@iowarp/clio-coder 0.3.0
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 +407 -0
- package/CODE_OF_CONDUCT.md +21 -0
- package/CONTRIBUTING.md +224 -0
- package/LICENSE +202 -0
- package/NOTICE +9 -0
- package/README.md +798 -0
- package/SECURITY.md +72 -0
- package/assets/clio-coder-logo-128.webp +0 -0
- package/damage-control-rules.yaml +419 -0
- package/dist/acp-UMLFVA3F.js +92 -0
- package/dist/agents-Q4MYPMUW.js +91 -0
- package/dist/auth-O6HYIJ6J.js +521 -0
- package/dist/chunk-262G75JS.js +35 -0
- package/dist/chunk-26BZQOAD.js +1281 -0
- package/dist/chunk-2J63S4SF.js +508 -0
- package/dist/chunk-3DANZDGR.js +717 -0
- package/dist/chunk-4UQA7NCT.js +29 -0
- package/dist/chunk-527KG6XR.js +497 -0
- package/dist/chunk-5LDRNKX2.js +1063 -0
- package/dist/chunk-5N2FG33Q.js +25 -0
- package/dist/chunk-67MTHP2E.js +135 -0
- package/dist/chunk-6CWDTGUC.js +20 -0
- package/dist/chunk-7BHLZB3A.js +2115 -0
- package/dist/chunk-7RBKDI66.js +348 -0
- package/dist/chunk-AMFR5YA3.js +541 -0
- package/dist/chunk-BBUH4VAA.js +1224 -0
- package/dist/chunk-BYEU76JP.js +899 -0
- package/dist/chunk-CLJ5HLUD.js +458 -0
- package/dist/chunk-D5YD55AR.js +116 -0
- package/dist/chunk-DXQNI4PC.js +61 -0
- package/dist/chunk-E3NYWENM.js +1004 -0
- package/dist/chunk-GNGDQYDU.js +34688 -0
- package/dist/chunk-GOTUR54M.js +9 -0
- package/dist/chunk-HBU5MTAM.js +41 -0
- package/dist/chunk-HMYNFFY4.js +28 -0
- package/dist/chunk-JPOWPFCU.js +1010 -0
- package/dist/chunk-JWHCJDCI.js +1215 -0
- package/dist/chunk-KBR4MZZR.js +41 -0
- package/dist/chunk-KKKPTZLM.js +93 -0
- package/dist/chunk-ME6DNWIU.js +66 -0
- package/dist/chunk-NI4DEJMC.js +88 -0
- package/dist/chunk-O4EJEDHO.js +659 -0
- package/dist/chunk-PIDUD6M2.js +31 -0
- package/dist/chunk-PS4PFJQP.js +29459 -0
- package/dist/chunk-QV47YRF4.js +48 -0
- package/dist/chunk-RQDWMVRB.js +279 -0
- package/dist/chunk-TFSSEXL6.js +136 -0
- package/dist/chunk-TKHQ4DGZ.js +8290 -0
- package/dist/chunk-TPOCL34A.js +2876 -0
- package/dist/chunk-UGYAX5YI.js +565 -0
- package/dist/chunk-UHTSULZS.js +461 -0
- package/dist/chunk-UU3R62TT.js +128 -0
- package/dist/chunk-UWIJNAOB.js +3906 -0
- package/dist/chunk-VOO7NYPP.js +914 -0
- package/dist/chunk-VPAWTYLY.js +117 -0
- package/dist/chunk-WD6AJM35.js +1216 -0
- package/dist/chunk-X3BR7HWV.js +115 -0
- package/dist/chunk-X3NE4WVW.js +120 -0
- package/dist/chunk-XNISANGE.js +1395 -0
- package/dist/chunk-XV4ZJ6ZM.js +3177 -0
- package/dist/cli/index.js +236 -0
- package/dist/clio-KIQ5SNDS.js +53 -0
- package/dist/components-JVHMUBEB.js +653 -0
- package/dist/config-ZFCDBMDC.js +372 -0
- package/dist/configure-G4E3A2PG.js +27 -0
- package/dist/context-CDXTP2MP.js +293 -0
- package/dist/context-E3KIFVXI.js +185 -0
- package/dist/context-clear-3F4PLXOS.js +102 -0
- package/dist/context-index-Q7YSYTR3.js +106 -0
- package/dist/docs-YIETIWZI.js +280 -0
- package/dist/doctor-M5HJJZOL.js +61 -0
- package/dist/domains/agents/builtins/architect.md +33 -0
- package/dist/domains/agents/builtins/coder.md +31 -0
- package/dist/domains/agents/builtins/context-bootstrap.md +38 -0
- package/dist/domains/agents/builtins/debugger.md +30 -0
