@sentry/warden 0.30.0 → 0.31.0
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/CHANGELOG.md +246 -0
- package/README.md +2 -1
- package/coverage/lcov-report/base.css +224 -0
- package/coverage/lcov-report/block-navigation.js +87 -0
- package/coverage/lcov-report/favicon.png +0 -0
- package/coverage/lcov-report/index.html +446 -0
- package/coverage/lcov-report/prettify.css +1 -0
- package/coverage/lcov-report/prettify.js +2 -0
- package/coverage/lcov-report/sort-arrow-sprite.png +0 -0
- package/coverage/lcov-report/sorter.js +210 -0
- package/coverage/lcov-report/src/action/checks/index.html +116 -0
- package/coverage/lcov-report/src/action/checks/manager.ts.html +499 -0
- package/coverage/lcov-report/src/action/error-reporting.ts.html +181 -0
- package/coverage/lcov-report/src/action/fix-evaluation/github.ts.html +508 -0
- package/coverage/lcov-report/src/action/fix-evaluation/index.html +161 -0
- package/coverage/lcov-report/src/action/fix-evaluation/index.ts.html +1243 -0
- package/coverage/lcov-report/src/action/fix-evaluation/judge.ts.html +817 -0
- package/coverage/lcov-report/src/action/fix-evaluation/types.ts.html +274 -0
- package/coverage/lcov-report/src/action/index.html +161 -0
- package/coverage/lcov-report/src/action/inputs.ts.html +529 -0
- package/coverage/lcov-report/src/action/pi-ncc-compat.ts.html +292 -0
- package/coverage/lcov-report/src/action/review/coordination.ts.html +208 -0
- package/coverage/lcov-report/src/action/review/index.html +131 -0
- package/coverage/lcov-report/src/action/review/poster.ts.html +1051 -0
- package/coverage/lcov-report/src/action/review-state.ts.html +280 -0
- package/coverage/lcov-report/src/action/triggers/executor.ts.html +856 -0
- package/coverage/lcov-report/src/action/triggers/index.html +116 -0
- package/coverage/lcov-report/src/action/workflow/base.ts.html +1135 -0
- package/coverage/lcov-report/src/action/workflow/index.html +146 -0
- package/coverage/lcov-report/src/action/workflow/pr-workflow.ts.html +2713 -0
- package/coverage/lcov-report/src/action/workflow/schedule.ts.html +1027 -0
- package/coverage/lcov-report/src/cli/args.ts.html +1657 -0
- package/coverage/lcov-report/src/cli/commands/add.ts.html +1567 -0
- package/coverage/lcov-report/src/cli/commands/build.ts.html +1618 -0
- package/coverage/lcov-report/src/cli/commands/index.html +191 -0
- package/coverage/lcov-report/src/cli/commands/init.ts.html +1357 -0
- package/coverage/lcov-report/src/cli/commands/runs.ts.html +2560 -0
- package/coverage/lcov-report/src/cli/commands/setup-app/browser.ts.html +214 -0
- package/coverage/lcov-report/src/cli/commands/setup-app/credentials.ts.html +220 -0
- package/coverage/lcov-report/src/cli/commands/setup-app/index.html +161 -0
- package/coverage/lcov-report/src/cli/commands/setup-app/manifest.ts.html +235 -0
- package/coverage/lcov-report/src/cli/commands/setup-app/server.ts.html +601 -0
- package/coverage/lcov-report/src/cli/commands/setup-app.ts.html +571 -0
- package/coverage/lcov-report/src/cli/commands/sync.ts.html +475 -0
- package/coverage/lcov-report/src/cli/context.ts.html +532 -0
- package/coverage/lcov-report/src/cli/diff-apply.ts.html +334 -0
- package/coverage/lcov-report/src/cli/files.ts.html +904 -0
- package/coverage/lcov-report/src/cli/fix.ts.html +1060 -0
- package/coverage/lcov-report/src/cli/git.ts.html +1201 -0
- package/coverage/lcov-report/src/cli/help.ts.html +1696 -0
- package/coverage/lcov-report/src/cli/index.html +281 -0
- package/coverage/lcov-report/src/cli/input.ts.html +397 -0
- package/coverage/lcov-report/src/cli/log-cleanup.ts.html +337 -0
- package/coverage/lcov-report/src/cli/main.ts.html +5107 -0
- package/coverage/lcov-report/src/cli/output/box.ts.html +790 -0
- package/coverage/lcov-report/src/cli/output/formatters.ts.html +1099 -0
- package/coverage/lcov-report/src/cli/output/icons.ts.html +142 -0
- package/coverage/lcov-report/src/cli/output/index.html +281 -0
- package/coverage/lcov-report/src/cli/output/index.ts.html +295 -0
- package/coverage/lcov-report/src/cli/output/ink-runner.tsx.html +1597 -0
- package/coverage/lcov-report/src/cli/output/jsonl-schema-gen.ts.html +355 -0
- package/coverage/lcov-report/src/cli/output/jsonl.ts.html +2137 -0
- package/coverage/lcov-report/src/cli/output/live-status.tsx.html +916 -0
- package/coverage/lcov-report/src/cli/output/reporter.ts.html +1630 -0
- package/coverage/lcov-report/src/cli/output/tasks.ts.html +3193 -0
- package/coverage/lcov-report/src/cli/output/tty.ts.html +310 -0
- package/coverage/lcov-report/src/cli/output/verbosity.ts.html +181 -0
- package/coverage/lcov-report/src/cli/signals.ts.html +199 -0
- package/coverage/lcov-report/src/cli/terminal.ts.html +1060 -0
- package/coverage/lcov-report/src/config/index.html +161 -0
- package/coverage/lcov-report/src/config/index.ts.html +94 -0
- package/coverage/lcov-report/src/config/loader.ts.html +1753 -0
- package/coverage/lcov-report/src/config/schema.ts.html +910 -0
- package/coverage/lcov-report/src/config/writer.ts.html +538 -0
- package/coverage/lcov-report/src/diff/apply.ts.html +241 -0
- package/coverage/lcov-report/src/diff/classify.ts.html +361 -0
- package/coverage/lcov-report/src/diff/coalesce.ts.html +1123 -0
- package/coverage/lcov-report/src/diff/context.ts.html +952 -0
- package/coverage/lcov-report/src/diff/index.html +191 -0
- package/coverage/lcov-report/src/diff/index.ts.html +100 -0
- package/coverage/lcov-report/src/diff/parser.ts.html +532 -0
- package/coverage/lcov-report/src/evals/harness.ts.html +700 -0
- package/coverage/lcov-report/src/evals/index.html +221 -0
- package/coverage/lcov-report/src/evals/index.ts.html +955 -0
- package/coverage/lcov-report/src/evals/names.ts.html +121 -0
- package/coverage/lcov-report/src/evals/runner.ts.html +664 -0
- package/coverage/lcov-report/src/evals/scaffold.ts.html +970 -0
- package/coverage/lcov-report/src/evals/types.ts.html +661 -0
- package/coverage/lcov-report/src/evals/usage.ts.html +178 -0
- package/coverage/lcov-report/src/evals/verify.ts.html +1054 -0
- package/coverage/lcov-report/src/event/context.ts.html +490 -0
- package/coverage/lcov-report/src/event/index.html +116 -0
- package/coverage/lcov-report/src/index.html +116 -0
- package/coverage/lcov-report/src/output/dedup.ts.html +2950 -0
- package/coverage/lcov-report/src/output/github-checks.ts.html +1579 -0
- package/coverage/lcov-report/src/output/index.html +161 -0
- package/coverage/lcov-report/src/output/renderer.ts.html +988 -0
- package/coverage/lcov-report/src/output/stale.ts.html +640 -0
- package/coverage/lcov-report/src/sdk/analyze.ts.html +3010 -0
- package/coverage/lcov-report/src/sdk/auth.ts.html +217 -0
- package/coverage/lcov-report/src/sdk/circuit-breaker.ts.html +304 -0
