feat(security): inject security policy summary into LLM system prompt (#4002)

Browse Source

Inject a human-readable summary of the active SecurityPolicy into the system prompt Safety section. LLM sees allowed commands, forbidden paths, autonomy level, and rate limits.

Supersedes #3968. Closes #2404

...

This commit is contained in:

Argenis

2026-03-19 17:54:12 -04:00

committed by GitHub

parent f7636ab81c

commit ade588b4ec

4 changed files with 312 additions and 2 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

web/dist/.gitkeep

Vendored