- package/dist/domains/agents/builtins/documenter.md +31 -0
- package/dist/domains/agents/builtins/git-master.md +30 -0
- package/dist/domains/agents/builtins/provenance.md +30 -0
- package/dist/domains/agents/builtins/researcher.md +71 -0
- package/dist/domains/agents/builtins/scout.md +42 -0
- package/dist/domains/agents/builtins/tester.md +31 -0
- package/dist/domains/agents/builtins/verifier.md +30 -0
- package/dist/domains/agents/builtins/wiki-writer.md +41 -0
- package/dist/eval-B3KZZESM.js +2674 -0
- package/dist/evidence-V67CHM35.js +233 -0
- package/dist/evolve-YDZSUQYA.js +518 -0
- package/dist/extensions-SRG7XCAH.js +207 -0
- package/dist/fleet-CA2CRTVG.js +760 -0
- package/dist/fleet-preflight-CLIAX7YR.js +21 -0
- package/dist/init-2OZDJE2D.js +227 -0
- package/dist/memory-3PIQQAKX.js +207 -0
- package/dist/models-DY35XI7Y.js +237 -0
- package/dist/paths-5OMXW7Z4.js +57 -0
- package/dist/preload-KZVHET2B.js +11 -0
- package/dist/reset-PIFYNOS3.js +216 -0
- package/dist/run-3VSPP24F.js +735 -0
- package/dist/share-D36RQCXM.js +241 -0
- package/dist/skills-F2MRLELY.js +445 -0
- package/dist/skills-eval-E2ZTW4PL.js +932 -0
- package/dist/targets-DZMEZAH4.js +977 -0
- package/dist/trace-7NYCUI2J.js +250 -0
- package/dist/uninstall-AD3JWHBB.js +322 -0
- package/dist/upgrade-WYYBKGDY.js +301 -0
- package/dist/usage-ULIDAGFF.js +755 -0
- package/dist/version-ROZ6CZKH.js +16 -0
- package/dist/wiki-generate-PKFIX6OB.js +377 -0
- package/dist/worker/entry.js +1739 -0
- package/docs/README.md +93 -0
- package/docs/acp.md +120 -0
- package/docs/alcf-provider.md +72 -0
- package/docs/architecture.md +172 -0
- package/docs/artifact-versions.md +54 -0
- package/docs/built-in-agents.md +265 -0
- package/docs/capacity-and-scheduling.md +97 -0
- package/docs/commands-and-modes.md +554 -0
- package/docs/config-knobs-audit.md +115 -0
- package/docs/configuration-and-targets.md +812 -0
- package/docs/context-engine.md +236 -0
- package/docs/dispatch-architecture-rationale.md +126 -0
- package/docs/documentation-coverage.md +46 -0
- package/docs/documentation-guide.md +166 -0
- package/docs/environment-variables.md +105 -0
- package/docs/eval-runner.md +205 -0
- package/docs/evals-internal.md +298 -0
- package/docs/evidence-and-memory.md +243 -0
- package/docs/evolution.md +143 -0
- package/docs/exit-codes-and-output.md +74 -0
- package/docs/extensions-and-sharing.md +306 -0
- package/docs/fleet-demo-runbook.md +179 -0
- package/docs/fleet-dispatch.md +591 -0
- package/docs/glossary.md +75 -0
- package/docs/html/agents_blueprint.html +936 -0
- package/docs/html/alcf_blueprint.html +324 -0
- package/docs/html/architecture_blueprint.html +850 -0
- package/docs/html/commands_blueprint.html +794 -0
- package/docs/html/config_knobs_audit_blueprint.html +178 -0
- package/docs/html/configuration_blueprint.html +1080 -0
- package/docs/html/context_blueprint.html +603 -0
- package/docs/html/documentation_blueprint.html +832 -0
- package/docs/html/environment_blueprint.html +404 -0
- package/docs/html/eval_blueprint.html +743 -0
- package/docs/html/evals_internal_blueprint.html +190 -0
