ouroboros/tests
Andrei Kaznacheev b38e461e58 feat: add apply_patch and edit_batch editing tools with editbench evidence
Two new repo-lane editing primitives beyond exact-match edit_text and
full-file write_file, both validated on the included editbench benchmark
before adoption:

- edit_batch: atomic batch of COUNTED exact replacements. Each edit
  declares the occurrence count it expects and replaces all of them; any
  mismatch aborts the whole batch with per-edit diagnostics. The safe
  replace-all: a miscount is an atomic refusal, not a silent corruption.
- apply_patch: context-anchored multi-file patch (V4A-style, no line
  numbers; optional @@ anchors; trailing-whitespace fuzzy fallback).
  Atomic across all files/hunks with per-hunk diagnostics; parser
  tolerates decorative trailing *** on headers (observed model quirk).

write_file repo lane gains two verification rails inherited from an
edit_sketch fast-apply tool that was implemented, benchmarked, and
REJECTED (data in devtools/benchmarks/editbench/README.md): a pre-write
syntax guard for .py/.json (force bypasses with an explicit
SYNTAX_GUARD_BYPASSED disclosure — no silent bypass, P3) and the unified
diff vs the previous version appended to overwrite results (capped with
an explicit truncation count, P1).

Registration follows the New Tool rule across every canonical surface:
safety.py TOOL_POLICY, tool_capabilities (CORE/ACTING envelopes + result
limits; local-readonly and heal lanes deliberately excluded), registry
(_FROZEN_TOOL_MODULES/_WORKSPACE_ALLOWED_TOOLS/_REPO_MUTATION_TOOLS),
outcomes (_ROOT_WRITE_TOOLS so patch/batch-only turns stay acceptance-
review-eligible; _RECOVERY_TOOL_NAMES), smoke EXPECTED_TOOLS, and the
SYSTEM.md/ARCHITECTURE.md/DEVELOPMENT.md/CHECKLISTS.md documentation in
the same commit (P6). The edit_text/write_file descriptions steer tool
selection at the schema source (per DEVELOPMENT's anti-pattern guidance,
not SYSTEM.md prose accretion).

devtools/benchmarks/editbench/ is the evidence and the regression rig:
5 editing tasks (trap-laden rename, surgical edit in a 1691-line module,
whole-function replacement, cross-file move, near-full-file transform),
per-config tool restriction via disabled_tools, deterministic grading,
token/latency/error mining. Migrated under the benchmark admission
contract (admit_benchmark_run/finalize_run_manifest, launcher_audit
MIGRATED_LAUNCHERS); it measures the current working tree by design, so
real runs use the recorded --allow-dirty-seed escape.

Headline numbers (grok-4.5, 3 runs/config, every run solved every task;
full tables in the editbench README): edit_batch finishes the rename
task in ONE tool call vs ~6 for edit_text/write_file; on a weak model
(gemini-3.6-flash) its advantage grows to 1.5-2.5x cheaper/faster; a
free-choice agent picked the right tool per task shape in every run.

No version carriers touched (maintainer assigns the release version).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-04 19:55:26 +05:00
..
fixtures release v6.82.0: truthful working cards, mobile gestures, and cancel run 2026-07-30 01:09:27 +03:00
__init__.py Initial commit from app bundle 2026-04-22 01:04:48 +03:00
_delivery_candidate_shared.py feat(v6.66.0): honest mutation attribution, attributed staging, environment-correct Python, auditable Skill Review history, and a drift-proof operator review wrapper 2026-07-16 22:25:04 +00:00
_shared.py v5.17.0-rc.1: unify review primitives and harden skill review 2026-05-12 01:28:36 +03:00
conftest.py feat(v6.68.0): contributor fast path with target-bound review evidence 2026-07-17 07:52:58 +03:00
fixtures_mock_clawhub.py v5.8.0-rc.1: make Repair observable and expand release CI 2026-05-06 02:34:19 +03:00
fixtures_mock_llm.py v5.8.0-rc.1: make Repair observable and expand release CI 2026-05-06 02:34:19 +03:00
test_acceptance_fence.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_accounting_scope_surfaces.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_acting_subagents.py release v6.82.0: truthful working cards, mobile gestures, and cancel run 2026-07-30 01:09:27 +03:00
test_advisory_observability.py fix(review): a clean advisory verdict stops being recorded as unparseable 2026-07-31 11:15:04 +03:00
test_advisory_preflight.py release: Ouroboros v6.26.0-rc.1 — systemic hardening: immune system, custody, memory integrity, native multimodal chat 2026-06-10 16:08:53 +03:00
test_agent_effort.py release: ship Ouroboros 6.65.0 planning and delivery reliability 2026-07-16 00:04:29 +00:00
test_agent_python_env.py rc(evolution): stabilize autonomous self-modification 2026-06-02 06:19:55 +03:00
test_agent_task_pipeline.py fix: preserve final replies after chat routing (#85) 2026-07-31 10:02:29 +03:00
test_anthropic_empty_block_fix.py fix(llm): stop sending Anthropic empty text blocks / cache_control-on-empty (provider_unavailable empties) 2026-06-28 03:25:48 +03:00
test_atomic_write_v639.py v6.39 Phase 4 (file-write reliability + visual verification): G atomic writes + J browser 2026-06-20 08:27:00 +03:00
test_attachment_staging.py feat(v6.52.1): GAIA-derived capability hardening + TB2.1 verification hygiene 2026-06-29 05:44:17 +03:00
test_benchmark_provenance_v6810.py fix: make managed task routing admission durable 2026-07-31 17:25:20 +03:00
test_broadcast_ws.py v5.22.0-rc.1: introduce gateway boundary 2026-05-16 00:29:04 +03:00
test_browser_isolation.py fix: v6.54.3 runtime reliability hardening from TB2.1/GAIA post-mortems 2026-07-03 22:26:08 +03:00
test_browser_tools_smoke.py feat(frontend-browser): add mobile-grade browser checks and UI polish 2026-06-05 15:42:53 +03:00
test_browser_url_policy.py fix(self-evolution): harden rc.3 server-driven evolution path 2026-06-09 04:24:31 +03:00
test_browser_visual_v639.py v6.39 Phase 4 (file-write reliability + visual verification): G atomic writes + J browser 2026-06-20 08:27:00 +03:00
test_budget_limits.py release: ship Ouroboros 6.65.0 planning and delivery reliability 2026-07-16 00:04:29 +00:00
