflow evaluator-type list|ls [options]`](#eigenpal-workflow-evaluator-type-listls-options)
|
|
74
73
|
- [`eigenpal workflow evaluator-type get [options] <type>`](#eigenpal-workflow-evaluator-type-get-options-type)
|
|
75
|
-
- [`eigenpal workflow step exec [options] <type>`](#eigenpal-workflow-step-exec-options-type)
|
|
76
74
|
|
|
77
75
|
## Surface
|
|
78
76
|
|
|
@@ -142,9 +140,7 @@ workflow
|
|
|
142
140
|
│ ├── list|ls
|
|
143
141
|
│ └── get <type>
|
|
144
142
|
├── validate [path]
|
|
145
|
-
|
|
146
|
-
└── step
|
|
147
|
-
└── exec <type>
|
|
143
|
+
└── clear-local [examples...]
|
|
148
144
|
```
|
|
149
145
|
|
|
150
146
|
## Commands
|
|
@@ -249,12 +245,6 @@ workflow
|
|
|
249
245
|
| `eigenpal workflow evaluator-type list\|ls [options]` | List every evaluator type with a one-line description. |
|
|
250
246
|
| `eigenpal workflow evaluator-type get [options] <type>` | Fetch the JSON Schema for one evaluator type. Pipe through `jq` to inspect specific fields. |
|
|
251
247
|
|
|
252
|
-
### Step
|
|
253
|
-
|
|
254
|
-
| Command | Description |
|
|
255
|
-
| ---------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------ |
|
|
256
|
-
| `eigenpal workflow step exec [options] <type>` | DISABLED — local mimic runners removed pending server-side redesign (EIG-104). Use `run` or `workflow experiment run` instead. |
|
|
257
|
-
|
|
258
248
|
## Details
|
|
259
249
|
|
|
260
250
|
### `eigenpal workflow list|ls [options]`
|
|
@@ -1276,22 +1266,3 @@ Fetch the JSON Schema for one evaluator type. Pipe through `jq` to inspect speci
|
|
|
1276
1266
|
| Flag | Required | Default | Description |
|
|
1277
1267
|
| -------------- | -------- | ------- | ------------- |
|
|
1278
1268
|
| `--out <path>` | no | | Write to file |
|
|
1279
|
-
|
|
1280
|
-
### `eigenpal workflow step exec [options] <type>`
|
|
1281
|
-
|
|
1282
|
-
DISABLED — local mimic runners removed pending server-side redesign (EIG-104). Use `run` or `workflow experiment run` instead.
|
|
1283
|
-
|
|
1284
|
-
### Arguments
|
|
1285
|
-
|
|
1286
|
-
| Name | Required | Variadic | Description |
|
|
1287
|
-
| ------ | -------- | -------- | ----------- |
|
|
1288
|
-
| `type` | yes | no | |
|
|
1289
|
-
|
|
1290
|
-
### Options
|
|
1291
|
-
|
|
1292
|
-
| Flag | Required | Default | Description |
|
|
1293
|
-
| ------------------------ | -------- | ------- | -------------------------------------- |
|
|
1294
|
-
| `--config-json <json>` | no | | (unused; kept for back-compat parsing) |
|
|
1295
|
-
| `--config-file <path>` | no | | (unused) |
|
|
1296
|
-
| `--inputs <pairs...>` | no | | (unused) |
|
|
1297
|
-
| `--output-schema <path>` | no | | (unused) |
|
|
@@ -394,16 +394,16 @@ agent automations.
