mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-09-15 00:19:14 +00:00
1b76ab9060
* feat: add opt-in task notes and compacted history recall * fix: validate task continuity state and preserve user answers Honor explicit opt-out, preserve clarification replies and capture failure statuses, validate notebook writes, and clear branch archive references. Update the config version and audit optional LLM credentials, with regression and integration evidence. * fix: align Helm config version with task continuity schema * fix: preserve mixed task history and declare continuity policies * fix: recover malformed history and evict archives atomically
100 lines
5.4 KiB
JSON
100 lines
5.4 KiB
JSON
{
|
|
"review_id": 5185922053,
|
|
"reviewed_commit": "bb77c69328ffcb3271e4da76c14d9a2df87a244d",
|
|
"base_commit": "4501c76b0f44cc55af6332d65ac2e7f5311f71fd",
|
|
"initial_red": {
|
|
"failed": 13,
|
|
"passed": 57,
|
|
"seconds": 2.39
|
|
},
|
|
"focused": {
|
|
"passed": 270,
|
|
"seconds": 3.86
|
|
},
|
|
"format": "passed",
|
|
"lint": "passed",
|
|
"full_branch": {
|
|
"failed": 15,
|
|
"passed": 15520,
|
|
"skipped": 182,
|
|
"deselected": 3,
|
|
"seconds": 372.86
|
|
},
|
|
"previous_full_base": {
|
|
"failed": 15,
|
|
"passed": 15427,
|
|
"skipped": 182,
|
|
"deselected": 3,
|
|
"seconds": 467.39
|
|
},
|
|
"fresh_base_failure_rerun": {
|
|
"failed": 15,
|
|
"seconds": 2.65
|
|
},
|
|
"branch_only_failure_ids": [],
|
|
"shared_failure_ids": [
|
|
"tests/test_browser_automation.py::TestBrowserTools::test_navigate_emits_screenshot_artifact_and_browser_view",
|
|
"tests/test_browser_automation.py::TestBrowserTools::test_navigate_returns_snapshot",
|
|
"tests/test_browser_automation.py::TestBrowserTools::test_navigate_screenshot_failure_does_not_break_action",
|
|
"tests/test_browser_router.py::test_validate_browser_url_rejects_private_and_non_http",
|
|
"tests/test_browserless_client.py::TestBrowserlessTools::test_web_fetch_and_web_capture_tools_agree_on_target_error_warning",
|
|
"tests/test_browserless_client.py::TestBrowserlessTools::test_web_fetch_tool_no_warning_for_normal_target_status",
|
|
"tests/test_browserless_client.py::TestBrowserlessTools::test_web_fetch_tool_success",
|
|
"tests/test_browserless_client.py::TestBrowserlessTools::test_web_fetch_tool_warns_on_target_error_status",
|
|
"tests/test_crawl4ai_tools.py::TestCrawl4AiTools::test_web_fetch_tool_invalid_filter_falls_back_to_fit",
|
|
"tests/test_crawl4ai_tools.py::TestCrawl4AiTools::test_web_fetch_tool_passes_configured_filter",
|
|
"tests/test_crawl4ai_tools.py::TestCrawl4AiTools::test_web_fetch_tool_success",
|
|
"tests/test_crawl4ai_tools.py::TestCrawl4AiTools::test_web_fetch_tool_truncates_to_4096",
|
|
"tests/test_fastcrw_tools.py::TestWebFetchTool::test_fetch_returns_error_string_on_exception",
|
|
"tests/test_fastcrw_tools.py::TestWebFetchTool::test_fetch_returns_error_when_no_content",
|
|
"tests/test_fastcrw_tools.py::TestWebFetchTool::test_fetch_uses_web_fetch_config"
|
|
],
|
|
"scope_control": {
|
|
"valid_sources_in_malformed_history_remain_readable": true,
|
|
"foreign_scope_isolated": true
|
|
},
|
|
"transaction_negative_control": "Switching capture to autocommit in an isolated process makes the real SQLITE_FULL rollback test fail because the previous sources are lost.",
|
|
"guidance": {
|
|
"errors": 0,
|
|
"warnings": 1,
|
|
"code": "AG002",
|
|
"effective_bytes": 97800
|
|
},
|
|
"coverage": [
|
|
"Shared validation at reachability, capture-failure fallback, lookup status and durable-context rendering; raw malformed checkpoints remain safe before compaction and are replaced after successful capture.",
|
|
"Malformed root values, scope, batches, status and omission counts; empty/absent controls and preserved source/scope isolation.",
|
|
"Real SQLite with a scaled 1024-page ceiling: repeated replacement, oversize replacement rollback, then successful recovery. Production remains at 32768 pages.",
|
|
"Duplicate capture while reducing retention, preserving its source and checkpoint reference.",
|
|
"Two synchronized writer threads, with distinct and identical incoming batches; stable final retention and source counts.",
|
|
"Earlier full clean-base results are retained; all 15 failed IDs were rerun on that unchanged clean base for this round.",
|
|
"No new real-model, historical prototype or deployment result is claimed."
