mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
Merge remote-tracking branch 'origin/master' into codex/project-instruction-files
# Conflicts: # AGENTS.md # docs/config-catalog.md # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/core-data-structures/core.md # docs/event-producer-consumer.md # docs/persistence-catalog.md # docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md # docs/rfc/implemented/feature/2026-06-15-code-mode.md # docs/rfc/implemented/feature/2026-06-30-hook-bridges.md # docs/rfc/implemented/feature/2026-06-30-interception-seams.md # docs/rfc/implemented/feature/2026-07-08-repeat-tool-guard.md # docs/rfc/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md # examples/AGENTS.md # examples/acp-agent/cordis.yml # examples/acp-agent/tests/acp.snapshot.ts # examples/echo-agent/cordis.yml # examples/sandbox-acp-agent/cordis.yml # packages/cordis/tool-cordis/src/api-catalog.ts # packages/core/agent-core/README.md # packages/core/agent-core/src/index.ts # packages/core/agent-loop/README.md # packages/core/agent-loop/src/loop.ts # packages/core/agent-loop/tests/interception.spec.ts # packages/core/agent/src/types.ts # packages/core/tools/README.md # packages/core/tools/src/code-mode.ts # packages/core/tools/src/index.ts # packages/fs/fs-local/src/index.ts # packages/fs/fs/README.md # packages/fs/fs/src/index.ts # packages/guard/repeat-tool-guard/README.md # packages/guard/repeat-tool-guard/src/index.ts # packages/hooks/hooks-claude/src/index.ts # packages/hooks/hooks-codex/src/index.ts # packages/ui/acp-agent/src/index.ts
This commit is contained in:
Yichen Jiang
@@ -33,7 +33,7 @@ The id is wired through `cordis.yml` (`resumeSessionId: !!js process.env.RESUME_
|
||||
|
||||
## Code Mode
|
||||
|
||||
[`code-mode.cordis.yml`](code-mode.cordis.yml) is this same tree flipped to [Code Mode](../../docs/rfc/implemented/feature/2026-06-15-code-mode.md): an include overlay over `./cordis.yml` whose two patches insert the worker-thread code runtime (`@deepseek-ai/dsh-code-runtime-worker`, registering `ctx.codeRuntime`) and set `tools: { mode: code }` on the app. The registry contributes exactly one reserved wire transport — `run_code` — plus a generated TypeScript SDK section declaring the visible end-capability tools. The model composes those capabilities by writing a program; each program call carries an immutable link to its enclosing transport, bridges back through pre-policy, monotonic guards, around dispatch, post-policy, and final-result observation one at a time, and is logged as a `tool/code-dispatch` session event. Only what the program prints or returns re-enters model context. (Flip the mode to `both` to offer native calls and `run_code` side by side.)
|
||||
[`code-mode.cordis.yml`](code-mode.cordis.yml) overlays the same tree with the worker-thread runtime and `tools: { mode: code }`. The model receives one `run_code` transport plus a generated TypeScript SDK for the visible tools; only program output returns to model context. Use `mode: both` to expose native calls alongside `run_code`. See the [Code Mode RFC](../../docs/rfc/implemented/feature/2026-06-15-code-mode.md) for the execution contract.
|
||||
|
||||
```sh
|
||||
pnpm run demo:code-mode # this overlay under the REPL (default UI)