|
|
|
394
394
|
<!-- GENERATED:DATASET_REFERENCE START -->
|
|
395
395
|
## Schema reference
|
|
396
396
|
|
|
397
|
-
_Generated from `@eigenpal/types/src/eval/dataset-archive.ts`, `expected-error.ts`, and `scoped-file-ref.ts`. Do not hand-edit between the GENERATED fences
|
|
397
|
+
_Generated from `@eigenpal/types/src/eval/dataset-archive.ts`, `expected-error.ts`, and `scoped-file-ref.ts`. Do not hand-edit between the GENERATED fences: run `bun run --cwd packages/cli generate:skill`._
|
|
398
398
|
|
|
399
399
|
### Archive layout (canonical)
|
|
400
400
|
|
|
401
401
|
```text
|
|
402
|
-
examples/<name>/input.json REQUIRED
|
|
403
|
-
examples/<name>/input/<file> OPTIONAL
|
|
404
|
-
examples/<name>/expected.json OPTIONAL
|
|
405
|
-
examples/<name>/expected/<file> OPTIONAL
|
|
406
|
-
examples/<name>/meta.json OPTIONAL
|
|
402
|
+
examples/<name>/input.json REQUIRED: full run input object
|
|
403
|
+
examples/<name>/input/<file> OPTIONAL: referenced from input.json
|
|
404
|
+
examples/<name>/expected.json OPTIONAL: success output or `{ "$error": ... }`
|
|
405
|
+
examples/<name>/expected/<file> OPTIONAL: referenced from expected.json
|
|
406
|
+
examples/<name>/meta.json OPTIONAL: see `DatasetMetaSchema` below
|
|
407
407
|
```
|
|
408
408
|
|
|
409
409
|
Importers reject any archive containing a top-level `manifest.json` (legacy layout). Example folder names must match:
|
|
@@ -419,11 +419,11 @@ Importers reject any archive containing a top-level `manifest.json` (legacy layo
|
|
|
419
419
|
|
|
420
420
|
Input files live under `input/` and are referenced as `{ "$file": "input/<path>" }`. Expected files use the `expected/` prefix in `expected.json`.
|
|
421
421
|
|
|
422
|
-
### `expected.json
|
|
422
|
+
### `expected.json`: success-expected output
|
|
423
423
|
|
|
424
424
|
When grading success, `expected.json` is a JSON object mirroring the workflow `output:` shape. File values use `{ "$file": "expected/<path>" }`.
|
|
425
425
|
|
|
426
|
-
### `expected.json
|
|
426
|
+
### `expected.json`: failure-expected (`$error`)
|
|
427
427
|
|
|
428
428
|
Failure-expected examples store a single top-level `$error` object. At least one of `code`, `messageContains`, or `step` is required:
|
|
429
429
|
|
|
@@ -448,8 +448,8 @@ Failure-expected examples store a single top-level `$error` object. At least one
|
|
|
448
448
|
|
|
449
449
|
Allowed values: `"append"` \| `"replace"`
|
|
450
450
|
|
|
451
|
-
- `append
|
|
452
|
-
- `replace
|
|
451
|
+
- `append`: add examples to the existing dataset.
|
|
452
|
+
- `replace`: wipe existing examples and import the archive fresh.
|
|
453
453
|
|
|
454
454
|
### Validation rules enforced at import
|
|
455
455
|
|
|
@@ -215,7 +215,7 @@ eigenpal runs cancel <exec-id> --json # raw server payload
|
|
|
215
215
|
|
|
216
216
|
The worker finishes the current step, then stops — the cancellation
|
|
217
217
|
check happens between every step transition, including inside
|
|
218
|
-
`control.foreach` / `control.parallel`
|
|
218
|
+
`control.foreach` / `control.parallel` bodies.
|
|
219
219
|
Behavior by current state:
|
|
220
220
|
|
|
221
221
|
- `created` / `pending` — transitions straight to `cancelled`.
|
|
@@ -311,9 +311,9 @@ LLM-judge scores have variance. To reduce flake:
|
|
|
311
311
|
- For high-stakes thresholds, run the experiment ≥3 times and average.
|
|
312
312
|
|
|
313
313
|
<!-- GENERATED:EVALUATOR_CATALOG START -->
|
|
314
|
-
## Evaluator types
|
|
314
|
+
## Evaluator types: full reference
|
|
315
315
|
|
|
316
|
-
_Generated from `EvalConfigYamlSchema` in `@eigenpal/types/src/eval/evaluator-config.ts`. Do not hand-edit between the GENERATED fences
|
|
316
|
+
_Generated from `EvalConfigYamlSchema` in `@eigenpal/types/src/eval/evaluator-config.ts`. Do not hand-edit between the GENERATED fences: run `bun run --cwd packages/cli generate:skill`._
|
|
317
317
|
|
|
318
318
|
### Top-level `evaluators.yaml`
|
|
319
319
|
|
|
@@ -330,10 +330,10 @@ _Generated from `EvalConfigYamlSchema` in `@eigenpal/types/src/eval/evaluator-co
|
|
|
330
330
|
| `description` | string | no | | One-sentence explanation, in business language, of what this evaluator measures and why a stakeholder should care. Shown in the dashboard to non-technical reviewers (legal, ops, finance) who never see the YAML or judge prompt. Skip implementation detail (model names, thresholds, dot-paths); those live in `config`. |
|
|
331
331
|
| `weight` | number | no | `1` | Relative importance in the weighted mean. The overall score is Σ(weightᵢ × scoreᵢ) / Σweight. Set to 0 to score-only without affecting overall. |
|
|
332
332
|
|
|
333
|
-
- `type
|
|
334
|
-
- `config
|
|
333
|
+
- `type`: required discriminator: `exact-diff`, `llm-judge`, `custom-script`.
