execweave 0.7.9__tar.gz → 0.8.2__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- execweave-0.8.2/.github/workflows/provider-capability-stage-integrity.yml +49 -0
- {execweave-0.7.9 → execweave-0.8.2}/PKG-INFO +4 -4
- {execweave-0.7.9 → execweave-0.8.2}/README.de.md +3 -3
- {execweave-0.7.9 → execweave-0.8.2}/README.fr.md +3 -3
- {execweave-0.7.9 → execweave-0.8.2}/README.ja.md +3 -3
- {execweave-0.7.9 → execweave-0.8.2}/README.ko.md +3 -3
- {execweave-0.7.9 → execweave-0.8.2}/README.md +3 -3
- {execweave-0.7.9 → execweave-0.8.2}/README.ru.md +3 -3
- {execweave-0.7.9 → execweave-0.8.2}/README.zh-CN.md +3 -3
- {execweave-0.7.9 → execweave-0.8.2}/README.zh-TW.md +3 -3
- execweave-0.8.2/RELEASE-PLAN-0.8.0.md +176 -0
- {execweave-0.7.9 → execweave-0.8.2}/pyproject.toml +2 -2
- {execweave-0.7.9 → execweave-0.8.2}/scripts/check_release_stage_integrity.py +56 -7
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/__init__.py +1 -1
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/_conversation_records_core.py +32 -10
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/cli.py +5 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/dashboard_shell.py +2 -1
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/live_core.py +18 -1
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/live_view.py +3 -1
- execweave-0.8.2/src/execweave/live_view_readability.py +201 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/top_cli.py +3 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/view_cli.py +3 -0
- execweave-0.8.2/src/execweave/viewer_agent_panel.py +304 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/viewer_dashboard_clean.py +117 -2
- execweave-0.8.2/tests/dashboard_readability_fixture.py +232 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/multi_agent_run_fixture.py +32 -2
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_agent_said_panel.py +4 -4
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_agent_topology_evidence.py +4 -1
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_conversation_agent_focus.py +4 -4
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_dashboard_information_architecture.py +4 -4
- execweave-0.8.2/tests/test_dashboard_readability_e2e.py +407 -0
- execweave-0.8.2/tests/test_dashboard_round_fold_state_e2e.py +258 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_dashboard_simplification.py +1 -1
- execweave-0.8.2/tests/test_fold_budget_setting.py +121 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_per_agent_conversation_default.py +4 -4
- execweave-0.8.2/tests/test_release_stage_integrity_version_guard.py +112 -0
- execweave-0.8.2/tests/test_shared_injected_context_scope.py +90 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_v069_dashboard_release.py +3 -3
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_viewer_agent_isolation_e2e.py +150 -2
- execweave-0.7.9/.github/workflows/provider-capability-stage-integrity.yml +0 -69
- execweave-0.7.9/RELEASE-PLAN-0.7.5-0.8.0.md +0 -824
- execweave-0.7.9/src/execweave/viewer_agent_panel.py +0 -90
- {execweave-0.7.9 → execweave-0.8.2}/.github/workflows/ci.yml +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/.github/workflows/cleanup-workflow-history.yml +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/.github/workflows/i18n.yml +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/.github/workflows/package-benchmark.yml +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/.github/workflows/package-smoke.yml +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/.github/workflows/publish.yml +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/.github/workflows/scalability.yml +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/.github/workflows/viewer-agent-isolation.yml +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/.github/workflows/wheel-smoke.yml +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/.github/workflows/windows-launcher.yml +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/.gitignore +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/LICENSE +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/benchmarks/phase1_overhead.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/antigravity-hooks.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/assets/codex.gif +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/benchmarks/README.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/benchmarks/v0.6.0-github-actions.json +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/benchmarks/v0.6.0-github-actions.svg +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/claude-code-hooks.de.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/claude-code-hooks.fr.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/claude-code-hooks.ja.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/claude-code-hooks.ko.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/claude-code-hooks.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/claude-code-hooks.ru.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/claude-code-hooks.zh-CN.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/claude-code-hooks.zh-TW.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/codex-hooks.de.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/codex-hooks.fr.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/codex-hooks.ja.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/codex-hooks.ko.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/codex-hooks.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/codex-hooks.ru.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/codex-hooks.zh-CN.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/codex-hooks.zh-TW.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/cursor-hooks.de.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/cursor-hooks.fr.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/cursor-hooks.ja.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/cursor-hooks.ko.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/cursor-hooks.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/cursor-hooks.ru.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/cursor-hooks.zh-CN.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/cursor-hooks.zh-TW.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/evidence-grades.de.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/evidence-grades.fr.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/evidence-grades.ja.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/evidence-grades.ko.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/evidence-grades.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/evidence-grades.ru.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/evidence-grades.zh-CN.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/evidence-grades.zh-TW.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/gemini-hooks.de.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/gemini-hooks.fr.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/gemini-hooks.ja.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/gemini-hooks.ko.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/gemini-hooks.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/gemini-hooks.ru.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/gemini-hooks.zh-CN.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/gemini-hooks.zh-TW.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/inference-gateway.de.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/inference-gateway.fr.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/inference-gateway.ja.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/inference-gateway.ko.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/inference-gateway.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/inference-gateway.ru.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/inference-gateway.zh-CN.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/inference-gateway.zh-TW.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/internal/provider-capability-matrix.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/live-graph.de.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/live-graph.fr.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/live-graph.ja.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/live-graph.ko.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/live-graph.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/live-graph.ru.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/live-graph.zh-CN.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/live-graph.zh-TW.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/model-runtime.de.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/model-runtime.fr.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/model-runtime.ja.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/model-runtime.ko.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/model-runtime.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/model-runtime.ru.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/model-runtime.zh-CN.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/model-runtime.zh-TW.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/opencode-plugin.de.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/opencode-plugin.fr.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/opencode-plugin.ja.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/opencode-plugin.ko.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/opencode-plugin.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/opencode-plugin.ru.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/opencode-plugin.zh-CN.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/opencode-plugin.zh-TW.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/phase-1-runtime-collection.de.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/phase-1-runtime-collection.fr.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/phase-1-runtime-collection.ja.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/phase-1-runtime-collection.ko.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/phase-1-runtime-collection.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/phase-1-runtime-collection.ru.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/phase-1-runtime-collection.zh-CN.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/phase-1-runtime-collection.zh-TW.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/phase-2-execution-graph.de.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/phase-2-execution-graph.fr.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/phase-2-execution-graph.ja.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/phase-2-execution-graph.ko.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/phase-2-execution-graph.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/phase-2-execution-graph.ru.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/phase-2-execution-graph.zh-CN.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/phase-2-execution-graph.zh-TW.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/rule-packs.de.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/rule-packs.fr.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/rule-packs.ja.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/rule-packs.ko.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/rule-packs.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/rule-packs.ru.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/rule-packs.zh-CN.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/rule-packs.zh-TW.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/run-integrity.de.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/run-integrity.fr.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/run-integrity.ja.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/run-integrity.ko.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/run-integrity.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/run-integrity.ru.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/run-integrity.zh-CN.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/run-integrity.zh-TW.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/runtime-threat-model.de.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/runtime-threat-model.fr.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/runtime-threat-model.ja.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/runtime-threat-model.ko.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/runtime-threat-model.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/runtime-threat-model.ru.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/runtime-threat-model.zh-CN.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/runtime-threat-model.zh-TW.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/security-analysis.de.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/security-analysis.fr.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/security-analysis.ja.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/security-analysis.ko.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/security-analysis.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/security-analysis.ru.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/security-analysis.zh-CN.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/security-analysis.zh-TW.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/semantic-telemetry.de.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/semantic-telemetry.fr.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/semantic-telemetry.ja.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/semantic-telemetry.ko.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/semantic-telemetry.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/semantic-telemetry.ru.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/semantic-telemetry.zh-CN.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/semantic-telemetry.zh-TW.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/docs/v0.6.5-hardening-decisions.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/scripts/audit_i18n_parity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/scripts/check_claude_hook.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/scripts/check_claude_record_graph.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/scripts/check_codex_hook.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/scripts/check_conversation_records.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/scripts/check_correlation_graph.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/scripts/check_inference_gateway_cli.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/scripts/check_model_runtime_cli.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/scripts/check_openai_compatible_cli.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/scripts/check_semantic_graph.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/scripts/check_viewer_js.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/scripts/check_wheel_install.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/scripts/check_windows_launchers.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/scripts/emit_claude_hook_smoke.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/scripts/emit_codex_hook_smoke.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/scripts/emit_cursor_hook_smoke.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/scripts/emit_gemini_hook_smoke.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/scripts/emit_opencode_plugin_smoke.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/scripts/make_semantic_smoke.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/scripts/probe_provider_capability.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/scripts/sync_i18n_nav.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/__main__.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/agent_bootstrap.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/agent_topology.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/agent_trace.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/analysis.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/anthropic.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/anthropic_cli.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/anthropic_full_fidelity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/antigravity_adapter.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/antigravity_adapter_base.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/antigravity_full_fidelity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/antigravity_full_fidelity_base.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/antigravity_full_fidelity_collaboration_base.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/antigravity_hook_cli.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/antigravity_record.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/antigravity_subagent_linkage.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/antigravity_trace_capability.