test_budget_pause_v664.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_budget_tracking.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_bugfixes_airi.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_bughunt_fixes.py release: Ouroboros v6.26.0-rc.1 — systemic hardening: immune system, custody, memory integrity, native multimodal chat 2026-06-10 16:08:53 +03:00
test_build_scripts.py fix: restore clear macOS DMG installation 2026-08-03 07:05:03 +03:00
test_cache_optimization.py feat(v6.81.0): benchmark provenance becomes a gate, and the artefacts stop lying 2026-07-26 03:40:44 +00:00
test_cancel_cascade_v664.py release v6.82.0: truthful working cards, mobile gestures, and cancel run 2026-07-30 01:09:27 +03:00
test_capability_evidence.py fix(v6.81.0): close the two cross-phase misses the green gates passed over 2026-07-26 05:51:45 +00:00
test_capability_probe_accounting_v664.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_chat_history_quotas.py release: ship Ouroboros 6.65.0 planning and delivery reliability 2026-07-16 00:04:29 +00:00
test_chat_id_policy.py v6.0.0: move A2A and Telegram into Hub skills 2026-05-08 23:57:04 +03:00
test_chat_logs_ui.py v5.16.0-rc.2: prune ~16k LOC of obsolete or duplicative tests 2026-05-11 22:57:32 +03:00
test_chat_provenance.py Initial commit from app bundle 2026-04-22 01:04:48 +03:00
test_chat_upload.py Merge remote-tracking branch 'managed/ouroboros' into ouroboros 2026-05-25 15:03:48 +03:00
test_checklist_permission_coverage.py v6.0.0: move A2A and Telegram into Hub skills 2026-05-08 23:57:04 +03:00
test_child_result_disposition.py feat(v6.66.0): honest mutation attribution, attributed staging, environment-correct Python, auditable Skill Review history, and a drift-proof operator review wrapper 2026-07-16 22:25:04 +00:00
test_child_skill_payload_and_budget_drift.py fix(v6.74.5): child-drive skill_payload reads resolve to the canonical data root; budget drift compares OpenRouter-only deltas 2026-07-22 07:20:01 +03:00
test_claude_code_gateway.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_cleanup_test_pollution.py v5.15.0-rc.8: quality dx closed-loop skills wave on top of rc.7 2026-05-11 03:32:41 +03:00
test_cli_entrypoint.py core: cli/headless/llm/launcher/registry follow-on adjustments 2026-06-11 16:10:51 +03:00
test_closed_objectives_layer_a.py fix: evolution objective-repeat loop (BUG3) + detached-HEAD orphan/diagnostic (BUG1/2) (#53) 2026-06-23 23:51:28 +03:00
test_code_inventory_v1.py release: Ouroboros v6.26.0-rc.1 — systemic hardening: immune system, custody, memory integrity, native multimodal chat 2026-06-10 16:08:53 +03:00
test_code_search_rg.py release: Ouroboros v6.27.0-rc.3 — fix-forward: Windows batch-test argv limit 2026-06-11 16:54:04 +03:00
test_colab_bootstrap.py release: ship native Telegram companion in v6.85.0 2026-07-30 18:14:07 +03:00
test_commit_gate.py tests+ci: green & de-flake the pre-push suite (P3/P6/xdist-safety) + parallelize CI ~9x (gate stays serial) (#55) 2026-06-26 02:56:34 +03:00
test_compaction.py feat(loop): per-class transient LLM retry, encrypted-reasoning strip-retry, robust context compaction (v6.28.0) 2026-06-12 17:45:28 +03:00
test_conftest_xdist_guard.py feat(v6.47.0): verify-before-done flagship + deep cooperative subagents + workspace-aware code-intel + skill-publish SSOT 2026-06-26 12:35:23 +03:00
test_consciousness.py fix: release Ouroboros v6.64.1 dynamic route pricing hotfix 2026-07-15 01:49:11 +03:00
test_consolidator.py release: Ouroboros v6.32.0 — multi-project (shtab i proekty) + full project awareness 2026-06-14 17:24:06 +03:00
test_context.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_context_budget_ssot.py release: Ouroboros v6.13.0 — low/max context modes 2026-06-03 18:55:16 +03:00
test_context_fit_v664.py feat(v6.81.0): benchmark provenance becomes a gate, and the artefacts stop lying 2026-07-26 03:40:44 +00:00
test_context_layout.py release: Ouroboros v6.13.0 — low/max context modes 2026-06-03 18:55:16 +03:00
test_context_overflow_hint.py release: Ouroboros v6.22.1 runtime reliability fixes 2026-06-08 01:23:42 +03:00
test_continual_learning_launcher.py v6.81.0: benchmark artefacts must not carry or claim what did not happen 2026-07-26 05:04:14 +00:00
test_contracts.py release: ship native Telegram companion in v6.85.0 2026-07-30 18:14:07 +03:00
test_contributor_flow.py feat(v6.68.0): contributor fast path with target-bound review evidence 2026-07-17 07:52:58 +03:00
test_crash_report.py release: Ouroboros v6.26.0-rc.1 — systemic hardening: immune system, custody, memory integrity, native multimodal chat 2026-06-10 16:08:53 +03:00
test_cross_model_reasoning_strip.py v6.39 Phase 1: provider/FM correctness + context + MCP (B1,B2,B3,D1,H) 2026-06-20 04:26:47 +03:00
test_data_shrink_guard.py feat(core): v6.40.0 — LLM-first project naming, per-model self-DoS guard, soft join-ledger, orchestrator read-only roots, turn-into-project ordering, deferrals 1-5 2026-06-21 18:32:37 +03:00
test_deep_self_review.py release v6.82.0: truthful working cards, mobile gestures, and cancel run 2026-07-30 01:09:27 +03:00
test_delegation_budget.py feat(v6.70.0): owner-facing honesty — full reviewer rationale, self-locating tool errors, and a decision-turn outcome contract 2026-07-17 10:18:10 +00:00
test_deliverables_layout.py feat(v6.46.0): GAIA-forensic hardening — generalizable runtime fixes + empirical context-window probe 2026-06-25 12:40:40 +03:00
test_delivery_candidate.py fix(v6.71.1): acceptance-review convergence — evidence-parity, obligation rebuttal wire, honest-partial quorum, ordinary-round acceptance path 2026-07-18 11:21:53 +00:00
test_delivery_forced_finalization.py release: ship Ouroboros 6.65.0 planning and delivery reliability 2026-07-16 00:04:29 +00:00
test_devtools_benchmarks.py feat: add apply_patch and edit_batch editing tools with editbench evidence 2026-08-04 19:55:26 +05:00
test_disabled_tools_policy.py fix: make managed task routing admission durable 2026-07-31 17:25:20 +03:00
test_doc_context.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_docs_sync.py feat(v6.67.0): composable declarative widgets, evidence-based UI acceptance, and explicit autonomy/minimalism governance 2026-07-16 23:05:58 +00:00
test_edit_ops.py feat: add apply_patch and edit_batch editing tools with editbench evidence 2026-08-04 19:55:26 +05:00
