@artemiskit/cli 0.2.0 → 0.2.3

package/CHANGELOG.md

@@ -1,5 +1,102 @@
 # @artemiskit/cli
 
+## 0.2.3
+
+### Patch Changes
+
+- 37403aa: ## v0.2.3 - Cost Tracking & Compliance Features
+
+  ### Cost Tracking
+
+  - **Automatic cost estimation**: Run results now include estimated API costs based on token usage and model pricing data
+  - **Cost display in output**: Summary output shows total tokens and estimated cost for each run
+  - **`--budget` flag**: Set a maximum budget in USD for `run`, `redteam`, and `stress` commands - the command fails (exit code 1) if the estimated cost exceeds the budget
+
+  ### History Enhancements
+
+  - **`--show-cost` flag**: Display cost column and total in `history` command output
+  - Cost data is stored with each run for historical tracking
+
+  ### Markdown Export
+
+  - **`--export markdown` flag**: Export run and redteam results to compliance-ready markdown format
+  - **`--export-output` flag**: Specify custom output directory for exports (default: `./artemis-exports`)
+  - Markdown reports include:
+    - Summary table with pass/fail rates, latency, token usage, and cost metrics
+    - Detailed results for failed test cases (run) or vulnerabilities found (redteam)
+    - Configuration used for the run
+    - Redaction summary (if enabled)
+    - Recommendations for remediation (redteam)
+
+  ### CI/CD Integration
+
+  - Budget enforcement in pipelines: `akit run scenarios/ --ci --budget 5.00`
+  - Cost tracking in CI summary output with `ARTEMISKIT_COST_USD` variable
+  - Automatic markdown report generation for compliance documentation
+
+- Updated dependencies [37403aa]
+  - @artemiskit/core@0.2.3
+  - @artemiskit/reports@0.2.3
+  - @artemiskit/adapter-openai@0.1.10
+  - @artemiskit/adapter-vercel-ai@0.1.10
+  - @artemiskit/redteam@0.2.3
+
+## 0.2.2
+
+### Patch Changes
+
+- d5ca7c6: Add baseline command and CI mode for regression detection
+
+  ### New Features
+
+  - **Baseline Command**: New `akit baseline` command with `set`, `list`, `get`, `remove` subcommands
+
+    - Lookup by run ID (default) or scenario name (`--scenario` flag)
+    - Store and manage baseline metrics for regression comparison
+
+  - **CI Mode**: New `--ci` flag for machine-readable output
+
+    - Outputs environment variable format for easy parsing
+    - Auto-detects CI environments (GitHub Actions, GitLab CI, etc.)
+    - Suppresses colors and spinners
+
+  - **Summary Formats**: New `--summary` flag with `json`, `text`, `security` formats
+
+    - JSON summary for pipeline parsing
+    - Security summary for compliance reporting
+
+  - **Regression Detection**: New `--baseline` and `--threshold` flags
+    - Compare runs against saved baselines
+    - Configurable regression threshold (default 5%)
+    - Exit code 1 on regression detection
+
+- Updated dependencies [d5ca7c6]
+  - @artemiskit/core@0.2.2
+  - @artemiskit/adapter-openai@0.1.9
+  - @artemiskit/adapter-vercel-ai@0.1.9
+  - @artemiskit/redteam@0.2.2
+  - @artemiskit/reports@0.2.2
+
+## 0.2.1
+
+### Patch Changes
+
+- fix: improve LLM grader compatibility with reasoning models
+
+  - Remove temperature parameter from LLM grader (reasoning models like o1, o3, gpt-5-mini only support temperature=1)
+  - Increase maxTokens from 200 to 1000 to accommodate reasoning models that use tokens for internal thinking
+  - Improve grader prompt for stricter JSON-only output format
+  - Add fallback parsing for malformed JSON responses
+  - Add markdown code block stripping from grader responses
+  - Add `modelFamily` configuration option to Azure OpenAI provider for correct parameter detection when deployment names differ from model names
+
+- Updated dependencies
+  - @artemiskit/core@0.2.1
+  - @artemiskit/adapter-openai@0.1.8
+  - @artemiskit/adapter-vercel-ai@0.1.8
+  - @artemiskit/redteam@0.2.1
+  - @artemiskit/reports@0.2.1
+
 ## 0.2.0
 
 ### Minor Changes