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/auto_specialized.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/backends.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/benchmark.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/claude_adapter.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/claude_delegation.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/claude_full_fidelity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/claude_hook_cli.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/claude_hook_contract.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/claude_model_observer.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/claude_record.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/codex_adapter.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/codex_conversation.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/codex_full_fidelity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/codex_hook_cli.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/codex_hook_lifecycle.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/codex_message_diagnostics.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/codex_message_transport_diagnostics.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/codex_record.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/codex_rollout_structures.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/codex_rollout_trace.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/codex_rollout_trace_base.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/collector.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/command.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/content_evidence.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/content_store.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/conversation_archive.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/conversation_message_identity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/conversation_preview.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/conversation_records.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/correlation.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/cursor_adapter.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/cursor_delegation.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/cursor_delegation_base.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/cursor_full_fidelity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/cursor_hook_cli.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/cursor_hook_contract.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/cursor_record.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/entry.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/evidence_availability.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/evidence_grade.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/fidelity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/filesystem.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/focus.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/gemini_adapter.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/gemini_full_fidelity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/gemini_hook_cli.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/gemini_hook_contract.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/gemini_record.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/graph.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/graph_ops.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/http_proxy.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/http_proxy_cli.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/inference_gateway.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/inference_gateway_cli.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/inference_gateway_full_fidelity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/inference_identity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/inference_identity_cli.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/integrity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/integrity_cli.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/litellm_callback.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/litellm_callback_cli.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/live.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/live_view_extra_style.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/live_view_markup.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/live_view_script_a.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/live_view_script_b.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/live_view_script_c.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/live_view_script_d.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/live_view_style.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/model_runtime.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/model_runtime_cli.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/model_runtime_full_fidelity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/openai_compatible.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/openai_compatible_cli.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/openai_compatible_full_fidelity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/opencode_adapter.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/opencode_event_contract.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/opencode_full_fidelity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/opencode_hook_cli.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/opencode_plugin_cli.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/opencode_record.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/opencode_task_linkage.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/overhead_benchmark.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/provider_capability.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/provider_lifecycle.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/provider_record.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/rule_pack.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/rule_pack_cli.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/scalability_benchmark.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/schema.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/scope.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/semantic.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/sink.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/strace_backend.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/stream_assembly.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/theme.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/top.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/validate.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/viewer.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/viewer_content_inspector.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/viewer_dashboard_focus.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/viewer_live_layout.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/viewer_projection.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/viewer_projection_base.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/src/execweave/workflow.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/fixtures/codex_multi_agent/PROVENANCE.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/fixtures/codex_multi_agent/hook-payloads.json +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/fixtures/codex_multi_agent/rollout-main.jsonl +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/fixtures/hooks/README.md +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/fixtures/hooks/claude.json +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/fixtures/hooks/codex.json +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/fixtures/hooks/cursor.json +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/fixtures/hooks/gemini.json +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/fixtures/hooks/manifest.json +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/fixtures/hooks/opencode.json +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_agent_bootstrap.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_agent_message_viewer.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_agent_node_labels.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_agent_trace_lifecycle.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_agent_trace_viewer_visibility.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_analysis.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_anthropic.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_antigravity_agent_collaboration.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_antigravity_cursor_launch.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_antigravity_lifecycle.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_antigravity_linkage_projection.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_antigravity_official_contract.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_antigravity_subagent_transcript_linkage.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_antigravity_trace_capability_cli.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_auto_specialized.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_backends.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_claude_adapter.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_claude_delegation.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_claude_full_fidelity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_claude_hook_contract.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_claude_hook_metadata.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_claude_hook_viewer.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_claude_model_observer.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_claude_record.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_codex_adapter.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_codex_archive_full_fidelity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_codex_conversation_isolation.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_codex_full_fidelity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_codex_hook_lifecycle.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_codex_hook_partial_capture.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_codex_message_diagnostics.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_codex_message_transport_diagnostics.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_codex_plain_routed_agent_message.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_codex_real_multi_agent_conversation.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_codex_record.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_codex_reducer_command.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_codex_rollout_structures.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_codex_rollout_trace.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_codex_routing_native_identity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_collector.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_command.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_condense.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_conversation_access.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_conversation_agent_isolation.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_conversation_identity_merge.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_conversation_message_observation_dedupe.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_conversation_provider_parity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_correlation.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_correlation_canonical_path.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_correlation_checker.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_correlation_process_exe.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_cross_provider_agent_trace.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_cursor_adapter.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_cursor_delegation.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_cursor_full_fidelity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_cursor_hook_contract.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_cursor_hook_fail_open.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_cursor_record.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_cursor_task_linkage.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_dashboard_ux_and_hook_projection.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_delegation_viewer.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_evidence_grade.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_execution_viewer.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_fidelity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_filesystem_resilience.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_focus.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_full_fidelity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_gemini_adapter.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_gemini_full_fidelity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_gemini_hook_contract.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_gemini_lifecycle.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_gemini_record.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_graph.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_graph_ops.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_hook_fixture_corpus.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_http_proxy.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_inference_gateway.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_inference_gateway_full_fidelity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_inference_identity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_integrity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_litellm_callback.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_live.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_live_auth.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_live_dashboard.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_live_dashboard_js.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_live_delta.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_live_logs_export.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_live_theme.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_lmstudio_auto_specialized.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_local_runtime_live_capture.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_model_runtime.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_model_runtime_full_fidelity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_openai_compatible.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_opencode_adapter.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_opencode_event_contract.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_opencode_event_lifecycle.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_opencode_full_fidelity.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_opencode_plugin.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_opencode_record.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_opencode_task_session_linkage.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_overhead_benchmark.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_provider_capability.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_provider_conversation_evidence.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_provider_lifecycle.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_rule_pack.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_schema.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_scope.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_semantic.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_strace_backend.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_stream_assembly.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_threat_model.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_top_detached.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_v063_features.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_v064_live_auto_integrations.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_v064_live_evidence.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_v079_review_e2e.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_v079_review_regressions.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_validate.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_version.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_viewer.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_viewer_content_inspector.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_viewer_projection.py +0 -0
