kevin/deepseek-harness
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/master' into codex/agent-session-jsonl-location

Browse Source 
# Conflicts:
#	docs/config-catalog.md
#	packages/hooks/hooks-codex/src/index.ts
#	packages/ui/acp-agent/src/index.ts
#	packages/ui/stdio-agent/src/index.ts
This commit is contained in:
Yichen Jiang
2026-07-14 09:51:50 +08:00
parent ba329b16ce a0359bc4a9
commit f570d2201e
145 changed files with 11502 additions and 583 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/build-exe-for-python-sdk.yml
+287
View File
@@ -0,0 +1,287 @@
name: Build single-exe
# Single-file executable (single-exe) builds of the DeepSeek Harness SDK
# runtime. The build pipeline and target platforms are specified in
# docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md:
# each target is built natively on a runner of its own platform (no
# cross-compilation) by scripts/build-exe-for-python-sdk.ts, which deploys
# the dsh-jsonrpc-agent-pkg closure manifest with @yao-pkg/pkg into
# dist-exe/.
#
# The run retains exactly the four wheels that make up one Python release:
# one platform-independent SDK wheel plus one native runtime wheel for each
# supported platform. The matrix still exercises the bare executable and
# source tree, but they are intermediate test inputs rather than artifacts.
#
# Two explicit triggers, deliberately no per-commit CI: the exe is a
# release-style deliverable, and the build (full pnpm build + pnpm deploy +
# pkg across a 3-platform matrix, ~100MB per artifact) is far too expensive
# to run on every push. Either dispatch it from the Actions tab, or put the
# `build-exe` label on a pull request to build that PR's merge result
# (remove and re-apply the label to rerun); any other label leaves the jobs
# skipped. There is no `ref` input on purpose: actions/checkout already
# checks out the ref the run was triggered on — the dispatched branch/tag,
# or the PR merge ref.
on:
workflow_dispatch:
inputs:
targets:
description: >-
Comma-separated pkg targets to build. Any subset of:
node24-linux-x64, node24-linux-arm64, node24-macos-arm64.
Empty builds all three.
type: string
required: false
default: ''
pull_request:
types: [labeled]
# Runs on the same ref supersede each other (per branch/tag for dispatch,
# per PR merge ref for label runs).
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
# Least privilege: the jobs only read the repo; artifact upload needs no
# extra scope.
permissions:
contents: read
jobs:
# Turn the `targets` input into the build matrix. The `matrix` context is
# not available in a job-level `if:` (jobs.<job_id>.if only sees
# github/needs/vars/inputs), so target selection happens here instead of
# skipping matrix legs; an unknown target name fails the whole run loudly
# instead of being silently ignored. The label gate lives here too: `build`
# needs this job, so skipping it skips the whole run.
plan:
name: plan targets
if: github.event_name == 'workflow_dispatch' || github.event.label.name == 'build-exe'
runs-on: ubuntu-latest
timeout-minutes: 5
outputs:
matrix: ${{ steps.plan.outputs.matrix }}
version: ${{ steps.version.outputs.version }}
steps:
- uses: actions/checkout@v6
- name: Resolve repository version
id: version
run: |
set -euo pipefail
version="$(jq -r '.version // empty' package.json)"
[[ "$version" =~ ^[0-9]+\.[0-9]+\.[0-9]+$ ]] || {
echo "::error::package.json version must be stable X.Y.Z, got '$version'"
exit 1
}
echo "version=$version" >> "$GITHUB_OUTPUT"
- name: Compute matrix from targets input
id: plan
env:
# Empty on label runs and on dispatch with the input left blank —
# both mean "all three targets".
TARGETS: ${{ inputs.targets || 'node24-linux-x64,node24-linux-arm64,node24-macos-arm64' }}
run: |
set -euo pipefail
matrix='[]'
IFS=',' read -r -a targets <<< "$TARGETS"
for raw in "${targets[@]}"; do
t="$(echo "$raw" | xargs)" # trim surrounding whitespace
[ -z "$t" ] && continue
# Native builds only — each target maps to a runner of its own
# platform: linux-arm64 uses GitHub's hosted arm64 label
# ubuntu-24.04-arm (there is no ubuntu-latest-arm), macos-arm64
# uses macos-latest (Apple Silicon since macos-14).
case "$t" in
node24-linux-x64) runner=ubuntu-latest ;;
node24-linux-arm64) runner=ubuntu-24.04-arm ;;
node24-macos-arm64) runner=macos-latest ;;
*)
echo "::error::Unknown target '$t'. Supported: node24-linux-x64, node24-linux-arm64, node24-macos-arm64."
exit 1
;;
esac
matrix="$(jq -c --arg target "$t" --arg runner "$runner" '. + [{target: $target, runner: $runner}]' <<< "$matrix")"
done
if [ "$matrix" = '[]' ]; then
echo "::error::The targets input selected nothing to build."
exit 1
fi
echo "Matrix: $matrix"
echo "matrix=$matrix" >> "$GITHUB_OUTPUT"
sdk-wheel:
needs: plan
name: deepseek_harness-${{ needs.plan.outputs.version }}-py3-none-any.whl
runs-on: ubuntu-latest
timeout-minutes: 5
steps:
- uses: actions/checkout@v6
- uses: actions/setup-python@v6
with:
python-version: '3.10'
- name: Install Python build tooling
run: python -m pip install uv==0.11.23
- name: Build release-shaped SDK wheel
run: >-
python scripts/build-python-release.py
--package sdk
--output-dir dist-python
- uses: actions/upload-artifact@v6
with:
name: deepseek_harness-${{ needs.plan.outputs.version }}-py3-none-any.whl
path: dist-python/deepseek_harness-${{ needs.plan.outputs.version }}-py3-none-any.whl
if-no-files-found: error
build:
needs: [plan, sdk-wheel]
name: ${{ matrix.target }}
runs-on: ${{ matrix.runner }}
timeout-minutes: 45
strategy:
fail-fast: false
matrix:
include: ${{ fromJSON(needs.plan.outputs.matrix) }}
steps:
- uses: actions/checkout@v6
- uses: actions/setup-node@v6
with:
node-version: 24
- uses: actions/setup-python@v6
with:
python-version: '3.10'
- name: Install Python build tooling
run: python -m pip install uv==0.11.23
- name: Enable corepack (pnpm)
run: corepack enable
- name: Resolve pnpm store path
id: pnpm-store
run: echo "path=$(pnpm store path --silent)" >> "$GITHUB_OUTPUT"
# Unlike ci.yml (x64-only), this matrix spans two Linux architectures
# that share runner.os, so runner.arch is part of the key.
- uses: actions/cache@v4
with:
path: ${{ steps.pnpm-store.outputs.path }}
key: ${{ runner.os }}-${{ runner.arch }}-node-24-pnpm-${{ hashFiles('pnpm-lock.yaml') }}
restore-keys: |
${{ runner.os }}-${{ runner.arch }}-node-24-pnpm-
# The first run per target has pkg-fetch download yao-pkg's patched
# Node binary into ~/.pkg-cache; cache it so later runs skip the
# download. The target string pins Node major + platform + arch;
# pnpm-lock.yaml rolls the key when @yao-pkg/pkg (and with it the
# pinned patched-binary version) is bumped, with restore-keys still
# seeding from the previous cache.
- uses: actions/cache@v4
with:
path: ~/.pkg-cache
key: pkg-fetch-${{ matrix.target }}-${{ hashFiles('pnpm-lock.yaml') }}
restore-keys: |
pkg-fetch-${{ matrix.target }}-
- name: Install (immutable)
run: pnpm install --frozen-lockfile
# The script runs the whole pipeline itself (pnpm run build → pnpm
# deploy --prod → pkg) and writes its output to dist-exe/ by default.
- name: Build single-exe
run: pnpm exec tsx scripts/build-exe-for-python-sdk.ts --targets=${{ matrix.target }}
- name: Resolve platform outputs
id: runtime
env:
TARGET: ${{ matrix.target }}
VERSION: ${{ needs.plan.outputs.version }}
run: |
set -euo pipefail
platform="${TARGET#node24-}"
exe="$PWD/dist-exe/dsh-jsonrpc-agent-pkg-$platform"
[ -x "$exe" ] || { echo "::error::$exe missing or not executable"; exit 1; }
case "$platform" in
linux-x64) wheel=deepseek_harness_runtime_bin-$VERSION-py3-none-manylinux_2_28_x86_64.whl ;;
linux-arm64) wheel=deepseek_harness_runtime_bin-$VERSION-py3-none-manylinux_2_28_aarch64.whl ;;
macos-arm64) wheel=deepseek_harness_runtime_bin-$VERSION-py3-none-macosx_11_0_arm64.whl ;;
*) echo "::error::Unsupported runtime platform $platform"; exit 1 ;;
esac
echo "platform=$platform" >> "$GITHUB_OUTPUT"
echo "exe=$exe" >> "$GITHUB_OUTPUT"
echo "wheel=$wheel" >> "$GITHUB_OUTPUT"
- name: Full-turn SDK, executable snapshot, and direct-binary smoke
run: >-
uv run --python 3.10 --group test --project python/sdk
python scripts/smoke-python-runtime.py
--scenario all
--exe "${{ steps.runtime.outputs.exe }}"
- name: Build release-shaped runtime wheel
run: >-
python scripts/build-python-release.py
--package runtime
--platform "${{ steps.runtime.outputs.platform }}"
--runtime-exe "${{ steps.runtime.outputs.exe }}"
--output-dir dist-python
- uses: actions/download-artifact@v8
with:
name: deepseek_harness-${{ needs.plan.outputs.version }}-py3-none-any.whl
path: dist-python
- name: Install only the SDK into a clean venv and run zero-config
env:
VERSION: ${{ needs.plan.outputs.version }}
run: |
set -euo pipefail
python -m venv "$RUNNER_TEMP/dsh-sdk-smoke"
"$RUNNER_TEMP/dsh-sdk-smoke/bin/python" -m pip install \
--find-links dist-python \
deepseek-harness=="$VERSION"
"$RUNNER_TEMP/dsh-sdk-smoke/bin/python" scripts/smoke-python-runtime.py \
--scenario sdk-default
- name: Check Linux GLIBC requirements
if: runner.os == 'Linux'
run: |
set -euo pipefail
readelf --version-info "${{ steps.runtime.outputs.exe }}" | tee glibc-versions.txt
maximum="$(sed -n 's/.*Name: GLIBC_\([0-9.]*\).*/\1/p' glibc-versions.txt | sort -V | tail -1)"
[ -n "$maximum" ] || { echo "::error::No GLIBC requirements found"; exit 1; }
dpkg --compare-versions "$maximum" le 2.28 || {
echo "::error::Executable requires GLIBC_$maximum but wheel claims manylinux_2_28"
exit 1
}
- name: Run wheel in a manylinux 2.28 container
if: runner.os == 'Linux'
env:
RUNNER_ARCH: ${{ runner.arch }}
VERSION: ${{ needs.plan.outputs.version }}
run: |
set -euo pipefail
case "$RUNNER_ARCH" in
X64) image=quay.io/pypa/manylinux_2_28_x86_64 ;;
ARM64) image=quay.io/pypa/manylinux_2_28_aarch64 ;;
*) echo "::error::Unsupported Linux runner architecture $RUNNER_ARCH"; exit 1 ;;
esac
docker run --rm -e VERSION -v "$PWD:/work" -w /work "$image" bash -euxo pipefail -c '
/opt/python/cp310-cp310/bin/python -m venv /tmp/dsh-sdk
/tmp/dsh-sdk/bin/python -m pip install --find-links /work/dist-python deepseek-harness=="$VERSION"
/tmp/dsh-sdk/bin/python /work/scripts/smoke-python-runtime.py --scenario sdk-default
'
- uses: actions/upload-artifact@v6
with:
name: ${{ steps.runtime.outputs.wheel }}
path: dist-python/${{ steps.runtime.outputs.wheel }}
if-no-files-found: error
.github/workflows/ci.yml
+18 -1
View File
@@ -143,6 +143,23 @@ jobs:
- name: Run compatibility gates
run: pnpm run check:node-compat
python-sdk:
runs-on: ubuntu-latest
name: python 3.10 / keyless SDK
steps:
- uses: actions/checkout@v6
- uses: actions/setup-python@v6
with:
python-version: '3.10'
cache: pip
- name: Install uv
run: python -m pip install uv==0.11.23
- name: Run complete keyless Python suite
run: uv run --python 3.10 --group test --project python/sdk pytest
# Single stable required check for branch protection: require "all checks
# passed" instead of enumerating matrix legs whose names change as lanes and
# node versions evolve. Every other job in THIS workflow must be listed in
@@ -154,7 +171,7 @@ jobs:
all-checks-passed:
name: all checks passed
runs-on: ubuntu-latest
needs: [node-24, node-compat]
needs: [node-24, node-compat, python-sdk]
if: always()
steps:
- name: Fail if any needed job did not succeed
.gitignore
+5
View File
@@ -19,3 +19,8 @@ tmp/
.DS_Store
.idea
mise.toml
dist-exe/
python/sdk-runtime/src/deepseek_harness_runtime/runtime/dsh-jsonrpc-agent-*
python/sdk-runtime/src/deepseek_harness_runtime/runtime/node/
python/**/__pycache__/
python/**/.pytest_cache/
.gitlab-ci.yml
+123
View File
@@ -0,0 +1,123 @@
workflow:
rules:
- if: '$CI_COMMIT_TAG =~ /^python-v\d+\.\d+\.\d+$/'
- when: never
stages:
- build
- publish
variables:
GIT_DEPTH: "0"
PIP_DISABLE_PIP_VERSION_CHECK: "1"
.python-tools:
before_script:
- python3 -m venv .ci-python
- . .ci-python/bin/activate
- export DSH_VERSION="$(python -c 'import json; print(json.load(open("package.json"))["version"])')"
- test "$CI_COMMIT_TAG" = "python-v$DSH_VERSION" || { echo "Tag $CI_COMMIT_TAG does not match package.json version $DSH_VERSION"; exit 1; }
- python -m pip install uv==0.11.23
sdk-wheel:
extends: .python-tools
stage: build
tags: [linux-x64]
script:
- python scripts/build-python-release.py --package sdk --tag "$CI_COMMIT_TAG" --output-dir release/sdk
artifacts:
paths: [release/sdk/*.whl]
expire_in: 1 week
.runtime-wheel:
extends: .python-tools
stage: build
script:
- corepack enable
- pnpm install --frozen-lockfile
- pnpm run verify-runtime-closure
- pnpm exec tsx scripts/build-exe-for-python-sdk.ts --targets="$PKG_TARGET"
- EXE="$PWD/dist-exe/dsh-jsonrpc-agent-pkg-$PLATFORM"
- test -x "$EXE"
- uv run --python 3.10 --group test --project python/sdk python scripts/smoke-python-runtime.py --scenario all --exe "$EXE"
- python scripts/build-python-release.py --package runtime --tag "$CI_COMMIT_TAG" --platform "$PLATFORM" --runtime-exe "$EXE" --output-dir "release/$PLATFORM"
- python -m venv .wheel-smoke
- .wheel-smoke/bin/python -m pip install --find-links "release/$PLATFORM" --find-links release/sdk deepseek-harness=="$DSH_VERSION"
- .wheel-smoke/bin/python scripts/smoke-python-runtime.py --scenario sdk-default
- |
if [ "${PLATFORM#linux-}" != "$PLATFORM" ]; then
readelf --version-info "$EXE" > glibc-versions.txt
maximum="$(sed -n 's/.*Name: GLIBC_\([0-9.]*\).*/\1/p' glibc-versions.txt | sort -V | tail -1)"
test -n "$maximum"
dpkg --compare-versions "$maximum" le 2.28
case "$PLATFORM" in
linux-x64) image=quay.io/pypa/manylinux_2_28_x86_64 ;;
linux-arm64) image=quay.io/pypa/manylinux_2_28_aarch64 ;;
*) echo "Unsupported Linux platform $PLATFORM"; exit 1 ;;
esac
docker run --rm -v "$PWD:/work" -w /work "$image" bash -euxo pipefail -c "/opt/python/cp310-cp310/bin/python -m venv /tmp/dsh-sdk && /tmp/dsh-sdk/bin/python -m pip install --find-links /work/release/$PLATFORM --find-links /work/release/sdk deepseek-harness==$DSH_VERSION && /tmp/dsh-sdk/bin/python /work/scripts/smoke-python-runtime.py --scenario sdk-default"
fi
artifacts:
paths: [release/$PLATFORM/*.whl]
expire_in: 1 week
runtime-linux-x64:
extends: .runtime-wheel
tags: [linux-x64]
variables:
PKG_TARGET: node24-linux-x64
PLATFORM: linux-x64
needs:
- job: sdk-wheel
artifacts: true
runtime-linux-arm64:
extends: .runtime-wheel
tags: [linux-arm64]
variables:
PKG_TARGET: node24-linux-arm64
PLATFORM: linux-arm64
needs:
- job: sdk-wheel
artifacts: true
runtime-macos-arm64:
extends: .runtime-wheel
tags: [macos-arm64]
variables:
PKG_TARGET: node24-macos-arm64
PLATFORM: macos-arm64
needs:
- job: sdk-wheel
artifacts: true
publish-python:
stage: publish
tags: [linux-x64]
resource_group: python-release
needs:
- job: sdk-wheel
artifacts: true
- job: runtime-linux-x64
artifacts: true
- job: runtime-linux-arm64
artifacts: true
- job: runtime-macos-arm64
artifacts: true
before_script:
- python3 -m venv .ci-python
- . .ci-python/bin/activate
- export DSH_VERSION="$(python -c 'import json; print(json.load(open("package.json"))["version"])')"
- test "$CI_COMMIT_TAG" = "python-v$DSH_VERSION" || { echo "Tag $CI_COMMIT_TAG does not match package.json version $DSH_VERSION"; exit 1; }
- python -m pip install twine==6.2.0
script:
- test "$(find release -name '*.whl' | wc -l | tr -d ' ')" = 4
- test -f "release/sdk/deepseek_harness-${DSH_VERSION}-py3-none-any.whl"
- test -f "release/linux-x64/deepseek_harness_runtime_bin-${DSH_VERSION}-py3-none-manylinux_2_28_x86_64.whl"
- test -f "release/linux-arm64/deepseek_harness_runtime_bin-${DSH_VERSION}-py3-none-manylinux_2_28_aarch64.whl"
- test -f "release/macos-arm64/deepseek_harness_runtime_bin-${DSH_VERSION}-py3-none-macosx_11_0_arm64.whl"
- python -m twine check release/*/*.whl
- export TWINE_USERNAME=gitlab-ci-token
- export TWINE_PASSWORD="$CI_JOB_TOKEN"
- export TWINE_REPOSITORY_URL="$CI_API_V4_URL/projects/$CI_PROJECT_ID/packages/pypi"
- python -m twine upload --non-interactive release/*/*.whl || { echo 'Publish failed. GitLab does not overwrite an existing version; create a new python-vX.Y.Z tag.'; exit 1; }
.jscpd.json
+15
View File
@@ -0,0 +1,15 @@
{
"minTokens": 60,
"minLines": 6,
"mode": "mild",
"format": ["typescript"],
"pattern": "**/*.ts",
"ignore": ["**/tests/**", "**/tsdown.config.ts"],
"ignorePattern": [
"(?s)/\\* jscpd:ignore-start \\*/.*?/\\* jscpd:ignore-end \\*/"
],
"reporters": ["console"],
"exitCode": 1,
"noColors": true,
"noTips": true
}
AGENTS.md
+3 -1
View File
@@ -25,7 +25,7 @@ packages/ Harness packages at packages/<group>/<pkg>/, all named @deepseek-ai
cordis/ self-referential toolset: the agent inspects/mounts plugins in its own runtime
hooks/ Claude Code / Codex hook bridges + shared wire-protocol library
session-persistence/ persistence seam + JSONL/SQLite backends
ui/ ACP bridge, app-boot glue, stdio/ACP app bins, user-approval and user-interaction seams, ask-user tool
ui/ ACP bridge, JSON-RPC SDK server, app-boot glue, stdio/ACP/SDK app bins, user-approval and user-interaction seams, ask-user tool
support/ dev/test infrastructure packages
util/ zero-dependency utilities
examples/ Runnable demos: thin cordis.yml leaves over the app packages (see examples/AGENTS.md)
@@ -46,6 +46,7 @@ pnpm run test:snapshot # keyless ACP replay vs goldens; filter: -t <name>
pnpm run test:snapshot:record # re-record goldens (needs key)
pnpm run typecheck
pnpm run lint
pnpm run duplication # cross-file TypeScript clone detection
pnpm run build # tsc emits lib/types, tsdown bundles runtime
pnpm run hygiene # knip + publint + workspace constraints + NodeNext consumer check
pnpm run doc-sync # all documentation gates; see the doc-sync script in package.json
@@ -63,6 +64,7 @@ During implementation, run the narrowest affected checks; run this full CI-equiv
set -euo pipefail
pnpm run typecheck
pnpm run lint
pnpm run duplication
pnpm run test:coverage
pnpm run test:snapshot
pnpm run doc-sync
docs/config-catalog.md
+41 -4
View File
@@ -31,7 +31,7 @@ export interface AcpConfig {
Depends on: `Stream` (`@agentclientprotocol/sdk`)
Source: [`packages/ui/acp/src/index.ts:248`](../packages/ui/acp/src/index.ts)
Source: [`packages/ui/acp/src/index.ts:250`](../packages/ui/acp/src/index.ts)
## `@deepseek-ai/dsh-acp-agent`
@@ -217,7 +217,7 @@ export interface Config {
}
```
Source: [`packages/code-runtime/code-runtime-worker/src/index.ts:29`](../packages/code-runtime/code-runtime-worker/src/index.ts)
Source: [`packages/code-runtime/code-runtime-worker/src/index.ts:30`](../packages/code-runtime/code-runtime-worker/src/index.ts)
## `@deepseek-ai/dsh-compact-basic`
@@ -331,7 +331,43 @@ export interface Config {
}
```
Source: [`packages/hooks/hooks-codex/src/index.ts:44`](../packages/hooks/hooks-codex/src/index.ts)
Source: [`packages/hooks/hooks-codex/src/index.ts:48`](../packages/hooks/hooks-codex/src/index.ts)
## `@deepseek-ai/dsh-jsonrpc`
Requires: `agents`
```ts config-catalog
/**
* Plugin config. Every field is a runtime-only test seam — none is part of the
* schemastery {@link Config}, so nothing here is settable from a `cordis.yml`
* (production always serves the process stdio and exits via `process.exit`).
*/
export interface JsonRpcConfig {
/**
* Transport input override. Production omits this (the plugin reads
* `process.stdin`); tests inject an in-memory `Readable` to drive the server
* without a subprocess.
*/
input?: Readable
/**
* Transport output override. Production omits this (the plugin writes
* `process.stdout` — the protocol channel); tests inject an in-memory
* `Writable` to capture frames.
*/
output?: Writable
/**
* Process-exit override for the `shutdown` request path. Production omits
* this (`process.exit`); tests inject a recorder so a driven shutdown does
* not kill the test process.
*/
exit?: (code: number) => void
}
```
Depends on: `Readable` (`node:stream`) · `Writable` (`node:stream`)
Source: [`packages/ui/jsonrpc/src/index.ts:55`](../packages/ui/jsonrpc/src/index.ts)
## `@deepseek-ai/dsh-llm-deepseek`
@@ -784,7 +820,7 @@ export interface Config {
}
```
Source: [`packages/core/system-prompt/src/index.ts:225`](../packages/core/system-prompt/src/index.ts)
Source: [`packages/core/system-prompt/src/index.ts:227`](../packages/core/system-prompt/src/index.ts)
## `@deepseek-ai/dsh-tool-bash`
@@ -1189,6 +1225,7 @@ Imported as libraries by other packages; a `cordis.yml` cannot load them.
- `@deepseek-ai/dsh-brand` ([`packages/util/brand/src/index.ts`](../packages/util/brand/src/index.ts))
- `@deepseek-ai/dsh-home` ([`packages/util/home/src/index.ts`](../packages/util/home/src/index.ts))
- `@deepseek-ai/dsh-hook-protocol` ([`packages/hooks/hook-protocol/src/index.ts`](../packages/hooks/hook-protocol/src/index.ts))
- `@deepseek-ai/dsh-jsonrpc-agent` ([`packages/ui/jsonrpc-agent/src/index.ts`](../packages/ui/jsonrpc-agent/src/index.ts))
- `@deepseek-ai/dsh-scope` ([`packages/core/scope/src/index.ts`](../packages/core/scope/src/index.ts))
- `@deepseek-ai/dsh-subagent-inprocess` ([`packages/subagent/subagent-inprocess/src/index.ts`](../packages/subagent/subagent-inprocess/src/index.ts))
- `@deepseek-ai/dsh-subagent-subprocess` ([`packages/subagent/subagent-subprocess/src/index.ts`](../packages/subagent/subagent-subprocess/src/index.ts))
docs/cookbook/adding-a-package.md
+1 -1
View File
@@ -18,7 +18,7 @@ packages/<group>/<pkg>/
Choose an existing group when one matches the package's role (`core`, `llm`, `bash`, `compact`, `subagent`, `todo`, `session-persistence`, `ui`, `util`, or `support`). A new group is allowed, but it is a pure container: no `package.json`, no source files, and packages still sit exactly one level below it.
package.json invariants (enforced by `pnpm run constraints` / `scripts/check-workspace-constraints.ts`): `private: true`, `version: 0.0.1`, `type: module`, `main: "lib/index.js"`, `types: "lib/types/index.d.ts"`, `exports["."].types: "./lib/types/index.d.ts"`, `exports["."].default: "./lib/index.js"`, `cordis` in BOTH peerDependencies and devDependencies (same range). Mirror every dsh peer dependency in devDependencies. `schemastery` goes in `dependencies` (it is a runtime validator), matching agent-loop. The `files` list is precise: `lib/index.js`, `lib/types/**/*.d.ts`, `lib/types/**/*.d.ts.map`, and `src`; do not publish `lib/types` JS or JS-map intermediates or stale root declaration files. CLI app packages with a package `bin` include `lib/bin.js` immediately after `lib/index.js` in `files`.
package.json invariants (enforced by `pnpm run constraints` / `scripts/check-workspace-constraints.ts`): `private: true`, a `version` matching the root `package.json`, `type: module`, `main: "lib/index.js"`, `types: "lib/types/index.d.ts"`, `exports["."].types: "./lib/types/index.d.ts"`, `exports["."].default: "./lib/index.js"`, `cordis` in BOTH peerDependencies and devDependencies (same range). Mirror every dsh peer dependency in devDependencies. `schemastery` goes in `dependencies` (it is a runtime validator), matching agent-loop. The `files` list is precise: `lib/index.js`, `lib/types/**/*.d.ts`, `lib/types/**/*.d.ts.map`, and `src`; do not publish `lib/types` JS or JS-map intermediates or stale root declaration files. CLI app packages with a package `bin` include `lib/bin.js` immediately after `lib/index.js` in `files`.
In-package relative imports use explicit `.ts` specifiers in source (for example, `export * from './types.ts'`). The compiler rewrites those to `.js` in emitted JS and leaves explicit `.ts` specifiers in declarations, which standard NodeNext/Node16 TypeScript consumers resolve to the sibling `.d.ts` files.
docs/cordis-catalog/services.md
+1 -1
View File
@@ -272,7 +272,7 @@ variable(name: string, provider: (context: AssembleContext) => string | undefine
async assemble(context: AssembleContext = {}): Promise<PromptAssembly>
```
Source: [`packages/core/system-prompt/src/index.ts:340`](../../packages/core/system-prompt/src/index.ts)
Source: [`packages/core/system-prompt/src/index.ts:342`](../../packages/core/system-prompt/src/index.ts)
## `ctx.tools` — `ToolRegistry`
docs/event-producer-consumer.md
+4 -4
View File
@@ -7,7 +7,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac
| Event | Mode | Declared in | Dispatchers | Listeners |
| --- | --- | --- | --- | --- |
| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:316`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) |
| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:316`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) |
| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:331`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) |
| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:605`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - |
| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:438`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) |
@@ -25,13 +25,13 @@ This matrix shows which packages dispatch each harness-owned event and which pac
| `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:138`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) |
| `fs/write-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:109`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) |
| `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:39`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`invariants`](../packages/support/invariants), [`llm-replay`](../packages/support/llm-replay) |
| `session/created` | `emit` | [`packages/core/session/src/index.ts:52`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`invariants`](../packages/support/invariants), [`session-persistence`](../packages/session-persistence/session-persistence) |
| `session/created` | `emit` | [`packages/core/session/src/index.ts:52`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence) |
| `session/disposed` | `emit` | [`packages/core/session/src/index.ts:64`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | - |
| `session/event` | `emit` | [`packages/core/session/src/index.ts:83`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio-agent`](../packages/ui/stdio-agent) |
| `session/event` | `emit` | [`packages/core/session/src/index.ts:83`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio-agent`](../packages/ui/stdio-agent) |
| `session/flush` | `parallel` | [`packages/core/session/src/index.ts:101`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) |
| `skill/provider-added` | `emit` | [`packages/skill/skill/src/index.ts:131`](../packages/skill/skill/src/index.ts) | [`skill`](../packages/skill/skill) (`emit`) | - |
| `skill/provider-removed` | `emit` | [`packages/skill/skill/src/index.ts:137`](../packages/skill/skill/src/index.ts) | [`skill`](../packages/skill/skill) (`emit`) | - |
| `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:90`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude) |
| `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:90`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) |
| `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:66`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) |
| `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:72`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`tool-subagent`](../packages/subagent/tool-subagent) |
| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:82`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude) |
docs/i18n/README.i18n.yaml
+2 -2
View File
@@ -2,5 +2,5 @@
# side as of the last confirmed-consistent state. Both languages carry equal authority;
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write
README.md: 6e2bbd27c3288037bafeb6cc71b801d56b956ab4
README.zh.md: 04c99ae336cf1e96cbc185f0ccbd063ef8977944
README.md: 81e958c8ae9552222f27b0f9674d4fa0ff2a481c
README.zh.md: 3764a9ade69f3ad99e36ccccbaed1d19d8bbb1f0
docs/i18n/README.md
+1 -1
View File
@@ -35,7 +35,7 @@ The gate's limit, stated plainly: **a green gate means the pair was confirmed co
## Scope, exclusions, and rollout
**Scope**: the root `README.md` and everything under `docs/**`. Package READMEs (`packages/**`) join the scope in a later batch.
**Scope**: the root `README.md`, everything under `docs/**`, and everything under `python/**`. Package READMEs (`packages/**`) join the scope in a later batch.
**Excluded** (never paired, and the gate rejects a `.zh.md` or `.i18n.yaml` for them):
docs/i18n/README.zh.md
+1 -1
View File
@@ -35,7 +35,7 @@
## 范围、排除与推进
**范围**：根 `README.md` 与 `docs/**` 下的全部内容。package README（`packages/**`）在后续批次加入范围。
**范围**：根 `README.md`、`docs/**` 下的全部内容，以及 `python/**` 下的全部内容。package README（`packages/**`）在后续批次加入范围。
**排除**（永不配对，门禁拒绝为它们建 `.zh.md` 或 `.i18n.yaml`）：
docs/i18n/terminology.md
+7
View File
@@ -22,6 +22,7 @@
| RAG | RAG | 首次出现可写：检索增强生成（RAG） |
| SDK | SDK | |
| SSE | SSE | 首次出现可写：SSE（Server-Sent Events） |
| VFS | VFS | 首次出现写：虚拟文件系统（VFS） |
| agent | agent | 首次出现可写：agent（智能体） |
| agent loop | agent loop | |
| backlog | backlog | 双语翻译语境指待翻清单 |
@@ -52,6 +53,7 @@
| block | 块 | |
| background task | 后台任务 | |
| backend | 后端 | |
| build target | 构建目标 | |
| capability | 能力 | |
| cancel | 取消 | |
| checkpoint | 检查点 | |
@@ -66,6 +68,7 @@
| coverage | 覆盖率 | |
| crash recovery | 崩溃恢复 | |
| dispose | dispose | 首次出现可写：dispose（释放资源）；正文优先保留英文 |
| deploy root | 部署根目录 | |
| durability | 持久性 | |
| enforcement frontier | 强制边界 | i18n 机制词：manifest `required` 清单所划的门禁生效范围 |
| event log | 事件日志 | |
@@ -95,6 +98,7 @@
| module | 模块 | |
| orphan | 孤立 | git 官方中文同译（如「孤立分支」）；指英文源已不存在的 `.zh.md`；不要译作：孤儿 |
| pairing | 配对 | |
| peer dependency | 对等依赖 | 首次出现写：对等依赖（peer dependency） |
| permission | 权限 | |
| persistence | 持久化 | |
| pipeline | 流水线 | |
@@ -110,6 +114,7 @@
| runtime | 运行时 | |
| sandbox | 沙箱 | |
| service | 服务 | |
| serving surface | 对外服务接口 | |
| session | 会话 | |
| session event | 会话事件 | |
| smoke test | 冒烟测试 | |
@@ -133,4 +138,6 @@
| turn | 轮次 | |
| typecheck | 类型检查 | |
| vocabulary | 词汇 | |
| wheel | wheel 包 | |
| workflow | 工作流 | |
| wrapper | 包装层 | |
docs/module-graph.md
+9
View File
@@ -93,6 +93,8 @@ flowchart TD
pkg_acp["acp"]
pkg_acp_agent["acp-agent"]
pkg_app_boot["app-boot"]
pkg_jsonrpc["jsonrpc"]
pkg_jsonrpc_agent["jsonrpc-agent"]
pkg_stdio_agent["stdio-agent"]
pkg_tool_ask_user["tool-ask-user"]
pkg_user_approval["user-approval"]
@@ -291,6 +293,11 @@ flowchart TD
pkg_subagent_mock --> pkg_agent
pkg_subagent_mock --> pkg_llm
pkg_subagent_mock --> pkg_subagent
pkg_jsonrpc --> pkg_agent
pkg_jsonrpc --> pkg_llm
pkg_jsonrpc --> pkg_llm_deepseek
pkg_jsonrpc --> pkg_session
pkg_jsonrpc --> pkg_subagent
pkg_workflow_workerthread --> pkg_agent
pkg_workflow_workerthread --> pkg_brand
pkg_workflow_workerthread --> pkg_llm
@@ -331,6 +338,7 @@ flowchart TD
| [`subagent-subprocess`](../packages/subagent/subagent-subprocess) | `subagent` | — |
| [`acp-snapshot`](../packages/support/acp-snapshot) | `support` | — |
| [`app-boot`](../packages/ui/app-boot) | `ui` | — |
| [`jsonrpc-agent`](../packages/ui/jsonrpc-agent) | `ui` | — |
| [`code-runtime`](../packages/code-runtime/code-runtime) | `code-runtime` | — |
| [`llm`](../packages/llm/llm) | `llm` | [`brand`](../packages/util/brand) |
| [`code-runtime-worker`](../packages/code-runtime/code-runtime-worker) | `code-runtime` | [`code-runtime`](../packages/code-runtime/code-runtime) |
@@ -385,6 +393,7 @@ flowchart TD
| [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) |
| [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) |
| [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent) |
| [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) |
| [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) |
| [`subagent-fork`](../packages/subagent/subagent-fork) | `subagent` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) |
| [`subagent-spawn`](../packages/subagent/subagent-spawn) | `subagent` | [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) |
docs/rfc/INDEX.md
+9 -1
View File
@@ -10,13 +10,18 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand;
|---|---|
| [Pre-tool input rewrite — a consistent design](proposed/feature/2026-06-30-pre-tool-input-rewrite.md) | 2026-06-30 |
| [Claude Code and Codex subagent backends (out-of-process delegation to external coding agents)](proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md) | 2026-07-07 |
| [Interactive side sessions and merge-back](proposed/feature/2026-07-08-interactive-side-sessions.md) | 2026-07-08 |
| [Stream workflow progress through tool calls](proposed/feature/2026-07-13-stream-workflow-progress-through-tool-calls.md) | 2026-07-13 |
### Simplification
| Title | First proposed |
|---|---|
| [Unify the agent id and the session id](proposed/simplification/2026-06-20-unify-agent-and-session-id.md) | 2026-06-20 |
| [Prune dead core-spine surface — `SurfaceManager.invalidate()`, the loop-internal exports, `ToolExecutionResult.callId`](proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md) | 2026-07-04 |
| [Prune dead public and result surface](proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md) | 2026-07-04 |
| [Drop unconsumed skill provider events](proposed/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md) | 2026-07-12 |
| [Prune unused web seam fields](proposed/simplification/2026-07-12-prune-unused-web-seam-fields.md) | 2026-07-12 |
| [Simplify session-log representation](proposed/simplification/2026-07-12-simplify-session-log-representation.md) | 2026-07-12 |
### Architecture
@@ -135,6 +140,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand;
| [A shared timeout/deadline primitive, with hard-kill left to each capability](implemented/architecture/2026-07-06-timeout-deadline-library.md) | 2026-07-06 |
| [Tool-call timeout policy as a plugin](implemented/architecture/2026-07-07-tool-call-timeout-policy.md) | 2026-07-07 |
| [The agent is a registration scope](implemented/architecture/2026-07-08-agent-scope-contexts.md) | 2026-07-08 |
| [Single-file executable SDK runtime distribution (single-exe)](implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md) | 2026-07-10 |
| [Agent-scope runtime design and correctness](implemented/architecture/2026-07-12-agent-scope-runtime-design.md) | 2026-07-12 |
### Process
@@ -199,6 +205,8 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand;
| [Return the ACP bridge to one live session per connection](rejected/simplification/2026-06-20-single-session-acp-bridge.md) | 2026-06-20 |
| [Truncate interrupted final turns on load](rejected/simplification/2026-06-20-truncate-interrupted-turns.md) | 2026-06-20 |
| [Prune the unimplemented subagent seam vocabulary](rejected/simplification/2026-07-04-prune-unimplemented-subagent-vocabulary.md) | 2026-07-04 |
| [Collapse workflows to the exercised foreground core](rejected/simplification/2026-07-12-collapse-workflow-to-foreground-core.md) | 2026-07-12 |
| [Prune unused skill registry surface](rejected/simplification/2026-07-12-prune-unused-skill-registry-surface.md) | 2026-07-12 |
### Architecture
docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.i18n.yaml
+6
View File
@@ -0,0 +1,6 @@
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
# side as of the last confirmed-consistent state. Both languages carry equal authority;
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write
2026-07-10-single-file-executable-sdk-runtime-distribution.md: 4170d9f63773ef998bc5393fabc98a2b9fcba2fa
2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md: 7d80fb572ea36010df4829121fabe8cf66944f6b
docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md
+85
View File
@@ -0,0 +1,85 @@
# RFC: Single-file executable SDK runtime distribution (single-exe)
Status: implemented
English | [中文](2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md)
## Problem
DeepSeek Harness needs a dedicated SDK distribution form for the Python library — no Node installation, runs directly on the target platform: a single-file executable (hereafter "the exe") that exposes a stdio JSON-RPC serving surface (`HarnessSdkServer`, the Python SDK's peer), where the plugins and configuration actually booted are decided entirely by a `cordis.yml` supplied from outside the exe.
