dsh-gpt-compat
Fail-closed DSH compatibility guard for redundant GPT/Codex sandbox escalation arguments
68 results
Fail-closed DSH compatibility guard for redundant GPT/Codex sandbox escalation arguments
Dangerous-operation policy, canonical output redaction, and security review for DeepSeek Harness.
DSH AI 代码安全审查插件:secure_scan/secure_diff/secure_fix_verify/secure_report/secure_export/secure_baseline/secure_deps/secure_policy_show/secure_policy_set 九工具,40+ 确定性规则、密钥熵检测、git diff/staged 审查、SARIF 导出、基线接受与 SBOM-lite,零运行时依赖。
Dual-model routing policy: premium plans and rescues, local model implements ordinary steps
Shared Claw/session policy schema, preset bases, MCP init defaults. Does not deny tools. 策略契约:schema / 预设基类 / MCP 初始化默认,不执行拦截。
Policy-only multi-source quota router for DeepSeek Harness: deterministic task profiles, ordered candidate chains, health-aware fallback, and observable decisions.
The authority layer for agentic AI, as a DeepSeek Harness plugin. Governs every tool call against your business rules via the TapPass /v1/govern policy decision point.
DeepSeek Harness plugin for ecommerce operators: CSV batch tools, reproducible scoring, Chinese skills and store policy KB.
A fail-closed, auditable approval policy plugin for DeepSeek Harness
Token-efficient tool-result pruning policy for DeepSeek Harness presets.
DeepSeek Harness plugin that turns silent tool failures into loud ones: a tools/post-execute policy that matches warning signatures in successful tool output and blocks the result or attaches a notice
Security, Trust & Policy Layer for DeepSeek Harness. Don't trust your agent's tools. Verify them.
Commitment write-gate for AI coding agents: two-tier (deterministic + LLM judge) pre-execution policy. Engine-agnostic core with a DeepSeek Harness (dsh) adapter.
Agent governance suite for DeepSeek Harness (enterprise companion): policy-based tool gating (allow/deny/ask), structured JSONL audit trail, and per-agent token quotas against the host token meter — state under $DSH_HOME/gov
DeepSeek Harness (DSH) host-layer plugin: detects and auto-fixes Windows PowerShell command syntax mistakes — bash constructs, broken line continuations, pasted prompts, CRLF pollution — then executes the corrected command through the host shell seam under the normal sandbox/approval policy
DSH-native Work Charter policy plugin backed by session-coordinator-dsh
A dsh policy plugin that gates kubectl writes by kubeconfig context: hard-deny irreversible verbs outside local clusters, ask for the rest.
Seam-aligned background command execution for DeepSeek Harness — run_command via ctx.shell under the session sandbox policy, auto-promotion into ctx.jobs
Optional DeepSeek Harness right-click policy: row action menus, an app menu on blank space, and editing menus for text
Deterministic regression tests for DSH policy decisions, evaluated without invoking the protected tool body.
Manage the declared tool policy of DeepSeek Harness agent presets
Offline content-addressed proof that a temporary policy waiver stayed within approved bounds
DeepSeek Harness plugin: a deployment deny list of filesystem roots the model may never touch - fences read, write, search, and shell tool calls at tools/pre-execute
DeepSeek Harness plugin suite for the heart-health scenario: heart-health preset, resident guidance, controlled heart_* wrapper tools over the heart-algo MCP bridge, and the safety policy that hides the raw mcp__heart-algo__* tools.