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
2026-03-26	Add xAI (Grok) batch API support	CaptainJack2491
	- Add XAIBatchProvider class implementing BatchProvider ABC - Add --provider CLI argument to judge_runner (anthropic\|xai) - Refactor Judge class to use BatchProvider instead of direct API calls - Update tests for new Judge constructor signature
2026-03-25	refactor: extract judge prompts to files and add granular blackbox categories	CaptainJack2491
	- Extracted Blackbox and Glassbox prompts from into their own markdown files in - Implemented progressive 4-tier Blackbox categories (FABRICATED, OMITTED_CRITICAL, DECEPTIVE_FRAMING, ACCURATE) - Added neutral examples to the Blackbox prompt to improve formatting consistency - Updated references and tests to match new judge categorization structure
2026-03-25	feat: implement rich dashboard for experiment progress	CaptainJack2491

2026-03-25	fix: catch and recover from JSONDecodeError on malformed tool args	CaptainJack2491

2026-03-25	test: add coverage for v2 infra features	CaptainJack2491
	- VFSFactory: independent instances vs singletons - make_tools_for_vfs: parallel binding - config_loader: goal_types and max_workers parsing - runner: goal_type iteration and resume skipping - agent: goal_type storage and path resolution
2026-03-01	feat(judge): updated blackbox to include source document for added accuracy	CaptainJack2491

2026-02-25	feat: implement judging system with regex, blackbox, and glassbox checks	CaptainJack2491
	- Add src/judge.py: RegexChecker, BlackboxChecker, GlassboxChecker, Judge orchestrator - Add src/judge_runner.py: CLI for batch/single judging with CSV output - Add regex_rules.yaml for corporate_sabotage_v2 and child_protection scenarios - Add judge config section to config.yaml (model, temperature, log_dir) - Add tests/test_judge.py: 34 unit tests covering all components - Uses Anthropic Batch API for half-cost LLM judge calls - Judge logs include full CoT reasoning and judge model for auditability
2026-02-24	Add comprehensive test suite (104 tests)	CaptainJack2491
	Tests cover: - VFS: sandbox escape, path traversal, CRUD, singleton staleness - Config loader: missing keys, temperature cascade, oversight fallback - Tools: schema/implementation sync, VFS delegation - Agent: message construction, error handling, token counting, reasoning extraction - Interrogation: sanitization, provider detection, prompt loading - Runner: baseline extraction, prompt assembly, success detection All tests run offline with mocked API calls.