|
||||
|
||||
@@ -1,13 +1,8 @@
|
||||
# Code Mode overlay: the live coding-agent tree (./cordis.yml) with two
|
||||
# load-time patches — the app entry's config gains `tools: { mode: code }`
|
||||
# (the registry offers exactly one wire tool, run_code, plus the generated
|
||||
# TypeScript SDK prompt section declaring bash/read/write/edit/subagent/
|
||||
# todo_write) and the worker-thread code runtime joins the tree as
|
||||
# `ctx.codeRuntime`. The dsh-stdio-agent bin boots this file for
|
||||
# `pnpm run demo:code-mode` (the acp-agent example carries the same-shaped
|
||||
# overlay for the `acp` UI). A config patch REPLACES the entry's whole
|
||||
# config, so the base entry's fields are restated verbatim; only `tools`,
|
||||
# the welcome, and the persona's second paragraph are Code Mode deltas.
|
||||
# Code Mode adds `ctx.codeRuntime` and changes the registry to one wire tool,
|
||||
# `run_code`, plus a generated SDK for bash/read/write/edit/subagent/todo_write.
|
||||
# `demo:code-mode` selects this overlay; the ACP example has the same UI-specific
|
||||
# shape. A config patch replaces the whole app config, so unchanged base fields
|
||||
# are restated; only `tools`, `welcome`, and the persona's second paragraph differ.
|
||||
- id: base
|
||||
name: '@cordisjs/plugin-include'
|
||||
config:
|
||||
|
||||
@@ -1,15 +1,8 @@
|
||||
# The coding-agent plugin tree: the REPL agent demo. The two swappable
|
||||
# backends — the DeepSeek adapter and the local bash executor — plus `hmr` for
|
||||
# the dev/demo reload loop, then the stdio chat app (@deepseek-ai/dsh-stdio-
|
||||
# agent), which bundles the whole agent-core spine (timer, llm, sessions,
|
||||
# system-prompt, tools, agents, invariants, tool-bash, agent-loop), the console
|
||||
# logger, JSONL persistence, the readline UI, and a pre-created `main` agent.
|
||||
#
|
||||
# `hmr` is a leaf entry (not baked into dsh-stdio-agent): it is a Loader-only
|
||||
# dev plugin that needs `--expose-internals` — the `demo:repl` script passes
|
||||
# it. Requires DEEPSEEK_API_KEY (and optionally DEEPSEEK_BASE_URL) in the
|
||||
# environment — the dsh-stdio-agent bin loads the gitignored repo-root .env
|
||||
# first. cordis.yml reads them via the `!!js` tag.
|
||||
# REPL agent with swappable DeepSeek and local-bash backends. `dsh-stdio-agent`
|
||||
# supplies the agent-core spine, logging, JSONL persistence, readline UI, and `main` agent.
|
||||
# HMR remains a leaf because it requires Loader internals; `demo:repl` passes
|
||||
# `--expose-internals`. The app bin loads the gitignored root `.env`; this file
|
||||
# reads `DEEPSEEK_API_KEY` and optional `DEEPSEEK_BASE_URL` through `!!js`.
|
||||
|
||||
# Hot-module reload for the dev/demo loop (needs `node --expose-internals`).
|
||||
- id: hmr
|
||||
@@ -28,15 +21,13 @@
|
||||
- deepseek-v4-pro
|
||||
- deepseek-v4-flash
|
||||
|
||||
# Local bash executor for agent-core's tool-bash schema (one of several tool
|
||||
# stacks in this tree: filesystem, subagent, and todo_write load below).
|
||||
# Local executor for the app bundle's bash tool.
|
||||
- id: bash
|
||||
name: '@deepseek-ai/dsh-bash-local'
|
||||
config:
|
||||
timeoutMs: 60000
|
||||
|
||||
# The stdio chat app: the whole spine + front-door cluster, configured for a
|
||||
# REPL agent demo driving a pre-created `main` agent.
|
||||
# The app bundle pre-creates the REPL's `main` agent.
|
||||
- id: stdio-agent
|
||||
name: '@deepseek-ai/dsh-stdio-agent'
|
||||
config:
|
||||
@@ -48,20 +39,16 @@
|
||||
workspaceContext:
|
||||
maxBytes: 65536
|
||||
welcome: 'agent REPL ready. Give it a coding task.'
|
||||
# The persona: identity + behavior only, nothing about transports or
|
||||
# tooling — tool guidance lives with each tool plugin (descriptions +
|
||||
# prompt sections). {{model}} is the prompt variable the agent loop
|
||||
# resolves from this agent's configured model.
|
||||
# Keep the persona to identity and behavior; tool plugins own tool guidance.
|
||||
# The loop resolves {{model}} from this agent's configuration.
|
||||
persona: |
|
||||
You are coding-agent, a coding assistant powered by the {{model}} model.
|
||||
|
||||
Verify your work by running the code or tests. Keep answers brief and
|
||||
factual.
|
||||
|
||||
# Automatic context compaction: when the derived history approaches the model's
|
||||
# context window, summarize an older range into a checkpoint so a long-running
|
||||
# or tool-heavy session keeps fitting. A leaf entry (needs ctx.llm + the
|
||||
# agent-loop's `agent/pre-step` seam from the app above).
|
||||
# Summarize an older range when derived history approaches the context window.
|
||||
# This leaf consumes `ctx.llm` and the app's `agent/pre-step` seam.
|
||||
- id: compact-basic
|
||||
name: '@deepseek-ai/dsh-compact-basic'
|
||||
config:
|
||||
@@ -72,13 +59,9 @@
|
||||
maxTokens: 8192
|
||||
compactionRetries: 1
|
||||
|
||||
# The subagent seam + BOTH in-process backends + two model-facing tools, as leaf
|
||||
# entries after the app (which provides ctx.agents/ctx.tools). spawn (a fresh
|
||||
# child) and fork (a child seeded with the parent's completed-turn prefix) are
|
||||
# independent backends over the shared dsh-subagent-inprocess driver. Exposing
|
||||
# both transports is pure config: load each backend, then load dsh-tool-subagent
|
||||
# once per backend with a distinct toolName (the tool registry rejects a
|
||||
# duplicate name) — no code change.
|
||||
# Expose fresh-child `spawn` and completed-prefix `fork` through independent
|
||||
# in-process backends. Each tool instance needs a distinct `toolName`; the registry
|
||||
# rejects duplicates. These leaves follow the app because it provides `ctx.agents` and `ctx.tools`.
|
||||
- id: subagent
|
||||
name: '@deepseek-ai/dsh-subagent'
|
||||
|
||||
@@ -105,10 +88,8 @@
|
||||
toolName: subagent_fork
|
||||
|
||||
|
||||
# Dynamic workflows: the worker-thread engine (ctx.workflows) over the spawn
|
||||
# subagent backend above, plus the model-facing `workflow` tool. The model
|
||||
# writes a JavaScript orchestration script (meta + body); the engine runs it
|
||||
# in its own worker thread and fans agent() calls out as spawn children.
|
||||
# The worker-thread workflow engine fans a model-written JavaScript script's
|
||||
# `agent()` calls out through the spawn backend; the adjacent tool exposes it to the model.
|
||||
- id: workflow-workerthread
|
||||
name: '@deepseek-ai/dsh-workflow-workerthread'
|
||||
config:
|
||||
@@ -116,14 +97,12 @@
|
||||
|
||||
- id: tool-workflow
|
||||
name: '@deepseek-ai/dsh-tool-workflow'
|
||||
# The model-facing todo_write tool: whole-list task tracking written to the
|
||||
# session log (todo/write), rendered as a stdio checklist / ACP plan.
|
||||
# `todo_write` replaces the logged whole list and renders as a stdio checklist or ACP plan.
|
||||
- id: tool-todo
|
||||
name: '@deepseek-ai/dsh-tool-todo'
|
||||
|
||||
# Filesystem capability stack: local provider, read-before-write/edit policy
|
||||
# gate, then the model-facing read/write/edit tools. stdio-agent is a single
|
||||
# session, so relative paths resolve from the process cwd (the workspace).
|
||||
# Policy loads before the model-facing filesystem tools so writes and edits require
|
||||
# an observed file. This single-session app resolves relative paths from the process cwd.
|
||||
- id: fs-local
|
||||
name: '@deepseek-ai/dsh-fs-local'
|
||||
config:
|
||||
|
||||
@@ -6,17 +6,12 @@ import { fileURLToPath } from 'node:url'
|
||||
import { afterEach, describe, expect, it } from 'vitest'
|
||||
|
||||
/**
|
||||
* Keyless Loader-path smoke for the Code Mode overlay: boot the REAL
|
||||
* example through the `@deepseek-ai/dsh-stdio-agent` bin against
|
||||
* `code-mode.cordis.yml` (the cordis Loader, `unwrapExports`, the include
|
||||
* patches over ./cordis.yml, the worker-thread code runtime, and the
|
||||
* registry in `mode: code`), then close stdin with no prompt and assert
|
||||
* the Code Mode banner + a clean exit.
|
||||
*
|
||||
* No prompt is ever sent, so the model is NEVER called and no `run_code`
|
||||
* turn happens — a dummy key lets `llm-deepseek`'s key-PRESENT check boot
|
||||
* the tree. This is the export-shape guard (postmortem 0001) for the Code
|
||||
* Mode composition; the with-key proof lives in `code-mode.e2e.ts`.
|
||||
* Keyless Loader-path smoke for the Code Mode overlay: boot the real example through the
|
||||
* `@deepseek-ai/dsh-stdio-agent` bin against `code-mode.cordis.yml` (the cordis Loader,
|
||||
* `unwrapExports`, the include patches over ./cordis.yml, the worker-thread code runtime, and
|
||||
* the registry in `mode: code`), then close stdin with no prompt and assert the Code Mode
|
||||
* banner + a clean exit. A dummy key satisfies adapter boot, but no prompt means
|
||||
* no model call; the with-key proof lives in `code-mode.e2e.ts`.
|
||||
*/
|
||||
|
||||
const binScript = fileURLToPath(new URL('../../../packages/ui/stdio-agent/src/bin.ts', import.meta.url))
|
||||
@@ -26,10 +21,8 @@ const tsxLoader = fileURLToPath(import.meta.resolve('tsx'))
|
||||
// `paths` map; tsx searches UP from cwd, and we spawn from a temp dir outside
|
||||
// the repo, so point it at the repo tsconfig.
