@grepr/cli 1.11.6-eb60d62 → 1.11.7-2d91dbf

package/build/dist/openapi-docs/schemas/PatternMatcher.md

@@ -4,6 +4,10 @@
 
 ## Properties
 
+- name: attributeTokenization (optional)
+  type: enum: `KEYS_ONLY`, `KEYS_AND_VALUES`
+  description: Use attribute shape only, or shape and whole-value similarity tokens.
+
 - name: delimiters (required)
   type: array of string
   description: Characters to use for splitting tokens.
@@ -16,6 +20,14 @@
   type: array of string
   description: Masks that are enabled for tokenizing messages.
 
+- name: excludedAttributePrefixes (optional)
+  type: array of array of string
+  description: Excluded attribute prefixes as arrays of literal key segments. Does not affect partition-by values or output attributes.
+
+- name: includedAttributePrefixes (optional)
+  type: array of array of string
+  description: Included attribute prefixes as arrays of literal key segments. Empty selects all. Array elements are traversed without indices.
+
 - name: masks (required)
   type: array of array of string
   description: Set of masks that can be applied to messages before tokenizing them. These masks are specified as pairs of (name, regex).
@@ -37,6 +49,10 @@
   type: number
   description: Controls how close a set of tokens are to a pattern before it is considered a match. Calculated as the percent of matching tokens between a pattern and a message.
 
+- name: tokenizationInput (optional)
+  type: enum: `MESSAGE_ONLY`, `ATTRIBUTES_ONLY`, `MESSAGE_AND_ATTRIBUTES`, `AUTO`
+  description: Selects message text, attributes, both, or message text with an attributes fallback.
+
 - name: type (required)
   type: enum: `pattern-matcher`
   description: Matches log patterns using an iterative feedback loop. Events with known patterns skip the global reducer for improved efficiency.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@grepr/cli",
-  "version": "1.11.6-eb60d62",
+  "version": "1.11.7-2d91dbf",
   "description": "Official Grepr CLI tool for submitting synchronous batch jobs with OAuth authentication",
   "main": "build/dist/grepr.js",
   "type": "module",

package/build/dist/docs-index/00b1368c-5d7a-44cc-b31d-a1bb14e0a94c.txt

@@ -1,43 +0,0 @@
-# LlmPromptResultsIcebergTableSource
-
-**Type**: `object`
-
-## Properties
-
-- name: datasetId (required)
-  type: string
-  description: The ID of the dataset to read data from.
-
-- name: end (required)
-  type: string
-  description: End of time interval to query data for.
-
-- name: limit (optional)
-  type: integer
-  description: The maximum number of rows to process
-
-- name: name (required)
-  type: string
-
-- name: offset (optional)
-  type: integer
-  description: Offset on the number of rows to process
-
-- name: query (required)
-  type: `query`
-
-- name: sortOrder (optional)
-  type: enum: `ASCENDING`, `DESCENDING`, `UNSORTED`
-  description: The order in which the rows should be sorted by
-
-- name: start (required)
-  type: string
-  description: Start of time interval to query data for.
-
-- name: type (required)
-  type: enum: `llm-prompt-results-iceberg-table-source`
-  description: Reads LLM prompt results from an Iceberg table for processing.
-
-- name: variables (optional)
-  type: object
-  description: Variables that can be used to modify the query while parsed

package/build/dist/docs-index/068baa5d-1f8e-4e2b-a522-9322810bb1e0.txt

@@ -1,11 +0,0 @@
-# Simple
-
-Simple workflow that sends the log event directly to the LLM.
-
-**Type**: `object`
-
-## Properties
-
-- name: type (required)
-  type: enum: `simple`
-  description: Simple workflow that sends the log event directly to the LLM.

