mirror of
https://github.com/deepseek-ai/deepseek-harness.git
synced 2026-09-14 04:01:35 +00:00
# Conflicts: # .agents/notes/implemented/architecture/2026-06-20-branded-ids.i18n.yaml # .agents/notes/implemented/architecture/2026-06-20-branded-ids.md # .agents/notes/implemented/architecture/2026-06-20-branded-ids.zh.md # packages/fs/tool-fs/tests/read-image.spec.ts # packages/llm/llm-deepseek/tests/adapter.e2e.ts # packages/llm/llm-deepseek/tests/serialize.spec.ts # packages/llm/llm-pi-ai/src/context.ts # packages/llm/llm-pi-ai/tests/context.spec.ts # packages/llm/llm-pi-ai/tests/convert.spec.ts # packages/llm/llm/src/message.ts # packages/llm/llm/tests/content.spec.ts
guard/ — loop-hygiene guard family
English | 中文
Behavioral guard plugins watch the agent loop for unproductive patterns and enforce per-call budgets. A guard is a self-contained consumer of core services and extension points, not a swappable capability.
| Package | Role | ctx key |
|---|---|---|
repeat-tool-reminder/ |
Advisory reminders for repeated tool calls | listens on tool and agent events |
timeout-policy/ |
Arms per-call tool deadlines as deployment policy | registers a tools/execute listener |
Reminders travel as additionalContexts on the tools/post-execute decision and are appended as logged plugin-sourced user/message events (tools); the timeout split across dsh-timeout, capability termination, and this policy layer is recorded in the timeout-library Agent Note.