cristiano.hoshikawa/agent_platform_oci
1
2
Fork 0
mirror of https://github.com/hoshikawa2/agent_platform_oci.git synced 2026-07-09 22:04:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

First commit

Browse Source
This commit is contained in:
hoshikawa2
2026-06-19 22:17:09 -03:00
commit 239203ee2a
533 changed files with 75195 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
evals/certification/evidencias/20260530_164528/html/report.html Normal file
View File

@@ -0,0 +1,6 @@
<!doctype html><html><head><meta charset='utf-8'><title>Agent Platform Certification Report</title>
<style>body{font-family:Arial,sans-serif;margin:32px}table{border-collapse:collapse;width:100%}td,th{border:1px solid #ddd;padding:8px;vertical-align:top}.ok{background:#eefbea}.fail{background:#ffecec}code{font-size:12px}</style></head><body>
<h1>Agent Platform Certification Report</h1>
<p><b>Status:</b> REPROVADO | <b>Passou:</b> 10/11 | <b>Gerado em:</b> 2026-05-30T16:45:58.362350</p>
<table><tr><th></th><th>Teste</th><th>Status</th><th>ms</th><th>Evidências</th></tr><tr class=ok><td>✅</td><td>01_backend_health</td><td>HTTP 200</td><td>31</td><td><code>evidencias/20260530_164528/logs/01_backend_health_curl.log</code><br><code>evidencias/20260530_164528/json/01_backend_health.json</code></td></tr><tr class=ok><td>✅</td><td>02_env_and_repository_config</td><td>HTTP 200; missing=[]</td><td>22</td><td><code>evidencias/20260530_164528/logs/02_debug_env_curl.log</code><br><code>evidencias/20260530_164528/json/02_debug_env.json</code><br><code>evidencias/20260530_164528/json/02_local_env_detected.json</code></td></tr><tr class=ok><td>✅</td><td>03_database_persistence_check</td><td>Banco não é SQLite local ou arquivo não encontrado; validação marcada como informativa</td><td>2</td><td><code>evidencias/20260530_164528/json/03_database_paths.json</code></td></tr><tr class=ok><td>✅</td><td>04_mcp_tools_list</td><td>HTTP 200; tools=8</td><td>21</td><td><code>evidencias/20260530_164528/logs/04_mcp_tools_curl.log</code><br><code>evidencias/20260530_164528/json/04_mcp_tools.json</code></td></tr><tr class=ok><td>✅</td><td>05_mcp_direct_tool_calls</td><td>tools_tested=2</td><td>129</td><td><code>evidencias/20260530_164528/logs/05_mcp_call_consultar_fatura_curl.log</code><br><code>evidencias/20260530_164528/json/05_mcp_call_consultar_fatura.json</code><br><code>evidencias/20260530_164528/logs/05_mcp_call_consultar_pedido_curl.log</code><br><code>evidencias/20260530_164528/json/05_mcp_call_consultar_pedido.json</code></td></tr><tr class=ok><td>✅</td><td>06_router_or_supervisor_decisions</td><td>scenarios=3</td><td>52</td><td><code>evidencias/20260530_164528/logs/06_debug_route_billing_curl.log</code><br><code>evidencias/20260530_164528/json/06_debug_route_billing.json</code><br><code>evidencias/20260530_164528/logs/06_debug_route_retail_order_curl.log</code><br><code>evidencias/20260530_164528/json/06_debug_route_retail_order.json</code><br><code>evidencias/20260530_164528/logs/06_debug_route_product_curl.log</code><br><code>evidencias/20260530_164528/json/06_debug_route_product.json</code></td></tr><tr class=fail><td>❌</td><td>07_gateway_e2e_mcp_memory_checkpoint</td><td>gateway=False; memory=True; checkpoint=True</td><td>14890</td><td><code>evidencias/20260530_164528/logs/07_gateway_message_1_curl.log</code><br><code>evidencias/20260530_164528/json/07_gateway_message_1.json</code><br><code>evidencias/20260530_164528/logs/07_gateway_message_2_curl.log</code><br><code>evidencias/20260530_164528/json/07_gateway_message_2.json</code><br><code>evidencias/20260530_164528/logs/07_gateway_message_3_curl.log</code><br><code>evidencias/20260530_164528/json/07_gateway_message_3.json</code><br><code>evidencias/20260530_164528/logs/07_session_messages_curl.log</code><br><code>evidencias/20260530_164528/logs/07_session_checkpoint_curl.log</code></td></tr><tr class=ok><td>✅</td><td>08_guardrails_behavior</td><td>Ao menos um cenário indicou comportamento de guardrail; revisar evidência</td><td>14273</td><td><code>evidencias/20260530_164528/logs/08_guardrails_prompt_injection_curl.log</code><br><code>evidencias/20260530_164528/json/08_guardrails_prompt_injection.json</code><br><code>evidencias/20260530_164528/logs/08_guardrails_pii_mask_curl.log</code><br><code>evidencias/20260530_164528/json/08_guardrails_pii_mask.json</code></td></tr><tr class=ok><td>✅</td><td>09_langfuse_trace_check</td><td>Langfuse desabilitado no .env; validação informativa</td><td>2</td><td><code>evidencias/20260530_164528/json/09_langfuse_config.json</code></td></tr><tr class=ok><td>✅</td><td>10_frontend_health</td><td>HTTP 200</td><td>18</td><td><code>evidencias/20260530_164528/logs/10_frontend_curl.log</code><br><code>evidencias/20260530_164528/logs/10_frontend_html.log</code></td></tr><tr class=ok><td>✅</td><td>11_basic_load_test</td><td>10/10 OK; rps=238.96</td><td>43</td><td><code>evidencias/20260530_164528/json/11_load_summary.json</code></td></tr></table>
</body></html>