package/build/dist/docs-index/16dae2a3-9ab0-44e6-8564-469bb2e96192.txt

@@ -1,61 +0,0 @@
-# LlmPrompt
-
-**Type**: `object`
-
-## Properties
-
-- name: availableRuleTypes (optional)
-  type: array of string
-  description: Rule types that the LLM can produce as output. When non-empty, the LLM output schema is augmented with a 'rules' field describing the available rule type schemas. Rules returned by the LLM are parsed and persisted to the LogRulesApplication operator for dynamic per-pattern rule application.
-
-- name: availableTools (optional)
-  type: array of `LlmToolConfig`
-  description: MCP tool integrations available for the LLM to invoke as terminal actions. Each entry references an integration that exposes MCP-compatible tools.
-
-- name: capacity (optional)
-  type: integer
-  description: Maximum number of concurrent LLM calls per operator instance. Note: Total concurrent calls = capacity × Flink parallelism. For example, with parallelism=4 and capacity=100, up to 400 concurrent calls may occur. Consider your LLM provider's rate limits when configuring this value.
-
-- name: integrationId (required)
-  type: string
-  description: The LLM integration ID (Gemini or OpenAI).
-
-- name: llmConfig (required)
-  type: `LlmConfig`
-
-- name: maxRetries (optional)
-  type: integer
-  description: Maximum number of retries for failed LLM calls.
-
-- name: name (required)
-  type: string
-
-- name: outputActions (optional)
-  type: array of enum: `FORWARD_TO_SINKS`
-  description: Controls where LLM-enriched events are routed after processing. Multiple actions can be combined.
-
-- name: outputSchema (optional)
-  type: string
-  description: JSON Schema defining the expected structure of the LLM output. When set, the LLM is instructed to return structured JSON matching this schema. The output will include an 'actionable' boolean and a 'user_result' object. Supports standard JSON Schema property keywords: type, description, and enum.
-
-- name: predicate (optional)
-  type: `EventPredicate`
-
-- name: promptInstruction (required)
-  type: string
-  description: The user's prompt instruction describing what the LLM should do. Context (event JSON, entity context, similar patterns) is assembled automatically by the system — do not include placeholders.
-
-- name: responseFormat (optional)
-  type: enum: `TEXT`, `JSON`
-  description: The format for the LLM response.
-
-- name: timeoutSeconds (optional)
-  type: integer
-  description: Timeout for LLM calls in seconds.
-
-- name: type (required)
-  type: enum: `llm-prompt`
-  description: Runs LLM prompts on new log patterns.
-
-- name: workflowConfig (optional)
-  type: `LlmWorkflowConfig`

package/build/dist/docs-index/654d5da3-7e4a-47ad-b76c-50ba9312eea1.txt

@@ -1,15 +0,0 @@
-# TriggerActionConfig
-
-Configuration for the trigger action operator in an AI pipeline.
-
-**Type**: `object`
-
-## Properties
-
-- name: capacity (optional)
-  type: integer
-  description: Maximum number of concurrent trigger handler calls.
-
-- name: timeoutSeconds (optional)
-  type: integer
-  description: Timeout for trigger handler execution in seconds.

package/build/dist/docs-index/8706eefa-5f8f-42a3-9269-9ae9a1d833f5.txt

@@ -1,15 +0,0 @@
-# LlmWorkflowConfig
-
-Configuration for the LLM workflow strategy.
-
-**Type**: `object`
-
-## One Of
-
-This schema accepts one of the following types:
-
-### Option 1
-`Simple`
-
-### Option 2
-`Rag`

package/build/dist/docs-index/92ab8f13-d673-4c48-8e3f-fa95073781f4.txt

@@ -1,45 +0,0 @@
-# EntityContextAggregation
-
-**Type**: `object`
-
-## Properties
-
-- name: capacity (optional)
-  type: integer
-  description: Maximum number of concurrent LLM calls per operator instance.
-
-- name: entityAttributes (optional)
-  type: array of string
-
-- name: entityTags (optional)
-  type: array of string
-
-- name: integrationId (required)
-  type: string
-  description: The LLM integration ID (Gemini or OpenAI).
-
-- name: llmConfig (required)
-  type: `LlmConfig`
-
-- name: maxRetries (optional)
-  type: integer
-  description: Maximum retries for failed LLM calls.
-
-- name: maxSummaryTokens (optional)
-  type: integer
-  description: Maximum token budget for the entity summary. The system prompt instructs the LLM to keep the summary within this bound.
-
-- name: name (required)
-  type: string
-
-- name: systemPromptOverride (optional)
-  type: string
-  description: Optional system prompt override. When null, a default system prompt is used that instructs the LLM to maintain a rolling entity summary and report whether the update is broadcast-worthy.
-
-- name: timeoutSeconds (optional)
-  type: integer
-  description: Timeout for LLM calls in seconds.
-
-- name: type (required)
-  type: enum: `entity-context-aggregation`
-  description: Maintains per-entity rolling context summaries using an LLM. Broadcasts significant updates for downstream prompt enrichment.

