mirror of
https://github.com/langbot-app/LangBot.git
synced 2026-08-31 06:37:14 +00:00
test(skills): harden local agent QA automation
This commit is contained in:
+1
-1
@@ -45,7 +45,7 @@ automation_reset_debug_chat: "1"
|
||||
automation_debug_chat_session_type: "person"
|
||||
automation_expected_text: "MULTITOOL_COMBO_FINAL qa_multitool_compaction_sentinel_6718 azalea-cobalt-7421 qa-plugin-smoke:multi-tool-a-local-agent qa-plugin-smoke:multi-tool-b-local-agent"
|
||||
automation_response_timeout_ms: "180000"
|
||||
automation_prompts_json: '[{"prompt":"请记住这个用于 local-agent 多工具组合回归测试的暗号:qa_multitool_compaction_sentinel_6718。请只回复 MEMORY_SET。","expected_text":"MEMORY_SET","response_timeout_ms":"180000"},{"prompt":"下面这轮只用于制造长历史压力,目标标记 MULTITOOL_RAG_GOAL 必须被压缩保留。请忽略填充内容,最后只回复 MULTITOOL_CONTEXT_PRESSURE_READY。填充片段 M001 multitool context padding. M002 multitool context padding. M003 multitool context padding. M004 multitool context padding. M005 multitool context padding. M006 multitool context padding. M007 multitool context padding. M008 multitool context padding. M009 multitool context padding. M010 multitool context padding. M011 multitool context padding. M012 multitool context padding. M013 multitool context padding. M014 multitool context padding. M015 multitool context padding. M016 multitool context padding. M017 multitool context padding. M018 multitool context padding. M019 multitool context padding. M020 multitool context padding. M021 multitool context padding. M022 multitool context padding. M023 multitool context padding. M024 multitool context padding. M025 multitool context padding. M026 multitool context padding. M027 multitool context padding. M028 multitool context padding. M029 multitool context padding. M030 multitool context padding. M031 multitool context padding. M032 multitool context padding.","expected_text":"MULTITOOL_CONTEXT_PRESSURE_READY","response_timeout_ms":"180000"},{"prompt":"MULTITOOL_COMBO final check: using the knowledge base, the compacted earlier passcode, and qa_plugin_echo twice with exactly multi-tool-a-local-agent then multi-tool-b-local-agent, return only MULTITOOL_COMBO_FINAL plus the passcode, the RAG sentinel, and both plugin tool results.","expected_text":"MULTITOOL_COMBO_FINAL qa_multitool_compaction_sentinel_6718 azalea-cobalt-7421 qa-plugin-smoke:multi-tool-a-local-agent qa-plugin-smoke:multi-tool-b-local-agent","response_timeout_ms":"180000"}]'
|
||||
automation_prompts_json: '[{"prompt":"请记住这个用于 local-agent 多工具组合回归测试的暗号:qa_multitool_compaction_sentinel_6718。请只回复 MEMORY_SET。","expected_text":"MEMORY_SET","response_timeout_ms":"180000"},{"prompt":"下面这轮只用于制造长历史压力,目标标记 MULTITOOL_RAG_GOAL 必须被压缩保留。请忽略填充内容,最后只回复 MULTITOOL_CONTEXT_PRESSURE_READY。填充片段 M001 multitool context padding. M002 multitool context padding. M003 multitool context padding. M004 multitool context padding. M005 multitool context padding. M006 multitool context padding. M007 multitool context padding. M008 multitool context padding. M009 multitool context padding. M010 multitool context padding. M011 multitool context padding. M012 multitool context padding. M013 multitool context padding. M014 multitool context padding. M015 multitool context padding. M016 multitool context padding. M017 multitool context padding. M018 multitool context padding. M019 multitool context padding. M020 multitool context padding. M021 multitool context padding. M022 multitool context padding. M023 multitool context padding. M024 multitool context padding. M025 multitool context padding. M026 multitool context padding. M027 multitool context padding. M028 multitool context padding. M029 multitool context padding. M030 multitool context padding. M031 multitool context padding. M032 multitool context padding.","expected_text":"MULTITOOL_CONTEXT_PRESSURE_READY","response_timeout_ms":"180000"},{"prompt":"MULTITOOL_COMBO final check: using the knowledge base, the compacted earlier passcode, and qa_plugin_echo twice with exactly multi-tool-a-local-agent then multi-tool-b-local-agent, return only MULTITOOL_COMBO_FINAL plus the passcode, the RAG sentinel, and both plugin tool results.","expected_text":"MULTITOOL_COMBO_FINAL","expected_texts":["qa_multitool_compaction_sentinel_6718","azalea-cobalt-7421","qa-plugin-smoke:multi-tool-a-local-agent","qa-plugin-smoke:multi-tool-b-local-agent"],"response_timeout_ms":"180000"}]'
|
||||
setup_automation:
|
||||
- "node:scripts/e2e/ensure-local-agent-pipeline.mjs --write-env"
|
||||
- "node:scripts/e2e/ensure-langrag-sentinel-kb.mjs --write-env"
|
||||
|
||||
+1
-1
@@ -45,7 +45,7 @@ automation_reset_debug_chat: "1"
|
||||
automation_debug_chat_session_type: "person"
|
||||
automation_expected_text: "PARALLEL_COMBO_FINAL qa_parallel_compaction_sentinel_8142 azalea-cobalt-7421 qa-plugin-smoke:parallel-tool-a-local-agent qa-plugin-smoke:parallel-tool-b-local-agent"
|
||||
automation_response_timeout_ms: "180000"
|
||||
