mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
6f01d4d099
# Conflicts: # docs/event-producer-consumer.md # examples/coding-agent/tests/code-mode.e2e.ts # examples/coding-agent/tests/harness.ts # examples/coding-agent/tests/resume.e2e.ts # examples/cordis-agent/tests/harness.ts # packages/bash/tool-bash/tests/integration.spec.ts # packages/compact/compact-basic/tests/compact-loop-repro.spec.ts # packages/cordis/tool-cordis/tests/integration.spec.ts # packages/core/agent-loop/tests/contract-regressions.spec.ts # packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts # packages/hooks/hooks-claude/tests/bridge.spec.ts # packages/hooks/hooks-claude/tests/coverage.spec.ts # packages/hooks/hooks-codex/tests/bridge.spec.ts # packages/hooks/hooks-codex/tests/coverage.spec.ts # packages/todo/tool-todo/tests/integration.spec.ts
guard/ — loop-hygiene guard family
Behavioral guard plugins that watch the agent loop for unproductive patterns and nudge the model back on course. A single product package — there is no interface/implementation seam here, because a guard is a self-contained consumer of existing core seams (tools/post-execute, agent/prompt-submit, agent/status), not a swappable capability.
| Package | Role | ctx key |
|---|---|---|
repeat-tool-guard/ |
Advisory reminders when an agent loops on identical tool calls | (listens on ctx.tools' waterfalls) |
Reminders travel as additionalContexts on the tools/post-execute decision; the agent loop appends them as logged context/message events after the step's tool results (see the tools package), so everything a guard says to the model is reconstructable from the session log.