- The JSONRPC protocol for talking to the Python SDK is already validated
- A standardized way for cordis.yml to load every plugin (ESModule) is needed
- The distribution must carry the Node runtime, and support a locally linked source debugging mode
## Decision
### Packaging route: @yao-pkg/pkg's `--sea` mode
The exe is packaged with the **`--sea` (enhanced SEA) mode** of [@yao-pkg/pkg](https://github.com/yao-pkg/pkg) (the actively maintained fork after vercel/pkg was archived). Relative to Node's native SEA, pkg adds a `/snapshot` VFS and runtime module hooks on top, hands the ESM entry to Node's default ESM loader unchanged, and depends on no ESM→CJS transpilation.
> Measured (macos-arm64, node24 target, pkg 6.21.0): bare-specifier ESM dynamic import inside the VFS (including top-level await), CJS interop, `node:sqlite`, fail-loud on package names outside the set, and on-disk ESM import outside the VFS all pass; `import.meta.url` comes through unchanged as `file:///snapshot/...`.
`--sea` requires target ≥ node22; the exe uniformly targets node24. One pkg invocation packages exactly one target; multi-platform builds invoke it once per platform.
Terminology reminder: pkg's `/snapshot` VFS has nothing to do with this repo's testing-system "snapshot" (ACP replay goldens, `$DSH_SNAPSHOT`); this document says "VFS" for the former.
### The serving surface is a plugin: the two packages ui/jsonrpc + ui/jsonrpc-agent
The deterministic protocol implementation (`server.ts` / `transport.ts`) lands as two packages on the existing `ui/acp` + `ui/acp-agent` pattern — the serving surface is itself a plugin:
- [`packages/ui/jsonrpc`](../../../../packages/ui/jsonrpc/README.md) (`@deepseek-ai/dsh-jsonrpc`): the pure protocol plugin; on apply it mounts `HarnessSdkServer` plus a line-delimited JSON-RPC transport on the process stdio, with disposal through `ctx.effect()`. Whether to serve is decided by `cordis.yml`; a yml that does not mount it is a legitimate process that does not serve. Protocol-level exit belongs to the plugin (after answering the `shutdown` request it disposes its own fiber, then `exit(0)`; an HMR-style unload only stops the service without exiting the process).
- [`packages/ui/jsonrpc-agent`](../../../../packages/ui/jsonrpc-agent/README.md) (`@deepseek-ai/dsh-jsonrpc-agent`): a thin app bin — `installFailLoud` + `loadEnv` + config discovery + `boot()` from [`dsh-app-boot`](../../../../packages/ui/app-boot/src/index.ts), done once boot completes; the server is brought up by the `dsh-jsonrpc` entry in the yml. Its only dependency is app-boot. Process-level exit belongs to the bin (stdin EOF/SIGTERM → dispose then 0, SIGINT → 130).
Config discovery has two channels and fails loudly when both are missing: the `DSH_CORDIS_CONFIG` environment variable first (the SDK client convention), then an argv positional argument; no default path and no built-in fallback whatsoever — "the plugins actually booted are decided by an external cordis.yml" is a hard semantic.
### Plugin resolution: the VFS holds a real package tree, the closure manifest IS the deploy root
Inside the exe's VFS sits a **real package tree in build-artifact form** (each package's `lib/` plus a real `node_modules`); the Loader resolves plugin names through standard dynamic `import()`: bare specifiers resolve upward along `node_modules` from the Loader's position inside the VFS, and land inside the VFS naturally. The closed set needs no allowlist code — the set is whatever the VFS has installed, and importing a name outside the set fails.
The deploy root is [`python/sdk-runtime/package.json`](../../../../python/sdk-runtime/package.json) (`dsh-jsonrpc-agent-pkg`, a pnpm workspace member and a zero-code pure dependency manifest) — the unified source of truth for "which plugins the exe ships" and "what the Python runtime distributes". Adding a plugin to the exe = adding one dependency line to the manifest and repackaging. [`scripts/verify-runtime-closure.ts`](../../../../scripts/verify-runtime-closure.ts) traverses every workspace package covered by that manifest and requires every non-optional workspace peer at the runtime root, reporting the complete referencing-package → missing-peer chain; CI static, pre-push, and the single-exe build run it before packaging. Deploy also packs by each package's `files`, so the shared chunks tsdown splits out must be covered by `files`.
### Build pipeline and artifacts
[`scripts/build-exe-for-python-sdk.ts`](../../../../scripts/build-exe-for-python-sdk.ts): runtime closure verification → `pnpm run build` → (after clearing) `pnpm --filter dsh-jsonrpc-agent-pkg deploy --legacy --prod --config.node-linker=hoisted --config.auto-install-peers=false --config.link-workspace-packages=true` **directly into** `python/sdk-runtime/src/deepseek_harness_runtime/runtime/node/` → inject the pkg configuration (`bin` points at `node_modules/@deepseek-ai/dsh-jsonrpc-agent/lib/bin.js` inside the closure, `assets` is a full glob — dynamic import is invisible to pkg's static analysis, so everything must be packed in explicitly) → one `pkg --sea` per target → the executables `dsh-jsonrpc-agent-pkg-<platform>-<arch>` land in `dist-exe/` and are copied back into the runtime directory. CI treats them as intermediate test inputs and retains their platform wheels. All four deploy flags are grounded in measurement: `--legacy` is the mandatory path with inject-workspace-packages off; hoisted yields a zero-symlink file tree (most stable for the pkg VFS, physically guaranteeing a single cordis instance); disabling automatic peer installation keeps unpublished package names from triggering registry resolution; link-workspace-packages points the closure at workspace/vendor sources.
CI: [`.github/workflows/build-exe-for-python-sdk.yml`](../../../../.github/workflows/build-exe-for-python-sdk.yml), triggered explicitly only — `workflow_dispatch`, or the `build-exe` label on a pull request; native builds on the three platforms linux-x64 / linux-arm64 (`ubuntu-24.04-arm`) / macos-arm64, with `~/.pkg-cache` cached; macOS ad-hoc signing is handled by pkg. Each leg drives a mock SSE model through the SDK with the default config and a custom `cordis.yml`, drives the exe directly over NDJSON JSON-RPC, verifies the JSONL and final response, and installs release-shaped wheels into a clean venv without `runtime_bin`; Linux additionally inspects GLIBC requirements and runs in a manylinux 2.28 container. The run retains only four artifacts, each containing one release file: the platform-independent SDK wheel and the three native runtime wheels; bare executables and source bundles remain intermediate test inputs. [`.gitlab-ci.yml`](../../../../.gitlab-ci.yml) accepts only `python-vX.Y.Z` tag pipelines whose version matches the root `package.json`, builds one SDK wheel and three native runtime wheels, then a single serialized job checks and publishes all four to the project PyPI registry. Windows is a non-goal.
### Python SDK distribution: two carriers, exe for production, node for development
The Python SDK lives at [`python/`](../../../../python/README.md): `python/sdk` (the client) + `python/sdk-runtime` (the runtime carrier package). The runtime package's data directory holds three kinds of content: the checked-in default `runtime/cordis.yml`, the build-injected platform exe, and the build-injected `runtime/node/` closure tree. `resolve_bundled_launch_args()` automatic resolution **finds the exe only**; the node carrier is enabled only by an explicit `DSH_RUNTIME_MODE=node` (running `runtime/node/node_modules/@deepseek-ai/dsh-jsonrpc-agent/lib/bin.js`, requiring a system node ≥22.19), positioned as the development-verification channel for members of this repo, and does not enter wheel distributions.
[`scripts/build-python-release.py`](../../../../scripts/build-python-release.py) reads the authoritative stable `X.Y.Z` from the repository root `package.json` and stages both packages at that version, with the SDK depending exactly on `deepseek-harness-runtime-bin==X.Y.Z`. An optional `python-vX.Y.Z` release tag is a consistency assertion and is rejected when it differs from the repository version; the source `pyproject.toml` development sentinel never determines a release version. The SDK is a `py3-none-any` wheel; the wheel-only runtime package contains exactly one exe and uses one of `py3-none-manylinux_2_28_x86_64`, `py3-none-manylinux_2_28_aarch64`, or `py3-none-macosx_11_0_arm64`. Its Hatch hook rejects sdists, universal tags, mixed executable payloads, and unsupported platforms.
The exe's "must be explicitly configured" hard semantic is unchanged; the zero-config experience is restored by the wrapper: when the caller gave no `cordis`, named no explicit runtime, and the environment has no `DSH_CORDIS_CONFIG`, the client explicitly injects the checked-in default `cordis.yml` (agent-core + preloaded llm-deepseek + JSONL persistence + bash-local + the `dsh-jsonrpc` serving entry, with `!!js` environment-variable fallbacks) via `DSH_CORDIS_CONFIG`.
### Naming lineage
`@deepseek-ai/dsh-jsonrpc-agent` (the package) → `dsh-jsonrpc-agent` (the bin) → `dsh-jsonrpc-agent-pkg` (the closure manifest; no scope prefix, deliberately sidestepping the constraints' package-shape rules for `@deepseek-ai/dsh-*`) → `dsh-jsonrpc-agent-pkg-<platform>-<arch>` (the exe artifacts). The wire `serverInfo.name` stays `deepseek-harness-sdk-runtime` (a protocol-stable value); the Python dist names are `deepseek-harness` / `deepseek-harness-runtime-bin`.
## Disposition of worker-style plugins
`dsh-workflow-workerthread` and `dsh-code-runtime-worker` are supported inside the exe. Their built hosts convert the sibling `lib/worker.cjs` URL with `fileURLToPath()` and pass the resulting filesystem string to `Worker`, which is the form pkg's Worker hook resolves inside the VFS. The worker entries are CommonJS because that hook compiles VFS worker files as CommonJS. The workflow engine keeps its data-URL bootstrap for unbuilt source execution; only its built sibling entry uses the filesystem string. The custom-config executable smoke loads both backends, invokes a real `run_code` call and a zero-agent `workflow` call, and requires each worker to return `42` from inside pkg's VFS.
## Testing
The verification surface has three tiers. Mechanism tier: the measured conclusions for the `--sea` chain are embedded in the Decision sections (ESM dynamic import inside the VFS, single cordis instance, fail-loud config chain, `node:sqlite`, macOS ad-hoc signing runs). SDK tier: the complete keyless pytest suite covers the client protocol against a fake runtime peer, subprocess cleanup, absolute cwd propagation, dual-carrier launch, and carrier resolution; root CI runs it on Python 3.10. End-to-end tier: every platform build completes a turn against a mock endpoint through the default SDK path, a custom config, and the direct binary protocol, with final text and JSONL checked. The custom config additionally drives `run_code` and a zero-agent `workflow` through their real worker files inside the packaged VFS. The same build leg runs a committed executable-specific snapshot through the Python SDK: a keyless scripted model mounts a Cordis plugin that registers a tool, invokes that tool from `run_code`, runs a direct spawn subagent and a workflow that starts a second spawn child, then unmounts the plugin. The comparison normalizes the SDK result and notification stream plus the parent and two child JSONL logs. This harness stays separate from ACP's `pnpm run test:snapshot` because the protocols and build artifacts differ. The platform wheel is then installed in a clean venv and run without `runtime_bin`.
Manual-driving caveat: the bin treats stdin EOF as "the client is gone" and disposes immediately, so a short-lived pipe aborts an in-flight turn — pipe-driven runs must keep stdin open until the turn ends.
## Alternatives considered
**Bare Node native SEA.** The injected main script must be a single CJS file, and the blob carries no filesystem and no module resolution, so a dynamic import of a bare specifier has nothing to resolve against; the only option is compiling plugins statically into the main script and registering them by hand — bypassing standard module resolution and hardcoding the plugin set, contrary to "configuration decides everything". The final route is in fact "the official SEA foundation + pkg's VFS/module-hook layer"; what was rejected is the bare use, not SEA itself.
**pkg standard mode.** Killed by the PoC, not a trade-off: it turns ESM into CJS + V8 bytecode via esbuild, the runtime vm compilation wires up no dynamic-import callback, every `import()` throws `ERR_VM_DYNAMIC_IMPORT_CALLBACK_MISSING`, and `--options experimental-require-module` has no effect; it also depends on community-patched Node binaries (no macos-arm64 prebuilt; compiling from source on the spot takes about 10 minutes). Zero viability for this repo's architecture.
**Pre-bundling each package ESM→CJS into the VFS.** The compromise that keeps real resolution semantics and only downgrades the module format; `--sea` passed measurement outright, so this layer of build complexity never needed introducing.
**jsonrpc-agent carrying the full closure dependencies.** The app bin would declare 53+ dependencies it never imports — a "packaging manifest" masquerading as real dependency relationships — and would force constraints to open two exceptions for it, cordis-in-dependencies and a files wildcard. With the closure manifest landing on the python-side manifest package, constraints needs no exception at all and the bin keeps the normal package shape isomorphic to acp-agent.
**An open plugin set (loading user plugins from disk).** This round ships a closed set; the PoC incidentally confirmed that on-disk ESM import outside the VFS works (through the `ctx.baseUrl` relative-path channel). It is listed as a future evolution, which must separately solve sharing the cordis instance inside the exe with external plugins.
## Consequences
**Bought**: zero-dependency single-file distribution on target platforms; plugin semantics strictly identical to running from source (the same real package tree, no transpilation, no registry); the serving surface, the plugin set, and the configuration all converge on two sources of truth — `cordis.yml` plus one dependency manifest; the exe and node carriers share one tree and one semantics, so development verification never waits for packaging; official Node binaries remove the patched-binary supply-chain concern.
**Paid**: artifacts on the order of 174MB with source entering the blob as-is (no bytecode obfuscation; a closed-source distribution requirement needs a separate evaluation); pkg's VFS/module-hook layer remains community-maintained (the build script pins `@yao-pkg/pkg@6.21.0`; upgrading is an explicit change); `--sea` is one invocation per target (matching CI's one leg per platform; local multi-platform builds are serial).
docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md
+85
View File
@@ -0,0 +1,85 @@
# RFC: 单文件可执行的 SDK 运行时分发（single-exe）
Status: implemented
[English](2026-07-10-single-file-executable-sdk-runtime-distribution.md) | 中文
## 问题
DeepSeek Harness 需要为 Python 库专门提供一种无需安装 Node、可直接在目标平台运行的 SDK 分发形态：一个单文件可执行程序（下称 exe），通过 stdio 提供 JSON-RPC 对外服务接口（`HarnessSdkServer`，Python SDK 的对端），且实际启动的插件与配置完全由 exe 外部输入的 `cordis.yml` 决定。
- 与 Python SDK 通信的 JSON-RPC 协议已经过验证
- 需要提供通过标准化 `cordis.yml` 加载所有插件（ES 模块）的能力
- 分发物要自带 Node 运行时，并支持本地源码链接的调试模式
## 决策
### 打包路线：@yao-pkg/pkg 的 `--sea` 模式
exe 使用 [@yao-pkg/pkg](https://github.com/yao-pkg/pkg)（vercel/pkg 归档后的活跃维护 fork）的 **`--sea`（enhanced SEA）模式**打包。相比 Node 原生 SEA，pkg 在其上增加 `/snapshot` 虚拟文件系统（VFS）与运行时模块钩子，将 ESM 入口原样交给 Node 默认的 ESM loader，不依赖任何 ESM→CJS 转译。
> 实测（macos-arm64、node24 构建目标、pkg 6.21.0）：VFS 内裸包名 ESM 动态 `import()`（含顶层 `await`）、CJS 互操作、`node:sqlite`、集合外包名明确报错、VFS 外磁盘 ESM `import()` 全部通过，`import.meta.url` 原样为 `file:///snapshot/...`。
`--sea` 要求构建目标 ≥ node22，exe 统一以 node24 为构建目标；每次 pkg 调用只打包一个构建目标，多平台各调用一次。
术语提醒：pkg 的 `/snapshot` VFS 与本仓库测试体系的“快照”（ACP 回放 golden、`$DSH_SNAPSHOT`）无关，本文用“VFS”指前者。
### 对外服务接口也是插件：ui/jsonrpc + ui/jsonrpc-agent 两包
确定性协议实现（`server.ts` / `transport.ts`）按 `ui/acp` + `ui/acp-agent` 的既有模式落为两包——对外服务接口本身也是插件：
- [`packages/ui/jsonrpc`](../../../../packages/ui/jsonrpc/README.md)（`@deepseek-ai/dsh-jsonrpc`）：纯协议插件；执行 `apply` 时，在进程 stdio 上挂载 `HarnessSdkServer` 与按行传输的 JSON-RPC 层，资源释放走 `ctx.effect()`。是否提供服务由 `cordis.yml` 决定；未挂载该插件的配置会启动一个不提供此服务的合法进程。协议级退出归插件所有（应答 `shutdown` 请求后 dispose 自身 fiber，再调用 `exit(0)`；HMR 式卸载只停止服务，不退出进程）。
- [`packages/ui/jsonrpc-agent`](../../../../packages/ui/jsonrpc-agent/README.md)（`@deepseek-ai/dsh-jsonrpc-agent`）：轻量应用入口——`installFailLoud` + `loadEnv` + 配置发现 + [`dsh-app-boot`](../../../../packages/ui/app-boot/src/index.ts) 的 `boot()`；`boot()` 完成后入口即完成，服务器由 `cordis.yml` 中的 `dsh-jsonrpc` 条目启动。它只依赖 `app-boot`。进程级退出归 `bin` 所有（stdin EOF/SIGTERM → dispose 后返回 0，SIGINT → 130）。
配置发现有两个通道，均缺失时立即报错：优先使用 `DSH_CORDIS_CONFIG` 环境变量（SDK 客户端约定），其次使用 argv 位置参数；没有默认路径或内置回退——“实际启动的插件由外部 `cordis.yml` 决定”是硬语义。
### 插件解析：VFS 装载真实包树，闭包清单就是部署根目录
exe 的 VFS 内是**构建产物形态的真实包树**（各包的 `lib/` + 真实 `node_modules`）。loader 通过标准动态 `import()` 解析插件名：裸包名从 VFS 内 loader 所在位置沿 `node_modules` 向上解析，自然落在 VFS 内。封闭集不需要白名单代码——VFS 中安装了什么，集合中就有什么；`import()` 集合外的名称会失败。
部署根目录是 [`python/sdk-runtime/package.json`](../../../../python/sdk-runtime/package.json)（`dsh-jsonrpc-agent-pkg`，pnpm 工作区成员、零代码纯依赖清单），也是“exe 安装哪些插件”与“Python 运行时分发什么”的统一事实源。向 exe 添加插件，就是在清单中增加一行依赖后重新打包。[`scripts/verify-runtime-closure.ts`](../../../../scripts/verify-runtime-closure.ts) 遍历该清单覆盖的全部工作区包，要求每个非可选的工作区对等依赖（peer dependency）都显式列在运行时根目录，并报告“引用包 → 缺失对等依赖”的完整链路；CI 静态检查、pre-push 与 single-exe 构建都会在打包前运行该门禁。部署还会依据各包的 `files` 字段打包，因此 tsdown 拆出的共享分片必须被 `files` 覆盖。
### 构建管线与产物
[`scripts/build-exe-for-python-sdk.ts`](../../../../scripts/build-exe-for-python-sdk.ts)：运行时闭包校验 → `pnpm run build` →（清空后）`pnpm --filter dsh-jsonrpc-agent-pkg deploy --legacy --prod --config.node-linker=hoisted --config.auto-install-peers=false --config.link-workspace-packages=true` **直接写入** `python/sdk-runtime/src/deepseek_harness_runtime/runtime/node/` → 注入 pkg 配置（`bin` 指向闭包内的 `node_modules/@deepseek-ai/dsh-jsonrpc-agent/lib/bin.js`；`assets` 使用全量 glob，因为动态 `import()` 对 pkg 静态分析不可见，必须显式打入全部内容）→ 每个构建目标调用一次 `pkg --sea` → 可执行文件 `dsh-jsonrpc-agent-pkg-<platform>-<arch>` 写入 `dist-exe/`，并拷回运行时目录。CI 将这些文件作为测试中间输入，只保留对应平台的 wheel 包。四个部署标志都有实测依据：未启用 `inject-workspace-packages` 时必须使用 `--legacy`；`hoisted` 产出无符号链接的文件树（对 pkg VFS 最稳定，并从物理上保证只有一个 Cordis 实例）；关闭对等依赖自动安装可避免未发布包名触发注册表解析；`link-workspace-packages` 让闭包指向工作区/vendor 源码。
CI 使用 [`.github/workflows/build-exe-for-python-sdk.yml`](../../../../.github/workflows/build-exe-for-python-sdk.yml)，且只允许显式触发：手动派发 `workflow_dispatch`，或给 PR 添加 `build-exe` 标签。linux-x64、linux-arm64（`ubuntu-24.04-arm`）和 macos-arm64 三个平台分别进行原生构建，并缓存 `~/.pkg-cache`；macOS 的 ad-hoc 签名由 pkg 处理。每个平台都使用模拟 SSE 模型，分别通过默认配置和自定义 `cordis.yml` 驱动 SDK，再通过 NDJSON JSON-RPC 直接驱动 exe，校验 JSONL 与最终响应；最后把发布形态的 wheel 包安装到干净的 venv 中，并在不传 `runtime_bin` 的情况下运行。Linux 还会检查 GLIBC 依赖，并在 manylinux 2.28 容器中运行。整次运行只保留 4 个产物，每个产物只含一个发布文件：平台无关的 SDK wheel 包和 3 个原生运行时 wheel 包；裸 exe 与源码包只作为测试中间输入。[`.gitlab-ci.yml`](../../../../.gitlab-ci.yml) 只接受版本与根目录 `package.json` 匹配的 `python-vX.Y.Z` 标签流水线，构建一个 SDK wheel 包和 3 个原生运行时 wheel 包，再由单个串行任务校验并将这 4 个文件发布到项目的 PyPI 注册表。Windows 不在目标范围内。
### Python SDK 分发：双载体，exe 用于生产，`node` 用于开发
Python SDK 位于 [`python/`](../../../../python/README.md)：`python/sdk` 是客户端，`python/sdk-runtime` 是运行时载体包。运行时包的数据目录包含三类内容：检入的默认 `runtime/cordis.yml`、构建注入的平台 exe，以及构建注入的 `runtime/node/` 闭包树。`resolve_bundled_launch_args()` 的自动解析**只查找 exe**；`node` 载体仅在显式设置 `DSH_RUNTIME_MODE=node` 时启用（运行 `runtime/node/node_modules/@deepseek-ai/dsh-jsonrpc-agent/lib/bin.js`，需要系统 Node ≥22.19），定位为本仓库成员的开发验证通道，不随 wheel 包分发。
[`scripts/build-python-release.py`](../../../../scripts/build-python-release.py) 从仓库根目录的 `package.json` 读取权威的稳定版本 `X.Y.Z`，以该版本暂存两个包，并让 SDK 精确依赖 `deepseek-harness-runtime-bin==X.Y.Z`。可选的 `python-vX.Y.Z` 发布标签只是一项一致性断言，与仓库版本不同时会被拒绝；源码 `pyproject.toml` 中的开发占位版本从不决定发布版本。SDK 是 `py3-none-any` wheel 包；只提供 wheel 包的运行时包恰好包含一个 exe，标签为 `py3-none-manylinux_2_28_x86_64`、`py3-none-manylinux_2_28_aarch64` 或 `py3-none-macosx_11_0_arm64`。其 Hatch 钩子拒绝 sdist、通用标签、混合可执行载荷以及不支持的平台。
exe“必须显式配置”的硬语义不变；零配置体验由包装层恢复：调用方没有提供 `cordis`、没有显式指定运行时，且环境中没有 `DSH_CORDIS_CONFIG` 时，客户端将检入的默认 `cordis.yml`（`agent-core` + 预载的 `llm-deepseek` + JSONL 持久化 + `bash-local` + `dsh-jsonrpc` 对外服务条目，并通过 `!!js` 使用环境变量兜底）显式注入 `DSH_CORDIS_CONFIG`。
### 命名血统
`@deepseek-ai/dsh-jsonrpc-agent`（包）→ `dsh-jsonrpc-agent`（`bin`）→ `dsh-jsonrpc-agent-pkg`（闭包清单；没有作用域前缀，刻意避开 `constraints` 对 `@deepseek-ai/dsh-*` 的包形状规则）→ `dsh-jsonrpc-agent-pkg-<platform>-<arch>`（exe 产物）。协议字段 `serverInfo.name` 保持为 `deepseek-harness-sdk-runtime`（协议稳定值）；Python 分发名为 `deepseek-harness` / `deepseek-harness-runtime-bin`。
## 工作线程插件
exe 内支持 `dsh-workflow-workerthread` 与 `dsh-code-runtime-worker`。两个后端构建后的宿主都通过 `fileURLToPath()` 转换相邻 `lib/worker.cjs` 的 URL，再将所得文件系统字符串传给 `Worker`；pkg 的 Worker 钩子可以用这种形式解析 VFS 内文件。该钩子会把 VFS 内的工作线程文件作为 CommonJS 编译，所以工作线程入口采用 CommonJS。工作流引擎在未构建的源码执行中仍保留 `data:` URL 引导程序，只有构建后的相邻入口使用文件系统字符串。自定义配置的可执行文件冒烟测试会加载两个后端，实际调用 `run_code` 与不启动 agent 的 `workflow`，并要求两个工作线程都从 pkg 的 VFS 内返回 `42`。
## 测试
验证面分三层。机制层：`--sea` 链路的实测结论内嵌在“决策”各节（VFS 内 ESM 动态 `import()`、单一 Cordis 实例、明确报错的配置链路、`node:sqlite`、macOS ad-hoc 签名可运行）。SDK 层：完整的无密钥 pytest 套件以假运行时对端覆盖客户端协议、子进程清理、绝对 `cwd` 传递、双载体启动与载体解析；根 CI 在 Python 3.10 上运行全部用例。端到端层：每个平台构建都通过默认 SDK 路径、自定义配置和直接二进制协议，对模拟端点完成一个轮次，并校验最终文本与 JSONL。自定义配置还会通过打包进 VFS 的真实工作线程文件执行 `run_code` 和不启动 agent 的 `workflow`。同一构建任务还会经 Python SDK 运行一组检入的 exe 专用快照：无密钥脚本化模型挂载一个会注册工具的 Cordis 插件，从 `run_code` 调用该工具，运行一个由 spawn 提供方直接启动的 subagent（子 agent）和一个会通过 spawn 启动第二个子 agent 的工作流，随后卸载该插件。比较时会规范化 SDK 结果与通知流，以及父会话和两个子会话的 JSONL 日志。该 harness 与 ACP 的 `pnpm run test:snapshot` 保持独立，因为二者的协议和构建产物不同。随后把平台 wheel 包安装进干净的 venv，并在不传 `runtime_bin` 的情况下运行。
手工驱动注意：`bin` 将 stdin EOF 视为“客户端已离开”并立即 dispose，短命管道会中止进行中的轮次——管道驱动必须保持 stdin 打开，直到轮次结束。
## 曾考虑的替代方案
**裸用 Node 原生 SEA。** 注入的主脚本必须是 CJS 单文件，blob 内没有文件系统与模块解析，因此动态 `import()` 无法解析裸包名；只能把插件静态编译进主脚本并手工注册。这会绕过标准模块解析并硬编码插件集合，与“配置决定一切”相悖。最终路线实际是“官方 SEA 基础 + pkg 的 VFS/模块钩子层”；否决的是裸用方式，而不是 SEA 本身。
**pkg 标准模式。** PoC 证明该模式不可行，而非权衡后放弃：它通过 esbuild 将 ESM 转为 CJS + V8 字节码，但运行时 VM 编译没有接入动态 `import()` 回调，任何 `import()` 都会抛出 `ERR_VM_DYNAMIC_IMPORT_CALLBACK_MISSING`，`--options experimental-require-module` 也无效；此外，它依赖社区补丁版 Node 二进制（macos-arm64 没有预编译版本，现场从源码编译约需 10 分钟）。该模式不适用于本仓库架构。
**每包 ESM→CJS 预打包进 VFS。** 保持真实解析语义、只降级模块格式的折中；`--sea` 直接通过实测，这层构建复杂度无需引入。
**让 jsonrpc-agent 承担完整闭包依赖。** 应用入口将声明 53 个以上自身并不 `import()` 的依赖，使“打包清单”伪装成真实依赖关系，还会迫使 `constraints` 为其增加 `cordis-in-dependencies` 与 `files` 通配符两个例外。将闭包清单放在 Python 侧的清单包后，`constraints` 不需要任何例外，`bin` 也能保持与 acp-agent 同构的正常包形状。
**开放插件集（从磁盘加载用户插件）。** 本期采用封闭集；PoC 同时证实，可以通过 `ctx.baseUrl` 相对路径通道从 VFS 外的磁盘 `import()` ESM。该能力列为后续演进，届时还需解决外部插件与 exe 内 Cordis 实例的共享问题。
## 后果
**买到的**：目标平台零依赖的单文件分发；插件语义与源码运行严格一致（同一棵真实包树，无转译、无注册表）；对外服务接口、插件集与配置全部收敛到 `cordis.yml` 和一份依赖清单这两个事实源；exe 与 `node` 双载体使用同一棵树和相同语义，开发验证无需等待打包；官方 Node 二进制消除了补丁版二进制的供应链顾虑。
**付出的**：产物约 174MB，且源码原样进入 blob（没有字节码混淆；闭源分发诉求需要另行评估）；pkg 的 VFS/模块钩子层仍由社区维护（构建脚本钉死 `@yao-pkg/pkg@6.21.0`，升级需要显式改动）；`--sea` 每个构建目标调用一次（与 CI 每个平台一个任务相匹配，本地多平台构建串行执行）。
docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md
+1 -1
View File
@@ -26,7 +26,7 @@ One deliberate strictness DIVERGENCE from CC: hook misuse — unknown or deferre
**Why node:worker_threads**: one run uses one unpooled worker because a workflow run is already heavyweight relative to thread startup. The script runs in a vm context inside the worker, keeping the script-visible surface to the hook contract instead of exposing a bare worker realm, while `agent()` bridges by message-port RPC to I/O-bound child loops on the host. This keeps `start()` from blocking the host on the script's synchronous slice, makes the post-cancel deadline end in a real `worker.terminate()`, and gives cross-thread values a serialization boundary by construction. isolated-vm was rejected for its maintenance state, required `--no-node-snapshot` consumer flag on Node ≥ 20, and node-gyp fallback.
Host-side meta validation and body pre-parsing preserve the seam's synchronous errors, and private enum-keyed payload maps define the wire protocol. Pending async starts, published child records, one host cancellation signal, worker-death reaping, result precedence, and disposal quiescence preserve the subagent run contract across that wire; the [agent-scope runtime-design RFC](../architecture/2026-07-12-agent-scope-runtime-design.md#workflow-children-are-pending-starts-or-published-records) owns those race algorithms. Coverage uses an in-process `MessageChannel` for worker-side logic that main-process V8 coverage cannot see and separately proves the built `lib/worker.js`—a second tsdown entry sanctioned by the `"./worker"` subpath export—under plain Node in the built-bin smoke gate.
Host-side meta validation and body pre-parsing preserve the seam's synchronous errors, and private enum-keyed payload maps define the wire protocol. Pending async starts, published child records, one host cancellation signal, worker-death reaping, result precedence, and disposal quiescence preserve the subagent run contract across that wire; the [agent-scope runtime-design RFC](../architecture/2026-07-12-agent-scope-runtime-design.md#workflow-children-are-pending-starts-or-published-records) owns those race algorithms. Coverage uses an in-process `MessageChannel` for worker-side logic that main-process V8 coverage cannot see and separately proves the built `lib/worker.cjs`—a second tsdown entry sanctioned by the `"./worker"` subpath export—under plain Node in the built-bin smoke gate.
**Meta as data, never evaluated**: the meta block reaches the seam as a plain JSON request field (the tool's schema-validated `meta` parameter) and the engine only shape-validates it, every violation named. This is a host-isolation invariant, not a convenience: evaluating a meta literal host-side — even one contractually "pure", in an empty timed vm context — hands script-controlled getters a host stack with no timeout the moment the result is READ, defeating the exact spin isolation the worker thread buys.
docs/rfc/implemented/process/2026-06-11-quality-gates.md
+3 -2
View File
@@ -11,8 +11,9 @@ This codebase is developed primarily by coding agents. Agents follow enforced ga
Every AGENTS.md promise gets a command that exits non-zero, wired into git hooks and CI both calling the same package.json scripts:
- Max-strict TypeScript (`noUncheckedIndexedAccess`, `exactOptionalPropertyTypes`, …); examples, tests, and scripts typecheck in CI via the root no-emit `tsconfig.json` while package/vendor code stays behind its own project-reference boundary.
- ESLint strict-type-checked + @stylistic (the house style, enforced); vendored code excluded.
- Per-file 100% coverage on `packages/*/src` (v8); unreachable defensive guards carry `/* v8 ignore */ ` with stated reasons instead of deletion.
- ESLint strict-type-checked + @stylistic (the house style, enforced), including file-local duplicated logic checks; vendored code excluded.
- jscpd detects cross-file clones in package production TypeScript and repository scripts; narrow source-range exceptions document deliberately parallel implementations.
- Per-file 100% coverage on `packages/*/*/src` (v8); unreachable defensive guards carry `/* v8 ignore */ ` with stated reasons instead of deletion.
- knip (dead code/deps), publint (package correctness), workspace constraints (workspace rules: private, cordis peer+dev, uniform version, ESM), and a NodeNext consumer typecheck for built package declarations.
- lefthook pre-commit (lint staged, typecheck, vendor-manifest guard) and pre-push (tests, hygiene); CI runs the full matrix on node 22.19/24/26 plus a demo smoke test driving the echo-agent end to end.
docs/rfc/implemented/process/2026-06-16-pnpm-over-yarn.md
+1 -1
View File
@@ -15,7 +15,7 @@ Adopt **pnpm 11.7.0**, pinned via the `packageManager` field and installed throu
- **Workspaces** move from the `package.json` `workspaces` array + `.yarnrc.yml` to `pnpm-workspace.yaml` (`vendor/*`, `packages/*` — the same globs; `examples/*` stay non-workspace, matching the prior setup and tsdown's explicit globs).
- **Strict symlinked linker** (pnpm's default) replaces Yarn's hoisted `node-modules` linker. We deliberately add **no** `node-linker=hoisted` / `shamefully-hoist` escape hatch: pnpm's non-flat `node_modules` makes phantom dependencies (importing an undeclared transitive dep) fail loudly, which is a *feature* for a repo whose whole quality story is mechanical gates ([mechanical quality gates](2026-06-11-quality-gates.md)). The gate suite — typecheck, lint, test, build, knip — is the safety net that proves no such phantom imports exist.
- **Build-script allowlist.** pnpm 10+ does not run dependency lifecycle scripts unless allowlisted. `pnpm-workspace.yaml` carries an explicit `allowBuilds` map (`esbuild`, `lefthook`, `@google/genai`, `protobufjs`) — the same supply-chain-hardening posture the repo already takes toward model/tool output, now applied to install-time code execution. `peerDependencyRules.allowedVersions.typescript: '>=5 <7'` silences benign peer-range warnings for the in-repo TypeScript.
- **Constraints become package-manager-independent.** `yarn.config.cjs` (which imported `@yarnpkg/types` and used `Yarn.workspaces()` / `workspace.set()`) is replaced by `scripts/check-workspace-constraints.ts`, a plain tsx script run as `pnpm run constraints`. It enforces the identical invariants — every package `private: true`; `@deepseek-ai/dsh-*` packages declare `cordis` as both a peer- and dev-dependency with matching ranges, `version: 0.0.1`, `type: module`; vendored packages checked for privacy only — over the same `vendor` + `packages` scope.
- **Constraints become package-manager-independent.** `yarn.config.cjs` (which imported `@yarnpkg/types` and used `Yarn.workspaces()` / `workspace.set()`) is replaced by `scripts/check-workspace-constraints.ts`, a plain tsx script run as `pnpm run constraints`. It enforces the identical invariants — every package `private: true`; `@deepseek-ai/dsh-*` packages declare `cordis` as both a peer- and dev-dependency with matching ranges, use the root `package.json` version, and set `type: module`; vendored packages checked for privacy only — over the same `vendor` + `packages` scope.
- All `yarn …` verbs across CI, lefthook hooks, `package.json` scripts, and docs become `pnpm …` / `pnpm run …`. `yarn.lock` → `pnpm-lock.yaml` (lockfile v9). `.gitignore` swaps `.yarn/` for `.pnpm-store/`. Vendored READMEs (e.g. `vendor/cordis/README.md`) keep their upstream `yarn` examples untouched per the Vendoring Policy.
## Alternatives considered
docs/rfc/proposed/feature/2026-07-08-interactive-side-sessions.md
+48
View File
@@ -0,0 +1,48 @@
# RFC: Interactive side sessions and merge-back
Status: proposed
## Problem
A user deep in a live session often wants to fork the conversation — ask "why did we structure it this way", explore an alternative, get an explanation — without polluting the main context and without abandoning the surface they are in. The harness has every primitive this needs and no product face for it: [the session-store fork API](../../implemented/feature/2026-06-30-session-store-fork-api.md) produces a `Session` with no attached agent and no way for a client to reach it, and [the fork subagent](../../implemented/feature/2026-06-21-subagent-capability-seam.md) seeds a child with the parent's prefix but runs it as a model-driven task whose whole transcript collapses into one tool result — neither yields a forked conversation the USER can talk to.
The return path is missing entirely: nothing carries a conclusion from one branch back into another. Whatever the user learns in an exploration branch is copy-pasted by hand or lost, with no provenance and no replayable record.
Terminal-first competitors ship half of each: single-shot side questions with inherited context, and user-switched branch copies that force a client restart. None ship the return verb. A harness that owns its session store and context assembly can do both cheaply — and can do so without breaking the provider prefix cache, which third-party wrappers structurally cannot.
## Proposal
A **side session** is an ordinary live session forked from a source session at its last completed turn, attached to its own agent, framed as a read-only advisor, with one new verb — **merge-back** — that hands a condensed note to the parent.
- **Fork + attach composes existing primitives.** The child is created via `ctx.agents.create({ seed, meta })` with the parent's balanced completed-turn prefix (the same slice the fork subagent takes) and `parentSession`/`seedLength` lineage stamped in `meta`. No new core service and no session-store change, for the same reasons [the fork API RFC](../../implemented/feature/2026-06-30-session-store-fork-api.md) rejected a standalone fork service.
