mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
53680ee6bc
# Conflicts: # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/event-producer-consumer.md # docs/module-graph.md # packages/context/time-context/tests/time-context.spec.ts # packages/cordis/tool-cordis/src/api-catalog.ts # packages/core/session/README.md # packages/core/session/src/types.ts # packages/core/session/tests/surface.spec.ts # packages/examples/acp-demo/tests/acp-agent.spec.ts # packages/examples/stdio-demo/tests/stdio-agent.spec.ts # packages/hooks/hooks-claude/tests/coverage.spec.ts # packages/hooks/hooks-codex/tests/coverage.spec.ts # packages/session-query/session-query/tests/session-query.spec.ts # packages/support/invariants/tests/invariants.spec.ts # packages/ui/acp/tests/harness.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.