test_effort_floor_v6732.py fix(v6.73.2): provider parameter value-rejections recover — learned effort floors + value-marker classifier 2026-07-21 00:31:04 +03:00
test_ensure_project_scope.py feat(v6.73.0): project origin invariant — the start-message-loss class is closed 2026-07-20 13:44:46 +03:00
test_event_bus.py release: Ouroboros v6.26.0-rc.1 — systemic hardening: immune system, custody, memory integrity, native multimodal chat 2026-06-10 16:08:53 +03:00
test_event_loop_isolation.py Initial commit from app bundle 2026-04-22 01:04:48 +03:00
test_event_state_visibility.py fix(supervisor): atomic update_state (+ fix toggle ImportError), visible event failures, temp sweep 2026-06-08 14:54:14 +03:00
test_events_llm_usage.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_evolution_fingerprint.py fix: evolution objective-repeat loop (BUG3) + detached-HEAD orphan/diagnostic (BUG1/2) (#53) 2026-06-23 23:51:28 +03:00
test_evolution_metrics_cache.py v5.2.2: marketplace and mobile stability wave 2026-04-27 21:03:22 +03:00
test_evolution_redesign.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_evolution_status.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_evolution_stop_and_cost.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_extension_companion.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_extension_dispatch_threaded.py release: ship native Telegram companion in v6.85.0 2026-07-30 18:14:07 +03:00
test_extension_isolated_deps.py release: Ouroboros v6.26.0-rc.1 — systemic hardening: immune system, custody, memory integrity, native multimodal chat 2026-06-10 16:08:53 +03:00
test_extension_loader.py release: ship native Telegram companion in v6.85.0 2026-07-30 18:14:07 +03:00
test_extension_process_runner.py release: ship native Telegram companion in v6.85.0 2026-07-30 18:14:07 +03:00
test_extension_surfaces.py feat(v6.67.0): composable declarative widgets, evidence-based UI acceptance, and explicit autonomy/minimalism governance 2026-07-16 23:05:58 +00:00
test_extensions_api.py release: ship native Telegram companion in v6.85.0 2026-07-30 18:14:07 +03:00
test_external_review_script.py feat(v6.81.0): benchmark provenance becomes a gate, and the artefacts stop lying 2026-07-26 03:40:44 +00:00
test_external_unmetered_dispatch.py release: v6.64.0 2026-07-14 19:14:35 +00:00
test_external_workspace_access.py feat: release v6.54.0 follow-up audit hardening 2026-07-01 14:50:35 +03:00
test_file_browser_api.py release: Ouroboros v6.26.0-rc.1 — systemic hardening: immune system, custody, memory integrity, native multimodal chat 2026-06-10 16:08:53 +03:00
test_files_ui.py feat(chat): outbound file delivery + WKWebView-safe open/download + rotation-safe history (v6.62.0) (#67) 2026-07-10 21:49:34 +03:00
test_filesystem_root_observability.py feat(core): v6.40.0 — LLM-first project naming, per-model self-DoS guard, soft join-ledger, orchestrator read-only roots, turn-into-project ordering, deferrals 1-5 2026-06-21 18:32:37 +03:00
test_finalize_marker_nudge.py fix(v6.61.4): answer-protocol finalization honesty — tier-token answers rejected, marker nudge no longer requires expected_output 2026-07-09 17:55:48 +03:00
test_gateway_history.py release v6.82.0: truthful working cards, mobile gestures, and cancel run 2026-07-30 01:09:27 +03:00
test_gateway_parity.py release v6.82.0: truthful working cards, mobile gestures, and cancel run 2026-07-30 01:09:27 +03:00
test_gateway_smoke.py feat(frontend-browser): add mobile-grade browser checks and UI polish 2026-06-05 15:42:53 +03:00
test_gateway_usage_accounting.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_gigachat_conversion.py fix: release Ouroboros v6.64.1 dynamic route pricing hotfix 2026-07-15 01:49:11 +03:00
test_git_ops_recovery.py release v6.82.0: truthful working cards, mobile gestures, and cancel run 2026-07-30 01:09:27 +03:00
test_git_ops_rollback_sync.py chore(release): converge re-audit findings and bump VERSION to 4.50.0-rc.3 (pre-release) 2026-04-24 04:41:22 +03:00
test_git_review_pipeline.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_git_rollback.py feat(review): add review substrate and code inventory 2026-05-27 05:42:56 +03:00
test_git_shell_policy.py git-policy: block self-repo git from task workspaces 2026-06-11 16:09:56 +03:00
test_granted_permissions_schema.py v6.0.0: move A2A and Telegram into Hub skills 2026-05-08 23:57:04 +03:00
test_headless_cli.py fix: make managed task routing admission durable 2026-07-31 17:25:20 +03:00
test_heartbeat_presentation.py release: ship Ouroboros 6.65.0 planning and delivery reliability 2026-07-16 00:04:29 +00:00
test_host_service_api.py release: Ouroboros v6.15.0 — full out-of-process extension parity + durable extension health + composer UX 2026-06-04 04:05:15 +03:00
test_host_service_rate_limiter.py fix(gateway): reap idle keys from host-service rate limiter to bound memory 2026-06-08 14:09:29 +03:00
test_identity_wording.py fix(v6.61.1): review-hardening round — adversarial r1/r2 + triad r1-r7 fixes 2026-07-09 12:58:37 +03:00
test_image_ordering_normalize.py feat(v6.52.1): GAIA-derived capability hardening + TB2.1 verification hygiene 2026-06-29 05:44:17 +03:00
test_immune_hardening.py fix(review): a clean advisory verdict stops being recorded as unparseable 2026-07-31 11:15:04 +03:00
test_improvement_backlog.py tests+ci: green & de-flake the pre-push suite (P3/P6/xdist-safety) + parallelize CI ~9x (gate stays serial) (#55) 2026-06-26 02:56:34 +03:00
test_isolated_deps.py release: Ouroboros v6.43.0 Phase 1 updater and skill trust fixes 2026-06-24 06:22:31 +03:00
test_iteration2_fixes.py WIP v6.83: step-budget enforcement for OSWorld submissions 2026-07-30 00:04:59 +00:00
test_join_ledger_d7.py feat(v6.66.0): honest mutation attribution, attributed staging, environment-correct Python, auditable Skill Review history, and a drift-proof operator review wrapper 2026-07-16 22:25:04 +00:00
test_jsonl_utils.py test: make jsonl tail fixture newline-stable 2026-05-20 03:14:05 +03:00
test_kill_process_tree_orphans.py Fix kill_process_tree: reap descendants that escaped the process group 2026-06-03 00:13:55 +03:00