package/build/dist/docs-index/946ebf1b-3907-4fe2-930c-5028551b5741.txt

@@ -1,43 +0,0 @@
-# GreprLlmPromptResultsSource
-
-**Type**: `object`
-
-## Properties
-
-- name: datasetId (required)
-  type: string
-  description: The ID of the dataset to read data from.
-
-- name: end (required)
-  type: string
-  description: End of time interval to query data for.
-
-- name: limit (optional)
-  type: integer
-  description: The maximum number of rows to process
-
-- name: name (required)
-  type: string
-
-- name: offset (optional)
-  type: integer
-  description: Offset on the number of rows to process
-
-- name: query (required)
-  type: `query`
-
-- name: sortOrder (optional)
-  type: enum: `ASCENDING`, `DESCENDING`, `UNSORTED`
-  description: The order in which the rows should be sorted by
-
-- name: start (required)
-  type: string
-  description: Start of time interval to query data for.
-
-- name: type (required)
-  type: enum: `grepr-llm-prompt-results-source`
-  description: Reads LLM prompt result events using Grepr's internal query system from an Iceberg Table.
-
-- name: variables (optional)
-  type: object
-  description: Variables that can be used to modify the query while parsed

package/build/dist/docs-index/9ae737d1-c03b-407b-8df7-9a61fdc6be65.txt

@@ -1,16 +0,0 @@
-# EmbeddingConfig
-
-Configuration for an embedding model. The 'type' field determines the provider.
-
-**Type**: `object`
-
-## Properties
-
-- name: dimensions (optional)
-  type: integer
-
-- name: model (optional)
-  type: string
-
-- name: type (required)
-  type: string

package/build/dist/docs-index/a93b9a1d-d911-4bb0-aa0e-e32052dbcc42.txt

@@ -1,43 +0,0 @@
-# TrinoLlmPromptResultsSource
-
-**Type**: `object`
-
-## Properties
-
-- name: datasetId (required)
-  type: string
-  description: The ID of the dataset to read data from.
-
-- name: end (required)
-  type: string
-  description: End of time interval to query data for.
-
-- name: limit (optional)
-  type: integer
-  description: The maximum number of rows to process
-
-- name: name (required)
-  type: string
-
-- name: offset (optional)
-  type: integer
-  description: Offset on the number of rows to process
-
-- name: query (required)
-  type: `query`
-
-- name: sortOrder (optional)
-  type: enum: `ASCENDING`, `DESCENDING`, `UNSORTED`
-  description: The order in which the rows should be sorted by
-
-- name: start (required)
-  type: string
-  description: Start of time interval to query data for.
-
-- name: type (required)
-  type: enum: `trino-llm-prompt-results-source`
-  description: Reads LLM prompt result events out of an Iceberg Table, executed against a Trino query engine.
-
-- name: variables (optional)
-  type: object
-  description: Variables that can be used to modify the query while parsed

package/build/dist/docs-index/bcfd51c3-0a79-4622-9add-292de2b5f918.txt

@@ -1,30 +0,0 @@
-# Rag
-
-RAG workflow that enriches the prompt with similar historical patterns from a vector store before sending to the LLM.
-
-**Type**: `object`
-
-## Properties
-
-- name: embeddingConfig (required)
-  type: `EmbeddingConfig`
-
-- name: embeddingIntegrationId (required)
-  type: string
-  description: The integration ID for the embedding model. Reuses existing OpenAI or Gemini integrations (same API key).
-
-- name: metadataFields (optional)
-  type: array of string
-  description: Event field references to store as filterable metadata on each vector and used to filter retrieval at query time. Values prefixed with '@' are resolved from event attributes; values without '@' are resolved from event tags. The metadata key is the bare field name (without '@'). Total filterable metadata per vector is limited to 2048 bytes.
-
-- name: topN (optional)
-  type: integer
-  description: Number of similar patterns to retrieve from the vector store.
-
-- name: type (required)
-  type: enum: `rag`
-  description: RAG workflow that enriches the prompt with similar historical patterns from a vector store before sending to the LLM.
-
-- name: vectorIndexIntegrationId (required)
-  type: string
-  description: The integration ID of the S3 Vector Index to use for similarity search.