|
|
334
|
+
- `config`: required object whose fields are defined by the selected evaluator type below.
|
|
335
335
|
|
|
336
|
-
### `exact-diff
|
|
336
|
+
### `exact-diff`: JSON deep-diff against expected output
|
|
337
337
|
|
|
338
338
|
| Field | Type | Required | Default | Description |
|
|
339
339
|
| --- | --- | --- | --- | --- |
|
|
@@ -356,7 +356,7 @@ _Generated from `EvalConfigYamlSchema` in `@eigenpal/types/src/eval/evaluator-co
|
|
|
356
356
|
| `numericTolerance` | number | no | | Maximum absolute difference for numeric leaves at or under this path. Omitted = inherit, then historical relative epsilon. Explicit `0` is exact. |
|
|
357
357
|
|
|
358
358
|
|
|
359
|
-
### `llm-judge
|
|
359
|
+
### `llm-judge`: LLM-as-judge scoring
|
|
360
360
|
|
|
361
361
|
| Field | Type | Required | Default | Description |
|
|
362
362
|
| --- | --- | --- | --- | --- |
|
|
@@ -365,11 +365,11 @@ _Generated from `EvalConfigYamlSchema` in `@eigenpal/types/src/eval/evaluator-co
|
|
|
365
365
|
| `mode` | `"continuous"` \| `"discrete"` | no | `"continuous"` | Continuous = the LLM returns a free-form score in [0, 1]. Discrete = the LLM picks one of your labels and the score is looked up from the table. |
|
|
366
366
|
| `labels` | record<string, number> | no | | Allowed labels and the score each maps to. Required in discrete mode. The judge MUST return one of these labels; each score must be in [0, 1]. |
|
|
367
367
|
| `passThreshold` | number | no | | Legacy per-evaluator pass threshold. Pass/fail now uses the single workflow-level pass threshold; this is read only to preserve the run gate of configs authored before the single-threshold model. |
|
|
368
|
-
| `promptExtension` | string | yes | | Required. Evaluation criteria appended to the judge prompt
|
|
368
|
+
| `promptExtension` | string | yes | | Required. Evaluation criteria appended to the judge prompt: describe what makes a good answer for this workflow (tone, completeness, edge cases). Cannot be empty: an empty prompt yields the model inventing its own criteria. |
|
|
369
369
|
| `docLabel` | string | no | `"output"` | Name the judge uses to refer to the output in its prompt (e.g. 'invoice', 'extraction'). Default is 'output'. |
|
|
370
370
|
|
|
371
371
|
|
|
372
|
-
### `custom-script
|
|
372
|
+
### `custom-script`: JavaScript in the sandbox
|
|
373
373
|
|
|
374
374
|
| Field | Type | Required | Default | Description |
|
|
375
375
|
| --- | --- | --- | --- | --- |
|
|
@@ -610,7 +610,7 @@ Generated from the same discriminated union used by evaluator validation; YAML k
|
|
|
610
610
|
"promptExtension": {
|
|
611
611
|
"type": "string",
|
|
612
612
|
"minLength": 10,
|
|
613
|
-
"description": "Required. Evaluation criteria appended to the judge prompt
|
|
613
|
+
"description": "Required. Evaluation criteria appended to the judge prompt: describe what makes a good answer for this workflow (tone, completeness, edge cases). Cannot be empty: an empty prompt yields the model inventing its own criteria."
|
|
614
614
|
},
|
|
615
615
|
"docLabel": {
|
|
616
616
|
"default": "output",
|
|
@@ -473,11 +473,11 @@ compose with `control.if` for legacy gating.
