@eigenpal/cli 0.10.7 → 0.10.9

package/dist/skill/SKILL.md

@@ -49,6 +49,10 @@ eigenpal workflow step-type get ai.extract --json | jq '.configSchema.properties
 
 # Validate and push.
 eigenpal workflow validate ./workflow.yaml
+# If the workflow has action.invoke-workflow steps, local validation cannot
+# resolve their targets (sibling workflows live in the server DB). Add --online
+# to check invoke targets, input types, and cycles before pushing.
+eigenpal workflow validate ./workflow.yaml --online
 eigenpal workflow push --file workflow.yaml
 
 # Run with ad-hoc input and read the output (use this for API-triggered workflows).

package/dist/skill/reference/evaluators.md

@@ -249,7 +249,7 @@ _Generated from `EvalConfigYamlSchema` in `@eigenpal/types/src/eval/evaluator-co
 | Field | Type | Required | Default | Description |
 | --- | --- | --- | --- | --- |
 | `evaluators` | array<object> | no | `[]` |  |
-| `passThreshold` | number | no | `0.7` |  |
+| `passThreshold` | number | no |  |  |
 
 ### Common entry fields (every evaluator type)
 
@@ -265,7 +265,7 @@ _Generated from `EvalConfigYamlSchema` in `@eigenpal/types/src/eval/evaluator-co
 | --- | --- | --- | --- | --- |
 | `numericTolerance` | number | no | `0.000001` | Maximum absolute difference between numeric values that still counts as equal. Use 1e-6 for floats, 0 for exact integer match. |
 | `allowExtraFields` | boolean | no | `true` | When on, extra fields in the actual output do not fail the diff. Off = actual must match expected exactly. |
-| `passThreshold` | number | no | `1` | Minimum diff score this evaluator must reach for a run to pass. 1.0 = perfect match required. |
+| `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. |
 | `paths` | array<string> | no |  | Dot-paths to scope the diff to a subset of the expected tree. Empty = diff entire expected. Syntax: `header.id`, `lineItems[].total`, `lineItems[0].sku`. Use this when expected has noisy sections you do not want to score. |
 
 
@@ -276,7 +276,7 @@ _Generated from `EvalConfigYamlSchema` in `@eigenpal/types/src/eval/evaluator-co
 | `model` | string | no |  | Which LLM grades the output. Falls back to the workspace's default LLM provider when unset. |
 | `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. |
 | `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]. |
-| `passThreshold` | number | no | `0.7` | Minimum judge score this evaluator must reach for a run to pass. |
+| `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. |
 | `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. |
 | `docLabel` | string | no | `"output"` | Name the judge uses to refer to the output in its prompt (e.g. 'invoice', 'extraction'). Default is 'output'. |
 
@@ -288,5 +288,5 @@ _Generated from `EvalConfigYamlSchema` in `@eigenpal/types/src/eval/evaluator-co
 | `function` | string | yes |  | Full TypeScript source for optional `type` aliases plus `function scoreScript(expected, actual): number { ... }`. Receives `expected` (the example's expected output) and `actual` (the workflow's actual output), returns a number in [0, 1] (the `: number` annotation is required). The `: number` return-type annotation is required and enforced at parse time. Throws are caught and scored as 0. |
 | `timeoutMs` | integer | no | `5000` | Maximum wall-clock time the script can run before it is killed and the run is marked failed. |
 | `memoryLimitMb` | integer | no | `10` | Maximum memory the sandbox may allocate. Increase if the script processes large arrays or strings. |
-| `passThreshold` | number | no | `1` | Minimum script score this evaluator must reach for a run to pass. |
+| `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. |
 <!-- GENERATED:EVALUATOR_CATALOG END -->