test_launcher_sync.py repo: retarget official home to razzant 2026-05-31 02:32:27 +03:00
test_live_mutation_fuses.py rc(evolution): stabilize autonomous self-modification 2026-06-02 06:19:55 +03:00
test_llm_budget.py feat(loop): per-class transient LLM retry, encrypted-reasoning strip-retry, robust context compaction (v6.28.0) 2026-06-12 17:45:28 +03:00
test_llm_client_refresh.py Initial commit from app bundle 2026-04-22 01:04:48 +03:00
test_llm_no_proxy.py fix(v6.73.2): provider parameter value-rejections recover — learned effort floors + value-marker classifier 2026-07-21 00:31:04 +03:00
test_llm_provider_routing.py release v6.82.0: truthful working cards, mobile gestures, and cancel run 2026-07-30 01:09:27 +03:00
test_llm_supported_parameters.py feat: release v6.54.0 follow-up audit hardening 2026-07-01 14:50:35 +03:00
test_local_routing_and_safety.py tests+ci: green & de-flake the pre-push suite (P3/P6/xdist-safety) + parallelize CI ~9x (gate stays serial) (#55) 2026-06-26 02:56:34 +03:00
test_local_tool_parsing.py feat(tools): introduce Tool API v2 and services 2026-05-27 05:42:39 +03:00
test_lockfile_helpers.py v5.8.3-rc.2: centralize state helpers 2026-05-08 02:12:09 +03:00
test_log_forwarding.py release: Ouroboros v6.12.0 — QA hardening 2026-06-03 04:00:21 +03:00
test_loop_compaction.py feat(loop): per-class transient LLM retry, encrypted-reasoning strip-retry, robust context compaction (v6.28.0) 2026-06-12 17:45:28 +03:00
test_loop_compaction_policy.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_loop_misc.py WIP v6.83: screenshot integrity fail-closed, clipboard routing for multiline text 2026-07-29 23:23:27 +00:00
test_marketplace_api.py feat(runtime-agents): expand planning subagents and harden skill lifecycle 2026-06-05 14:18:29 +03:00
test_marketplace_clawhub.py tests+ci: green & de-flake the pre-push suite (P3/P6/xdist-safety) + parallelize CI ~9x (gate stays serial) (#55) 2026-06-26 02:56:34 +03:00
test_marketplace_fetcher.py release: Ouroboros v6.26.0-rc.1 — systemic hardening: immune system, custody, memory integrity, native multimodal chat 2026-06-10 16:08:53 +03:00
test_marketplace_provenance_contract.py release: Ouroboros v6.26.0-rc.1 — systemic hardening: immune system, custody, memory integrity, native multimodal chat 2026-06-10 16:08:53 +03:00
test_max_context_gate.py onboarding bug (#59) 2026-07-01 03:20:50 +03:00
test_max_tokens_constants.py feat(v6.81.0): benchmark provenance becomes a gate, and the artefacts stop lying 2026-07-26 03:40:44 +00:00
test_mcp_api.py release: Ouroboros v6.26.0-rc.1 — systemic hardening: immune system, custody, memory integrity, native multimodal chat 2026-06-10 16:08:53 +03:00
test_mcp_client.py v6.39 Phase 1: provider/FM correctness + context + MCP (B1,B2,B3,D1,H) 2026-06-20 04:26:47 +03:00
test_mcp_registry_integration.py v6.39 Phase 1: provider/FM correctness + context + MCP (B1,B2,B3,D1,H) 2026-06-20 04:26:47 +03:00
test_mcp_settings_roundtrip.py v5.20.0: add MCP client integration 2026-05-13 02:36:36 +03:00
test_mcp_ui_static.py v5.20.0: add MCP client integration 2026-05-13 02:36:36 +03:00
test_media_tools.py fix(test): make ffmpeg-resolver sibling test Windows-aware (3-OS CI) 2026-07-05 07:28:24 +00:00
test_memory_blocks.py release: Ouroboros v6.26.0-rc.1 — systemic hardening: immune system, custody, memory integrity, native multimodal chat 2026-06-10 16:08:53 +03:00
test_memory_tool_hints.py release: Ouroboros v6.26.0-rc.1 — systemic hardening: immune system, custody, memory integrity, native multimodal chat 2026-06-10 16:08:53 +03:00
test_message_bus.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_message_routing.py tests+ci: green & de-flake the pre-push suite (P3/P6/xdist-safety) + parallelize CI ~9x (gate stays serial) (#55) 2026-06-26 02:56:34 +03:00
test_model_catalog_api.py fix(headless-provider-capabilities): restore workspace review and provider invariants 2026-06-05 06:14:12 +03:00
test_model_concurrency.py feat(core): v6.40.0 — LLM-first project naming, per-model self-DoS guard, soft join-ledger, orchestrator read-only roots, turn-into-project ordering, deferrals 1-5 2026-06-21 18:32:37 +03:00
test_model_slot_role_model.py release v6.82.0: truthful working cards, mobile gestures, and cancel run 2026-07-30 01:09:27 +03:00
test_multimodal_chat.py release v6.82.0: truthful working cards, mobile gestures, and cancel run 2026-07-30 01:09:27 +03:00
test_mutation_attribution.py feat(v6.66.0): honest mutation attribution, attributed staging, environment-correct Python, auditable Skill Review history, and a drift-proof operator review wrapper 2026-07-16 22:25:04 +00:00
test_narration_display.py feat(narration): narrate empty tool-round bubbles with provider-returned reasoning 2026-06-19 07:29:18 +03:00
test_native_seed_trust.py release: ship native Telegram companion in v6.85.0 2026-07-30 18:14:07 +03:00
test_navigation_shell_static.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_no_core_a2a_telegram_imports.py v6.0.0: move A2A and Telegram into Hub skills 2026-05-08 23:57:04 +03:00
test_no_duplicate_companions.py v6.0.0: move A2A and Telegram into Hub skills 2026-05-08 23:57:04 +03:00
test_objective_repeat_counter.py fix: evolution objective-repeat loop (BUG3) + detached-HEAD orphan/diagnostic (BUG1/2) (#53) 2026-06-23 23:51:28 +03:00
test_observability_outcomes_v2.py release: ship Ouroboros 6.65.0 planning and delivery reliability 2026-07-16 00:04:29 +00:00
test_observability_retention.py release: Ouroboros v6.26.0-rc.1 — systemic hardening: immune system, custody, memory integrity, native multimodal chat 2026-06-10 16:08:53 +03:00
test_onboarding_wizard.py release v6.82.0: truthful working cards, mobile gestures, and cancel run 2026-07-30 01:09:27 +03:00
test_oop_extension_parity.py release: Ouroboros v6.26.0-rc.1 — systemic hardening: immune system, custody, memory integrity, native multimodal chat 2026-06-10 16:08:53 +03:00
test_osworld_adapter.py feat(v6.81.0): benchmark provenance becomes a gate, and the artefacts stop lying 2026-07-26 03:40:44 +00:00
test_osworld_cu_bridge.py release v6.87.1: a clean review verdict stops being unparseable, and the release lane goes green 2026-07-31 13:02:51 +03:00
