dsh-self-evolve
由 Agent 编写的 DeepSeek Harness 程序性记忆：一个受保护的 skill_manage 工具、一个可选择启用的回合后审查器，以及一个可选的 Jev 决策门。
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add github:Kosello/dsh-self-evolve#ce43a82ab89cd79c9aa18fc8b0f208751bf2dfa7Self Evolve 以 dsh-self-evolve 发布，当前版本为 0.4.0。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
Agent-authored procedural memory for DeepSeek Harness.
The agent saves a proven procedure as a SKILL.md in a root the harness already
scans, and future sessions follow it instead of rediscovering it — with the
guards, budgets and approvals an unattended self-improvement loop needs.
This is a fork of jianghuife/dsh-self-evolve
(MIT), ported to DSH 0.2.1-rc.2 and extended. The upstream proof of concept was
a single 0.1.0 release; this fork keeps its small core and adds the missing
safety rails plus the automatic half of the loop.
Status:
0.4.0, 106 tests, typechecked against DSH0.2.1-rc.2. Not published to npm; install from GitHub or a local checkout.
| Capability | Details |
|---|---|
skill_manage tool | list, create, patch, edit, delete (archives), write_file, remove_file, pin, unpin |
| User + project scope | ~/.dsh/skills and <project>/.dsh/skills, plus flat <name>.md skills |
| Read before write | a skill must be loaded with the skill tool before it can be patched, edited, deleted or pinned |
| Duplicate refusal | create rejects near-duplicates and names the skill to patch instead |
| Credential + lint scan | blocks credential-shaped text; warns on oversized bodies, incident-log shape, references sprawl, destructive shell idioms |
| Staged approvals | optional writeApproval; review diffs with /skills pending, settle with approve/reject |
| Post-turn reviewer | opt-in fork of the finished turn that patches or creates skills, isolated from the main transcript |
| Jev gate | optional TypeSafe Jev call that can cancel a pointless review, with deterministic fallback |
| Curator | mechanical aging: stale after 30 days, archived after 90, pinned skills exempt, only agent-authored skills, never hard-deleted |
| Usage ledger | records loads and review-gate decisions for tuning |
0.2.1-rc.2 (the tested target; other 0.2.x may work).TYPESAFE_API_KEY) only if you enable the Jev gate.From GitHub (once the repository is published):
dsh plugin --profile web add github:Kosello/dsh-self-evolve
From a local checkout:
git clone https://github.com/Kosello/dsh-self-evolve.git
cd dsh-self-evolve
npm ci
npm run build # produces dist/ (also committed for GitHub installs)
dsh plugin --profile web add "$PWD"
Then restart the profile. The plugin activates as the self-evolve row and adds
skill_manage together with the /skills command. See
docs/installation.md for manual wiring, environment
files, verification and uninstall.
Everything is optional; defaults keep the plugin useful and quiet. Put overrides
on the row in your profile's cordis.patch.yml:
- id: self-evolve
config:
readBeforeWrite: true # default
writeApproval: false # set true to review every write
review:
enabled: true # the reviewer spends tokens; opt in
turnInterval: 10
toolCallThreshold: 15
gate: jev # counters (default) or jev
jev:
model: jev-latest
apiKeyEnv: TYPESAFE_API_KEY
confidentNo: 0.75
The full key reference, including the reviewer and gate budgets, is in docs/configuration.md.
The gate is off unless you ask for it, and it degrades to counters when it cannot run. Give the harness the key through a dedicated env file rather than the profile YAML:
install -m 600 /dev/null ~/.dsh/typesafe.env
printf 'TYPESAFE_API_KEY=%s\n' "$YOUR_KEY" >> ~/.dsh/typesafe.env
mkdir -p ~/.config/systemd/user/deepseek-harness.service.d
printf '[Service]\nEnvironmentFile=%%h/.dsh/typesafe.env\n' \
> ~/.config/systemd/user/deepseek-harness.service.d/typesafe.conf
systemctl --user daemon-reload
systemctl --user restart deepseek-harness.service
The model gets one new tool:
| Action | Purpose |
|---|---|
list | skills across both scopes, with uses and layout |
create | new skill; scope: "user" | "project" |
patch | exact-text replace inside SKILL.md (preferred update) |
edit | replace body/description wholesale |
delete | archive (never hard-delete) |
write_file / remove_file | supporting files under the skill directory |
pin / unpin | exempt a skill from curator aging |
Humans get the /skills command:
/skills pending | diff <id> | approve <id|all> | reject <id|all>
/skills approval on|off
/skills review on|off|now
Worked examples are in docs/usage.md.
turn ends ──▶ counters due? ──▶ (optional) Jev gate ──▶ fork reviewer
│
skill_manage ─┴─▶ ~/.dsh/skills/<name>/SKILL.md
│
next session ─┴─▶ skill catalog (progressive disclosure)
The reviewer and gate are described in docs/review-loop.md; the module map is in docs/architecture.md.
skill_manage, so read-before-write,
duplicate refusal, credential scanning and staged approval all still apply.skill + skill_manage right after activation; DSH has no per-activation
tool filter, so this is defence in depth, not a sandbox. Run with
writeApproval: true when reviewing untrusted conversations.Details and threat model: docs/security.md.
npm ci
npm run check # tsc against DSH 0.2.1-rc.2
npm test # 106 unit/integration tests
npm run build # dist/index.js
npm run smoke # built tool → real dsh-skill + dsh-skill-filesystem catalog
npm run gate-stats # summarize ~/.dsh/self-evolve/gates.jsonl
npm run verify # check + test + build + smoke
CI runs the same checks on every push (.github/workflows/ci.yml).
0.2.1-rc.2; the plugin API is young and may move.subagent service and a provider (fork by default).MIT. The upstream copyright notice is retained in LICENSE; this
fork's changes are offered under the same terms. Upstream:
jianghuife/dsh-self-evolve.