dsh-output-custody-proof
Content-addressed proof for body-free DSH tool-result custody stages
12 results
Content-addressed proof for body-free DSH tool-result custody stages
A runtime prompt-injection shield for DeepSeek Harness tool results.
Deterministic, recoverable tool-result compression and cache-aware compaction for DeepSeek Harness
DeepSeek Harness host plugin: archive raw tool results into the session folder, clear them from the visible conversation at round boundaries, and let the model recall them through a read_tool_result_log tool.
Token-efficient tool-result pruning policy for DeepSeek Harness presets.
Adaptive task and risk routing, loop budgets, and progressive tool-result pruning for DeepSeek Harness
Data-loss-prevention plugin for DeepSeek Harness: a non-configurable tool guard floor, tool-result redaction, and fail-closed telemetry redaction
Post-edit diagnostics for DeepSeek Harness: runs configured type-checkers and linters after a successful write/edit and feeds the findings back to the model as tool-result context
Zero-loss tool-result pruning for the DeepSeek Harness (DSH): oversized tool results are spilled to a file first, then pruned with exact elided-span offsets and a recovery locator. A dsh-plugin.
Durable DeepSeek Harness bundle: the local-model performance tuning carried as a re-installable plugin layer (compaction, tool-result pruning, time context, cloud title routing, text-toolcall guard) — survives dsh updates
Context Compaction plugin for DeepSeek Harness: tool-result pruning, LLM or offline-rule summarization with a user-facing compression report, dead-loop guard, and /restore rollback.
Keep DSH tool results cache-prefix safe: truncate a result before it first enters the session surface, and never rewrite a tool result a provider request has already delivered.