package/build/dist/docs-index/c7397e87-e5c7-4b8e-87e8-6062de86c77c.txt

@@ -1,16 +0,0 @@
-# SqlOperations
-
-SQL operations applied at various stages of log processing.
-
-**Type**: `object`
-
-## Properties
-
-- name: pre-exceptions (optional)
-  type: `TemplateSqlOperation`
-
-- name: pre-parser (optional)
-  type: `TemplateSqlOperation`
-
-- name: pre-warehouse (optional)
-  type: `TemplateSqlOperation`

package/build/dist/docs-index/d6c18070-f9b2-4790-a96c-49feb2468e1d.txt

@@ -1,23 +0,0 @@
-# LlmConfig
-
-Configuration for the LLM provider and model.
-
-**Type**: `object`
-
-## Properties
-
-- name: maxTokens (optional)
-  type: integer
-  description: Maximum tokens in the response.
-
-- name: model (required)
-  type: string
-  description: The model identifier.
-
-- name: providerConfigs (optional)
-  type: object
-  description: Provider-specific configuration. For OPENAI, may include 'baseUrl'. For GEMINI, may include 'projectId'.
-
-- name: temperature (optional)
-  type: number
-  description: Temperature for response generation. Lower values are more deterministic.

package/build/dist/docs-index/d7f332d9-aee7-4e3d-b763-6d45a81f3470.txt

@@ -1,19 +0,0 @@
-# LlmToolConfig
-
-MCP tool integrations available for the LLM to invoke as terminal actions. Each entry references an integration that exposes MCP-compatible tools.
-
-**Type**: `object`
-
-## Properties
-
-- name: allowedTools (optional)
-  type: array of string
-  description: Which tools from this MCP server to expose to the LLM. If empty or null, all tools from the server are available.
-
-- name: description (optional)
-  type: string
-  description: Optional description override for the LLM to understand when to use this integration. e.g., "Use this to create tickets for anomalous behavior"
-
-- name: integrationId (required)
-  type: string
-  description: Integration ID for the MCP server (e.g., a Notion integration).

package/build/dist/docs-index/e3da6b82-6422-44a1-bbe5-3800f9403b73.txt

@@ -1,59 +0,0 @@
-# AiPipelineTemplateInput
-
-Schema for the AI pipeline job graph.
-
-**Type**: `object`
-
-## Properties
-
-- name: datasetId (required)
-  type: string
-  description: The unique identifier for the dataset.
-
-- name: entityContextAggregation (optional)
-  type: `EntityContextAggregation`
-
-- name: exceptions (required)
-  type: array of `TemplateException`
-  description: A list of template-specific exceptions to apply in the pipeline.
-
-- name: filters (required)
-  type: `LogReducerFilters`
-
-- name: llmPrompts (required)
-  type: array of `LlmPrompt`
-  description: LLM prompt configurations.
-
-- name: llmResultsDatasetId (optional)
-  type: string
-  description: Optional dataset ID for storing LLM prompt results in an Iceberg table.
-
-- name: parsers (required)
-  type: array of `Operation`
-  description: A list of parsers to be applied to the data.
-
-- name: patternMatcher (required)
-  type: `PatternMatcher`
-
-- name: processedLogsSink (optional)
-  type: `LogsIcebergTableSink`
-
-- name: processedLogsSinkFilter (optional)
-  type: `LogsFilter`
-
-- name: sampler (optional)
-  type: `LogsEventSampler`
-
-- name: sinks (required)
-  type: array of `TemplateLogSink`
-  description: A list of template log sinks, each specific to a vendor with optional filter configuration.
-
-- name: sources (required)
-  type: array of `Operation`
-  description: A list of data sources, each conforming to one of the defined source types.
-
-- name: sqlOperations (optional)
-  type: `SqlOperations`
-
-- name: triggerAction (optional)
-  type: `TriggerActionConfig`

package/build/dist/docs-index/f3206751-1b81-43dd-bc71-b27b4f9eb457.txt

@@ -1,19 +0,0 @@
-# LogReducerFilters
-
-Filters applied at various stages of log processing.
-
-**Type**: `object`
-
-## Properties
-
-- name: pre-aggregation (optional)
-  type: `LogsFilter`
-
-- name: pre-exceptions (optional)
-  type: `LogsFilter`
-
-- name: pre-parser (optional)
-  type: `LogsFilter`
-
-- name: pre-warehouse (optional)
-  type: `LogsFilter`

