ericleoo/dsh-escalation-tolerance

README 摘要

@deepseek-ai/dsh-escalation-tolerance Tolerate redundant sandbox permissions requests – a Cordis plugin that turns hard failures into harmless no‑ops when a tool asks for a permission mode that is already active. Problem Some GPT‑family models (e.g., gpt-5.6-luna , azure/gpt-5.4-mini ) speculatively send sandbox permissions on ordinary tool calls, even when the session already runs at that permission level. The shared escalation validator ( @deepseek-ai/dsh-sandbox ) expects any escalation request to be strictly wider than the call’s effective mode; otherwise it fails with: This means a trivial pwd can crash the tool if the model adds a redundant sandbox permissions field. Solution This plugin hooks into the tools/execute waterfall and inspects the requested sandbox permissions . If the requested mode is not strictly wider than the session's standing mode, it strips both sandbox permissions and justification from the arguments. The tool then executes at the standing mode – exactly what would have happened had the model not sent the redundant request. Genuine escalations (modes that are strictly wider) are left untouched and still go through the normal approval flow. Security note: …

分类