- package/docs/html/evolution_blueprint.html +674 -0
- package/docs/html/extensions_blueprint.html +2065 -0
- package/docs/html/fleet_dispatch_blueprint.html +286 -0
- package/docs/html/index.html +919 -0
- package/docs/html/lifecycle_blueprint.html +723 -0
- package/docs/html/memory_blueprint.html +699 -0
- package/docs/html/middleware_blueprint.html +664 -0
- package/docs/html/models_blueprint.html +2366 -0
- package/docs/html/observability_blueprint.html +683 -0
- package/docs/html/provider_adapter_blueprint.html +245 -0
- package/docs/html/safety_blueprint.html +1386 -0
- package/docs/html/shared.css +571 -0
- package/docs/html/shared.js +143 -0
- package/docs/html/skills_blueprint.html +671 -0
- package/docs/html/soak_blueprint.html +182 -0
- package/docs/html/tool_usage_blueprint.html +350 -0
- package/docs/html/tools_blueprint.html +2249 -0
- package/docs/html/trace_blueprint.html +235 -0
- package/docs/html/tui_design_blueprint.html +314 -0
- package/docs/html/validation_blueprint.html +961 -0
- package/docs/html/worker_dispatch_blueprint.html +231 -0
- package/docs/installation-and-lifecycle.md +308 -0
- package/docs/middleware-and-components.md +148 -0
- package/docs/model-catalog.md +189 -0
- package/docs/observability.md +233 -0
- package/docs/proactive-memory.md +452 -0
- package/docs/prompt-envelope-and-tools.md +142 -0
- package/docs/provider-adapter-cookbook.md +148 -0
- package/docs/release-cut-checklist.md +138 -0
- package/docs/safety-model.md +357 -0
- package/docs/scientific-validation.md +105 -0
- package/docs/session-lifecycle.md +156 -0
- package/docs/skills-marketplace.md +46 -0
- package/docs/tool-usage.md +527 -0
- package/docs/trace-store.md +132 -0
- package/docs/troubleshooting.md +33 -0
- package/docs/tui-design.md +239 -0
- package/docs/worker-dispatch-mechanics.md +242 -0
- package/package.json +132 -0
- package/skills/README.md +408 -0
- package/skills/git/commit-crafting/SKILL.md +79 -0
- package/skills/git/commit-crafting/evals.md +92 -0
- package/skills/git/create-pr/SKILL.md +116 -0
- package/skills/git/create-pr/evals.md +114 -0
- package/skills/git/investigate-issue/SKILL.md +139 -0
- package/skills/git/investigate-issue/evals.md +94 -0
- package/skills/git/resolve-merge-conflicts/SKILL.md +96 -0
- package/skills/git/resolve-merge-conflicts/evals.md +58 -0
- package/skills/git/review-changes/SKILL.md +103 -0
- package/skills/git/review-changes/evals.md +85 -0
- package/skills/git/worktree-create/SKILL.md +92 -0
- package/skills/git/worktree-create/evals.md +97 -0
- package/skills/git/worktree-create/references/worktree-setup.md +66 -0
- package/skills/git/worktree-merge/SKILL.md +95 -0
- package/skills/git/worktree-merge/evals.md +114 -0
- package/skills/skill-marketplace.json +261 -0
- package/skills/workflow/cut-it/SKILL.md +86 -0
- package/skills/workflow/cut-it/evals.md +42 -0
- package/src/domains/agents/builtins/architect.md +33 -0
- package/src/domains/agents/builtins/coder.md +31 -0
- package/src/domains/agents/builtins/context-bootstrap.md +38 -0
- package/src/domains/agents/builtins/debugger.md +30 -0
- package/src/domains/agents/builtins/documenter.md +31 -0
