Files
deepseek-harness/examples/headless-agent
Tianyi Cui d488330ba4 fix(rebase): migrate the replayed E2B branch onto the rebased parent
The linear replay carried old-lineage content over parent-owned files;
this checkpoint restores them and adapts the branch to the parent's
post-rebase seam:

- restore all pty/lsp/subprocess/code-runtime surfaces to the parent's
  exact content (this branch claims none of them) and drop the net-zero
  code-runtime-e2b/pty-e2b/lsp-e2b residue and its registrations
- widen serializeRemoteEnvironment to the seam's NodeJS.ProcessEnv
  tombstone contract: an explicit undefined removes an ambient entry
- migrate the two E2B fixture Agent stubs to the Inbox-model interface
  and Session.create
- re-apply the branch's gen-doc-graphs roles, THIRD_PARTY_NOTICES e2b
  row, and packages/README group row (trimmed to the doc budget);
  regenerate catalogs and re-record bilingual pairings
2026-08-08 22:19:13 +08:00
..
2026-08-08 15:08:07 +08:00

headless-agent

English | 中文

Headless one-shot agent wiring: DeepSeek V4 + local bash and filesystem tools + subagent delegation + workflows and fresh-agent Ralph iteration + todo_write + JSONL persistence, with @deepseek-ai/dsh-cli-demo as the app front door.

Run it

# repo root .env (gitignored) or exported env:
#   DEEPSEEK_API_KEY=sk-…
#   DEEPSEEK_BASE_URL=https://…   # optional; defaults to the public API
pnpm run demo:headless "fix the failing test in this workspace"
pnpm run demo:headless --output-format json -- "summarize the implementation"
pnpm run demo:headless --output-format stream-json -- "run the focused tests"

Exactly one nonblank positional task is required; quote tasks containing spaces. There is no -p flag. text prints the last text-bearing assistant message, json prints one DSH-native result record, and stream-json emits the top-level session's canonical task-turn events before that record. Child sessions surface only through parent tool events and results.

Each invocation creates and persists a fresh session, runs all model and tool steps in one turn, flushes, disposes, and exits. This is non-interactive automation: there is no prompt, approval, resume, second turn, or stdin context. The configured tools can mutate the launch workspace, run commands, spawn child agents, and consume provider tokens.

E2B POC overlay

e2b.cordis.yml replaces the local filesystem and subprocess providers with one shared E2B sandbox while retaining dsh-bash-local and the same model-facing tools. Put E2B_API_KEY beside DEEPSEEK_API_KEY in the gitignored root .env, then run:

pnpm run demo:e2b "create hello.txt, read it back, and run pwd"

The overlay creates the same absolute cwd inside the sandbox, but it does not upload or mount the host workspace. File and Bash mutations exist only in E2B; Cordis, model calls, agent/session state, session logs, skills, and SDK buffers remain on the host. The demo kills its sandbox on timeout and disposal. It is a provider-composition POC, not a whole-harness migration or a workspace-sync feature.

Advanced and snapshot wiring

advanced.cordis.yml adds Code Mode and the Cordis tools to the shipped leaf. advanced.cordis.snapshot.yml replaces only the live LLM with replay. The tests under tests/ own the keyless real-Loader smoke, key-gated world-verified smoke, and the stream-json replay snapshot with its parent and child session fixtures.

The package-level CLI contract documents output records, exit status, cancellation, persistence, and model/token effects.