@artemiskit/cli 0.2.0 → 0.2.2

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/CHANGELOG.md CHANGED
@@ -1,5 +1,61 @@
1
1
  # @artemiskit/cli
2
2
 
3
+ ## 0.2.2
4
+
5
+ ### Patch Changes
6
+
7
+ - d5ca7c6: Add baseline command and CI mode for regression detection
8
+
9
+ ### New Features
10
+
11
+ - **Baseline Command**: New `akit baseline` command with `set`, `list`, `get`, `remove` subcommands
12
+
13
+ - Lookup by run ID (default) or scenario name (`--scenario` flag)
14
+ - Store and manage baseline metrics for regression comparison
15
+
16
+ - **CI Mode**: New `--ci` flag for machine-readable output
17
+
18
+ - Outputs environment variable format for easy parsing
19
+ - Auto-detects CI environments (GitHub Actions, GitLab CI, etc.)
20
+ - Suppresses colors and spinners
21
+
22
+ - **Summary Formats**: New `--summary` flag with `json`, `text`, `security` formats
23
+
24
+ - JSON summary for pipeline parsing
25
+ - Security summary for compliance reporting
26
+
27
+ - **Regression Detection**: New `--baseline` and `--threshold` flags
28
+ - Compare runs against saved baselines
29
+ - Configurable regression threshold (default 5%)
30
+ - Exit code 1 on regression detection
31
+
32
+ - Updated dependencies [d5ca7c6]
33
+ - @artemiskit/core@0.2.2
34
+ - @artemiskit/adapter-openai@0.1.9
35
+ - @artemiskit/adapter-vercel-ai@0.1.9
36
+ - @artemiskit/redteam@0.2.2
37
+ - @artemiskit/reports@0.2.2
38
+
39
+ ## 0.2.1
40
+
41
+ ### Patch Changes
42
+
43
+ - fix: improve LLM grader compatibility with reasoning models
44
+
45
+ - Remove temperature parameter from LLM grader (reasoning models like o1, o3, gpt-5-mini only support temperature=1)
46
+ - Increase maxTokens from 200 to 1000 to accommodate reasoning models that use tokens for internal thinking
47
+ - Improve grader prompt for stricter JSON-only output format
48
+ - Add fallback parsing for malformed JSON responses
49
+ - Add markdown code block stripping from grader responses
50
+ - Add `modelFamily` configuration option to Azure OpenAI provider for correct parameter detection when deployment names differ from model names
51
+
52
+ - Updated dependencies
53
+ - @artemiskit/core@0.2.1
54
+ - @artemiskit/adapter-openai@0.1.8
55
+ - @artemiskit/adapter-vercel-ai@0.1.8
56
+ - @artemiskit/redteam@0.2.1
57
+ - @artemiskit/reports@0.2.1
58
+
3
59
  ## 0.2.0
4
60
 
5
61
  ### Minor Changes