mirror of https://github.com/deepseek-ai/deepseek-harness synced 2026-08-15 21:04:50 +00:00

Files

Tianyi Cui 0d6bfd8856 refactor(process): split the process manager out of the bash executor

New process/ capability family: @deepseek-ai/dsh-process owns ctx.processes —
abstract ProcessManager.spawn(spec) over a fully-explicit ProcessSpawnSpec —
plus the shared DSH_* managed-environment and CollectedOutput vocabulary;
@deepseek-ai/dsh-process-local carries the former bash-local run.ts plumbing
(detached groups, tail-keep spill-backed output, credential scrub, kill
escalation, kill-and-join disposal) with no config of its own.

dsh-bash-local becomes a consumer: it keeps command defaulting, the fused
deadline timedOut/aborted classification, the model-friendly terminal env
(now merged through the ordinary env channel), and the [stderr]-marked
background read merge, and spawns through ctx.processes. Background-process
lifetime moves to the manager, so an executor reload no longer kills live
background work; a background spawn failure is injected once into the read
path instead of being buffered as fake stderr. dsh-bash re-exports the moved
vocabulary so bash consumers keep one import root; dsh-bash-sandbox only
redeclares the inherited inject.

Every composition loading a bash executor now loads dsh-process-local (CLI,
examples, python bundled runtime, create-sdk bash feature, inline test
configs).

2026-07-26 06:59:01 +08:00

tests

refactor: drop obsolete expose-internals flag

2026-07-23 20:35:09 +08:00

cordis.yml

refactor(process): split the process manager out of the bash executor

2026-07-26 06:59:01 +08:00

package.json

refactor(examples): rename DSBench composition to jsonrpc-agent

2026-07-19 22:19:42 +08:00

README.md

feat(examples): configure max-token success via env

2026-07-19 23:03:08 +08:00

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.