- {execweave-0.7.9 → execweave-0.8.2}/tests/test_workflow.py +0 -0
|
@@ -0,0 +1,49 @@
|
|
|
1
|
+
name: Provider Capability Stage Integrity
|
|
2
|
+
|
|
3
|
+
# No path filter. This job guards release red lines — the disabled CONNECT handler,
|
|
4
|
+
# the existing test set, the conversation completeness vocabulary, release metadata —
|
|
5
|
+
# so it must run on every pull request. A filter listing only the capability-probe
|
|
6
|
+
# files would arm the guard exactly when the guarded files are NOT the ones changing:
|
|
7
|
+
# a pull request that weakens http_proxy.py, deletes a test, or bumps the version
|
|
8
|
+
# while touching none of those paths would skip this job entirely.
|
|
9
|
+
on:
|
|
10
|
+
pull_request:
|
|
11
|
+
workflow_dispatch:
|
|
12
|
+
inputs:
|
|
13
|
+
baseline_ref:
|
|
14
|
+
description: Base commit or ref used to reconstruct baseline test node IDs
|
|
15
|
+
required: true
|
|
16
|
+
type: string
|
|
17
|
+
|
|
18
|
+
permissions:
|
|
19
|
+
contents: read
|
|
20
|
+
|
|
21
|
+
jobs:
|
|
22
|
+
integrity:
|
|
23
|
+
runs-on: ubuntu-latest
|
|
24
|
+
steps:
|
|
25
|
+
- name: Check out pull request
|
|
26
|
+
uses: actions/checkout@v4
|
|
27
|
+
with:
|
|
28
|
+
fetch-depth: 0
|
|
29
|
+
|
|
30
|
+
- name: Set up Python
|
|
31
|
+
uses: actions/setup-python@v5
|
|
32
|
+
with:
|
|
33
|
+
python-version: "3.12"
|
|
34
|
+
cache: pip
|
|
35
|
+
|
|
36
|
+
- name: Install
|
|
37
|
+
run: python -m pip install -e ".[dev]"
|
|
38
|
+
|
|
39
|
+
- name: Validate stage integrity
|
|
40
|
+
shell: bash
|
|
41
|
+
env:
|
|
42
|
+
BASELINE_REF: "${{ github.event.pull_request.base.sha || inputs.baseline_ref }}"
|
|
43
|
+
HEAD_REF: "${{ github.head_ref }}"
|
|
44
|
+
run: |
|
|
45
|
+
args=(--baseline-ref "$BASELINE_REF")
|
|
46
|
+
if [[ "$HEAD_REF" == release/* ]]; then
|
|
47
|
+
args+=(--allow-test-change "tests/test_v069_dashboard_release.py=release metadata assertions may advance only on a release/* pull request; the historical test name remains stable because the node-ID floor refuses renames")
|
|
48
|
+
fi
|
|
49
|
+
python scripts/check_release_stage_integrity.py "${args[@]}"
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.5
|
|
2
2
|
Name: execweave
|
|
3
|
-
Version: 0.
|
|
3
|
+
Version: 0.8.2
|
|
4
4
|
Summary: Turn AI-agent runtime behavior into a local interactive execution graph.
|
|
5
5
|
Project-URL: Homepage, https://github.com/Irish-kw/ExecWeave
|
|
6
6
|
Project-URL: Repository, https://github.com/Irish-kw/ExecWeave
|
|
@@ -84,7 +84,7 @@ Install the latest published wheel/sdist from PyPI:
|
|
|
84
84
|
python -m pip install -U execweave
|
|
85
85
|
```
|
|
86
86
|
|
|
87
|
-
The current release is **v0.
|
|
87
|
+
The current release is **v0.8.2**.
|
|
88
88
|
|
|
89
89
|
For development:
|
|
90
90
|
|
|
@@ -120,7 +120,7 @@ execweave record --open -- python my_agent.py
|
|
|
120
120
|
|
|
121
121
|
`execweave top -- codex` keeps the Agent interactive in the launch terminal while opening/attaching the detached Top dashboard according to the host environment.
|
|
122
122
|
|
|
123
|
-
**v0.
|
|
123
|
+
**v0.8.2 — every round, and every node, says what it holds.** A run is rarely one question, and the panel had room for one: it paired the oldest prompt with the newest answer, so a two-round run showed the first question beside the second question's reply while the first round's own answer stayed unreachable. Rounds are the unit now — the newest is open, older ones fold to a line naming their own moment and question, and a subagent's fold carries the timestamp and wording of the root round it came from. Two subagents had also been losing their Response: the rule that stops a provider's shared preamble from being read as one agent's assignment matched any long text appearing under two agents, and a child's answer appears both in its own record and in its parent's. That rule now reaches inbound messages only, so what an agent wrote stays its own however often the run repeats it. Selecting a process, a file or a network endpoint no longer draws an empty panel: each names what it is — a command line with its pid and parent, a path with the history that touched it, an address with the process that reached it. And a type crowded past its budget keeps its newest members drawn while the older ones collapse into a single node that still names every one it holds, so a run that touches a thousand paths stays readable without losing one of them. The provider-neutral, agent-local multi-agent conversations each agent owns are the same records they always were; what changed is that a reader can reach all of them instead of one. The budget past which a type folds is `--fold-budget N` on every command that renders a dashboard, so a deployment whose agents write hundreds of files chooses its own number instead of editing the package. v0.8.2 fixes two Dashboard regressions on top of that: older conversation rounds now keep the reader's explicit open/closed state across the 800 ms live refresh, and multi-agent graphs use a stable root/child hierarchy where lifecycle return edges do not affect rank, shared tool/model connections use separated ports and bundled trunks, and selecting an agent fades unrelated edges. These are presentation-only changes: Live, finished, and `viewer.html` still share the same renderer and raw graph evidence is unchanged.
|
|
124
124
|
|
|
125
125
|
The unified dashboard brings the execution graph, logs, and conversation records into the same inspection flow. Finalized runs generate `conversations.md` and `conversations.json`, while validated provider transcripts are copied into the run-local SHA-256 content store. Claude Code, OpenAI Codex, Cursor, OpenCode, and Google Antigravity use the strongest provider-exposed multi-agent evidence available to each integration. For gateways and local runtimes that expose only root request/response traffic, ExecWeave shows only that root conversation and does not invent subagents or hidden routing.
|
|
126
126
|
|
|
@@ -329,7 +329,7 @@ Conversation isolation is an attribution/display rule, not a redaction boundary.
|
|
|
329
329
|
|
|
330
330
|
## Current status
|
|
331
331
|
|
|
332
|
-
v0.
|
|
332
|
+
v0.8.2 combines cross-platform runtime collection, materialized execution graphs, standalone/live dashboards, conservative provider↔runtime correlation, full-fidelity content-addressed provider evidence, attributable multi-agent execution traces, direct run-local conversation access, agent-local conversation isolation across provider-neutral projections, per-round agent conversation panels, and self-describing non-agent nodes with per-type folding in the standalone and live dashboards. Supported integrations preserve the strongest identity/routing evidence actually exposed by each provider and abstain when that evidence is unavailable. Observed evidence and inference remain separate by design. v0.8.2 additionally preserves reader-controlled conversation fold state across live polling and applies topology-aware multi-agent layout/routing without changing raw evidence.
|
|
333
333
|
|
|
334
334
|
## Documentation
|
|
335
335
|
|
|
@@ -31,7 +31,7 @@ Installieren Sie das neueste veröffentlichte wheel/sdist von PyPI:
|
|
|
31
31
|
python -m pip install -U execweave
|
|
32
32
|
```
|
|
33
33
|
|
|
34
|
-
Die aktuelle Version ist **v0.
|
|
34
|
+
Die aktuelle Version ist **v0.8.2**.
|
|
35
35
|
|
|
36
36
|
Für die Entwicklung:
|
|
37
37
|
|
|
@@ -67,7 +67,7 @@ execweave record --open -- python my_agent.py
|
|
|
67
67
|
|
|
68
68
|
`execweave top -- codex` hält den Agent im Startterminal interaktiv und öffnet bzw. verbindet gleichzeitig das detached Top dashboard entsprechend der Host-Umgebung.
