k-eval 0.3.0__tar.gz → 0.3.2__tar.gz
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.
- {k_eval-0.3.0 → k_eval-0.3.2}/PKG-INFO +3 -20
- {k_eval-0.3.0 → k_eval-0.3.2}/README.md +2 -19
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval.egg-info/PKG-INFO +3 -20
- {k_eval-0.3.0 → k_eval-0.3.2}/pyproject.toml +5 -1
- {k_eval-0.3.0 → k_eval-0.3.2}/MANIFEST.in +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/__init__.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/agent/__init__.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/agent/domain/__init__.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/agent/domain/agent.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/agent/domain/factory.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/agent/domain/observer.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/agent/domain/result.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/agent/domain/usage.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/agent/infrastructure/__init__.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/agent/infrastructure/claude_sdk.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/agent/infrastructure/errors.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/agent/infrastructure/factory.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/agent/infrastructure/observer.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/agent/infrastructure/registry.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/cli/__init__.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/cli/main.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/cli/output/__init__.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/cli/output/aggregator.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/cli/output/eee.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/config/__init__.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/config/domain/__init__.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/config/domain/agent.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/config/domain/condition.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/config/domain/condition_mcp_server.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/config/domain/config.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/config/domain/dataset.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/config/domain/execution.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/config/domain/judge.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/config/domain/mcp_server.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/config/domain/observer.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/config/infrastructure/__init__.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/config/infrastructure/env_interpolation.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/config/infrastructure/errors.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/config/infrastructure/observer.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/config/infrastructure/yaml_loader.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/core/__init__.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/core/errors.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/dataset/__init__.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/dataset/domain/__init__.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/dataset/domain/load_result.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/dataset/domain/loader.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/dataset/domain/observer.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/dataset/domain/sample.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/dataset/infrastructure/__init__.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/dataset/infrastructure/errors.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/dataset/infrastructure/jsonl_loader.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/dataset/infrastructure/observer.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/evaluation/__init__.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/evaluation/application/__init__.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/evaluation/application/runner.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/evaluation/domain/__init__.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/evaluation/domain/observer.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/evaluation/domain/run.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/evaluation/domain/summary.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/evaluation/infrastructure/__init__.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/evaluation/infrastructure/composite_observer.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/evaluation/infrastructure/observer.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/evaluation/infrastructure/progress_observer.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/judge/__init__.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/judge/domain/__init__.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/judge/domain/factory.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/judge/domain/judge.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/judge/domain/observer.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/judge/domain/score.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/judge/infrastructure/__init__.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/judge/infrastructure/errors.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/judge/infrastructure/factory.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/judge/infrastructure/litellm.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval/judge/infrastructure/observer.py +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval.egg-info/SOURCES.txt +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval.egg-info/dependency_links.txt +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval.egg-info/entry_points.txt +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval.egg-info/requires.txt +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/k_eval.egg-info/top_level.txt +0 -0
- {k_eval-0.3.0 → k_eval-0.3.2}/setup.cfg +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: k-eval
|
|
3
|
-
Version: 0.3.
|
|
3
|
+
Version: 0.3.2
|
|
4
4
|
Summary: Context-aware evaluation framework for AI agents using MCP.
|
|
5
5
|
Author: jsell-rh
|
|
6
6
|
License-Expression: Apache-2.0
|
|
@@ -40,22 +40,6 @@ k-eval uses [uv](https://docs.astral.sh/uv/) for dependency management. Install
|
|
|
40
40
|
curl -LsSf https://astral.sh/uv/install.sh | sh
|
|
41
41
|
```
|
|
42
42
|
|
|
43
|
-
### Install `k-eval`
|
|
44
|
-
|
|
45
|
-
```bash
|
|
46
|
-
git clone https://github.com/jsell-rh/k-eval.git
|
|
47
|
-
cd k-eval/src/k-eval
|
|
48
|
-
|
|
49
|
-
# Core dependencies
|
|
50
|
-
uv sync
|
|
51
|
-
|
|
52
|
-
# With Vertex AI provider support
|
|
53
|
-
uv sync --extra vertex_ai
|
|
54
|
-
|
|
55
|
-
# All provider dependencies
|
|
56
|
-
uv sync --extra all
|
|
57
|
-
```
|
|
58
|
-
|
|
59
43
|
### Run `k-eval`
|
|
60
44
|
|
|
61
45
|
`k-eval` runs are configured using `yaml` configuration files (see [Configuration](#Configuration)).
|
|
@@ -64,8 +48,7 @@ Once an evaluation is defined in a `yaml` file, you can invoke
|
|
|
64
48
|
`k-eval` like:
|
|
65
49
|
|
|
66
50
|
```bash
|
|
67
|
-
|
|
68
|
-
uv run python -m k_eval.cli.main /path/to/config.yaml
|
|
51
|
+
uvx --python 3.13 "k-eval[all]" /path/to/config.yaml
|
|
69
52
|
```
|
|
70
53
|
|
|
71
54
|
See [docs/run-configuration.md](docs/run-configuration.md) for authentication setup and all CLI options.
