@outlit/pi 2.1.1 → 2.1.2

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/README.md CHANGED
@@ -53,7 +53,7 @@ pi install npm:@outlit/pi
53
53
 
54
54
  The skill gives the model generic guidance for choosing between customer records, users, timelines, facts, search, sources, and SQL when SQL tools are enabled. It does not add CLI or MCP instructions; it assumes the Outlit tools registered by this package are the available interface.
55
55
 
56
- The facts tool supports `factTypes` filters for narrowing structured customer-memory evidence. Anomaly detector fact types are not supported as public filters because customers may not have configured core actions, activation paths, or funnels.
56
+ The facts tool supports `factTypes` filters for narrowing structured evidence. Public filters include customer-memory facts and relationship transitions such as `CONTACT_DEPARTURE`, `CONTACT_POSITION_CHANGE`, and `CONTACT_DISENGAGEMENT`. Anomaly detector fact types are not supported as public filters because customers may not have configured core actions, activation paths, or funnels.
57
57
 
58
58
  ## Custom Toolsets
59
59
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@outlit/pi",
3
- "version": "2.1.1",
3
+ "version": "2.1.2",
4
4
  "description": "Pi package for Outlit customer intelligence tools and skill guidance",
5
5
  "license": "Apache-2.0",
6
6
  "author": "Outlit AI",
@@ -66,7 +66,7 @@
66
66
  "test": "vitest run"
67
67
  },
68
68
  "dependencies": {
69
- "@outlit/tools": "^2.1.1"
69
+ "@outlit/tools": "^2.1.2"
70
70
  },
71
71
  "peerDependencies": {
72
72
  "@mariozechner/pi-coding-agent": "*",
@@ -32,7 +32,7 @@ Use customer lookups before SQL. SQL is for aggregates, joins, cohorts, time-ser
32
32
  ## Facts vs Search vs Timeline
33
33
 
34
34
  - Use `outlit_list_facts` to list what Outlit already knows about an account.
35
- - Use `factTypes` for specific extracted fact classes such as `CHURN_RISK`, `EXPANSION`, `SENTIMENT`, `BUDGET`, `REQUIREMENTS`, `PRODUCT_USAGE`, or `CHAMPION_RISK` when those are relevant. Do not request anomaly detector fact types such as `CORE_ACTION_DECAY`, `CADENCE_BREAK`, `QUIET_ACCOUNT`, `ACTIVATION_RATE_DROP`, or `FUNNEL_DROPOFF` as filters.
35
+ - Use `factTypes` for specific public fact classes such as `CHURN_RISK`, `EXPANSION`, `PRODUCT_USAGE`, `CONTACT_DEPARTURE`, `CONTACT_POSITION_CHANGE`, or `CONTACT_DISENGAGEMENT` when those are relevant. Do not request anomaly detector fact types such as `CORE_ACTION_DECAY`, `CADENCE_BREAK`, `QUIET_ACCOUNT`, `ACTIVATION_RATE_DROP`, or `FUNNEL_DROPOFF` as filters.
36
36
  - Use `outlit_get_fact` when you already have a fact id and need that exact fact.
37
37
  - Use `outlit_search_customer_context` for a specific question or theme, including cross-customer questions.
38
38
  - Use `outlit_get_source` when you need the exact email, call, calendar event, ticket, or other source artifact behind a fact or search hit.