|
|
69
69
|
|
|
70
|
-
**v0.
|
|
70
|
+
**v0.8.2 — jede Runde und jeder Knoten sagt, was er enthält.** Ein Run besteht selten aus einer einzigen Frage, das Panel hatte aber nur für eine Platz: Es stellte die älteste Frage neben die neueste Antwort, sodass ein Run mit zwei Runden die erste Frage neben der Antwort der zweiten zeigte, während die eigene Antwort der ersten Runde unerreichbar blieb. Die Runde ist jetzt die Einheit — die neueste steht offen, ältere klappen zu einer Zeile zusammen, die ihren eigenen Zeitpunkt und ihre eigene Frage nennt, und die Faltung eines Subagents trägt Zeitstempel und Wortlaut der Wurzelrunde, aus der sie stammt. Zwei Subagents verloren zudem ihre Antwort: Die Regel, die verhindert, dass die gemeinsame Präambel eines Providers als Zuweisung eines Agents gelesen wird, traf auf jeden langen Text zu, der unter zwei Agents auftaucht — und die Antwort eines Kindes steht sowohl in seinem eigenen als auch im Datensatz seines Elternteils. Diese Regel greift nun nur noch bei eingehenden Nachrichten, sodass das, was ein Agent geschrieben hat, sein eigenes bleibt, wie oft der Run es auch wiederholt. Die Auswahl eines Prozesses, einer Datei oder eines Netzwerk-Endpunkts zeichnet kein leeres Panel mehr: Jeder nennt, was er ist — eine Kommandozeile mit ihrer pid und ihrem Elternprozess, ein Pfad mit der Historie, die ihn berührt hat, eine Adresse mit dem Prozess, der sie erreicht hat. Und ein Typ, der sein Budget überschreitet, behält seine neuesten Mitglieder gezeichnet, während die älteren zu einem einzigen Knoten zusammenklappen, der weiterhin jedes einzelne benennt, das er hält — ein Run, der tausend Pfade berührt, bleibt so lesbar, ohne einen davon zu verlieren. Die provider-neutralen, agent-lokalen Multi-Agent-Conversations, die jeder Agent besitzt, sind dieselben Datensätze wie zuvor; geändert hat sich, dass ein Leser sie alle erreicht statt nur eine. Ab wann ein Typ faltet, bestimmt `--fold-budget N` auf jedem Befehl, der ein Dashboard erzeugt — eine Installation, deren Agents Hunderte von Dateien schreiben, wählt ihre eigene Zahl, statt das Paket zu ändern. v0.8.2 behebt zusätzlich zwei Dashboard-Regressionen: Ältere conversation rounds behalten über den 800-ms-Live-Refresh hinweg genau den vom Leser gesetzten geöffnet/geschlossen-Zustand, und Multi-Agent-Graphs verwenden eine stabile root/child-Hierarchie, in der lifecycle return edges den rank nicht beeinflussen, gemeinsame tool/model-Verbindungen über getrennte ports und gebündelte trunks laufen und bei Auswahl eines Agents irrelevante edges ausgeblendet werden. Das sind reine Presentation-Änderungen: Live, finished und `viewer.html` verwenden weiterhin denselben renderer, und die raw graph evidence bleibt unverändert.
|
|
71
71
|
|
|
72
72
|
Das vereinheitlichte Dashboard bringt execution graph, logs und conversation records in denselben Inspection-Flow. Finalisierte Runs erzeugen `conversations.md` und `conversations.json`; validierte Provider-Transcripts werden in den run-local SHA-256 content store kopiert. Claude Code, OpenAI Codex, Cursor, OpenCode und Google Antigravity verwenden jeweils die stärkste Multi-Agent-Evidence, die ihre Integration tatsächlich offenlegt. Wenn ein Gateway oder lokaler Runtime nur root request/response sichtbar macht, zeigt ExecWeave nur diese Root-Conversation und erfindet weder Subagents noch hidden routing.
|
|
73
73
|
|
|
@@ -276,7 +276,7 @@ Conversation isolation ist eine Attribution-/Display-Regel, keine Redaction Boun
|
|
|
276
276
|
|
|
277
277
|
## Aktueller Stand
|
|
278
278
|
|
|
279
|
-
v0.
|
|
279
|
+
v0.8.2 kombiniert cross-platform runtime collection, materialized execution graphs, standalone/live dashboards, konservative provider↔runtime correlation, full-fidelity content-addressed provider evidence, attributable multi-agent execution traces, direkten run-local conversation access, agent-local conversation isolation in provider-neutralen Projektionen, Conversation-Panels pro Runde sowie sich selbst beschreibende Nicht-Agent-Knoten mit Faltung pro Typ in den Standalone- und Live-Dashboards. Jede Integration bewahrt nur die stärkste identity/routing evidence, die der Provider tatsächlich offenlegt, und enthält sich, wenn diese Evidence fehlt. Observed evidence und inference bleiben konstruktiv getrennt. v0.8.2 bewahrt außerdem den vom Leser gesteuerten conversation-fold-Zustand über Live-Polling hinweg und verwendet topology-aware Multi-Agent-Layout/-Routing, ohne die raw evidence zu verändern.
|
|
280
280
|
|
|
281
281
|
## Dokumentation
|
|
282
282
|
|
|
@@ -31,7 +31,7 @@ Installez le dernier wheel/sdist publié depuis PyPI :
|
|
|
31
31
|
python -m pip install -U execweave
|
|
32
32
|
```
|
|
33
33
|
|
|
34
|
-
La version courante est **v0.
|
|
34
|
+
La version courante est **v0.8.2**.
|
|
35
35
|
|
|
36
36
|
Pour le développement :
|
|
37
37
|
|
|
@@ -67,7 +67,7 @@ execweave record --open -- python my_agent.py
|
|
|
67
67
|
|
|
68
68
|
`execweave top -- codex` garde l’Agent interactif dans le terminal de lancement tout en ouvrant ou en attachant le dashboard Top détaché selon l’environnement hôte.
|
|
69
69
|
|
|
70
|
-
**v0.
|
|
70
|
+
**v0.8.2 — chaque tour, et chaque nœud, dit ce qu'il contient.** Un run se limite rarement à une seule question, et le panneau n'avait de place que pour une : il associait la plus ancienne question à la plus récente réponse, si bien qu'un run de deux tours montrait la première question à côté de la réponse de la seconde, tandis que la réponse propre au premier tour restait inaccessible. Le tour est désormais l'unité — le plus récent est ouvert, les plus anciens se replient en une ligne nommant leur propre moment et leur propre question, et le repli d'un subagent porte l'horodatage et la formulation du tour racine dont il provient. Deux subagents perdaient aussi leur Réponse : la règle qui empêche le préambule partagé d'un provider d'être lu comme l'assignation d'un agent correspondait à tout texte long apparaissant sous deux agents, or la réponse d'un enfant apparaît à la fois dans son propre enregistrement et dans celui de son parent. Cette règle ne touche plus que les messages entrants, de sorte que ce qu'un agent a écrit reste le sien, quel que soit le nombre de fois où le run le répète. Sélectionner un processus, un fichier ou un point de terminaison réseau ne dessine plus un panneau vide : chacun dit ce qu'il est — une ligne de commande avec son pid et son parent, un chemin avec l'historique qui l'a touché, une adresse avec le processus qui l'a atteinte. Et un type encombré au-delà de son budget garde ses membres les plus récents dessinés tandis que les plus anciens se replient en un seul nœud qui nomme encore chacun de ceux qu'il contient, si bien qu'un run touchant mille chemins reste lisible sans en perdre un seul. Les conversations multi-agent provider-neutral et agent-local que chaque agent possède sont les mêmes enregistrements qu'auparavant ; ce qui a changé, c'est qu'un lecteur peut désormais les atteindre toutes plutôt qu'une seule. Le seuil à partir duquel un type se replie est `--fold-budget N`, disponible sur chaque commande qui produit un tableau de bord : un déploiement dont les agents écrivent des centaines de fichiers choisit son propre nombre au lieu de modifier le paquet. v0.8.2 corrige en plus deux régressions du Dashboard : les anciens conversation rounds conservent l'état ouvert/fermé explicitement choisi par le lecteur malgré le refresh live de 800 ms, et les graphes multi-agent utilisent une hiérarchie root/child stable où les lifecycle return edges n'influencent pas le rank, les connexions tool/model partagées passent par des ports séparés et des trunks regroupés, et la sélection d'un agent atténue les edges sans rapport. Ces changements sont uniquement de présentation : Live, finished et `viewer.html` partagent toujours le même renderer et la raw graph evidence reste inchangée.