automation_prompts_json: '[{"prompt":"请记住这个用于 local-agent 并行工具组合回归测试的暗号:qa_parallel_compaction_sentinel_8142。请只回复 MEMORY_SET。","expected_text":"MEMORY_SET","response_timeout_ms":"180000"},{"prompt":"下面这轮只用于制造长历史压力,目标标记 PARALLEL_RAG_GOAL 必须被压缩保留。请忽略填充内容,最后只回复 PARALLEL_CONTEXT_PRESSURE_READY。填充片段 P001 parallel context padding. P002 parallel context padding. P003 parallel context padding. P004 parallel context padding. P005 parallel context padding. P006 parallel context padding. P007 parallel context padding. P008 parallel context padding. P009 parallel context padding. P010 parallel context padding. P011 parallel context padding. P012 parallel context padding. P013 parallel context padding. P014 parallel context padding. P015 parallel context padding. P016 parallel context padding. P017 parallel context padding. P018 parallel context padding. P019 parallel context padding. P020 parallel context padding. P021 parallel context padding. P022 parallel context padding. P023 parallel context padding. P024 parallel context padding. P025 parallel context padding. P026 parallel context padding. P027 parallel context padding. P028 parallel context padding. P029 parallel context padding. P030 parallel context padding. P031 parallel context padding. P032 parallel context padding.","expected_text":"PARALLEL_CONTEXT_PRESSURE_READY","response_timeout_ms":"180000"},{"prompt":"PARALLEL_COMBO final check: using the knowledge base, the compacted earlier passcode, and one model turn that calls qa_plugin_echo for both parallel-tool-a-local-agent and parallel-tool-b-local-agent, return only PARALLEL_COMBO_FINAL plus the passcode, the RAG sentinel, and both plugin tool results.","expected_text":"PARALLEL_COMBO_FINAL qa_parallel_compaction_sentinel_8142 azalea-cobalt-7421 qa-plugin-smoke:parallel-tool-a-local-agent qa-plugin-smoke:parallel-tool-b-local-agent","response_timeout_ms":"180000"}]'
|
||||
automation_prompts_json: '[{"prompt":"请记住这个用于 local-agent 并行工具组合回归测试的暗号:qa_parallel_compaction_sentinel_8142。请只回复 MEMORY_SET。","expected_text":"MEMORY_SET","response_timeout_ms":"180000"},{"prompt":"下面这轮只用于制造长历史压力,目标标记 PARALLEL_RAG_GOAL 必须被压缩保留。请忽略填充内容,最后只回复 PARALLEL_CONTEXT_PRESSURE_READY。填充片段 P001 parallel context padding. P002 parallel context padding. P003 parallel context padding. P004 parallel context padding. P005 parallel context padding. P006 parallel context padding. P007 parallel context padding. P008 parallel context padding. P009 parallel context padding. P010 parallel context padding. P011 parallel context padding. P012 parallel context padding. P013 parallel context padding. P014 parallel context padding. P015 parallel context padding. P016 parallel context padding. P017 parallel context padding. P018 parallel context padding. P019 parallel context padding. P020 parallel context padding. P021 parallel context padding. P022 parallel context padding. P023 parallel context padding. P024 parallel context padding. P025 parallel context padding. P026 parallel context padding. P027 parallel context padding. P028 parallel context padding. P029 parallel context padding. P030 parallel context padding. P031 parallel context padding. P032 parallel context padding.","expected_text":"PARALLEL_CONTEXT_PRESSURE_READY","response_timeout_ms":"180000"},{"prompt":"PARALLEL_COMBO final check: using the knowledge base, the compacted earlier passcode, and one model turn that calls qa_plugin_echo for both parallel-tool-a-local-agent and parallel-tool-b-local-agent, return only PARALLEL_COMBO_FINAL plus the passcode, the RAG sentinel, and both plugin tool results.","expected_text":"PARALLEL_COMBO_FINAL","expected_texts":["qa_parallel_compaction_sentinel_8142","azalea-cobalt-7421","qa-plugin-smoke:parallel-tool-a-local-agent","qa-plugin-smoke:parallel-tool-b-local-agent"],"response_timeout_ms":"180000"}]'
|
||||
setup_automation:
|
||||
- "node:scripts/e2e/ensure-local-agent-pipeline.mjs --write-env"
|
||||
- "node:scripts/e2e/ensure-langrag-sentinel-kb.mjs --write-env"
|
||||
|
||||
@@ -6,6 +6,18 @@ import sys
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
def has_initial_failure_section(report: str) -> bool:
|
||||
folded = report.casefold()
|
||||
return any(
|
||||
marker in folded
|
||||
for marker in (
|
||||
"initial fail",
|
||||
"initially fail",
|
||||
"baseline fail",
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
def main() -> int:
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--workspace", required=True)
|
||||
@@ -43,7 +55,7 @@ def main() -> int:
|
||||
assert result["acceptance"] == "PASS"
|
||||
report = (workspace / "AGENT_REPORT.md").read_text(encoding="utf-8")
|
||||
folded_report = report.casefold()
|
||||
assert "initial" in folded_report and "fail" in folded_report, "report missing initial failure section"
|
||||
assert has_initial_failure_section(report), "report missing initial failure section"
|
||||
assert "root causes" in folded_report, "report missing section: root causes"
|
||||
assert any(
|
||||
heading in folded_report
|
||||
|
||||
Reference in New Issue
Block a user