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

Files

Tianyi Cui c94f1563f5 test(acp-example): five snapshot scenarios + cancel/error input ops

Adds the first cut of snapshot scenarios, each asserting a normalized stdout
transcript golden and (for model turns) a re-persisted session-log golden:

- text-turn, tool-call-turn, multi-turn: RECORDED against the real API — the
  committed session.jsonl is a genuine harvested log; replay derives the model
  script from it and reproduces deterministically with no key. tool-call-turn
  exercises the real bash executor (echo SNAPSHOT_OK → tool/call + tool/result
  + a post-tool answer step).
- error-finish, cancel: AUTHORED via a replay.override.json sidecar (the live
  API can't be coaxed into a deterministic 401 or mid-stream cancel). error-
  finish replays a {kind:throw} 401 → the bridge answers the prompt with a
  JSON-RPC error and the log records turn/end{kind:error}; cancel replays a
  {kind:hang} → stopReason:cancelled.

Two input-DSL ops support these: promptExpectError (awaits the prompt, asserts
it rejects — the editor's view of a failed turn — and swallows it) and
promptAndCancel (dispatches the prompt unawaited, waits until the client
OBSERVES the streamed agent_message_chunk, then cancels — pinning frame order
so the cancel transcript is deterministic; fixes a flake Codex caught where the
late chunk and the cancelled response could interleave either way).

Scenarios carry a `recorded` flag so test:snapshot:record only re-runs the
live-API ones. reasoning/max-tokens scenarios are deferred (hard to force
deterministically from the live model). Per docs/rfc/implemented/2026-06-19.

2026-06-19 04:10:49 +08:00

acp-agent

test(acp-example): five snapshot scenarios + cancel/error input ops

2026-06-19 04:10:49 +08:00

coding-agent

Merge branch 'feat/acp-1-max-tokens-turn-end' into feat/acp-2-bridge

2026-06-16 23:40:23 +08:00

echo-agent

fix(session): synthesize tool results for interrupted tool calls on crash recovery (review #33 )

2026-06-16 23:50:52 +08:00

base.yml

feat(acp): ACP bridge — drive the coding agent from an editor over JSON-RPC stdio

2026-06-16 18:44:31 +08:00

README.md

feat: migrate to pnpm

2026-06-16 14:55:37 +08:00

README.md

Examples

Runnable demos (not workspaces) that showcase how the harness is wired.

echo-agent

A mock model + echo tool + stdio UI + JSONL persistence demo. Demonstrates:

Loading plugins from a cordis.yml via @cordisjs/plugin-loader + @cordisjs/plugin-include
Registering a mock LlmAdapter (streaming scripted responses)
Registering a tool via ctx.tools.register()
Persisting session events to JSONL via the session/event + session/flush pattern
A minimal stdio UI consuming agent/stream-chunk and session events

Run with: pnpm run demo:echo

When prompted, type "echo " to trigger a tool call round-trip.

coding-agent

The real thing: DeepSeek V4 + the bash tool suite + stdio chat + JSONL persistence, wired from cordis.yml. Where echo-agent proves the skeleton with mocks, this is a usable coding assistant.

Run with: pnpm run demo:coding (needs DEEPSEEK_API_KEY in the environment or a gitignored repo-root .env). See coding-agent/README.md for details.