|
|
71
71
|
|
|
72
72
|
Le dashboard unifié rassemble execution graph, logs et conversation records dans le même flux d’inspection. Les runs finalisés génèrent `conversations.md` et `conversations.json`, et les transcripts provider validés sont copiés dans le content store SHA-256 local au run. Claude Code, OpenAI Codex, Cursor, OpenCode et Google Antigravity exploitent chacun le niveau de multi-agent evidence réellement exposé par leur integration. Lorsqu’un gateway ou un local runtime n’expose que des request/response root, ExecWeave affiche uniquement cette root conversation et n’invente ni subagent ni hidden routing.
|
|
73
73
|
|
|
@@ -276,7 +276,7 @@ La conversation isolation est une règle d’attribution et d’affichage, pas u
|
|
|
276
276
|
|
|
277
277
|
## État actuel
|
|
278
278
|
|
|
279
|
-
v0.
|
|
279
|
+
v0.8.2 combine cross-platform runtime collection, materialized execution graphs, standalone/live dashboards, conservative provider↔runtime correlation, full-fidelity content-addressed provider evidence, attributable multi-agent execution traces, accès direct aux conversations run-local, agent-local conversation isolation dans les projections provider-neutral, des panneaux de conversation par tour et des nœuds non-agent qui se décrivent eux-mêmes avec un repli par type dans les dashboards standalone et live. Chaque integration conserve uniquement la meilleure identity/routing evidence réellement exposée par le provider et s’abstient lorsque cette evidence manque. Observed evidence et inference restent séparées par conception. v0.8.2 conserve aussi l'état de repli conversation contrôlé par le lecteur entre les live polling et applique un layout/routing multi-agent topology-aware sans modifier la raw evidence.
|
|
280
280
|
|
|
281
281
|
## Documentation
|
|
282
282
|
|
|
@@ -31,7 +31,7 @@ PyPI から最新の wheel/sdist をインストールします。
|
|
|
31
31
|
python -m pip install -U execweave
|
|
32
32
|
```
|
|
33
33
|
|
|
34
|
-
現在のリリースは **v0.
|
|
34
|
+
現在のリリースは **v0.8.2** です。
|
|
35
35
|
|
|
36
36
|
開発環境では次のようにインストールできます。
|
|
37
37
|
|
|
@@ -67,7 +67,7 @@ execweave record --open -- python my_agent.py
|
|
|
67
67
|
|
|
68
68
|
`execweave top -- codex` は Agent を起動 terminal 上でインタラクティブなまま保ち、ホスト環境に応じて detached Top dashboard を開くか既存のものに attach します。
|
|
69
69
|
|
|
70
|
-
**v0.
|
|
70
|
+
**v0.8.2 — どのラウンドも、どの node も、自分が何を持っているかを述べる。** 一回の実行が一つの問いで終わることは稀ですが、パネルには一つ分の場所しかありませんでした。最も古い問いに最も新しい回答を並べるため、二ラウンドの実行では最初の問いの隣に二番目の問いの回答が出て、最初のラウンド自身の回答には到達できませんでした。いまはラウンドが単位です。最新のものは開いたまま、古いものは自分の時刻と問いを示す一行に畳まれ、subagent の折り畳みは、それが属する root ラウンドと同じ時刻と文言を持ちます。さらに二つの subagent は自分の Response を失っていました。provider の共通前置きをある agent の assignment と読ませないための規則が、二つの agent の下に現れる長い文字列すべてに一致していたためです。child の回答は自分の記録にも親の記録にも現れます。この規則はいま受信したメッセージだけを見るので、agent が書いたものは実行中に何度繰り返されても自分のものです。process、file、network endpoint を選んでも空のパネルは出ません。それぞれが自分を述べます。コマンドラインとその pid と親、パスとそれに触れた履歴、アドレスとそこへ到達した process です。そしてある型が上限を超えて混み合うと、新しいものは描かれたまま、古いものは一つの node に畳まれ、そこに含まれるすべてを名前で列挙します。千の path に触れる実行でも、一つも失わずに読める状態が保たれます。 各 agent が保持する provider-neutral かつ agent-local な multi-agent conversation は以前と同じ記録のままです。変わったのは、読者がその一部ではなく全体に到達できることです。 ある型がどこから畳まれるかは、Dashboard を生成するすべてのコマンドの `--fold-budget N` で決まります。数百のファイルを書く配置環境は、パッケージを書き換えずに自分の数を選べます。 v0.8.2 ではさらに 2 つの Dashboard 回帰を修正しました。古い conversation round は 800 ms ごとの live refresh をまたいでも読者が明示的に選んだ開閉状態を保持し、multi-agent graph は安定した root/child 階層を使います。lifecycle return edge は rank に影響せず、共有 tool/model 接続は分離した port と bundled trunk で描画され、agent を選択すると無関係な edge が薄くなります。これらは presentation のみの変更で、Live・finished・`viewer.html` は引き続き同じ renderer を共有し、raw graph evidence は変更しません。
|
|
71
71
|
|
|
72
72
|
統合 dashboard では execution graph、logs、conversation records を同じ inspection flow で確認できます。Finalized run は `conversations.md` と `conversations.json` を生成し、検証済み provider transcript は run-local SHA-256 content store にコピーされます。Claude Code、OpenAI Codex、Cursor、OpenCode、Google Antigravity は、それぞれが実際に公開する最も強い multi-agent evidence を利用します。gateway や local runtime が root request/response しか公開しない場合、ExecWeave は root conversation だけを表示し、subagent や hidden routing を捏造しません。
|
|
73
73
|
|
|
@@ -276,7 +276,7 @@ Conversation isolation は attribution/display の規則であり redaction boun
|
|
|
276
276
|
|
|
277
277
|
## 現在の状態
|
|
278
278
|
|
|
279
|
-
v0.
|
|
279
|
+
v0.8.2 は cross-platform runtime collection、materialized execution graph、standalone/live dashboard、保守的な provider↔runtime correlation、content-addressed full-fidelity provider evidence、attributable multi-agent execution trace、run-local conversation access、provider-neutral projection 上の agent-local conversation isolation、standalone および live dashboard での per-round agent conversation パネルと、自己記述する non-agent node および型ごとの折り畳みを統合します。各 integration は provider が実際に公開した最も強い identity/routing evidence のみを保持し、不足する場合は abstain します。Observed evidence と inference は設計上分離されたままです。 v0.8.2 ではさらに、live polling をまたいで読者が制御した conversation fold 状態を保持し、raw evidence を変えずに topology-aware な multi-agent layout/routing を適用します。
|
|
280
280
|
|
|
281
281
|
## ドキュメント
|
|
282
282
|
|
|
@@ -31,7 +31,7 @@ PyPI에서 최신 wheel/sdist를 설치합니다.
|
|
|
31
31
|
python -m pip install -U execweave
|
|
32
32
|
```
|
|
33
33
|
|
|
34
|
-
현재 릴리스는 **v0.
|
|
34
|
+
현재 릴리스는 **v0.8.2** 입니다.