- package/src/domains/agents/builtins/git-master.md +30 -0
- package/src/domains/agents/builtins/provenance.md +30 -0
- package/src/domains/agents/builtins/researcher.md +71 -0
- package/src/domains/agents/builtins/scout.md +42 -0
- package/src/domains/agents/builtins/tester.md +31 -0
- package/src/domains/agents/builtins/verifier.md +30 -0
- package/src/domains/agents/builtins/wiki-writer.md +41 -0
- package/src/domains/agents/fleets/build-review.md +34 -0
- package/src/domains/agents/fleets/build-test.md +35 -0
- package/src/domains/agents/fleets/sdlc.md +86 -0
- package/src/domains/prompts/fragments/identity/clio-worker.md +11 -0
- package/src/domains/prompts/fragments/identity/clio.md +26 -0
- package/src/domains/prompts/fragments/operating/contract.md +64 -0
- package/src/domains/prompts/fragments/safety/auto-edit.md +14 -0
- package/src/domains/prompts/fragments/safety/full-auto.md +14 -0
- package/src/domains/prompts/fragments/safety/read-only.md +13 -0
- package/src/domains/prompts/fragments/safety/suggest.md +13 -0
- package/src/domains/prompts/fragments/wiki/page.md +75 -0
- package/src/domains/prompts/fragments/wiki/plan.md +48 -0
- package/src/domains/providers/models/cloud-models/alcf.yaml +40 -0
- package/src/domains/providers/models/local-models/clio-local-coding-targets.yaml +993 -0
|
@@ -0,0 +1,190 @@
|
|
|
1
|
+
<!DOCTYPE html>
|
|
2
|
+
<html lang="en">
|
|
3
|
+
<head>
|
|
4
|
+
<meta charset="UTF-8">
|
|
5
|
+
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
|
6
|
+
<title>Internal Eval Suites Blueprint (v0.3.0)</title>
|
|
7
|
+
<link rel="stylesheet" href="shared.css">
|
|
8
|
+
<style>
|
|
9
|
+
.internal-warning {
|
|
10
|
+
background: rgba(239, 68, 68, 0.08);
|
|
11
|
+
border: 1px solid rgba(239, 68, 68, 0.3);
|
|
12
|
+
color: var(--color-rose);
|
|
13
|
+
padding: 1rem;
|
|
14
|
+
border-radius: 8px;
|
|
15
|
+
margin-bottom: 2rem;
|
|
16
|
+
font-size: 0.9rem;
|
|
17
|
+
}
|
|
18
|
+
</style>
|
|
19
|
+
</head>
|
|
20
|
+
<body>
|
|
21
|
+
<div class="container">
|
|
22
|
+
<header>
|
|
23
|
+
<div class="header-left">
|
|
24
|
+
<div class="header-logo">
|
|
25
|
+
<svg viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" style="color: var(--color-rose);"><title>Icon</title>
|
|
26
|
+
<path d="M10.29 3.86L1.82 18a2 2 0 0 0 1.71 3h16.94a2 2 0 0 0 1.71-3L13.71 3.86a2 2 0 0 0-3.42 0z"></path>
|
|
27
|
+
<line x1="12" y1="9" x2="12" y2="13"></line>
|
|
28
|
+
<line x1="12" y1="17" x2="12.01" y2="17"></line>
|
|
29
|
+
</svg>
|
|
30
|
+
</div>
|
|
31
|
+
<div class="header-title-wrapper">
|
|
32
|
+
<h1 style="background: linear-gradient(to right, #ffffff, #c7d2fe, var(--color-rose)); -webkit-background-clip: text; -webkit-text-fill-color: transparent;">Internal Eval Suites</h1>
|
|
33
|
+
<p>Private validation matrices, regression seeds, and offline datasets guidelines</p>
|
|
34
|
+
<div class="meta-chips-row">
|
|
35
|
+
<span class="chip">Source: docs/evals-internal.md</span>
|
|
36
|
+
<span class="chip chip-orange" style="color: var(--color-rose); border-color: rgba(239, 68, 68, 0.3); background: rgba(239, 68, 68, 0.05);">clio-coder docs evals_internal</span>