package/build/dist/docs-index/f8b01a27-656a-45fb-8ab8-84c7a921f979.json

@@ -1 +0,0 @@
-{"docType":"schema"}

package/build/dist/docs-index/f8bd694b-ad52-4960-9d6f-2acd77eb2d4b.json

@@ -1 +0,0 @@
-{"docType":"schema"}

package/build/dist/docs-index/f91df831-ee60-46b3-a522-78d6783207fa.json

@@ -1 +0,0 @@
-{"docType":"schema"}

package/build/dist/docs-index/fa481e51-07e1-482d-b2d8-3a5e3f3be1c5.json

@@ -1 +0,0 @@
-{"docType":"schema"}

package/build/dist/docs-index/fab27c3b-686c-4ee5-92f8-60573fddcdac.json

@@ -1 +0,0 @@
-{"docType":"schema"}

package/build/dist/docs-index/fad71634-ca8c-486b-9cc3-28bc68ee8616.json

@@ -1 +0,0 @@
-{"docType":"schema"}

package/build/dist/docs-index/fb169226-600c-493e-b3a2-daa3bb14e3f9.json

@@ -1 +0,0 @@
-{"docType":"schema"}

package/build/dist/docs-index/fb8b04f9-f89e-4c50-b14e-12205f60470f.json

@@ -1 +0,0 @@
-{"docType":"schema"}

package/build/dist/docs-index/fc5be0d5-5d7f-45b7-9c1e-b0346e862fd5.json

@@ -1 +0,0 @@
-{"docType":"schema"}

package/build/dist/docs-index/fc8db8d2-9629-4f6c-9b76-5fb59f0a6f55.json

@@ -1 +0,0 @@
-{"docType":"schema"}

package/build/dist/docs-index/fd9c36ac-4523-484e-a217-949289675cfe.json

@@ -1 +0,0 @@
-{"docType":"schema"}

package/build/dist/docs-index/ff0d3f7f-8f93-4fa4-be2c-cd3fedba4e8a.json

@@ -1 +0,0 @@
-{"docType":"schema"}

package/build/dist/docs-index/ff10eaf4-840b-447f-87d4-286bef54ee74.json

@@ -1 +0,0 @@
-{"docType":"schema"}

package/build/dist/docs-index/ff269049-5c22-411f-ab48-5a19470f65e8.json

@@ -1 +0,0 @@
-{"docType":"schema"}

package/build/dist/docs-index/ff55311f-7ad6-4ad1-9f67-61d534c1738d.json

@@ -1 +0,0 @@
-{"docType":"schema"}

package/build/dist/openapi-docs/schemas/AiPipelineTemplateInput.md

@@ -1,59 +0,0 @@
-# AiPipelineTemplateInput
-
-Schema for the AI pipeline job graph.
-
-**Type**: `object`
-
-## Properties
-
-- name: datasetId (required)
-  type: string
-  description: The unique identifier for the dataset.
-
-- name: entityContextAggregation (optional)
-  type: `EntityContextAggregation`
-
-- name: exceptions (required)
-  type: array of `TemplateException`
-  description: A list of template-specific exceptions to apply in the pipeline.
-
-- name: filters (required)
-  type: `LogReducerFilters`
-
-- name: llmPrompts (required)
-  type: array of `LlmPrompt`
-  description: LLM prompt configurations.
-
-- name: llmResultsDatasetId (optional)
-  type: string
-  description: Optional dataset ID for storing LLM prompt results in an Iceberg table.
-
-- name: parsers (required)
-  type: array of `Operation`
-  description: A list of parsers to be applied to the data.
-
-- name: patternMatcher (required)
-  type: `PatternMatcher`
-
-- name: processedLogsSink (optional)
-  type: `LogsIcebergTableSink`
-
-- name: processedLogsSinkFilter (optional)
-  type: `LogsFilter`
-
-- name: sampler (optional)
-  type: `LogsEventSampler`
-
-- name: sinks (required)
-  type: array of `TemplateLogSink`
-  description: A list of template log sinks, each specific to a vendor with optional filter configuration.
-
-- name: sources (required)
-  type: array of `Operation`
-  description: A list of data sources, each conforming to one of the defined source types.
-
-- name: sqlOperations (optional)
-  type: `SqlOperations`
-
-- name: triggerAction (optional)
-  type: `TriggerActionConfig`

package/build/dist/openapi-docs/schemas/EmbeddingConfig.md

@@ -1,16 +0,0 @@
-# EmbeddingConfig
-
-Configuration for an embedding model. The 'type' field determines the provider.
-
-**Type**: `object`
-
-## Properties
-
-- name: dimensions (optional)
-  type: integer
-
-- name: model (optional)
-  type: string
-
-- name: type (required)
-  type: string