CHANGELOG.md
MANIFEST.in
README.md
pyproject.toml
src/pydocs_eval/__init__.py
src/pydocs_eval/_bench_cache.py
src/pydocs_eval/_retrieval_extra.py
src/pydocs_eval/arm_identity.py
src/pydocs_eval/bench_cache_cli.py
src/pydocs_eval/gold_resolver.py
src/pydocs_eval/registries.py
src/pydocs_eval/runner.py
src/pydocs_eval/sweep.py
src/pydocs_eval/sweep_support.py
src/pydocs_eval/task_rendering.py
src/pydocs_eval/agent_track/__init__.py
src/pydocs_eval/agent_track/__main__.py
src/pydocs_eval/agent_track/_arm.py
src/pydocs_eval/agent_track/_command.py
src/pydocs_eval/agent_track/_guidance.py
src/pydocs_eval/agent_track/_injection.py
src/pydocs_eval/agent_track/_judge.py
src/pydocs_eval/agent_track/_parse.py
src/pydocs_eval/agent_track/_runner.py
src/pydocs_eval/agent_track/_types.py
src/pydocs_eval/agent_track/orchestrator.py
src/pydocs_eval/agent_track/report.py
src/pydocs_eval/campaign/__init__.py
src/pydocs_eval/campaign/__main__.py
src/pydocs_eval/campaign/aggregator.py
src/pydocs_eval/campaign/budget.py
src/pydocs_eval/campaign/cells.py
src/pydocs_eval/campaign/index_cache.py
src/pydocs_eval/campaign/ledger.py
src/pydocs_eval/campaign/lockfile.py
src/pydocs_eval/campaign/overlay_resolver.py
src/pydocs_eval/campaign/prebuild.py
src/pydocs_eval/campaign/runner.py
src/pydocs_eval/campaign/smoke.py
src/pydocs_eval/campaign/strata.py
src/pydocs_eval/campaign/overlays/__init__.py
src/pydocs_eval/campaign/overlays/suggestions_off.yaml
src/pydocs_eval/datasets/__init__.py
src/pydocs_eval/datasets/_bug_loc_gold.py
src/pydocs_eval/datasets/_citations.py
src/pydocs_eval/datasets/_crosscommitvuln_build.py
src/pydocs_eval/datasets/_download.py
src/pydocs_eval/datasets/_parquet.py
src/pydocs_eval/datasets/_repo_cache.py
src/pydocs_eval/datasets/_split.py
src/pydocs_eval/datasets/base_dataset.py
src/pydocs_eval/datasets/bug_localization.py
src/pydocs_eval/datasets/combined.py
src/pydocs_eval/datasets/corpus.py
src/pydocs_eval/datasets/crosscommitvuln.py
src/pydocs_eval/datasets/ds1000.py
src/pydocs_eval/datasets/ds1000_schema.py
src/pydocs_eval/datasets/repo_qa.py
src/pydocs_eval/datasets/repoqa.py
src/pydocs_eval/datasets/structural_recall.py
src/pydocs_eval/datasets/swe_qa.py
src/pydocs_eval/datasets/swe_qa_pro.py
src/pydocs_eval/datasets/task_ids.py
src/pydocs_eval/datasets/data/__init__.py
src/pydocs_eval/datasets/data/crosscommitvuln/NOTICE
src/pydocs_eval/datasets/data/crosscommitvuln/__init__.py
src/pydocs_eval/datasets/data/crosscommitvuln/banned_tokens.jsonl
src/pydocs_eval/datasets/data/crosscommitvuln/records.jsonl
src/pydocs_eval/datasets_swe/__init__.py
src/pydocs_eval/datasets_swe/__main__.py
src/pydocs_eval/datasets_swe/composition.py
src/pydocs_eval/datasets_swe/discriminative.py
src/pydocs_eval/datasets_swe/download.py
src/pydocs_eval/datasets_swe/overlap.py
src/pydocs_eval/datasets_swe/pins.py
src/pydocs_eval/datasets_swe/records.py
src/pydocs_eval/datasets_swe/splits.py
src/pydocs_eval/datasets_swe/touch_log.py
src/pydocs_eval/metrics/__init__.py
src/pydocs_eval/metrics/_relevance.py
src/pydocs_eval/metrics/aggregate.py
src/pydocs_eval/metrics/ast_match.py
src/pydocs_eval/metrics/base_metric.py
src/pydocs_eval/metrics/coverage.py
