2 commits

Author	SHA1	Message	Date
darrenhinde	9675e30ca4	chore: cleanup documentation - remove temporary and redundant files ... Cleanup Summary: - Deleted .tmp/ directory (20+ temporary development files) - Deleted tasks/ directory (old task tracking files) - Removed 10 redundant/historical markdown files from evals/ Files Deleted: - evals/DOCUMENTATION_CLEANUP.md (historical) - evals/SCRIPTS_ORGANIZATION.md (historical) - evals/agents/AGENT_TESTING_GUIDE.md (redundant) - evals/agents/openagent/CONTEXT_LOADING_COVERAGE.md (historical) - evals/agents/openagent/IMPLEMENTATION_SUMMARY.md (historical) - evals/agents/opencoder/README.md (redundant) - evals/agents/shared/README.md (redundant) - evals/framework/scripts/README.md (redundant) - evals/results/README.md (redundant) - evals/test_tmp/README.md (redundant) Result: - Reduced from 120+ markdown files to 92 (excluding node_modules) - Reduced evals/ from 20 to 10 markdown files - Kept essential documentation: - evals/README.md (main guide) - evals/GETTING_STARTED.md (quick start) - evals/HOW_TESTS_WORK.md (technical details) - evals/ARCHITECTURE.md (system architecture) - evals/framework/README.md (framework docs) - evals/framework/SDK_EVAL_README.md (SDK guide) - evals/agents/openagent/README.md (test suite) - Kept dev/ directory (important OpenCode internals documentation) Benefits: - Clearer documentation structure - Less confusion about where to find information - Removed outdated/historical files - Easier to navigate and maintain	2025-11-26 21:54:18 +00:00
darrenhinde	8eb4b31ef4	feat(evals): add opencoder test suite and fix expected violation handling ... - Create separate test folder for opencoder agent with 4 tests - Update openagent tests to use multi-turn prompts for approval workflow - Fix test runner to properly handle expectedViolations with shouldViolate: true - Add mustUseAnyOf behavior expectation for flexible tool matching - Add unit tests for timeline-builder and context-loading-evaluator - Update documentation to reflect agent-specific test structure - Remove outdated AGENT_DETECTION_STATUS.md Opencoder tests: 4/4 passing Key insight: openagent uses text-based approval, opencoder uses tool permissions only	2025-11-26 01:52:18 +00:00