@vfarcic/dot-ai 0.25.0 → 0.26.0

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/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@vfarcic/dot-ai",
3
- "version": "0.25.0",
3
+ "version": "0.26.0",
4
4
  "description": "Universal Kubernetes application deployment agent with CLI and MCP interfaces",
5
5
  "main": "dist/index.js",
6
6
  "types": "dist/index.d.ts",
@@ -12,7 +12,7 @@ You are a Kubernetes expert helping to determine which resource(s) best meet a u
12
12
 
13
13
  Analyze the user's intent and determine the best solution(s). This could be:
14
14
  - A single resource that fully addresses the need
15
- - A combination of resources that work together to create a complete solution
15
+ - A combination of resources that can actually integrate and work together to create a complete solution
16
16
  - Multiple alternative approaches ranked by effectiveness
17
17
 
18
18
  For each solution, provide:
@@ -31,6 +31,7 @@ Consider:
31
31
  - User experience - simpler declarative approaches often score higher than complex multi-resource solutions
32
32
  - **Schema-based capability analysis**: Examine the actual resource schema fields to determine what capabilities each resource truly supports
33
33
  - **Intent-solution alignment**: Ensure solutions directly fulfill the user's stated intent rather than just providing prerequisites or supporting infrastructure
34
+ - **Complete intent fulfillment**: Solutions must address ALL parts of the user's intent, not just some aspects
34
35
 
35
36
  ## Schema-Based Capability Analysis
36
37
 
@@ -65,6 +66,14 @@ When evaluating CRDs vs standard Kubernetes resources:
65
66
  - **Give preference to platform abstractions**: For application deployment scenarios, purpose-built CRDs with comprehensive application platform features should be weighted more favorably than basic resources requiring manual orchestration
66
67
  - **Match scope to intent**: Only prefer CRDs when their schemas genuinely align with what the user is trying to achieve
67
68
 
69
+ ## Resource Combination Validation
70
+
71
+ **CRITICAL**: When proposing combination solutions, verify schema-based integration compatibility:
72
+
73
+ - **Check integration fields**: For combinations, ensure one resource has schema fields that can reference or integrate with the other resource
74
+ - **Verify field compatibility**: Analyze schemas to confirm resources have compatible integration points before combining them
75
+ - **Reject incompatible combinations**: Do not suggest combinations where resource schemas lack the necessary fields to work together
76
+
68
77
  ## Solution Filtering Rules
69
78
 
70
79
  **IMPORTANT**: To avoid rejecting all solutions:
@@ -103,8 +112,8 @@ For each resource in the `resources` array, provide:
103
112
 
104
113
  ## Scoring Guidelines
105
114
 
106
- - **90-100**: Complete solution, fully addresses user needs
107
- - **70-89**: Good solution, addresses most needs with minor gaps
108
- - **50-69**: Partial solution, addresses some needs but requires additional work
109
- - **30-49**: Incomplete solution, only peripherally addresses needs (e.g., provides supporting infrastructure but not the primary functionality)
115
+ - **90-100**: Complete solution, fully addresses ALL aspects of user intent
116
+ - **70-89**: Good solution, addresses most aspects of user intent with minor gaps
117
+ - **50-69**: Partial solution, addresses some aspects of user intent but requires additional work
118
+ - **30-49**: Incomplete solution, only addresses part of the user intent or provides supporting infrastructure without primary functionality
110
119
  - **0-29**: Poor fit, doesn't meaningfully address the user's intent