|
|
37
|
+
</div>
|
|
38
|
+
</div>
|
|
39
|
+
</div>
|
|
40
|
+
<div class="header-right">
|
|
41
|
+
<span class="version-badge" style="color: var(--color-rose); border-color: rgba(239, 68, 68, 0.3); background: rgba(239, 68, 68, 0.08);">Clio Coder v0.3.0 (Internal)</span>
|
|
42
|
+
<a href="index.html" class="back-btn">
|
|
43
|
+
<svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><title>Icon</title><line x1="19" y1="12" x2="5" y2="12"></line><polyline points="12 19 5 12 12 5"></polyline></svg>
|
|
44
|
+
Dashboard Hub
|
|
45
|
+
</a>
|
|
46
|
+
</div>
|
|
47
|
+
</header>
|
|
48
|
+
|
|
49
|
+
<div class="page-layout-grid">
|
|
50
|
+
<nav class="sidebar" aria-label="Table of Contents">
|
|
51
|
+
<div class="toc-container">
|
|
52
|
+
<div class="toc-title">On This Page</div>
|
|
53
|
+
<ul class="toc-list">
|
|
54
|
+
<!-- Dynamically populated -->
|
|
55
|
+
</ul>
|
|
56
|
+
</div>
|
|
57
|
+
</nav>
|
|
58
|
+
|
|
59
|
+
<main>
|
|
60
|
+
<div class="internal-warning">
|
|
61
|
+
<strong>INTERNAL DEVELOPMENT NOTICE:</strong> These specifications represent private datasets and validation benchmarks. Keep all raw calibration outputs and prompt matrices out of public pull requests.
|
|
62
|
+
</div>
|
|
63
|
+
|
|
64
|
+
<div class="glass-card">
|
|
65
|
+
<h2>Overview Summary</h2>
|
|
66
|
+
<p>Private evaluation suites operate locally. We run them from the repository root pointing to external paths, ensuring dataset privacy while validating orchestrator performance.</p>
|
|
67
|
+
</div>
|
|
68
|
+
|
|
69
|
+
<div class="tabs-nav">
|
|
70
|
+
<button type="button" class="tab-btn active" onclick="switchTab('seeds')">
|
|
71
|
+
Regression Seeds
|
|
72
|
+
</button>
|
|
73
|
+
<button type="button" class="tab-btn" onclick="switchTab('gates')">
|
|
74
|
+
Internal Gates Checklist
|
|
75
|
+
</button>
|
|
76
|
+
</div>
|
|
77
|
+
|
|
78
|
+
<!-- Tab 1: Seeds -->
|
|
79
|
+
<div class="tab-pane active" id="pane-seeds">
|
|
80
|
+
<div class="blueprint-layout">
|
|
81
|
+
<div class="specs-col">
|
|
82
|
+
<div class="glass-card">
|
|
83
|
+
<h3>Regression Seed Selector</h3>
|
|
84
|
+
<p>Select a seed pattern to view its YAML specification template:</p>
|
|
85
|
+
|
|
86
|
+
<div class="form-group">
|
|
87
|
+
<label for="seedSelect">YAML Seed</label>
|
|
88
|
+
<select id="seedSelect" onchange="updateSeedYaml()">
|
|
89
|
+
<option value="regression">Context Regression (context determinism)</option>
|
|
90
|
+
<option value="matrix">Model Matrix (target smoke suite)</option>
|
|
91
|
+
</select>
|
|
92
|
+
</div>
|
|
93
|
+
</div>
|
|
94
|
+
</div>
|
|
95
|
+
|
|
96
|
+
<div class="specs-col">
|
|
97
|
+
<div class="glass-card">
|
|
98
|
+
<h3>YAML Specification</h3>
|
|
99
|
+
<pre><code id="seedYamlCode">// Populated dynamically</code></pre>
|
|
100
|
+
</div>
|
|
101
|
+
</div>
|
|
102
|
+
</div>
|
|
103
|
+
</div>
|
|
104
|
+
|
|
105
|
+
<!-- Tab 2: Gates -->
|
|
106
|
+
<div class="tab-pane" id="pane-gates">
|
|
107
|
+
<div class="glass-card">
|
|
108
|
+
<h3>Internal Sanitization Gates</h3>
|
|
109
|
+
