[Bug]: Inserts into vecstorelogs and agentlogs fail with "index row size exceeds btree maximum 2704" (same defect fixed in #72, but on sibling indexes)
1
#486
[Security] a failed sandbox probe still gives the agent the Docker daemon, without verifying that it blocks host escapes
2
#484
[Enhancement]: Configure CPU and memory ceilings for flow workers
#482
[Bug]: Pentagi Deletes Logs During Task Updates
1
#481
unable to update PentAGI
#480
[Bug]: API server does not gracefully shut down on termination
[Bug]: Local Ollama agents produce well-formed tool-call JSON as message content instead of tool_calls (reflector/generator/enricher/searcher all affected)
1
#471
Code fences around stored code, Sploitus sources and Graphiti episodes close early when the content has a ``` line
1
#467
[Enhancement]: Native PII & Target Masking for Cloud LLMs (via Microsoft Presidio/LiteLLM Integration)
1
#462
REST list filters with `=` or `!=` ignore text values that contain upper case
1
#460
An unreachable LLM host hangs flow setup for about 7 minutes with nothing in the logs
1
#457
[Bug]: primary agent can report a fabricated subtask result without delegating or running anything
1
#455
[Enhancement]:Allow MVP and potential Skill features to access external custom knowledge bases
4
#454
[Bug]: 无法使用，公网目标授权门禁非常严格
2
#452
Gemini 429 rate limits are not retried
1
#450
[Enhancement]: compact size
1
#449
[Bug]: AI Agents Settings cannot be saved
5
#446
A failed task title call fails the whole task
1
#434
[Enhancement]: Add Webz.io News Search as a search engine
1
#432
[Bug]: Cannot login on fresh install
8
#403
[Bug]: Resources page freezes with large resource libraries
4
#398
[Enhancement]: Simplify Custom LLM provider setup through the web UI
2
#391
[Bug]: In some cases, retrieving flow details may hang
