Почетна Преглед Помоћ
Регистрација Пријавите се
haiany
/
deepseek-harness
огледало од https://github.com/deepseek-ai/deepseek-harness.git
1
0
Креирај огранак 0
Датотеке Дискусије 0 Вики
Дрво: 58dc5f94de
Гране Ознаке
deepseek-harnes...
/
examples
/
jsonrpc-agent
Tianyi Cui d139948ed2 feat(persistence): compress JSONL logs with Zstandard пре 1 месец
..
tests d139948ed2 feat(persistence): compress JSONL logs with Zstandard пре 1 месец
README.md 642b1c29d3 feat(examples): configure max-token success via env пре 1 месец
cordis.yml 642b1c29d3 feat(examples): configure max-token success via env пре 1 месец
package.json a1c85447b8 refactor(examples): rename DSBench composition to jsonrpc-agent пре 1 месец

README.md

jsonrpc-agent

The unattended coding-agent composition for the Python SDK's bundled JSON-RPC runtime. It intentionally loads no terminal UI, console logger, approval surface, or user-interaction tool because stdout belongs to the SDK protocol and turns are driven by the SDK.

The model-facing tools are:

  • bash, foreground only
  • read, write, and edit
  • subagent, using one foreground in-process spawn provider
  • todo_write

The surrounding runtime also loads JSONL session persistence and automatic context compaction. maxTokensAsSuccess keeps a token-limited model turn as an accepted evaluation result while preserving its max-tokens reason.

Runtime environment

Variable Purpose
DEEPSEEK_API_KEY Credential passed to the OpenAI-compatible host endpoint
DEEPSEEK_BASE_URL Host endpoint used by dsh-llm-deepseek
DSH_CWD Agent workspace for bash and filesystem tools
DSH_MAX_TOKENS_AS_SUCCESS true (default) accepts token-limited results; false reports them as errors
DSH_SESSION_ROOT JSONL trajectory directory
DSH_SYSTEM_PROMPT Deployment-provided coding persona

Pass the config path through the Python SDK's cordis option or DSH_CORDIS_CONFIG. The bundled executable already carries every plugin named by this file; the target machine does not need Node.js.