Files
deepseek-harness/examples/headless-agent
Turtle 1ac946f747 feat(context): add tmux-context plugin injecting the agent's tmux location
Add @deepseek-ai/dsh-tmux-context: an opt-in per-turn context plugin that
reads which tmux session/window/pane this agent process runs in (plus the
window layout tree) via the ctx.bash seam, and injects it as one durable,
source-attributed user/message when the location changes.

- Pull on the first step of each turn; no tmux hook or background process.
- Detect a real pane by tty, not $TMUX_PANE alone: a terminal launched from
  a tmux shell inherits $TMUX/$TMUX_PANE from that ancestor, so the command
  also matches the pane's #{pane_tty} against this process's controlling
  terminal and emits fields only on a match.
- No-op outside a real pane, without a bash executor, or on a malformed
  reading.
- Own location and layout only: no pane sizes, no sibling-pane scraping.
- Unit tests at 100% per-file coverage, plus a keyless Loader e2e with a
  mock bash provider so it replays without tmux.
- Agent Note: 2026-07-27-tmux-location-context.
2026-07-28 21:40:13 +08:00
..
2026-07-26 05:06:39 +08:00
2026-07-26 05:06:39 +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.

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.