|
|
],
|
|
"previous_ci_failure": {
|
|
"run_id": 34683883582,
|
|
"job_id": 103527323502,
|
|
"step": "Install uv",
|
|
"error": "fetch failed",
|
|
"backend_dependency_install": "skipped",
|
|
"backend_tests": "skipped"
|
|
},
|
|
"source_sha256": {
|
|
"backend/packages/harness/deerflow/agents/middlewares/AGENTS.md": "db9ff80a863c6ce8045264d0d048a2fb5e91cf00f951d271df64a87390b53917",
|
|
"backend/packages/harness/deerflow/agents/middlewares/durable_context_middleware.py": "cf37b6d48e81b1f4c8c9a9c1a12a874d893e423e13a771c17d988c19dde9bdfd",
|
|
"backend/packages/harness/deerflow/agents/task_continuity/archive.py": "f15ffc029e571f09ab3fa41319f6e5a7a70c0ce48425677cc3ccbe400a0dd448",
|
|
"backend/packages/harness/deerflow/agents/task_continuity/state.py": "0d35bf66316d9d2e09b20b124af77cbb40aa0f38eb0d43cb333a31d0266510c0",
|
|
"backend/tests/test_task_continuity.py": "5e46fdda1dcc14a896ef9a6cfeb64fa80d9842238adb995f46b5ef29a2e49149",
|
|
"docs/task-continuity.md": "38e242b80a2134247fef0094b6663184a365705540c7ed38ae62039b371812dc"
|
|
},
|
|
"log_sha256": {
|
|
"red": "b09887adda07187a612cfabd15123b825e1639013b829b1fae520707b5118ab6",
|
|
"focused": "a2d44dccc5bb9110be1dffb5154df8d6a3104ac8a14aba6712e35e71ad49d3ca",
|
|
"format": "e460172c2fa4fa9bb169e44621311f0785bf4a4deb011ba04364a7d13e55f453",
|
|
"lint": "f2d84da72b0d5e3287e7bf39c8b1096f1291c6d95f4e87e96d226557177f1229",
|
|
"full_branch": "7a43ffcc2d2e17fa5cc0657a3053d829b63a3bd65ede1c81fdf4e038b50c4710",
|
|
"base_failure_rerun": "bf3ada8c9b018f87438a4661480fb8e83143a8b2ac1f4a909c2f52b92af8779c",
|
|
"transaction_negative_control": "41a768c42168e1e74e429149f932851fb7c2f261d40bab68fd60b6e7177c9bd7",
|
|
"guidance": "cf6328d4b2e711aae8b9b3d4e6b733bfdbd4d6cbe22f47e04342e4f9c41ef97d",
|
|
"scope_control": "574971bfef4d6048d97de89a00e57f2377c8bd3429f9be2ce6acbec7971c6c0d"
|
|
}
|
|
}
|