|
|
35
35
|
|
|
36
36
|
개발 설치:
|
|
37
37
|
|
|
@@ -67,7 +67,7 @@ execweave record --open -- python my_agent.py
|
|
|
67
67
|
|
|
68
68
|
`execweave top -- codex`는 Agent를 시작 terminal에서 interactive 상태로 유지하면서 host 환경에 따라 detached Top dashboard를 열거나 attach합니다.
|
|
69
69
|
|
|
70
|
-
**v0.
|
|
70
|
+
**v0.8.2 — 모든 라운드와 모든 node 가 자신이 무엇을 담고 있는지 말합니다.** 한 번의 실행이 하나의 질문으로 끝나는 경우는 드물지만 패널에는 하나의 자리밖에 없었습니다. 가장 오래된 질문에 가장 새로운 답변을 짝지었기 때문에, 두 라운드짜리 실행에서는 첫 번째 질문 옆에 두 번째 질문의 답변이 놓이고 첫 라운드 자신의 답변에는 닿을 수 없었습니다. 이제 단위는 라운드입니다. 가장 새로운 라운드는 펼쳐진 채로 두고, 오래된 라운드는 자신의 시각과 질문을 밝히는 한 줄로 접히며, subagent 의 접힌 줄은 그것이 속한 root 라운드와 같은 시각과 문구를 가집니다. 또한 두 subagent 가 자신의 Response 를 잃고 있었습니다. provider 의 공통 서문을 어느 agent 의 assignment 로 읽지 않게 하는 규칙이, 두 agent 아래에 나타나는 긴 텍스트 전부와 일치했기 때문입니다. child 의 답변은 자기 기록에도 부모 기록에도 나타납니다. 이 규칙은 이제 들어온 메시지만 봅니다. 따라서 agent 가 쓴 것은 실행 중 몇 번 반복되든 그 agent 의 것입니다. process, file, network endpoint 를 선택해도 더 이상 빈 패널이 그려지지 않습니다. 각자 자신을 밝힙니다. 명령줄과 그 pid 및 부모, 경로와 그것을 건드린 이력, 주소와 그곳에 도달한 process 입니다. 그리고 어떤 유형이 한도를 넘어 붐비면 가장 새로운 것들은 그려진 채로 두고 오래된 것들은 하나의 node 로 접히며, 그 안에 담긴 모든 것을 여전히 이름으로 열거합니다. 천 개의 path 를 건드리는 실행도 하나도 잃지 않은 채 읽을 수 있습니다. 각 agent 가 소유한 provider-neutral, agent-local multi-agent conversation 은 예전과 같은 기록 그대로입니다. 달라진 것은 읽는 사람이 그중 일부가 아니라 전부에 닿을 수 있다는 점입니다. 어떤 유형이 어디서부터 접히는지는 Dashboard 를 만드는 모든 명령의 `--fold-budget N` 이 정합니다. 수백 개의 파일을 쓰는 배포 환경은 패키지를 고치지 않고 자신의 숫자를 고를 수 있습니다. v0.8.2에서는 두 가지 Dashboard 회귀를 추가로 수정했습니다. 이전 conversation round는 800 ms live refresh 이후에도 사용자가 명시적으로 선택한 열림/닫힘 상태를 유지하며, multi-agent graph는 안정적인 root/child 계층을 사용합니다. lifecycle return edge는 rank에 영향을 주지 않고, 공유 tool/model 연결은 분리된 port와 bundled trunk로 라우팅되며, agent를 선택하면 관련 없는 edge가 흐려집니다. 이는 presentation에만 해당하는 변경으로 Live, finished, `viewer.html`은 계속 같은 renderer를 공유하고 raw graph evidence는 바뀌지 않습니다.
|
|
71
71
|
|
|
72
72
|
통합 dashboard는 execution graph, logs, conversation records를 하나의 inspection flow에서 제공합니다. Finalized run은 `conversations.md`와 `conversations.json`을 만들며, 검증된 provider transcript는 run-local SHA-256 content store로 복사됩니다. Claude Code, OpenAI Codex, Cursor, OpenCode, Google Antigravity는 각 integration이 실제로 노출하는 가장 강한 multi-agent evidence를 사용합니다. gateway나 local runtime이 root request/response만 노출하면 ExecWeave는 root conversation만 보여 주며 subagent나 hidden routing을 만들어내지 않습니다.
|
|
73
73
|
|
|
@@ -276,7 +276,7 @@ Conversation isolation은 attribution/display 규칙이지 redaction boundary가
|
|
|
276
276
|
|
|
277
277
|
## 현재 상태
|
|
278
278
|
|
|
279
|
-
v0.
|
|
279
|
+
v0.8.2은 cross-platform runtime collection, materialized execution graph, standalone/live dashboard, 보수적인 provider↔runtime correlation, content-addressed full-fidelity provider evidence, attributable multi-agent execution trace, run-local conversation access, provider-neutral projection의 agent-local conversation isolation, standalone 및 live dashboard의 per-round agent conversation 패널과 스스로를 설명하는 non-agent node 및 유형별 접기를 통합합니다. 각 integration은 provider가 실제로 노출한 가장 강한 identity/routing evidence만 보존하고 충분한 증거가 없으면 abstain합니다. Observed evidence와 inference는 설계상 계속 분리됩니다. v0.8.2는 또한 live polling 사이에서 사용자가 제어한 conversation fold 상태를 유지하고 raw evidence를 바꾸지 않은 채 topology-aware multi-agent layout/routing을 적용합니다.
|
|
280
280
|
|
|
281
281
|
## 문서
|
|
282
282
|
|
|
@@ -31,7 +31,7 @@ Install the latest published wheel/sdist from PyPI:
|
|
|
31
31
|
python -m pip install -U execweave
|
|
32
32
|
```
|
|
33
33
|
|
|
34
|
-
The current release is **v0.
|
|
34
|
+
The current release is **v0.8.2**.
|
|
35
35
|
|
|
36
36
|
For development:
|
|
37
37
|
|
|
@@ -67,7 +67,7 @@ execweave record --open -- python my_agent.py
|
|
|
67
67
|
|
|
68
68
|
`execweave top -- codex` keeps the Agent interactive in the launch terminal while opening/attaching the detached Top dashboard according to the host environment.
|
|
69
69
|
|
|
70
|
-
**v0.
|
|
70
|
+
**v0.8.2 — every round, and every node, says what it holds.** A run is rarely one question, and the panel had room for one: it paired the oldest prompt with the newest answer, so a two-round run showed the first question beside the second question's reply while the first round's own answer stayed unreachable. Rounds are the unit now — the newest is open, older ones fold to a line naming their own moment and question, and a subagent's fold carries the timestamp and wording of the root round it came from. Two subagents had also been losing their Response: the rule that stops a provider's shared preamble from being read as one agent's assignment matched any long text appearing under two agents, and a child's answer appears both in its own record and in its parent's. That rule now reaches inbound messages only, so what an agent wrote stays its own however often the run repeats it. Selecting a process, a file or a network endpoint no longer draws an empty panel: each names what it is — a command line with its pid and parent, a path with the history that touched it, an address with the process that reached it. And a type crowded past its budget keeps its newest members drawn while the older ones collapse into a single node that still names every one it holds, so a run that touches a thousand paths stays readable without losing one of them. The provider-neutral, agent-local multi-agent conversations each agent owns are the same records they always were; what changed is that a reader can reach all of them instead of one. The budget past which a type folds is `--fold-budget N` on every command that renders a dashboard, so a deployment whose agents write hundreds of files chooses its own number instead of editing the package. v0.8.2 fixes two Dashboard regressions on top of that: older conversation rounds now keep the reader's explicit open/closed state across the 800 ms live refresh, and multi-agent graphs use a stable root/child hierarchy where lifecycle return edges do not affect rank, shared tool/model connections use separated ports and bundled trunks, and selecting an agent fades unrelated edges. These are presentation-only changes: Live, finished, and `viewer.html` still share the same renderer and raw graph evidence is unchanged.