|
|
|
473
473
|
<!-- GENERATED:STEP_CATALOG START -->
|
|
474
474
|
## Full catalog
|
|
475
475
|
|
|
476
|
-
_Generated from `STEP_SCHEMAS` in `@eigenpal/types/src/workflow/step-configs.ts`. Do not hand-edit between the GENERATED fences
|
|
476
|
+
_Generated from `STEP_SCHEMAS` in `@eigenpal/types/src/workflow/step-configs.ts`. Do not hand-edit between the GENERATED fences: run `bun run --cwd packages/cli generate:skill`._
|
|
477
477
|
|
|
478
|
-
### AI steps
|
|
478
|
+
### AI steps: model-backed processing
|
|
479
479
|
|
|
480
|
-
#### `ai.parse-v2
|
|
480
|
+
#### `ai.parse-v2`: Parse Document
|
|
481
481
|
|
|
482
482
|
Automatically read native, scanned, and mixed documents with capability-aware OCR/vision fallback and explicit completeness.
|
|
483
483
|
|
|
@@ -1724,7 +1724,7 @@ Output schema:
|
|
|
1724
1724
|
```
|
|
1725
1725
|
|
|
1726
1726
|
|
|
1727
|
-
#### `ai.parse
|
|
1727
|
+
#### `ai.parse`: Parse Document v1
|
|
1728
1728
|
|
|
1729
1729
|
Parse Document v1, the retired parser, kept only so existing workflows run unchanged. Do not add it to workflows: use ai.parse-v2 (Parse Document), which picks native text, OCR or vision per page.
|
|
1730
1730
|
|
|
@@ -2785,7 +2785,7 @@ Output schema:
|
|
|
2785
2785
|
```
|
|
2786
2786
|
|
|
2787
2787
|
|
|
2788
|
-
#### `ai.extract
|
|
2788
|
+
#### `ai.extract`: Extract Data
|
|
2789
2789
|
|
|
2790
2790
|
Extract structured data from text using AI with a JSON schema
|
|
2791
2791
|
|
|
@@ -2976,7 +2976,7 @@ Output schema:
|
|
|
2976
2976
|
```
|
|
2977
2977
|
|
|
2978
2978
|
|
|
2979
|
-
#### `ai.split
|
|
2979
|
+
#### `ai.split`: Split Document
|
|
2980
2980
|
|
|
2981
2981
|
Split a parsed document into named sections using an LLM. Consumes ai.parse output; emits per-section page ranges and text ready for downstream ai.extract via control.parallel_map.
|
|
2982
2982
|
|
|
@@ -3446,7 +3446,7 @@ Output schema:
|
|
|
3446
3446
|
```
|
|
3447
3447
|
|
|
3448
3448
|
|
|
3449
|
-
#### `ai.segment
|
|
3449
|
+
#### `ai.segment`: Separate Documents
|
|
3450
3450
|
|
|
3451
3451
|
Separate a concatenated batch (one big scan) into typed document instances using an LLM. Consumes ai.parse output and a type taxonomy; discovers an unknown number of documents in any order and emits per-document page ranges + text + type, ready for type-specific ai.extract via control.parallel_map. The inverse of ai.split.
|
|
3452
3452
|
|
|
@@ -3811,7 +3811,7 @@ Output schema:
|
|
|
3811
3811
|
```
|
|
3812
3812
|
|
|
3813
3813
|
|
|
3814
|
-
#### `ai.classify
|
|
3814
|
+
#### `ai.classify`: Classify
|
|
3815
3815
|
|
|
3816
3816
|
Classify a document or text into one of a fixed label set using an LLM. Output exposes the picked label (constrained to the configured names), a coarse confidence, and a short justification. Pair with control.fail to reject documents that match an undesired label.
|
|
3817
3817
|
|
|
@@ -3951,7 +3951,7 @@ Output schema:
|
|
|
3951
3951
|
```
|
|
3952
3952
|
|
|
3953
3953
|
|
|
3954
|
-
#### `ai.classify-pages
|
|
3954
|
+
#### `ai.classify-pages`: Label Pages
|
|
3955
3955
|
|
|
3956
3956
|
Assign zero or more labels to each page independently (multi-label) using an LLM. Consumes ai.parse output; emits per-page labels and a byLabel map (label -> page indices) that supports NON-contiguous selections. Feed byLabel.<label> straight into ai.vision `pageIndices` to inspect scattered pages of a type (e.g. every signature or property-photo page).