- **Advisor framing rides the log, not the system prompt.** The rules ("you are a read-only side advisor; explain, do not mutate; refuse task continuation") are `inject()`ed as a `context/message` with source `{ kind: 'plugin', plugin: 'sidechat' }` immediately after creation. The child's system prompt stays byte-identical to the parent's, so the provider's prefix cache covers the inherited history.
- **Merge-back is one condense turn plus one injection.** The child is prompted for a bounded handback note (a hard length cap), which is then `inject()`ed into the PARENT as a `context/message` with the same plugin source. The parent's next request sees it at its chronological position; replay and [reconstructability](../../implemented/architecture/2026-07-05-reconstructable-requests.md) hold by construction; no new event type enters [the session vocabulary](../../../core-data-structures/session.md).
- **The surface binding is deliberately unspecified.** How a user invokes the fork and the merge, and how a handback note is presented, are client concerns; while the harness speaks through protocols whose UI it does not control, this RFC pins only the surface-agnostic mechanics above and leaves presentation to the first surface the project owns.
Scope also excludes: rewind productization (mechanically the same fork-to-an-earlier-boundary, an entirely different product question), session tree views, a model-facing side-session tool, and `forkName`/`mergedInto` metadata.
## Prototype
A spike (branch `spike/side-sessions-b`) validates the mechanics against the live adapter: a fork that leaves the source log untouched, a child seeded with the full inherited prefix, a multi-turn advisor exchange that demonstrably uses parent history, and a merge-back the parent's next turn quotes correctly.
## Alternatives considered
- **Carry side conversations through the subagent seam.** Rejected: a subagent child is a model-driven run — the parent's model spawns it, drives it, and consumes its result as a tool result. A side session is user-driven, needs its own client-visible session and lifecycle, and must outlive any single parent turn.
- **Persona via `system-prompt/assemble` section filtering.** Rejected as the default path: any system-prompt byte change invalidates the provider prefix cache from token 0, forfeiting the cheap fork that makes side sessions attractive on long histories. The filter seam remains available for deployments that prefer hard prompt separation over cache reuse.
- **A dedicated `sidechat/*` event family for the handback.** Deferred: `context/message` with a mandatory plugin source already satisfies durability, provenance, and replay. A first-class event earns its catalog, persistence, and snapshot costs only if a UI needs to render handbacks as dedicated cards.
- **Binding the proposal to a protocol surface now.** Rejected in review: the harness currently speaks through client-owned UIs it does not control, so any presentation contract written today would be speculative. The RFC pins the surface-agnostic mechanics and defers presentation to the first surface the project owns.
- **Surface-level mirroring of the handback.** Rejected in review: a visible record emitted outside the log vanishes on replay while the model still sees it. Whatever surface eventually renders the handback must derive its presentation from the durable `context/message`, so live and replayed views come from the same event.
## Acceptance criteria
- Forking a live session yields a child agent seeded with the source's balanced completed-turn prefix, with `parentSession` and `seedLength` in its header and a system prompt byte-identical to the parent's; the source log is untouched by the fork.
- The advisor framing is exactly one plugin-sourced `context/message` at the head of the child's appended history — never a system-prompt change.
- Merge-back appends exactly one length-capped `context/message` to the parent with source `plugin: sidechat`; the parent's next request sees it, and replay reproduces it at the same position.
- Parent and child run concurrently without cross-talk between their logs or streams.
- Coverage: unit tests for the fork/attach and merge-back mechanics; surface-level snapshot coverage lands with whichever surface first binds the feature.
## Risks
- **Read-only is advisory in v1.** The rules are injected context, not enforcement; a determined prompt can still drive mutating tools. The hard gate is a `tools/pre-execute` deny via [the interception seams](../../implemented/feature/2026-06-30-interception-seams.md), and the RFC's advisor framing is written so that gate can be added without changing the mechanics.
- **A compacted source forks its compacted view.** The child inherits the summary, not the original turns; whichever surface binds the feature should disclose this once [compaction](../../implemented/feature/2026-06-18-compaction-capability-seam.md) ships in this path.
- **Handback notes spend parent tokens.** The length cap and one-note-per-merge bound the cost, but a user who merges repeatedly accumulates notes; a future consolidation pass belongs to the compaction work, not here.
docs/rfc/proposed/feature/2026-07-13-stream-workflow-progress-through-tool-calls.md
+41
View File
@@ -0,0 +1,41 @@
# RFC: Stream workflow progress through tool calls
Status: proposed
## Problem
The workflow engine intentionally emits balanced `workflow/*` observation events for run, phase, narration, and child-agent progress, but no production consumer presents them. Editors therefore show one pending workflow tool card until the final result even while the engine already reports which phase is active, what the script logged, and which children started or settled. The [dynamic-workflows decision](../../implemented/feature/2026-07-05-dynamic-workflows.md) explicitly reserves ACP progress UI for this event stream.
Making `dsh-acp` listen to workflow events directly would invert the capability boundary: the generic UI bridge would depend on an optional workflow package and special-case one tool name. The tool pipeline already owns the routing facts a live update needs—agent and call id—but exposes only pure pending/final presenters, so a long-running tool has no provider-neutral way to report transient UI state between them.
## Proposal
Add a live progress channel to `dsh-tools`. The registry-owned `ToolExecution` gains `reportProgress(view): boolean`, where `view` is a detached provider-neutral generic progress snapshot containing an optional replacement title and UI-facing content blocks. Progress cannot change the call's args-derived card tag, kind, raw input, locations, terminal intent, or diff intent; it updates only the live title/content within the presentation chosen up front. While the execution is active, the method validates and snapshots the view, then dispatches a contained, agent-scoped `tools/progress` observation carrying the authoritative execution identity and snapshot. Once final-result processing begins it returns `false` and emits nothing, so a late asynchronous reporter cannot overwrite a terminal card. Observer exceptions are logged and cannot fail the tool.
`dsh-acp` consumes `tools/progress` generically. It resolves the execution's agent through its existing agent-to-session map and emits an in-progress `tool_call_update` for the same call id. Because reporting is available only inside the tool execution pipeline, the durable `tool/call` and its ACP `tool_call` always precede the first update; closing the reporter before `tools/result` ensures no progress update follows the completed/failed card. Progress is live UI state rather than model input or durable history: session replay continues to reconstruct the pending and final cards from `tool/call` and `tool/result` without replaying transient updates.
`dsh-tool-workflow` becomes the first producer. Each tool execution installs a compact event capture before calling `ctx.workflows.start()`, because a valid engine may emit progress synchronously inside `start()`. Until the call returns, the capture reduces observed events into candidate states keyed by `WorkflowRunInfo.id`; it then selects the returned `WorkflowRun.id`, discards other candidates, reports the accumulated snapshot, and routes later matching events directly. If `start()` throws, the capture is disposed and its candidates are dropped. This preserves engine swappability without adding observer correlation to `WorkflowStartRequest` or requiring progress to wait until `start()` returns.
The reducer consumes the existing start, phase, log, agent-start, agent-end, and end events, reporting a replacement snapshot with the current phase, latest log line, active child labels, and completed/failed/cancelled counts. It does not accumulate a narration transcript; settled children leave the active set and become counters. `workflow/end`, tool settlement, or plugin disposal removes the reducer entry and event capture. The six workflow events, their metadata, paired child lifecycle, run handle, cancellation channels, and observer containment remain unchanged; third-party observers can continue consuming them directly.
Update the tool execution/presentation docs, generated event and API catalogs, workflow package docs, and the workflow data-structure catalog. ACP integration coverage must exercise the real workflow tool and worker seam with a scripted model boundary; the primary ACP snapshot suite adds one workflow-progress scenario because this changes the editor-facing transcript.
## Alternatives considered
**Delete the workflow observation surface.** Rejected in [the collapse-workflow simplification](../../rejected/simplification/2026-07-12-collapse-workflow-to-foreground-core.md): the events and their balanced lifecycle are intentional, and the missing piece is a consumer.
**Teach ACP about workflows directly.** This could map `WorkflowRunInfo` to a session and card, but it would make the generic bridge depend on an optional capability and bypass the rule that tools own presentation intent. A tool-progress channel solves the same routing problem for every long-running tool.
**Persist every progress update as a session event.** That would make live narration replayable, but it would permanently enlarge logs with state whose authoritative durable outcome is already the tool call/result pair. If resumable workflow progress becomes a product requirement, it needs a workflow-journaling design rather than UI snapshots disguised as durable facts.
## Acceptance criteria
- `ToolExecution.reportProgress()` is registry-owned, agent-scoped, snapshotting, observer-contained, and returns `false` without dispatch after terminal processing starts.
- ACP routes progress to the correct call in the correct live session; concurrent workflows in different sessions cannot cross-talk, and no `tool_call_update` appears before its `tool_call` or after its terminal update.
- Workflow progress shows the current phase, latest log line, active children, and outcome counts while preserving all existing `workflow/*` events and run semantics; a seam test engine that emits start, phase, log, child, and end events synchronously inside `start()` loses none of that reducer state.
- Cancellation, worker death, tool failure, session close, and plugin disposal release reducer state; replay emits only the durable pending/final card pair.
- Unit, workflow integration, ACP integration, snapshot, typecheck, coverage, doc-sync, module-graph, build, and hygiene gates pass.
## Risks
This adds a public live-progress method and event to the tool seam, so implementations must keep the active/terminal boundary exact and detach snapshots before observers see them. The pre-start capture can briefly observe unrelated workflow runs, so it holds only compact candidate state keyed by run id and drops every non-matching candidate as soon as `start()` returns. A workflow can emit many progress changes; the bounded reducer avoids transcript growth but still sends one UI update per meaningful event after correlation. If measured clients need coalescing, it must be a defaulted validated bridge configuration rather than a hardcoded throttle. Transient progress intentionally disappears on replay, so the final tool result remains the only durable workflow card content.
docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md
+16 -38
View File
@@ -4,57 +4,35 @@ Status: proposed
## Problem
The agent factory carries TWO ids for what is, in every live consumer, one thing:
The agent factory carries two ids for each live agent/session pair: `agentId`, the `AgentRegistry` routing handle, and `sessionId`, the event-sourced/persisted-log identity. `CreateAgentOptions` takes both; `ResumeAgentOptions` takes `agentId` plus `resumeSessionId`; in-process subagents mint two independent UUIDs despite recording lineage separately.
- `agentId` — the `AgentRegistry` handle (the actor identity; the registry rejects a duplicate).
- `sessionId` — the event-sourced session / persisted-log identity (`session.header.id`).
ACP already uses the same value for both identities. Where they diverge, stdio keeps `labelBySession` solely to recover an agent label from session events, and hooks expose both values for authors to reconcile. No production path reattaches one live agent object to several sessions or drives one session through several agent ids.
`CreateAgentOptions` takes both separately; `ResumeAgentOptions` takes an `agentId` plus a `resumeSessionId`. They diverge in exactly three places:
The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) has no reservation side tables: create and resume use one `AgentCreationTransaction`, and agent/session entries use the same final-entry collision rule. Separate ids therefore do not duplicate asynchronous liveness, rollback, or quiescence machinery. Identity unification is only an API and representation simplification: it deletes one caller-supplied id, one UUID per in-process child, and the remaining translation paths without changing the transaction lifecycle.
- **Config-driven create** (`AgentLoop.create`): a stable `agentId` (e.g. `"echo"`) with a fresh per-run `sessionId` (`${id}-session-<uuid>`).
- **Resume**: a caller-supplied `agentId` (e.g. `"main"`) on a persisted `resumeSessionId`.
- **In-process subagent children**: the backend mints the child's `agentId` and `sessionId` as two independent UUIDs (`packages/subagent/subagent-inprocess/src/index.ts`) that nothing distinguishes — `parentSession` records lineage independently.
Where a live consumer looks an agent up, no lookup needs an id translation: the ACP bridge — the primary production path — already unifies the two (`agentId === sessionId === <uuid>`; both factory call sites brand `AgentId(sessionId)` directly, and its reverse lookup keys on the `Agent` object itself), and the CC hooks bridge resolves subagent children directly by the `agentId` its lifecycle event carries. The one production population whose two ids actually DIVERGE is the in-process subagent children — the same cosmetic separation as the config path, and the same one-field simplification under unification. One consumer already pays the two-id tax: ui-stdio keeps a `labelBySession` map (seeded from the registry, maintained by `agent/created`/`agent/disposed` listeners) solely to translate `session.header.id` back to an agent id for its turn labels — machinery that deletes outright when the ids unify. And the CC hooks bridge stamps `session_id: agent.session.header.id` into every hook payload, so under unification a subagent hook's `session_id` and `agent_id` become the same string — one less identity for a hook author to reconcile.
The separation is **latent generality no consumer exercises**: nothing reads a *stable* `agentId` back across runs (each process starts fresh, and persistence keys off the session id, never the agent id). The config path's "stable agentId, fresh sessionId" buys nothing concrete — it is cosmetic. And the `agentId !== sessionId` case is precisely what opens the bash owner-token alias hole: the bash completion-notice routes by `session.header.id`, but the registry enforces uniqueness only on `agentId`, so a programmatic caller registering two agents with different agent ids but the SAME session id can mis-route a notice (see [agent lifecycle and ownership seams](../../implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md) § Seam precondition). The current code documents this as a precondition rather than guaranteeing it.
Session itself repeats the same fact as `Session.id` and `Session.header.id`. Construction rejects a header whose id differs, so the aliases are constrained equal; the durable boundary must nevertheless validate the duplicate, and production consumers choose between its two homes.
## Proposal
Make an agent BE its session: one id. An agent's registry handle IS its `session.header.id`.
Make an agent's registry id equal its session id. `CreateAgentOptions` accepts one id used for both final registry entries; resume registers the agent under the resumed session id; subagent creation mints one combined id; Session keeps one identity home by deriving `id` from `header.id` or removing the alias. Keep the existing creation transaction, final-entry collision checks, and exact-entry detach semantics; remove only maps and fields whose sole job is translating between the ids.
- `CreateAgentOptions` drops the separate `sessionId` — the single `id` is both the registry handle and the live/persisted session id. (ACP already passes the same UUID for both, so its call site simplifies to one field.)
- `ResumeAgentOptions` drops the separate `agentId` — resuming `sessionId` X registers the agent under id X. (ACP already does this.)
- The config path (`AgentLoop.create`) uses its configured `id` directly as the session id, applying whatever resume-or-create policy it adopts (today it appends a per-run uuid to avoid colliding with an on-disk log; that policy moves onto the single id, e.g. the config id IS the session and a durable backend resumes it — to be settled in the implementing PR).
- The registry's existing unique-`agentId` check becomes, by construction, a unique-session-id guarantee — the bash alias hole is closed with NO new defensive invariant: two agents cannot share a session id because the session id is the agent id.
The config-driven path must first settle its currently hidden resume-or-create policy. Today it uses a stable agent label and fresh UUID-suffixed session id to avoid colliding with a durable log on the next run. Under unification it must deliberately resume the fixed id, mint a fresh combined id, or expose an explicit policy; implementation must not pick silently.
`agent/created` and `agent/disposed` remain outside this proposal. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search.
## Alternatives considered
### Why not just enforce session-id uniqueness in `AgentRegistry.register()`?
That was the review's first suggestion. It would couple the generic registry to a session-uniqueness assumption (the registry tracks *agents*, not sessions) and entrench the very separation this RFC removes. Unifying the ids closes the hole more cleanly — there is nothing left to enforce.
**Keep separate routing and log identities.** The config-driven loop uses a stable configured agent id with a fresh UUID session on each fresh process start. That is a real use of the distinction: a stable routing/display label plus a new durable conversation. Unification can proceed only after choosing whether this path resumes a fixed identity, mints a combined per-run identity, or exposes the policy explicitly. If the stable label is a required product contract, reject this proposal rather than hiding it in another map.
## Acceptance criteria
- `ctx.agents.create`/`resume` take a single id; the ACP bridge passes one id.
- The config-driven agent path has a deliberate, documented session-id policy (no silent per-run id divergence that no consumer reads).
- The bash owner-token alias hole is gone by construction (no two live agents can share a session id).
- All existing behavior the tests pin (ACP create/resume/load, config startup, durability) still holds — or the tests change WITH the behavior where the divergence was an artifact (per AGENTS.md "tests document behavior, not golden truth").
- Agent create/resume and subagent creation carry one identity; `Session` stores it in one place.
- The existing creation transaction keeps final-entry collision, exact-entry detach, rollback, and quiescence guarantees without adding identity-specific lifecycle state.
- ACP, stdio, hooks, bash ownership, persistence, and lineage need no agent/session id translation.
- The config-driven resume-or-create policy is explicit and covered across a durable restart.
- `agent/created`/`agent/disposed` are removed only if a post-change production search finds no listener; otherwise they and their publication semantics stay.
- Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass.
## Risks
This touches public factory interfaces (`CreateAgentOptions`, `ResumeAgentOptions`, `AgentFactory`) and the config-agent id scheme, so it is a deliberate cross-package change, not a local patch — it ships as its own PR (converged with Codex); the bash owner-token precondition it closes is documented in [agent lifecycle and ownership seams](../../implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md).
The genuine risks of collapsing the two ids into one (the case AGAINST this proposal — to be weighed honestly before implementing):
- **It forecloses a one-agent-resumes-many-sessions / one-session-driven-by-many-agents future.** Today the separate ids leave room for an agent (a stable actor) to detach from one session and attach to another, or for a handoff where a new agent process adopts an existing session under a new actor handle. Unifying makes "agent" and "session" the same lifetime, so any such future needs a NEW seam (e.g. an explicit `actorId` distinct from the session) — re-introducing the very separation we removed. We judge this generality currently unused, but it is a door this change closes.
- **Subagents / fork / spawn may WANT a stable actor id across forked sessions.** The [subagent seam](../../implemented/feature/2026-06-21-subagent-capability-seam.md) runs a child agent seeded from a parent's event log (fork). If a future design wants "the same agent identity across a fork" (parent and child share an actor but have distinct session logs), a unified id blocks it. The implementing PR must check the intended fork/spawn model BEFORE unifying, or accept that fork always mints a fresh combined id. (As shipped, each subagent child mints its own distinct agent id — `parentSession` records lineage — so the seam does not currently rely on a shared actor id, but unifying would foreclose adding one.)
- **The config-driven resume-or-create policy becomes load-bearing, not cosmetic.** Today the per-run-uuid session id quietly sidesteps the "a fixed id collides with its own on-disk log on the second run" problem. Once the id is unified and stable, a config agent restarting MUST decide resume-vs-fresh deliberately — there is no longer a throwaway session id to hide behind. Getting this wrong reintroduces the create-collision the uuid was avoiding (a durable backend refuses to re-create an id whose log exists). This is the one real design decision the implementing PR owns, and it is easy to get subtly wrong.
- **Persisted/on-disk identity becomes the agent identity.** Unifying means the registry handle is now a persisted, externally-meaningful string (a session id a client chose), not an internal label. A caller that previously used a short human label (`"main"`) as the agent id now must use the session id. This is fine for ACP (already a UUID) but is a semantic narrowing for any programmatic embedder that relied on naming its agents independently of session storage.
- **Migration churn touches every create/resume call site and its tests.** `CreateAgentOptions`/`ResumeAgentOptions` shape changes ripple to ACP, the config path, the agent-loop factory, and ~dozens of test fixtures that currently pass distinct `agentId`/`sessionId` (some deliberately distinct to exercise the divergence — those tests change WITH the behavior, per AGENTS.md "tests document behavior, not golden truth"). The risk is mechanical but broad; a missed call site is a type error, but a missed *test* could silently lose coverage of a path.
The one real design question the implementing PR must settle first is the config-driven resume-or-create policy once the id is unified (today's per-run-uuid behavior is a demo simplification already flagged `TODO(demo)`). If, on closer look, the fork/spawn or multi-session-actor futures turn out to be wanted, this RFC should be REJECTED in favor of the lighter "enforce session-id uniqueness in the registry" guard — the alias hole is not reachable via ACP, so keeping the ids separate and merely documenting (or mechanically enforcing) the precondition remains a valid alternative.
This forecloses latent multi-session-actor and session-handoff designs, makes persisted client-chosen session identity the registry identity, and touches every factory fixture. The config restart decision is blocking, not mechanical. If separate routing identity is a real requirement, reject this RFC and retain the current caller-supplied pair plus final-entry arbitration.
docs/rfc/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md
+41 -13
View File
@@ -1,32 +1,60 @@
# RFC: Prune dead core-spine surface — `SurfaceManager.invalidate()`, the loop-internal exports, `ToolExecutionResult.callId`
# RFC: Prune dead public and result surface
Status: proposed
## Problem
Three pieces of public spine surface share one defect class: their only possible role is to be ignored, or their trigger is unreachable.
Several package-root exports, result fields, and convenience methods have no production consumer. They survive because tests import internals through public entry points or because a type anticipated a caller that never arrived. Each item is small in isolation, but together they enlarge the SDK contract, generated catalogs, documentation, and regression matrix without enabling a shipped path.
1. **`SurfaceManager.invalidate()`** (`packages/core/session/src/surface.ts`). Its documented trigger — "the log has been replaced wholesale (e.g. after Session seed)" — is structurally unreachable: seeding happens inside the `Session` constructor, `_surface` is created lazily on first access, and the log reference is never reassigned afterward, so no constructed `SurfaceManager` ever observes a wholesale replacement. Sole caller: its own unit test. A rollback primitive protecting a scenario the implementation cannot produce.
2. **The `runLoop`, `Inbox`, and `InboxMessage` exports** (`packages/core/agent-loop/src/index.ts`). `runLoop` has no importer outside the package — the only callers are the package's own internals (the agent constructs its loop with it), so the public re-export has zero consumers; `Inbox`/`InboxMessage` likewise reach outside code only through the package's own inbox spec (switchable to the source module). The exports contradict the package's own docs — the inbox module doc says the public surface is `Agent.send()`/`Agent.steer()` — and the [architecture dependency rule](../../../architecture.md): nothing programs against `dsh-agent-loop`; a replacement loop is a different bundle built on `dsh-agent`, not a consumer of this package's internals. `ReactLoopAgent` stays exported (cross-package tests construct it by package name).
3. **`ToolExecutionResult.callId`** (`packages/core/tools/src/index.ts`; the input `ToolExecution.callId` stays). Zero consumers read it. A `tools/execute` wrapper may construct or replace a result, but the registry rejects any `callId` that differs from the immutable execution identity and rebuilds later outcomes from protected snapshots; `tools/post-execute` receives that same execution beside the result, and the observe-only `tools/result` notification receives both as immutable values. The loop independently correlates with its model call's `call.id`, while ACP correlates through the session event's `data.callId`. The result field is therefore a compulsory copy of information already present at every extension point, plus validation and regression tests whose only job is to prove the copy cannot disagree.
The production corpus is `packages/*/*/src`, example sources/config, and runtime scripts. Tests, package READMEs, and RFC prose are evidence of publication but not fixed callers. `cordis_inspect` makes `packages/cordis/tool-cordis/src/api-catalog.ts` model-visible, and `cordis_mount` can invoke injected services through guarded real-service proxies, so catalogued service methods and returned shapes are a genuine dynamic product surface. The table therefore distinguishes absence of a fixed repository caller from unreachability: rows touching catalogued vocabulary intentionally contract what model-written mounts can discover and call, while package-root implementation helpers are not reached through that service façade. Exact-symbol searches produce the following inventory:
| Surface | Production evidence | Simplification |
| --- | --- | --- |
| `SurfaceManager.invalidate()` | Only its unit test calls it; seeding completes before the lazily-created manager exists and the session never replaces its log reference. | Delete it and its impossible wholesale-replacement contract. |
| `ToolExecutionResult.callId` | Every hook already receives the immutable `ToolExecution`; the loop and ACP correlate through the call/session event. No consumer reads the duplicate result field. | Remove the field, copy/mismatch guards, and tests that prove the duplicate cannot disagree. |
| `ReactLoopAgent` root export | Outside-package named imports are tests; production programs against `Agent` and creates/resumes through `ctx.agents`. | Return/interface-type `Agent` and make the concrete loop class package-internal; keep the deliberate synchronous config-only `AgentLoop.create()` path. |
| `workflow-workerthread` protocol/runtime/session re-exports and named `WorkerWorkflowEngine` | Every package-name consumer uses the default engine; the workflow RFC already defines the worker wire protocol as private. | Keep the default plugin class/config contract; drop the duplicate named class export and keep protocol modules source-private. |
| `code-runtime-worker` protocol/bootstrap re-exports | Outside-package production/e2e consumers use `WorkerCodeRuntime` and config, not `BootstrapPort`, `PatchableStream`, or worker message/boot types. | Keep the runtime class/config contract and make its wire/bootstrap vocabulary source-private. |
| ACP translation/presenter root exports | `agentOptions`, `streamSessionEventUpdate`, `todosToPlan`, `ToolPresenter`, `nullToolPresenter`, and `TerminalRendering` have only same-file or ACP-test consumers; the sole outside-package production consumer mounts the plugin namespace. | Keep `name`, `inject`, `Config`, `AcpConfig`, and `apply`; make translation/presentation helpers source-private and test them in-package. |
| `providerWording` and `completedTurnPrefix` root exports | Each has one same-package production caller; only the balanced-prefix helper has a same-package white-box test. | Make them source-private and test provider behavior. |
| `depthOf`, `SubagentDepthError`, `SENSITIVE_ENV_PATTERN`, `waitForExit`, and `exitsWithin` root exports | Production subagent backends consume the in-process runner and subprocess construction/disposal helpers, not these enforcement/test internals. | Keep depth/environment/exit behavior but make the helpers and error/regex source-private; test through spawn and disposal. |
| `PersistenceCoordinator.inits`, backend `inits` accessors, `seedCoversPrefix`, and `assertSerializable` | The accessors exist for white-box tests; `seedCoversPrefix` has no outside production importer; `assertSerializable` has no production caller and duplicates the coordinator append boundary's lossless snapshot. | Observe initialization through `session/flush`, make `seedCoversPrefix` source-private, and delete `assertSerializable`. Keep both backends, `SessionHeader`, and SQLite's version contract. |
| `LlmError.status` and replay status | Adapters/replay populate it, but production branches on stable error code/message and never reads raw status. | Remove the unread field and replay plumbing while preserving error classification. |
| `BlockAssembler.push()` return value | Both production callers ignore the returned completed block. | Return `void`; keep the deliberately public `blocks()`/`message()` contract. |
| `compactRegion`'s separate `session` argument | The fixed caller passes the same object already present as `agent.session`; the model-visible mount API can also call the method, but accepting two identities permits a mounted plugin to provide an incoherent pair. | Keep the manual-region seam while deliberately narrowing it to `agent.session` as the one source of truth. |
| `CompactionResult.startSeq`, `summarySeq`, `endSeq`, and `summary` | The production consumer reads only shadowed range/seq/token accounting; the durable log owns summary and event identity. | Remove the four result echoes while keeping both shared transcript renderers. |
| `BasicCompactService` estimation/summarization visibility | No outside production caller invokes the five methods; the implemented RFC names only `estimateContentTokens()` and `summarize()` as subclass hooks. | Make those two `protected` and the three orchestration-only estimators private. |
| `CodeLogEntry.source`/`level` and `RunCodeMeta.dispatches` | Every production consumer maps logs to text; no presenter/model path reads the other fields or the persisted dispatch count. | Make code-runtime logs strings (or text-only entries) and remove result-meta dispatch plumbing; keep the local counter that mints deterministic dispatch ids. |
| `ToolNotFoundError.toolName`, `SystemPrompt.config`, and `BashTask.command` | Each stored public value has no production reader. | Drop the unread field while retaining error messages, resolved configuration behavior, and task lifecycle. |
| Backend package-root implementation helpers | The exact inventory below is called only through relative same-package imports. Production namespace imports mount the retained plugin contract without reading these properties; named root consumers are tests. | Retain each adapter/provider/service and its config/error contract; stop exporting the listed helper functions/constants at package roots. |
| Consumer package-root implementation helpers | The exact inventory below has only same-package production callers. Production namespace imports mount plugin contracts without reading helper properties; named root consumers are tests. | Retain plugin contracts and stable error codes; move tests to package-local modules or public behavior and stop exporting the listed helpers at package roots. |
### Grouped helper-export inventory
- `dsh-llm-deepseek`: `httpErrorCode`, `serializeMessages`, `serializeRequest`, `DONE`, `parseSse`, `mapFinishReason`, `mapUsage`, and `translate`; `dsh-llm-pi-ai`: `buildModel`, `mapStopReason`, `mapUsage`, `toPiContext`, and `toStreamChunks`.
- `dsh-bash-local`: `DEFAULT_GRACE_MS`, `ENV_OVERRIDES`, `killGroup`, `OutputCollector`, and `runBash`; `dsh-bash-sandbox`: `shellQuote`, `classifyDenial`, and `classifyRunnerFailure`; `dsh-sandbox-local`: `bwrapProfileArgs`, `landlockProfileArgs`, and `seatbeltProfileArgs`. The public mutable test-injection fields and their types are outside this proposal.
- `dsh-fs-local`: `applyLiteralEdit`, `listDirectory`, `probe`, `readForEdit`, `readTextForDiff`, `readWholeText`, `resolveLocalTarget`, `restoreLineEndings`, `streamWholeText`, and `writeFileAtomic`.
- `dsh-web-fetch-local`: `classifyContentType`, `decoderForCharset`, `isSameOrigin`, `parseCharset`, and `validateFetchUrl`; `dsh-web-search-exa`: `mapExaResponse` and `mapExaResult`; `dsh-web-search-deepseek`: `citationSnippets` and `mapAnthropicResponse`; `dsh-web-search-perplexity`: `mapPerplexityResponse` and `mapPerplexityResult`.
- `dsh-tool-fs`: `READ_LIMIT`, `STREAM_MIN_SIZE`, `READ_MAX_BYTES`, `READ_MAX_LINE_LENGTH`, `DIFF_CONTEXT`, `applyReadTool`, `parseReadArgs`, `applyWriteTool`, `formatWriteOutput`, `parseWriteArgs`, `applyEditTool`, `formatEditOutput`, `parseEditArgs`, `buildWindow`, `formatReadOutput`, `computeHunkDiffs`, and `diffsFromMeta`.
- `dsh-tool-web`: `WEB_SEARCH_MAX_RESULTS`, `applyWebSearchTool`, `formatSearchOutput`, `parseSearchArgs`, `presentSearchCall`, `applyWebFetchTool`, `formatFetchOutput`, `parseFetchArgs`, `presentFetchCall`, `renderBody`, and `htmlToMarkdown`; `dsh-timeout-policy`: `toolTimeoutResult`; `dsh-compact-basic`: `resolveConfig`; `dsh-tool-bash`: `renderResult`.
## Proposal
Delete the method and its test; delete the three export lines and their `packages/core/agent-loop/README.md` rows, pointing the inbox spec at the source module; drop the result field from the type, the registry's construction sites (deny, dispatch, `toolErrorResult`, post-execute snapshots), its around-wrapper mismatch validation, the loop's ignore-comment, and the tests that prove the duplicate id cannot matter. The result's consumed `additionalContext` ferry and the execution object's authoritative `callId` stay untouched. Update the `ToolExecutionResult` paste in [tools.md](../../../core-data-structures/tools.md) (and its `scripts/type-equiv.manifest.json` row) and the result-shape row in `packages/core/tools/README.md`; for the `invalidate()` removal, amend the [session-surface RFC](../../implemented/architecture/2026-06-18-session-surface.md)'s full-rebuild-after-wholesale-replacement sentence per [implemented/AGENTS.md](../../implemented/AGENTS.md).
Sequencing: the surface-cache work (tool-pairing balance caching) neither uses nor touches `invalidate`, so that removal can land after or alongside it mechanically. The full execution pipeline carries the immutable execution object through pre-policy, guards, around-dispatch wrappers, post-policy, and final result observation; nothing needs the result to repeat its id.
Remove or demote every row as one bounded coordinated public-surface cleanup. Update package READMEs, JSDoc, generated API/event catalogs, type-equivalence records, exports maps where needed, and tests so they exercise the owning public seam instead of preserving test-only entry points. Do not collapse any capability seam, LLM adapter, persistence backend, or lifecycle quiescence contract.
## Alternatives considered
### Why not keep them?
**Keep test conveniences and self-contained results public.** Public helpers can make white-box tests convenient, self-contained result fields can look ergonomic, and future embedders might want the concrete loop or enumeration methods. Those benefits are hypothetical; today they make every implementation and document explain states that no shipped caller can observe. A real consumer can introduce the smallest contract it needs, with its ownership and failure semantics known.
A future consumer that swaps a session's log in place would want a reset primitive — it re-adds `invalidate` with itself. A replacement-loop author might want to reuse the inbox or the driver — the architecture already answers that a replacement loop is a different bundle. An isolated result-logging listener might want self-contained correlation on the result — the execution object is in scope at every listener, and a field that exists only to be ignored is worse than absent: it invites exactly the orphaned-pairing bug the loop comment warns about.
**Keep every catalogued member for model-written mounts.** The self-referential toolset is a real generic consumer route, not generated-doc noise. Its value comes from an accurate, composable service surface, however, not from preserving duplicate fields or incoherent argument pairs indefinitely; each catalogued contraction above removes a fact available elsewhere on the same execution, agent, or result and updates the API reference in the same change.
## Acceptance criteria
- `invalidate()` and the result `callId` appear only in this RFC; `runLoop`/`Inbox`/`InboxMessage` remain package-internal only — no re-export from the package index and no outside-package importer; the agent-loop README lists only the consumed public surface; the inbox spec imports the source module.
- The complete tool-pipeline contract tests pass with the shrunk result type; the around-wrapper mismatch test, mutation-guard id assertions, and proves-ignored loop test disappear with the duplicate field.
- Exact-symbol searches show no removed surface outside this RFC and any implemented-RFC amendments.
- Every surface listed in this RFC is absent or demoted as specified; deliberately retained extension/test contracts outside the inventory are unchanged.
- Tool execution, compaction, both LLM adapters, both persistence backends, workflow isolation, and agent creation/resume retain their shipped behavior.
- Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass.
## Risks
All three are compile-visible removals with no runtime behavior change on any shipped path.
Most removals are compile-visible but runtime-neutral. The compaction argument cleanup deliberately forbids a session/context mismatch while retaining the manual-region seam. External pre-release embedders and existing model-written mounts may import fewer helpers, pass fewer arguments, or receive narrower result shapes; this is an intentional product-surface contraction, not merely generated-catalog cleanup. The repository is unreleased, so carrying unsupported surface is the larger foundation cost.
docs/rfc/proposed/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md
+32
View File
@@ -0,0 +1,32 @@
# RFC: Drop unconsumed skill provider events
Status: proposed
## Problem
Two skill-registry notifications are produced but have no production listener. The generated producer/consumer matrix and exact event-name searches find only declarations, emit sites, tests, generated catalogs, and prose for `skill/provider-added` and `skill/provider-removed`.
Skill discovery reads the current provider map on demand, provider registration synchronously clears completed catalogs, and the post-await revision check prevents stale discovery from entering the cache. No sibling plugin waits for a skill provider through these events, unlike the live `subagent/provider-added` consumer that tolerates concurrent sibling loading.
`tools/change` and `system-prompt/change` are explicitly outside this proposal. Existing simplification decisions retain them as intentional observation points for live tool and prompt UIs, and self-referential mounted plugins already use `tools/change`. This proposal also leaves `subagent/provider-added`/`removed` unchanged because `tool-subagent` has a production lifecycle consumer.
## Proposal
Delete the two skill-provider declarations and every emit path, rollback-order branch, test, and generated catalog/matrix row that exists only for them. Remove the corresponding skill-registry README/JSDoc contract. Where tests used an event to observe cleanup, assert provider lookup or collected output instead.
Amend the skill-system RFC and package documentation so provider registration is described as direct effect-owned state with cache invalidation, not as a lifecycle notification contract.
## Alternatives considered
**Keep skill-provider notifications for future plugins.** A third-party plugin could observe provider availability, but direct provider registration and on-demand lookup are the extension contract; no current consumer needs a push signal. If a future sibling-load race appears, it can introduce a notification with the identity and readiness semantics that consumer requires, as the subagent registry did.
## Acceptance criteria
- The generated event matrix contains no row for `skill/provider-added` or `skill/provider-removed`.
- Skill discovery, direct runtime registration, provider effect rollback/disposal, cache invalidation, and registry lookup cleanup behave unchanged; listener-triggered rollback disappears with the events.
- `tools/change`, `system-prompt/change`, and the real subagent provider lifecycle consumer remain documented and covered.
- Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass.
## Risks
This removes pre-release skill-provider observation points while retaining both ways third-party plugins contribute skills: direct runtime registration and provider registration. A future consumer that needs live provider availability must add a purpose-built notification rather than relying on these generic events.
docs/rfc/proposed/simplification/2026-07-12-prune-unused-web-seam-fields.md
+30
View File
@@ -0,0 +1,30 @@
# RFC: Prune unused web seam fields
Status: proposed
## Problem
The web capability carries request/result/status values that every shipped implementation populates but no production consumer reads. `WebSearchResult.providerId` and `query` and `WebFetchResult.providerId` are result echoes; `tool-web` formats only content/sources/truncation or final URL/status/body/truncation, and no other runtime reads them. Search providers return `WebProviderStatus.reason`, but resolution checks only `available` and intentionally emits a generic unavailable diagnostic.
`WebFetchRequest.timeoutMs` is likewise never set by a production caller. `tool-web` supplies only the URL, uses the tool definition's timeout plus `exec.signal` for the caller deadline, and relies on the local provider's configured default as a backstop. The unused per-request override forces `web-fetch-local` to expose `maxTimeoutMs`, clamp two timeout sources, and document/test precedence no product path can select. `WebExecContext` is another one-field wrapper: every caller allocates `{ signal }` and every provider immediately unwraps `exec?.signal`; no second execution-control field exists.
## Proposal
Remove the search/fetch `providerId` result echoes and search `query` echo; callers already own the request and provider selection. Shrink provider status to availability alone, preferably a boolean-returning method if that produces the clearest seam. Remove per-request fetch timeout, `maxTimeoutMs`, and their clamp/validation branches while retaining the provider's configurable default timeout and tool-level deadline. Replace `WebExecContext` with a direct optional `AbortSignal` parameter.
Update all web implementations, the model-facing tool, package READMEs/JSDoc, type-equivalence records, and tests. Keep the interface/implementation/consumer package split, provider selection, source citations, final-URL/status data, truncation reporting, and all safety limits.
## Alternatives considered
**Keep self-describing results, per-request deadlines, and an extensible execution-context object.** Result echoes can help generic telemetry, a request timeout can help trusted programmatic callers, and the wrapper leaves room for future controls. No such consumer/second field exists; carrying duplicate identity, a second deadline policy, and wrap/unwrap plumbing through every provider makes the current contract harder to implement and explain. If telemetry or per-call budget control arrives, it should define which deadline wins, where provider identity is observed, and whether multiple controls justify a context object.