src/pydocs_eval/metrics/hit_at_k.py
src/pydocs_eval/metrics/library_resolution_at_k.py
src/pydocs_eval/metrics/map_at_k.py
src/pydocs_eval/metrics/mrr.py
src/pydocs_eval/metrics/ndcg_at_k.py
src/pydocs_eval/metrics/pass_at_1_needle.py
src/pydocs_eval/metrics/precision_at_1.py
src/pydocs_eval/metrics/recall_at_k.py
src/pydocs_eval/optimize/__init__.py
src/pydocs_eval/optimize/__main__.py
src/pydocs_eval/optimize/_agent_track_binding.py
src/pydocs_eval/optimize/_overlay_server.py
src/pydocs_eval/optimize/_prefix_report.py
src/pydocs_eval/optimize/_split.py
src/pydocs_eval/optimize/_types.py
src/pydocs_eval/optimize/arm_runtime.py
src/pydocs_eval/optimize/arm_scoring.py
src/pydocs_eval/optimize/arms.py
src/pydocs_eval/optimize/artifact_diff.py
src/pydocs_eval/optimize/ask_binding.py
src/pydocs_eval/optimize/closing_report.py
src/pydocs_eval/optimize/dry_doubles.py
src/pydocs_eval/optimize/dry_run.py
src/pydocs_eval/optimize/ladder.py
src/pydocs_eval/optimize/load_firewall.py
src/pydocs_eval/optimize/lockfile_divergence.py
src/pydocs_eval/optimize/minibatch_filter.py
src/pydocs_eval/optimize/orchestrator.py
src/pydocs_eval/optimize/protocols.py
src/pydocs_eval/optimize/registries.py
src/pydocs_eval/optimize/run_config.py
src/pydocs_eval/optimize/selection.py
src/pydocs_eval/optimize/trials_ledger.py
src/pydocs_eval/optimize/artifacts/__init__.py
src/pydocs_eval/optimize/artifacts/_delimited.py
src/pydocs_eval/optimize/artifacts/ask_architecture.py
src/pydocs_eval/optimize/artifacts/ask_prompt.py
src/pydocs_eval/optimize/artifacts/ask_prompt_seed.md
src/pydocs_eval/optimize/artifacts/retrieval_config.py
src/pydocs_eval/optimize/artifacts/search_skill.py
src/pydocs_eval/optimize/artifacts/tool_docs.py
src/pydocs_eval/optimize/artifacts/usage_skill.py
src/pydocs_eval/optimize/artifacts/usage_skill_seed.md
src/pydocs_eval/optimize/candidates/__init__.py
src/pydocs_eval/optimize/candidates/candidate.py
src/pydocs_eval/optimize/candidates/firewall.py
src/pydocs_eval/optimize/candidates/ledger.py
src/pydocs_eval/optimize/configs/__init__.py
src/pydocs_eval/optimize/configs/campaign_preregistration.yaml
src/pydocs_eval/optimize/configs/optimize_ask_architecture.yaml
src/pydocs_eval/optimize/configs/optimize_ask_prompt.yaml
src/pydocs_eval/optimize/configs/optimize_ask_prompt_combined.yaml
src/pydocs_eval/optimize/configs/optimize_search_skill.yaml
src/pydocs_eval/optimize/configs/optimize_search_skill_bug_loc.yaml
src/pydocs_eval/optimize/configs/optimize_search_skill_repo_qa.yaml
src/pydocs_eval/optimize/configs/optimize_tool_docs.yaml
src/pydocs_eval/optimize/configs/optimize_usage_skill.yaml
src/pydocs_eval/optimize/fitness/__init__.py
src/pydocs_eval/optimize/fitness/_ask_rubric_report.py
src/pydocs_eval/optimize/fitness/ask_rubric.py
src/pydocs_eval/optimize/fitness/campaign.py
src/pydocs_eval/optimize/fitness/paired_agent.py
src/pydocs_eval/optimize/fitness/retrieval.py
src/pydocs_eval/optimize/gepa_harness/__init__.py
src/pydocs_eval/optimize/gepa_harness/acceptance.py
src/pydocs_eval/optimize/gepa_harness/adapter.py
src/pydocs_eval/optimize/gepa_harness/module_selector.py
src/pydocs_eval/optimize/gepa_harness/neutralization.py
