Sharl210/dsh-strip-sandbox-permissions

README 摘要

dsh-strip-sandbox-permissions A zero-dependency DeepSeek Harness (DSH) plugin that ignores sandbox permissions / justification fields carried in model tool-call arguments, preventing false sandbox escalation rejections. Problem Some models (a post-training tendency) automatically attach sandbox permissions (and its companion justification ) to tool calls. When the session already runs with sufficient permission (for example full access), carrying a non-strictly-wider value triggers a false rejection from the DSH sandbox: How it works Every model tool call flows through the llm/stream waterfall, so this is the single interception point that covers every adapter. Adapters emit a block-end chunk carrying the fully assembled tool-call block at the end of the stream. This plugin rewrites that block: it parses the arguments object, deletes the top-level sandbox permissions / justification keys, and re-serializes. Session logs and replay both see the cleaned arguments, so nothing downstream disagrees. Only those two escalation-specific keys are stripped; every other argument is preserved verbatim. A new block is produced only when one of the keys actually exists — otherwise the original b…

分类