- package/coverage/lcov-report/src/sdk/errors.ts.html +658 -0
- package/coverage/lcov-report/src/sdk/extract.ts.html +1810 -0
- package/coverage/lcov-report/src/sdk/fix-quality.ts.html +841 -0
- package/coverage/lcov-report/src/sdk/haiku.ts.html +1456 -0
- package/coverage/lcov-report/src/sdk/index.html +416 -0
- package/coverage/lcov-report/src/sdk/json-output.ts.html +508 -0
- package/coverage/lcov-report/src/sdk/model-pricing.json.html +499 -0
- package/coverage/lcov-report/src/sdk/otel.ts.html +433 -0
- package/coverage/lcov-report/src/sdk/post-process.ts.html +412 -0
- package/coverage/lcov-report/src/sdk/prepare.ts.html +400 -0
- package/coverage/lcov-report/src/sdk/pricing.ts.html +778 -0
- package/coverage/lcov-report/src/sdk/prompt-sections.ts.html +595 -0
- package/coverage/lcov-report/src/sdk/prompt.ts.html +451 -0
- package/coverage/lcov-report/src/sdk/report-files.ts.html +166 -0
- package/coverage/lcov-report/src/sdk/retry.ts.html +202 -0
- package/coverage/lcov-report/src/sdk/runner.ts.html +400 -0
- package/coverage/lcov-report/src/sdk/runtimes/claude.ts.html +1693 -0
- package/coverage/lcov-report/src/sdk/runtimes/index.html +176 -0
- package/coverage/lcov-report/src/sdk/runtimes/index.ts.html +244 -0
- package/coverage/lcov-report/src/sdk/runtimes/model-selectors.ts.html +328 -0
- package/coverage/lcov-report/src/sdk/runtimes/pi.ts.html +2104 -0
- package/coverage/lcov-report/src/sdk/runtimes/types.ts.html +508 -0
- package/coverage/lcov-report/src/sdk/types.ts.html +730 -0
- package/coverage/lcov-report/src/sdk/usage.ts.html +502 -0
- package/coverage/lcov-report/src/sdk/verify.ts.html +1027 -0
- package/coverage/lcov-report/src/sentry.ts.html +994 -0
- package/coverage/lcov-report/src/skill-builder/agentic.ts.html +1063 -0
- package/coverage/lcov-report/src/skill-builder/authoring-provider.ts.html +334 -0
- package/coverage/lcov-report/src/skill-builder/definition.ts.html +748 -0
- package/coverage/lcov-report/src/skill-builder/index.html +236 -0
- package/coverage/lcov-report/src/skill-builder/outline-contract.ts.html +400 -0
- package/coverage/lcov-report/src/skill-builder/outline-state.ts.html +382 -0
- package/coverage/lcov-report/src/skill-builder/outline.ts.html +1402 -0
- package/coverage/lcov-report/src/skill-builder/skill-contract.ts.html +382 -0
- package/coverage/lcov-report/src/skill-builder/skill-prompts.ts.html +1180 -0
- package/coverage/lcov-report/src/skill-builder/skill.ts.html +2398 -0
- package/coverage/lcov-report/src/skills/index.html +131 -0
- package/coverage/lcov-report/src/skills/loader.ts.html +1693 -0
- package/coverage/lcov-report/src/skills/remote.ts.html +1909 -0
- package/coverage/lcov-report/src/triggers/index.html +116 -0
- package/coverage/lcov-report/src/triggers/matcher.ts.html +841 -0
- package/coverage/lcov-report/src/types/index.html +116 -0
- package/coverage/lcov-report/src/types/index.ts.html +1240 -0
- package/coverage/lcov-report/src/utils/async.ts.html +331 -0
- package/coverage/lcov-report/src/utils/exec.ts.html +496 -0
- package/coverage/lcov-report/src/utils/index.html +176 -0
- package/coverage/lcov-report/src/utils/index.ts.html +313 -0
- package/coverage/lcov-report/src/utils/path.ts.html +202 -0
- package/coverage/lcov-report/src/utils/version.ts.html +136 -0
- package/coverage/lcov.info +19134 -0
- package/dist/cli/commands/runs.d.ts +1 -1
- package/dist/cli/commands/runs.d.ts.map +1 -1
- package/dist/cli/commands/runs.js +1 -1
- package/dist/cli/commands/runs.js.map +1 -1
- package/dist/cli/files.d.ts.map +1 -1
- package/dist/cli/files.js +10 -11
- package/dist/cli/files.js.map +1 -1
- package/dist/sdk/verify.d.ts.map +1 -1
- package/dist/sdk/verify.js +3 -2
- package/dist/sdk/verify.js.map +1 -1
- package/dist/skill-builder/outline.d.ts.map +1 -1
- package/dist/skill-builder/outline.js.map +1 -1
- package/package.json +8 -3
- package/test-results.junit.xml +4329 -0
- package/dist/evals/index.d.ts +0 -22
- package/dist/evals/index.d.ts.map +0 -1
- package/dist/evals/index.js +0 -92
- package/dist/evals/index.js.map +0 -1
- package/dist/evals/judge.d.ts +0 -12
- package/dist/evals/judge.d.ts.map +0 -1
- package/dist/evals/judge.js +0 -171
- package/dist/evals/judge.js.map +0 -1
- package/dist/evals/runner.d.ts +0 -18
- package/dist/evals/runner.d.ts.map +0 -1
- package/dist/evals/runner.js +0 -149
- package/dist/evals/runner.js.map +0 -1
- package/dist/evals/setup.d.ts +0 -2
- package/dist/evals/setup.d.ts.map +0 -1
- package/dist/evals/setup.js +0 -22
- package/dist/evals/setup.js.map +0 -1
- package/dist/evals/types.d.ts +0 -160
- package/dist/evals/types.d.ts.map +0 -1
- package/dist/evals/types.js +0 -148
- package/dist/evals/types.js.map +0 -1
|
@@ -0,0 +1,664 @@
|
|
|
1
|
+
|
|
2
|
+
<!doctype html>
|
|
3
|
+
<html lang="en">
|
|
4
|
+
|
|
5
|
+
<head>
|
|
6
|
+
<title>Code coverage report for src/evals/runner.ts</title>
|
|
7
|
+
<meta charset="utf-8" />
|
|
8
|
+
<link rel="stylesheet" href="../../prettify.css" />
|
|
9
|
+
<link rel="stylesheet" href="../../base.css" />
|
|
10
|
+
<link rel="shortcut icon" type="image/x-icon" href="../../favicon.png" />
|
|
11
|
+
<meta name="viewport" content="width=device-width, initial-scale=1" />
|
|
12
|
+
<style type='text/css'>
|
|
13
|
+
.coverage-summary .sorter {
|
|
14
|
+
background-image: url(../../sort-arrow-sprite.png);
|
|
15
|
+
}
|
|
16
|
+
</style>
|
|
17
|
+
</head>
|
|
18
|
+
|
|
19
|
+
<body>
|
|
20
|
+
<div class='wrapper'>
|
|
21
|
+
<div class='pad1'>
|
|
22
|
+
<h1><a href="../../index.html">All files</a> / <a href="index.html">src/evals</a> runner.ts</h1>
|
|
23
|
+
<div class='clearfix'>
|
|
24
|
+
|
|
25
|
+
<div class='fl pad1y space-right2'>
|
|
26
|
+
<span class="strong">38.46% </span>
|
|
27
|
+
<span class="quiet">Statements</span>
|
|
28
|
+
<span class='fraction'>25/65</span>
|
|
29
|
+
</div>
|
|
30
|
+
|
|
31
|
+
|
|
32
|
+
<div class='fl pad1y space-right2'>
|
|
33
|
+
<span class="strong">3.84% </span>
|
|
34
|
+
<span class="quiet">Branches</span>
|
|
35
|
+
<span class='fraction'>1/26</span>
|
|
36
|
+
</div>
|
|
37
|
+
|
|
38
|
+
|
|
39
|
+
<div class='fl pad1y space-right2'>
|
|
40
|
+
<span class="strong">25% </span>
|
|
41
|
+
<span class="quiet">Functions</span>
|
|
42
|
+
<span class='fraction'>2/8</span>
|
|
43
|
+
</div>
|
|
44
|
+
|
|
45
|
+
|
|
46
|
+
<div class='fl pad1y space-right2'>
|
|
47
|
+
<span class="strong">38.09% </span>
|
|
48
|
+
<span class="quiet">Lines</span>
|
|
49
|
+
<span class='fraction'>24/63</span>
|
|
50
|
+
</div>
|
|
51
|
+
|
|
52
|
+
|
|
53
|
+
</div>
|
|
54
|
+
<p class="quiet">
|
|
55
|
+
Press <em>n</em> or <em>j</em> to go to the next uncovered block, <em>b</em>, <em>p</em> or <em>k</em> for the previous block.