<p>Ensure these checks are satisfied before copy-promoting metrics summaries to <code>benchmarks/results/</code>:</p>
|
|
110
|
+
|
|
111
|
+
<div style="margin-top:1.5rem; display:flex; flex-direction:column; gap:1rem;">
|
|
112
|
+
<label class="checkbox-item"><input type="checkbox"> No secret tokens or private keys in target parameters.</label>
|
|
113
|
+
<label class="checkbox-item"><input type="checkbox"> Output logs are stripped of internal file path structures.</label>
|
|
114
|
+
<label class="checkbox-item"><input type="checkbox"> Evaded files are sanitized to `manifest.json` and `summary.json` only.</label>
|
|
115
|
+
<label class="checkbox-item"><input type="checkbox"> Run IDs do not expose host user names or local system metadata.</label>
|
|
116
|
+
</div>
|
|
117
|
+
</div>
|
|
118
|
+
</div>
|
|
119
|
+
|
|
120
|
+
<!-- Related Navigation -->
|
|
121
|
+
<nav class="related-nav" aria-label="Related Pages">
|
|
122
|
+
<a href="worker_dispatch_blueprint.html" class="nav-link-card">
|
|
123
|
+
<span class="nav-label">Previous Blueprint</span>
|
|
124
|
+
<span class="nav-title">Worker Dispatch Mechanics</span>
|
|
125
|
+
</a>
|
|
126
|
+
<a href="config_knobs_audit_blueprint.html" class="nav-link-card next">
|
|
127
|
+
<span class="nav-label">Next Blueprint</span>
|
|
128
|
+
<span class="nav-title">Config Knobs Audit</span>
|
|
129
|
+
</a>
|
|
130
|
+
</nav>
|
|
131
|
+
</main>
|
|
132
|
+
</div>
|
|
133
|
+
|
|
134
|
+
<footer>
|
|
135
|
+
<p>Clio Coder Internal Evals Blueprint • Version 0.3.0 • Gnosis Research Center</p>
|
|
136
|
+
</footer>
|
|
137
|
+
</div>
|
|
138
|
+
|
|
139
|
+
<script src="shared.js"></script>
|
|
140
|
+
<script>
|
|
141
|
+
const SEEDS = {
|
|
142
|
+
regression: `version: 2
|
|
143
|
+
suite:
|
|
144
|
+
id: internal-context-regression
|
|
145
|
+
title: Internal context regression
|
|
146
|
+
visibility: private
|
|
147
|
+
matrix:
|
|
148
|
+
targets:
|
|
149
|
+
- id: local
|
|
150
|
+
repeats: 3
|
|
151
|
+
tasks:
|
|
152
|
+
- id: context-index-private
|
|
153
|
+
workspace:
|
|
154
|
+
kind: local
|
|
155
|
+
path: .
|
|
156
|
+
runner:
|
|
157
|
+
kind: context-index
|
|
158
|
+
verify:
|
|
159
|
+
assertions:
|
|
160
|
+
- metric: context.indexedFiles
|
|
161
|
+
op: gt
|
|
162
|
+
value: 0`,
|
|
163
|
+
matrix: `version: 2
|
|
164
|
+
suite:
|
|
165
|
+
id: internal-model-matrix
|
|
166
|
+
title: Internal model matrix
|
|
167
|
+
visibility: private
|
|
168
|
+
matrix:
|
|
169
|
+
targets:
|
|
170
|
+
- id: local-fast
|
|
171
|
+
model: example-fast-model
|
|
172
|
+
- id: local-deep
|
|
173
|
+
model: example-deep-model
|
|
174
|
+
repeats: 2`
|
|
175
|
+
};
|
|
176
|
+
|
|
177
|
+
function updateSeedYaml() {
|
|
178
|
+
const val = document.getElementById("seedSelect").value;
|
|
179
|
+
document.getElementById("seedYamlCode").innerText = SEEDS[val];
|
|
180
|
+
if (window.initTableOfContents) window.initTableOfContents();
|
|
181
|
+
}
|
|
182
|
+
|
|
183
|
+
// Init
|
|
184
|
+
window.onload = () => {
|
|
185
|
+
updateSeedYaml();
|
|
186
|
+
window.updateSeedYaml = updateSeedYaml;
|
|
187
|
+
};
|
|
188
|
+
</script>
|
|
189
|
+
</body>
|
|
190
|
+
</html>
|