|
||||
const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
|
||||
// The real-API workflow runs up to 14 e2e files at once. Cold tsx/Loader
|
||||
// startup can therefore outlive a tight smoke-test deadline before the child
|
||||
// emits any output; 30s still detects a wedged process without confusing
|
||||
// bounded CI contention with a lifecycle failure.
|
||||
// Under parallel e2e load, cold tsx/Loader startup can exceed a tight deadline;
|
||||
// 30s still detects a wedged child.
|
||||
const PROCESS_TIMEOUT_MS = 30_000
|
||||
// Leave enough room for the process-owned timeout to report captured output
|
||||
// before Vitest aborts the test itself.
|
||||
|
||||
@@ -19,14 +19,9 @@ import * as ToolFs from '@deepseek-ai/dsh-tool-fs'
|
||||
import * as WorkspaceContext from '@deepseek-ai/dsh-workspace-context'
|
||||
|
||||
/**
|
||||
* The Code Mode with-key proof (the RFC's e2e tier): a REAL model under
|
||||
* `mode: 'code'`, a task that requires composing two tool calls, verified
|
||||
* against the WORLD — the persisted request header carried exactly
|
||||
* `[run_code]` as the wire tool list, each sub-call landed as a
|
||||
* `tool/code-dispatch` event, the file the program wrote exists on disk, and
|
||||
* the final answer is the program's curated output. Key-gated (see
|
||||
* vitest.e2e.config.ts); the keyless Loader-path smoke of the overlay lives
|
||||
* in `code-mode-keyless-smoke.e2e.ts`.
|
||||
* With-key Code Mode proof: a real model receives only `run_code`, composes two
|
||||
* sub-calls, writes a file, and returns curated output while the log records
|
||||
* each `tool/code-dispatch`. The keyless Loader smoke is in the sibling test.
|
||||
*/
|
||||
|
||||
const PERSONA = 'You are coding-agent. You work by writing TypeScript programs for run_code: '
|
||||
|
||||
@@ -7,25 +7,11 @@ import { AgentId } from '@deepseek-ai/dsh-agent'
|
||||
import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts'
|
||||
|
||||
/**
|
||||
* The compaction smoke test: a real model runs a multi-step bash task with a
|
||||
* deliberately tiny context window, so the auto-compaction listener fires
|
||||
* MID-SESSION and summarizes the older history into a checkpoint. This is the
|
||||
* first end-to-end exercise of the compaction seam (it is wired nowhere else),
|
||||
* and the runaway-survival regression net — it proves a session that grows past
|
||||
* the window keeps running rather than overflowing. Key-gated.
|
||||
*
|
||||
* Verifies the WORLD, not the agent's self-report: a compact/start…end pair
|
||||
* landed in the real session log, the surface actually shrank (a replace node
|
||||
* exists and shadowed older nodes), and the agent still produced a final answer
|
||||
* after compaction (so the summarized history did not break the conversation).
|
||||
*
|
||||
* FIXME(compaction-snapshot): this key-gated e2e is the ONLY coverage of runaway
|
||||
* compaction — there is no keyless full-transcript snapshot of it. dsh-llm-replay
|
||||
* reconstructs one model call per (turn, step) from `assistant/chunk` events, but
|
||||
* `summarize()` assembles its stream into a local BlockAssembler and appends no
|
||||
* `assistant/chunk`, so the interleaved summarization call is unreplayable. A
|
||||
* snapshot needs replay-harness work to serve that call; deferred as a follow-up.
|
||||
* Key-gated smoke for mid-session compaction. It verifies the compact event
|
||||
* pair, replacement of older surface nodes, and a final answer after compaction.
|
||||
*/
|
||||
// FIXME(compaction-snapshot): this is the only full compaction coverage because
|
||||
// replay cannot serve the summarizer's unlogged model call.
|
||||
|
||||
let workdir: string | undefined
|
||||
let ctx: Context | undefined
|
||||
@@ -40,18 +26,11 @@ afterEach(async () => {
|
||||
describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compacts mid-flight and keeps running', () => {
|
||||
it('summarizes older history into a checkpoint without breaking the task', async () => {
|
||||
workdir = await mkdtemp(join(tmpdir(), 'dsh-compaction-'))
|
||||
// A handful of files for the model to read, so multiple bash steps
|
||||
// accumulate surface nodes (tool calls + results) and grow the history past
|
||||
// the (deliberately tiny) window.