|
|
3957
3957
|
|
|
@@ -4121,7 +4121,7 @@ Output schema:
|
|
|
4121
4121
|
```
|
|
4122
4122
|
|
|
4123
4123
|
|
|
4124
|
-
#### `ai.vision
|
|
4124
|
+
#### `ai.vision`: Inspect Pages (Vision)
|
|
4125
4125
|
|
|
4126
4126
|
Inspect rendered page images with a vision model and return structured JSON matching a schema. The visual counterpart to Extract Data: use it for conclusions that live in the pixels rather than the text (is the document signed? are the photos usable?). Renders PDF, image, or Office/Word inputs; route to specific pages with an ai.split page range to keep it cheap.
|
|
4127
4127
|
|
|
@@ -4355,7 +4355,7 @@ Output schema:
|
|
|
4355
4355
|
```
|
|
4356
4356
|
|
|
4357
4357
|
|
|
4358
|
-
#### `ai.search-files
|
|
4358
|
+
#### `ai.search-files`: Search Files
|
|
4359
4359
|
|
|
4360
4360
|
Investigate a ZIP archive with a question and return an answer plus file citations. Read-only: the step opens files in the archive and never writes back. ZIP is the only accepted format in this version. Optionally scope the search to a folder prefix and cap how many files and investigation turns may run.
|
|
4361
4361
|
|
|
@@ -4505,7 +4505,7 @@ Output schema:
|
|
|
4505
4505
|
```
|
|
4506
4506
|
|
|
4507
4507
|
|
|
4508
|
-
#### `ai.figure-crops
|
|
4508
|
+
#### `ai.figure-crops`: Figure Crops
|
|
4509
4509
|
|
|
4510
4510
|
Crop and caption figure elements from a parsed PDF. Renders the source document, crops each kind=figure bbox from ai.parse output, and describes the crop with a vision model. Output is captions plus normalized bboxes for evidence viewers.
|
|
4511
4511
|
|
|
@@ -4715,9 +4715,9 @@ Output schema:
|
|
|
4715
4715
|
```
|
|
4716
4716
|
|
|
4717
4717
|
|
|
4718
|
-
### Transform steps
|
|
4718
|
+
### Transform steps: deterministic data transforms
|
|
4719
4719
|
|
|
4720
|
-
#### `transform.set
|
|
4720
|
+
#### `transform.set`: Set Value
|
|
4721
4721
|
|
|
4722
4722
|
Set key-value pairs in the output object
|
|
4723
4723
|
|
|
@@ -4785,7 +4785,7 @@ Output schema:
|
|
|
4785
4785
|
```
|
|
4786
4786
|
|
|
4787
4787
|
|
|
4788
|
-
#### `transform.remove
|
|
4788
|
+
#### `transform.remove`: Remove Fields
|
|
4789
4789
|
|
|
4790
4790
|
Remove specified fields from an object
|
|
4791
4791
|
|
|
@@ -4853,7 +4853,7 @@ Output schema:
|
|
|
4853
4853
|
```
|
|
4854
4854
|
|
|
4855
4855
|
|
|
4856
|
-
#### `transform.combine
|
|
4856
|
+
#### `transform.combine`: Combine Data
|
|
4857
4857
|
|
|
4858
4858
|
Merge multiple objects or concatenate arrays
|
|
4859
4859
|
|
|
@@ -4937,7 +4937,7 @@ Output schema:
|
|
|
4937
4937
|
```
|
|
4938
4938
|
|
|
4939
4939
|
|
|
4940
|
-
#### `transform.split
|
|
4940
|
+
#### `transform.split`: Split Data
|
|
4941
4941
|
|
|
4942
4942
|
Split a string by delimiter or extract keys from an object
|
|
4943
4943
|
|
|
@@ -5056,7 +5056,7 @@ Output schema:
|
|
|
5056
5056
|
```
|
|
5057
5057
|
|
|
5058
5058
|
|
|
5059
|
-
#### `transform.merge
|
|
5059
|
+
#### `transform.merge`: Merge Inputs
|
|
5060
5060
|
|
|
5061
5061
|
Merge multiple named inputs into a single output
|
|
5062
5062
|
|
|
@@ -5141,7 +5141,7 @@ Output schema:
|
|
|
5141
5141
|
```
|
|
5142
5142
|
|
|
5143
5143
|
|
|
5144
|
-
#### `transform.template
|
|
5144
|
+
#### `transform.template`: Fill Template
|
|
5145
5145
|
|
|
5146
5146
|
Fill a DOCX or XLSX workspace template with data from previous steps. Reference a tmpl_... id, or a local ./templates/file.xlsx path (CLI push uploads it). Git agent templates use the fill-template skill instead and cannot be referenced here. File IDs (file_...) are not accepted. Placeholders are auto-detected. In the Office file use {placeholder} and {table:array.prop}; {{placeholder}} in an XLSX file is rejected ({{ }} is YAML Liquid only).