## Acceptance criteria
- Every retained web request/result/status field has a production reader or is required to execute the provider request.
- Tool-visible search/fetch output, provider fallback, abort behavior, configured timeout backstop, truncation, and citations remain covered.
- No `maxTimeoutMs`, request-timeout precedence branch, or one-field execution-context wrapper remains.
- Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass.
## Risks
Pre-release programmatic callers lose result provenance echoes and per-request fetch deadlines. The provider still has a deployment-configurable timeout and respects cancellation, so the simplification removes configurability rather than a safety bound.
docs/rfc/proposed/simplification/2026-07-12-simplify-session-log-representation.md
+36
View File
@@ -0,0 +1,36 @@
# RFC: Simplify session-log representation
Status: proposed
## Problem
The session log maintains two representations that cost more machinery than their consumers require: a pseudo-linked surface and custom request-header deltas.
`SurfaceManager` stores the same order in an array, a seq map, and mutable `prev`/`next` links. Production never reads `prev`; compact's sole `next` read is the successor of an array position. Replacement already uses `indexOf`, so the links do not make its dominant operation constant-time. A seq array with linear replacement lookup has the same asymptotic replacement cost and one representation to validate.
The request-header subsystem implements a custom system/tool delta codec and transmission-decision layer even though its contract says deltas are an encoding optimization, not a reconstructability requirement. Retaining the initial/resume full snapshot at each loop-instance boundary, then writing a canonical full `request/header` whenever that instance's assembled header changes, preserves replay while deleting `SystemDelta`, `ToolsDelta`, round-trip fallback, and the durable `request/header-delta` variant. Codec-only vocabulary disappears with the codec, not because its individual arms were invalid.
This proposal deliberately retains append and replacement `sourceEventSeqs`, crash-repair provenance, and all `SessionStartSource` variants: implemented RFCs give those fields an audit/interception role that zero current readers does not overturn.
## Proposal
Make `SurfaceManager.nodes` a `readonly number[]` of event sequences and remove the public `SurfaceNode` shape. Keep the internal replace-generation signal; update tool-pairing balance and compaction callers to use array values/indices for predecessor, successor, and replacement ranges, removing node links and the seq-to-node map. Replace post-anchor header deltas with canonical full changed-header snapshots and remove the delta codec/event/tests; initial and resume anchors remain full snapshots even when the folded header is unchanged.
Amend the session-surface and reconstructable-request RFCs where they describe the removed encoding. Update event types/invariants, request logging/replay, persistence fixtures, generated catalogs, package docs, and snapshots. Replace the codec-only `fallback` reason with an explicit `change` reason for post-anchor full snapshots, distinguishing them from the retained `initial` and `resume` anchors.
`SESSION_FORMAT_VERSION` is deliberately pinned at `0`, so an old v0 log containing `request/header-delta` would otherwise pass the version check and silently lose header changes after the delta fold is deleted. Seed/load validation must reject that legacy event fail-loud at the format boundary; no compatibility fold or migration is added.
## Alternatives considered
**Keep linked nodes and compact deltas for possible scale.** Links could help a future cursor API, and deltas can reduce logs when large tool schemas change by a small amount. No shipped cursor uses the links, while full snapshots trade disk size for substantially simpler correctness. If header volume proves material, compression or a measured canonical-delta scheme can be designed around real traces.
## Acceptance criteria
- `SurfaceManager.nodes` is one ordered seq array with no `SurfaceNode`, link fields, or seq-to-node map; incremental append processing and the internal replace-generation signal remain, while the separate public `invalidate()` deletion stays owned by the dead-surface RFC.
- Replaying full changed-header snapshots reconstructs exactly the same requests; no header-delta event/type/codec remains.
- A v0 seed or persisted log containing legacy `request/header-delta` is rejected before replay, with coverage for JSONL and SQLite load paths.
- New-shape v0 JSONL/SQLite replay, provenance, crash repair, compaction, snapshots, invariants, typecheck, coverage, doc-sync, build, and hygiene pass.
## Risks
Full headers increase log volume, and linear replacement lookup could be slower on very large surfaces. Replacements are already linear because the implementation calls `indexOf`; benchmarks should be added only if real traces show the simpler array is a bottleneck. Because the format version remains `0`, forgetting the explicit legacy-event rejection would be silent data corruption rather than a type error; the fail-loud load test is therefore part of the proposal, not optional cleanup.
docs/rfc/rejected/simplification/2026-07-12-collapse-workflow-to-foreground-core.md
+37
View File
@@ -0,0 +1,37 @@
# RFC: Collapse workflows to the exercised foreground core
Status: rejected — Workflow progress is an intentional observation surface; make it useful through a consumer instead of deleting it.
## Problem
The workflow capability executes foreground JavaScript that composes subagents, but it also carries an unconsumed progress-observation system. No production listener subscribes to any of the six `workflow/*` events; listeners exist only in workflow tests. Nevertheless the seam defines run/phase/agent outcome payloads, the worker sends phase/log/agent lifecycle protocol messages, the host forwards them through a `liveAgents` pairing ledger, and the engine maintains run ids solely to correlate those notifications.
The progress vocabulary is not merely unused; it cannot serve its only named future owner without redesign. `WorkflowRunInfo` contains `{id, meta}` but no parent agent, session, or tool-call identity, while the model-facing tool never exposes the run id. A global ACP listener could not route an event to the correct client session. `meta.phases` is never consulted, `phase(title)` does not validate against it, phase `detail`/`model` and agent `label`/`phase` feed only events, and `whenToUse` is validated and copied but never rendered or selected. `phase()` and `log()` still cross the worker boundary despite having no receiver.
The live handle repeats event-era data after those observers disappear. `WorkflowRun.id` has no non-event consumer, while the tool reads `run.meta.name` only to render a value it already owns as `args.meta.name`; neither belongs on the execution/cancellation handle.
Cancellation also has two public channels for one synchronous start. `WorkflowStartRequest.signal` is passed to the worker host, while the sole production caller separately bridges the same signal to `WorkflowRun.cancel()`. Because `start()` returns the run before control can yield, there is no readiness window that requires request-time cancellation; the duplicate signal adds host listener/disarm state without closing a race.
`WorkflowError.fatal` is the same speculative branch in miniature: every production construction is fatal, `fatal: false` exists only in tests, and combinators already distinguish workflow failures with `instanceof`.
## Proposal
Keep the exercised core: `agent(prompt, { schema, model })`, `parallel`, `pipeline`, `args`, concurrency/agent caps, cancellation, bounded disposal, structured results, worker isolation, and foreground tool collection. Remove all `workflow/*` events and their event-only info/outcome types; remove `phase()`, `log()`, agent `label`/`phase`, phase declarations, `whenToUse`, and their worker messages/host observers; collapse workflow metadata to the name the tool actually uses; remove event-only run ids/meta snapshots and the synthesized agent-end ledger. Shrink `WorkflowRun` to `result`, `cancel()`, and `dispose()`; the tool renders the request-owned name. Remove `WorkflowStartRequest.signal` and the worker host's input-signal listener/disarm state, retaining the caller-owned bridge from its abort signal to `run.cancel()`. Make `WorkflowError` one fatal error class without a boolean mode or `isFatalWorkflowError()` helper.
Amend the implemented dynamic-workflow RFC and update the seam/tool/worker READMEs, tool schema, generated catalogs and package graph, worker type-equivalence records, unit tests, and workflow snapshot/header fixtures. Progress UI work, if commissioned, starts from a correlation contract that names the parent agent/session/tool call instead of reviving this protocol unchanged.
## Alternatives considered
**Keep the prebuilt observation vocabulary for a future UI.** The current shape resembles Claude Code dynamic-workflow metadata, and the host deliberately pairs each forwarded agent start with either the worker's end or a synthesized terminal end. Removing it gives up compatibility-by-shape and makes progress UI a new design task, but the existing payloads still lack routable ownership, so balanced lifecycles alone cannot make the named ACP owner viable without redesign.
## Acceptance criteria
- The workflow public seam contains only execution, cancellation, result, and disposal contracts with a production consumer.
- No workflow event, phase/log protocol message, run-id generator, progress-only metadata, host pairing ledger, or fatal-mode branch remains.
- The run handle has no id/meta echoes, and cancellation has one holder-owned channel after synchronous `start()` returns.
- Parallel/pipeline behavior, caps, cancellation quiescence, worker containment, structured output, and the model-facing workflow scenarios retain coverage.
- Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass.
## Risks
This is a compile-visible contraction of the workflow DSL, event taxonomy, handle, and start request. Existing workflow calls that supply descriptive metadata, and scripts that use `phase`, `log`, or labels, must shrink; programmatic callers bridge their own abort source to the returned handle; and a future observer must add a better-correlated seam. The execution semantics that make workflows useful do not change.
docs/rfc/rejected/simplification/2026-07-12-prune-unused-skill-registry-surface.md
+27
View File
@@ -0,0 +1,27 @@
# RFC: Prune unused skill registry surface
Status: rejected — Direct runtime skill registration is an intentional extension path for third-party plugins.
## Problem
The skill service's embedded-runtime subsystem has zero production caller of `ctx.skills.register()`. It adds a reserved `runtime` provider name, a runtime map/rank/source, duplicate policy, a second revision in cache keys, normalization, disposers, and tests alongside the provider seam every shipped skill already uses. `SkillSummary.whenToUse` and candidate/definition `path` are parsed and copied but never read by a production consumer: the model catalog renders name/description, resource loading uses `resourceBase`, and providers own their locator. The deliberately open `metadata` extension point stays.
## Proposal
Remove `SkillService.register()`, `SkillRegistration`, the runtime pseudo-provider and reserved-name rules, runtime revisions/cache branches, and runtime-only source/rank normalization. Tests that need an embedded skill register a small real provider. Retain `providerRevision` as the in-flight discovery epoch, but key completed catalogs by cwd alone: every provider mutation synchronously clears the cache, and the post-await revision comparison already prevents inserting stale work. Remove `whenToUse`, `SkillCandidate.path`, and `SkillDefinition.path` from the skill contract and local-provider copies while retaining provider locator/root paths; retain `metadata`, `disableModelInvocation`, `source`, `provider`, `locator`, and `resourceBase` as either deliberate extension vocabulary or production-consumed fields.
Amend the skill-system RFC, README, JSDoc, catalogs, and tests. Agent-scoped system-prompt sections, tool providers, and variables are explicitly outside this proposal: the [agent-scope contributor contract](../../implemented/architecture/2026-07-08-agent-scope-contexts.md) intentionally allows all three to be registered during `setup(agentCtx)` through the agent-owned context, so absence of a fixed in-repo scoped registration is not evidence of non-consumption.
## Alternatives considered
**Keep runtime skill registration for embedders.** It is a deliberate synchronous direct-definition convenience in the implemented skill RFC. A small provider wrapper can expose the same embedded data under effect-owned lifetime, but it must implement async `list()`/`get()`, carry provider identity, and accept provider duplicate semantics. The proposal chooses that one regular path over preserving a second ranking, validation, cache-invalidation, and lookup path.
## Acceptance criteria
- Skill collection has one provider-backed path, a cwd-only completed-cache key, and a revision epoch only for in-flight invalidation; retained skill fields have a production reader or a recorded deliberate extension contract.
- Agent-scoped prompt sections, variables, tool providers, tool guards, and structured-output commit behavior in native and Code Mode remain unchanged.
- Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass.
## Risks
This is a compile-visible contraction of the pre-release skill registry. External programmatic `list()`/`get()` consumers lose `whenToUse` routing hints and candidate/definition `path`; the shipped model catalog never renders them, and resource resolution keeps its explicit `resourceBase` plus provider-owned opaque locator, but those fields are not observationally identical. Skill-local frontmatter parsing must continue to preserve and validate the supported metadata schema, and external providers remain able to supply embedded, filesystem, remote, or other skill sources.
docs/testing.md
+1 -1
View File
@@ -25,7 +25,7 @@ An e2e assertion re-runs the command or re-reads the file externally; a keyword
- A plugin shipped via `cordis.yml` needs at least one test through the REAL Loader path: hand-built `ctx.plugin({...})` mounts bypass `unwrapExports` and cannot catch a broken export shape ([postmortem 0001](postmortem/0001-acp-default-export-drops-inject.md); export-shape rules in [packages/AGENTS.md](../packages/AGENTS.md)).
- A guard only guards if the regression actually fails it. For a plugin without `inject` (bundle/composition plugins), a Loader smoke stays green under a broken export shape — add an explicit `expect('default' in mod).toBe(false)` plus an `unwrapExports` round-trip assertion, and prove it: introduce the regression, watch red, revert.
- "Real entry path" means the published artifact: the package `bin` points at built `lib/bin.js` under plain `node`, which tsx masks (settle races, module resolution, a swallowed load failure exiting 0). The same applies to any non-index runtime entry the built package resolves at run time (the worker-thread runtime's sibling `lib/worker.js`). Keep the built-artifact smokes green (`packages/ui/*/tests/built-bin.e2e.ts`, `packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts`), and assert a genuinely-missing config exits non-zero.
- "Real entry path" means the published artifact: the package `bin` points at built `lib/bin.js` under plain `node`, which tsx masks (settle races, module resolution, a swallowed load failure exiting 0). The same applies to any non-index runtime entry the built package resolves at run time (the worker-thread runtime's sibling `lib/worker.cjs`). Keep the built-artifact smokes green (`packages/ui/*/tests/built-bin.e2e.ts`, `packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts`), and assert a genuinely-missing config exits non-zero.
- An e2e that spawns an example from a temp cwd sets `TSX_TSCONFIG_PATH` to the repo-root tsconfig, or it silently falls back to stale built `lib/` ([examples/AGENTS.md](../examples/AGENTS.md)).
## When a snapshot test is required
eslint.config.mjs
+18
View File
@@ -1,4 +1,5 @@
import stylistic from '@stylistic/eslint-plugin'
import sonarjs from 'eslint-plugin-sonarjs'
import tseslint from 'typescript-eslint'
/**
@@ -123,6 +124,23 @@ export default tseslint.config(
},
},
// --- file-local duplication (all owned TypeScript) ---------------------
{
files: ['packages/**/*.ts', 'examples/**/*.ts', 'scripts/**/*.ts'],
plugins: { sonarjs },
rules: {
// Cross-file clones are covered separately by jscpd.
'sonarjs/duplicates-in-character-class': 'error',
'sonarjs/no-all-duplicated-branches': 'error',
'sonarjs/no-duplicate-in-composite': 'error',
'sonarjs/no-duplicate-test-title': 'error',
'sonarjs/no-identical-conditions': 'error',
'sonarjs/no-identical-expressions': 'error',
'sonarjs/no-identical-functions': 'error',
'sonarjs/no-duplicated-branches': 'error',
},
},
// --- formatting (everything we own) -------------------------------------
{
files: ['packages/**/*.ts', 'examples/**/*.ts', 'scripts/**/*.ts', 'eslint.config.mjs'],
examples/acp-agent/advanced.cordis.snapshot.yml
+29
View File
@@ -0,0 +1,29 @@
# Keyless replay counterpart to advanced.cordis.yml. It composes the same
# Code Mode + Cordis + subagent + workflow tree while replacing only the live
# model adapter with the committed multi-session replay script.
- id: base
name: '@cordisjs/plugin-include'
config:
path: ./cordis.yml
patches:
- id: llm-deepseek
name: '@deepseek-ai/dsh-llm-deepseek'
disabled: true
- id: acp-agent
name: '@deepseek-ai/dsh-acp-agent'
config:
model: deepseek-v4-flash
persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
tools:
mode: both
persona: |
You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}.
Verify your work by running the code or tests. Keep answers brief and factual.
- insert:
- id: code-runtime
name: '@deepseek-ai/dsh-code-runtime-worker'
- id: tool-cordis
name: '@deepseek-ai/dsh-tool-cordis'
- id: llm-replay
name: '@deepseek-ai/dsh-llm-replay'
examples/acp-agent/advanced.cordis.yml
+25
View File
@@ -0,0 +1,25 @@
# Advanced ACP snapshot overlay: keep every native tool on the wire, add the
# Code Mode worker, and opt into the self-referential Cordis toolset. The base
# tree already supplies direct spawn subagents and the workflow worker, so this
# composition exercises all four boundaries in one editor-facing ACP turn.
- id: base
name: '@cordisjs/plugin-include'
config:
path: ./cordis.yml
patches:
- id: acp-agent
name: '@deepseek-ai/dsh-acp-agent'
config:
model: deepseek-v4-flash
persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
tools:
mode: both
persona: |
You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}.
Verify your work by running the code or tests. Keep answers brief and factual.
- insert:
- id: code-runtime
name: '@deepseek-ai/dsh-code-runtime-worker'
- id: tool-cordis
name: '@deepseek-ai/dsh-tool-cordis'
examples/acp-agent/tests/acp.snapshot.ts
+16
View File
@@ -26,6 +26,7 @@ const AGENT = {
// replay swap resolves each one's sibling `*cordis.snapshot.yml`).
const CODE_MODE_CONFIG = fileURLToPath(new URL('../code-mode.cordis.yml', import.meta.url))
const BOTH_MODE_CONFIG = fileURLToPath(new URL('../both-mode.cordis.yml', import.meta.url))
const ADVANCED_CONFIG = fileURLToPath(new URL('../advanced.cordis.yml', import.meta.url))
function snapshotModeFromEnv(value: string | undefined): SnapshotSuiteOptions['mode'] {
switch (value) {
@@ -75,6 +76,21 @@ const SCENARIOS: Scenario[] = [
// child runs as a spawn subagent under the worker-thread engine (its session is the
// child fixture), and the tool result carries the script's return value.
{ name: 'workflow-run', hasModelTurn: true, recorded: true, childSessions: 1 },
// ACP-facing counterpart to the packaged Python SDK snapshot: Cordis mounts
// a live marker, Code Mode inspects it through the worker bridge, then a
// direct child and a workflow child run before the mount is disposed. This
// class adds both Code Mode and the opt-in Cordis tools to the base tree, so
// it owns a distinct request-header pin. The scripted fixture is authored:
// the value is deterministic cross-boundary composition, not live-model prose.
{
name: 'advanced-toolchain',
hasModelTurn: true,
recorded: false,
childSessions: 2,
pinsHeader: true,
headerClass: 'advanced',
configPath: ADVANCED_CONFIG,
},
// Hook matrix — one scenario per hook point × its headline Decision outcome,
// across BOTH bridges (Claude `hooks.json`, Codex `codex-hooks.json`, seeded in
// workspace/). The block scenarios need no model call: a UserPromptSubmit hook
examples/acp-agent/tests/snapshots/advanced-toolchain/input.json
+7
View File
@@ -0,0 +1,7 @@
{
"steps": [
{ "op": "initialize" },
{ "op": "newSession" },
{ "op": "prompt", "text": "Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_ACP_OK." }
]
}
examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl
+13
View File
File diff suppressed because one or more lines are too long
examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl
+13
View File
File diff suppressed because one or more lines are too long
examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl
+64
View File
File diff suppressed because one or more lines are too long
examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.golden.jsonl
+14
View File
@@ -0,0 +1,14 @@
{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}}
{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"advanced-mount","title":"Mount plugin into live cordis runtime","kind":"execute","status":"in_progress","rawInput":{"code":"return { name: 'snapshot-marker', apply() {} }"}}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"advanced-mount","status":"completed","content":[{"type":"content","content":{"type":"text","text":"mounted dyn-1 (plugin \"snapshot-marker\", state: active)"}}]}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"advanced-code","title":"return await tools.cordis_inspect({ what: 'dynamic' })","kind":"execute","status":"in_progress","rawInput":"return await tools.cordis_inspect({ what: 'dynamic' })"}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"advanced-code","status":"completed","content":[{"type":"content","content":{"type":"text","text":"## dynamic\n- dyn-1: snapshot-marker [active]"}}]}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"advanced-direct-child","title":"subagent","kind":"other","status":"in_progress","rawInput":{"description":"Check direct child","prompt":"Reply with exactly DIRECT_CHILD_OK and nothing else."}}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"advanced-direct-child","status":"completed","content":[{"type":"content","content":{"type":"text","text":"DIRECT_CHILD_OK"}}]}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"advanced-workflow","title":"workflow: advanced-acp-snapshot","kind":"other","status":"in_progress","rawInput":"phase('Delegate')\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\nreturn { reply }"}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"advanced-workflow","status":"completed","content":[{"type":"content","content":{"type":"text","text":"workflow \"advanced-acp-snapshot\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WORKFLOW_CHILD_OK\"\n}"}}]}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"advanced-unmount","title":"Unmount dyn-1","kind":"delete","status":"in_progress"}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"advanced-unmount","status":"completed","content":[{"type":"content","content":{"type":"text","text":"unmounted dyn-1 (plugin \"snapshot-marker\")"}}]}}}
{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"ADVANCED_ACP_OK"}}}}
{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}}
examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md
+151
View File
@@ -0,0 +1,151 @@
You are an AI agent powered by the DeepSeek Harness SDK.
You are a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}.
Verify your work by running the code or tests. Keep answers brief and factual.
Use the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.
Use the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.
Use the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.
Check the [exit code: N] marker on every bash result; investigate failures before moving on.
Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.
## Writing code for run_code
Pass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:
- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools["my-tool"](args)`. Every call resolves to the tool's text output as a string. Tool arguments must be JSON-serializable.
- A FAILED tool call rejects with an `Error` carrying the tool's error text — `try/catch` it to handle and continue.
- Calls execute sequentially, even under `Promise.all`.
- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.
The available tools:
```ts
declare const tools: {
/** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. */
bash(args: {
/** The bash command to execute. */
command: string;
/** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: "ls" → "List files in current directory"; "git status" → "Show working tree status"; "npm install" → "Install package dependencies". */
description: string;
/** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */
timeoutMs?: number;
/** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */
workdir?: string;
/** Run in the background and return a task id immediately. No timeout applies. */
run_in_background?: boolean;
}): Promise<string>;
/** Ask the executor to kill a running background bash task by task id. */
bash_kill(args: {
/** Task id returned by the bash tool. */
task_id: string;
}): Promise<string>;
/** Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output. */
bash_output(args: {
/** Task id returned by the bash tool. */
task_id: string;
}): Promise<string>;
/** Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. */
cordis_inspect(args: {
/** Limit the report to one section. Omit for all sections. */
what?: "services" | "plugins" | "tools" | "dynamic" | "api" | "events";
}): Promise<string>;
/** Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:"api" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:"events"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:<id>]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:"api" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */
cordis_mount(args: {
/** Body of an async JS function; must `return` the plugin to mount. */
code: string;
}): Promise<string>;
/** Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop). */
cordis_unmount(args: {
/** The dynamic mount id returned by cordis_mount (e.g. "dyn-1"). */
id: string;
}): Promise<string>;
/** Edit an existing UTF-8 text file by replacing literal text. */
edit(args: {
/** Path to edit, resolved by the filesystem backend. */
file_path: string;
/** Literal text to replace. Must match exactly. */
old_string: string;
/** Literal replacement text. Use an empty string to delete the match. */
new_string: string;
/** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */
replace_all?: boolean;
}): Promise<string>;
/** Read a UTF-8 text file and return line-numbered content. */
read(args: {
/** Path to read, resolved by the filesystem backend. */
file_path: string;
/** 1-based first line to return. Defaults to 1. */
offset?: number;
/** Maximum number of lines to return. Defaults to 2000. */
limit?: number;
}): Promise<string>;
/** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */
skill(args: {
/** The exact skill name from the available skills list. */
name: string;
}): Promise<string>;
/** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. */
subagent(args: {
/** A short (3-5 word) description of the delegated task, for display. */
description: string;
/** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */
prompt: string;
}): Promise<string>;
/** Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. */
subagent_fork(args: {
/** A short (3-5 word) description of the delegated task, for display. */
description: string;
/** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */
prompt: string;
}): Promise<string>;
/** Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished). */
todo_write(args: {
/** The COMPLETE task list, replacing any previous list. */
todos: ({
/** What the task is — a short imperative line. */
content: string;
/** pending (not started) | in_progress (now) | completed (done). */
status: "pending" | "in_progress" | "completed";
})[];
}): Promise<string>;
/** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */
workflow(args: {
/** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`). */
script: string;
/** The workflow identity block (plain JSON — never code). */
meta: {
/** Short kebab-case workflow name. */
name: string;
/** One-line description of what the workflow does. */
description: string;
/** Optional guidance on when this workflow applies. */
whenToUse?: string;
/** Optional phase declarations matched by phase() calls. */
phases?: {
/** The phase title phase() calls match by exact string. */
title: string;
/** Optional one-line description of the phase. */
detail?: string;
/** Optional model override this phase is expected to use. */
model?: string;
}[];
};
/** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {"files": [...]}). */
args?: Record<string, unknown>;
}): Promise<string>;
/** Create or fully replace a UTF-8 text file. */
write(args: {
/** Path to write, resolved by the filesystem backend. */
file_path: string;
/** Full UTF-8 text content to write. */
content: string;
}): Promise<string>;
}
```
examples/coding-agent/tests/keyless-smoke.e2e.ts
+2
View File
@@ -25,6 +25,8 @@ import { afterEach, describe, expect, it } from 'vitest'
* product.
*/
// TODO(loader-smoke-harness): extract the shared spawn/tempdir/timeout/EOF
// harness used here, code-mode-keyless-smoke, and cordis-agent's keyless smoke.
// 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.
knip.json
+4 -1
View File
@@ -2,7 +2,7 @@
"$schema": "https://unpkg.com/knip@5/schema.json",
"exclude": ["duplicates"],
"ignoreBinaries": ["bwrap", "sandbox-exec"],
"ignoreWorkspaces": ["vendor/*"],
"ignoreWorkspaces": ["vendor/*", "python/sdk-runtime"],
"workspaces": {
".": {
"entry": [
@@ -86,6 +86,9 @@
"entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"],
"project": ["src/**/*.ts", "tests/**/*.ts"]
},
"packages/ui/jsonrpc-agent": {
"project": ["src/**/*.ts"]
},
"packages/subagent/subagent-spawn": {
"entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"],
"project": ["src/**/*.ts", "tests/**/*.ts"]
package.json
+5 -1
View File
@@ -17,6 +17,7 @@
"typecheck": "tsc -b tsconfig.json",
"lint": "eslint .",
"lint:fix": "eslint . --fix",
"duplication": "jscpd --config .jscpd.json packages scripts",
"test": "vitest run",
"test:coverage": "vitest run --coverage",
"test:e2e": "vitest run --config vitest.e2e.config.ts",
@@ -45,6 +46,7 @@
"verify-translation-pairing": "tsx scripts/verify-translation-pairing.ts",
"verify-doc-budgets": "tsx scripts/verify-doc-budgets.ts",
"verify-node-next-types": "tsx scripts/verify-node-next-types.ts",
"verify-runtime-closure": "tsx scripts/verify-runtime-closure.ts",
"gen-cordis-catalog": "tsx scripts/gen-cordis-catalog.ts",
"gen-rfc-index": "tsx scripts/gen-rfc-index.ts",
"verify-cordis-catalog": "tsx scripts/gen-cordis-catalog.ts --check",
@@ -64,7 +66,7 @@
"verify-module-graph": "tsx scripts/gen-module-graph.ts --check",
"constraints": "tsx scripts/check-workspace-constraints.ts",
"doc-sync": "pnpm run doc-typecheck && pnpm run verify-cordis-catalog && pnpm run verify-cordis-api && pnpm run verify-export-jsdoc && pnpm run verify-tool-catalog && pnpm run verify-config-catalog && pnpm run verify-persistence-catalog && pnpm run verify-doc-graphs && pnpm run verify-scoped-dispatch && pnpm run verify-md-wrap && pnpm run verify-md-links && pnpm run verify-doc-refs && pnpm run verify-package-paths && pnpm run verify-mermaid && pnpm run verify-rfc-classification && pnpm run verify-rfc-format && pnpm run verify-type-equiv && pnpm run verify-translation-pairing && pnpm run verify-doc-budgets",
"hygiene": "pnpm run knip && pnpm run publint && pnpm run constraints && pnpm run verify-node-next-types",
"hygiene": "pnpm run knip && pnpm run publint && pnpm run constraints && pnpm run verify-node-next-types && pnpm run verify-runtime-closure",
"demo:echo": "node --expose-internals --import tsx packages/ui/stdio-agent/src/bin.ts examples/echo-agent/cordis.yml",
"demo:repl": "node --expose-internals --import tsx packages/ui/stdio-agent/src/bin.ts examples/coding-agent/cordis.yml",
"demo:code-mode": "node scripts/demo-code-mode.mjs",
@@ -81,7 +83,9 @@
"@types/node": "^22.20.0",
"@vitest/coverage-v8": "^4.1.8",
"eslint": "^10.4.1",
"eslint-plugin-sonarjs": "^4.1.0",
"fast-check": "^4.8.0",
"jscpd": "^5.0.12",
"jsdom": "29.1.1",
"knip": "^6.16.1",
"lefthook": "^2.1.9",
packages/README.md
+1 -1
View File
@@ -25,7 +25,7 @@ Packages are grouped by modular role at `packages/<group>/<pkg>/`. The group dir
| [`cordis/`](cordis/README.md) | Self-referential runtime toolset: inspect the live runtime's plugins and services, mount/unmount model-written plugins ([design](../docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md)) | Product — stable surface |
| [`hooks/`](hooks/README.md) | Hook bridges + the shared Claude Code / Codex wire-protocol library | Product — stable surface |
| [`session-persistence/`](session-persistence/README.md) | Persistence capability family: the seam + JSONL/SQLite backends | Product — stable surface |
| [`ui/`](ui/README.md) | Editor/client integration surfaces: ACP bridge, app packages, user-approval and user-interaction seams, ask-user tool | Product — stable surface |
| [`ui/`](ui/README.md) | Editor/client integration surfaces: ACP bridge, JSON-RPC SDK server, app packages, user-approval and user-interaction seams, ask-user tool | Product — stable surface |
| [`support/`](support/README.md) | Dev/test/example infrastructure (invariants, replay adapter, subagent mock) | Support — lower compatibility expectations |
| [`util/`](util/README.md) | Low-level zero-dependency utilities shared across groups (branding, Harness home resolution, timeout classification) | Support — small, stable, harness-dep-free |
packages/bash/tool-bash/tests/tools.spec.ts
+13 -22
View File
@@ -104,16 +104,7 @@ async function callUntilText(
throw new Error(`${name} output did not include ${JSON.stringify(expected)}; last text was ${JSON.stringify(last !== undefined ? text(last) : '')}`)
}
class LossyReadBashExecutor extends BashExecutor {
private readonly task: BashTask = {
id: BashTaskId('bash-lossy'),
command: 'fake',
status: 'running',
exitCode: null,
signal: null,
done: Promise.resolve(),
}
abstract class TestBashExecutor extends BashExecutor {
resolve(request: BashExecRequest): BashExecSpec {
return {
command: request.command,
@@ -124,6 +115,17 @@ class LossyReadBashExecutor extends BashExecutor {
sandboxMode: request.sandboxMode,
}
}
}
class LossyReadBashExecutor extends TestBashExecutor {
private readonly task: BashTask = {
id: BashTaskId('bash-lossy'),
command: 'fake',
status: 'running',
exitCode: null,
signal: null,
done: Promise.resolve(),
}
run(): Promise<BashRunResult> {
return Promise.reject(new Error('not used'))
@@ -1170,7 +1172,7 @@ describe('sandbox rendering', () => {
// it anyway: an executor that reports no sandboxMode (fields never
// advertised) whose task nonetheless carries denial facts must render
// the marker without suggesting a lever the schema does not offer.
class FactsOnlyExecutor extends BashExecutor {
class FactsOnlyExecutor extends TestBashExecutor {
private readonly task: BashTask = {
id: BashTaskId('bash-facts'),
command: 'fake',
@@ -1181,17 +1183,6 @@ describe('sandbox rendering', () => {
sandbox: { mode: 'read-only', denied: true },
}
resolve(request: BashExecRequest): BashExecSpec {
return {
command: request.command,
workdir: request.workdir ?? process.cwd(),
timeoutMs: request.timeoutMs ?? 0,
...request.signal ? { signal: request.signal } : {},
owner: request.owner,
sandboxMode: request.sandboxMode,
}
}
run(): Promise<BashRunResult> { return Promise.reject(new Error('not used')) }
start(): BashTask { return this.task }
get(id: string): BashTask | undefined { return id === this.task.id ? this.task : undefined }
packages/code-runtime/code-runtime-worker/README.md
+1 -1
View File
@@ -29,4 +29,4 @@ Every field is validated (positive numbers) and defaulted; there are no other tu
## The worker entry, unbuilt and built
`worker.ts` is deliberately erasable-only TypeScript with type-only cross-package imports: unbuilt (vitest/tsx), the host spawns `src/worker.ts` directly and Node's native type stripping loads it; built, the entry ships as the sibling bundle `lib/worker.js` (its own tsdown entry). The built path is pinned by `tests/built-lib.e2e.ts`, the real-load-path guard from [docs/testing.md](../../../docs/testing.md).
`worker.ts` is deliberately erasable-only TypeScript with type-only cross-package imports: unbuilt (vitest/tsx), the host spawns `src/worker.ts` directly and Node's native type stripping loads it; built, the entry ships as the sibling CommonJS bundle `lib/worker.cjs` (its own tsdown entry). The CommonJS format is required because pkg's VFS Worker hook compiles filesystem-string entries as CommonJS. The host converts either entry URL to a filesystem string before constructing `Worker`, which works through both ordinary Node resolution and that pkg hook. The built path is pinned by `tests/built-lib.e2e.ts`, the real-load-path guard from [docs/testing.md](../../../docs/testing.md).
packages/code-runtime/code-runtime-worker/package.json
+2 -2
View File
@@ -13,14 +13,14 @@
},
"./worker": {
"types": "./lib/types/worker.d.ts",
"default": "./lib/worker.js"
"default": "./lib/worker.cjs"
},
"./src/*": "./src/*",
"./package.json": "./package.json"
},
"files": [
"lib/index.js",
"lib/worker.js",
"lib/worker.cjs",
"lib/types/**/*.d.ts",
"lib/types/**/*.d.ts.map",
"src"
packages/code-runtime/code-runtime-worker/src/index.ts
+10 -6
View File
@@ -14,6 +14,7 @@
import { Worker } from 'node:worker_threads'
import { stripTypeScriptTypes } from 'node:module'
import { fileURLToPath } from 'node:url'
import { Context } from 'cordis'
import z from 'schemastery'
import { CodeRuntime } from '@deepseek-ai/dsh-code-runtime'
@@ -98,16 +99,19 @@ interface LiveRun {
}
/**
* The worker entry module. Source runs unbuilt (`src/worker.ts`, loadable
* The worker entry path. Source runs unbuilt (`src/worker.ts`, loadable
* directly on this repo's Node range via native type stripping — the file
* is erasable-only with type-only relative imports); the built package
* ships it as a sibling bundle (`lib/worker.js`, its own tsdown entry).
* ships it as a sibling CommonJS bundle (`lib/worker.cjs`, its own tsdown
* entry) because pkg's VFS Worker hook compiles string-path entries as
* CommonJS.
* The URL *pathname*'s extension says which world this module is in —
* pathname, because dev-time module runners (vitest) may suffix
* `import.meta.url` with a query string; relative resolution drops it.
* `import.meta.url` with a query string; relative resolution drops it. Worker
* receives a filesystem string so pkg's VFS Worker hook can resolve it.
*/
/* v8 ignore next -- the './worker.js' arm is the built-lib world, unreachable unbuilt by construction; the built-lib e2e pins it. */
const WORKER_URL = new URL(new URL(import.meta.url).pathname.endsWith('.ts') ? './worker.ts' : './worker.js', import.meta.url)
/* v8 ignore next -- the './worker.cjs' arm is the built-lib world, unreachable unbuilt by construction; the built-lib e2e pins it. */
const WORKER_PATH = fileURLToPath(new URL(new URL(import.meta.url).pathname.endsWith('.ts') ? './worker.ts' : './worker.cjs', import.meta.url))
/** Render an unknown thrown value as a message, `Error` or not. */
function messageOf(error: unknown): string {
@@ -273,7 +277,7 @@ export class WorkerCodeRuntime extends CodeRuntime {
maxLogBytes: this.config.maxLogBytes,
maxValueBytes: this.config.maxValueBytes,
}
const worker = new Worker(WORKER_URL, {
const worker = new Worker(WORKER_PATH, {
workerData: bootData,
// Model code gets NO ambient environment — stronger than the scrubbed
// env the defensive-patterns rule requires for spawned commands.
packages/code-runtime/code-runtime-worker/src/worker.ts
+1 -1
View File
@@ -17,4 +17,4 @@ import type { WorkerBootData } from './protocol.ts'
// A worker always has a parent port; guard loudly rather than run detached.
if (!parentPort) throw new Error('dsh-code-runtime-worker: worker entry loaded outside a worker thread')
await runWorkerMain(parentPort, workerData as WorkerBootData, { stdout: process.stdout, stderr: process.stderr })
void runWorkerMain(parentPort, workerData as WorkerBootData, { stdout: process.stdout, stderr: process.stderr })
packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts
+3 -3
View File
@@ -8,7 +8,7 @@ import { describe, expect, it } from 'vitest'
* BUILT-ARTIFACT smoke for the published package (the real-load-path guard
* from docs/testing.md): the unit suite runs `src/` under vitest, where the
* worker entry resolves to `src/worker.ts` — a consumer runs `lib/index.js`
* under plain `node`, where it must resolve the sibling `lib/worker.js`
* under plain `node`, where it must resolve the sibling `lib/worker.cjs`
* bundle instead. This spawns plain `node` (NOT tsx) from inside the package
* directory and imports the package BY NAME, so resolution flows through the
* real `exports` map exactly as it would from a downstream install; the
@@ -21,11 +21,11 @@ import { describe, expect, it } from 'vitest'
*/
const pkgDir = fileURLToPath(new URL('..', import.meta.url))
const built = ['lib/index.js', 'lib/worker.js'].every(file => existsSync(join(pkgDir, file)))
const built = ['lib/index.js', 'lib/worker.cjs'].every(file => existsSync(join(pkgDir, file)))
&& existsSync(join(pkgDir, '../code-runtime/lib/index.js'))
describe.skipIf(!built)('built lib real load path (plain node)', () => {
it('runs a TypeScript program with a binding through lib/index.js and its lib/worker.js entry', async () => {
it('runs a TypeScript program with a binding through lib/index.js and its lib/worker.cjs entry', async () => {
const script = `
const { Context } = await import('cordis')
const { WorkerCodeRuntime } = await import('@deepseek-ai/dsh-code-runtime-worker')
packages/code-runtime/code-runtime-worker/tsdown.config.ts
+5 -3
View File
@@ -3,8 +3,10 @@ import { defineConfig } from 'tsdown'
/**
* Package-shape override (see the root tsdown.config.ts): besides the
* default lib/index.js bundle, the worker BOOTSTRAP ships as its own
* sibling entry — `new Worker(new URL('./worker.js', import.meta.url))`
* loads it as a file, so it cannot be part of the index bundle. TWO
* sibling CommonJS entry — `new Worker(fileURLToPath(new URL('./worker.cjs', import.meta.url)))`
* loads it as a file, so it cannot be part of the index bundle. pkg's VFS
* Worker hook compiles string-path entries as CommonJS, so an ESM worker is
* not viable inside the executable. TWO
* single-entry builds, not one two-entry build: a multi-entry build emits
* the shared bootstrap module as a `lib/bootstrap-*.js` chunk both bundles
* import, which the package.json `files` whitelist (deliberately exact)
@@ -25,7 +27,7 @@ export default defineConfig([
{
entry: ['lib/types/worker.js'],
outDir: 'lib',
format: ['esm'],
format: ['cjs'],
platform: 'node',
target: 'es2024',
fixedExtension: false,
packages/core/agent/src/index.ts
+2
View File
@@ -202,6 +202,8 @@ interface FactorySlot {
*/
export class AgentRegistry extends Service {
private store = new Map<AgentId, AgentEntry>()
// TODO(agent-entry-mirror): derive exact-object checks from store.get(agent.id)
// plus entry.agent identity; this WeakMap mirrors the authoritative id map.
private entries = new WeakMap<Agent, AgentEntry>()
private factory: FactorySlot | undefined
packages/core/system-prompt/src/index.ts
+2
View File
@@ -103,6 +103,8 @@ export interface PromptSection {
export interface AssembledSection {
/** The contributing section's unique name. */
name: string
// TODO(assembled-section-order): drop this output field; registry order has
// already sorted the array, and no production renderer/listener reads it.