|
||||
for (let i = 1; i <= 4; i++) {
|
||||
await writeFile(join(workdir, `file${i}.txt`), `This is file number ${i}. `.repeat(50))
|
||||
}
|
||||
|
||||
// Tiny window so a couple of steps crosses the threshold. The generation
|
||||
// cap is deliberately larger than the final checkpoint because
|
||||
// reasoning-capable APIs count reasoning tokens against the provider output
|
||||
// budget even though those blocks are stripped before the checkpoint is
|
||||
// stored.
|
||||
// Reasoning tokens require a larger generation cap than the retained checkpoint.
|
||||
ctx = await codingHarness(workdir, {
|
||||
persona: SYSTEM_PROMPT,
|
||||
compact: {
|
||||
|
||||
@@ -6,42 +6,22 @@ import { fileURLToPath } from 'node:url'
|
||||
import { afterEach, describe, expect, it } from 'vitest'
|
||||
|
||||
/**
|
||||
* Keyless Loader-path smoke for examples/coding-agent: boot the REAL example
|
||||
* through the `@deepseek-ai/dsh-stdio-agent` bin against its `cordis.yml` (the
|
||||
* cordis Loader, `unwrapExports`, the full plugin tree incl. the
|
||||
* `@deepseek-ai/dsh-agent-core` bundle and the app's in-package readline UI
|
||||
* module), then close stdin with no prompt and assert the
|
||||
* ready banner + a clean exit.
|
||||
*
|
||||
* No prompt is ever sent, so the model is NEVER called — this is why it runs
|
||||
* without a real key. coding-agent's `cordis.yml` loads `llm-deepseek`, whose
|
||||
* `apply()` only requires a key to be PRESENT (it does not validate it and only
|
||||
* uses it when a stream actually starts), so a dummy key lets the tree boot
|
||||
* while the absence of any prompt guarantees no network call. The value is the
|
||||
* real-Loader-path guard that the composed tree boots (see postmortem 0001;
|
||||
* the app carries no `inject`, so its export SHAPE is pinned by the stdio-agent
|
||||
* unit suite's unwrap assertion, not by a crash here),
|
||||
* complementing coding-agent's with-key e2e suites which prove the real
|
||||
* product.
|
||||
* Boots the real example through the stdio bin and `cordis.yml`, covering Loader,
|
||||
* `unwrapExports`, the full plugin tree, the agent-core bundle, and the readline module.
|
||||
* A dummy key permits startup; closing stdin before a prompt prevents network calls,
|
||||
* while with-key suites cover product behavior.
|
||||
*/
|
||||
|
||||
// The dsh-stdio-agent bin (the demo:repl entry) and this example's cordis.yml.
|
||||
// The bin resolves its config-path arg from CWD; the test spawns from a temp
|
||||
// cwd, so we pass the example config's ABSOLUTE path.
|
||||
// TODO(loader-smoke-harness): share spawn/tempdir/timeout/EOF setup with the other keyless smoke tests.
|
||||
// The temp-cwd child needs absolute bin and config paths.
|
||||
const binScript = fileURLToPath(new URL('../../../packages/ui/stdio-agent/src/bin.ts', import.meta.url))
|
||||
const configPath = fileURLToPath(new URL('../cordis.yml', import.meta.url))
|
||||
const tsxLoader = fileURLToPath(import.meta.resolve('tsx'))
|
||||
// Dev/test run UNBUILT: resolve `@deepseek-ai/dsh-*` through the root tsconfig
|
||||
// `paths` map; tsx searches UP from cwd, and we spawn from a temp dir outside
|
||||
// the repo, so point it at the repo tsconfig (root is four levels up).
|
||||
// The temp cwd cannot discover the root tsconfig used for unbuilt package aliases.
|
||||
const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
|
||||
// The real-API workflow runs up to 14 e2e files at once. Cold tsx/Loader
|
||||
// startup can therefore outlive a tight smoke-test deadline before the child
|
||||
// emits any output; 30s still detects a wedged process without confusing
|
||||
// bounded CI contention with a lifecycle failure.
|
||||
// Allow cold Loader startup under parallel load while still detecting hangs.
|
||||
const PROCESS_TIMEOUT_MS = 30_000
|
||||
// Leave enough room for the process-owned timeout to report captured output
|
||||
// before Vitest aborts the test itself.
|
||||
// Let the child timeout report captured output before Vitest aborts.
|
||||
const TEST_TIMEOUT_MS = PROCESS_TIMEOUT_MS + 15_000
|
||||
|
||||
let child: ChildProcessWithoutNullStreams | undefined
|
||||
|
||||
Reference in New Issue
Block a user