|
|
56
|
+
</p>
|
|
57
|
+
<template id="filterTemplate">
|
|
58
|
+
<div class="quiet">
|
|
59
|
+
Filter:
|
|
60
|
+
<input type="search" id="fileSearch">
|
|
61
|
+
</div>
|
|
62
|
+
</template>
|
|
63
|
+
</div>
|
|
64
|
+
<div class='status-line low'></div>
|
|
65
|
+
<pre><table class="coverage">
|
|
66
|
+
<tr><td class="line-count quiet"><a name='L1'></a><a href='#L1'>1</a>
|
|
67
|
+
<a name='L2'></a><a href='#L2'>2</a>
|
|
68
|
+
<a name='L3'></a><a href='#L3'>3</a>
|
|
69
|
+
<a name='L4'></a><a href='#L4'>4</a>
|
|
70
|
+
<a name='L5'></a><a href='#L5'>5</a>
|
|
71
|
+
<a name='L6'></a><a href='#L6'>6</a>
|
|
72
|
+
<a name='L7'></a><a href='#L7'>7</a>
|
|
73
|
+
<a name='L8'></a><a href='#L8'>8</a>
|
|
74
|
+
<a name='L9'></a><a href='#L9'>9</a>
|
|
75
|
+
<a name='L10'></a><a href='#L10'>10</a>
|
|
76
|
+
<a name='L11'></a><a href='#L11'>11</a>
|
|
77
|
+
<a name='L12'></a><a href='#L12'>12</a>
|
|
78
|
+
<a name='L13'></a><a href='#L13'>13</a>
|
|
79
|
+
<a name='L14'></a><a href='#L14'>14</a>
|
|
80
|
+
<a name='L15'></a><a href='#L15'>15</a>
|
|
81
|
+
<a name='L16'></a><a href='#L16'>16</a>
|
|
82
|
+
<a name='L17'></a><a href='#L17'>17</a>
|
|
83
|
+
<a name='L18'></a><a href='#L18'>18</a>
|
|
84
|
+
<a name='L19'></a><a href='#L19'>19</a>
|
|
85
|
+
<a name='L20'></a><a href='#L20'>20</a>
|
|
86
|
+
<a name='L21'></a><a href='#L21'>21</a>
|
|
87
|
+
<a name='L22'></a><a href='#L22'>22</a>
|
|
88
|
+
<a name='L23'></a><a href='#L23'>23</a>
|
|
89
|
+
<a name='L24'></a><a href='#L24'>24</a>
|
|
90
|
+
<a name='L25'></a><a href='#L25'>25</a>
|
|
91
|
+
<a name='L26'></a><a href='#L26'>26</a>
|
|
92
|
+
<a name='L27'></a><a href='#L27'>27</a>
|
|
93
|
+
<a name='L28'></a><a href='#L28'>28</a>
|
|
94
|
+
<a name='L29'></a><a href='#L29'>29</a>
|
|
95
|
+
<a name='L30'></a><a href='#L30'>30</a>
|
|
96
|
+
<a name='L31'></a><a href='#L31'>31</a>
|
|
97
|
+
<a name='L32'></a><a href='#L32'>32</a>
|
|
98
|
+
<a name='L33'></a><a href='#L33'>33</a>
|
|
99
|
+
<a name='L34'></a><a href='#L34'>34</a>
|
|
100
|
+
<a name='L35'></a><a href='#L35'>35</a>
|
|
101
|
+
<a name='L36'></a><a href='#L36'>36</a>
|
|
102
|
+
<a name='L37'></a><a href='#L37'>37</a>
|
|
103
|
+
<a name='L38'></a><a href='#L38'>38</a>
|
|
104
|
+
<a name='L39'></a><a href='#L39'>39</a>
|
|
105
|
+
<a name='L40'></a><a href='#L40'>40</a>
|
|
106
|
+
<a name='L41'></a><a href='#L41'>41</a>
|
|
107
|
+
<a name='L42'></a><a href='#L42'>42</a>
|
|
108
|
+
<a name='L43'></a><a href='#L43'>43</a>
|
|
109
|
+
<a name='L44'></a><a href='#L44'>44</a>
|
|
110
|
+
<a name='L45'></a><a href='#L45'>45</a>
|
|
111
|
+
<a name='L46'></a><a href='#L46'>46</a>
|
|
112
|
+
<a name='L47'></a><a href='#L47'>47</a>
|
|
113
|
+
<a name='L48'></a><a href='#L48'>48</a>
|
|
114
|
+
<a name='L49'></a><a href='#L49'>49</a>
|
|
115
|
+
<a name='L50'></a><a href='#L50'>50</a>
|
|
116
|
+
<a name='L51'></a><a href='#L51'>51</a>
|
|
117
|
+
<a name='L52'></a><a href='#L52'>52</a>
|
|
118
|
+
<a name='L53'></a><a href='#L53'>53</a>
|
|
119
|
+
<a name='L54'></a><a href='#L54'>54</a>
|
|
120
|
+
<a name='L55'></a><a href='#L55'>55</a>
|
|
121
|
+
<a name='L56'></a><a href='#L56'>56</a>
|
|
122
|
+
<a name='L57'></a><a href='#L57'>57</a>
|
|
123
|
+
<a name='L58'></a><a href='#L58'>58</a>
|
|
124
|
+
<a name='L59'></a><a href='#L59'>59</a>
|
|
125
|
+
<a name='L60'></a><a href='#L60'>60</a>
|
|
126
|
+
<a name='L61'></a><a href='#L61'>61</a>
|
|
127
|
+
<a name='L62'></a><a href='#L62'>62</a>
|
|
128
|
+
<a name='L63'></a><a href='#L63'>63</a>
|
|
129
|
+
<a name='L64'></a><a href='#L64'>64</a>
|
|
130
|
+
<a name='L65'></a><a href='#L65'>65</a>
|
|
131
|
+
<a name='L66'></a><a href='#L66'>66</a>
|
|
132
|
+
<a name='L67'></a><a href='#L67'>67</a>
|
|
133
|
+
<a name='L68'></a><a href='#L68'>68</a>
|
|
134
|
+
<a name='L69'></a><a href='#L69'>69</a>
|
|
135
|
+
<a name='L70'></a><a href='#L70'>70</a>
|
|
136
|
+
<a name='L71'></a><a href='#L71'>71</a>
|
|
137
|
+
<a name='L72'></a><a href='#L72'>72</a>
|
|
138
|
+
<a name='L73'></a><a href='#L73'>73</a>
|
|
139
|
+
<a name='L74'></a><a href='#L74'>74</a>
|
|
140
|
+
<a name='L75'></a><a href='#L75'>75</a>
|
|
141
|
+
<a name='L76'></a><a href='#L76'>76</a>
|
|
142
|
+
<a name='L77'></a><a href='#L77'>77</a>
|
|
143
|
+
<a name='L78'></a><a href='#L78'>78</a>
|
|
144
|
+
<a name='L79'></a><a href='#L79'>79</a>
|
|
145
|
+
<a name='L80'></a><a href='#L80'>80</a>
|
|
146
|
+
<a name='L81'></a><a href='#L81'>81</a>
|
|
147
|
+
<a name='L82'></a><a href='#L82'>82</a>
|
|
148
|
+
<a name='L83'></a><a href='#L83'>83</a>
|
|
149
|
+
<a name='L84'></a><a href='#L84'>84</a>
|
|
150
|
+
<a name='L85'></a><a href='#L85'>85</a>
|
|
151
|
+
<a name='L86'></a><a href='#L86'>86</a>
|
|
152
|
+
<a name='L87'></a><a href='#L87'>87</a>
|
|
153
|
+
<a name='L88'></a><a href='#L88'>88</a>
|
|
154
|
+
<a name='L89'></a><a href='#L89'>89</a>
|
|
155
|
+
<a name='L90'></a><a href='#L90'>90</a>
|
|
156
|
+
<a name='L91'></a><a href='#L91'>91</a>
|
|
157
|
+
<a name='L92'></a><a href='#L92'>92</a>
|
|
158
|
+
<a name='L93'></a><a href='#L93'>93</a>
|
|
159
|
+
<a name='L94'></a><a href='#L94'>94</a>
|
|
160
|
+
<a name='L95'></a><a href='#L95'>95</a>
|
|
161
|
+
<a name='L96'></a><a href='#L96'>96</a>
|
|
162
|
+
<a name='L97'></a><a href='#L97'>97</a>
|
|
163
|
+
<a name='L98'></a><a href='#L98'>98</a>
|
|
164
|
+
<a name='L99'></a><a href='#L99'>99</a>
|
|
165
|
+
<a name='L100'></a><a href='#L100'>100</a>
|
|
166
|
+
<a name='L101'></a><a href='#L101'>101</a>
|
|
167
|
+
<a name='L102'></a><a href='#L102'>102</a>