src/pydocs_eval/optimize/gepa_harness/optimizer.py
src/pydocs_eval/optimize/gepa_harness/reflective.py
src/pydocs_eval/optimize/multitask/__init__.py
src/pydocs_eval/optimize/multitask/plans.py
src/pydocs_eval/optimize/multitask/sampling.py
src/pydocs_eval/optimize/optimizers/__init__.py
src/pydocs_eval/optimize/optimizers/config_search.py
src/pydocs_eval/optimize/optimizers/critique_refine.py
src/pydocs_eval/optimize/optimizers/skillopt.py
src/pydocs_eval/optimize/preflight/__init__.py
src/pydocs_eval/optimize/preflight/__main__.py
src/pydocs_eval/optimize/preflight/health_check.py
src/pydocs_eval/optimize/preflight/report.py
src/pydocs_eval/optimize/prereg/__init__.py
src/pydocs_eval/optimize/prereg/__main__.py
src/pydocs_eval/optimize/prereg/config.py
src/pydocs_eval/optimize/prereg/power.py
src/pydocs_eval/optimize/prereg/report.py
src/pydocs_eval/optimize/rubric/__init__.py
src/pydocs_eval/optimize/rubric/check_config_row.py
src/pydocs_eval/optimize/rubric/checks.py
src/pydocs_eval/optimize/rubric/gates.py
src/pydocs_eval/optimize/rubric/judge.py
src/pydocs_eval/optimize/rubric/model.py
src/pydocs_eval/optimize/rubric/sample_ledger.py
src/pydocs_eval/optimize/rubric/trajectory_evidence.py
src/pydocs_eval/reporting/__init__.py
src/pydocs_eval/reporting/_plot_common.py
src/pydocs_eval/reporting/baseline_record.py
src/pydocs_eval/reporting/ci_compare.py
src/pydocs_eval/reporting/plot_baselines.py
src/pydocs_eval/reporting/plot_metric_vs_latency.py
src/pydocs_eval/reporting/plot_timings.py
src/pydocs_eval/reporting/plotting.py
src/pydocs_eval/reporting/report.py
src/pydocs_eval/systems/__init__.py
src/pydocs_eval/systems/_mcp_http.py
src/pydocs_eval/systems/base_system.py
src/pydocs_eval/systems/context7.py
src/pydocs_eval/systems/neuledge.py
src/pydocs_eval/systems/pydocs.py
src/pydocs_eval/systems/pydocs_oracle.py
src/pydocs_eval/trackers/__init__.py
src/pydocs_eval/trackers/base_tracker.py
src/pydocs_eval/trackers/jsonl_tracker.py
src/pydocs_eval/trackers/mlflow_tracker.py
src/pydocs_eval/trajectory/__init__.py
src/pydocs_eval/trajectory/attribution.py
src/pydocs_eval/trajectory/blob_store.py
src/pydocs_eval/trajectory/compare_labels.py
src/pydocs_eval/trajectory/compute_metrics_cli.py
src/pydocs_eval/trajectory/consumers.py
src/pydocs_eval/trajectory/eval_report.py
src/pydocs_eval/trajectory/feedback.py
src/pydocs_eval/trajectory/gate.py
src/pydocs_eval/trajectory/gold_diff.py
src/pydocs_eval/trajectory/merge.py
src/pydocs_eval/trajectory/metrics.py
src/pydocs_eval/trajectory/path_normalizer.py
src/pydocs_eval/trajectory/rollout.py
src/pydocs_eval/trajectory/schema.py
src/pydocs_eval/trajectory/shaped_score.py
src/pydocs_eval/trajectory/stream_reader.py
src/pydocs_eval/trajectory/taxonomy.py
src/pydocs_eval/trajectory/configs/__init__.py
src/pydocs_eval/trajectory/configs/score_weights.yaml
src/pydocs_eval/trajectory/configs/taxonomy.yaml
src/pydocs_mcp_eval.egg-info/PKG-INFO
src/pydocs_mcp_eval.egg-info/SOURCES.txt
src/pydocs_mcp_eval.egg-info/dependency_links.txt
src/pydocs_mcp_eval.egg-info/entry_points.txt
src/pydocs_mcp_eval.egg-info/requires.txt
src/pydocs_mcp_eval.egg-info/top_level.txt