mirror of
https://github.com/abhigyanpatwari/GitNexus.git
synced 2026-09-15 23:32:49 +00:00
a2fdf9e93c
The proposer authors the overlay the benchmark arms are scored with, but its clone was never sanitized: it could read eval/workflow_bench, i.e. the task prompts and the hidden oracles it was about to be graded against. The last diagnostic run did exactly that, reading inv-feature-list-repos-filter.oracle.test.ts directly, so a proposal could win the gate by encoding expected behavior into a skill instead of being a better skill. Sanitize the proposer clone exactly as run_cell already does. Also remove the PreToolUse tool-input normalizer. It never ran: headless `claude -p` (2.1.247) dispatches no hooks from inline --settings, a settings file, project/user/local --setting-sources, or a trusted ~/.claude.json project entry. Keeping it would read as a control in review while enforcing nothing, and it was the sole reason the proposer stopped using --bare — which stays off on its own merits, since bare ignores --tools and would cost the proposer Grep and Glob. Blank optional arguments from the OpenAI adapter remain handled where the code is ours: MCP aliases in local-backend normalizeToolParams. Built-in Read still rejects pages:"" and the model self-corrects on the next turn. Co-authored-by: Cursor <cursoragent@cursor.com> |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| conftest.py | ||
| test_ce_plugin_runtime.py | ||
| test_errors.py | ||
| test_evolve.py | ||
| test_mcp_bridge.py | ||
| test_model_gateway.py | ||
| test_oracle_assets.py | ||
| test_parse_run_id.py | ||
| test_process_control.py | ||
| test_promotion_apply.py | ||
| test_property_based.py | ||
| test_proposer_sandbox.py | ||
| test_runner_hardening.py | ||
| test_sanitized_graph.py | ||
| test_session_progress.py | ||
| test_task_assets.py | ||
| test_tool_scripts.py | ||
| test_workflow_bench.py | ||
| test_workflow_bench_evolution.py | ||
| test_workflow_bench_sessions.py | ||