/** The contributing section's order (sections arrive sorted ascending). */
order: number
/** The resolved (but not yet interpolated) section text. */
packages/guard/repeat-tool-guard/src/index.ts
+2
View File
@@ -202,6 +202,8 @@ export function apply(ctx: Context, config: Config): void {
throw new Error(`repeat-tool-guard: invalid argumentsPreviewChars ${argumentsPreviewChars} — must be an integer >= 1`)
}
// TODO(agent-keyed-repeat-chain): key a WeakMap by the Agent itself; that
// removes the disposal-only status listener and cannot collide on id reuse.
const chains = new Map<AgentId, Chain>()
/** Whether a tool participates in the chain (untracked calls are transparent: they neither count nor reset). */
packages/hooks/hooks-codex/src/config.ts
+4
View File
@@ -53,6 +53,9 @@ export function parseCodexConfig(raw: unknown): ParsedCodexConfig {
for (const event of CODEX_EVENTS) {
const rawGroups = hooksMap[event]
// Matcher-group parsing remains dialect-local because the supported hook
// shapes and skip reasons differ from Claude Code's.
/* jscpd:ignore-start */
if (!Array.isArray(rawGroups)) continue
const groups: MatcherGroup[] = []
for (const rawGroup of rawGroups) {
@@ -64,6 +67,7 @@ export function parseCodexConfig(raw: unknown): ParsedCodexConfig {
if (!hook) continue
const type = typeof hook.type === 'string' ? hook.type : 'command'
if (type !== 'command') { skipped.push({ event, reason: `unsupported "${type}" hook` }); continue }
/* jscpd:ignore-end */
if (hook.async === true) { skipped.push({ event, reason: 'async hook' }); continue }
if (typeof hook.command !== 'string') continue
// Codex accepts `timeout` or the `timeoutSec` alias.
packages/hooks/hooks-codex/src/index.ts
+16
View File
@@ -15,6 +15,9 @@
* @module @deepseek-ai/dsh-hooks-codex
*/
// Each dialect bridge keeps its complete dependency list visible at the entry
// point; a cross-package facade for imports alone would add indirection.
/* jscpd:ignore-start */
import { readFileSync } from 'node:fs'
import type { Context } from 'cordis'
import z from 'schemastery'
@@ -36,6 +39,7 @@ import {
type MergedHookOutcome,
} from '@deepseek-ai/dsh-hook-protocol'
import { parseCodexConfig, type CodexHookConfig } from './config.ts'
/* jscpd:ignore-end */
export const name = 'hooks-codex'
export const inject = ['bash']
@@ -154,6 +158,9 @@ export function apply(ctx: Context, config: Config): void {
output.additionalContext = output.stdout
}
outputs.push(output)
// Execution and decision mapping remain in each bridge so dialect
// differences stay explicit at their owning seam.
/* jscpd:ignore-start */
if (output.systemMessage !== undefined) {
ctx.logger.warn(`hooks-codex: ${point} hook emitted a systemMessage, which is not yet surfaced (ignored)`)
}
@@ -203,12 +210,14 @@ export function apply(ctx: Context, config: Config): void {
if (context) agent.inject(context.content, { source: context.source })
})
.catch((error: unknown) => { ctx.logger.warn(`hooks-codex: SessionStart hook failed: ${String(error)}`) }))
/* jscpd:ignore-end */
})
// UserPromptSubmit → PromptDecision. Codex can only BLOCK (no allow/ask).
ctx.on('agent/prompt-submit', async (agent, content, _source, next): Promise<PromptDecision> => {
const turn = lastTurn(agent)
const merged = await runPoint('UserPromptSubmit', '', { ...turnBase(ctx, agent, 'UserPromptSubmit', model), prompt: blocksToText(content) }, { agent, turn, plainStdoutAsContext: true })
/* jscpd:ignore-start */
if (merged.decision === 'deny') return { kind: 'block', reason: merged.reason ?? 'blocked by UserPromptSubmit hook' }
// Context alone is not a veto: DELEGATE so a later prompt-submit listener can
// still block/rewrite, then fold our context onto its decision.
@@ -226,6 +235,7 @@ export function apply(ctx: Context, config: Config): void {
ctx.on('tools/pre-execute', async (exec, next): Promise<PreToolDecision> => {
const turn = lastTurn(exec.agent)
const merged = await runPoint('PreToolUse', exec.name, preToolPayload(ctx, exec, model), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} })
/* jscpd:ignore-end */
if (merged.decision === 'deny') return { kind: 'deny', reason: merged.reason ?? 'blocked by PreToolUse hook' }
return next()
})
@@ -233,6 +243,7 @@ export function apply(ctx: Context, config: Config): void {
// PostToolUse → PostToolDecision (block with feedback, or attach context).
ctx.on('tools/post-execute', async (exec, result, next): Promise<PostToolDecision> => {
const turn = lastTurn(exec.agent)
/* jscpd:ignore-start */
const merged = await runPoint('PostToolUse', exec.name, postToolPayload(ctx, exec, result, model), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} })
const context = contextFrom(merged)
if (merged.decision === 'deny') {
@@ -258,6 +269,7 @@ export function apply(ctx: Context, config: Config): void {
// loop-guard (stop_hook_active + a max-consecutive cap) is deferred.
ctx.on('agent/turn-continuation', async (agent, turn, _default, next): Promise<ContinuationDecision> => {
const merged = await runPoint('Stop', '', { ...turnBase(ctx, agent, 'Stop', model), stop_hook_active: false, last_assistant_message: null }, { agent, turn })
/* jscpd:ignore-end */
if (merged.decision === 'deny') {
// A blocking Stop hook forces continuation; a block with no reason (exit 2,
// empty stderr) still forces it — fall back to a generic steering line
@@ -272,6 +284,9 @@ export function apply(ctx: Context, config: Config): void {
// --- Codex DIALECT payloads: snake_case, model on every event, turn_id on
// turn-scoped events. ---
// These small payload helpers intentionally remain next to the dialect shape;
// sharing them would pull bridge-only agent/LLM dependencies into hook-protocol.
/* jscpd:ignore-start */
function lastTurn(agent: Agent | undefined): number {
if (!agent) return 0
const last = [...agent.session.events].findLast(e => e.type === 'turn/start')
@@ -284,6 +299,7 @@ function lastTurn(agent: Agent | undefined): number {
function blocksToText(content: ContentBlock[]): string {
return content.filter((b): b is Extract<ContentBlock, { type: 'text' }> => b.type === 'text').map(b => b.text).join('')
}
/* jscpd:ignore-end */
/** Base fields on every Codex payload (no turn_id). */
function base(ctx: Context, agent: Agent | undefined, event: string, model: string): Record<string, unknown> {
packages/session-persistence/session-persistence-jsonl/src/index.ts
+4
View File
@@ -89,6 +89,9 @@ export class SessionPersistenceJsonl extends SessionPersistence implements Persi
this.coordinator = new PersistenceCoordinator<number>(this.ctx, this)
}
// Each backend keeps the typed service surface beside its storage hooks;
// extracting these trivial forwards would add an inheritance seam.
/* jscpd:ignore-start */
// --- SessionPersistence service surface (delegated to the coordinator) ---
/** Resolve the absolute target path without touching the filesystem. */
@@ -121,6 +124,7 @@ export class SessionPersistenceJsonl extends SessionPersistence implements Persi
get inits(): Map<Session, Promise<void>> {
return this.coordinator.inits
}
/* jscpd:ignore-end */
// --- PersistenceBackend hooks (the file-bytes storage primitives) ---
packages/support/invariants/tests/invariants.spec.ts
+1 -1
View File
@@ -874,7 +874,7 @@ describe('scoped-dispatch invariants', () => {
['tools/result', [{ callId: 'c', name: 't', arguments: {}, agent }, { callId: 'c', content: [], isError: false }]],
]
for (const [event, args] of rows) {
const subject = event.startsWith('tools/') ? agent : agent
const subject = agent
expect(() => { (ctx.emit as (...a: unknown[]) => void)(scopeTarget(agent, subject), event, ...args) },
`${event} with matching carrier`).not.toThrow()
expect(() => { (ctx.emit as (...a: unknown[]) => void)(scopeTarget(agent, other), event, ...args) },
packages/support/llm-replay/tests/llm-replay.spec.ts
+10 -20
View File
@@ -54,6 +54,16 @@ function chunkEvent(seq: number, turn: number, step: number, chunk: StreamChunk)
let dir: string
let file: string
/** Write a session log file and return its path. */
function writeSession(filename: string, header: { id: string; createdAt: number }, calls: StreamChunk[][]): string {
let seq = 1
const events: SessionEvent[] = []
calls.forEach((chunks, step) => { for (const c of chunks) events.push(chunkEvent(seq++, 1, step + 1, c)) })
const path = join(dir, filename)
writeFileSync(path, sessionJsonl(events, header), 'utf8')
return path
}
beforeEach(() => {
dir = mkdtempSync(join(tmpdir(), 'llm-replay-spec-'))
file = join(dir, 'session.jsonl')
@@ -391,16 +401,6 @@ describe('parseSessionHeader', () => {
})
describe('loadSessionScripts', () => {
/** Write a session log file and return its path. */
function writeSession(filename: string, header: { id: string; createdAt: number }, calls: StreamChunk[][]): string {
let seq = 1
const events: SessionEvent[] = []
calls.forEach((chunks, step) => { for (const c of chunks) events.push(chunkEvent(seq++, 1, step + 1, c)) })
const path = join(dir, filename)
writeFileSync(path, sessionJsonl(events, header), 'utf8')
return path
}
it('returns one primary script for a single-session scenario', () => {
const f = writeSession('session.jsonl', { id: 'p', createdAt: 100 }, [TEXT_CHUNKS])
const scripts: SessionScript[] = loadSessionScripts({ file: f })
@@ -508,16 +508,6 @@ describe('installLlmReplay (per-session keying)', () => {
{ type: 'finish', reason: { kind: 'stop' } },
]
/** Write a session log file and return its path. */
function writeSession(filename: string, header: { id: string; createdAt: number }, calls: StreamChunk[][]): string {
let seq = 1
const events: SessionEvent[] = []
calls.forEach((chunks, step) => { for (const c of chunks) events.push(chunkEvent(seq++, 1, step + 1, c)) })
const path = join(dir, filename)
writeFileSync(path, sessionJsonl(events, header), 'utf8')
return path
}
const live = (id: string): GenerateOptions =>
({ model: 'm', messages: [], sessionId: id as NonNullable<GenerateOptions['sessionId']> })
packages/ui/README.md
+5 -3
View File
@@ -10,10 +10,12 @@ Integrations that expose the agent to an external editor or client. These are **
| `tool-ask-user/` | Model-facing `ask_user_question` tool over `ctx.userInteraction` | (registers on `ctx.tools`) |
| `stdio-agent/` | Terminal stdio chat APP: the agent-core spine + console logger + readline UI + a pre-created `main` agent, with a `bin` | (composition + `bin`) |
| `acp-agent/` | ACP server APP: the agent-core spine + JSONL persistence + the `acp` bridge (no stdout logger), with a `bin` | (composition + `bin`) |
| `app-boot/` | Shared boot glue for the two app bins: `.env` loading, fail-loud Loader guards, snapshot-aware config resolution, the settle-the-tree boot sequence | (library for the bins) |
| `jsonrpc/` | Stdio JSON-RPC SDK server plugin: serves `HarnessSdkServer` to out-of-process SDK clients (the Python SDK) on the process stdio | (drives `ctx.agents`) |
| `jsonrpc-agent/` | JSON-RPC SDK server APP: a bin-only boot of an external `cordis.yml` whose `jsonrpc` entry is the serving face; the single-exe runtime entrypoint | (`bin` only) |
| `app-boot/` | Shared boot glue for the app bins: `.env` loading, fail-loud Loader guards, snapshot-aware config resolution, the settle-the-tree boot sequence | (library for the bins) |
A UI integration is a client-driver plugin, not a loop change and not a capability seam: it consumes the existing `agent/*` event taxonomy and the `dsh-agent` factory. The readline UI is the unstructured analogue of the `acp` bridge and lives INSIDE the stdio app (the `stdio-chat` module of [`stdio-agent/`](stdio-agent/README.md)): it is scaffolding for that one front door, not an independently swappable integration, so it carries no package boundary of its own.
A UI integration is a client-driver plugin, not a loop change and not a capability seam: it consumes the existing `agent/*` event taxonomy and the `dsh-agent` factory. The `jsonrpc` plugin is the SDK-client sibling of the `acp` bridge (a JSON-RPC server over `ctx.agents` for out-of-process SDK clients rather than editors). The readline UI is the unstructured analogue of the `acp` bridge and lives INSIDE the stdio app (the `stdio-chat` module of [`stdio-agent/`](stdio-agent/README.md)): it is scaffolding for that one front door, not an independently swappable integration, so it carries no package boundary of its own.
`user-approval`, `user-interaction`, and `tool-ask-user` live here because asking a human is a UI-backed product affordance, not part of the providerless core spine. `user-approval` owns the one-shot `ctx.approval` decision mechanism and its policy tier; answerers remain with their UI channel owners. `user-interaction` remains provider-neutral (`ctx.userInteraction`), while `tool-ask-user` is its model-facing consumer and the app/bridge packages provide concrete providers.
`stdio-agent` and `acp-agent` are the two **app packages**: each composes the [`core/agent-core`](../core/agent-core/README.md) spine with its coupled front-door cluster (and owns the boot `bin`), so a leaf `cordis.yml` is the swappable backends plus one app entry plus any optional product tools. They live in `ui/` because each IS a user-facing front door; the stdout-purity coupling (logger vs. no logger) becomes a property of the artifact rather than a leaf convention.
`stdio-agent` and `acp-agent` are the two composing **app packages**: each composes the [`core/agent-core`](../core/agent-core/README.md) spine with its coupled front-door cluster (and owns the boot `bin`), so a leaf `cordis.yml` is the swappable backends plus one app entry plus any optional product tools. `jsonrpc-agent` is the third app but bin-only — no composition plugin, because the SDK runtime's hard semantic is that the external `cordis.yml` composes everything, the serving `jsonrpc` entry included. They live in `ui/` because each IS a user-facing front door; the stdout-purity coupling (logger vs. no logger) becomes a property of the artifact rather than a leaf convention.
packages/ui/acp-agent/src/index.ts
+6
View File
@@ -66,6 +66,9 @@ export interface Config {
skills?: agentCore.SkillConfig
}
// Each front door owns a complete, directly readable config schema; extracting
// the common fields would make two small app contracts depend on a new facade.
/* jscpd:ignore-start */
export const Config: z<Config> = z.object({
model: z.string().required(),
persona: z.string(),
@@ -75,9 +78,12 @@ export const Config: z<Config> = z.object({
toolOrder: z.array(z.string()).default(undefined as unknown as string[]),
tools: ToolRegistry.Config,
dshHome: z.string(),
// TODO(single-default-literal): share this schema default and the defensive
// apply() fallback through one named constant while retaining both boundaries.
persistenceRoot: z.string().default('./.sessions'),
skills: agentCore.SkillConfigSchema,
})
/* jscpd:ignore-end */
/**
* Compose the spine with the ACP front door. The agent-core bundle pre-creates
packages/ui/acp/src/index.ts
+7 -2
View File
@@ -107,6 +107,8 @@ export const name = 'acp'
// because `initialize` advertises `loadSession: true`. `tools` lets a tool own
// how its calls render (`presentCall`/`presentResult`); the bridge looks up the
// definition by name and falls back to a generic presentation when absent.
// TODO(acp-session-inject): drop `sessions`; this bridge never reads
// ctx.sessions, and agent/session ownership is already behind ctx.agents.
export const inject = ['agents', 'sessions', 'sessionPersistence', 'tools', 'userInteraction']
/**
@@ -352,10 +354,13 @@ export function apply(ctx: Context, config: AcpConfig): void {
// this warn sink so a throwing tool presenter is logged, not propagated.
const makePresenter = (agent?: Agent): ToolPresenter => new ToolPresenter(tools, (message) => { logger.warn(message) }, agent)
// TODO(derive-acp-session-id): derive an event's id from agent.session and
// verify sessions.get(id)?.agent === agent; then remove this reverse map and
// SessionRecord.sessionId, whose sole read duplicates the same identity.
// Live sessions keyed by id (RFC 011 multi-session), plus an agent→sessionId
// reverse map so `agent/*` events (which carry only the Agent) demux in O(1).
// The two stay in lockstep: a record is added to `sessions` and the agent to
// `bySession` together, and removed together.
// The forward record and weak reverse entry are installed together; removing
// the record releases its strong Agent reference, so the WeakMap entry expires.
const sessions = new Map<SessionId, SessionRecord>()
const bySession = new WeakMap<Agent, SessionId>()
// Session ids whose `session/load` is mid-`resume()` (the slot is reserved
packages/ui/acp/tests/stream-update.spec.ts
+15 -29
View File
@@ -30,6 +30,21 @@ function registryOf(...tools: ToolDefinition[]): Pick<ToolRegistryType, 'get'> {
return { get: name => map.get(name) }
}
function updatesWith(presenter: ToolPresenter, ...events: SessionEvent[]): SessionNotification['update'][] {
const out: SessionNotification['update'][] = []
for (const event of events) streamSessionEventUpdate(SessionId('s1'), event, n => out.push(n.update), presenter)
return out
}
async function fsCtx(): Promise<Context> {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(FsLocal)
await ctx.plugin(ToolFs)
return ctx
}
function evt<T extends SessionEvent['type']>(type: T, data: Extract<SessionEvent, { type: T }>['data']): SessionEvent {
return { type, seq: 0, time: 0, data } as SessionEvent
}
@@ -181,12 +196,6 @@ describe('ToolPresenter (tool-owned presentation via the tool registry)', () =>
}),
}
function updatesWith(presenter: ToolPresenter, ...events: SessionEvent[]): SessionNotification['update'][] {
const out: SessionNotification['update'][] = []
for (const event of events) streamSessionEventUpdate(SessionId('s1'), event, n => out.push(n.update), presenter)
return out
}
it('tool/call uses the tool: description→title, command→rawInput, tool kind', () => {
const presenter = new ToolPresenter(registryOf(bashLike))
const [update] = updatesWith(presenter, evt('tool/call', {
@@ -627,21 +636,6 @@ describe('result-time diff card (REAL fs edit tool → tool_call_update diff blo
// result card the bridge forwards as `{ type: 'diff' }` content blocks. Uses
// the REAL tool (not a stand-in) per the anti-mock convention, mirroring the
// call-side diff test above.
async function fsCtx(): Promise<Context> {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(FsLocal)
await ctx.plugin(ToolFs)
return ctx
}
function updatesWith(presenter: ToolPresenter, ...events: SessionEvent[]): SessionNotification['update'][] {
const out: SessionNotification['update'][] = []
for (const event of events) streamSessionEventUpdate(SessionId('s1'), event, n => out.push(n.update), presenter)
return out
}
it('forwards the applied-hunk meta onto the wire as tool_call_update diff content', async () => {
const ctx = await fsCtx()
const presenter = new ToolPresenter(ctx.tools)
@@ -739,14 +733,6 @@ describe('relative-path display titles (bridge relativizes the title against the
// diff paths RAW. Drive it with the REAL fs tools so the title/locations come
// from the shipping presentCall, and pass an ABSOLUTE file path (which a real
// editor forwards). The presenter is pure/args-only; the cwd is known only here.
async function fsCtx(): Promise<Context> {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(FsLocal)
await ctx.plugin(ToolFs)
return ctx
}
function callUpdate(ctx: Context, sessionCwd: string | undefined, name: string, args: unknown): SessionNotification['update'] {
const presenter = new ToolPresenter(ctx.tools)
const out: SessionNotification['update'][] = []
packages/ui/jsonrpc-agent/README.md
+17
View File
@@ -0,0 +1,17 @@
# @deepseek-ai/dsh-jsonrpc-agent
The **JSON-RPC SDK server app bin** (`dsh-jsonrpc-agent`): boot a harness from an externally supplied `cordis.yml` and let its [`@deepseek-ai/dsh-jsonrpc`](../jsonrpc/README.md) entry serve SDK clients over newline-delimited JSON-RPC on stdio. Structurally the SDK-runtime sibling of [`acp-agent`](../acp-agent/README.md)'s bin, but bin-only: there is no composition plugin here, because "the plugins that actually start come from the external config" is the SDK runtime's hard semantic — the leaf `cordis.yml` composes the spine, the backends, AND the serving face. This package is the entrypoint of the single-exe distribution (its `lib/bin.js` is what the packaged executable runs) — see [docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md](../../../docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md).
## Config discovery
Two channels, environment first: `$DSH_CORDIS_CONFIG` (the existing SDK-client convention, wins), then the `argv[2]` positional path (`dsh-jsonrpc-agent <path/to/cordis.yml>`, the human channel, isomorphic to `dsh-acp-agent`). An empty value counts as absent on either channel. Neither given, or the path missing on disk: the bin prints a one-line usage naming both channels to stderr and exits 1 — there is no default `./cordis.yml` and no built-in fallback config. A config that names a plugin which fails to load fails loud through the shared [`dsh-app-boot`](../app-boot/README.md) guards (`assertEntriesLoaded` + the unhandled-rejection handler), never a silent half-boot. There is no `DSH_SNAPSHOT` handling: this protocol is not part of the ACP snapshot tier.
Note the deliberate flip side of config-decides-everything: a config that loads no `dsh-jsonrpc` entry boots fine and serves nothing — the bin cannot know which plugin is "the server".
## Exit lifecycle
The bin owns the PROCESS-level exits: stdin EOF (the SDK client is gone — an in-flight turn is deliberately cut off, see the risk note in docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md) and `SIGTERM` dispose the root context to quiescence and exit 0; `SIGINT` does the same but exits 130. The PROTOCOL-level exit — a `shutdown` JSON-RPC request answered first, then exit 0 — is owned by the `dsh-jsonrpc` plugin, which holds the server and transport; the two paths are individually idempotent and safe to race.
## stdout is the protocol
stdout carries only JSON-RPC frames; the bin and the app-boot guards write diagnostics to stderr only, and the booted config must load no stdout logger (see the `dsh-jsonrpc` README).
packages/ui/jsonrpc-agent/package.json
+41
View File
@@ -0,0 +1,41 @@
{
"name": "@deepseek-ai/dsh-jsonrpc-agent",
"description": "JSON-RPC SDK server app bin: boots an externally supplied cordis.yml (DSH_CORDIS_CONFIG or argv, no built-in fallback) whose dsh-jsonrpc entry serves SDK clients over stdio; the single-exe runtime entrypoint",
"version": "0.0.1",
"private": true,
"type": "module",
"main": "lib/index.js",
"types": "lib/types/index.d.ts",
"bin": {
"dsh-jsonrpc-agent": "lib/bin.js"
},
"exports": {
".": {
"types": "./lib/types/index.d.ts",
"default": "./lib/index.js"
},
"./bin": {
"types": "./lib/types/bin.d.ts",
"default": "./lib/bin.js"
},
"./src/*": "./src/*",
"./package.json": "./package.json"
},
"files": [
"lib/index.js",
"lib/bin.js",
"lib/types/**/*.d.ts",
"lib/types/**/*.d.ts.map",
"src"
],
"license": "BSD-3-Clause",
"dependencies": {
"@deepseek-ai/dsh-app-boot": "workspace:^"
},
"peerDependencies": {
"cordis": "^4.0.0-rc.6"
},
"devDependencies": {
"cordis": "^4.0.0-rc.6"
}
}
packages/ui/jsonrpc-agent/src/bin.ts
+75
View File
@@ -0,0 +1,75 @@
#!/usr/bin/env node
/**
* The `dsh-jsonrpc-agent` bin: boot a harness from an externally supplied
* `cordis.yml` whose `@deepseek-ai/dsh-jsonrpc` entry serves SDK clients over
* newline-delimited JSON-RPC on stdio. The shared boot glue — `.env` loading,
* the fail-loud Loader guards, the settle-the-tree boot sequence — lives in
* {@link @deepseek-ai/dsh-app-boot}, shared with the stdio/ACP bins; this bin
* owns only config discovery and the process-level exit lifecycle:
*
* - Config discovery is `$DSH_CORDIS_CONFIG` (the existing SDK-client
* convention, wins) or the `argv[2]` positional path (the human channel,
* isomorphic to `dsh-acp-agent`); an empty value counts as absent. Neither
* given, or the path missing on disk, prints the one-line usage to stderr
* and exits 1. No built-in fallback — the external config IS the deployment
* (docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md).
* No `DSH_SNAPSHOT` handling: this
* protocol is not part of the ACP snapshot tier.
* - stdin EOF (the SDK client is gone) and SIGTERM dispose the root context
* to quiescence and exit 0; SIGINT does the same but exits 130. The
* `shutdown` JSON-RPC request's answer-then-exit-0 path is owned by the
* `dsh-jsonrpc` plugin, which holds the server (see its README).
*
* IMPORTANT: stdout is the JSON-RPC channel. Diagnostics go to STDERR only (a
* stray stdout write corrupts the protocol frames), which the app-boot guards
* already honor.
*
* @module @deepseek-ai/dsh-jsonrpc-agent/bin
*/
import { existsSync } from 'node:fs'
import { boot, installFailLoud, loadEnv, resolveConfigPath } from '@deepseek-ai/dsh-app-boot'
const NAME = 'dsh-jsonrpc-agent'
/* v8 ignore start -- thin self-executing composition over the unit-tested
dsh-app-boot helpers; the serving lifecycle it boots is unit-tested in
@deepseek-ai/dsh-jsonrpc, and the composed artifact is exercised by the
single-exe acceptance drive (docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md) */
installFailLoud(NAME)
loadEnv(NAME)
// Env wins over the positional argument; an empty value on either channel
// counts as absent. There is deliberately NO default `./cordis.yml`: "the
// plugins that actually start come from an explicit external config" is a
// hard semantic of the SDK runtime.
const fromEnv = process.env['DSH_CORDIS_CONFIG']
const fromArgv = process.argv[2]
const requested = fromEnv !== undefined && fromEnv !== ''
? fromEnv
: fromArgv !== undefined && fromArgv !== '' ? fromArgv : undefined
const configPath = requested === undefined ? undefined : resolveConfigPath(requested, undefined)
if (configPath === undefined || !existsSync(configPath)) {
process.stderr.write(
`usage: ${NAME} <path/to/cordis.yml> (or set DSH_CORDIS_CONFIG=<path>, which wins); the config is required — there is no built-in fallback\n`,
)
process.exit(1)
}
const ctx = await boot(NAME, configPath)
let exiting = false
async function disposeAndExit(code: number): Promise<void> {
if (exiting) return
exiting = true
try {
await ctx.fiber.dispose()
} finally {
process.exit(code)
}
}
process.stdin.on('end', () => { void disposeAndExit(0) })
process.on('SIGTERM', () => { void disposeAndExit(0) })
process.on('SIGINT', () => { void disposeAndExit(130) })
/* v8 ignore stop */
packages/ui/jsonrpc-agent/src/index.ts
+14
View File
@@ -0,0 +1,14 @@
/**
* The `dsh-jsonrpc-agent` app package IS its bin (see `./bin.ts`): config
* discovery plus the process-level exit lifecycle around a booted
* `cordis.yml`. This module deliberately exports nothing — unlike the
* stdio/ACP app packages there is no composition plugin here, because the
* serving face is the {@link @deepseek-ai/dsh-jsonrpc} plugin the external
* config loads like any other entry (which plugins actually start is the
* config's decision, the hard semantic of the SDK runtime; see
* docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md).
*
* @module @deepseek-ai/dsh-jsonrpc-agent
*/
export {}
packages/ui/jsonrpc-agent/tsconfig.json
+21
View File
@@ -0,0 +1,21 @@
{
"extends": "../../../tsconfig.base.json",
"compilerOptions": {
"rootDir": "src",
"outDir": "lib/types"
},
"include": [
"src"
],
"references": [
{
"path": "../../../vendor/cordis"
},
{
"path": "../../../vendor/loader"
},
{
"path": "../app-boot"
}
]
}
packages/ui/jsonrpc-agent/tsdown.config.ts
+19
View File
@@ -0,0 +1,19 @@
import { defineConfig } from 'tsdown'
/**
* jsonrpc-agent ships TWO entries: the doc-only module (`index`) and the CLI
* `bin` (`bin`), the latter referenced by package.json `bin`/`exports["./bin"]`.
* The root tsdown builds only `lib/types/index.js`, so this override adds
* `lib/types/bin.js`. Declarations come from `tsc -b` (dts: false),
* matching every package.
*/
export default defineConfig({
entry: ['lib/types/index.js', 'lib/types/bin.js'],
outDir: 'lib',
format: ['esm'],
platform: 'node',
target: 'es2024',
fixedExtension: false,
dts: false,
clean: false,
})
packages/ui/jsonrpc/README.md
+23
View File
@@ -0,0 +1,23 @@
# @deepseek-ai/dsh-jsonrpc
The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC server that lets an out-of-process SDK client (e.g. the Python `deepseek_harness` package) drive DeepSeek Harness agents without touching Cordis. The client speaks newline-delimited JSON-RPC on the process stdin/stdout ([`HarnessSdkServer`](src/server.ts): `initialize` → `session/prompt` → `shutdown`, with `session.event` / `session.finished` / `subagent.*` notifications over [`JsonRpcLineTransport`](src/transport.ts)). The SDK-client analogue of the [`acp`](../acp/README.md) bridge, split the same way: this package is the protocol plugin, [`jsonrpc-agent`](../jsonrpc-agent/README.md) is the app bin that boots a `cordis.yml` around it — which process serves this protocol is a config decision, not a hardcoded bin. This plugin is the serving face of the single-exe distribution plan — see [docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md](../../../docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md).
## Wiring
`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`) and demuxes `subagent/end` through the registry. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`); a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`.
## Config
No `cordis.yml`-settable keys. The `JsonRpcConfig` fields (`input`, `output`, `exit`) are runtime-only test seams so a spec can drive the server over in-memory streams without a subprocess or a killed test process; production always serves the process stdio and exits via `process.exit`.
## stdout is the protocol
The process stdout this plugin runs in carries only JSON-RPC frames. The tree that loads it must load NO stdout logger (a console logger corrupts the frames) — the guarantee is config-only, same as the ACP bridge. Diagnostics go to stderr.
## Shutdown and exit semantics
The plugin owns the PROTOCOL-level exit: a `shutdown` request is answered first (the response frame flushes), then the plugin disposes its own fiber — running the effect disposer: an idempotent `server.shutdown()` (every SDK-created agent disposed to quiescence, event subscriptions detached) plus `transport.close()` — and exits the process with code 0. Own-fiber disposal is deliberate: the request's `server.shutdown()` already flushed all SDK-owned session state, and the process exit that follows is the teardown of the rest of the tree. Process-level exits (stdin EOF → 0, SIGTERM → 0, SIGINT → 130) belong to the app bin, which disposes the whole root context. Fiber disposal WITHOUT a `shutdown` request (HMR-style unload) just stops serving — it never exits the process.
## Wire notes
`initialize.serverInfo.name` is the wire-stable `deepseek-harness-sdk-runtime` (SDK clients key on it, independent of this package's name). A session accepts at most one in-flight `session/prompt`; an overlapping prompt for the same `sessionId` fails immediately through the standard handler-error response, while other sessions remain independent and the same session can be reused after the active prompt settles. Persistence roots and the deployment persona come from `cordis.yml`; the wire exposes only parameters the server applies.
packages/ui/jsonrpc/package.json
+46
View File
@@ -0,0 +1,46 @@
{
"name": "@deepseek-ai/dsh-jsonrpc",
"description": "Stdio JSON-RPC SDK server plugin: serves HarnessSdkServer over newline-delimited JSON-RPC on the process stdio, letting an out-of-process SDK client (e.g. the Python SDK) drive DeepSeek Harness agents",
"version": "0.0.1",
"private": true,
"type": "module",
"main": "lib/index.js",
"types": "lib/types/index.d.ts",
"exports": {
".": {
"types": "./lib/types/index.d.ts",
"default": "./lib/index.js"
},
"./src/*": "./src/*",
"./package.json": "./package.json"
},
"files": [
"lib/index.js",
"lib/types/**/*.d.ts",
"lib/types/**/*.d.ts.map",
"src"
],
"license": "BSD-3-Clause",
"dependencies": {
"schemastery": "^3.17.0"
},
"peerDependencies": {
"@deepseek-ai/dsh-agent": "^0.0.1",
"@deepseek-ai/dsh-llm": "^0.0.1",
"@deepseek-ai/dsh-llm-deepseek": "^0.0.1",
"@deepseek-ai/dsh-session": "^0.0.1",
"@deepseek-ai/dsh-subagent": "^0.0.1",
"cordis": "^4.0.0-rc.6"
},
"devDependencies": {
"@cordisjs/plugin-loader": "workspace:^",
"@deepseek-ai/dsh-agent": "workspace:^",
"@deepseek-ai/dsh-agent-core": "workspace:^",
"@deepseek-ai/dsh-llm": "workspace:^",
"@deepseek-ai/dsh-llm-deepseek": "workspace:^",
"@deepseek-ai/dsh-session": "workspace:^",
"@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^",
"@deepseek-ai/dsh-subagent": "workspace:^",
"cordis": "^4.0.0-rc.6"
}
}
packages/ui/jsonrpc/src/index.ts
+144
View File
@@ -0,0 +1,144 @@
/**
* The SDK-facing stdio JSON-RPC server plugin: mounting it wires a
* {@link JsonRpcLineTransport} over the process stdio and serves
* {@link HarnessSdkServer} (`initialize` → `session/prompt`* → `shutdown`,
* plus the `session.*`/`subagent.*` notifications) to an out-of-process SDK
* client (e.g. the Python `deepseek_harness` package). The structured
* SDK-client analogue of the `acp` bridge: a client-driver plugin over
* `ctx.agents`, not a loop change and not a capability seam. Which process
* actually serves this protocol is a `cordis.yml` decision — the tree that
* loads this plugin IS the SDK server (the `dsh-jsonrpc-agent` bin boots such
* a tree for the single-exe distribution; see
* docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md).
*
* stdout is the protocol: this plugin must run in a tree that loads NO stdout
* logger (the console logger writes to stdout and would corrupt the JSON-RPC
* frames). The guarantee is config-only — see the package README.
*
* Exit-lifecycle split: this plugin owns the PROTOCOL-level exit (the
* `shutdown` request answers first, then the plugin disposes its own fiber and
* exits 0 — see {@link apply}); process-level exits (stdin EOF, SIGTERM,
* SIGINT) belong to the app bin (`dsh-jsonrpc-agent`), which disposes the
* whole root context.
*
* Plugin export shape: named `name`/`inject`/`Config`/`apply`, NO default
* export — the cordis Loader's `unwrapExports` does `exports.default ??
* exports`, so a stray default would collapse the module to the bare `apply`
* and silently drop `inject`/`name`/`Config` (see docs/postmortem/0001).
*
* @module @deepseek-ai/dsh-jsonrpc
*/
import type { Context } from 'cordis'
import type { Readable, Writable } from 'node:stream'
import Schema from 'schemastery'
import { HarnessSdkServer } from './server.ts'
import { JsonRpcLineTransport } from './transport.ts'
export * from './server.ts'
export * from './transport.ts'
export const name = 'jsonrpc'
// The server programs against the agent factory only: `agents` is read on
// every `session/prompt` (get-or-create) and on `subagent/end` demux. The LLM
// seam is deliberately NOT injected — `initialize` reads it opportunistically
// via `ctx.get('llm')` (the topology-independent lookup for a non-injected
// service, per packages/AGENTS.md) to decide whether to lazily mount the
// DeepSeek adapter for the requested model.
export const inject = ['agents']
/**
* Plugin config. Every field is a runtime-only test seam — none is part of the
* schemastery {@link Config}, so nothing here is settable from a `cordis.yml`
* (production always serves the process stdio and exits via `process.exit`).
*/
export interface JsonRpcConfig {
/**
* Transport input override. Production omits this (the plugin reads
* `process.stdin`); tests inject an in-memory `Readable` to drive the server
* without a subprocess.
*/
input?: Readable
/**
* Transport output override. Production omits this (the plugin writes
* `process.stdout` — the protocol channel); tests inject an in-memory
* `Writable` to capture frames.
*/
output?: Writable
/**
* Process-exit override for the `shutdown` request path. Production omits
* this (`process.exit`); tests inject a recorder so a driven shutdown does
* not kill the test process.
*/
exit?: (code: number) => void
}
export const Config: Schema<JsonRpcConfig> = Schema.object({})
/**
* Mount the SDK server on the process stdio: build the line transport and
* {@link HarnessSdkServer}, dispatch incoming requests, and start reading
* frames. Disposal is an effect: disposing this plugin's fiber runs
* `server.shutdown()` (disposes every SDK-created agent to quiescence and
* detaches the event subscriptions) and `transport.close()`.