|
|
71
71
|
|
|
72
72
|
The unified dashboard brings the execution graph, logs, and conversation records into the same inspection flow. Finalized runs generate `conversations.md` and `conversations.json`, while validated provider transcripts are copied into the run-local SHA-256 content store. Claude Code, OpenAI Codex, Cursor, OpenCode, and Google Antigravity use the strongest provider-exposed multi-agent evidence available to each integration. For gateways and local runtimes that expose only root request/response traffic, ExecWeave shows only that root conversation and does not invent subagents or hidden routing.
|
|
73
73
|
|
|
@@ -276,7 +276,7 @@ Conversation isolation is an attribution/display rule, not a redaction boundary.
|
|
|
276
276
|
|
|
277
277
|
## Current status
|
|
278
278
|
|
|
279
|
-
v0.
|
|
279
|
+
v0.8.2 combines cross-platform runtime collection, materialized execution graphs, standalone/live dashboards, conservative provider↔runtime correlation, full-fidelity content-addressed provider evidence, attributable multi-agent execution traces, direct run-local conversation access, agent-local conversation isolation across provider-neutral projections, per-round agent conversation panels, and self-describing non-agent nodes with per-type folding in the standalone and live dashboards. Supported integrations preserve the strongest identity/routing evidence actually exposed by each provider and abstain when that evidence is unavailable. Observed evidence and inference remain separate by design. v0.8.2 additionally preserves reader-controlled conversation fold state across live polling and applies topology-aware multi-agent layout/routing without changing raw evidence.
|
|
280
280
|
|
|
281
281
|
## Documentation
|
|
282
282
|
|
|
@@ -31,7 +31,7 @@ ExecWeave — source-available, local-first проект наблюдаемос
|
|
|
31
31
|
python -m pip install -U execweave
|
|
32
32
|
```
|
|
33
33
|
|
|
34
|
-
Текущая версия — **v0.
|
|
34
|
+
Текущая версия — **v0.8.2**.
|
|
35
35
|
|
|
36
36
|
Для разработки:
|
|
37
37
|
|
|
@@ -67,7 +67,7 @@ execweave record --open -- python my_agent.py
|
|
|
67
67
|
|
|
68
68
|
`execweave top -- codex` оставляет Agent интерактивным в стартовом terminal и одновременно открывает либо подключает detached Top dashboard в зависимости от host environment.
|
|
69
69
|
|
|
70
|
-
**v0.
|
|
70
|
+
**v0.8.2 — каждый раунд и каждый узел говорят, что в них есть.** Прогон редко состоит из одного вопроса, а в панели помещался только один: она ставила самый старый вопрос рядом с самым свежим ответом, поэтому прогон из двух раундов показывал первый вопрос рядом с ответом на второй, а собственный ответ первого раунда оставался недостижимым. Теперь единицей стал раунд — самый свежий раскрыт, более старые сворачиваются в строку, называющую собственное время и собственный вопрос, а свёртка subagent несёт отметку времени и формулировку корневого раунда, из которого она пришла. Два subagent к тому же теряли свой ответ: правило, не дающее прочесть общую преамбулу provider как задание одного agent, срабатывало на любой длинный текст, встречающийся под двумя agent, а ответ потомка появляется и в его собственной записи, и в записи родителя. Теперь это правило смотрит только на входящие сообщения, поэтому написанное agent остаётся его собственным, сколько бы раз прогон это ни повторил. Выбор процесса, файла или сетевой конечной точки больше не рисует пустую панель: каждый называет, что он такое — командная строка со своим pid и родителем, путь с историей того, что его касалось, адрес с процессом, который до него дошёл. А тип, переполнивший свой бюджет, оставляет отрисованными самые свежие элементы, тогда как более старые сворачиваются в один узел, который по-прежнему называет каждый из них, так что прогон, затрагивающий тысячу путей, остаётся читаемым и не теряет ни одного. Provider-neutral, agent-local multi-agent conversations, которыми владеет каждый agent, — те же самые записи, что и раньше; изменилось то, что читатель добирается до всех них, а не до одной. Порог, за которым тип сворачивается, задаёт `--fold-budget N` у каждой команды, которая строит панель, так что развёртывание, чьи agent пишут сотни файлов, выбирает своё число, а не правит пакет. v0.8.2 дополнительно исправляет две регрессии Dashboard: старые conversation rounds сохраняют явно выбранное читателем состояние open/closed между live refresh каждые 800 мс, а multi-agent graph использует стабильную иерархию root/child, где lifecycle return edges не влияют на rank, общие tool/model connections проходят через раздельные ports и bundled trunks, а при выборе agent несвязанные edges приглушаются. Это только presentation-изменения: Live, finished и `viewer.html` по-прежнему используют один renderer, а raw graph evidence не меняется.
|
|
71
71
|
|
|
72
72
|
Единый dashboard объединяет execution graph, logs и conversation records в одном inspection flow. Finalized runs создают `conversations.md` и `conversations.json`, а проверенные provider transcripts копируются в run-local SHA-256 content store. Claude Code, OpenAI Codex, Cursor, OpenCode и Google Antigravity используют наиболее сильную multi-agent evidence, которую реально раскрывает соответствующая integration. Если gateway или local runtime показывает только root request/response, ExecWeave отображает только root conversation и не выдумывает subagents или hidden routing.
|
|
73
73
|
|
|
@@ -276,7 +276,7 @@ Conversation isolation — это правило attribution/display, а не re
|
|
|
276
276
|
|
|
277
277
|
## Текущий статус
|
|
278
278
|
|
|
279
|
-
v0.
|
|
279
|
+
v0.8.2 объединяет cross-platform runtime collection, materialized execution graphs, standalone/live dashboards, conservative provider↔runtime correlation, full-fidelity content-addressed provider evidence, attributable multi-agent execution traces, прямой run-local conversation access, agent-local conversation isolation в provider-neutral projections, панели conversation по раундам и самоописывающиеся non-agent узлы со свёрткой по типу в standalone и live dashboards. Каждая integration сохраняет только наиболее сильную identity/routing evidence, реально раскрытую provider, и abstain-ит при её отсутствии. Observed evidence и inference по-прежнему разделены архитектурно. v0.8.2 также сохраняет управляемое читателем состояние conversation fold между live polling и применяет topology-aware multi-agent layout/routing без изменения raw evidence.
|
|
280
280
|
|
|
281
281
|
## Документация
|
|
282
282
|
|
|
@@ -31,7 +31,7 @@ ExecWeave 是一个 source-available、local-first 的可观测性项目,把 A
|
|
|
31
31
|
python -m pip install -U execweave
|
|
32
32
|
```
|
|
33
33
|
|
|
34
|
-
当前正式版本是 **v0.
