Files
deepseek-harness/examples/cordis-agent
_Kerman 57d90c343d Merge remote-tracking branch 'origin/master' into xtr/agent-loop-message-machine
# Conflicts:
#	.agents/notes/implemented/feature/2026-06-14-acp-agent-client-protocol.md
#	.agents/notes/implemented/feature/2026-06-14-acp-agent-client-protocol.zh.md
#	.agents/notes/implemented/feature/2026-06-30-hook-bridges.i18n.yaml
#	.agents/notes/implemented/feature/2026-06-30-interception-seams.i18n.yaml
#	.agents/notes/implemented/feature/2026-07-06-sandbox.i18n.yaml
#	.agents/notes/implemented/feature/2026-07-06-sandbox.md
#	.agents/notes/implemented/feature/2026-07-06-sandbox.zh.md
#	.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml
#	.agents/notes/implemented/feature/2026-07-19-same-session-goal-round-driver.i18n.yaml
#	.agents/notes/implemented/feature/2026-07-25-workspace-ui-product-flow.i18n.yaml
#	.agents/notes/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.i18n.yaml
#	docs/architecture.i18n.yaml
#	docs/cookbook/adding-a-tool.i18n.yaml
#	docs/cookbook/extension-cookbook.i18n.yaml
#	docs/core-data-structures/llm-streaming.i18n.yaml
#	docs/core-data-structures/session.i18n.yaml
#	docs/core-data-structures/tools.i18n.yaml
#	docs/event-producer-consumer.md
#	docs/persistence-catalog.md
#	examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/stdout.expected.jsonl
#	examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl
#	examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl
#	examples/acp-agent/tests/snapshots/fs-escalation-approved/session.jsonl
#	examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl
#	examples/acp-agent/tests/snapshots/permission-switching/session.jsonl
#	examples/acp-agent/tests/snapshots/plan-mode-reject/session.jsonl
#	examples/acp-agent/tests/snapshots/plan-mode/session.jsonl
#	examples/acp-agent/tests/snapshots/session-sandbox-root/session.jsonl
#	packages/context/session-reference/README.md
#	packages/core/agent-loop/tests/agent.spec.ts
#	packages/hooks/hooks-claude/tests/coverage-cases.ts
#	packages/host/runtime/tests/host-runtime.spec.ts
#	packages/llm/llm-retry/tests/retry.spec.ts
#	packages/session-persistence/session-persistence/src/coordinator.ts
#	packages/support/acp-snapshot/README.md
#	packages/support/acp-snapshot/src/normalize.ts
#	packages/ui/acp/acp-feature-support.md
#	packages/ui/acp/src/codec.ts
#	packages/ui/acp/src/index.ts
#	packages/ui/acp/tests/bridge.spec.ts
#	packages/ui/acp/tests/codec.spec.ts
#	packages/ui/acp/tests/config-options.spec.ts
#	packages/ui/acp/tests/dispose.spec.ts
#	packages/ui/acp/tests/edges.spec.ts
#	packages/ui/acp/tests/stream-update.spec.ts
#	packages/ui/acp/tests/turns.spec.ts
2026-07-26 14:05:33 +08:00
..
2026-07-20 19:26:04 +08:00

cordis-agent

The self-referential harness demo: the DeepSeek V4 coding spine on the full-screen TUI plus @deepseek-ai/dsh-tool-cordis, which hands the model three tools over the live cordis runtime it is running inside — inspect it, mount new plugins into it, and dispose them again. The ctx.fs and ctx.web services are mounted (provider-only, no model-facing file/web tools) so the plugins the agent writes have real capabilities to build on; Node built-ins are trapped in the sandbox and redirect to those services. The design (sandbox semantics, mount lifecycle, cross-mount composition, caveats) lives in the toolset Agent Note.

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:cordis

The intended demo is staged — verify the listener link first, then let the agent extend itself:

> Mount a plugin that listens to the 'agent/status' event and logs every status change, then run `echo hi` with bash.
  [tool call] cordis_mount({"code": "return { name: 'status-logger', apply(ctx) { ctx.on('agent/status', (agent, status) => console.log('status →', status)) } }"})
  [tool result] mounted dyn-1 (plugin "status-logger", state: active)
  [tool call] bash({"command": "echo hi"})
[cordis:dyn-1] status → …            ← the mounted listener firing, live
> Now give yourself a reverse_text tool and use it on "harness".
  [tool call] cordis_mount({"code": "return { name: 'reverse-text', inject: ['tools'], apply(ctx) { ctx.tools.register(harness.defineTool({ name: 'reverse_text', … })) } }"})
  [tool call] reverse_text({"text": "harness"})   ← a tool the agent built for itself, one step earlier
> Unmount both.
  [tool call] cordis_unmount({"id": "dyn-1"})

Ask for cordis_inspect with what: "api" or what: "events" to see the generated service/event reference the agent writes plugin code against, and try two cooperating mounts (ctx.provide in one, inject in the other) to watch cordis park and revive the consumer.

End-to-end tests

tests/keyless-smoke.e2e.ts boots the real cordis.yml through the Loader with a dummy key and asserts the banner, package-name resolution, and clean EOF exit. tests/cordis-tools.e2e.ts is the with-key smoke: a real model mounts a status listener and the test verifies its tagged console line, creates and uses a reverse_text tool, and composes two mounts through provide/inject. packages/cordis/tool-cordis carries the unit coverage under the per-file 100% gate.