|
|
168
|
+
<a name='L103'></a><a href='#L103'>103</a>
|
|
169
|
+
<a name='L104'></a><a href='#L104'>104</a>
|
|
170
|
+
<a name='L105'></a><a href='#L105'>105</a>
|
|
171
|
+
<a name='L106'></a><a href='#L106'>106</a>
|
|
172
|
+
<a name='L107'></a><a href='#L107'>107</a>
|
|
173
|
+
<a name='L108'></a><a href='#L108'>108</a>
|
|
174
|
+
<a name='L109'></a><a href='#L109'>109</a>
|
|
175
|
+
<a name='L110'></a><a href='#L110'>110</a>
|
|
176
|
+
<a name='L111'></a><a href='#L111'>111</a>
|
|
177
|
+
<a name='L112'></a><a href='#L112'>112</a>
|
|
178
|
+
<a name='L113'></a><a href='#L113'>113</a>
|
|
179
|
+
<a name='L114'></a><a href='#L114'>114</a>
|
|
180
|
+
<a name='L115'></a><a href='#L115'>115</a>
|
|
181
|
+
<a name='L116'></a><a href='#L116'>116</a>
|
|
182
|
+
<a name='L117'></a><a href='#L117'>117</a>
|
|
183
|
+
<a name='L118'></a><a href='#L118'>118</a>
|
|
184
|
+
<a name='L119'></a><a href='#L119'>119</a>
|
|
185
|
+
<a name='L120'></a><a href='#L120'>120</a>
|
|
186
|
+
<a name='L121'></a><a href='#L121'>121</a>
|
|
187
|
+
<a name='L122'></a><a href='#L122'>122</a>
|
|
188
|
+
<a name='L123'></a><a href='#L123'>123</a>
|
|
189
|
+
<a name='L124'></a><a href='#L124'>124</a>
|
|
190
|
+
<a name='L125'></a><a href='#L125'>125</a>
|
|
191
|
+
<a name='L126'></a><a href='#L126'>126</a>
|
|
192
|
+
<a name='L127'></a><a href='#L127'>127</a>
|
|
193
|
+
<a name='L128'></a><a href='#L128'>128</a>
|
|
194
|
+
<a name='L129'></a><a href='#L129'>129</a>
|
|
195
|
+
<a name='L130'></a><a href='#L130'>130</a>
|
|
196
|
+
<a name='L131'></a><a href='#L131'>131</a>
|
|
197
|
+
<a name='L132'></a><a href='#L132'>132</a>
|
|
198
|
+
<a name='L133'></a><a href='#L133'>133</a>
|
|
199
|
+
<a name='L134'></a><a href='#L134'>134</a>
|
|
200
|
+
<a name='L135'></a><a href='#L135'>135</a>
|
|
201
|
+
<a name='L136'></a><a href='#L136'>136</a>
|
|
202
|
+
<a name='L137'></a><a href='#L137'>137</a>
|
|
203
|
+
<a name='L138'></a><a href='#L138'>138</a>
|
|
204
|
+
<a name='L139'></a><a href='#L139'>139</a>
|
|
205
|
+
<a name='L140'></a><a href='#L140'>140</a>
|
|
206
|
+
<a name='L141'></a><a href='#L141'>141</a>
|
|
207
|
+
<a name='L142'></a><a href='#L142'>142</a>
|
|
208
|
+
<a name='L143'></a><a href='#L143'>143</a>
|
|
209
|
+
<a name='L144'></a><a href='#L144'>144</a>
|
|
210
|
+
<a name='L145'></a><a href='#L145'>145</a>
|
|
211
|
+
<a name='L146'></a><a href='#L146'>146</a>
|
|
212
|
+
<a name='L147'></a><a href='#L147'>147</a>
|
|
213
|
+
<a name='L148'></a><a href='#L148'>148</a>
|
|
214
|
+
<a name='L149'></a><a href='#L149'>149</a>
|
|
215
|
+
<a name='L150'></a><a href='#L150'>150</a>
|
|
216
|
+
<a name='L151'></a><a href='#L151'>151</a>
|
|
217
|
+
<a name='L152'></a><a href='#L152'>152</a>
|
|
218
|
+
<a name='L153'></a><a href='#L153'>153</a>
|
|
219
|
+
<a name='L154'></a><a href='#L154'>154</a>
|
|
220
|
+
<a name='L155'></a><a href='#L155'>155</a>
|
|
221
|
+
<a name='L156'></a><a href='#L156'>156</a>
|
|
222
|
+
<a name='L157'></a><a href='#L157'>157</a>
|
|
223
|
+
<a name='L158'></a><a href='#L158'>158</a>
|
|
224
|
+
<a name='L159'></a><a href='#L159'>159</a>
|
|
225
|
+
<a name='L160'></a><a href='#L160'>160</a>
|
|
226
|
+
<a name='L161'></a><a href='#L161'>161</a>
|
|
227
|
+
<a name='L162'></a><a href='#L162'>162</a>
|
|
228
|
+
<a name='L163'></a><a href='#L163'>163</a>
|
|
229
|
+
<a name='L164'></a><a href='#L164'>164</a>
|
|
230
|
+
<a name='L165'></a><a href='#L165'>165</a>
|
|
231
|
+
<a name='L166'></a><a href='#L166'>166</a>
|
|
232
|
+
<a name='L167'></a><a href='#L167'>167</a>
|
|
233
|
+
<a name='L168'></a><a href='#L168'>168</a>
|
|
234
|
+
<a name='L169'></a><a href='#L169'>169</a>
|
|
235
|
+
<a name='L170'></a><a href='#L170'>170</a>
|
|
236
|
+
<a name='L171'></a><a href='#L171'>171</a>
|
|
237
|
+
<a name='L172'></a><a href='#L172'>172</a>
|
|
238
|
+
<a name='L173'></a><a href='#L173'>173</a>
|
|
239
|
+
<a name='L174'></a><a href='#L174'>174</a>
|
|
240
|
+
<a name='L175'></a><a href='#L175'>175</a>
|
|
241
|
+
<a name='L176'></a><a href='#L176'>176</a>
|
|
242
|
+
<a name='L177'></a><a href='#L177'>177</a>
|
|
243
|
+
<a name='L178'></a><a href='#L178'>178</a>
|
|
244
|
+
<a name='L179'></a><a href='#L179'>179</a>
|
|
245
|
+
<a name='L180'></a><a href='#L180'>180</a>
|
|
246
|
+
<a name='L181'></a><a href='#L181'>181</a>
|
|
247
|
+
<a name='L182'></a><a href='#L182'>182</a>
|
|
248
|
+
<a name='L183'></a><a href='#L183'>183</a>
|
|
249
|
+
<a name='L184'></a><a href='#L184'>184</a>
|
|
250
|
+
<a name='L185'></a><a href='#L185'>185</a>
|
|
251
|
+
<a name='L186'></a><a href='#L186'>186</a>
|
|
252
|
+
<a name='L187'></a><a href='#L187'>187</a>
|
|
253
|
+
<a name='L188'></a><a href='#L188'>188</a>
|
|
254
|
+
<a name='L189'></a><a href='#L189'>189</a>
|
|
255
|
+
<a name='L190'></a><a href='#L190'>190</a>
|
|
256
|
+
<a name='L191'></a><a href='#L191'>191</a>
|
|
257
|
+
<a name='L192'></a><a href='#L192'>192</a>
|
|
258
|
+
<a name='L193'></a><a href='#L193'>193</a>
|
|
259
|
+
<a name='L194'></a><a href='#L194'>194</a></td><td class="line-coverage quiet"><span class="cline-any cline-neutral"> </span>
|
|
260
|
+
<span class="cline-any cline-neutral"> </span>
|
|
261
|
+
<span class="cline-any cline-neutral"> </span>
|
|
262
|
+
<span class="cline-any cline-neutral"> </span>
|
|
263
|
+
<span class="cline-any cline-neutral"> </span>
|
|
264
|
+
<span class="cline-any cline-neutral"> </span>
|
|
265
|
+
<span class="cline-any cline-neutral"> </span>
|
|
266
|
+
<span class="cline-any cline-neutral"> </span>
|
|
