dsh-memory-ga
适用于 DeepSeek Harness 的门控 GA 风格分层记忆：强制注入的 L1、工作检查点，以及结算至 Skills/L1/L2——不会静默自动保留。
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:DiligenceLai/dsh-memory-ga#8a7150fac7c7cc063b688bf789e1feb26e82bcfcMemory Ga 以 dsh-memory-ga 发布，当前版本为 0.1.2。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。
Gated, file-based long-term memory for DeepSeek Harness — inspired by GenericAgent’s discipline: No Execution, No Memory.
Your agent already has Skills.
What it usually lacks is a small, trustworthy index of facts + rules, a session notepad, and a settlement ritual that turns hard-won lessons into Skills / facts — without silently poisoning memory from every chat.
Language: English · 中文
Coding agents forget. Vector “auto-memory” products remember too much — drafts, wrong turns, guesses.
dsh-memory-ga takes the other path:
| Principle | What you get |
|---|---|
| Verified only | Long-term writes only after tools (or the user) confirmed reality |
| Hard-injected L1 | A ≤~30-line index + RULES every turn — not a pointer you might never open |
| Working notepad | Session key_info re-injected while non-empty |
| Gated settlement | start_long_term_update opens a protocol; it does not auto-edit your files |
| Skills stay Skills | Reusable procedures → DSH Skills. Memory is not a second SOP warehouse |
| Local & auditable | Plain UTF-8 under $DSH_HOME/memory — diff, backup, hand-edit |
No embeddings required. No cloud bank. No silent retain.
$DSH_HOME/memory/
L0_memory_management.md # constitution (how to remember)
global_mem_insight.txt # L1: NAV + RULES → hard-injected
global_mem.txt # L2: verified facts → read on demand (≤9-line sections + pointers)
l3/<topic>.md # L3: long-form fact dossiers (L2 sections point here)
.working/<session>.txt # optional session notepad dump
DSH platform (not this folder)
Skills / skill catalog # procedures
Sessions # full transcripts (query via DSH, not a memory “L4” tree)
No notes-style junk drawer and no memory-tree L4. l3/ holds fact dossiers only — procedures belong to Skills (Skill = how-to, L3 = what-is).
If a Skill is wrong, fix the Skill — don’t keep a shadow errata page in memory.
Verified + worth keeping?
├─ reusable workflow → DSH Skill (+ optional L1 one-liner)
├─ env / config fact → L2 (± L1 pointer)
├─ very long fact → l3/<topic>.md dossier (+ L2 pointer)
├─ one global rule → L1 RULES
└─ this task only → Working (or discard)
| Tool | Role |
|---|---|
update_working_checkpoint | Replace session notepad (key_info) |
start_long_term_update | Return L0 + settlement protocol (no automatic writes) |
memory_status | Paths, L1/L2 sizes, l3 dossier count, working empty?, nudge counters |
Optional soft nudges (default on): after enough steps, gently remind checkpoint / settlement. Never force tool calls. Never auto-write L1/L2.
Compatible with DSH Cordis plugins (dsh.bundle.patch).
In your profile directory (example: $DSH_HOME/profiles/web):
pnpm add dsh-memory-ga@github:DiligenceLai/dsh-memory-ga
Ensure the profile loads the package (either list it under dsh.profile.bundles or rely on the package’s cordis.patch.yml insert — same pattern as other DSH community plugins).
pnpm add dsh-memory-ga@file:../path/to/dsh-memory-ga
Note: some package managers copy
file:deps. After editing the plugin source, reinstall/relink the profile dependency and restart DSH (or wait for profile HMR).
Copy the bundled skill into the user skills root so the agent can load memory-management:
skills/memory-management/SKILL.md → $DSH_HOME/skills/memory-management/SKILL.md
Restart or wait until the skill filesystem rescans.
memory_status → should show $DSH_HOME/memory.update_working_checkpoint with a short note → next model step should include ### [WORKING MEMORY].start_long_term_update → protocol + full L0; disk unchanged until you edit.First boot creates missing L0/L1/L2 from templates and never overwrites existing files.
Cordis config on plugin id memory-ga (optional):
- id: memory-ga
config:
# root: null # default: $DSH_HOME/memory
bootstrap: true
injectL1: true
injectWorking: true
l1MaxChars: 1200
workingMaxChars: 1200
persistWorkingFile: true
nudge:
enabled: true
workingEvery: 12
settleAfterSteps: 15
maxWorkingNudges: 3
maxSettleNudges: 2
Hard dependency: the plugin declares inject: ["tools", "systemPrompt", "llm"]. @deepseek-ai/dsh-llm (with createUserMessage) must be present in the host composition — working-memory and nudge injection rely on it. If it is missing, the plugin still loads but memory_status will warn that working/nudges are not injected, rather than silently failing.
workingMaxChars is the single cap for both storing and injecting the working notepad, so memory_status.workingChars always reflects what the model actually sees.
memory/If you want maximum automatic recall across tools, look at other stacks.
If you want controlled crystallization and git-friendly truth, you’re in the right place.
This repository ships generic templates only.
Your real L1/L2 live under $DSH_HOME/memory on your machine and are never part of this package.
Do not commit personal memory files, tokens, or absolute home paths into forks.
git clone <this-repo>
cd dsh-memory-ga
pnpm install # schemastery + peers for local smoke
Entry: lib/index.js (Cordis name / inject / Config / apply).
Issues and PRs welcome: install docs for more profiles, stronger nudge hooks, project-scoped memory overlays, session-search Skill examples.
MIT — see LICENSE.
GenericAgent is a separate project; this plugin only borrows the memory discipline, not GA’s full runtime.