*
* The `shutdown` request's process-exit semantics live HERE, because the
* plugin owns the server and transport: the request is answered first, an
* explicit output-write barrier confirms the response frame flushed, then the
* plugin disposes its
* OWN fiber and calls `exit(0)`. Own-fiber disposal is sufficient — the
* request's `server.shutdown()` already brought every SDK-created agent to
* quiescence (their session logs are flushed by the awaited agent-handle
* disposes), the fiber's effect disposer re-runs the idempotent shutdown and
* closes the transport, and the process exit that follows IS the teardown of
* the rest of the tree (the bin's EOF/signal handlers own root-context
* disposal for the process-level exits).
*/
export function apply(ctx: Context, config: JsonRpcConfig): void {
// Capture the fiber handle NOW, during apply(): the shutdown path runs LATER,
// from the transport's read loop, and must dispose exactly this plugin's
// fiber (cf. the injection-scope capture note in the acp bridge).
const fiber = ctx.fiber
/* v8 ignore next -- production stdio wiring; tests always inject the runtime seams */
const input = config.input ?? process.stdin
/* v8 ignore next -- production stdio wiring; tests always inject the runtime seams */
const output = config.output ?? process.stdout
/* v8 ignore next -- production exit wiring; tests always inject the runtime seams */
const exit = config.exit ?? ((code: number): void => { process.exit(code) })
const transport = new JsonRpcLineTransport(input, output)
const server = new HarnessSdkServer(ctx, transport)
// The shutdown-request exit path, exactly once (a second `shutdown` frame
// racing the dispose shares the same task). Flush and disposal failures are
// settled independently: once shutdown was answered, process exit is still
// the honest outcome and neither failure may prevent the next teardown step.
let exitTask: Promise<void> | undefined
const disposeAndExit = (): Promise<void> => {
exitTask ??= (async () => {
await Promise.allSettled([Promise.resolve().then(() => transport.flush())])
await Promise.allSettled([Promise.resolve().then(() => fiber.dispose())])
exit(0)
})()
return exitTask
}
transport.onRequest(async (method, params) => {
const result = await server.handleRequest(method, params)
if (method === 'shutdown') {
// The transport writes the returned result after this handler resolves.
// Schedule the explicit flush barrier after that write, then dispose this
// plugin's fiber and exit 0 (see apply's doc).
setImmediate(() => { void disposeAndExit() })
}
return result
})
ctx.effect(() => {
transport.start()
return async () => {
await server.shutdown()
transport.close()
}
}, 'jsonrpc.serve')
}
packages/ui/jsonrpc/src/server.ts
+276
View File
@@ -0,0 +1,276 @@
/**
* `HarnessSdkServer`: the JSON-RPC method surface the `dsh-jsonrpc` plugin
* serves to out-of-process SDK clients (e.g. the Python `deepseek_harness`
* package). Requests: `initialize` → `session/prompt`* → `shutdown`.
* Notifications pushed to the host: `session.event` (every durable session
* event, verbatim), `session.finished` (per prompt turn settle),
* `subagent.started` / `subagent.finished` (child-session lineage and run
* outcomes). The server owns only the SDK-facing session map — the harness
* itself is the context the plugin mounts in; plugins, persistence, and
* the LLM adapter set all come from the external `cordis.yml`.
*
* @module @deepseek-ai/dsh-jsonrpc/server
*/
import type { Context } from 'cordis'
import { resolve } from 'node:path'
import type { ContentBlock } from '@deepseek-ai/dsh-llm'
import type { AgentHandle } from '@deepseek-ai/dsh-agent'
import { AgentId } from '@deepseek-ai/dsh-agent'
import { SessionId, type TurnEndReason } from '@deepseek-ai/dsh-session'
import type { SubagentRunEndInfo } from '@deepseek-ai/dsh-subagent'
import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
import type { JsonRpcTransportPeer } from './transport.ts'
/** Parameters of the `initialize` request (once per process, before any prompt). */
export interface InitializeParams {
/** Working directory recorded on every SDK-created session's header. */
cwd: string
/** Model name every SDK-created agent runs on (see {@link HarnessSdkServer.initialize} for adapter fallback). */
model: string
}
/** Result of the `initialize` request: the server's identity for the SDK handshake. */
export interface InitializeResult {
/** Wire-stable server identity (`deepseek-harness-sdk-runtime`) and version. */
serverInfo: { name: string; version: string }
}
/**
* Parameters of a `session/prompt` request: one user turn on one SDK session,
* with at most one in flight per session.
*/
export interface SessionPromptParams {
/** The SDK-side session id; an unknown id lazily creates the agent+session pair. */
sessionId: string
/** The prompt content blocks, sent verbatim as the user message. */
contentBlocks: ContentBlock[]
}
/** Result of a `session/prompt` request: the prompt ran to turn settle (outcome rides on `session.finished`). */
export interface SessionPromptResult {
/** Always `true`; the turn outcome is the paired `session.finished` notification. */
accepted: true
}
interface SessionRecord {
handle: AgentHandle
lastTurnEnd: TurnEndReason | undefined
activePrompt: boolean
}
interface SubagentRecord {
childSessionId: string
parentSessionId: string | undefined
}
/**
* The SDK server over a booted harness context. Constructing it subscribes to
* the context's `session/event`, `session/created`, `agent/created`, and
* `subagent/end` events and forwards them to the host as notifications; the
* subscriptions live until {@link shutdown}. One instance serves one transport
* peer for the process lifetime — there is no re-`initialize`.
*/
export class HarnessSdkServer {
private cwd = process.cwd()
private model = 'deepseek'
private llmFiber: { dispose(): Promise<void> } | undefined
private readonly sessions = new Map<string, SessionRecord>()
private readonly sessionCreations = new Map<string, Promise<SessionRecord>>()
private readonly subagentSessions = new Map<string, SubagentRecord>()
private readonly disposers: (() => void)[] = []
private shutdownTask: Promise<Record<string, never>> | undefined
private shuttingDown = false
constructor(
private readonly ctx: Context,
private readonly transport: JsonRpcTransportPeer,
) {
this.disposers.push(ctx.on('session/event', (session, event) => {
if (event.type === 'turn/end') {
const rec = this.sessions.get(String(session.id))
if (rec) rec.lastTurnEnd = event.data.reason
}
this.transport.notify('session.event', { sessionId: String(session.id), event })
}))
this.disposers.push(ctx.on('session/created', (session) => {
const parentSession = session.header.parentSession
if (parentSession === undefined) return
this.transport.notify('subagent.started', {
parentSessionId: String(parentSession),
childSessionId: String(session.id),
})
}))
// Cache agent → session lineage on creation: by the time `subagent/end`
// fires the child agent may already be disposed and gone from the registry.
this.disposers.push(ctx.on('agent/created', (agent) => {
this.subagentSessions.set(String(agent.id), {
childSessionId: String(agent.session.id),
parentSessionId: agent.session.header.parentSession === undefined
? undefined
: String(agent.session.header.parentSession),
})
}))
this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => {
const rec = this.subagentSessions.get(String(info.id))
const agent = this.ctx.agents.get(info.id)
const childSessionId = rec?.childSessionId ?? (agent === undefined ? undefined : String(agent.session.id))
const parentSessionId = rec?.parentSessionId ?? (
agent?.session.header.parentSession === undefined ? undefined : String(agent.session.header.parentSession)
)
if (childSessionId === undefined) return
this.transport.notify('subagent.finished', {
provider: info.provider,
agentId: String(info.id),
...(parentSessionId === undefined ? {} : { parentSessionId }),
childSessionId,
status: info.stopReason === 'completed' ? 'ok' : 'error',
stopReason: info.stopReason,
...(info.lastAssistantMessage === undefined ? {} : { lastAssistantMessage: info.lastAssistantMessage }),
})
}))
}
/**
* Handle `initialize`: record the SDK deployment facts (cwd, model) and, when
* no registered adapter serves `params.model`, mount the DeepSeek adapter for
* it (credentials from `$DEEPSEEK_API_KEY`/`$DEEPSEEK_BASE_URL`) — a config
* that already registered an adapter for the model wins.
* @param params - the SDK handshake parameters.
* @returns the server identity for the handshake.
*/
async initialize(params: InitializeParams): Promise<InitializeResult> {
this.cwd = resolve(params.cwd)
this.model = params.model
if (!this.llmFiber && !this.hasAdapterFor(this.model)) {
this.llmFiber = await this.ctx.plugin(LlmDeepSeek, { models: [this.model] })
}
return { serverInfo: { name: 'deepseek-harness-sdk-runtime', version: '0.0.1' } }
}
/**
* Handle `session/prompt`: get-or-create the session's agent, send the
* content as the user message, await turn settle (quiescence), then notify
* `session.finished` with the settled turn's outcome. A session accepts at
* most one prompt at a time; an overlapping request fails immediately while
* other sessions remain independent.
* @param params - the target session id and prompt content.
* @returns `{ accepted: true }` after the turn settled.
*/
async prompt(params: SessionPromptParams): Promise<SessionPromptResult> {
const rec = await this.getOrCreateSession(params.sessionId)
if (rec.activePrompt) throw new Error(`session already has an active prompt: ${params.sessionId}`)
rec.activePrompt = true
try {
rec.lastTurnEnd = undefined
rec.handle.agent.send(params.contentBlocks)
await rec.handle.agent.whenIdle()
const status = this.finishedStatus(rec.lastTurnEnd)
this.transport.notify('session.finished', {
sessionId: params.sessionId,
status,
reason: rec.lastTurnEnd,
})
return { accepted: true }
} finally {
rec.activePrompt = false
}
}
/**
* Handle `shutdown`: dispose every SDK-created agent handle (awaiting loop
* quiescence), unmount the adapter fiber this server mounted (if any), and
* detach the event subscriptions. The CONTEXT stays up — the bin disposes it
* as part of process exit.
* @returns an empty object (the JSON-RPC result).
*/
shutdown(): Promise<Record<string, never>> {
this.shutdownTask ??= this.performShutdown()
return this.shutdownTask
}
private async performShutdown(): Promise<Record<string, never>> {
this.shuttingDown = true
const pendingCreations = [...this.sessionCreations.values()]
await Promise.allSettled(pendingCreations)
this.sessionCreations.clear()
const records = [...this.sessions.values()]
this.sessions.clear()
this.subagentSessions.clear()
const failures: unknown[] = []
while (this.disposers.length > 0) {
try {
this.disposers.pop()?.()
} catch (error) {
failures.push(error)
}
}
const teardownResults = await Promise.allSettled([
...records.map(rec => Promise.resolve().then(() => rec.handle.dispose())),
...(this.llmFiber === undefined ? [] : [Promise.resolve().then(() => this.llmFiber?.dispose())]),
])
this.llmFiber = undefined
failures.push(...teardownResults
.filter((result): result is PromiseRejectedResult => result.status === 'rejected')
.map(result => result.reason as unknown))
if (failures.length === 1) throw failures[0]
if (failures.length > 1) throw new AggregateError(failures, 'SDK server teardown failed')
return {}
}
/**
* Dispatch one incoming JSON-RPC request to its typed handler. Throws (→ a
* JSON-RPC error response) on an unknown method.
* @param method - the JSON-RPC method name.
* @param params - the raw params object from the wire.
* @returns the handler's result, to be serialized as the response.
*/
async handleRequest(method: string, params: Record<string, unknown> | undefined): Promise<unknown> {
switch (method) {
case 'initialize':
return this.initialize(params as unknown as InitializeParams)
case 'session/prompt':
return this.prompt(params as unknown as SessionPromptParams)
case 'shutdown':
return this.shutdown()
default:
throw new Error(`unknown DeepSeek Harness SDK runtime method: ${method}`)
}
}
private async getOrCreateSession(sessionId: string): Promise<SessionRecord> {
if (this.shuttingDown) throw new Error('SDK server is shutting down')
const existing = this.sessions.get(sessionId)
if (existing) return existing
const pending = this.sessionCreations.get(sessionId)
if (pending) return pending
const creation = this.createSession(sessionId)
this.sessionCreations.set(sessionId, creation)
void creation.then(
() => { this.sessionCreations.delete(sessionId) },
() => { this.sessionCreations.delete(sessionId) },
)
return creation
}
private async createSession(sessionId: string): Promise<SessionRecord> {
const handle = await this.ctx.agents.create({
agentId: AgentId(sessionId),
sessionId: SessionId(sessionId),
meta: { cwd: this.cwd },
agentOptions: { model: this.model },
})
const rec: SessionRecord = { handle, lastTurnEnd: undefined, activePrompt: false }
this.sessions.set(sessionId, rec)
return rec
}
private finishedStatus(reason: TurnEndReason | undefined): 'ok' | 'error' {
if (!reason) return 'error'
return reason.kind === 'completed' ? 'ok' : 'error'
}
private hasAdapterFor(model: string): boolean {
return this.ctx.get('llm')?.models().includes(model) ?? false
}
}
packages/ui/jsonrpc/src/transport.ts
+238
View File
@@ -0,0 +1,238 @@
/**
* Newline-delimited JSON-RPC 2.0 transport over a byte stream pair (the SDK
* server's stdio channel). One JSON frame per line; a frame with `id`+`method`
* is an incoming request, `id` alone matches a pending outgoing request, and
* `method` alone is a notification. Malformed lines are ignored (a resilient
* wire reader, not a validator); handler failures become JSON-RPC error
* responses, never a crashed transport.
*
* @module @deepseek-ai/dsh-jsonrpc/transport
*/
import { randomUUID } from 'node:crypto'
import type { Readable, Writable } from 'node:stream'
import { StringDecoder } from 'node:string_decoder'
type JsonRpcId = string | number
type RequestHandler = (method: string, params: Record<string, unknown>) => Promise<unknown>
type NotificationHandler = (method: string, params: Record<string, unknown>) => void
/**
* The outbound half of a JSON-RPC peer — what {@link HarnessSdkServer} needs
* to talk BACK to the host: awaited `request`s and fire-and-forget `notify`s.
* Narrow on purpose so tests substitute a recording fake without a stream pair.
*/
export interface JsonRpcTransportPeer {
/**
* Send a request to the remote peer and await its response.
* @param method - the JSON-RPC method name.
* @param params - the request parameters object.
* @returns the remote peer's `result`; rejects on a JSON-RPC `error`
* response, a write failure, or transport/input closure.
*/
request(method: string, params: Record<string, unknown>): Promise<unknown>
/**
* Send a notification (no response expected). An omitted `params` sends no
* `params` member at all.
* @param method - the JSON-RPC method name.
* @param params - the optional notification parameters object.
*/
notify(method: string, params?: Record<string, unknown>): void
}
interface PendingRequest {
resolve: (value: unknown) => void
reject: (error: Error) => void
}
/**
* Line-delimited JSON-RPC 2.0 endpoint over a `Readable`/`Writable` pair.
* Inert until {@link start} attaches the input listeners; {@link close}
* detaches them and rejects every pending outgoing request (dispose-safe: the
* streams themselves are not destroyed — the caller owns them). Incoming
* requests are dispatched to the single {@link onRequest} handler (a missing
* handler answers `-32601 method not found`; a throwing handler answers
* `-32603` with the message); incoming notifications go to {@link
* onNotification} and are dropped without one.
*/
export class JsonRpcLineTransport implements JsonRpcTransportPeer {
private buffer = ''
private readonly decoder = new StringDecoder('utf8')
private started = false
private requestHandler: RequestHandler | undefined
private notificationHandler: NotificationHandler | undefined
private readonly pending = new Map<JsonRpcId, PendingRequest>()
constructor(
private readonly input: Readable,
private readonly output: Writable,
) {}
/** Attach the input listeners and begin reading frames. Idempotent. */
start(): void {
if (this.started) return
this.started = true
this.input.on('data', this.onData)
this.input.on('error', this.onInputError)
this.input.on('end', this.onInputEnd)
}
/**
* Detach the input listeners and reject every pending outgoing request with
* "JSON-RPC transport closed". Safe to call without a prior {@link start}.
*/
close(): void {
this.input.off('data', this.onData)
this.input.off('error', this.onInputError)
this.input.off('end', this.onInputEnd)
this.failPending(new Error('JSON-RPC transport closed'))
}
/**
* Install THE handler for incoming requests (a later call replaces it).
* @param handler - resolves to the response `result`; a rejection becomes a
* `-32603` error response carrying the message.
*/
onRequest(handler: RequestHandler): void {
this.requestHandler = handler
}
/**
* Install THE handler for incoming notifications (a later call replaces it).
* @param handler - invoked per notification with the method and normalized
* params object.
*/
onNotification(handler: NotificationHandler): void {
this.notificationHandler = handler
}
request(method: string, params: Record<string, unknown>): Promise<unknown> {
const id = `req_${randomUUID().replaceAll('-', '')}`
const message = { jsonrpc: '2.0', id, method, params }
return new Promise((resolve, reject) => {
this.pending.set(id, { resolve, reject })
try {
this.write(message)
} catch (error) {
this.pending.delete(id)
reject(error instanceof Error ? error : new Error(String(error)))
}
})
}
notify(method: string, params?: Record<string, unknown>): void {
this.write(params === undefined ? { jsonrpc: '2.0', method } : { jsonrpc: '2.0', method, params })
}
/**
* Wait until every frame written before this call has reached the output's
* write callback. The empty queued write is a barrier and emits no protocol
* bytes.
* @returns a promise that settles with the output write callback.
*/
flush(): Promise<void> {
return new Promise<void>((resolve, reject) => {
this.output.write('', (error) => {
if (error) reject(error)
else resolve()
})
})
}
private readonly onData = (chunk: Buffer | string): void => {
this.buffer += typeof chunk === 'string' ? chunk : this.decoder.write(chunk)
this.drainLines()
}
private drainLines(): void {
for (;;) {
const newline = this.buffer.indexOf('\n')
if (newline < 0) break
const line = this.buffer.slice(0, newline).trim()
this.buffer = this.buffer.slice(newline + 1)
if (!line) continue
void this.handleLine(line)
}
}
private readonly onInputError = (error: Error): void => {
this.failPending(error)
}
private readonly onInputEnd = (): void => {
this.buffer += this.decoder.end()
this.drainLines()
this.failPending(new Error('JSON-RPC input closed'))
}
private async handleLine(line: string): Promise<void> {
let message: unknown
try {
message = JSON.parse(line)
} catch {
// Swallows ONLY JSON.parse syntax errors: a malformed wire line is a
// peer bug this resilient reader skips; nothing else runs in the try.
return
}
if (!message || typeof message !== 'object') return
const frame = message as Record<string, unknown>
const id = frame.id
const method = frame.method
if ((typeof id === 'string' || typeof id === 'number') && typeof method === 'string') {
await this.handleIncomingRequest(id, method, objectParams(frame.params))
return
}
if (typeof id === 'string' || typeof id === 'number') {
this.handleIncomingResponse(id, frame)
return
}
if (typeof method === 'string') {
this.notificationHandler?.(method, objectParams(frame.params))
}
}
private async handleIncomingRequest(id: JsonRpcId, method: string, params: Record<string, unknown>): Promise<void> {
const handler = this.requestHandler
if (!handler) {
this.writeError(id, -32601, `method not found: ${method}`)
return
}
try {
const result = await handler(method, params)
this.write({ jsonrpc: '2.0', id, result })
} catch (error) {
this.writeError(id, -32603, error instanceof Error ? error.message : String(error))
}
}
private handleIncomingResponse(id: JsonRpcId, frame: Record<string, unknown>): void {
const pending = this.pending.get(id)
if (!pending) return
this.pending.delete(id)
if (frame.error && typeof frame.error === 'object') {
const error = frame.error as Record<string, unknown>
pending.reject(new Error(typeof error.message === 'string' ? error.message : 'JSON-RPC error'))
return
}
pending.resolve(frame.result)
}
private writeError(id: JsonRpcId, code: number, message: string): void {
this.write({ jsonrpc: '2.0', id, error: { code, message } })
}
private write(message: Record<string, unknown>): void {
this.output.write(`${JSON.stringify(message)}\n`)
}
private failPending(error: Error): void {
const pending = [...this.pending.values()]
this.pending.clear()
for (const waiter of pending) waiter.reject(error)
}
}
/** Normalize JSON-RPC `params` to a plain object (arrays and scalars collapse to `{}`). */
function objectParams(params: unknown): Record<string, unknown> {
return params && typeof params === 'object' && !Array.isArray(params) ? params as Record<string, unknown> : {}
}
packages/ui/jsonrpc/tests/plugin-apply.spec.ts
+316
View File
@@ -0,0 +1,316 @@
import { createServer } from 'node:http'
import type { IncomingMessage, Server, ServerResponse } from 'node:http'
import { mkdtemp, rm } from 'node:fs/promises'
import { join } from 'node:path'
import { tmpdir } from 'node:os'
import { PassThrough, Writable } from 'node:stream'
import { afterEach, describe, expect, it, vi } from 'vitest'
import { Context } from 'cordis'
import * as agentCore from '@deepseek-ai/dsh-agent-core'
import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
import * as jsonrpc from '../src/index.ts'
/**
* apply()-level lifecycle coverage for the @deepseek-ai/dsh-jsonrpc plugin:
* the plugin is mounted through the REAL namespace mount path —
* `ctx.plugin(jsonrpc, config)` over the module namespace object, exactly what
* the Loader hands cordis after `unwrapExports` (plugin-shape.spec pins that
* identity) — with the runtime-only `input`/`output`/`exit` seams from
* {@link jsonrpc.JsonRpcConfig} replacing the process stdio, so the whole
* pipeline (line transport → HarnessSdkServer → notifications back onto the
* wire) runs in-process. The scenarios pin the plugin's exit-lifecycle split:
* a `shutdown` REQUEST answers first, then disposes the plugin's own fiber and
* calls `exit(0)` exactly once (a racing second `shutdown` must not re-exit);
* a bare fiber dispose (HMR-style unload, no request) only stops serving and
* never touches `exit`.
*/
/** One ordered observation on the plugin's outward-facing seams: a JSON-RPC frame written to `output`, or an `exit(code)` call. */
type WireEvent =
| { kind: 'frame'; frame: Record<string, unknown> }
| { kind: 'write-complete'; ids: (string | number)[] }
| { kind: 'exit'; code: number }
interface ApplyHarness {
ctx: Context
/** The jsonrpc plugin's own fiber (NOT the root), for the HMR-style dispose scenario. */
fiber: Awaited<ReturnType<Context['plugin']>>
/** Every output frame and exit call, in observation order — ordering assertions read this. */
events: WireEvent[]
outputErrors: Error[]
send(frame: Record<string, unknown>): void
sendRaw(text: string): void
frames(): Record<string, unknown>[]
exits(): number[]
waitForFrame(predicate: (frame: Record<string, unknown>) => boolean, description: string): Promise<Record<string, unknown>>
dispose(): Promise<void>
}
/** Poll `get` until it yields a value (5s cap) — the output side is fed asynchronously from the transport's read loop. */
async function waitFor<T>(get: () => T | undefined, description: string): Promise<T> {
const deadline = Date.now() + 5000
for (;;) {
const value = get()
if (value !== undefined) return value
if (Date.now() > deadline) throw new Error(`timed out waiting for ${description}`)
await new Promise(resolve => setTimeout(resolve, 5))
}
}
/** Let pending microtasks, setImmediate callbacks, and stream events drain — for asserting that something did NOT happen. */
async function settle(): Promise<void> {
await new Promise(resolve => setTimeout(resolve, 25))
}
/**
* Boot a minimal harness context (agent-core bundle + JSONL persistence, the
* server.spec recipe) and mount the jsonrpc plugin on it through the real
* namespace mount path, with in-memory seams standing in for stdio/exit.
*/
async function mountPlugin(
storageDir: string,
options: { writeDelayMs?: number; failFlush?: boolean } = {},
): Promise<ApplyHarness> {
const ctx = new Context()
await ctx.plugin(agentCore)
await ctx.plugin(SessionPersistenceJsonl, { root: storageDir })
await new Promise(resolve => setTimeout(resolve, 50))
const input = new PassThrough()
const events: WireEvent[] = []
const outputErrors: Error[] = []
let pendingOutput = ''
// A hand-rolled Writable (not a PassThrough): _write records frames on
// admission and write-complete only when its callback fires, so a delayed
// output proves exit waits for the transport's flush barrier.
const output = new Writable({
write(chunk: Buffer, _encoding, callback) {
const ids: (string | number)[] = []
pendingOutput += chunk.toString('utf8')
for (;;) {
const newline = pendingOutput.indexOf('\n')
if (newline < 0) break
const line = pendingOutput.slice(0, newline).trim()
pendingOutput = pendingOutput.slice(newline + 1)
if (line) {
const frame = JSON.parse(line) as Record<string, unknown>
events.push({ kind: 'frame', frame })
if (typeof frame.id === 'string' || typeof frame.id === 'number') ids.push(frame.id)
}
}
const complete = (): void => {
if (options.failFlush === true && chunk.length === 0) {
callback(new Error('flush callback failed'))
return
}
events.push({ kind: 'write-complete', ids })
callback()
}
if ((options.writeDelayMs ?? 0) > 0) setTimeout(complete, options.writeDelayMs)
else complete()
},
})
output.on('error', (error: Error) => { outputErrors.push(error) })
const exit = (code: number): void => { events.push({ kind: 'exit', code }) }
const fiber = await ctx.plugin(jsonrpc, { input, output, exit })
const frames = (): Record<string, unknown>[] =>
events.flatMap(event => event.kind === 'frame' ? [event.frame] : [])
return {
ctx,
fiber,
events,
outputErrors,
send: (frame) => { input.write(`${JSON.stringify(frame)}\n`) },
sendRaw: (text) => { input.write(text) },
frames,
exits: () => events.flatMap(event => event.kind === 'exit' ? [event.code] : []),
waitForFrame: (predicate, description) => waitFor(() => frames().find(predicate), description),
dispose: async () => { await ctx.fiber.dispose() },
}
}
const servers: Server[] = []
afterEach(async () => {
await Promise.all(servers.splice(0).map(server => new Promise(resolve => server.close(resolve))))
vi.unstubAllEnvs()
})
/** The server.spec mock OpenAI-compatible SSE endpoint, so a prompt turn completes without a real key. */
async function mockCompletionServer(): Promise<{ url: string; requests: unknown[] }> {
const requests: unknown[] = []
const server = createServer((request: IncomingMessage, response: ServerResponse) => {
let body = ''
request.on('data', (chunk: Buffer) => { body += chunk.toString('utf8') })
request.on('end', () => {
requests.push(JSON.parse(body))
response.writeHead(200, { 'content-type': 'text/event-stream' })
response.write('data: {"choices":[{"delta":{"role":"assistant","content":null,"reasoning_content":""}}]}\n\n')
response.write('data: {"choices":[{"delta":{"content":"done"}}]}\n\n')
response.write('data: {"choices":[{"delta":{"content":""},"finish_reason":"stop"}],"usage":{"prompt_tokens":3,"completion_tokens":1}}\n\n')
response.write('data: [DONE]\n\n')
response.end()
})
})
servers.push(server)
await new Promise<void>(resolve => server.listen(0, '127.0.0.1', resolve))
const address = server.address()
if (address === null || typeof address === 'string') throw new Error('no port')
return { url: `http://127.0.0.1:${address.port}`, requests }
}
describe('dsh-jsonrpc plugin apply', () => {
it('serves initialize over the injected stdio pair', async () => {
const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-apply-init-'))
vi.stubEnv('DEEPSEEK_API_KEY', 'test-key')
const harness = await mountPlugin(storageDir)
try {
harness.send({ jsonrpc: '2.0', id: 'init-1', method: 'initialize', params: { cwd: storageDir, model: 'apply-model' } })
const response = await harness.waitForFrame(frame => frame.id === 'init-1', 'initialize response')
expect(response).toEqual({
jsonrpc: '2.0',
id: 'init-1',
result: { serverInfo: { name: 'deepseek-harness-sdk-runtime', version: '0.0.1' } },
})
expect(harness.exits()).toEqual([])
} finally {
await harness.dispose()
await rm(storageDir, { recursive: true, force: true })
}
})
it('drives a session/prompt turn end-to-end and forwards session notifications as output frames', async () => {
const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-apply-prompt-'))
const llmServer = await mockCompletionServer()
vi.stubEnv('DEEPSEEK_API_KEY', 'test-key')
vi.stubEnv('DEEPSEEK_BASE_URL', llmServer.url)
const harness = await mountPlugin(storageDir)
try {
harness.send({ jsonrpc: '2.0', id: 1, method: 'initialize', params: { cwd: storageDir, model: 'dsagent-model' } })
await harness.waitForFrame(frame => frame.id === 1, 'initialize response')
harness.send({
jsonrpc: '2.0',
id: 2,
method: 'session/prompt',
params: { sessionId: 'main', contentBlocks: [{ type: 'text', text: 'fix it' }] },
})
const response = await harness.waitForFrame(frame => frame.id === 2, 'prompt response')
expect(response.result).toEqual({ accepted: true })
expect(llmServer.requests).toHaveLength(1)
const body = llmServer.requests[0] as { model: string; messages: { role: string }[] }
expect(body.model).toBe('dsagent-model')
expect(body.messages.at(-1)?.role).toBe('user')
// The server's notify() path rides the SAME transport apply() built:
// session.event / session.finished arrive as id-less frames on output.
const notifications = harness.frames().filter(frame => frame.id === undefined)
expect(notifications.some(frame => frame.method === 'session.event')).toBe(true)
expect(notifications.find(frame => frame.method === 'session.finished')).toMatchObject({
jsonrpc: '2.0',
params: { sessionId: 'main', status: 'ok' },
})
} finally {
await harness.dispose()
await rm(storageDir, { recursive: true, force: true })
}
})
it('answers shutdown before exiting 0 exactly once, even against a racing second shutdown', async () => {
const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-apply-shutdown-'))
const harness = await mountPlugin(storageDir, { writeDelayMs: 10 })
try {
// Two shutdown frames in ONE chunk: both are dispatched from the same
// read-loop pass, so both setImmediate exit callbacks get scheduled and
// the second must hit the `exiting` guard instead of re-entering.
const first = { jsonrpc: '2.0', id: 'sd-1', method: 'shutdown' }
const second = { jsonrpc: '2.0', id: 'sd-2', method: 'shutdown' }
harness.sendRaw(`${JSON.stringify(first)}\n${JSON.stringify(second)}\n`)
await waitFor(() => harness.exits().length > 0 ? true : undefined, 'exit recorder call')
expect(harness.exits()).toEqual([0])
// Response-then-exit ordering: both response write callbacks and the
// empty flush barrier complete before exit(0), even on delayed output.
const exitIndex = harness.events.findIndex(event => event.kind === 'exit')
const firstResponse = harness.events.findIndex(event => event.kind === 'frame' && event.frame.id === 'sd-1')
const secondResponse = harness.events.findIndex(event => event.kind === 'frame' && event.frame.id === 'sd-2')
const firstComplete = harness.events.findIndex(event => event.kind === 'write-complete' && event.ids.includes('sd-1'))
const secondComplete = harness.events.findIndex(event => event.kind === 'write-complete' && event.ids.includes('sd-2'))
const flushComplete = harness.events.findIndex(event => event.kind === 'write-complete' && event.ids.length === 0)
expect(firstResponse).toBeGreaterThanOrEqual(0)
expect(secondResponse).toBeGreaterThanOrEqual(0)
expect(firstComplete).toBeGreaterThan(firstResponse)
expect(secondComplete).toBeGreaterThan(secondResponse)
expect(flushComplete).toBeGreaterThan(firstComplete)
expect(flushComplete).toBeGreaterThan(secondComplete)
expect(exitIndex).toBeGreaterThan(flushComplete)
// Idempotent: the racing second shutdown never produces a second exit.
await settle()
expect(harness.exits()).toEqual([0])
// The plugin fiber is disposed: the transport reads no further frames.
const before = harness.frames().length
harness.send({ jsonrpc: '2.0', id: 'after-exit', method: 'initialize', params: { cwd: storageDir, model: 'x' } })
await settle()
expect(harness.frames().length).toBe(before)
} finally {
await harness.dispose()
await rm(storageDir, { recursive: true, force: true })
}
})
it('still disposes and exits once when the flush callback fails', async () => {
const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-apply-flush-failure-'))
const harness = await mountPlugin(storageDir, { failFlush: true })
try {
harness.send({ jsonrpc: '2.0', id: 'sd-fail', method: 'shutdown' })
await waitFor(() => harness.exits().length > 0 ? true : undefined, 'exit after flush failure')
await settle()
expect(harness.exits()).toEqual([0])
expect(harness.outputErrors.map(error => error.message)).toEqual(['flush callback failed'])
const before = harness.frames().length
harness.send({ jsonrpc: '2.0', id: 'after-flush-failure', method: 'initialize', params: { cwd: storageDir, model: 'x' } })
await settle()
expect(harness.frames().length).toBe(before)
} finally {
await harness.dispose()
await rm(storageDir, { recursive: true, force: true })
}
})
it('stops serving on a bare fiber dispose (HMR-style unload) without calling exit', async () => {
const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-apply-dispose-'))
const harness = await mountPlugin(storageDir)
try {
// Prove the pipeline is live first (an unknown method still answers, as
// a JSON-RPC error frame — the transport's handler-rejection path).
harness.send({ jsonrpc: '2.0', id: 'probe-1', method: 'nope/unknown' })
const error = await harness.waitForFrame(frame => frame.id === 'probe-1', 'error response for unknown method')
expect(error.error).toMatchObject({
code: -32603,
message: 'unknown DeepSeek Harness SDK runtime method: nope/unknown',
})
await harness.fiber.dispose()
// The effect disposer shut the server and closed the transport — later
// frames are never read — and the exit seam was never touched.
const before = harness.frames().length
harness.send({ jsonrpc: '2.0', id: 'probe-2', method: 'initialize', params: { cwd: storageDir, model: 'x' } })
await settle()
expect(harness.frames().length).toBe(before)
expect(harness.exits()).toEqual([])
} finally {
await harness.dispose()
await rm(storageDir, { recursive: true, force: true })
}
})
})
packages/ui/jsonrpc/tests/plugin-shape.spec.ts
+32
View File
@@ -0,0 +1,32 @@
import { describe, expect, it } from 'vitest'
import Loader from '@cordisjs/plugin-loader'
import * as jsonrpc from '../src/index.ts'
/**
* REAL-export-path guard for the @deepseek-ai/dsh-jsonrpc namespace plugin
* (the packages/AGENTS.md red line: a plugin shipped via `cordis.yml` needs a
* test through the real Loader/export path). A hand-built `ctx.plugin({...})`
* mount bypasses `unwrapExports` — the exact path that once collapsed a
* namespace plugin with a stray `export default` and silently dropped its
* `inject` (docs/postmortem/0001) — so this spec drives the REAL
* `Loader.unwrapExports` over the module namespace and asserts the
* `name`/`inject`/`Config`/`apply` shape survives it intact.
*/
describe('dsh-jsonrpc plugin export shape', () => {
it('has the namespace-plugin export shape (no stray default) so the Loader keeps name/inject/Config/apply', () => {
// A stray `export default` would make `unwrapExports` (`exports.default ??