package/dist/skill/reference/step-types.md

@@ -390,6 +390,10 @@ Extract structured data from text using AI with a JSON schema
 | `provider` | string | no |  | Provider ID (e.g., "openai-gpt4o") |
 | `model` | string | no |  | Model override |
 | `maxInputTokens` | integer | no |  | Max input tokens. Truncates input text and logs a warning when exceeded. Omit for no limit. |
+| `grounded` | boolean | no |  | Optional. When true, adds a grounding pass: each schema field gets a source span + confidence (high=verbatim, medium=fuzzy, low=ungrounded) under a `_grounding` key, and ungrounded/fuzzy fields are flagged for human review. Grounding always calls OpenAI directly (independent of the extract provider) and requires OPENAI_API_KEY. Values stay the reliable schema-typed ones. |
+| `groundingModel` | string | no |  | Provider/model for the grounding pass. Defaults to the workspace default LLM; grounding runs against OpenAI, so pick an OpenAI-compatible model. |
+| `groundingExamples` | array<object> | no |  | Optional few-shot examples pinning grounding to verbatim source text per field. |
+| `reviewOn` | `"medium_or_low"` \| `"low_only"` | no |  | Which grounding confidences flag a field for review. Default: medium_or_low. |
 
 **Output:** `record<string, unknown>`
 
@@ -415,6 +419,27 @@ Split a parsed document into named sections using an LLM. Consumes ai.parse outp
 | --- | --- | --- | --- | --- |
 | `splits` | array<object> | yes |  | Sections found in the document, in page order. Absent sections are omitted. |
 
+#### `ai.segment` — Separate Documents
+
+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.
+
+**Config** (in `step.with`):
+
+| Field | Type | Required | Default | Description |
+| --- | --- | --- | --- | --- |
+| `input` | string | yes |  | Template expression resolving to ai.parse output, e.g. "{{ steps.parse.output }}" |
+| `documentTypes` | array<object> | yes |  | The document-type taxonomy. The LLM tags each detected document with one of these names, or the reserved "unknown" type when none fit. |
+| `rules` | string | no |  | Optional natural-language rules appended to the system prompt. |
+| `provider` | string | no |  | Provider ID from eigenpal.config.yaml. Falls back to the tenant default LLM provider when omitted. |
+| `windowTokenBudget` | integer | no |  | Override the per-window token ceiling. Defaults to env SPLIT_WINDOW_TOKEN_BUDGET or 20000. |
+
+**Output:** `object`
+
+| Field | Type | Required | Default | Description |
+| --- | --- | --- | --- | --- |
+| `summary` | object | yes |  | Batch-level escalation summary: labelled vs unlabelled counts + docs needing review. |
+| `documents` | array<object> | yes |  | Documents discovered in the batch, in page order. The full batch is covered. |
+
 #### `ai.classify` — Classify
 
 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.
@@ -732,6 +757,25 @@ Branch execution based on a condition expression
 | `branch` | `"then"` \| `"else"` | yes |  | Which branch was executed |
 | `result` | unknown | yes |  | Output from executed branch |
 
+#### `control.switch` — Switch
+
+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.
+
+**Config** (at step level):
+
+| Field | Type | Required | Default | Description |
+| --- | --- | --- | --- | --- |
+| `on` | string | yes |  | Template expression whose resolved value selects the case, e.g. "{{ doc.type }}". |
+| `cases` | array<object> | yes |  | Ordered cases; the first whose `when` matches runs. Each case has its own `steps`. |
+
+**Output:** `object`
+
+| Field | Type | Required | Default | Description |
+| --- | --- | --- | --- | --- |
+| `matched` | string \| number \| boolean \| null | yes |  | The `when` value that matched, or null when the default (or no) branch ran. |
+| `branch` | `"case"` \| `"default"` \| `"none"` | yes |  | Which branch executed. |
+| `result` | unknown | yes |  | Output from the executed branch (its last step). |
+
 #### `control.foreach` — For Each
 
 Loop over an array and execute steps for each item

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@eigenpal/cli",
-  "version": "0.10.7",
+  "version": "0.10.9",
   "description": "Eigenpal CLI — author and run document workflows from your terminal. Agent-ready.",
   "keywords": [
     "eigenpal",