267
|
+
<span class="cline-any cline-neutral"> </span>
|
|
268
|
+
<span class="cline-any cline-neutral"> </span>
|
|
269
|
+
<span class="cline-any cline-neutral"> </span>
|
|
270
|
+
<span class="cline-any cline-neutral"> </span>
|
|
271
|
+
<span class="cline-any cline-neutral"> </span>
|
|
272
|
+
<span class="cline-any cline-neutral"> </span>
|
|
273
|
+
<span class="cline-any cline-neutral"> </span>
|
|
274
|
+
<span class="cline-any cline-neutral"> </span>
|
|
275
|
+
<span class="cline-any cline-neutral"> </span>
|
|
276
|
+
<span class="cline-any cline-neutral"> </span>
|
|
277
|
+
<span class="cline-any cline-neutral"> </span>
|
|
278
|
+
<span class="cline-any cline-neutral"> </span>
|
|
279
|
+
<span class="cline-any cline-neutral"> </span>
|
|
280
|
+
<span class="cline-any cline-neutral"> </span>
|
|
281
|
+
<span class="cline-any cline-neutral"> </span>
|
|
282
|
+
<span class="cline-any cline-neutral"> </span>
|
|
283
|
+
<span class="cline-any cline-neutral"> </span>
|
|
284
|
+
<span class="cline-any cline-neutral"> </span>
|
|
285
|
+
<span class="cline-any cline-neutral"> </span>
|
|
286
|
+
<span class="cline-any cline-neutral"> </span>
|
|
287
|
+
<span class="cline-any cline-neutral"> </span>
|
|
288
|
+
<span class="cline-any cline-neutral"> </span>
|
|
289
|
+
<span class="cline-any cline-neutral"> </span>
|
|
290
|
+
<span class="cline-any cline-neutral"> </span>
|
|
291
|
+
<span class="cline-any cline-neutral"> </span>
|
|
292
|
+
<span class="cline-any cline-neutral"> </span>
|
|
293
|
+
<span class="cline-any cline-neutral"> </span>
|
|
294
|
+
<span class="cline-any cline-neutral"> </span>
|
|
295
|
+
<span class="cline-any cline-neutral"> </span>
|
|
296
|
+
<span class="cline-any cline-neutral"> </span>
|
|
297
|
+
<span class="cline-any cline-neutral"> </span>
|
|
298
|
+
<span class="cline-any cline-neutral"> </span>
|
|
299
|
+
<span class="cline-any cline-neutral"> </span>
|
|
300
|
+
<span class="cline-any cline-neutral"> </span>
|
|
301
|
+
<span class="cline-any cline-neutral"> </span>
|
|
302
|
+
<span class="cline-any cline-neutral"> </span>
|
|
303
|
+
<span class="cline-any cline-neutral"> </span>
|
|
304
|
+
<span class="cline-any cline-neutral"> </span>
|
|
305
|
+
<span class="cline-any cline-yes">1x</span>
|
|
306
|
+
<span class="cline-any cline-neutral"> </span>
|
|
307
|
+
<span class="cline-any cline-yes">1x</span>
|
|
308
|
+
<span class="cline-any cline-yes">8x</span>
|
|
309
|
+
<span class="cline-any cline-neutral"> </span>
|
|
310
|
+
<span class="cline-any cline-yes">1x</span>
|
|
311
|
+
<span class="cline-any cline-yes">1x</span>
|
|
312
|
+
<span class="cline-any cline-yes">1x</span>
|
|
313
|
+
<span class="cline-any cline-neutral"> </span>
|
|
314
|
+
<span class="cline-any cline-neutral"> </span>
|
|
315
|
+
<span class="cline-any cline-neutral"> </span>
|
|
316
|
+
<span class="cline-any cline-neutral"> </span>
|
|
317
|
+
<span class="cline-any cline-neutral"> </span>
|
|
318
|
+
<span class="cline-any cline-yes">1x</span>
|
|
319
|
+
<span class="cline-any cline-yes">1x</span>
|
|
320
|
+
<span class="cline-any cline-yes">1x</span>
|
|
321
|
+
<span class="cline-any cline-yes">1x</span>
|
|
322
|
+
<span class="cline-any cline-neutral"> </span>
|
|
323
|
+
<span class="cline-any cline-yes">1x</span>
|
|
324
|
+
<span class="cline-any cline-neutral"> </span>
|
|
325
|
+
<span class="cline-any cline-yes">1x</span>
|
|
326
|
+
<span class="cline-any cline-yes">1x</span>
|
|
327
|
+
<span class="cline-any cline-neutral"> </span>
|
|
328
|
+
<span class="cline-any cline-no"> </span>
|
|
329
|
+
<span class="cline-any cline-neutral"> </span>
|
|
330
|
+
<span class="cline-any cline-neutral"> </span>
|
|
331
|
+
<span class="cline-any cline-yes">1x</span>
|
|
332
|
+
<span class="cline-any cline-yes">1x</span>
|
|
333
|
+
<span class="cline-any cline-yes">1x</span>
|
|
334
|
+
<span class="cline-any cline-neutral"> </span>
|
|
335
|
+
<span class="cline-any cline-neutral"> </span>
|
|
336
|
+
<span class="cline-any cline-yes">1x</span>
|
|
337
|
+
<span class="cline-any cline-yes">1x</span>
|
|
338
|
+
<span class="cline-any cline-yes">1x</span>
|
|
339
|
+
<span class="cline-any cline-yes">1x</span>
|
|
340
|
+
<span class="cline-any cline-neutral"> </span>
|
|
341
|
+
<span class="cline-any cline-neutral"> </span>
|
|
342
|
+
<span class="cline-any cline-yes">1x</span>
|
|
343
|
+
<span class="cline-any cline-yes">1x</span>
|
|
344
|
+
<span class="cline-any cline-neutral"> </span>
|
|
345
|
+
<span class="cline-any cline-yes">1x</span>
|
|
346
|
+
<span class="cline-any cline-yes">1x</span>
|
|
347
|
+
<span class="cline-any cline-neutral"> </span>
|
|
348
|
+
<span class="cline-any cline-neutral"> </span>
|
|
349
|
+
<span class="cline-any cline-no"> </span>
|
|
350
|
+
<span class="cline-any cline-no"> </span>
|
|
351
|
+
<span class="cline-any cline-neutral"> </span>
|
|
352
|
+
<span class="cline-any cline-neutral"> </span>
|
|
353
|
+
<span class="cline-any cline-neutral"> </span>
|
|
354
|
+
<span class="cline-any cline-neutral"> </span>
|
|
355
|
+
<span class="cline-any cline-no"> </span>
|
|
356
|
+
<span class="cline-any cline-no"> </span>
|
|
357
|
+
<span class="cline-any cline-neutral"> </span>
|
|
358
|
+
<span class="cline-any cline-neutral"> </span>
|
|
359
|
+
<span class="cline-any cline-neutral"> </span>
|
|
360
|
+
<span class="cline-any cline-no"> </span>
|
|
361
|
+
<span class="cline-any cline-no"> </span>
|
|
362
|
+
<span class="cline-any cline-no"> </span>
|
|
363
|
+