|
|
5147
5147
|
|
|
@@ -5241,7 +5241,7 @@ Output schema:
|
|
|
5241
5241
|
```
|
|
5242
5242
|
|
|
5243
5243
|
|
|
5244
|
-
#### `transform.pdf-embed
|
|
5244
|
+
#### `transform.pdf-embed`: Embed PDF Text
|
|
5245
5245
|
|
|
5246
5246
|
Embed OCR text layer into scanned PDFs/images to make them searchable
|
|
5247
5247
|
|
|
@@ -5340,7 +5340,7 @@ Output schema:
|
|
|
5340
5340
|
```
|
|
5341
5341
|
|
|
5342
5342
|
|
|
5343
|
-
#### `transform.crop-regions
|
|
5343
|
+
#### `transform.crop-regions`: Crop Regions
|
|
5344
5344
|
|
|
5345
5345
|
Render a PDF or image and crop normalized bounding boxes into JPEG run output artifacts. Pair with transform.script (bbox lists from ai.parse layout) and ai.extract or ai.vision for captions.
|
|
5346
5346
|
|
|
@@ -5602,7 +5602,7 @@ Output schema:
|
|
|
5602
5602
|
```
|
|
5603
5603
|
|
|
5604
5604
|
|
|
5605
|
-
#### `transform.xlsx-to-json
|
|
5605
|
+
#### `transform.xlsx-to-json`: Spreadsheet to JSON
|
|
5606
5606
|
|
|
5607
5607
|
Convert an XLS or XLSX spreadsheet to a JSON array of row objects. Supports headerless files, named or positional columns, displayed text, and a single rectangular range.
|
|
5608
5608
|
|
|
@@ -5997,7 +5997,7 @@ Output schema:
|
|
|
5997
5997
|
```
|
|
5998
5998
|
|
|
5999
5999
|
|
|
6000
|
-
#### `transform.json-to-xlsx
|
|
6000
|
+
#### `transform.json-to-xlsx`: JSON to XLSX
|
|
6001
6001
|
|
|
6002
6002
|
Convert JSON rows into an XLSX spreadsheet. Pair with transform.xlsx-to-json. Formula-looking strings stay text; nested cell values are rejected.
|
|
6003
6003
|
|
|
@@ -6270,7 +6270,7 @@ Output schema:
|
|
|
6270
6270
|
```
|
|
6271
6271
|
|
|
6272
6272
|
|
|
6273
|
-
#### `transform.script
|
|
6273
|
+
#### `transform.script`: Script
|
|
6274
6274
|
|
|
6275
6275
|
Execute a TypeScript function in a QuickJS sandbox. Input keys become function parameters in any order, and the required `: R` return-type annotation IS this step's output schema: `inputs: { items, taxRate }` accepts `function script(taxRate: …, items: …): R { … }`.
|
|
6276
6276
|
|
|
@@ -6347,7 +6347,7 @@ Output schema:
|
|
|
6347
6347
|
```
|
|
6348
6348
|
|
|
6349
6349
|
|
|
6350
|
-
#### `transform.text-chunker
|
|
6350
|
+
#### `transform.text-chunker`: Text Chunker
|
|
6351
6351
|
|
|
6352
6352
|
Split long text into chunks with regex-anchored boundaries, overlap, and header preservation. Accepts raw text or a parsed-document object; chunks carry source page indexes when pages are provided.