test_ouroboroshub.py release: Ouroboros v6.25.0-rc.3 — consolidation pass and function-gate headroom 2026-06-10 06:26:35 +03:00
test_owner_attestation_v639.py release: Ouroboros v6.43.0 Phase 1 updater and skill trust fixes 2026-06-24 06:22:31 +03:00
test_owner_facing_honesty.py fix: preserve final replies after chat routing (#85) 2026-07-31 10:02:29 +03:00
test_p3_commit_binding.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_packaged_cli.py release: prepare v5.31.0-rc.1 2026-05-22 15:50:13 +03:00
test_packaging_sync.py fix: restore clear macOS DMG installation 2026-08-03 07:05:03 +03:00
test_page_chrome_static.py release v6.82.0: truthful working cards, mobile gestures, and cancel run 2026-07-30 01:09:27 +03:00
test_path_normalization.py feat(core): v6.35.0 — real-usage quality meta-fixes from a benchmark forensic audit 2026-06-17 04:09:28 +03:00
test_per_skill_version_resync.py release: ship native Telegram companion in v6.85.0 2026-07-30 18:14:07 +03:00
test_phase1_orchestration.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_plan_review.py feat(v6.81.0): benchmark provenance becomes a gate, and the artefacts stop lying 2026-07-26 03:40:44 +00:00
test_plan_review_script.py feat(v6.69.0): review-economics — cacheable reviewer prompts, honest router-rejection accounting, and review-wave budget admission 2026-07-17 08:03:16 +00:00
test_planning_swarm_adaptive_wait.py feat(v6.81.0): benchmark provenance becomes a gate, and the artefacts stop lying 2026-07-26 03:40:44 +00:00
test_platform_guard.py tests+ci: green & de-flake the pre-push suite (P3/P6/xdist-safety) + parallelize CI ~9x (gate stays serial) (#55) 2026-06-26 02:56:34 +03:00
test_plugin_api_skill_job_dir.py v5.13.0-rc.1: polish skills UI and publishing diagnostics 2026-05-10 18:57:15 +03:00
test_polyglot_inventory.py release: Ouroboros v6.33.0 — Capability-Evidence context modes, multi-project + LLM-first named projects, WS11 UI/UX 2026-06-15 09:21:57 +03:00
test_post_task_evolution.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_preflight_runner.py feat(v6.68.0): contributor fast path with target-bound review evidence 2026-07-17 07:52:58 +03:00
test_pricing.py feat(v6.81.0): benchmark provenance becomes a gate, and the artefacts stop lying 2026-07-26 03:40:44 +00:00
test_process_custody.py feat(process-custody): v6.36.2 — reap skill-companion orphans (log-only) (#51) 2026-06-17 22:06:21 +03:00
test_process_memory.py fix(v6.71.1): acceptance-review convergence — evidence-parity, obligation rebuttal wire, honest-partial quorum, ordinary-round acceptance path 2026-07-18 11:21:53 +00:00
test_process_resource_leaks.py release v6.82.0: truthful working cards, mobile gestures, and cancel run 2026-07-30 01:09:27 +03:00
test_project_conversion_rehome.py feat(v6.73.0): project origin invariant — the start-message-loss class is closed 2026-07-20 13:44:46 +03:00
test_project_delete_lifecycle.py feat(v6.73.0): project origin invariant — the start-message-loss class is closed 2026-07-20 13:44:46 +03:00
test_project_facts.py fix: make managed task routing admission durable 2026-07-31 17:25:20 +03:00
test_project_lease.py release: Ouroboros v6.33.0 — Capability-Evidence context modes, multi-project + LLM-first named projects, WS11 UI/UX 2026-06-15 09:21:57 +03:00
test_project_lease_ui_conversion.py fix(lease): a UI-converted task holds its project's one-writer lease (v6.37.1) 2026-06-18 14:19:17 +03:00
test_project_lineage_chat.py wip(project): C4.4 lineage-aware project chat membership 2026-06-18 03:04:11 +03:00
test_project_routing_v664.py fix: make managed task routing admission durable 2026-07-31 17:25:20 +03:00
test_projects_v6640.py fix: preserve final replies after chat routing (#85) 2026-07-31 10:02:29 +03:00
test_promote_chat_flow.py fix: make managed task routing admission durable 2026-07-31 17:25:20 +03:00
test_promote_event_transport.py fix: make managed task routing admission durable 2026-07-31 17:25:20 +03:00
test_prompt_cache_v664.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_protected_artifacts_policy.py feat(v6.57.0): swarm & outcome honesty + safety/effort settings (Phase 1) 2026-07-09 01:14:10 +03:00
test_provider_failure_reporting.py fix: release Ouroboros v6.64.1 dynamic route pricing hotfix 2026-07-15 01:49:11 +03:00
test_provider_integration.py release v6.82.0: truthful working cards, mobile gestures, and cancel run 2026-07-30 01:09:27 +03:00
test_public_site_metadata.py fix: restore clear macOS DMG installation 2026-08-03 07:05:03 +03:00
test_python_interpreter.py fix(test): 3-OS portability for the v6.67.0 suites 2026-07-16 23:52:36 +00:00
test_qa_fixes_6_12.py release: Ouroboros v6.12.0 — QA hardening 2026-06-03 04:00:21 +03:00
test_query_code.py feat(core): v6.34.0 — multi-task chat steering + resilience + v6.33.0 review carryover 2026-06-16 05:01:19 +03:00
test_recent_tasks_tool.py v5.17.0-rc.1: unify review primitives and harden skill review 2026-05-12 01:28:36 +03:00
test_reflection_tool_usage.py release: Ouroboros v6.33.0 — Capability-Evidence context modes, multi-project + LLM-first named projects, WS11 UI/UX 2026-06-15 09:21:57 +03:00
test_release_proof.py fix: restore clear macOS DMG installation 2026-08-03 07:05:03 +03:00
test_release_sync.py release v6.87.1: a clean review verdict stops being unparseable, and the release lane goes green 2026-07-31 13:02:51 +03:00
test_repo_commit_detached_head.py fix: evolution objective-repeat loop (BUG3) + detached-HEAD orphan/diagnostic (BUG1/2) (#53) 2026-06-23 23:51:28 +03:00
test_repo_commit_dirty_tree.py release: Ouroboros v6.26.0-rc.1 — systemic hardening: immune system, custody, memory integrity, native multimodal chat 2026-06-10 16:08:53 +03:00
test_repo_read_limits.py feat(v6.69.0): review-economics — cacheable reviewer prompts, honest router-rejection accounting, and review-wave budget admission 2026-07-17 08:03:16 +00:00
test_repo_remotes.py release(colab): restore full Colab launch and transport control (v6.10.0) 2026-06-02 01:42:20 +03:00
test_restart_reconnect.py test: align reconnect guard with viewport anchor contract 2026-08-03 06:17:09 +03:00