// exports`) collapse the module to the bare default, dropping `inject` —
// the plugin would then throw "cannot get property … without inject" at
// its first `ctx.agents` read. Adding `export default` fails this test.
expect('default' in jsonrpc).toBe(false)
expect(typeof jsonrpc.apply).toBe('function')
const loader = Object.create(Loader.prototype) as Loader
const unwrapped = loader.unwrapExports(jsonrpc) as Record<string, unknown>
expect(unwrapped).toBe(jsonrpc)
expect(unwrapped.name).toBe('jsonrpc')
expect(unwrapped.inject).toEqual(['agents'])
expect(unwrapped.Config).toBeDefined()
expect(typeof unwrapped.apply).toBe('function')
})
})
packages/ui/jsonrpc/tests/server.spec.ts
+572
View File
@@ -0,0 +1,572 @@
import { createServer } from 'node:http'
import type { IncomingMessage, Server, ServerResponse } from 'node:http'
import { mkdtemp, rm } from 'node:fs/promises'
import { join } from 'node:path'
import { tmpdir } from 'node:os'
import { afterEach, describe, expect, it, vi } from 'vitest'
import { Context } from 'cordis'
import { AgentId, type Agent, type AgentHandle } from '@deepseek-ai/dsh-agent'
import { SessionId } from '@deepseek-ai/dsh-session'
import * as agentCore from '@deepseek-ai/dsh-agent-core'
import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
import SubagentService, { type SubagentRunEndInfo } from '@deepseek-ai/dsh-subagent'
import { HarnessSdkServer, type JsonRpcTransportPeer } from '../src/index.ts'
class FakeTransport implements JsonRpcTransportPeer {
notifications: { method: string; params?: Record<string, unknown> }[] = []
async request(method: string, params: Record<string, unknown>): Promise<unknown> {
throw new Error(`the SDK server should not call host JSON-RPC method ${method} with ${JSON.stringify(params)}`)
}
notify(method: string, params?: Record<string, unknown>): void {
this.notifications.push(params === undefined ? { method } : { method, params })
}
}
const servers: Server[] = []
afterEach(async () => {
await Promise.all(servers.splice(0).map(server => new Promise(resolve => server.close(resolve))))
vi.unstubAllEnvs()
})
async function mockCompletionServer(): Promise<{ url: string; requests: unknown[]; headers: IncomingMessage['headers'][] }> {
const requests: unknown[] = []
const headers: IncomingMessage['headers'][] = []
const server = createServer((request: IncomingMessage, response: ServerResponse) => {
let body = ''
request.on('data', (chunk: Buffer) => { body += chunk.toString('utf8') })
request.on('end', () => {
requests.push(JSON.parse(body))
headers.push(request.headers)
response.writeHead(200, { 'content-type': 'text/event-stream' })
response.write('data: {"choices":[{"delta":{"role":"assistant","content":null,"reasoning_content":""}}]}\n\n')
response.write('data: {"choices":[{"delta":{"content":"done"}}]}\n\n')
response.write('data: {"choices":[{"delta":{"content":""},"finish_reason":"stop"}],"usage":{"prompt_tokens":3,"completion_tokens":1}}\n\n')
response.write('data: [DONE]\n\n')
response.end()
})
})
servers.push(server)
await new Promise<void>(resolve => server.listen(0, '127.0.0.1', resolve))
const address = server.address()
if (address === null || typeof address === 'string') throw new Error('no port')
return { url: `http://127.0.0.1:${address.port}`, requests, headers }
}
async function makeHarness(storageDir: string) {
const ctx = new Context()
await ctx.plugin(agentCore)
await ctx.plugin(SubagentService)
await ctx.plugin(SessionPersistenceJsonl, { root: storageDir })
await new Promise(resolve => setTimeout(resolve, 50))
return ctx
}
/** Drive the owning service so test lifecycle events carry the real parent scope. */
async function settleSubagent(ctx: Context, parent: Agent, info: SubagentRunEndInfo): Promise<void> {
const disposeProvider = ctx.subagents.registerProvider({
name: info.provider,
capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false },
inheritsParentContext: false,
async start() {
return {
id: info.id,
result: info.lastAssistantMessage === undefined
? Promise.reject(new Error('synthetic infrastructure failure'))
: Promise.resolve({ output: info.lastAssistantMessage, stopReason: info.stopReason }),
dispose: () => Promise.resolve(),
}
},
})
try {
const run = await ctx.subagents.start(info.provider, {
parent,
prompt: [],
signal: new AbortController().signal,
})
await run.result.then(() => undefined, () => undefined)
await run.dispose()
} finally {
disposeProvider()
}
}
describe('HarnessSdkServer', () => {
it('creates a harness agent and calls the configured OpenAI-compatible endpoint', async () => {
const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-'))
const llmServer = await mockCompletionServer()
vi.stubEnv('DEEPSEEK_API_KEY', 'test-key')
vi.stubEnv('DEEPSEEK_BASE_URL', llmServer.url)
const ctx = await makeHarness(storageDir)
try {
const transport = new FakeTransport()
const server = new HarnessSdkServer(ctx, transport)
const init = await server.handleRequest('initialize', {
cwd: storageDir,
model: 'dsagent-model',
}) as { serverInfo: { name: string } }
expect(init.serverInfo.name).toBe('deepseek-harness-sdk-runtime')
await server.handleRequest('session/prompt', {
sessionId: 'main',
contentBlocks: [{ type: 'text', text: 'fix it' }],
})
expect(llmServer.requests).toHaveLength(1)
const body = llmServer.requests[0] as { model: string; messages: { role: string }[] }
expect(body.model).toBe('dsagent-model')
expect(body.messages[0]?.role).toBe('system')
expect(body.messages.at(-1)?.role).toBe('user')
expect(llmServer.headers[0]?.authorization).toBe('Bearer test-key')
expect(transport.notifications.some(n => n.method === 'session.event')).toBe(true)
expect(transport.notifications.at(-1)).toMatchObject({
method: 'session.finished',
params: { sessionId: 'main', status: 'ok' },
})
await server.handleRequest('session/prompt', {
sessionId: 'main',
contentBlocks: [{ type: 'text', text: 'again' }],
})
expect(llmServer.requests).toHaveLength(2)
const orphanHandle = await ctx.agents.create({
agentId: AgentId('orphan-agent'),
sessionId: SessionId('orphan-session'),
meta: { cwd: storageDir },
agentOptions: { model: 'dsagent-model' },
})
orphanHandle.agent.send([{ type: 'text', text: 'outside the sdk session map' }])
await orphanHandle.agent.whenIdle()
await orphanHandle.dispose()
expect(llmServer.requests).toHaveLength(3)
await server.handleRequest('shutdown', undefined)
} finally {
await ctx.fiber.dispose()
await rm(storageDir, { recursive: true, force: true })
}
})
it('rejects overlapping prompts for one session without serializing other sessions', async () => {
let releaseMain: (() => void) | undefined
const firstMainIdle = new Promise<void>((resolve) => { releaseMain = resolve })
const mainWhenIdle = vi.fn<() => Promise<void>>()
.mockReturnValueOnce(firstMainIdle)
.mockResolvedValue(undefined)
const mainSend = vi.fn()
const mainAgent = {
send: mainSend,
whenIdle: mainWhenIdle,
} as unknown as Agent
const otherSend = vi.fn()
const otherAgent = {
send: otherSend,
whenIdle: vi.fn(() => Promise.resolve()),
} as unknown as Agent
const mainHandle = { agent: mainAgent, dispose: vi.fn(() => Promise.resolve()) }
const otherHandle = { agent: otherAgent, dispose: vi.fn(() => Promise.resolve()) }
const create = vi.fn(async (options: { agentId: AgentId }) =>
String(options.agentId) === 'main' ? mainHandle : otherHandle)
const ctx = {
on: vi.fn(() => () => undefined),
agents: { create, get: () => undefined },
get: () => undefined,
} as unknown as Context
const server = new HarnessSdkServer(ctx, new FakeTransport())
const prompt = (sessionId: string, text: string) => server.prompt({
sessionId,
contentBlocks: [{ type: 'text', text }],
})
const first = prompt('main', 'first')
await vi.waitFor(() => { expect(mainSend).toHaveBeenCalledOnce() })
await expect(prompt('main', 'overlap')).rejects.toThrow('session already has an active prompt: main')
await expect(prompt('other', 'independent')).resolves.toEqual({ accepted: true })
releaseMain?.()
await expect(first).resolves.toEqual({ accepted: true })
await expect(prompt('main', 'sequential')).resolves.toEqual({ accepted: true })
mainWhenIdle.mockRejectedValueOnce(new Error('turn wait failed'))
await expect(prompt('main', 'failing')).rejects.toThrow('turn wait failed')
await expect(prompt('main', 'after failure')).resolves.toEqual({ accepted: true })
expect(mainSend).toHaveBeenCalledTimes(4)
expect(otherSend).toHaveBeenCalledOnce()
await server.shutdown()
expect(mainHandle.dispose).toHaveBeenCalledOnce()
expect(otherHandle.dispose).toHaveBeenCalledOnce()
})
it('notifies the host when a child session is created with parent lineage', async () => {
const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-'))
const ctx = await makeHarness(storageDir)
try {
const transport = new FakeTransport()
const server = new HarnessSdkServer(ctx, transport)
ctx.sessions.create(SessionId('root-session'), {
meta: { cwd: storageDir },
})
ctx.sessions.create(SessionId('child-session'), {
meta: { cwd: storageDir, parentSession: SessionId('main') },
})
expect(transport.notifications).toContainEqual({
method: 'subagent.started',
params: {
parentSessionId: 'main',
childSessionId: 'child-session',
},
})
await server.shutdown()
} finally {
await ctx.fiber.dispose()
await rm(storageDir, { recursive: true, force: true })
}
})
it('creates an SDK session without an optional system prompt', async () => {
const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-no-system-'))
const llmServer = await mockCompletionServer()
vi.stubEnv('DEEPSEEK_API_KEY', 'test-key')
vi.stubEnv('DEEPSEEK_BASE_URL', llmServer.url)
const ctx = await makeHarness(storageDir)
try {
const server = new HarnessSdkServer(ctx, new FakeTransport())
await server.initialize({ cwd: storageDir, model: 'plain-model' })
await server.prompt({
sessionId: 'plain',
contentBlocks: [{ type: 'text', text: 'hello' }],
})
expect(llmServer.requests).toHaveLength(1)
await server.shutdown()
} finally {
await ctx.fiber.dispose()
await rm(storageDir, { recursive: true, force: true })
}
})
it('notifies the host when a subagent run settles', async () => {
const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-end-'))
const ctx = await makeHarness(storageDir)
try {
const transport = new FakeTransport()
const server = new HarnessSdkServer(ctx, transport)
const parentHandle = await ctx.agents.create({
agentId: AgentId('parent-agent'),
sessionId: SessionId('main'),
meta: { cwd: storageDir },
agentOptions: { model: 'deepseek' },
})
const handle = await ctx.agents.create({
agentId: AgentId('child-agent'),
sessionId: SessionId('child-session'),
meta: { cwd: storageDir, parentSession: SessionId('main') },
agentOptions: { model: 'deepseek' },
})
await settleSubagent(ctx, parentHandle.agent, {
provider: 'spawn',
id: AgentId('child-agent'),
stopReason: 'completed',
lastAssistantMessage: [{ type: 'text', text: 'child done' }],
})
expect(transport.notifications).toContainEqual({
method: 'subagent.finished',
params: {
provider: 'spawn',
agentId: 'child-agent',
parentSessionId: 'main',
childSessionId: 'child-session',
status: 'ok',
stopReason: 'completed',
lastAssistantMessage: [{ type: 'text', text: 'child done' }],
},
})
await handle.dispose()
await parentHandle.dispose()
await server.shutdown()
} finally {
await ctx.fiber.dispose()
await rm(storageDir, { recursive: true, force: true })
}
})
it('falls back to live agent lineage for uncached subagent end events', async () => {
const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-fallback-'))
const ctx = await makeHarness(storageDir)
let parentHandle: AgentHandle | undefined
let handle: AgentHandle | undefined
let failedHandle: AgentHandle | undefined
try {
parentHandle = await ctx.agents.create({
agentId: AgentId('fallback-parent-agent'),
sessionId: SessionId('fallback-parent'),
meta: { cwd: storageDir },
agentOptions: { model: 'deepseek' },
})
handle = await ctx.agents.create({
agentId: AgentId('fallback-child-agent'),
sessionId: SessionId('fallback-child-session'),
meta: { cwd: storageDir, parentSession: SessionId('fallback-parent') },
agentOptions: { model: 'deepseek' },
})
failedHandle = await ctx.agents.create({
agentId: AgentId('failed-child-agent'),
sessionId: SessionId('failed-child-session'),
meta: { cwd: storageDir },
agentOptions: { model: 'deepseek' },
})
const transport = new FakeTransport()
const server = new HarnessSdkServer(ctx, transport)
await settleSubagent(ctx, parentHandle.agent, {
provider: 'fork',
id: AgentId('fallback-child-agent'),
stopReason: 'max-tokens',
lastAssistantMessage: [],
})
await settleSubagent(ctx, parentHandle.agent, {
provider: 'fork',
id: AgentId('failed-child-agent'),
stopReason: 'error',
})
await settleSubagent(ctx, parentHandle.agent, {
provider: 'fork',
id: AgentId('missing-child-agent'),
stopReason: 'error',
})
expect(transport.notifications).toContainEqual({
method: 'subagent.finished',
params: {
provider: 'fork',
agentId: 'fallback-child-agent',
parentSessionId: 'fallback-parent',
childSessionId: 'fallback-child-session',
status: 'error',
stopReason: 'max-tokens',
lastAssistantMessage: [],
},
})
expect(transport.notifications).toContainEqual({
method: 'subagent.finished',
params: {
provider: 'fork',
agentId: 'failed-child-agent',
childSessionId: 'failed-child-session',
status: 'error',
stopReason: 'error',
},
})
expect(transport.notifications.some(n =>
n.method === 'subagent.finished'
&& n.params?.agentId === 'missing-child-agent',
)).toBe(false)
await server.shutdown()
} finally {
await handle?.dispose()
await failedHandle?.dispose()
await parentHandle?.dispose()
await ctx.fiber.dispose()
await rm(storageDir, { recursive: true, force: true })
}
})
it('does not re-register an LLM adapter that already exists', async () => {
const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-existing-llm-'))
const ctx = await makeHarness(storageDir)
vi.stubEnv('DEEPSEEK_API_KEY', 'test-key')
await ctx.plugin(LlmDeepSeek, { models: ['preinstalled-model'] })
try {
const server = new HarnessSdkServer(ctx, new FakeTransport())
const inspect = server as unknown as { hasAdapterFor(model: string): boolean }
expect(inspect.hasAdapterFor('preinstalled-model')).toBe(true)
expect(inspect.hasAdapterFor('missing-model')).toBe(false)
await server.initialize({ cwd: storageDir, model: 'preinstalled-model' })
expect(ctx.get('llm')?.models().filter(model => model === 'preinstalled-model')).toEqual(['preinstalled-model'])
await server.shutdown()
} finally {
await ctx.fiber.dispose()
await rm(storageDir, { recursive: true, force: true })
}
})
it('registers a missing model when an LLM service already exists', async () => {
const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-new-llm-'))
const ctx = await makeHarness(storageDir)
vi.stubEnv('DEEPSEEK_API_KEY', 'test-key')
await ctx.plugin(LlmDeepSeek, { models: ['other-model'] })
try {
const server = new HarnessSdkServer(ctx, new FakeTransport())
await server.initialize({ cwd: storageDir, model: 'new-model' })
expect(ctx.get('llm')?.models()).toEqual(expect.arrayContaining(['other-model', 'new-model']))
await server.shutdown()
} finally {
await ctx.fiber.dispose()
await rm(storageDir, { recursive: true, force: true })
}
})
it('classifies defensive finish states', async () => {
const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-finish-states-'))
const ctx = await makeHarness(storageDir)
try {
const server = new HarnessSdkServer(ctx, new FakeTransport()) as unknown as {
finishedStatus(reason: unknown): 'ok' | 'error'
shutdown(): Promise<Record<string, never>>
}
expect(server.finishedStatus(undefined)).toBe('error')
expect(server.finishedStatus({ kind: 'max-tokens' })).toBe('error')
expect(server.finishedStatus({ kind: 'error' })).toBe('error')
await server.shutdown()
} finally {
await ctx.fiber.dispose()
await rm(storageDir, { recursive: true, force: true })
}
})
it('reports no adapter when the LLM service is absent', async () => {
const ctx = new Context()
try {
const server = new HarnessSdkServer(ctx, new FakeTransport()) as unknown as {
hasAdapterFor(model: string): boolean
shutdown(): Promise<Record<string, never>>
}
expect(server.hasAdapterFor('missing-model')).toBe(false)
await server.shutdown()
} finally {
await ctx.fiber.dispose()
}
})
it('rejects unknown JSON-RPC runtime methods', async () => {
const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-unknown-'))
const ctx = await makeHarness(storageDir)
try {
const server = new HarnessSdkServer(ctx, new FakeTransport())
await expect(server.handleRequest('does/not/exist', {}))
.rejects
.toThrow('unknown DeepSeek Harness SDK runtime method: does/not/exist')
await server.shutdown()
} finally {
await ctx.fiber.dispose()
await rm(storageDir, { recursive: true, force: true })
}
})
it('coalesces concurrent session creation and retries a failed creation', async () => {
let resolveShared: ((handle: AgentHandle) => void) | undefined
const sharedCreation = new Promise<AgentHandle>((resolve) => { resolveShared = resolve })
const sharedHandle = { agent: {} as Agent, dispose: vi.fn(() => Promise.resolve()) }
const retryHandle = { agent: {} as Agent, dispose: vi.fn(() => Promise.resolve()) }
const create = vi.fn<(options: unknown) => Promise<AgentHandle>>()
.mockReturnValueOnce(sharedCreation)
.mockRejectedValueOnce(new Error('creation failed'))
.mockResolvedValueOnce(retryHandle)
const ctx = {
on: vi.fn(() => () => undefined),
agents: { create, get: () => undefined },
get: () => undefined,
} as unknown as Context
const server = new HarnessSdkServer(ctx, new FakeTransport()) as unknown as {
getOrCreateSession(sessionId: string): Promise<{ handle: AgentHandle }>
shutdown(): Promise<Record<string, never>>
}
const first = server.getOrCreateSession('shared')
const second = server.getOrCreateSession('shared')
expect(create).toHaveBeenCalledTimes(1)
resolveShared?.(sharedHandle)
const [firstRecord, secondRecord] = await Promise.all([first, second])
expect(firstRecord).toBe(secondRecord)
await expect(server.getOrCreateSession('retry')).rejects.toThrow('creation failed')
await expect(server.getOrCreateSession('retry')).resolves.toMatchObject({ handle: retryHandle })
expect(create).toHaveBeenCalledTimes(3)
await server.shutdown()
expect(sharedHandle.dispose).toHaveBeenCalledOnce()
expect(retryHandle.dispose).toHaveBeenCalledOnce()
await expect(server.getOrCreateSession('after-shutdown')).rejects.toThrow('SDK server is shutting down')
})
it('resolves a relative cwd before creating the session', async () => {
const create = vi.fn<(options: unknown) => Promise<AgentHandle>>()
.mockResolvedValue({ agent: {} as Agent, dispose: () => Promise.resolve() })
const ctx = {
on: vi.fn(() => () => undefined),
agents: { create, get: () => undefined },
get: () => ({ models: () => ['model'] }),
} as unknown as Context
const server = new HarnessSdkServer(ctx, new FakeTransport()) as unknown as {
initialize(params: { cwd: string; model: string }): Promise<unknown>
getOrCreateSession(sessionId: string): Promise<unknown>
shutdown(): Promise<Record<string, never>>
}
await server.initialize({ cwd: '.', model: 'model' })
await server.getOrCreateSession('relative')
expect(create).toHaveBeenCalledWith(expect.objectContaining({ meta: { cwd: process.cwd() } }))
await server.shutdown()
})
it('settles every teardown and aggregates multiple failures', async () => {
const firstDispose = vi.fn(() => { throw new Error('first teardown failed') })
const secondDispose = vi.fn(() => Promise.reject(new Error('second teardown failed')))
const ctx = {
on: vi.fn(() => () => undefined),
agents: { create: vi.fn(), get: () => undefined },
get: () => undefined,
} as unknown as Context
const server = new HarnessSdkServer(ctx, new FakeTransport()) as unknown as {
sessions: Map<string, { handle: AgentHandle; lastTurnEnd: undefined; activePrompt: boolean }>
shutdown(): Promise<Record<string, never>>
}
server.sessions.set('first', { handle: { agent: {} as Agent, dispose: firstDispose }, lastTurnEnd: undefined, activePrompt: false })
server.sessions.set('second', { handle: { agent: {} as Agent, dispose: secondDispose }, lastTurnEnd: undefined, activePrompt: false })
await expect(server.shutdown()).rejects.toThrow('SDK server teardown failed')
expect(firstDispose).toHaveBeenCalledOnce()
expect(secondDispose).toHaveBeenCalledOnce()
})
it('continues teardown after a subscription disposer fails', async () => {
let subscription = 0
const listenerFailure = new Error('listener teardown failed')
const on = vi.fn(() => {
subscription += 1
return subscription === 1 ? () => { throw listenerFailure } : () => undefined
})
const ctx = {
on,
agents: { create: vi.fn(), get: () => undefined },
get: () => undefined,
} as unknown as Context
const server = new HarnessSdkServer(ctx, new FakeTransport())
await expect(server.shutdown()).rejects.toBe(listenerFailure)
expect(on).toHaveBeenCalledTimes(4)
})
})
packages/ui/jsonrpc/tests/transport.spec.ts
+260
View File
@@ -0,0 +1,260 @@
import { once } from 'node:events'
import { PassThrough, Writable } from 'node:stream'
import { describe, expect, it } from 'vitest'
import { JsonRpcLineTransport } from '../src/index.ts'
function transportPair() {
const aToB = new PassThrough()
const bToA = new PassThrough()
const a = new JsonRpcLineTransport(bToA, aToB)
const b = new JsonRpcLineTransport(aToB, bToA)
return { a, b, aToB, bToA }
}
describe('JsonRpcLineTransport', () => {
it('supports bidirectional requests and notifications over newline-delimited JSON-RPC', async () => {
const { a, b } = transportPair()
const notifications: Record<string, unknown>[] = []
a.onRequest(async (method, params) => {
expect(method).toBe('echo')
return { echoed: params }
})
b.onNotification((method, params) => {
notifications.push({ method, params })
})
a.start()
b.start()
const response = await b.request('echo', { value: 42 })
expect(response).toEqual({ echoed: { value: 42 } })
a.notify('session.finished', { sessionId: 'main', status: 'ok' })
a.notify('heartbeat')
await new Promise(resolve => setTimeout(resolve, 10))
expect(notifications).toEqual([
{ method: 'session.finished', params: { sessionId: 'main', status: 'ok' } },
{ method: 'heartbeat', params: {} },
])
a.close()
b.close()
})
it('reports JSON-RPC request errors from the remote peer', async () => {
const { a, b } = transportPair()
a.onRequest(async () => {
throw new Error('handler boom')
})
a.start()
b.start()
await expect(b.request('explode', {})).rejects.toThrow('handler boom')
a.close()
b.close()
})
it('stringifies non-Error request handler failures', async () => {
const { a, b } = transportPair()
a.onRequest(async () => {
throw 'string boom'
})
a.start()
b.start()
await expect(b.request('explode-string', {})).rejects.toThrow('string boom')
a.close()
b.close()
})
it('reports method-not-found when no request handler is installed', async () => {
const { a, b } = transportPair()
a.start()
b.start()
await expect(b.request('missing', {})).rejects.toThrow('method not found: missing')
a.close()
b.close()
})
it('normalizes non-object request params and ignores notifications without a handler', async () => {
const { aToB, bToA, b } = transportPair()
const seen: Record<string, unknown>[] = []
b.onRequest(async (method, params) => {
seen.push({ method, params })
return { ok: true }
})
b.start()
aToB.write('{"jsonrpc":"2.0","method":"ignored"}\n')
aToB.write('{"jsonrpc":"2.0","id":7,"method":"array-params","params":[]}\n')
const chunk = (await once(bToA, 'data'))[0] as Buffer | string
expect(seen).toEqual([{ method: 'array-params', params: {} }])
expect(JSON.parse(String(chunk))).toEqual({ jsonrpc: '2.0', id: 7, result: { ok: true } })
b.close()
})
it('ignores malformed frames and accepts notifications without params', async () => {
const { aToB, b } = transportPair()
const notifications: Record<string, unknown>[] = []
b.onNotification((method, params) => {
notifications.push({ method, params })
})
b.start()
b.start()
aToB.write('not json\n')
aToB.write('\n')
aToB.write('null\n')
aToB.write('{"jsonrpc":"2.0","params":{}}\n')
aToB.write('{"jsonrpc":"2.0","method":"tick"}\n')
aToB.emit('data', '{"jsonrpc":"2.0","method":"string-chunk"}\n')
await new Promise(resolve => setTimeout(resolve, 10))
expect(notifications).toEqual([
{ method: 'tick', params: {} },
{ method: 'string-chunk', params: {} },
])
b.close()
})
it('preserves multibyte UTF-8 characters split across Buffer chunks', async () => {
const input = new PassThrough()
const output = new PassThrough()
const transport = new JsonRpcLineTransport(input, output)
const notifications: Record<string, unknown>[] = []
transport.onNotification((method, params) => { notifications.push({ method, params }) })
transport.start()
const frame = Buffer.from(`${JSON.stringify({ jsonrpc: '2.0', method: 'message', params: { text: '你好' } })}\n`)
const character = Buffer.from('你')
const characterStart = frame.indexOf(character)
expect(characterStart).toBeGreaterThanOrEqual(0)
input.write(frame.subarray(0, characterStart + 1))
input.write(frame.subarray(characterStart + 1))
await new Promise(resolve => setTimeout(resolve, 10))
expect(notifications).toEqual([{ method: 'message', params: { text: '你好' } }])
transport.close()
})
it('flush waits for all earlier output writes', async () => {
const events: string[] = []
const output = new Writable({
write(chunk: Buffer, _encoding, callback) {
const label = chunk.length === 0 ? 'barrier' : 'frame'
events.push(`start:${label}`)
setTimeout(() => {
events.push(`finish:${label}`)
callback()
}, 5)
},
})
const transport = new JsonRpcLineTransport(new PassThrough(), output)
transport.notify('tick')
await transport.flush()
expect(events).toEqual([
'start:frame',
'finish:frame',
'start:barrier',
'finish:barrier',
])
transport.close()
})
it('reports an output callback failure from flush', async () => {
const output = {
write(_chunk: string, callback?: (error?: Error) => void) {
callback?.(new Error('flush failed'))
return true
},
}
const transport = new JsonRpcLineTransport(new PassThrough(), output as never)
await expect(transport.flush()).rejects.toThrow('flush failed')
})
it('rejects pending requests when the input closes', async () => {
const { aToB, b } = transportPair()
b.start()
const pending = b.request('never-replies', {})
aToB.end()
await expect(pending).rejects.toThrow('JSON-RPC input closed')
b.close()
})
it('rejects pending requests when the input errors', async () => {
const { aToB, b } = transportPair()
b.start()
const pending = b.request('never-replies', {})
aToB.emit('error', new Error('input broke'))
await expect(pending).rejects.toThrow('input broke')
b.close()
})
it('rejects pending requests when the transport closes', async () => {
const { b } = transportPair()
const pending = b.request('never-replies', {})
b.close()
await expect(pending).rejects.toThrow('JSON-RPC transport closed')
})
it('rejects a request when writing the frame throws', async () => {
const input = new PassThrough()
const output = {
write() {
throw new Error('write exploded')
},
}
const transport = new JsonRpcLineTransport(input, output as never)
await expect(transport.request('write-fails', {})).rejects.toThrow('write exploded')
})
it('stringifies non-Error write failures', async () => {
const input = new PassThrough()
const output = {
write() {
throw 'write string'
},
}
const transport = new JsonRpcLineTransport(input, output as never)
await expect(transport.request('write-fails', {})).rejects.toThrow('write string')
})
it('uses a fallback message for malformed JSON-RPC error responses', async () => {
const { aToB, bToA, b } = transportPair()
b.start()
const pending = b.request('remote-error', {})
const requestChunk = (await once(bToA, 'data'))[0] as Buffer | string
const request = JSON.parse(String(requestChunk)) as { id: string }
aToB.write(`${JSON.stringify({ jsonrpc: '2.0', id: request.id, error: {} })}\n`)
await expect(pending).rejects.toThrow('JSON-RPC error')
b.close()
})
it('ignores responses that do not match a pending request', async () => {
const { aToB, b } = transportPair()
b.start()
aToB.write('{"jsonrpc":"2.0","id":"unknown","result":{"ignored":true}}\n')
await new Promise(resolve => setTimeout(resolve, 10))
b.close()
})
})
packages/ui/jsonrpc/tsconfig.json
+33
View File
@@ -0,0 +1,33 @@
{
"extends": "../../../tsconfig.base.json",
"compilerOptions": {
"rootDir": "src",
"outDir": "lib/types"
},
"include": [
"src"
],
"references": [
{
"path": "../../../vendor/cordis"
},
{
"path": "../../../vendor/schemastery"
},
{
"path": "../../llm/llm"
},
{
"path": "../../llm/llm-deepseek"
},
{
"path": "../../core/agent"
},
{
"path": "../../core/session"
},
{
"path": "../../subagent/subagent"
}
]
}
packages/ui/stdio-agent/src/index.ts
+2
View File
@@ -96,6 +96,8 @@ export const Config: z<Config> = z.object({
toolOrder: z.array(z.string()).default(undefined as unknown as string[]),
tools: ToolRegistry.Config,
dshHome: z.string(),
// TODO(single-default-literal): share these schema defaults and defensive
// apply() fallbacks through named constants while retaining both boundaries.
persistenceRoot: z.string().default('./.sessions'),
welcome: z.string().default('ready.'),
skills: agentCore.SkillConfigSchema,
packages/ui/stdio-agent/src/stdio-chat.ts
+2
View File
@@ -36,6 +36,8 @@ export const inject = ['agents', 'userInteraction']
export interface Config {
/** Banner printed once on start, before the first `> ` prompt. */
welcome?: string
// TODO(fixed-stdio-agent): this app-internal plugin is mounted only for the
// precreated `main` agent; remove configurability and its config-only test.
/** Id of the agent stdin drives (`send`/`steer`) and whose status gates the EOF exit; rendering is global. Defaults to `'main'`. */
agent?: string
}
packages/web/web-search-perplexity/src/provider.ts
+8
View File
@@ -99,12 +99,16 @@ export class PerplexitySearchProvider implements WebSearchProvider {
constructor(private readonly options: PerplexitySearchProviderOptions) {}
// Availability checks stay beside each provider's distinct config contract;
// a shared base class would obscure which fields make this backend usable.
/* jscpd:ignore-start */
status(): WebProviderStatus {
if (this.options.apiKey.length === 0) return { available: false, reason: 'missing-credential' }
if (!URL.canParse(this.options.baseURL)) return { available: false, reason: 'misconfigured' }
if (!isPositiveInteger(this.options.maxTokens)) return { available: false, reason: 'misconfigured' }
return { available: true }
}
/* jscpd:ignore-end */
async search(request: WebSearchRequest, exec?: { readonly signal?: AbortSignal }): Promise<WebSearchResult> {
let response: Response
@@ -159,6 +163,9 @@ export class PerplexitySearchProvider implements WebSearchProvider {
}
}
// These two predicates are intentionally local: exporting generic internals
// from the public web seam would cost more API surface than these pure checks.
/* jscpd:ignore-start */
/** True for a fetch/`AbortSignal` abort, surfaced as `WEB_ABORTED`. */
function isAbortError(error: unknown): boolean {
return error instanceof DOMException && error.name === 'AbortError'
@@ -168,3 +175,4 @@ function isAbortError(error: unknown): boolean {
function isPositiveInteger(value: number): boolean {
return Number.isInteger(value) && value > 0
}
/* jscpd:ignore-end */
packages/workflow/tool-workflow/README.md
+2 -2
View File
@@ -4,7 +4,7 @@ The model-facing **`workflow` tool**: run a JavaScript orchestration script that
## What the model sees
Two parameters: `script` (required — the full `export const meta = {...}` + body text; the tool DESCRIPTION carries the complete authoring contract: hooks, semantics, the supported schema subset) and `args` (optional JSON object exposed to the script as the `args` global; a bare list is wrapped as a field, a deliberate deviation from Claude Code's any-JSON `args` so the wire schema stays honest). The plugin also contributes a `tool:<toolName>` system-prompt section carrying the usage policy — use the tool only on an explicit user ask for a workflow / large orchestration; prefer plain subagent calls for one or two delegations — per the convention that tool guidance ships with the tool plugin, never in the deployment persona.
Three parameters: `meta` (required identity data: `name`, `description`, and optional progress annotations), `script` (required plain JavaScript body — no `export const meta` statement; the tool description carries the complete authoring contract), and `args` (optional JSON object exposed to the script as the `args` global; wrap a bare list in a field so the wire schema stays honest). The plugin also contributes a `tool:<toolName>` system-prompt section carrying the usage policy — use the tool only on an explicit user ask for a workflow / large orchestration; prefer plain subagent calls for one or two delegations — per the convention that tool guidance ships with the tool plugin, never in the deployment persona.
## Lifecycle
@@ -12,7 +12,7 @@ Collection is SYNCHRONOUS this cut (like [`dsh-tool-subagent`](../../subagent/to
## Render intent
Decided up front (per the [render-intent RFC](../../../docs/rfc/implemented/architecture/2026-07-02-tool-render-intent-union.md)): a `generic` card titled `workflow: <meta.name>`, the name sniffed TEXTUALLY from `args.script` (presentation must be a pure function of args, so it cannot ask the engine to parse); the script text rides as `rawInput`. The result keeps the generic card.
Decided up front (per the [render-intent RFC](../../../docs/rfc/implemented/architecture/2026-07-02-tool-render-intent-union.md)): a `generic` card titled `workflow: <meta.name>`, read directly from `args.meta.name` (presentation is a pure function of args and does not ask the engine to parse); the script text rides as `rawInput`. The result keeps the generic card.
## Config
packages/workflow/workflow-workerthread/README.md
+1 -1
View File
@@ -32,7 +32,7 @@ Unknown options, malformed arguments, unsupported schemas, tripped caps, provide
## Run sequence
`start()` validates meta and parses the body, creates the worker, and returns a holder-owned `WorkflowRun`. A ready/go handshake prevents a start-signal cancellation racing worker boot from executing the script's initial synchronous slice.
`start()` validates meta and parses the body, creates the worker, and returns a holder-owned `WorkflowRun`. Source mode uses a data-URL bootstrap that installs the TypeScript transforms inside the worker; built mode passes the sibling CommonJS bundle `lib/worker.cjs` as a filesystem string. CommonJS is required because pkg's VFS Worker hook compiles filesystem-string entries in that format; the same entry also works under ordinary Node resolution. A ready/go handshake prevents a start-signal cancellation racing worker boot from executing the script's initial synchronous slice.
For each `agent()` call:
packages/workflow/workflow-workerthread/package.json
+2 -2
View File
@@ -13,14 +13,14 @@
},
"./worker": {
"types": "./lib/types/worker.d.ts",
"default": "./lib/worker.js"
"default": "./lib/worker.cjs"
},
"./src/*": "./src/*",
"./package.json": "./package.json"
},
"files": [
"lib/index.js",
"lib/worker.js",
"lib/worker.cjs",
"lib/types/**/*.d.ts",
"lib/types/**/*.d.ts.map",
"src"
packages/workflow/workflow-workerthread/src/host.ts
+4 -3
View File
@@ -43,6 +43,7 @@
import { Worker } from 'node:worker_threads'
import type { WorkerOptions } from 'node:worker_threads'
import { fileURLToPath } from 'node:url'
import type { Context } from 'cordis'
import type { Agent } from '@deepseek-ai/dsh-agent'
import { assertNever } from '@deepseek-ai/dsh-llm'
@@ -87,12 +88,12 @@ interface ChildRecord {
* AMBIENT channel only — an escapee still holds process-wide privileges
* like fs access (the README's trust premise stands).
* @param init - the run payload, passed as `workerData`.
* @returns the entry URL and the Worker options to spawn it with.
* @returns the entry path or URL and the Worker options to spawn it with.
*/
function resolveWorkerSpawn(init: WorkerInit): { entry: URL; options: WorkerOptions } {
function resolveWorkerSpawn(init: WorkerInit): { entry: string | URL; options: WorkerOptions } {
/* v8 ignore next 3 -- the built-output arm: tests always run unbuilt (src/); the built-worker e2e exercises this shape for real */
if (!import.meta.url.endsWith('.ts')) {
return { entry: new URL('./worker.js', import.meta.url), options: { workerData: init, env: {}, execArgv: [] } }
return { entry: fileURLToPath(new URL('./worker.cjs', import.meta.url)), options: { workerData: init, env: {}, execArgv: [] } }
}
// Resolve tsx lazily: only the unbuilt shape executes this arm, so a built
// consumer never needs the dev-only loader installed. A JavaScript entry is
packages/workflow/workflow-workerthread/tests/built-worker.e2e.ts
+3 -3
View File
@@ -8,17 +8,17 @@ import { describe, expect, it } from 'vitest'
const packageRoot = fileURLToPath(new URL('..', import.meta.url))
const builtIndex = join(packageRoot, 'lib', 'index.js')
const builtWorker = join(packageRoot, 'lib', 'worker.js')
const builtWorker = join(packageRoot, 'lib', 'worker.cjs')
const run = promisify(execFile)
/**
* The BUILT-output guard for the worker entry: every other suite runs
* unbuilt (src/ + tsx), so nothing else proves that `lib/index.js` resolves
* its sibling `lib/worker.js` and that the bundle boots a worker under plain
* its sibling `lib/worker.cjs` and that the bundle boots a worker under plain
* node (no tsx loader). Keyless — a zero-agent script needs no provider —
* and self-skips until `pnpm run build` has produced the bundles.
*/
describe.skipIf(!existsSync(builtIndex) || !existsSync(builtWorker))('built worker entry (lib/worker.js)', () => {
describe.skipIf(!existsSync(builtIndex) || !existsSync(builtWorker))('built worker entry (lib/worker.cjs)', () => {
it('the built engine spawns its built worker under plain node and completes a run', async () => {
// ESM resolves bare specifiers from the IMPORTING FILE's location, so the
// driver must live inside the package for its node_modules to apply — a
packages/workflow/workflow-workerthread/tsdown.config.ts
+4 -2
View File
@@ -6,7 +6,9 @@ import { defineConfig } from 'tsdown'
* entries are JS emitted by tsc under lib/types and are bundled as two
* single-entry passes so shared modules (realm, runtime, session) are inlined
* into each instead of split into a hash-named chunk (the worker entry must
* be a self-contained file the Worker constructor can load by path).
* be a self-contained file the Worker constructor can load by path). The
* worker bundle is CommonJS because pkg's VFS Worker hook compiles
* filesystem-string entries as CommonJS.