|
|
6353
6353
|
|
|
@@ -6579,7 +6579,7 @@ Output schema:
|
|
|
6579
6579
|
```
|
|
6580
6580
|
|
|
6581
6581
|
|
|
6582
|
-
#### `transform.regex-extract
|
|
6582
|
+
#### `transform.regex-extract`: Regex Extract
|
|
6583
6583
|
|
|
6584
6584
|
Pull named fields from text via regex patterns (deterministic counterpart to ai.extract). Accepts raw text or a parsed-document object; matches carry `_evidence.pageIndex` when pages are provided.
|
|
6585
6585
|
|
|
@@ -6780,7 +6780,7 @@ Output schema:
|
|
|
6780
6780
|
```
|
|
6781
6781
|
|
|
6782
6782
|
|
|
6783
|
-
#### `transform.archive-list
|
|
6783
|
+
#### `transform.archive-list`: List Archive
|
|
6784
6784
|
|
|
6785
6785
|
List files inside a ZIP archive. Returns sorted normalized paths with compressed and uncompressed sizes. Optionally filter by folder prefix or substring, then page with offset and limit. ZIP is the only accepted format in this version. Pair with foreach or parallel_map and transform.archive-extract to open individual files.
|
|
6786
6786
|
|
|
@@ -6902,7 +6902,7 @@ Output schema:
|
|
|
6902
6902
|
```
|
|
6903
6903
|
|
|
6904
6904
|
|
|
6905
|
-
#### `transform.archive-extract
|
|
6905
|
+
#### `transform.archive-extract`: Extract Archive File
|
|
6906
6906
|
|
|
6907
6907
|
Extract exactly one file from a ZIP archive and store it as a run output file. Downstream steps can pass {{ steps.extract.output }} into Parse, Vision, or another archive step. Nested ZIPs are stored as ZIP files, not unpacked. Each extraction is capped at 64 MiB. ZIP is the only accepted format in this version.
|
|
6908
6908
|
|
|
@@ -6998,7 +6998,7 @@ Output schema:
|
|
|
6998
6998
|
```
|
|
6999
6999
|
|
|
7000
7000
|
|
|
7001
|
-
#### `transform.merge-documents
|
|
7001
|
+
#### `transform.merge-documents`: Merge Documents
|
|
7002
7002
|
|
|
7003
7003
|
Concatenate several files into one PDF run output, in order. Accepts PDFs, images (multi-page TIFF included) and Word, PowerPoint, OpenDocument or RTF documents. Use it when one logical document arrives as several uploads: pass {{ steps.merge.output.file }} into Parse so page labels, page ranges and vision page indices stay continuous across every source. Output sources[] maps each input file to its merged page range.
|
|
7004
7004
|
|
|
@@ -7152,9 +7152,9 @@ Output schema:
|
|
|
7152
7152
|
```
|
|
7153
7153
|
|
|
7154
7154
|
|
|
7155
|
-
### Action steps
|
|
7155
|
+
### Action steps: external side effects
|
|
7156
7156
|
|
|
7157
|
-
#### `action.http
|
|
7157
|
+
#### `action.http`: HTTP Request
|
|
7158
7158
|
|
|
7159
7159
|
Make an HTTP request to an external API
|
|
7160
7160
|
|
|
@@ -7285,7 +7285,7 @@ Output schema:
|
|
|
7285
7285
|
```
|
|
7286
7286
|
|
|
7287
7287
|
|
|
7288
|
-
#### `action.invoke-workflow
|
|
7288
|
+
#### `action.invoke-workflow`: Invoke Workflow
|
|
7289
7289
|
|
|
7290
7290
|
Execute another workflow and return its output
|
|
7291
7291
|
|
|
@@ -7395,7 +7395,7 @@ Output schema:
|
|
|
7395
7395
|
```
|
|
7396
7396
|
|
|
7397
7397
|
|
|
7398
|
-
#### `action.website-reader
|
|
7398
|
+
#### `action.website-reader`: Website Reader
|
|
7399
7399
|
|
|
7400
7400
|
Fetch a webpage and convert content to markdown
|
|
7401
7401
|
|
|
@@ -7527,13 +7527,13 @@ Output schema:
|
|
|
7527
7527
|
```
|
|
7528
7528
|
|
|
7529
7529
|
|
|
7530
|
-
#### `action.email
|
|
7530
|
+
#### `action.email`: Send Email
|
|
7531
7531
|
|
|
7532
7532
|
Send an email with optional attachments via a selected email server. At most 10 recipients combined across to, cc, and bcc.
