@agentscope-ai/reme-dsh-plugin
面向 DeepSeek Harness 的 ReMe 记忆与上下文集成
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add @agentscope-ai/reme-dsh-plugin@0.1.0Reme Dsh Plugin 以 @agentscope-ai/reme-dsh-plugin 发布，当前版本为 0.1.0。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。
点击下方 Badge 复制 Markdown，粘贴到 README 即可。
验证 package.json 声明的 GitHub 仓库，即可管理这个公开页面。认领后，Hub 会优先安排当前版本的安全扫描，并在通过后公开展示结果。
认领这个 Plugin →This guide explains how to install, configure, and use @agentscope-ai/reme-dsh-plugin with DeepSeek Harness (DSH), including memory guidance injection, the reme_search tool, automatic memory, daily consolidation, and the ReMe Status page.
The screenshots come from a real local integration test against the current DSH source tree. Both the interface and ReMe guidance are set to English, and the isolated DSH and ReMe workspaces contain only fictional Project Aurora data. No .env values, API keys, access tokens, or personal memories appear in the screenshots.
When a DSH session starts, the plugin injects guidance that tells the root agent when and how to use long-term memory. It also registers the read-only reme_search tool. After a turn completes, the plugin can submit user and assistant messages to ReMe auto_memory; a daily schedule can run auto_dream to consolidate journal entries into durable personal knowledge.
New session
└─ Inject long-term-memory guidance
└─ Agent decides whether the request depends on history
└─ reme_search → ReMe search → daily / digest files
Completed conversation
└─ Automatic-memory batch → ReMe auto_memory → daily files
└─ Scheduled consolidation → ReMe auto_dream → digest files
The DSH adapter injects usage guidance, not every historical memory. Relevant memories enter the conversation only when the agent calls reme_search. This keeps unrelated history out of the prompt and helps prevent historical content from being treated as new instructions.
search, auto_memory, and auto_dream jobs.0.1.2-rc.1 or later; this integration is tested against 0.1.5-rc.2.^22.19.0 or >=24.0.0, matching the current DSH engine range.The default ReMe endpoint is http://127.0.0.1:2333. ReMe HTTP does not use API-key authentication, so do not expose it directly to an untrusted network.
This package replaces the former @agentscope-ai/reme/dsh entry. Remove the combined package before installing the new
host-specific plugin.
reme start workspace_dir=/absolute/path/to/your/reme-workspace \
service.host=127.0.0.1 service.port=3457
For development and screenshots, use an isolated directory outside the repository, such as /tmp/reme-dsh-demo. Do not write runtime memory into the repository's .reme/ directory.
Install the published package:
dsh plugin --profile web add @agentscope-ai/reme-dsh-plugin
For local package development, pass the package directory to DSH so the profile records a local link:
cd /path/to/deepseek-harness
pnpm link /path/to/ReMe/integrations/dsh --workspace-root
dsh plugin --profile web add /path/to/ReMe/integrations/dsh
The first command makes a source checkout's package resolver see the local plugin; the second installs its bundle into the web profile. A published DSH installation normally needs only dsh plugin ... add. Do not commit a machine-specific link: dependency to DSH.
The package declares cordis.patch.yml through package.json#dsh.bundle.patch. The patch mounts exactly one Host runtime in an isolated remeMemory realm. DSH discovers the Web entry separately through package.json#dsh.client; mounting the package twice causes a remeMemory service collision in current DSH releases.
dsh web --no-open --port 3090
Open the local URL printed by DSH and select a workspace. If DSH enables an access token, use the authenticated URL from its startup output and do not copy the token into documentation or screenshots.
ReMe and DSH can share an OpenAI-compatible model endpoint during local verification without copying a secret into YAML. Load the ReMe repository's .env in the shell, then reference the environment variable from the DSH llm-pi-ai route:
set -a
source /path/to/ReMe/.env
set +a
# The patch/settings document contains only these references, never the value.
# apiKeyEnv: LLM_API_KEY
# baseURL: !!js process.env.LLM_BASE_URL
dsh web --no-open --port 3090
Declare the route with api: openai-completions, select LLM_MODEL_NAME (or an explicitly configured model id), and use DSH's generic @deepseek-ai/dsh-llm-pi-ai adapter. The direct llm-deepseek adapter adds DeepSeek-specific request extensions and is not the right compatibility layer for an arbitrary OpenAI-compatible gateway. Never print, screenshot, or commit the resolved key.
Open Settings → Plugins → Plugin configuration → ReMe Memory. Save changes before starting the next session. Settings are stored in DSH's user settings document and apply to subsequent requests and captures. A language change affects new sessions; a schedule change immediately reschedules the next consolidation.
ReMe Memory plugin configuration
| UI meaning | Configuration key | Default | Description |
|---|---|---|---|
| Service URL | endpoint | http://127.0.0.1:2333 | Absolute ReMe HTTP URL using http or https. |
| Guidance language | language | en | en or zh; controls guidance injected into new sessions. |
| Default search results | searchLimit | 5 | Default reme_search result limit, from 1 to 50. |
| Search timeout | requestTimeoutMs | 10000 | Search timeout in milliseconds, from 1,000 to 120,000. |
| Automatic memory | autoMemoryEnabled | true | Capture completed user/assistant turns for auto_memory. |
| Exclude subagents | rootAgentsOnly | true | Inject guidance and capture conversations only for root agents. |
| Submission interval | autoMemoryInterval | 5 | Submit after this many completed turns, from 1 to 1,000. |
| Memory consolidation | autoDreamEnabled | true | Run auto_dream on the daily schedule. |
| Consolidation schedule | dreamCron | 0 23 * * * | Five-field cron expression interpreted in timezone. |
| Consolidation guidance | dreamHint | empty | Optional guidance passed to auto_dream. |
| Workspace timezone | timezone | Asia/Shanghai | IANA timezone used for batching and scheduling. |
| Background timeout | backgroundTimeoutMs | 3600000 | Timeout for auto_memory and auto_dream. |
| Shutdown flush timeout |
Deployment configuration also supports REME_URL, or REME_HOST together with REME_PORT. The timer-only test option dreamIntervalMs is intentionally excluded from user settings.