test_review_anti_thrashing.py release: Ouroboros v6.25.0-rc.3 — consolidation pass and function-gate headroom 2026-06-10 06:26:35 +03:00
test_review_artifact_truncation.py Prepare Ouroboros v6.3.0-rc.2 2026-05-28 03:40:22 +03:00
test_review_async_routing.py release: Ouroboros v6.25.0-rc.3 — consolidation pass and function-gate headroom 2026-06-10 06:26:35 +03:00
test_review_context_atlas.py feat(evolution): window-fit context, guaranteed-fit scope assembly, plan_task degraded fallback, identical-diff review-attempt cap, solve-capability ledger, lifecycle extraction with deterministic cycle cleanup (v6.30.0) 2026-06-13 01:01:40 +03:00
test_review_convergence_rule.py release: Ouroboros v6.25.0-rc.3 — consolidation pass and function-gate headroom 2026-06-10 06:26:35 +03:00
test_review_eligibility.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_review_fidelity.py release: Ouroboros v6.26.0-rc.1 — systemic hardening: immune system, custody, memory integrity, native multimodal chat 2026-06-10 16:08:53 +03:00
test_review_intent_split.py release: ship Ouroboros 6.65.0 planning and delivery reliability 2026-07-16 00:04:29 +00:00
test_review_model_timeout.py fix(review): restore strict scope and triad gate fidelity 2026-06-05 21:45:13 +03:00
test_review_observability.py feat(v6.81.0): benchmark provenance becomes a gate, and the artefacts stop lying 2026-07-26 03:40:44 +00:00
test_review_prompt_caching.py feat(v6.81.0): benchmark provenance becomes a gate, and the artefacts stop lying 2026-07-26 03:40:44 +00:00
test_review_readiness_gate.py release: Ouroboros v6.26.0-rc.1 — systemic hardening: immune system, custody, memory integrity, native multimodal chat 2026-06-10 16:08:53 +03:00
test_review_substrate_v2.py WIP v6.83: acceptance premise-branch, worker forensics clauses, gate 4d 2026-07-29 23:29:28 +00:00
test_review_verification_v6544.py feat(v6.81.0): benchmark provenance becomes a gate, and the artefacts stop lying 2026-07-26 03:40:44 +00:00
test_route_to_project.py fix: make managed task routing admission durable 2026-07-31 17:25:20 +03:00
test_runtime_mode_core.py release v6.82.0: truthful working cards, mobile gestures, and cancel run 2026-07-30 01:09:27 +03:00
test_runtime_mode_elevation.py release v6.82.0: truthful working cards, mobile gestures, and cancel run 2026-07-30 01:09:27 +03:00
test_runtime_reliability_v655.py fix(v6.73.2): provider parameter value-rejections recover — learned effort floors + value-marker classifier 2026-07-21 00:31:04 +03:00
test_safety_policy.py fix(v6.73.2): provider parameter value-rejections recover — learned effort floors + value-marker classifier 2026-07-21 00:31:04 +03:00
test_scope_review.py release v6.82.0: truthful working cards, mobile gestures, and cancel run 2026-07-30 01:09:27 +03:00
test_scratchpad_consolidation.py fix: release Ouroboros v6.64.2 benchmark integrity hotfix 2026-07-15 00:20:19 +00:00
test_semantic_dedup_v6370.py fix(ci): drop unused json/pytest imports tripping the ruff F gate in test_semantic_dedup_v6370 2026-06-18 06:24:23 +03:00
test_send_file.py feat(chat): outbound file delivery + WKWebView-safe open/download + rotation-safe history (v6.62.0) (#67) 2026-07-10 21:49:34 +03:00
test_send_photo.py release: Ouroboros v6.26.0-rc.1 — systemic hardening: immune system, custody, memory integrity, native multimodal chat 2026-06-10 16:08:53 +03:00
test_send_video.py Prepare Ouroboros v6.4.0-rc.1 2026-05-28 05:47:56 +03:00
test_server_auth.py v5.4.0: Improve OpenClaw skills UX and compatibility 2026-04-30 23:49:06 +03:00
test_server_runtime.py fix: stabilize mobile UI and refresh reviewer defaults (#82) 2026-07-31 08:13:53 +03:00
test_server_shutdown.py feat(devtools-benchmarks): add official benchmark harnesses and workspace executor 2026-06-06 12:03:30 +03:00
test_services_tool_v2.py services: keep_alive / service_teardown=keep for external verifiers 2026-06-11 16:09:56 +03:00
test_settings_budget_hotreload.py feat(v6.81.0): benchmark provenance becomes a gate, and the artefacts stop lying 2026-07-26 03:40:44 +00:00
test_settings_effort.py fix: stabilize mobile UI and refresh reviewer defaults (#82) 2026-07-31 08:13:53 +03:00
test_settings_ui_syntax.py feat(v6.67.0): composable declarative widgets, evidence-based UI acceptance, and explicit autonomy/minimalism governance 2026-07-16 23:05:58 +00:00
test_shell_redirect_guard.py fix(review): adversarial pass-1 findings for v6.37.0 2026-06-18 04:19:24 +03:00
test_shell_run_shell.py fix: release v6.53.2 with stable timeout tests 2026-07-01 10:57:45 +03:00
test_skill_create_golden.py fix(skills): close the runtime_data manifest-first skill-create bypass 2026-06-19 14:16:37 +03:00
test_skill_dependencies.py v5.15.0-rc.9: test-suite structural consolidation pass 2026-05-11 18:36:08 +03:00
test_skill_disable_ui.py Merge pull request #41 from ndrew1337/fix/skill-disable-ui-feedback 2026-06-05 22:19:57 +03:00
test_skill_exec.py release: ship native Telegram companion in v6.85.0 2026-07-30 18:14:07 +03:00
test_skill_flow_guards.py release: ship Ouroboros 6.65.0 planning and delivery reliability 2026-07-16 00:04:29 +00:00
test_skill_lifecycle_queue.py feat(v6.66.0): honest mutation attribution, attributed staging, environment-correct Python, auditable Skill Review history, and a drift-proof operator review wrapper 2026-07-16 22:25:04 +00:00
test_skill_loader.py release: ship native Telegram companion in v6.85.0 2026-07-30 18:14:07 +03:00
test_skill_manifest_v11.py release: ship native Telegram companion in v6.85.0 2026-07-30 18:14:07 +03:00
test_skill_migrations.py tests+ci: green & de-flake the pre-push suite (P3/P6/xdist-safety) + parallelize CI ~9x (gate stays serial) (#55) 2026-06-26 02:56:34 +03:00
test_skill_observability.py release: Ouroboros v6.17.0 deep core capability 2026-06-05 02:38:49 +03:00
test_skill_payload_policy.py Release 5.26.0-rc.1 safe codebase reduction 2026-05-19 21:46:08 +03:00
test_skill_publish.py fix(review/skills): break skill-publish convergence loop; deep-self-review pack always fits; calibrate scope pack for Claude tokenizer (v6.27.1) 2026-06-12 16:50:30 +03:00
test_skill_review.py release v6.82.0: truthful working cards, mobile gestures, and cancel run 2026-07-30 01:09:27 +03:00
