mirror of
https://github.com/deepseek-ai/deepseek-harness.git
synced 2026-09-13 04:03:30 +00:00
- llm-retry: validate config before registering the projection unit; document the branded-retry-id zod cast; start stateVersion at 1. - agent-loop: register turnBoundary only after every config validation, so a rejected constructor leaves no unit behind; the defensive-cap test no longer needs fiber cleanup. - agent-instructions: keep newest-first per-scope change history so the latest visible change survives a surface replacement shadowing the newest one (restores the previous scan-visible semantics); add a regression test for the delete-after-shadow sequence. - tool-skill: keep catalog-message history so a shadowed newest catalog message still falls back to the latest visible digest. - session-query-sqlite: drop the unused required sessionProjections injection. - plan-mode: restore the command/done error-drop regression test and the cold-replay command/done fold; drop the inaccurate state-reference comment. - tool-todo: remove a stray blank line; document the turnBoundary reader contract on the projection type.
skill/ — skill capability family
English | 中文
This family discovers reusable agent instructions and exposes them to the model through a provider-neutral catalog and loader.
| Package | Role | ctx key |
|---|---|---|
skill/ |
Defines skill provider registration and lookup | ctx.skills |
skill-badge/ |
Contributes the optional bundled dsh badge skill | registers on ctx.skills |
skill-filesystem/ |
Discovers skills from local filesystems | registers on ctx.skills |
tool-skill/ |
Publishes the skill catalog and model-facing loader | registers on ctx.tools |
This capability remains outside the core control spine and can use local, embedded, or remote providers without changing the model-facing contract.
The subsystem reference — discovery priority, catalog snapshots, the skill loader — is docs/subsystems/skills.md.