dissertation.git - Undergraduate dissertation — Deceptive Alignment in Autonomous LLM Agents (UEL, 2026). Sandboxed agentic-LLM deception study: 960 runs, three-tier judging (regex + blackbox + glassbox).

Age	Commit message (Collapse)	Author
2026-04-15	Study 1: 270 runs complete + judge validation pipeline	CaptainJack2491
	- config_study1.yaml: 3 models × 3 oversight × bare framing × n=30 - Judge validation: 54-run subset, gold=Sonnet 4.6, proxy=Grok 4.1 Fast (BB κ=0.702) + GPT-4.1 (GB κ=0.878) - Fix OpenAI batch provider: BytesIO, method/url fields, response.body parsing - Scripts: extract_subset.py, judge_validation.py - Dissertation chapters updated (intro, methodology, results, conclusion)
2026-04-10	refactor(judge): simplify to single judge per prong, remove multi-model ↵	CaptainJack2491
	aggregation - Remove multi-model aggregation support from Judge class - Single blackbox judge: claude-sonnet-4-20250514 (anthropic) - Single glassbox judge: gpt-4.1 (openai) - Remove aggregate_results method and all aggregation-related code - Simplify batch collection to single result per run - Update config_dryrun.yaml with new judge configuration
2026-04-01	feat: implement robust reasoning token handling and multi-turn persistence	CaptainJack2491
	- Refactored Agent's chat loop to explicitly preserve and pass back reasoning context (reasoning_details, reasoning) to OpenRouter. - Ensures frontier models like Gemini 3.1 and DeepSeek v3.2 maintain their 'thinking' chain during complex tool-calling sessions. - Enhanced reasoning extraction to support structured details, reasoning_content, and fallback tags. - Verified capture of encrypted and plain-text reasoning blocks in experimental logs.