On agent/session-start, the plugin injects long-term-memory guidance as native plugin context. Expand Context injection · reme-memory in the message flow to inspect both the content and provenance.
The guidance establishes four rules:
daily and digest Markdown files.reme_search before answering questions that depend on past facts, preferences, decisions, people, dates, experience, or todos.auto_memory and auto_dream jobs normally maintain memory without manual agent calls.The injected message carries plugin=reme-memory and form=instructions provenance. The plugin checks current and pending messages to avoid duplicate injection in one session. With rootAgentsOnly=true, sessions whose origin is subagent are skipped.
reme_searchA normal request can cause the agent to use memory automatically. For a deterministic check, explicitly request the tool and sources:
Use reme_search to look up my long-term memory: what are the weekly report time,
report format, and primary database for Project Aurora? Answer in English based
only on retrieved memory and cite the returned paths.
In the screenshot, the agent performs one read-only search and returns ranked evidence from daily/2026-09-11/Project Aurora kickoff.md and digest/wiki/project-aurora.md. It reports Friday at 4:00 PM, concise Markdown, and PostgreSQL with Redis used only as cache.
| Parameter | Required | Description |
|---|---|---|
query | Yes | Focused natural-language search query; an empty value fails closed. |
limit | No | Result limit from 1 to 50; defaults to the plugin's searchLimit. |
min_score | No | Minimum score; normally leave it at 0. Negative values become 0. |
An empty successful response becomes No relevant memory found.. Service failures become ReMe search failed: ..., allowing the agent to report a failed lookup instead of guessing.
With autoMemoryEnabled=true, the plugin listens to DSH session events and collects completed user and assistant messages per session. When autoMemoryInterval is reached, the batch enters a background queue and calls ReMe auto_memory. Plugin-generated context and tool results are excluded from capture so they cannot be laundered back into long-term memory.
Chat completion and durable memory completion are asynchronous. To verify persistence, open ReMe Status → Auto Memory, wait until running and queued tasks return to zero, and confirm that the latest submission is marked Completed.
Open Settings → ReMe Status. Full service diagnostics load when the page opens or the user refreshes them. While the page is visible, only the DSH plugin runtime counters refresh every 5 seconds.
Overview shows connectivity, ReMe version, endpoint, refresh time, automatic-memory and consolidation settings, process RSS, estimated component memory, active sessions, and queued turns. Server configuration (redacted) exposes a safe view of app_config. A green Connected badge confirms the health request, but optional component availability should still be checked under Components.
This tab reports active sessions, queued turns, running tasks, queued tasks, and the pipeline from conversation turns through the submission queue to long-term memory. Activity states include Queued, Running, Completed, Failed, and Cancelled. Activity is process-local diagnostic history; ReMe workspace files remain the durable source of truth.
ReMe Status Memory Consolidation
This tab shows the next run, cron schedule, timezone, and current-process result. The flow is Journal entries → Organize and connect → Personal knowledge base. Consolidate Memory Now manually invokes auto_dream, which may call a model and modify workspace files. The completion banner in the screenshot was produced by a real call that added a source link to digest/wiki/project-aurora.md.
Components displays health and resource usage for the file graph, file store, keyword index, and optional embedding store. An unconfigured embedding instance is not itself a failure. If a derived index is unhealthy, rebuild it from source Markdown instead of deleting or rewriting user memory.
Journal browses the workspace's daily files. The left pane searches and selects files; the right pane previews paths, frontmatter metadata, and Markdown content. The list is capped at the newest 5,000 files.
ReMe Status Personal Knowledge Base
Personal Knowledge Base browses consolidated digest files. Journal entries preserve time-oriented source material, while digest documents hold stable, deduplicated knowledge for long-term recall. Wikilinks can preserve provenance back to the source journal entry.
reme start is still running and verify the endpoint protocol, host, and port.127.0.0.1 refers to each machine separately; configure a browser-reachable address.requestTimeoutMs when the service legitimately needs more than ten seconds.language; existing sessions are not reinjected.rootAgentsOnly=true.reme_searchreme_search, base the answer on the result, and cite sources.limit or min_score only when needed.autoMemoryEnabled=true and check whether autoMemoryInterval has been reached.shutdownTimeoutMs drain budget.The test used DSH 0.1.5-rc.2, ReMe 0.4.1.11 on port 3457, and isolated Project Aurora workspaces. It verified:
reme-memory plugin context with correct provenance.reme_search call returning consistent daily and digest evidence through an OpenAI-compatible model route.auto_memory submission with no queued task remaining and a new daily/2026-09-11/project-aurora-conventions.md file.auto_dream consolidation with an updated digest/wiki/project-aurora.md source list.DSH screenshots live in integrations/dsh/figures/ and ship with the plugin package.
shutdownTimeoutMs |
5000 |
| Budget for draining background work during shutdown. |