matt/recon
1
0
Fork 0
mirror of https://github.com/zvx-echo6/recon.git synced 2026-05-20 06:34:40 +02:00
Code Issues Projects Releases Packages Wiki Activity

Initial commit: RECON codebase baseline

Browse source 
Current state of the pipeline code as of 2026-04-14 (Phase 1 scaffolding complete).
Config has new_pipeline.enabled=false and crawler.sites=[] per refactor plan.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Matt 2026-04-14 14:57:23 +00:00
commit 563c16bb71
59 changed files with 18327 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

76
templates/knowledge/web_ingest.html Normal file
View file

@ -0,0 +1,76 @@
{% extends "base.html" %}
{% block content %}
<h3 class="section-title mb-16">Web Ingest</h3>
<div style="margin-bottom:8px;">
<a href="#single" class="btn active" onclick="showSection('single')" id="tab-single">Single/Batch URL</a>
<a href="#crawl" class="btn" onclick="showSection('crawl')" id="tab-crawl">Site Crawl</a>
</div>
<div id="section-single">
<div class="panel">
<div class="mb-16">
<label class="text-dim text-xs" style="text-transform:uppercase;display:block;margin-bottom:4px;">URL(s) — one per line for batch</label>
<textarea id="wi-urls" class="search-box" rows="4" placeholder="https://example.com/article" style="resize:vertical;margin-bottom:0;"></textarea>
</div>
<div class="mb-16">
<label class="text-dim text-xs" style="text-transform:uppercase;display:block;margin-bottom:4px;">Category</label>
<input type="text" id="wi-category" list="wi-cat-list" class="search-box" value="Web"
placeholder="Category..." style="margin-bottom:0;">
<datalist id="wi-cat-list">{{ options_html|safe }}</datalist>
</div>
<button class="btn" id="wi-btn" onclick="doWebIngest()">Ingest</button>
<span id="wi-status" style="margin-left:12px;font-size:12px;"></span>
</div>
<div id="wi-results" style="display:none;" class="panel" style="max-height:300px;overflow-y:auto;"></div>
</div>
<div id="section-crawl" style="display:none;">
<div class="panel">
<div class="mb-16">
<label class="text-dim text-xs" style="text-transform:uppercase;display:block;margin-bottom:4px;">Site URL</label>
<input type="text" id="crawl-url" class="search-box" placeholder="https://example.com" style="margin-bottom:0;">
</div>
<div class="grid-2 mb-16">
<div>
<label class="text-dim text-xs" style="text-transform:uppercase;display:block;margin-bottom:4px;">Category</label>
<input type="text" id="crawl-category" list="wi-cat-list" class="search-box" value="Web" style="margin-bottom:0;">
</div>
<div>
<label class="text-dim text-xs" style="text-transform:uppercase;display:block;margin-bottom:4px;">Max Pages</label>
<input type="number" id="crawl-max-pages" class="search-box" value="500" min="1" max="5000" style="margin-bottom:0;">
</div>
</div>
<div class="grid-2 mb-16">
<div>
<label class="text-dim text-xs" style="text-transform:uppercase;display:block;margin-bottom:4px;">Include Paths (comma-separated)</label>
<input type="text" id="crawl-include" class="search-box" placeholder="/docs/, /blog/" style="margin-bottom:0;">
</div>
<div>
<label class="text-dim text-xs" style="text-transform:uppercase;display:block;margin-bottom:4px;">Exclude Paths (comma-separated)</label>
<input type="text" id="crawl-exclude" class="search-box" placeholder="/search, /login" style="margin-bottom:0;">
</div>
</div>
<button class="btn" id="crawl-preview-btn" onclick="doCrawl(true)">Preview</button>
<button class="btn" id="crawl-btn" onclick="doCrawl(false)" style="margin-left:8px;">Crawl &amp; Ingest</button>
<span id="crawl-status" style="margin-left:12px;font-size:12px;"></span>
</div>
<div id="crawl-results" style="display:none;" class="panel" style="max-height:400px;overflow-y:auto;font-size:12px;"></div>
</div>
<h3 class="section-title mt-24">Recent Web Ingestions</h3>
<table>
<tr><th>Title</th><th>Source/Category</th><th>Status</th><th>Pages</th><th>Concepts</th></tr>
{% for d in web_docs %}
<tr>
<td title="{{ d.path or '' }}" style="max-width:400px;overflow:hidden;text-overflow:ellipsis;white-space:nowrap;">{{ d.book_title or d.filename or '?' }}</td>
<td>{{ d.source or '' }}/{{ d.category or '' }}</td>
<td><span class="status status-{{ d.status or 'unknown' }}">{{ d.status or 'unknown' }}</span></td>
<td>{{ d.pages_extracted or 0 }}</td>
<td>{{ d.concepts_extracted or 0 }}</td>
</tr>
{% endfor %}
</table>
{% endblock %}
{% block scripts %}
<script src="/static/js/web-ingest.js"></script>
{% endblock %}