<span class="cline-any cline-neutral"> </span>
|
|
364
|
+
<span class="cline-any cline-neutral"> </span>
|
|
365
|
+
<span class="cline-any cline-neutral"> </span>
|
|
366
|
+
<span class="cline-any cline-neutral"> </span>
|
|
367
|
+
<span class="cline-any cline-neutral"> </span>
|
|
368
|
+
<span class="cline-any cline-neutral"> </span>
|
|
369
|
+
<span class="cline-any cline-neutral"> </span>
|
|
370
|
+
<span class="cline-any cline-neutral"> </span>
|
|
371
|
+
<span class="cline-any cline-neutral"> </span>
|
|
372
|
+
<span class="cline-any cline-neutral"> </span>
|
|
373
|
+
<span class="cline-any cline-neutral"> </span>
|
|
374
|
+
<span class="cline-any cline-neutral"> </span>
|
|
375
|
+
<span class="cline-any cline-neutral"> </span>
|
|
376
|
+
<span class="cline-any cline-no"> </span>
|
|
377
|
+
<span class="cline-any cline-no"> </span>
|
|
378
|
+
<span class="cline-any cline-no"> </span>
|
|
379
|
+
<span class="cline-any cline-neutral"> </span>
|
|
380
|
+
<span class="cline-any cline-no"> </span>
|
|
381
|
+
<span class="cline-any cline-no"> </span>
|
|
382
|
+
<span class="cline-any cline-no"> </span>
|
|
383
|
+
<span class="cline-any cline-no"> </span>
|
|
384
|
+
<span class="cline-any cline-neutral"> </span>
|
|
385
|
+
<span class="cline-any cline-neutral"> </span>
|
|
386
|
+
<span class="cline-any cline-neutral"> </span>
|
|
387
|
+
<span class="cline-any cline-no"> </span>
|
|
388
|
+
<span class="cline-any cline-no"> </span>
|
|
389
|
+
<span class="cline-any cline-neutral"> </span>
|
|
390
|
+
<span class="cline-any cline-no"> </span>
|
|
391
|
+
<span class="cline-any cline-neutral"> </span>
|
|
392
|
+
<span class="cline-any cline-neutral"> </span>
|
|
393
|
+
<span class="cline-any cline-neutral"> </span>
|
|
394
|
+
<span class="cline-any cline-no"> </span>
|
|
395
|
+
<span class="cline-any cline-no"> </span>
|
|
396
|
+
<span class="cline-any cline-neutral"> </span>
|
|
397
|
+
<span class="cline-any cline-no"> </span>
|
|
398
|
+
<span class="cline-any cline-neutral"> </span>
|
|
399
|
+
<span class="cline-any cline-neutral"> </span>
|
|
400
|
+
<span class="cline-any cline-neutral"> </span>
|
|
401
|
+
<span class="cline-any cline-neutral"> </span>
|
|
402
|
+
<span class="cline-any cline-neutral"> </span>
|
|
403
|
+
<span class="cline-any cline-no"> </span>
|
|
404
|
+
<span class="cline-any cline-neutral"> </span>
|
|
405
|
+
<span class="cline-any cline-neutral"> </span>
|
|
406
|
+
<span class="cline-any cline-no"> </span>
|
|
407
|
+
<span class="cline-any cline-no"> </span>
|
|
408
|
+
<span class="cline-any cline-no"> </span>
|
|
409
|
+
<span class="cline-any cline-neutral"> </span>
|
|
410
|
+
<span class="cline-any cline-neutral"> </span>
|
|
411
|
+
<span class="cline-any cline-no"> </span>
|
|
412
|
+
<span class="cline-any cline-no"> </span>
|
|
413
|
+
<span class="cline-any cline-neutral"> </span>
|
|
414
|
+
<span class="cline-any cline-no"> </span>
|
|
415
|
+
<span class="cline-any cline-no"> </span>
|
|
416
|
+
<span class="cline-any cline-no"> </span>
|
|
417
|
+
<span class="cline-any cline-neutral"> </span>
|
|
418
|
+
<span class="cline-any cline-no"> </span>
|
|
419
|
+
<span class="cline-any cline-neutral"> </span>
|
|
420
|
+
<span class="cline-any cline-neutral"> </span>
|
|
421
|
+
<span class="cline-any cline-neutral"> </span>
|
|
422
|
+
<span class="cline-any cline-neutral"> </span>
|
|
423
|
+
<span class="cline-any cline-neutral"> </span>
|
|
424
|
+
<span class="cline-any cline-neutral"> </span>
|
|
425
|
+
<span class="cline-any cline-neutral"> </span>
|
|
426
|
+
<span class="cline-any cline-neutral"> </span>
|
|
427
|
+
<span class="cline-any cline-no"> </span>
|
|
428
|
+
<span class="cline-any cline-neutral"> </span>
|
|
429
|
+
<span class="cline-any cline-neutral"> </span>
|
|
430
|
+
<span class="cline-any cline-neutral"> </span>
|
|
431
|
+
<span class="cline-any cline-neutral"> </span>
|
|
432
|
+
<span class="cline-any cline-neutral"> </span>
|
|
433
|
+
<span class="cline-any cline-no"> </span>
|
|
434
|
+
<span class="cline-any cline-no"> </span>
|
|
435
|
+
<span class="cline-any cline-no"> </span>
|
|
436
|
+
<span class="cline-any cline-no"> </span>
|
|
437
|
+
<span class="cline-any cline-neutral"> </span>
|
|
438
|
+
<span class="cline-any cline-neutral"> </span>
|
|
439
|
+
<span class="cline-any cline-no"> </span>
|
|
440
|
+
<span class="cline-any cline-neutral"> </span>
|
|
441
|
+
<span class="cline-any cline-neutral"> </span>
|
|
442
|
+
<span class="cline-any cline-neutral"> </span>
|
|
443
|
+
<span class="cline-any cline-neutral"> </span>
|
|
444
|
+
<span class="cline-any cline-neutral"> </span>
|
|
445
|
+
<span class="cline-any cline-neutral"> </span>
|
|
446
|
+
<span class="cline-any cline-neutral"> </span>
|
|
447
|
+
<span class="cline-any cline-no"> </span>
|
|
448
|
+
<span class="cline-any cline-no"> </span>
|
|
449
|
+
<span class="cline-any cline-neutral"> </span>
|
|
450
|
+
<span class="cline-any cline-neutral"> </span>
|
|
451
|
+
<span class="cline-any cline-neutral"> </span>
|
|
452
|
+
<span class="cline-any cline-neutral"> </span></td><td class="text"><pre class="prettyprint lang-js">import { basename, join, dirname } from 'node:path';
|
|
453
|
+
import { copyFileSync, cpSync, mkdirSync, mkdtempSync, rmSync, existsSync } from 'node:fs';
|
|
454
|
+
import { tmpdir } from 'node:os';
|
|
455
|
+
import { execGitNonInteractive } from '../utils/exec.js';
|
|
456
|
+
import { buildLocalEventContext } from '../cli/context.js';
|
|
457
|
+
import { resolveSkillAsync } from '../skills/loader.js';
