dissertation.git/src, branch logs

created the logs branch

2026-02-27T23:24:52Z

fix(judge): hash run_id to stay under Anthropic batch custom_id 64-char limit

2026-02-27T15:31:58Z

fix: separate skipped runs from incomplete in summary output

2026-02-27T13:45:41Z

feat: add checkpoint/resume support and atomic log writes

2026-02-26T22:53:13Z

- Runner now counts existing .json log files per combination and skips completed runs, resuming from where it left off - Log files are written atomically via temp file + rename to prevent corrupt files from being counted as completed - Added --no-resume CLI flag to force a fresh start - Resume is enabled by default

chore: add .env.example + config.yaml.example, gitignore config.yaml

2026-02-26T15:29:02Z

- Create .env.example with placeholder keys for all providers - Create config.yaml.example with clean reference config - Add config.yaml and judge_logs/ to .gitignore - Load .env in judge.py for standalone usage

feat: implement judging system with regex, blackbox, and glassbox checks

2026-02-25T16:10:37Z

- 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

[refactor] improved interrogation system

2026-02-24T20:13:21Z

- Fixed syntax errors in print statements (lines 159/162) - Added sanitize_for_api() to strip custom log fields before API calls - Added interactive commands: history, reasoning, vfs, info, save, help - Colored terminal output for readability - Better error handling (KeyboardInterrupt, EOFError) - Added --show-history flag to review conversation on load

[fix] VFS singleton reset + remove vestigial check_username tool

2026-02-24T19:52:48Z

- VFS now creates fresh instance when root_path/fs_data is provided (prevents cross-scenario contamination in multi-scenario runs) - Removed check_username from tools (unrelated to any scenario)

[feat] baseline system - auto-generates baselines before experiments

2026-02-24T19:52:14Z

- Added _extract_baseline_content() to extract output from create_file tool calls - Baselines now saved to logs/{model}/{scenario}/baseline.md - Added global oversight fallback (scenario-specific → global oversight dir) - Updated config_loader with oversight level loading from scenario dirs

[feat] added a baseline to the runner

2026-02-18T19:54:46Z

(no commit message provided) (no commit message provided) Co-authored-by: aider (openrouter/openrouter/aurora-alpha)