test_skill_review_passes.py feat(v6.69.0): review-economics — cacheable reviewer prompts, honest router-rejection accounting, and review-wave budget admission 2026-07-17 08:03:16 +00:00
test_skill_review_persist_guard.py release: Ouroboros v6.26.0-rc.1 — systemic hardening: immune system, custody, memory integrity, native multimodal chat 2026-06-10 16:08:53 +03:00
test_skill_review_profile.py release(colab): restore full Colab launch and transport control (v6.10.0) 2026-06-02 01:42:20 +03:00
test_skill_review_runner.py feat(v6.66.0): honest mutation attribution, attributed staging, environment-correct Python, auditable Skill Review history, and a drift-proof operator review wrapper 2026-07-16 22:25:04 +00:00
test_skill_smoke_official.py ci(skills): skill_smoke Tier 6 — production review→grant→enable flow on a cheap reviewer slot (#72) 2026-07-22 01:11:54 +03:00
test_skip_tests_doc_only.py fix(review): address first adversarial review findings 2026-05-05 01:48:05 +03:00
test_smoke.py feat: add apply_patch and edit_batch editing tools with editbench evidence 2026-08-04 19:55:26 +05:00
test_startup_hygiene.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_subagent_handoff_d7.py feat(v6.66.0): honest mutation attribution, attributed staging, environment-correct Python, auditable Skill Review history, and a drift-proof operator review wrapper 2026-07-16 22:25:04 +00:00
test_subagent_media_lineage.py fix(review): triad+scope round-1 critical findings for v6.37.0 2026-06-18 04:42:13 +03:00
test_subagent_reliability.py fix(test): update source-string assertions for the v6.39.1 UI refactor 2026-06-20 22:39:40 +03:00
test_subagents_phase3.py feat(runtime-agents): expand planning subagents and harden skill lifecycle 2026-06-05 14:18:29 +03:00
test_swarm_coordination_v639.py fix(test): drop unused pytest import (ruff F401, CI quick-test gate) 2026-06-20 17:50:16 +03:00
test_swarm_fanout_telemetry.py feat(subagents): swarm fan-out telemetry + accept/reject markers (6.22.3) 2026-06-08 07:10:29 +03:00
test_swarm_parallel_spawn.py feat(subagents): parallel schedule_subagent emission + parent-side emit lock (6.22.2) 2026-06-08 06:49:56 +03:00
test_swe_pro_e1v2.py fix(v6.75.0): benchmark run provenance becomes a gate, not a report 2026-07-25 18:24:25 +00:00
test_task_cancel_endpoint_v682.py release v6.82.0: truthful working cards, mobile gestures, and cancel run 2026-07-30 01:09:27 +03:00
test_task_constraint_server_routing.py fix: make managed task routing admission durable 2026-07-31 17:25:20 +03:00
test_task_constraint_tools.py tests+ci: green & de-flake the pre-push suite (P3/P6/xdist-safety) + parallelize CI ~9x (gate stays serial) (#55) 2026-06-26 02:56:34 +03:00
test_task_done_ordering.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_task_result_monotonic.py release v6.82.0: truthful working cards, mobile gestures, and cancel run 2026-07-30 01:09:27 +03:00
test_task_status_flow.py release v6.82.0: truthful working cards, mobile gestures, and cancel run 2026-07-30 01:09:27 +03:00
test_telegram_bridge_safety.py release: ship native Telegram companion in v6.85.0 2026-07-30 18:14:07 +03:00
test_telegram_health_tasks.py release: ship native Telegram companion in v6.85.0 2026-07-30 18:14:07 +03:00
test_telegram_markdown.py release: ship native Telegram companion in v6.85.0 2026-07-30 18:14:07 +03:00
test_telegram_miniapp_cloudflare_tunnel.py fix(telegram): recover Mini App menu and preserve tunnel errors 2026-07-31 16:51:21 +03:00
test_telegram_miniapp_companion.py release: ship native Telegram companion in v6.85.0 2026-07-30 18:14:07 +03:00
test_telegram_miniapp_lifecycle.py fix(telegram): recover Mini App menu and preserve tunnel errors 2026-07-31 16:51:21 +03:00
test_telegram_miniapp_platform_support.py release: ship native Telegram companion in v6.85.0 2026-07-30 18:14:07 +03:00
test_telegram_miniapp_plugin.py release: ship native Telegram companion in v6.85.0 2026-07-30 18:14:07 +03:00
test_telegram_miniapp_runtime_status.py release: ship native Telegram companion in v6.85.0 2026-07-30 18:14:07 +03:00
test_telegram_miniapp_sidecar.py release: ship native Telegram companion in v6.85.0 2026-07-30 18:14:07 +03:00
test_telegram_miniapp_telegram_menu.py fix(telegram): recover Mini App menu and preserve tunnel errors 2026-07-31 16:51:21 +03:00
test_telegram_miniapp_tunnel_watchdog.py release: ship native Telegram companion in v6.85.0 2026-07-30 18:14:07 +03:00
test_telegram_model_budget.py release: ship native Telegram companion in v6.85.0 2026-07-30 18:14:07 +03:00
test_telegram_notifications.py release: ship native Telegram companion in v6.85.0 2026-07-30 18:14:07 +03:00
test_telegram_settings.py release: ship native Telegram companion in v6.85.0 2026-07-30 18:14:07 +03:00
test_telegram_subagent_cards.py release: ship native Telegram companion in v6.85.0 2026-07-30 18:14:07 +03:00
test_telegram_transport_safety.py release: ship native Telegram companion in v6.85.0 2026-07-30 18:14:07 +03:00
test_terminal_durability_v664.py release: ship Ouroboros 6.65.0 planning and delivery reliability 2026-07-16 00:04:29 +00:00
test_tool_api_v2_public_surface.py feat(v6.81.0): benchmark provenance becomes a gate, and the artefacts stop lying 2026-07-26 03:40:44 +00:00
test_tool_capabilities.py fix(v6.71.2): compact batch handoffs and settle OpenRouter ToS rejections at confirmed zero 2026-07-18 17:40:37 +00:00
test_tool_execution_classification.py release: ship Ouroboros 6.65.0 planning and delivery reliability 2026-07-16 00:04:29 +00:00
test_tool_policy.py release: Ouroboros v6.25.0-rc.3 — consolidation pass and function-gate headroom 2026-06-10 06:26:35 +03:00
test_transcript_seal.py release: Ouroboros v6.26.0-rc.1 — systemic hardening: immune system, custody, memory integrity, native multimodal chat 2026-06-10 16:08:53 +03:00
test_transport_commands.py release: Ouroboros v6.26.0-rc.1 — systemic hardening: immune system, custody, memory integrity, native multimodal chat 2026-06-10 16:08:53 +03:00
test_transport_metadata.py tests+ci: green & de-flake the pre-push suite (P3/P6/xdist-safety) + parallelize CI ~9x (gate stays serial) (#55) 2026-06-26 02:56:34 +03:00