|
|
458
|
+
import { runSkill } from '../sdk/runner.js';
|
|
459
|
+
import { formatEvalId } from './names.js';
|
|
460
|
+
import type { EvalMeta } from './types.js';
|
|
461
|
+
import type { Finding, SkillReport } from '../types/index.js';
|
|
462
|
+
import type { FindingProcessingEvent } from '../sdk/runner.js';
|
|
463
|
+
import type { RuntimeName } from '../sdk/runtimes/types.js';
|
|
464
|
+
|
|
465
|
+
export interface RunEvalOptions {
|
|
466
|
+
/** Anthropic API key */
|
|
467
|
+
apiKey: string;
|
|
468
|
+
/** Override the model from the YAML spec */
|
|
469
|
+
model?: string;
|
|
470
|
+
/** Override the runtime from the YAML spec */
|
|
471
|
+
runtime?: RuntimeName;
|
|
472
|
+
/** Enable verbose logging */
|
|
473
|
+
verbose?: boolean;
|
|
474
|
+
}
|
|
475
|
+
|
|
476
|
+
export interface EvalSkillRunResult {
|
|
477
|
+
/** Display name (e.g. "code-review/case") */
|
|
478
|
+
name: string;
|
|
479
|
+
/** Eval metadata */
|
|
480
|
+
meta: EvalMeta;
|
|
481
|
+
/** Skill report from the agent run */
|
|
482
|
+
report: SkillReport;
|
|
483
|
+
/** Verbose logs from the agent run */
|
|
484
|
+
logs: string[];
|
|
485
|
+
/** Duration of the skill run in ms */
|
|
486
|
+
durationMs: number;
|
|
487
|
+
}
|
|
488
|
+
|
|
489
|
+
/**
|
|
490
|
+
* Set up a temporary git repository for an eval scenario.
|
|
491
|
+
*
|
|
492
|
+
* Creates a real git repo with a `main` commit containing the skill definition
|
|
493
|
+
* and an `eval` branch containing only fixture files. This gives
|
|
494
|
+
* the agent a real git environment to explore with Read/Grep and produces
|
|
495
|
+
* real git diffs for the pipeline to parse.
|
|
496
|
+
*/
|
|
497
|
+
export function setupEvalRepo(meta: EvalMeta, log: (msg: string) => void): string {
|
|
498
|
+
const tmpDir = mkdtempSync(join(tmpdir(), `warden-eval-${meta.name}-`));
|
|
499
|
+
|
|
500
|
+
try {
|
|
501
|
+
const git = (args: string[]) => execGitNonInteractive(args, { cwd: tmpDir });
|
|
502
|
+
|
|
503
|
+
git(['init', '--initial-branch=main']);
|
|
504
|
+
git(['config', 'user.email', 'eval@warden.dev']);
|
|
505
|
+
git(['config', 'user.name', 'Warden Eval']);
|
|
506
|
+
|
|
507
|
+
// Copy skill into repo. If it lives in a directory (skill-name/SKILL.md),
|
|
508
|
+
// copy the whole directory to preserve resource subdirs (scripts/, references/).
|
|
509
|
+
// For flat .md files, just copy the single file. Commit it on main so eval
|
|
510
|
+
// diffs contain only fixture code, not the skill used to run the eval.
|
|
511
|
+
const skillSrcDir = dirname(meta.skillPath);
|
|
512
|
+
const skillMarker = join(skillSrcDir, 'SKILL.md');
|
|
513
|
+
const skillDestDir = join(tmpDir, '.warden', 'skills');
|
|
514
|
+
mkdirSync(skillDestDir, { recursive: true });
|
|
515
|
+
|
|
516
|
+
if (existsSync(skillMarker)) {
|
|
517
|
+
// Directory-format skill: copy entire directory to preserve resources
|
|
518
|
+
const skillDirName = basename(skillSrcDir);
|
|
519
|
+
cpSync(skillSrcDir, join(skillDestDir, skillDirName), { recursive: true });
|
|
520
|
+
} else <span class="missing-if-branch" title="else path not taken" >E</span>{
|
|
521
|
+
<span class="cstat-no" title="statement not covered" > copyFileSync(meta.skillPath, join(skillDestDir, basename(meta.skillPath)));</span>
|
|
522
|
+
}
|
|
523
|
+
|
|
524
|
+
git(['add', '.']);
|
|
525
|
+
git(['commit', '-m', 'install eval skill']);
|
|
526
|
+
git(['checkout', '-b', 'eval']);
|
|
527
|
+
|
|
528
|
+
// Copy fixture files, preserving their parent directory name
|
|
529
|
+
for (const srcPath of meta.filePaths) {
|
|
530
|
+
const destDir = join(tmpDir, basename(dirname(srcPath)));
|
|
531
|
+
mkdirSync(destDir, { recursive: true });
|
|
532
|
+
copyFileSync(srcPath, join(destDir, basename(srcPath)));
|
|
533
|
+
}
|
|
534
|
+
|
|
535
|
+
git(['add', '.']);
|
|
536
|
+
git(['commit', '-m', `add fixture: ${meta.name}`]);
|
|
537
|
+
|
|
538
|
+
log(`Repo ready: ${tmpDir} (${meta.filePaths.length} file(s))`);
|
|
539
|
+
return tmpDir;
|
|
540
|
+
} catch (error) {
|
|
541
|
+
// Clean up on partial failure so we don't leak temp directories
|
|
542
|
+
<span class="cstat-no" title="statement not covered" > rmSync(tmpDir, { recursive: true, force: true });</span>
|
|
543
|
+
<span class="cstat-no" title="statement not covered" > throw error;</span>
|
|
544
|
+
}
|
|
545
|
+
}
|
|
546
|
+
|
|
547
|
+
function <span class="fstat-no" title="function not covered" >formatFinding(f</span>inding: Finding): string {
|
|
548
|
+
const loc = <span class="cstat-no" title="statement not covered" >finding.location ? `${finding.location.path}:${finding.location.startLine}` : 'general';</span>
|
|
549
|
+
<span class="cstat-no" title="statement not covered" > return `${loc} "${finding.title}"`;</span>
|
|
550
|
+
}
|
|
551
|
+
|
|
552
|
+
function <span class="fstat-no" title="function not covered" >formatFindingProcessingEvent(e</span>vent: FindingProcessingEvent): string {
|
|
553
|
+
const reason = <span class="cstat-no" title="statement not covered" >event.reason ? ` (${event.reason})` : '';</span>
|
|
554
|
+
const replacement = <span class="cstat-no" title="statement not covered" >event.replacement ? ` -> ${formatFinding(event.replacement)}` : '';</span>
|
|
555
|
+
<span class="cstat-no" title="statement not covered" > return `Finding ${event.stage}:${event.action} ${formatFinding(event.finding)}${replacement}${reason}`;</span>
|
|
556
|
+
}
|
|
557
|
+
|
|
558
|
+
/**
|
|
559
|
+
* Run a single eval scenario through Warden's skill pipeline.