|
|
7533
7533
|
|
|
7534
7534
|
**Behavior and examples:** `eigenpal docs read steps/action/email`
|
|
7535
7535
|
|
|
7536
|
-
**Durable retry:**
|
|
7536
|
+
**Durable retry:** Supported only for failures where the provider did not accept the message: SMTP connection errors before the message is sent, and Resend network errors, rate limits and server failures (Resend dedupes on an idempotency key). A message that may have been accepted is never resent.
|
|
7537
7537
|
|
|
7538
7538
|
**Config** (in `step.with`):
|
|
7539
7539
|
|
|
@@ -7769,9 +7769,9 @@ Output schema:
|
|
|
7769
7769
|
```
|
|
7770
7770
|
|
|
7771
7771
|
|
|
7772
|
-
### Control steps
|
|
7772
|
+
### Control steps: flow control
|
|
7773
7773
|
|
|
7774
|
-
#### `control.if
|
|
7774
|
+
#### `control.if`: Condition
|
|
7775
7775
|
|
|
7776
7776
|
Branch execution based on a condition expression
|
|
7777
7777
|
|
|
@@ -7849,7 +7849,7 @@ Output schema:
|
|
|
7849
7849
|
```
|
|
7850
7850
|
|
|
7851
7851
|
|
|
7852
|
-
#### `control.switch
|
|
7852
|
+
#### `control.switch`: Switch
|
|
7853
7853
|
|
|
7854
7854
|
Multi-way routing: resolve an expression and run the first case whose value matches (else default). Cleaner than a nested control.if chain for routing an item to one of N pipelines by a discriminator field like a document type.
|
|
7855
7855
|
|
|
@@ -7957,7 +7957,7 @@ Output schema:
|
|
|
7957
7957
|
```
|
|
7958
7958
|
|
|
7959
7959
|
|
|
7960
|
-
#### `control.foreach
|
|
7960
|
+
#### `control.foreach`: For Each
|
|
7961
7961
|
|
|
7962
7962
|
Loop over an array and execute steps for each item
|
|
7963
7963
|
|
|
@@ -8045,7 +8045,7 @@ Output schema:
|
|
|
8045
8045
|
```
|
|
8046
8046
|
|
|
8047
8047
|
|
|
8048
|
-
#### `control.parallel_map
|
|
8048
|
+
#### `control.parallel_map`: Parallel Map
|
|
8049
8049
|
|
|
8050
8050
|
Iterate over an array with concurrent execution up to a limit
|
|
8051
8051
|
|
|
@@ -8141,7 +8141,7 @@ Output schema:
|
|
|
8141
8141
|
```
|
|
8142
8142
|
|
|
8143
8143
|
|
|
8144
|
-
#### `control.parallel
|
|
8144
|
+
#### `control.parallel`: Parallel
|
|
8145
8145
|
|
|
8146
8146
|
Execute multiple branches concurrently
|
|
8147
8147
|
|
|
@@ -8186,7 +8186,7 @@ Output schema:
|
|
|
8186
8186
|
```
|
|
8187
8187
|
|
|
8188
8188
|
|
|
8189
|
-
#### `control.wait
|
|
8189
|
+
#### `control.wait`: Wait
|
|
8190
8190
|
|
|
8191
8191
|
Pause workflow execution for a specified duration
|
|
8192
8192
|
|
|
@@ -8249,7 +8249,7 @@ Output schema:
|
|
|
8249
8249
|
```
|
|
8250
8250
|
|
|
8251
8251
|
|
|
8252
|
-
#### `control.human_review
|
|
8252
|
+
#### `control.human_review`: Human Review
|
|
8253
8253
|
|
|
8254
8254
|
Pause the run for selective field confirmation or correction, then continue with the reviewed data.
|
|
8255
8255
|
|
|
@@ -8695,7 +8695,7 @@ Output schema:
|
|
|
8695
8695
|
```
|
|
8696
8696
|
|
|
8697
8697
|
|
|
8698
|
-
#### `control.fail
|
|
8698
|
+
#### `control.fail`: Fail
|
|
8699
8699
|
|
|
8700
8700
|
Terminate the workflow with a typed status code + message. With an optional condition, only fails when the condition is truthy; otherwise always fails when reached. Pair with ai.classify or any prior step to fail fast on bad inputs.
|
|
8701
8701
|
|