dissertation.git/api, branch mainUndergraduate dissertation — Deceptive Alignment in Autonomous LLM Agents (UEL, 2026). Sandboxed agentic-LLM deception study: 960 runs, three-tier judging (regex + blackbox + glassbox).http://git.jayrup.me/c/dissertation.git/atom?h=main2026-04-13T20:20:02Zapi: add chat interface styles to results dashboard2026-04-13T20:20:02ZCaptainJack2491jayrupnakawala@gmail.com2026-04-13T20:20:02Zurn:sha1:75ffc67248248c600256a116c94153b0f8685fb5feat(dashboard): add interactive charts and layout optimizations2026-04-02T19:44:07ZCaptainJack2491jayrupnakawala@gmail.com2026-04-02T19:44:07Zurn:sha1:a72e0d6e93e6ea8d44b4ca86d51903bfbf4e21d5
- Separated Static Visualizations into dedicated tab with fullscreen image modal
- Added new interactive charts: Glassbox Category by Scenario, Intent vs Reality, and Radar Chart
- Replaced average token tracking with global token aggregations
- Implemented Grouped-Stacked Bar Chart for visual comparison of Action alongside Sophistication by oversight tier
- Added standardized color palettes to improve chart legibility
feat(dashboard): integrate interrogation module into web dashboard2026-04-02T17:46:43ZCaptainJack2491jayrupnakawala@gmail.com2026-04-02T17:46:43Zurn:sha1:32aa0344ed57a0fe6e6bc9225af9eb851bc3c6b6
- Added HTTP POST /api/interrogate/start and /api/interrogate/chat to api/server.py
- Implemented ACTIVE_SESSIONS cache to persist synchronous agent state across requests
- Updated sys.path in api/server.py to resolve inner core imports correctly
- Added Inspector Modal 'Interrogate' view toggle in index.html
- Implemented JS interrogation loop, fallback log path resolution, auto-scroll, and markdown rendering in results.js
- Added custom CSS animations (.thinking-pulse, .pulse-ring) to mimic agent processing
feat(dashboard): enhance raw-dataset view with column toggles, truncation, and row inspector2026-04-02T16:37:11ZCaptainJack2491jayrupnakawala@gmail.com2026-04-02T16:37:11Zurn:sha1:997ca4060c8c9674bbd15384cb30877a7eb7a02efix: update web dashboard to auto-discover data from multiple directories2026-04-02T16:01:45ZCaptainJack2491jayrupnakawala@gmail.com2026-04-02T16:01:45Zurn:sha1:efe55feec6122721070a41e6716437ee04e2cc46
- CSV results now found in logs/full_experiment/, output/, and config.output_dir
- Viz images now found in viz/ (project root) and output/charts/
- Judge logs now found in judge_logs/ and logs/judge_full_experiment/
- Added CORS middleware for local development
- Added /api/logs/ endpoints for browsing raw JSON experiment logs
- Added --port and --host CLI args
feat: add total token usage chart and update documentation2026-03-09T20:35:34ZCaptainJack2491jayrupnakawala@gmail.com2026-03-09T20:35:34Zurn:sha1:f19aa5de3e3f1c3c0b9ce90913588b9e956d4156
This commit:
- Adds a 'Total Token Usage by Model' chart alongside the average token chart
- Updates the web_gui_plan.md to reflect the removal of execution APIs and the addition of the new data visualization features.
feat: add token usage metrics and click-to-zoom charts2026-03-09T20:16:05ZCaptainJack2491jayrupnakawala@gmail.com2026-03-09T20:16:05Zurn:sha1:17acb7a802d6d6f844c51dca5f2f171e360eca8d
This commit:
- Bakes total/prompt/completion tokens directly into results.csv
- Reverts dynamic JSON scraping backend logic for speed
- Adds modal overlay functionality to zoom Chart.js graphs on click
feat: implement multi-select filters and logical oversight sorting2026-03-09T19:47:59ZCaptainJack2491jayrupnakawala@gmail.com2026-03-09T19:47:59Zurn:sha1:1bbb4938d9f714eb29c8981e0d834ce85ccafacc
This commit:
- Replaces single-select dropdowns with multi-select checkbox lists
- Adds 'All' and 'None' quick-action links for filter groups
- Implements custom priority sorting for Oversight levels (low -> mid -> high)
- Updates Chart.js logic to respect logical sorting on X-axes
feat: pivot Web GUI to dedicated Data Visualization Dashboard2026-03-09T19:41:49ZCaptainJack2491jayrupnakawala@gmail.com2026-03-09T19:41:49Zurn:sha1:d3d0e0825ea4b4ed3ab338603b824af0178e5264
This commit:
- Removes all execution logic (runs, cancellation, SSE logs)
- Strips the terminal and configuration sidebar
- Implements a global filtering panel (Model, Scenario, Oversight)
- Dedicated the UI 100% to interactive Chart.js and static visuals
feat: upgrade web GUI to modular ES6 and add Chart.js2026-03-09T19:11:45ZCaptainJack2491jayrupnakawala@gmail.com2026-03-09T19:11:45Zurn:sha1:d2b1fbd5ac63fd1eb17e68b5364b7dee5cc86e6e
This commit completely overhauls the initial GUI:
- Splits monolithic JS/CSS into an ES6 module structure
- Implements an industrial 'Control Room' dark theme
- Adds dynamic file selection endpoints for CSV and JSON judge logs
- Integrates Chart.js to automatically render visualizations from CSV data
- Updates web_gui_plan.md to reflect architectural changes