|
|
560
|
+
*
|
|
561
|
+
* The only thing mocked is the GitHub event payload (no real PR).
|
|
562
|
+
* Everything else runs for real: git repo, diff parsing, SDK invocation,
|
|
563
|
+
* agent with Read/Grep tools, and finding extraction.
|
|
564
|
+
*/
|
|
565
|
+
export async function <span class="fstat-no" title="function not covered" >runEvalSkill(</span>
|
|
566
|
+
meta: EvalMeta,
|
|
567
|
+
options: RunEvalOptions
|
|
568
|
+
): Promise<EvalSkillRunResult> {
|
|
569
|
+
const startTime = <span class="cstat-no" title="statement not covered" >Date.now();</span>
|
|
570
|
+
const <span class="cstat-no" title="statement not covered" >name = formatEvalId(meta);</span>
|
|
571
|
+
const logs: string[] = <span class="cstat-no" title="statement not covered" >[];</span>
|
|
572
|
+
|
|
573
|
+
const log = <span class="cstat-no" title="statement not covered" ><span class="fstat-no" title="function not covered" >(m</span>sg: string): void => {</span>
|
|
574
|
+
<span class="cstat-no" title="statement not covered" > logs.push(`[${Date.now() - startTime}ms] ${msg}`);</span>
|
|
575
|
+
<span class="cstat-no" title="statement not covered" > if (options.verbose) {</span>
|
|
576
|
+
<span class="cstat-no" title="statement not covered" > console.log(` [eval:${name}] ${msg}`);</span>
|
|
577
|
+
}
|
|
578
|
+
};
|
|
579
|
+
|
|
580
|
+
<span class="cstat-no" title="statement not covered" > if (meta.filePaths.length === 0) {</span>
|
|
581
|
+
<span class="cstat-no" title="statement not covered" > throw new Error(`No fixture files specified for eval: ${name}`);</span>
|
|
582
|
+
}
|
|
583
|
+
<span class="cstat-no" title="statement not covered" > log(`Fixture file(s): ${meta.filePaths.map(<span class="fstat-no" title="function not covered" >(f</span>) => <span class="cstat-no" title="statement not covered" >f.split('/').pop())</span>.join(', ')}`);</span>
|
|
584
|
+
|
|
585
|
+
let repoDir: string | undefined;
|
|
586
|
+
|
|
587
|
+
<span class="cstat-no" title="statement not covered" > try {</span>
|
|
588
|
+
<span class="cstat-no" title="statement not covered" > repoDir = setupEvalRepo(meta, log);</span>
|
|
589
|
+
|
|
590
|
+
const <span class="cstat-no" title="statement not covered" >context = buildLocalEventContext({</span>
|
|
591
|
+
base: 'main',
|
|
592
|
+
head: 'eval',
|
|
593
|
+
cwd: repoDir,
|
|
594
|
+
defaultBranch: 'main',
|
|
595
|
+
});
|
|
596
|
+
<span class="cstat-no" title="statement not covered" > log(`Context built: ${context.pullRequest?.files.length ?? 0} file(s) from git diff`);</span>
|
|
597
|
+
|
|
598
|
+
// Resolve skill from where setupEvalRepo placed it
|
|
599
|
+
const <span class="cstat-no" title="statement not covered" >skillSrcDir = dirname(meta.skillPath);</span>
|
|
600
|
+
const <span class="cstat-no" title="statement not covered" >isDirectorySkill = existsSync(join(skillSrcDir, 'SKILL.md'));</span>
|
|
601
|
+
const skillPath = <span class="cstat-no" title="statement not covered" >isDirectorySkill</span>
|
|
602
|
+
? join(repoDir, '.warden', 'skills', basename(skillSrcDir))
|
|
603
|
+
: join(repoDir, '.warden', 'skills', basename(meta.skillPath));
|
|
604
|
+
const skill = <span class="cstat-no" title="statement not covered" >await resolveSkillAsync(skillPath);</span>
|
|
605
|
+
<span class="cstat-no" title="statement not covered" > log(`Skill resolved: ${skill.name}`);</span>
|
|
606
|
+
|
|
607
|
+
const model = <span class="cstat-no" title="statement not covered" >options.model ?? meta.model;</span>
|
|
608
|
+
const runtime = <span class="cstat-no" title="statement not covered" >options.runtime ?? meta.runtime;</span>
|
|
609
|
+
<span class="cstat-no" title="statement not covered" > log(`Running skill with model: ${model} [${runtime}]`);</span>
|
|
610
|
+
|
|
611
|
+
const report = <span class="cstat-no" title="statement not covered" >await runSkill(skill, context, {</span>
|
|
612
|
+
apiKey: options.apiKey,
|
|
613
|
+
model,
|
|
614
|
+
runtime,
|
|
615
|
+
verbose: options.verbose,
|
|
616
|
+
parallel: false,
|
|
617
|
+
callbacks: options.verbose
|
|
618
|
+
? {
|
|
619
|
+
onFindingProcessing: <span class="fstat-no" title="function not covered" >(e</span>vent) => {
|
|
620
|
+
<span class="cstat-no" title="statement not covered" > log(formatFindingProcessingEvent(event));</span>
|
|
621
|
+
},
|
|
622
|
+
}
|
|
623
|
+
: undefined,
|
|
624
|
+
});
|
|
625
|
+
|
|
626
|
+
<span class="cstat-no" title="statement not covered" > log(`Skill complete: ${report.findings.length} finding(s)`);</span>
|
|
627
|
+
<span class="cstat-no" title="statement not covered" > for (const finding of report.findings) {</span>
|
|
628
|
+
const loc = <span class="cstat-no" title="statement not covered" >finding.location ? ` (${finding.location.path}:${finding.location.startLine})` : '';</span>
|
|
629
|
+
<span class="cstat-no" title="statement not covered" > log(` [${finding.severity}] ${finding.title}${loc}`);</span>
|
|
630
|
+
}
|
|
631
|
+
|
|
632
|
+
<span class="cstat-no" title="statement not covered" > return {</span>
|
|
633
|
+
name,
|
|
634
|
+
meta,
|
|
635
|
+
report,
|
|
636
|
+
logs,
|
|
637
|
+
durationMs: Date.now() - startTime,
|
|
638
|
+
};
|
|
639
|
+
} finally {
|
|
640
|
+
<span class="cstat-no" title="statement not covered" > if (repoDir) {</span>
|
|
641
|
+
<span class="cstat-no" title="statement not covered" > rmSync(repoDir, { recursive: true, force: true });</span>
|
|
642
|
+
}
|
|
643
|
+
}
|
|
644
|
+
}
|
|
645
|
+
</pre></td></tr></table></pre>
|
|
646
|
+
|
|
647
|
+
<div class='push'></div><!-- for sticky footer -->
|
|
648
|
+
</div><!-- /wrapper -->
|
|
649
|
+
<div class='footer quiet pad2 space-top1 center small'>
|
|
650
|
+
Code coverage generated by
|
|
651
|
+
<a href="https://istanbul.js.org/" target="_blank" rel="noopener noreferrer">istanbul</a>
|
|
652
|
+
at 2026-05-17T04:35:52.381Z
|
|
653
|
+
</div>
|
|
654
|
+
<script src="../../prettify.js"></script>
|
|
655
|
+
<script>
|
|
656
|
+
window.onload = function () {
|
|
657
|
+
prettyPrint();
|
|
658
|
+
};
|
|
659
|
+
</script>
|
|
660
|
+
<script src="../../sorter.js"></script>
|
|
661
|
+
<script src="../../block-navigation.js"></script>
|
|
662
|
+
</body>
|
|
663
|
+
</html>
|
|
664
|
+
|