dsh-anchored-standard

中文说明

An experimental DeepSeek Harness agent preset that bootstraps the first model request with a Minimal-aligned prompt and two tools, then exposes the complete Standard tool catalog after the first durable tool call.

This is a community project. It is not an official DeepSeek preset and is not affiliated with or endorsed by DeepSeek.

Why

DeepSeek V4 Pro conditions strongly on the API-visible tool catalog. In the Project2 evaluation, Standard and PTC produced scores of 91 and 92, while the official Minimal preset produced 99 and 96. Permanently staying on Minimal, however, gives up the Standard preset's broader tool set.

Anchored Standard separates initial trajectory selection from later tool use:

1. Keep the Minimal complete system prompt.
2. Expose only the platform shell plus read on the first model request.
3. After the session records its first tool/call, expose all Standard tools.
4. Derive the phase from durable session events so resume and reload preserve it.

On Windows the bootstrap catalog is pwsh/read; on Linux it is bash/read.

Results

Project2 V4.1b, DeepSeek V4 Pro, reasoningEffort=max, Windows native:

Run	Ability	Reasoning blocks	we	let's	let me	Visible replies
r1	98	193	179	88	1	1
r2	99	162	165	98	0	1

Both runs emitted exactly two tool-catalog snapshots: two bootstrap tools, followed by the 25-tool Standard catalog. The result is reproducible evidence for this task, not a claim of universal improvement across models or workloads.

Full methodology and aggregate evidence are in xiaobright/modeltest.

Compatibility

Developed and tested against:

• DeepSeek Harness 0.1.0-rc.5
• repository commit 47f9438
• Node.js 24 on Windows

DeepSeek Harness is currently a developer preview and explicitly permits breaking changes. This preset is a full snapshot of the Standard composition, so review upstream changes before using it with a newer release.

Install

Clone this repository, then copy the entire preset directory into the user preset root under the id anchored-standard.

PowerShell:

$target = Join-Path $env:USERPROFILE '.dsh\.agent-presets\anchored-standard'
if (Test-Path -LiteralPath $target) { throw "Preset already exists: $target" }
New-Item -ItemType Directory -Force -Path (Split-Path -Parent $target) | Out-Null
Copy-Item -Recurse -LiteralPath '.\preset' -Destination $target

Linux/macOS:

dsh_home="${DSH_HOME:-$HOME/.dsh}"
mkdir -p "$dsh_home/.agent-presets"
test ! -e "$dsh_home/.agent-presets/anchored-standard"
cp -R preset "$dsh_home/.agent-presets/anchored-standard"

Fully restart DeepSeek Harness, create a blank session, and select Anchored Standard (experimental). Do not switch an active session from a different preset.

Verify

Export the session JSONL and inspect request/header events:

• the first header should contain only pwsh/read or bash/read;
• after the first tool call, the next changed header should contain the full Standard catalog;
• subsequent requests should keep that full catalog.

Run the local zero-dependency tests with:

npm test

Important behavior

• If the first model response makes no tool call, promotion does not occur.
• A failed tool execution still promotes the session because the durable tool/call already exists.
• The tool catalog changes once, so request-prefix cache continuity also changes once between the first and second model requests.
• The preset has the same trust level as shell access. Review its files before installation.
• The plugin performs no network requests and adds no telemetry.

Official ecosystem guidance

DeepSeek currently asks community plugin authors to publish plugins in their own GitHub projects and add the dsh-plugin repository topic for discovery. The official repository does not currently accept external pull requests and does not mandate a community repository template. See the official CONTRIBUTING.md.

License

MIT. preset/agent.cordis.yml is derived from the DeepSeek Harness Standard preset; the original DeepSeek copyright and MIT notice are retained in NOTICE.