test_triad_review_primitive.py feat(review): add review substrate and code inventory 2026-05-27 05:42:56 +03:00
test_ui_browser_smoke.py v5.22.0-rc.1: introduce gateway boundary 2026-05-16 00:29:04 +03:00
test_ui_preferences_api.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_ui_smoke_playwright.py fix: delay live card compact layout 2026-08-03 07:34:34 +03:00
test_unix_computer_use_remote_backends.py release v6.83.0: an undecodable screenshot fails where it is taken, an infeasibility verdict is judged as an argument, and a declared step budget is one the runtime enforces 2026-07-30 00:40:45 +00:00
test_unix_computer_use_skill.py WIP v6.83: step-budget enforcement for OSWorld submissions 2026-07-30 00:04:59 +00:00
test_update_merge_assisted.py release: Ouroboros v6.41.0 — project naming, safe merge-aware updates, full-output bubbles, Activity, skill token budget 2026-06-23 21:22:24 +03:00
test_update_merge_plan.py release: Ouroboros v6.41.0 — project naming, safe merge-aware updates, full-output bubbles, Activity, skill token budget 2026-06-23 21:22:24 +03:00
test_update_merge_policy.py release: Ouroboros v6.41.0 — project naming, safe merge-aware updates, full-output bubbles, Activity, skill token budget 2026-06-23 21:22:24 +03:00
test_update_status_cache.py release: Ouroboros v6.43.0 Phase 1 updater and skill trust fixes 2026-06-24 06:22:31 +03:00
test_usage_accounting.py fix(v6.81.0): close the two cross-phase misses the green gates passed over 2026-07-26 05:51:45 +00:00
test_usage_scope_transport_v664.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_v636_regressions.py feat(v6.81.0): benchmark provenance becomes a gate, and the artefacts stop lying 2026-07-26 03:40:44 +00:00
test_v646_hardening.py feat(v6.60.0): answer protocol by contract, blocking widening, bytes-equal verification (Phase 4) 2026-07-09 03:05:55 +03:00
test_v647_megacommit.py feat(v6.81.0): benchmark provenance becomes a gate, and the artefacts stop lying 2026-07-26 03:40:44 +00:00
test_v652_scratch_and_masking.py feat(v6.81.0): benchmark provenance becomes a gate, and the artefacts stop lying 2026-07-26 03:40:44 +00:00
test_v664_acceptance_planning.py release: ship Ouroboros 6.65.0 planning and delivery reliability 2026-07-16 00:04:29 +00:00
test_v671_acceptance_convergence.py feat(v6.74.0): acceptance review becomes a reviewer-authored terminating dialogue 2026-07-21 19:57:55 +00:00
test_v674_acceptance_dialogue.py feat(v6.81.0): benchmark provenance becomes a gate, and the artefacts stop lying 2026-07-26 03:40:44 +00:00
test_v674_light_mode_cwd.py fix(v6.74.3): Windows portability of one v6.74.0 guard test 2026-07-21 21:00:08 +00:00
test_v678_acceptance_state.py feat(v6.81.0): benchmark provenance becomes a gate, and the artefacts stop lying 2026-07-26 03:40:44 +00:00
test_v678_receipt_reconciliation.py feat(v6.81.0): benchmark provenance becomes a gate, and the artefacts stop lying 2026-07-26 03:40:44 +00:00
test_v6502_capability.py feat(v6.50.3): TB2.1 capability + swarm-affordance hardening 2026-06-28 01:41:07 +03:00
test_v6570_swarm_honesty.py fix(v6.73.2): provider parameter value-rejections recover — learned effort floors + value-marker classifier 2026-07-21 00:31:04 +03:00
test_v6580_projects_foundation.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_v6590_projects_entry.py fix: make managed task routing admission durable 2026-07-31 17:25:20 +03:00
test_v6600_answer_protocol.py fix(v6.61.2): 3-OS test portability for the v6.61.1 hardening suites 2026-07-09 13:30:13 +03:00
test_v6610_adaptive_planning.py feat(v6.61.0): adaptive planning — plan_class, tiered reviewer docs, task-fit scouts (Phase 5) 2026-07-09 03:26:02 +03:00
test_v6613_project_room_lens.py fix(v6.61.3): project-room chat lens — the room's chat lane looks at the project folder 2026-07-09 16:39:20 +03:00
test_v6730_origin_invariant.py fix: make managed task routing admission durable 2026-07-31 17:25:20 +03:00
test_verify_artifact_lifecycle.py feat(v6.57.0): swarm & outcome honesty + safety/effort settings (Phase 1) 2026-07-09 01:14:10 +03:00
test_vision.py WIP v6.83: step-budget enforcement for OSWorld submissions 2026-07-30 00:04:59 +00:00
test_vision_capability_routing.py v6.39 Phase 2 (F1): model-slot role-model + 429-aware fallback chain + cooldown 2026-06-20 06:47:41 +03:00
test_vision_routing.py release: Ouroboros v6.45.0 Phase 3 vision routing and GAIA adapter 2026-06-24 06:28:14 +03:00
test_web_search.py fix: release Ouroboros v6.64.1 dynamic route pricing hotfix 2026-07-15 01:49:11 +03:00
test_web_utils_ssot.py release: Ouroboros v6.12.0 — QA hardening 2026-06-03 04:00:21 +03:00
test_widgets_ui_static.py feat(v6.67.0): composable declarative widgets, evidence-based UI acceptance, and explicit autonomy/minimalism governance 2026-07-16 23:05:58 +00:00
test_windows_zip_path_length.py v5.8.0-rc.1: make Repair observable and expand release CI 2026-05-06 02:34:19 +03:00
test_worker_crash_retry.py fix: make managed task routing admission durable 2026-07-31 17:25:20 +03:00
test_workspace_executor.py fix: make managed task routing admission durable 2026-07-31 17:25:20 +03:00
test_workspace_executor_cleanup.py feat(devtools-benchmarks): add official benchmark harnesses and workspace executor 2026-06-06 12:03:30 +03:00
test_ws2_skill_dispatch.py tests+ci: green & de-flake the pre-push suite (P3/P6/xdist-safety) + parallelize CI ~9x (gate stays serial) (#55) 2026-06-26 02:56:34 +03:00
test_ws3_wedge_resilience.py release: v6.64.0 2026-07-14 18:55:54 +00:00
test_ws4_ws_hardening.py feat(core): v6.34.0 — multi-task chat steering + resilience + v6.33.0 review carryover 2026-06-16 05:01:19 +03:00
test_ws5_carryover.py feat(v6.81.0): benchmark provenance becomes a gate, and the artefacts stop lying 2026-07-26 03:40:44 +00:00
test_ws9_small_fixes.py release: Ouroboros v6.33.0 — Capability-Evidence context modes, multi-project + LLM-first named projects, WS11 UI/UX 2026-06-15 09:21:57 +03:00
test_zombie_prevention.py release: Ouroboros v6.26.0-rc.1 — systemic hardening: immune system, custody, memory integrity, native multimodal chat 2026-06-10 16:08:53 +03:00