|
|
@@ -73,7 +56,7 @@ See [docs/run-configuration.md](docs/run-configuration.md) for authentication se
|
|
|
73
56
|
#### CLI Options
|
|
74
57
|
|
|
75
58
|
```bash
|
|
76
|
-
|
|
59
|
+
uvx --python 3.13 "k-eval[all]" --help
|
|
77
60
|
|
|
78
61
|
Usage: python -m cli.main [OPTIONS] CONFIG_PATH
|
|
79
62
|
|
|
@@ -10,22 +10,6 @@ k-eval uses [uv](https://docs.astral.sh/uv/) for dependency management. Install
|
|
|
10
10
|
curl -LsSf https://astral.sh/uv/install.sh | sh
|
|
11
11
|
```
|
|
12
12
|
|
|
13
|
-
### Install `k-eval`
|
|
14
|
-
|
|
15
|
-
```bash
|
|
16
|
-
git clone https://github.com/jsell-rh/k-eval.git
|
|
17
|
-
cd k-eval/src/k-eval
|
|
18
|
-
|
|
19
|
-
# Core dependencies
|
|
20
|
-
uv sync
|
|
21
|
-
|
|
22
|
-
# With Vertex AI provider support
|
|
23
|
-
uv sync --extra vertex_ai
|
|
24
|
-
|
|
25
|
-
# All provider dependencies
|
|
26
|
-
uv sync --extra all
|
|
27
|
-
```
|
|
28
|
-
|
|
29
13
|
### Run `k-eval`
|
|
30
14
|
|
|
31
15
|
`k-eval` runs are configured using `yaml` configuration files (see [Configuration](#Configuration)).
|
|
@@ -34,8 +18,7 @@ Once an evaluation is defined in a `yaml` file, you can invoke
|
|
|
34
18
|
`k-eval` like:
|
|
35
19
|
|
|
36
20
|
```bash
|
|
37
|
-
|
|
38
|
-
uv run python -m k_eval.cli.main /path/to/config.yaml
|
|
21
|
+
uvx --python 3.13 "k-eval[all]" /path/to/config.yaml
|
|
39
22
|
```
|
|
40
23
|
|
|
41
24
|
See [docs/run-configuration.md](docs/run-configuration.md) for authentication setup and all CLI options.
|
|
@@ -43,7 +26,7 @@ See [docs/run-configuration.md](docs/run-configuration.md) for authentication se
|
|
|
43
26
|
#### CLI Options
|
|
44
27
|
|
|
45
28
|
```bash
|
|
46
|
-
|
|
29
|
+
uvx --python 3.13 "k-eval[all]" --help
|
|
47
30
|
|
|
48
31
|
Usage: python -m cli.main [OPTIONS] CONFIG_PATH
|
|
49
32
|
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: k-eval
|
|
3
|
-
Version: 0.3.
|
|
3
|
+
Version: 0.3.2
|
|
4
4
|
Summary: Context-aware evaluation framework for AI agents using MCP.
|
|
5
5
|
Author: jsell-rh
|
|
6
6
|
License-Expression: Apache-2.0
|
|
@@ -40,22 +40,6 @@ k-eval uses [uv](https://docs.astral.sh/uv/) for dependency management. Install
|
|
|
40
40
|
curl -LsSf https://astral.sh/uv/install.sh | sh
|
|
41
41
|
```
|
|
42
42
|
|
|
43
|
-
### Install `k-eval`
|
|
44
|
-
|
|
45
|
-
```bash
|
|
46
|
-
git clone https://github.com/jsell-rh/k-eval.git
|
|
47
|
-
cd k-eval/src/k-eval
|
|
48
|
-
|
|
49
|
-
# Core dependencies
|
|
50
|
-
uv sync
|
|
51
|
-
|
|
52
|
-
# With Vertex AI provider support
|
|
53
|
-
uv sync --extra vertex_ai
|
|
54
|
-
|
|
55
|
-
# All provider dependencies
|
|
56
|
-
uv sync --extra all
|
|
57
|
-
```
|
|
58
|
-
|
|
59
43
|
### Run `k-eval`
|
|
60
44
|
|
|
61
45
|
`k-eval` runs are configured using `yaml` configuration files (see [Configuration](#Configuration)).
|
|
@@ -64,8 +48,7 @@ Once an evaluation is defined in a `yaml` file, you can invoke
|
|
|
64
48
|
`k-eval` like:
|
|
65
49
|
|
|
66
50
|
```bash
|
|
67
|
-
|
|
68
|
-
uv run python -m k_eval.cli.main /path/to/config.yaml
|
|
51
|
+
uvx --python 3.13 "k-eval[all]" /path/to/config.yaml
|
|
69
52
|
```
|
|
70
53
|
|
|
71
54
|
See [docs/run-configuration.md](docs/run-configuration.md) for authentication setup and all CLI options.
|
|
@@ -73,7 +56,7 @@ See [docs/run-configuration.md](docs/run-configuration.md) for authentication se
|
|
|
73
56
|
#### CLI Options
|
|
74
57
|
|
|
75
58
|
```bash
|
|
76
|
-
|
|
59
|
+
uvx --python 3.13 "k-eval[all]" --help
|
|
77
60
|
|
|
78
61
|
Usage: python -m cli.main [OPTIONS] CONFIG_PATH
|
|
79
62
|
|
|
@@ -1,6 +1,10 @@
|
|
|
1
|
+
[build-system]
|
|
2
|
+
requires = ["setuptools>=77"]
|
|
3
|
+
build-backend = "setuptools.build_meta"
|
|
4
|
+
|
|
1
5
|
[project]
|
|
2
6
|
name = "k-eval"
|
|
3
|
-
version = "0.3.
|
|
7
|
+
version = "0.3.2"
|
|
4
8
|
description = "Context-aware evaluation framework for AI agents using MCP."
|
|
5
9
|
readme = "README.md"
|
|
6
10
|
license = "Apache-2.0"
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|