|
|
34
|
+
当前正式版本是 **v0.8.2**。
|
|
35
35
|
|
|
36
36
|
开发安装:
|
|
37
37
|
|
|
@@ -67,7 +67,7 @@ execweave record --open -- python my_agent.py
|
|
|
67
67
|
|
|
68
68
|
`execweave top -- codex` 会让 Agent 保持在启动 terminal 中交互,并根据主机环境打开或附加 detached Top dashboard。
|
|
69
69
|
|
|
70
|
-
**v0.
|
|
70
|
+
**v0.8.2 — 每一轮、每一个 node,都说得出自己有什么。** 一次运行很少只有一个问题,面板却只放得下一个:它把最旧的提问配上最新的回答,于是两轮的运行会把第一个问题和第二个问题的回答排在一起,而第一轮自己的回答根本点不到。现在以轮为单位——最新的一轮展开,较旧的折叠成一行,标明它自己的时间与问题;subagent 的折叠行沿用它所属 root 轮次的时间与叙述。另外有两个 subagent 一直遗失自己的 Response:那条避免把 provider 共用前言当成某个 agent 交办的规则,会比对任何同时出现在两个 agent 底下的长文字,而 child 的回答本来就同时出现在它自己的记录与父层的记录里。该规则现在只看送进来的消息,所以 agent 写的东西不管在运行中重复几次都仍然是它自己的。选取 process、file 或网络端点不再画出空面板:各自说明自己是什么——命令行连同它的 pid 与父进程、路径连同动过它的历程、地址连同连上它的进程。而某个类型多到超过额度时,最新的仍然画出来,较旧的收合成单一 node,并且仍然列出它收了哪些,因此动到上千个路径的运行依然读得下去,也不会漏掉任何一个。 每个 agent 各自拥有的 provider-neutral、agent-local multi-agent conversation 仍是原本那份记录;变的是读者现在读得到全部,而不是其中一段。 某个类型从哪里开始折叠,由每个会产生 Dashboard 的命令上的 `--fold-budget N` 决定,因此写入上百个文件的部署可以自己选数字,不必去改包。 v0.8.2 在此基础上修复两个 Dashboard 回归:较旧的 conversation round 在每 800 ms 的 live refresh 后保持读者明确留下的展开/收起状态;multi-agent graph 使用稳定的 root/child 层级,lifecycle return edge 不影响 rank,共用 tool/model 连接使用分离 port 与 bundled trunk,选择 agent 时淡化无关 edge。这些都只改变 presentation:Live、finished 与 `viewer.html` 仍共用同一 renderer,raw graph evidence 完全不变。
|
|
71
71
|
|
|
72
72
|
统一 dashboard 把 execution graph、logs 与 conversation records 放进同一条 inspection flow。Finalized run 会生成 `conversations.md` 与 `conversations.json`,经过验证的 provider transcript 也会复制进 run-local SHA-256 content store。Claude Code、OpenAI Codex、Cursor、OpenCode 与 Google Antigravity 都依据各自实际暴露的 evidence 强度建立 multi-agent trace;如果 gateway 或 local runtime 只提供 root request/response,ExecWeave 就只显示 root conversation,不会虚构 subagent 或 hidden routing。
|
|
73
73
|
|
|
@@ -276,7 +276,7 @@ Conversation isolation 是 attribution/display 规则,而不是 redaction boun
|
|
|
276
276
|
|
|
277
277
|
## 当前状态
|
|
278
278
|
|
|
279
|
-
v0.
|
|
279
|
+
v0.8.2 组合 cross-platform runtime collection、materialized execution graph、standalone/live dashboard、保守的 provider↔runtime correlation、content-addressed full-fidelity provider evidence、可归属的 multi-agent execution trace、run-local conversation access,provider-neutral projection 上的 agent-local conversation isolation,以及 standalone 与 live dashboard 上的 per-round agent conversation 面板、会自我说明并依类型折叠的 non-agent node。各 integration 只保留 provider 实际暴露的最强 identity/routing evidence,证据不足时选择 abstain。Observed evidence 与 inference 从设计上保持分离。 v0.8.2 还会在 live polling 之间保留读者控制的 conversation fold 状态,并应用 topology-aware 的 multi-agent layout/routing,而不改动 raw evidence。
|
|
280
280
|
|
|
281
281
|
## 文档
|
|
282
282
|
|
|
@@ -31,7 +31,7 @@ ExecWeave 是一個 source-available、local-first 的可觀測性專案,會
|
|
|
31
31
|
python -m pip install -U execweave
|
|
32
32
|
```
|
|
33
33
|
|
|
34
|
-
目前正式版本是 **v0.
|
|
34
|
+
目前正式版本是 **v0.8.2**。
|
|
35
35
|
|
|
36
36
|
開發安裝:
|
|
37
37
|
|
|
@@ -67,7 +67,7 @@ execweave record --open -- python my_agent.py
|
|
|
67
67
|
|
|
68
68
|
`execweave top -- codex` 會讓 Agent 保持在啟動 terminal 中互動,並依主機環境開啟或附加 detached Top dashboard。
|
|
69
69
|
|
|
70
|
-
**v0.
|
|
70
|
+
**v0.8.2 — 每一輪、每一個 node,都說得出自己有什麼。** 一次執行很少只有一個問題,面板卻只放得下一個:它把最舊的提問配上最新的回答,於是兩輪的執行會把第一個問題和第二個問題的回答排在一起,而第一輪自己的回答根本點不到。現在以輪為單位——最新的一輪展開,較舊的摺疊成一行,標明它自己的時間與問題;subagent 的摺疊行沿用它所屬 root 輪次的時間與敘述。另外有兩個 subagent 一直遺失自己的 Response:那條避免把 provider 共用前言當成某個 agent 交辦的規則,會比對任何同時出現在兩個 agent 底下的長文字,而 child 的回答本來就同時出現在它自己的紀錄與父層的紀錄裡。該規則現在只看送進來的訊息,所以 agent 寫的東西不管在執行中重複幾次都仍然是它自己的。選取 process、file 或網路端點不再畫出空面板:各自說明自己是什麼——指令列連同它的 pid 與父行程、路徑連同動過它的歷程、位址連同連上它的行程。而某個類型多到超過額度時,最新的仍然畫出來,較舊的收合成單一 node,並且仍然列出它收了哪些,因此動到上千個路徑的執行依然讀得下去,也不會漏掉任何一個。 每個 agent 各自擁有的 provider-neutral、agent-local multi-agent conversation 仍是原本那份紀錄;變的是讀者現在讀得到全部,而不是其中一段。 某個類型從哪裡開始摺疊,由每個會產生 Dashboard 的命令上的 `--fold-budget N` 決定,因此寫入上百個檔案的部署可以自己選數字,不必去改套件。 v0.8.2 在此基礎上修正兩個 Dashboard 回歸:較舊的 conversation round 會在每 800 ms 的 live refresh 後維持讀者明確留下的展開/收合狀態;multi-agent graph 則使用穩定的 root/child 階層,lifecycle return edge 不影響 rank,共用 tool/model 連線使用分離 port 與 bundled trunk,選取 agent 時淡化無關 edge。這些都只改 presentation:Live、finished 與 `viewer.html` 仍共用同一 renderer,raw graph evidence 完全不變。
|
|
71
71
|
|
|
72
72
|
統一 dashboard 把 execution graph、logs 與 conversation records 放進同一條 inspection flow。Finalized run 會產生 `conversations.md` 與 `conversations.json`,經驗證的 provider transcript 也會複製進 run-local SHA-256 content store。Claude Code、OpenAI Codex、Cursor、OpenCode 與 Google Antigravity 都依各自實際曝露的 evidence 強度建立 multi-agent trace;若 gateway 或 local runtime 只提供 root request/response,ExecWeave 就只顯示 root conversation,不會虛構 subagent 或 hidden routing。
|
|
73
73
|
|
|
@@ -276,7 +276,7 @@ Conversation isolation 是 attribution/display 規則,不是 redaction boundar
|
|
|
276
276
|
|
|
277
277
|
## 目前狀態
|
|
278
278
|
|
|
279
|
-
v0.
|
|
279
|
+
v0.8.2 整合 cross-platform runtime collection、materialized execution graph、standalone/live dashboard、保守的 provider↔runtime correlation、content-addressed full-fidelity provider evidence、可歸屬的 multi-agent execution trace、run-local conversation access,provider-neutral projection 上的 agent-local conversation isolation,以及 standalone 與 live dashboard 上的 per-round agent conversation 面板、會自我說明並依類型摺疊的 non-agent node。各 integration 只保留 provider 實際曝露的最強 identity/routing evidence,證據不足時選擇 abstain。Observed evidence 與 inference 仍從設計上分離。 v0.8.2 另外會在 live polling 間保留讀者控制的 conversation fold 狀態,並套用 topology-aware 的 multi-agent layout/routing,而不改動 raw evidence。
|
|
280
280
|
|
|
281
281
|
## 文件
|
|
282
282
|
|