English · 中文 · Español · Português · हिन्दी

dsh-phocinae

A local, non-generative decision layer for DeepSeek Harness. A 150M-parameter model answers yes/no, choice and 2–10 score questions in one forward pass, and a fail-closed gate screens tool calls before they run.

• Runs on your machine; no cloud API, no API key.
• phocinae_ask for typed batch decisions; phocinae_gate for one command or action.
• The gate hooks tools/pre-execute: unreachable service → ask a human, never silently allow.
• The model does not write prose or code. It makes one structured decision.

Quick start

pip install phocinae-server
huggingface-cli download Phocinae/Phocinae-Largha-150M-v1 --local-dir ./model
PHOC_MODEL_DIR=./model python -m phocinae.main
dsh plugin --profile web add dsh-phocinae@0.2.5
curl http://127.0.0.1:8155/health

{"status":"ok","model_loaded":true} means the service is ready. Pin dsh-phocinae@0.2.5: a bare add dsh-phocinae can resolve to an older build while pnpm's minimumReleaseAge gate holds a fresh release back.

What you get

Examples

Ask two questions about one state:

{"state":"The user wants to delete /tmp/build. The path is inside the workspace.","questions":[{"id":"safe","type":"noul","threshold":0.8},{"id":"urgency","type":"score"}]}

The response shape is:

{"answers":{"safe":true,"urgency":4},"confidence":{"safe":0.92,"urgency":0.71},"escalate":false}

Gate a dangerous command:

{"command":"rm -rf /","toolName":"shell","cwd":"/home/me/project"}

It returns decision: "deny" with a reason and confidence; the command is never run. These outputs illustrate the schema, not a recorded fixture.

How it works

1. The host calls phocinae_ask, phocinae_gate, or the pre-execute gate.
2. The plugin sends the raw state to http://127.0.0.1:8155/v1/systemone.
3. The service returns one structured answer per question.
4. The gate maps the answer to allow / ask / deny; low confidence becomes escalate, and an unreachable service becomes ask in failMode: closed.

Configuration

Defaults live in cordis.patch.yml and lib/config.mjs. Every key has a default.

To use only the tools and screen nothing:

- id: phocinae
config:
gate:
mode: off

Security and boundaries

• Loopback only. The state contains raw tool-call text; a non-loopback endpoint is a load-time error unless explicitly allowed.
• Fail-closed. Service errors/timeouts route screened calls to a human; a missing tool name is not allowlisted.
• Not a sandbox. The gate is an additional approval signal, not a replacement for the host sandbox or human approval.
• No generation. The model cannot answer knowledge questions, write code, or summarize; use a chat model for that.

Compatibility

• Node ^22.19 or >=24.
• DSH >=0.2.1-0 <0.3.0; the bundle row mounts phocinae_ask, phocinae_gate, the gate and the skill.
• phocinae-server must be reachable at the configured endpoint.

Troubleshooting

License

Apache-2.0. The model card and server are separate projects: Phocinae-Largha-150M-v1 and phocinae-server.