*/
export default defineConfig([
{
@@ -22,7 +24,7 @@ export default defineConfig([
{
entry: ['lib/types/worker.js'],
outDir: 'lib',
format: ['esm'],
format: ['cjs'],
platform: 'node',
target: 'es2024',
fixedExtension: false,
pnpm-lock.yaml
Generated
+412
View File
@@ -29,9 +29,15 @@ importers:
eslint:
specifier: ^10.4.1
version: 10.5.0(jiti@2.7.0)
eslint-plugin-sonarjs:
specifier: ^4.1.0
version: 4.1.0(eslint@10.5.0(jiti@2.7.0))
fast-check:
specifier: ^4.8.0
version: 4.8.0
jscpd:
specifier: ^5.0.12
version: 5.0.12
jsdom:
specifier: 29.1.1
version: 29.1.1
@@ -1283,6 +1289,50 @@ importers:
specifier: ^4.0.0-rc.6
version: 4.0.0-rc.6(@cordisjs/plugin-include@vendor+include)(@cordisjs/plugin-loader@vendor+loader)
packages/ui/jsonrpc:
dependencies:
schemastery:
specifier: ^3.17.0
version: 3.18.0
devDependencies:
'@cordisjs/plugin-loader':
specifier: workspace:^
version: link:../../../vendor/loader
'@deepseek-ai/dsh-agent':
specifier: workspace:^
version: link:../../core/agent
'@deepseek-ai/dsh-agent-core':
specifier: workspace:^
version: link:../../core/agent-core
'@deepseek-ai/dsh-llm':
specifier: workspace:^
version: link:../../llm/llm
'@deepseek-ai/dsh-llm-deepseek':
specifier: workspace:^
version: link:../../llm/llm-deepseek
'@deepseek-ai/dsh-session':
specifier: workspace:^
version: link:../../core/session
'@deepseek-ai/dsh-session-persistence-jsonl':
specifier: workspace:^
version: link:../../session-persistence/session-persistence-jsonl
'@deepseek-ai/dsh-subagent':
specifier: workspace:^
version: link:../../subagent/subagent
cordis:
specifier: ^4.0.0-rc.6
version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@vendor+loader)
packages/ui/jsonrpc-agent:
dependencies:
'@deepseek-ai/dsh-app-boot':
specifier: workspace:^
version: link:../app-boot
devDependencies:
cordis:
specifier: ^4.0.0-rc.6
version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4)
packages/ui/stdio-agent:
devDependencies:
'@cordisjs/plugin-include':
@@ -1613,6 +1663,204 @@ importers:
specifier: ^4.19.2
version: 4.22.4
python/sdk-runtime:
dependencies:
'@cordisjs/plugin-include':
specifier: workspace:^
version: link:../../vendor/include
'@cordisjs/plugin-loader':
specifier: workspace:^
version: link:../../vendor/loader
'@cordisjs/plugin-timer':
specifier: workspace:^
version: link:../../vendor/timer
'@deepseek-ai/dsh-acp':
specifier: workspace:^
version: link:../../packages/ui/acp
'@deepseek-ai/dsh-agent':
specifier: workspace:^
version: link:../../packages/core/agent
'@deepseek-ai/dsh-agent-core':
specifier: workspace:^
version: link:../../packages/core/agent-core
'@deepseek-ai/dsh-agent-loop':
specifier: workspace:^
version: link:../../packages/core/agent-loop
'@deepseek-ai/dsh-app-boot':
specifier: workspace:^
version: link:../../packages/ui/app-boot
'@deepseek-ai/dsh-bash':
specifier: workspace:^
version: link:../../packages/bash/bash
'@deepseek-ai/dsh-bash-local':
specifier: workspace:^
version: link:../../packages/bash/bash-local
'@deepseek-ai/dsh-brand':
specifier: workspace:^
version: link:../../packages/util/brand
'@deepseek-ai/dsh-code-runtime':
specifier: workspace:^
version: link:../../packages/code-runtime/code-runtime
'@deepseek-ai/dsh-code-runtime-worker':
specifier: workspace:^
version: link:../../packages/code-runtime/code-runtime-worker
'@deepseek-ai/dsh-compact':
specifier: workspace:^
version: link:../../packages/compact/compact
'@deepseek-ai/dsh-compact-basic':
specifier: workspace:^
version: link:../../packages/compact/compact-basic
'@deepseek-ai/dsh-fs':
specifier: workspace:^
version: link:../../packages/fs/fs
'@deepseek-ai/dsh-fs-local':
specifier: workspace:^
version: link:../../packages/fs/fs-local
'@deepseek-ai/dsh-fs-policy':
specifier: workspace:^
version: link:../../packages/fs/fs-policy
'@deepseek-ai/dsh-hook-protocol':
specifier: workspace:^
version: link:../../packages/hooks/hook-protocol
'@deepseek-ai/dsh-hooks-claude':
specifier: workspace:^
version: link:../../packages/hooks/hooks-claude
'@deepseek-ai/dsh-hooks-codex':
specifier: workspace:^
version: link:../../packages/hooks/hooks-codex
'@deepseek-ai/dsh-invariants':
specifier: workspace:^
version: link:../../packages/support/invariants
'@deepseek-ai/dsh-jsonrpc':
specifier: workspace:^
version: link:../../packages/ui/jsonrpc
'@deepseek-ai/dsh-jsonrpc-agent':
specifier: workspace:^
version: link:../../packages/ui/jsonrpc-agent
'@deepseek-ai/dsh-llm':
specifier: workspace:^
version: link:../../packages/llm/llm
'@deepseek-ai/dsh-llm-deepseek':
specifier: workspace:^
version: link:../../packages/llm/llm-deepseek
'@deepseek-ai/dsh-llm-pi-ai':
specifier: workspace:^
version: link:../../packages/llm/llm-pi-ai
'@deepseek-ai/dsh-repeat-tool-guard':
specifier: workspace:^
version: link:../../packages/guard/repeat-tool-guard
'@deepseek-ai/dsh-sandbox':
specifier: workspace:^
version: link:../../packages/sandbox/sandbox
'@deepseek-ai/dsh-scope':
specifier: workspace:^
version: link:../../packages/core/scope
'@deepseek-ai/dsh-session':
specifier: workspace:^
version: link:../../packages/core/session
'@deepseek-ai/dsh-session-persistence':
specifier: workspace:^
version: link:../../packages/session-persistence/session-persistence
'@deepseek-ai/dsh-session-persistence-jsonl':
specifier: workspace:^
version: link:../../packages/session-persistence/session-persistence-jsonl
'@deepseek-ai/dsh-session-persistence-sqlite':
specifier: workspace:^
version: link:../../packages/session-persistence/session-persistence-sqlite
'@deepseek-ai/dsh-skill':
specifier: workspace:^
version: link:../../packages/skill/skill
'@deepseek-ai/dsh-skill-local':
specifier: workspace:^
version: link:../../packages/skill/skill-local
'@deepseek-ai/dsh-subagent':
specifier: workspace:^
version: link:../../packages/subagent/subagent
'@deepseek-ai/dsh-subagent-acp':
specifier: workspace:^
version: link:../../packages/subagent/subagent-acp
'@deepseek-ai/dsh-subagent-fork':
specifier: workspace:^
version: link:../../packages/subagent/subagent-fork
'@deepseek-ai/dsh-subagent-inprocess':
specifier: workspace:^
version: link:../../packages/subagent/subagent-inprocess
'@deepseek-ai/dsh-subagent-spawn':
specifier: workspace:^
version: link:../../packages/subagent/subagent-spawn
'@deepseek-ai/dsh-subagent-subprocess':
specifier: workspace:^
version: link:../../packages/subagent/subagent-subprocess
'@deepseek-ai/dsh-system-prompt':
specifier: workspace:^
version: link:../../packages/core/system-prompt
'@deepseek-ai/dsh-timeout':
specifier: workspace:^
version: link:../../packages/util/timeout
'@deepseek-ai/dsh-timeout-policy':
specifier: workspace:^
version: link:../../packages/timeout/timeout-policy
'@deepseek-ai/dsh-tool-ask-user':
specifier: workspace:^
version: link:../../packages/ui/tool-ask-user
'@deepseek-ai/dsh-tool-bash':
specifier: workspace:^
version: link:../../packages/bash/tool-bash
'@deepseek-ai/dsh-tool-cordis':
specifier: workspace:^
version: link:../../packages/cordis/tool-cordis
'@deepseek-ai/dsh-tool-fs':
specifier: workspace:^
version: link:../../packages/fs/tool-fs
'@deepseek-ai/dsh-tool-skill':
specifier: workspace:^
version: link:../../packages/skill/tool-skill
'@deepseek-ai/dsh-tool-subagent':
specifier: workspace:^
version: link:../../packages/subagent/tool-subagent
'@deepseek-ai/dsh-tool-todo':
specifier: workspace:^
version: link:../../packages/todo/tool-todo
'@deepseek-ai/dsh-tool-web':
specifier: workspace:^
version: link:../../packages/web/tool-web
'@deepseek-ai/dsh-tool-workflow':
specifier: workspace:^
version: link:../../packages/workflow/tool-workflow
'@deepseek-ai/dsh-tools':
specifier: workspace:^
version: link:../../packages/core/tools
'@deepseek-ai/dsh-user-approval':
specifier: workspace:^
version: link:../../packages/ui/user-approval
'@deepseek-ai/dsh-user-interaction':
specifier: workspace:^
version: link:../../packages/ui/user-interaction
'@deepseek-ai/dsh-web':
specifier: workspace:^
version: link:../../packages/web/web
'@deepseek-ai/dsh-web-fetch-local':
specifier: workspace:^
version: link:../../packages/web/web-fetch-local
'@deepseek-ai/dsh-web-search-deepseek':
specifier: workspace:^
version: link:../../packages/web/web-search-deepseek
'@deepseek-ai/dsh-web-search-exa':
specifier: workspace:^
version: link:../../packages/web/web-search-exa
'@deepseek-ai/dsh-web-search-perplexity':
specifier: workspace:^
version: link:../../packages/web/web-search-perplexity
'@deepseek-ai/dsh-workflow':
specifier: workspace:^
version: link:../../packages/workflow/workflow
'@deepseek-ai/dsh-workflow-workerthread':
specifier: workspace:^
version: link:../../packages/workflow/workflow-workerthread
cordis:
specifier: workspace:^
version: link:../../vendor/cordis
vendor/cordis:
dependencies:
'@cordisjs/plugin-include':
@@ -3087,6 +3335,14 @@ packages:
buffer-equal-constant-time@1.0.1:
resolution: {integrity: sha512-zRpUiDwd/xk6ADqPMATG8vc9VPrkck7T07OIx0gnjmJAnHnTVXNQG3vfvWNuiZIkwu9KrKdA1iJKfsfTVxE6NA==}
builtin-modules@3.3.0:
resolution: {integrity: sha512-zhaCDicdLuWN5UbN5IMnFqNMhNfo919sH85y2/ea+5Yg9TsTkeZxpL+JLbp6cgYFS4sRLp3YV4S6yDuqVWHYOw==}
engines: {node: '>=6'}
bytes@3.1.2:
resolution: {integrity: sha512-/Nf7TyzTx6S3yRJObOAV7956r8cr2+Oj8AC5dt8wSP3BQAoeX58NoHyCU8P8zGkNXStjTSi6fzO6F0pBdcYbEg==}
engines: {node: '>= 0.8'}
cac@7.0.0:
resolution: {integrity: sha512-tixWYgm5ZoOD+3g6UTea91eow5z6AAHaho3g0V9CNSNb45gM8SmflpAc+GRd1InC4AqN/07Unrgp56Y94N9hJQ==}
engines: {node: '>=20.19.0'}
@@ -3393,6 +3649,11 @@ packages:
resolution: {integrity: sha512-/veY75JbMK4j1yjvuUxuVsiS/hr/4iHs9FTT6cgTexxdE0Ly/glccBAkloH/DofkjRbZU3bnoj38mOmhkZ0lHw==}
engines: {node: '>=12'}
eslint-plugin-sonarjs@4.1.0:
resolution: {integrity: sha512-rh+FlVz0yfd2RNIb6WqSkuGh0addX/Qi5scwQ5FphXDFrM6fZKcxP1+attJ78yUKcyYfiu6MTaISPpAFPzqRJw==}
peerDependencies:
eslint: ^8.0.0 || ^9.0.0 || ^10.0.0
eslint-scope@9.1.2:
resolution: {integrity: sha512-xS90H51cKw0jltxmvmHy2Iai1LIqrfbw57b79w/J7MfvDfkIkFZ+kj6zC3BjtUwh150HsSSdxXZcsuv72miDFQ==}
engines: {node: ^20.19.0 || ^22.13.0 || >=24}
@@ -3518,6 +3779,9 @@ packages:
engines: {node: ^8.16.0 || ^10.6.0 || >=11.0.0}
os: [darwin]
functional-red-black-tree@1.0.1:
resolution: {integrity: sha512-dsKNQNdj6xA3T+QlADDA7mOSlX0qiMINjn0cgr+eGHGsbSHzTabcIogz2+p/iqP1Xs6EP/sS2SbqH+brGTbq0g==}
gaxios@7.1.5:
resolution: {integrity: sha512-5FZy72Rh8LhtjmvDrKkI+lVhrsQrVKVsItxMoDm5mNQE+xR0WVIIs+jzPSJgBvKVsLi24fZhXJIsNI0bihDzFg==}
engines: {node: '>=18'}
@@ -3537,6 +3801,10 @@ packages:
resolution: {integrity: sha512-XxwI8EOhVQgWp6iDL+3b0r86f4d6AX6zSU55HfB4ydCEuXLXc5FcYeOu+nnGftS4TEju/11rt4KJPTMgbfmv4A==}
engines: {node: '>=10.13.0'}
globals@17.7.0:
resolution: {integrity: sha512-Czmyns5dUsq4seFBR/Kdydhmo8y9kC79hiSkPn0YcGtNnYWnrgt0vjrSjx9tspoDGWm2CMarffRuLjM4xUz8xg==}
engines: {node: '>=18'}
globrex@0.1.2:
resolution: {integrity: sha512-uHJgbwAMwNFf5mLst7IWLNg14x1CkeqglJb/K3doi4dw6q2IvAAmM/Y81kevy83wP+Sst+nutFTYOGg3d1lsxg==}
@@ -3643,6 +3911,44 @@ packages:
resolution: {integrity: sha512-ePWsvanv0DWuDRsW8dnt+R4jQ31SCRCQ7hhNcPXZPsoBZiemuZNYGf7adZdqX2D86j6rvKp3RpCxVTSb8WQlOw==}
hasBin: true
jscpd-darwin-arm64@5.0.12:
resolution: {integrity: sha512-CQCDYhQY9yOGGeauzkRGYW/QtXurPCjfDkEhUoM/M5UdmpzxfG3i9mnNsaheJ0RdFRf73mL7JaLVRP8U2l5/kA==}
cpu: [arm64]
os: [darwin]
jscpd-darwin-x64@5.0.12:
resolution: {integrity: sha512-7XNCDfChP9fPkIWLepd0zGnTov7/5mR7rJ5Utc1MdWFdgkN//qz6FAJ1FhQA0E/qjFedy9XTucfUCgLybSBsjw==}
cpu: [x64]
os: [darwin]
jscpd-linux-arm64-gnu@5.0.12:
resolution: {integrity: sha512-i/usHD0/8twzb2Qo4vFWcnuAD4IDLS6K/mTXwYy1CiJZDw4gmjfH45jtjdKUyoutTAiNs+ZWZgx1gIRljUbFuA==}
cpu: [arm64]
os: [linux]
libc: [glibc]
jscpd-linux-x64-gnu@5.0.12:
resolution: {integrity: sha512-TqaeSTaGawcqyXSrQvYJFtLRn4aQeHgphGGsq2ZtVAg+lPeuMmh81c3bl0yi2dL3gDX1RGBQKBVul1XQknOuoA==}
cpu: [x64]
os: [linux]
libc: [glibc]
jscpd-linux-x64-musl@5.0.12:
resolution: {integrity: sha512-WelugY1/rdoo0Y0sqJ2XQOIvyIZTfRe+vP3MJe4XvEUwPF0v+9SQoS34FnfblRhsddVixyNkgl7x/sHid9UMJw==}
cpu: [x64]
os: [linux]
libc: [musl]
jscpd-windows-x64-msvc@5.0.12:
resolution: {integrity: sha512-01x1klKjvfzI6Of5tI9u72x7TIQZQLLG6kMdsEPJKl/BXbskdknrfCepeTXRBbdFPKs25jfcd0klZ4OdDvww5w==}
cpu: [x64]
os: [win32]
jscpd@5.0.12:
resolution: {integrity: sha512-87dC+akj2mCywlt8p3xnRlDg0B55u4GDbfE9cuwOOeIxbEuWuIoNqGoYi65A0516aJ4EzAjGwBj1Qb/Ahc8WAQ==}
engines: {node: '>=18'}
hasBin: true
jsdom@29.1.1:
resolution: {integrity: sha512-ECi4Fi2f7BdJtUKTflYRTiaMxIB0O6zfR1fX0GXpUrf6flp8QIYn1UT20YQqdSOfk2dfkCwS8LAFoJDEppNK5Q==}
engines: {node: ^20.19.0 || ^22.13.0 || >=24.0.0}
@@ -3673,6 +3979,10 @@ packages:
json-stable-stringify-without-jsonify@1.0.1:
resolution: {integrity: sha512-Bdboy+l7tA3OGW6FjyFHWkP5LuByj1Tk33Ljyq0axyzdk9//JSi2u3fP1QSmd1KNwq6VOKYGlAu87CisVir6Pw==}
jsx-ast-utils-x@0.1.0:
resolution: {integrity: sha512-eQQBjBnsVtGacsG9uJNB8qOr3yA8rga4wAaGG1qRcBzSIvfhERLrWxMAM1hp5fcS6Abo8M4+bUBTekYR0qTPQw==}
engines: {node: ^18.18.0 || ^20.9.0 || >=21.1.0}
jwa@2.0.1:
resolution: {integrity: sha512-hRF04fqJIP8Abbkq5NKGN0Bbr3JxlQ+qhZufXVr0DvujKy93ZCbXZMHDL4EOtodSbCWxOqR8MS1tXA5hwqCXDg==}
@@ -3839,6 +4149,9 @@ packages:
lodash-es@4.18.1:
resolution: {integrity: sha512-J8xewKD/Gk22OZbhpOVSwcs60zhd95ESDwezOFuA3/099925PdHJ7OFHNTGtajL3AlZkykD32HykiMo+BIBI8A==}
lodash.merge@4.6.2:
resolution: {integrity: sha512-0KpjqXRVvrYyCsX1swR/XTK0va6VQkQM6MNo7PqW77ByjAhoARA8EfrP1N4+KlKj8YS0ZUCtRT/YUuhyYDujIQ==}
long@5.3.2:
resolution: {integrity: sha512-mNAgZ1GmyNhD7AuqnTG3/VQ26o760+ZYBPKjPvugO8+nLbYfX6TVpJPseBvopbdY+qpZ/lKUnmEc1LeZYS3QAA==}
@@ -4144,6 +4457,14 @@ packages:
resolution: {integrity: sha512-GDhwkLfywWL2s6vEjyhri+eXmfH6j1L7JE27WhqLeYzoh/A3DBaYGEj2H/HFZCn/kMfim73FXxEJTw06WtxQwg==}
engines: {node: '>= 14.18.0'}
refa@0.12.1:
resolution: {integrity: sha512-J8rn6v4DBb2nnFqkqwy6/NnTYMcgLA+sLr0iIO41qpv0n+ngb7ksag2tMRl0inb1bbO/esUwzW1vbJi7K0sI0g==}
engines: {node: ^12.0.0 || ^14.0.0 || >=16.0.0}
regexp-ast-analysis@0.7.1:
resolution: {integrity: sha512-sZuz1dYW/ZsfG17WSAG7eS85r5a0dDsvg+7BiiYR5o6lKCAtUrEwdmRmaGF6rwVj3LcmAeYkOWKEPlbPzN3Y3A==}
engines: {node: ^12.0.0 || ^14.0.0 || >=16.0.0}
require-from-string@2.0.2:
resolution: {integrity: sha512-Xf0nWe6RseziFMu+Ap9biiUbmplq6S9/p+7w7YXP/JBHhrUDDUhwa+vANyubuqfZWTveU//DYVGsDG7RKL/vEw==}
engines: {node: '>=0.10.0'}
@@ -4210,6 +4531,10 @@ packages:
schemastery@3.18.0:
resolution: {integrity: sha512-Jw2uxjoyyqc/yeurmChUEc/jbi8GsrdXV/KmqRUDZXJAXAmrJiPsz8vKa17l/VckyzljHZ9oGaul443CQiXxtA==}
scslre@0.3.0:
resolution: {integrity: sha512-3A6sD0WYP7+QrjbfNA2FN3FsOaGGFoekCVgTyypy53gPxhbkCIjtO6YWgdrfM+n/8sI8JeXZOIxsHjMTNxQ4nQ==}
engines: {node: ^14.0.0 || >=16.0.0}
semver@7.8.4:
resolution: {integrity: sha512-rUCObTnP32Q08R2uuIrt7r9PlEonuTmtuXYcW6s5kjdlj3xbnwe+21yXptAUYcMAABLkYYTtnmzb3w3EDZfueA==}
engines: {node: '>=10'}
@@ -4906,6 +5231,14 @@ snapshots:
cosmokit: 1.8.1
js-yaml: 4.2.0
'@cordisjs/plugin-include@1.0.4(@cordisjs/plugin-loader@vendor+loader)(cordis@4.0.0-rc.6)':
dependencies:
'@cordisjs/plugin-loader': link:vendor/loader
cordis: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@vendor+loader)
cosmokit: 1.8.1
js-yaml: 4.2.0
optional: true
'@cordisjs/plugin-loader@1.0.0-rc.4(cordis@4.0.0-rc.6)':
dependencies:
cordis: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4)
@@ -5892,6 +6225,10 @@ snapshots:
buffer-equal-constant-time@1.0.1: {}
builtin-modules@3.3.0: {}
bytes@3.1.2: {}
cac@7.0.0: {}
ccount@2.0.1: {}
@@ -5918,6 +6255,14 @@ snapshots:
'@cordisjs/plugin-include': 1.0.4(@cordisjs/plugin-loader@1.0.0-rc.4)(cordis@4.0.0-rc.6)
'@cordisjs/plugin-loader': 1.0.0-rc.4(cordis@4.0.0-rc.6)
cordis@4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@vendor+loader):
dependencies:
'@standard-schema/spec': 1.1.0
cosmokit: 1.8.1
optionalDependencies:
'@cordisjs/plugin-include': 1.0.4(@cordisjs/plugin-loader@vendor+loader)(cordis@4.0.0-rc.6)
'@cordisjs/plugin-loader': link:vendor/loader
cordis@4.0.0-rc.6(@cordisjs/plugin-include@vendor+include)(@cordisjs/plugin-loader@vendor+loader):
dependencies:
'@standard-schema/spec': 1.1.0
@@ -6223,6 +6568,23 @@ snapshots:
escape-string-regexp@5.0.0: {}
eslint-plugin-sonarjs@4.1.0(eslint@10.5.0(jiti@2.7.0)):
dependencies:
'@eslint-community/regexpp': 4.12.2
builtin-modules: 3.3.0
bytes: 3.1.2
eslint: 10.5.0(jiti@2.7.0)
functional-red-black-tree: 1.0.1
globals: 17.7.0
jsx-ast-utils-x: 0.1.0
lodash.merge: 4.6.2
minimatch: 10.2.5
scslre: 0.3.0
semver: 7.8.4
ts-api-utils: 2.5.0(typescript@6.0.3)
typescript: 6.0.3
yaml: 2.9.0
eslint-scope@9.1.2:
dependencies:
'@types/esrecurse': 4.3.1
@@ -6367,6 +6729,8 @@ snapshots:
fsevents@2.3.3:
optional: true
functional-red-black-tree@1.0.1: {}
gaxios@7.1.5:
dependencies:
extend: 3.0.2
@@ -6395,6 +6759,8 @@ snapshots:
dependencies:
is-glob: 4.0.3
globals@17.7.0: {}
globrex@0.1.2: {}
google-auth-library@10.7.0:
@@ -6489,6 +6855,33 @@ snapshots:
dependencies:
argparse: 2.0.1
jscpd-darwin-arm64@5.0.12:
optional: true
jscpd-darwin-x64@5.0.12:
optional: true
jscpd-linux-arm64-gnu@5.0.12:
optional: true
jscpd-linux-x64-gnu@5.0.12:
optional: true
jscpd-linux-x64-musl@5.0.12:
optional: true
jscpd-windows-x64-msvc@5.0.12:
optional: true
jscpd@5.0.12:
optionalDependencies:
jscpd-darwin-arm64: 5.0.12
jscpd-darwin-x64: 5.0.12
jscpd-linux-arm64-gnu: 5.0.12
jscpd-linux-x64-gnu: 5.0.12
jscpd-linux-x64-musl: 5.0.12
jscpd-windows-x64-msvc: 5.0.12
jsdom@29.1.1:
dependencies:
'@asamuzakjp/css-color': 5.1.11
@@ -6532,6 +6925,8 @@ snapshots:
json-stable-stringify-without-jsonify@1.0.1: {}
jsx-ast-utils-x@0.1.0: {}
jwa@2.0.1:
dependencies:
buffer-equal-constant-time: 1.0.1
@@ -6676,6 +7071,8 @@ snapshots:
lodash-es@4.18.1: {}
lodash.merge@4.6.2: {}
long@5.3.2: {}
longest-streak@3.1.0: {}
@@ -7192,6 +7589,15 @@ snapshots:
readdirp@4.1.2: {}
refa@0.12.1:
dependencies:
'@eslint-community/regexpp': 4.12.2
regexp-ast-analysis@0.7.1:
dependencies:
'@eslint-community/regexpp': 4.12.2
refa: 0.12.1
require-from-string@2.0.2: {}
resolve-pkg-maps@1.0.0: {}
@@ -7284,6 +7690,12 @@ snapshots:
'@standard-schema/spec': 1.1.0
cosmokit: 1.8.1
scslre@0.3.0:
dependencies:
'@eslint-community/regexpp': 4.12.2
refa: 0.12.1
regexp-ast-analysis: 0.7.1
semver@7.8.4: {}
shebang-command@2.0.0:
pnpm-workspace.yaml
+3
View File
@@ -1,6 +1,9 @@
packages:
- vendor/*
- packages/*/*
# Deploy root of the single-exe build: a pure dependency manifest whose
# closure is what the exe bundles and what the Python runtime distributes.
- python/sdk-runtime
peerDependencyRules:
allowedVersions:
pytest.ini
+8
View File
@@ -0,0 +1,8 @@
# Root pytest config: pin collection to the Python SDK's real test tree.
# Without this, a bare `pytest` from the repo root recursively collects the
# whole worktree — including gitignored residue such as scratch checkouts or
# venvs — and same-basename test modules collide with an "import file
# mismatch" collection error.
[pytest]
testpaths = python/sdk/tests
norecursedirs = node_modules .git dist-exe
python/README.i18n.yaml
+6
View File
@@ -0,0 +1,6 @@
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
# side as of the last confirmed-consistent state. Both languages carry equal authority;
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write
README.md: 35ed645ce0e4d5e4c88c8aae2fe33d94aea79b3e
README.zh.md: 214c5cd1900e52f9fe479247f9940a97bb22766b
python/README.md
+76
View File
@@ -0,0 +1,76 @@
# DeepSeek Harness Python SDK
English | [中文](README.zh.md)
Python packages for driving DeepSeek Harness as a subprocess: a client SDK that spawns the `dsh-jsonrpc-agent` binary and talks newline-delimited JSON-RPC over stdio. The runtime carrier is the single-file executable produced by this repo; design, build, and acceptance details live in [docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md](../docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md).
## Packages
| Directory | Dist / module | Role |
|---|---|---|
| [sdk](sdk/) | `deepseek-harness` / `deepseek_harness` | Client SDK: the `DeepSeekHarness` high-level turns API and the lower-level `HarnessClient` JSON-RPC client |
| [sdk-runtime](sdk-runtime/) | `deepseek-harness-runtime-bin` / `deepseek_harness_runtime` | Runtime carrier: locates the bundled runtime binaries and ships the default agent configuration |
## Building the runtime executable
The platform executables are build artifacts, not checked into git. From the repo root:
```sh
pnpm install
pnpm exec tsx scripts/build-exe-for-python-sdk.ts # host platform, ~2 min
pnpm exec tsx scripts/build-exe-for-python-sdk.ts --skip-build # lib/ artifacts already built
pnpm exec tsx scripts/build-exe-for-python-sdk.ts --targets=node24-linux-x64,node24-linux-arm64,node24-macos-arm64
```
Products land in `dist-exe/` and are synced into this package at `sdk-runtime/src/deepseek_harness_runtime/runtime/dsh-jsonrpc-agent-pkg-<platform>-<arch>` (platform: `linux`/`macos`; arch: `x64`/`arm64`) — after a local build the SDK finds the executable with no further setup. The `build-exe-for-python-sdk` CI workflow (manual dispatch, or the `build-exe` PR label) exercises the same binaries but retains only the four release wheels. Which plugins the exe bundles and how the carriers are organized: [sdk-runtime README](sdk-runtime/README.md); the build also refreshes the dev-only node carrier (see "against the Node source" below).
## Validating the SDK against the executable
```sh
export UV_PROJECT_ENVIRONMENT="$PWD/tmp/py-sdk-venv" # keep the venv out of python/
uv sync --project python/sdk --group test
uv run --project python/sdk pytest python/sdk/tests/test_bundled_runtime.py # boots the real carriers
uv run --project python/sdk pytest # full suite; keyless tests included
```
For an interactive check (needs `DEEPSEEK_API_KEY` in the environment or the repo-root `.env`):
```python
from deepseek_harness import DeepSeekHarness
with DeepSeekHarness() as harness:
print(harness.run("say hi").final_response) # auto-resolution picks the bundled exe
```
## Running the SDK against the Node source (no executable)
Two flavors, both for repo members:
- **Built node carrier** — set `DSH_RUNTIME_MODE=node` and the SDK runs `runtime/node/node_modules/@deepseek-ai/dsh-jsonrpc-agent/lib/bin.js` on the system Node (>= 22.19). The tree is refreshed on every build-script run and is the same dependency closure the exe snapshots, so plugin semantics are identical. Never auto-selected, never distributed.
- **Unbuilt source (tsx)** — point the client straight at the bin's TypeScript source for edit-run loops and debugging: `launch_args_override=("./node_modules/.bin/tsx", "packages/ui/jsonrpc-agent/src/bin.ts")` with `cwd` at the repo root, plus a config via `cordis=...` (or rely on the default-config injection). [sdk/tests/manual_sdk_agent_smoke.py](sdk/tests/manual_sdk_agent_smoke.py) is the worked example.
## Distributing the Python packages
The root [`package.json`](../package.json) version is authoritative for both Python distributions. The common staging script reads that version, injects it into both wheels, and pins the SDK metadata to the same `deepseek-harness-runtime-bin==X.Y.Z`; an optional `python-vX.Y.Z` release tag is accepted only when it matches the repository version. Build the pure SDK wheel once and one runtime wheel on each native platform:
```sh
version="$(node -p "require('./package.json').version")"
python scripts/build-python-release.py --package sdk --output-dir dist-python
python scripts/build-python-release.py --package runtime --platform macos-arm64 --runtime-exe dist-exe/dsh-jsonrpc-agent-pkg-macos-arm64 --output-dir dist-python
pip install --find-links dist-python deepseek-harness=="$version"
```
The runtime distribution is wheel-only and rejects sdist builds, missing executables, and mixed-platform payloads. Its three wheel tags are `py3-none-manylinux_2_28_x86_64`, `py3-none-manylinux_2_28_aarch64`, and `py3-none-macosx_11_0_arm64`; the SDK remains `py3-none-any`. A matching `python-vX.Y.Z` tag pipeline builds these four non-conflicting files and publishes them together, so a normal `pip install deepseek-harness==X.Y.Z` selects the matching runtime wheel and `import deepseek_harness` needs no `runtime_bin`.
## Zero-config semantics
The runtime binary itself always requires an explicit config (`$DSH_CORDIS_CONFIG`, or a config path as the first argv argument), has no built-in fallback, and boots only what the config lists. Zero-config is SDK wrapper behavior: when the caller uses no explicit channel, the client injects the runtime package's checked-in default configuration ([runtime/cordis.yml](sdk-runtime/src/deepseek_harness_runtime/runtime/cordis.yml)) via `DSH_CORDIS_CONFIG`; any explicit channel wins and disables the injection. The full injection conditions live in the [sdk README](sdk/README.md); the default config's contents and the hard semantic in the [sdk-runtime README](sdk-runtime/README.md).
The executable is also a supported direct interface; keep stdin open for the NDJSON JSON-RPC exchange and supply a config explicitly:
```sh
DSH_CORDIS_CONFIG=/absolute/path/cordis.yml ./dsh-jsonrpc-agent-pkg-macos-arm64
```
## Test layout
`test_client.py` is fully keyless (a Python fake runtime is the peer). `test_bundled_runtime.py` boots each bundled carrier and skips per carrier when its artifact is missing. `test_runtime_resolution.py` covers the carrier-resolution rules without spawning anything.
python/README.zh.md
+76
View File
@@ -0,0 +1,76 @@
# DeepSeek Harness Python SDK
[English](README.md) | 中文
以子进程方式驱动 DeepSeek Harness 的 Python 包：客户端 SDK spawn `dsh-jsonrpc-agent` 二进制，并通过 stdio 上按行分隔的 JSON-RPC 与之通信。运行时载体是本仓库产出的单文件可执行文件；设计、构建与验收细节见 [docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md](../docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md)。
## 包
| 目录 | 分发名 / 模块 | 职责 |
|---|---|---|
| [sdk](sdk/) | `deepseek-harness` / `deepseek_harness` | 客户端 SDK：高层回合 API `DeepSeekHarness` 与低层 JSON-RPC 客户端 `HarnessClient` |
| [sdk-runtime](sdk-runtime/) | `deepseek-harness-runtime-bin` / `deepseek_harness_runtime` | 运行时载体：定位内置的运行时二进制，并携带默认的 agent（智能体）配置 |
## 构建运行时可执行文件
各平台可执行文件是构建产物，不检入 git。在仓库根目录执行：
```sh
pnpm install
pnpm exec tsx scripts/build-exe-for-python-sdk.ts # host platform, ~2 min
pnpm exec tsx scripts/build-exe-for-python-sdk.ts --skip-build # lib/ artifacts already built
pnpm exec tsx scripts/build-exe-for-python-sdk.ts --targets=node24-linux-x64,node24-linux-arm64,node24-macos-arm64
```
产物落入 `dist-exe/`，并同步进本包的 `sdk-runtime/src/deepseek_harness_runtime/runtime/dsh-jsonrpc-agent-pkg-<platform>-<arch>`（platform：`linux`/`macos`；arch：`x64`/`arm64`），本地构建完成后 SDK 不需要额外设置就能找到可执行文件。`build-exe-for-python-sdk` CI 工作流（手动触发，或给 PR 打 `build-exe` 标签）会测试同样的二进制，但只保留 4 个发布用 wheel 包。exe 内置哪些插件、载体如何组织，见 [sdk-runtime README](sdk-runtime/README.md)；构建还会顺带刷新仅供开发使用的 `node` 载体（见下文「对着 Node 源码运行」）。
## 用可执行文件验证 SDK
```sh
export UV_PROJECT_ENVIRONMENT="$PWD/tmp/py-sdk-venv" # keep the venv out of python/
uv sync --project python/sdk --group test
uv run --project python/sdk pytest python/sdk/tests/test_bundled_runtime.py # boots the real carriers
uv run --project python/sdk pytest # full suite; keyless tests included
```
交互式验证（需要环境变量或仓库根 `.env` 中的 `DEEPSEEK_API_KEY`）：
```python
from deepseek_harness import DeepSeekHarness
with DeepSeekHarness() as harness:
print(harness.run("say hi").final_response) # auto-resolution picks the bundled exe
```
## 对着 Node 源码运行 SDK（不用可执行文件）
两种方式，均面向仓库成员：
- **已构建的 `node` 载体**——设置 `DSH_RUNTIME_MODE=node`，SDK 会用系统 Node（>= 22.19）运行 `runtime/node/node_modules/@deepseek-ai/dsh-jsonrpc-agent/lib/bin.js`。这棵树每次运行构建脚本都会刷新，与 exe 打入 pkg 虚拟文件系统（VFS）的是同一份依赖闭包，因此插件语义一致。它不会被自动选中，也不进入分发物。
- **未构建的源码（tsx）**——把客户端直接指向 `bin` 的 TypeScript 源码，用于编辑、运行和调试：`launch_args_override=("./node_modules/.bin/tsx", "packages/ui/jsonrpc-agent/src/bin.ts")`，`cwd` 设为仓库根，再通过 `cordis=...` 传入配置（或使用默认配置注入）。[sdk/tests/manual_sdk_agent_smoke.py](sdk/tests/manual_sdk_agent_smoke.py) 是现成范例。
## 分发 Python 包
根目录 [`package.json`](../package.json) 的版本是两个 Python 分发物的权威版本。统一暂存脚本读取这个版本并注入两个 wheel 包，同时在 SDK 元数据中钉死相同版本的 `deepseek-harness-runtime-bin==X.Y.Z`；可选的 `python-vX.Y.Z` 发布标签只有与仓库版本匹配时才会被接受。纯 SDK wheel 包只构建一次，运行时 wheel 包则在每个原生平台各构建一个：
```sh
version="$(node -p "require('./package.json').version")"
python scripts/build-python-release.py --package sdk --output-dir dist-python
python scripts/build-python-release.py --package runtime --platform macos-arm64 --runtime-exe dist-exe/dsh-jsonrpc-agent-pkg-macos-arm64 --output-dir dist-python
pip install --find-links dist-python deepseek-harness=="$version"
```
运行时分发物只提供 wheel 包，并拒绝 sdist 构建、缺失可执行文件以及混合平台载荷。三个 wheel 包标签分别是 `py3-none-manylinux_2_28_x86_64`、`py3-none-manylinux_2_28_aarch64` 与 `py3-none-macosx_11_0_arm64`；SDK 保持 `py3-none-any`。匹配的 `python-vX.Y.Z` 标签流水线统一构建并发布这 4 个互不冲突的文件，因此常规的 `pip install deepseek-harness==X.Y.Z` 会选中匹配平台的运行时 wheel 包，`import deepseek_harness` 不需要 `runtime_bin`。
## 零配置语义
运行时二进制本身始终要求显式配置（`$DSH_CORDIS_CONFIG`，或作为首个 argv 参数的配置路径），没有内置兜底，也只启动配置里列出的内容。零配置是 SDK 包装层的行为：调用方没有使用任何显式通道时，客户端把运行时包检入的默认配置（[runtime/cordis.yml](sdk-runtime/src/deepseek_harness_runtime/runtime/cordis.yml)）注入 `DSH_CORDIS_CONFIG`；任一显式通道存在即优先采用，并禁用注入。注入条件的完整定义见 [sdk README](sdk/README.md)，默认配置的内容与硬语义见 [sdk-runtime README](sdk-runtime/README.md)。
可执行文件也支持直接调用；在 NDJSON JSON-RPC 交互期间保持 stdin 打开，并显式提供配置：
```sh
DSH_CORDIS_CONFIG=/absolute/path/cordis.yml ./dsh-jsonrpc-agent-pkg-macos-arm64
```
## 测试布局
`test_client.py` 完全无需密钥（对端是 Python 假运行时）。`test_bundled_runtime.py` 逐个启动内置载体，某个载体产物缺失时跳过对应用例。`test_runtime_resolution.py` 覆盖载体解析规则，不 spawn 任何进程。
python/sdk-runtime/README.i18n.yaml
+6
View File
@@ -0,0 +1,6 @@
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
# side as of the last confirmed-consistent state. Both languages carry equal authority;
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write
README.md: 4beac57526761bb150e90b60f0030ed311c4034d
README.zh.md: c0cc0eef6a9b569105408d2f2e6321795493036a
python/sdk-runtime/README.md
+29
View File
@@ -0,0 +1,29 @@
# DeepSeek Harness Runtime Wheel
English | [中文](README.zh.md)
Runtime carrier package for the Python SDK (dist `deepseek-harness-runtime-bin`, module `deepseek_harness_runtime`): it locates the bundled runtime binaries the `deepseek-harness` client spawns, and ships the default configuration behind zero-config runs.
## Runtime carriers
Two carriers coexist under `src/deepseek_harness_runtime/runtime/`, both injected by the repo's `scripts/build-exe-for-python-sdk.ts` build and both gitignored:
- **exe (production)** — single-file executables `dsh-jsonrpc-agent-pkg-<platform>-<arch>` (platform: `linux`/`macos`; arch: `x64`/`arm64`). No Node installation needed on the target machine. This is the only carrier that ships in wheel distributions; this package does not publish sdists.
- **node (dev-only)** — the full deploy closure under `runtime/node/` (`package.json` + `node_modules/`), executed as `node runtime/node/node_modules/@deepseek-ai/dsh-jsonrpc-agent/lib/bin.js` on a system Node >= 22.19. It is the current checkout's source build, meant for repo-local development and verification only; it is never selected automatically and is excluded from distributions.
Both carriers hold the same content, defined once: the [package.json](package.json) at this package's root is the deploy root of the single-exe pipeline — a pure dependency manifest (no code of its own) whose dependency closure IS both the plugin set compiled into the exe and the tree materialized into `runtime/node/`. Adding a plugin to the distribution means adding one dependency line there and rebuilding.
Missing carriers raise `FileNotFoundError` naming the acquisition routes: build via `scripts/build-exe-for-python-sdk.ts` in a deepseek-harness checkout, or install the matching platform runtime wheel produced by the `build-exe-for-python-sdk` CI workflow. The workflow retains wheels rather than standalone executable archives. Acquisition strategy is deliberately separate from the lookup interface, so an on-demand download can replace it later without touching callers.
Each wheel contains exactly one executable. The fixed tags are `py3-none-manylinux_2_28_x86_64`, `py3-none-manylinux_2_28_aarch64`, and `py3-none-macosx_11_0_arm64`; the build hook rejects `py3-none-any`, absent or multiple executables, and unsupported platform tags. The repository root `package.json` supplies the shared version for this package and the SDK, and a `python-vX.Y.Z` release tag must match it.
## Resolution API
- `resolve_bundled_launch_args(mode=None) -> tuple[str, ...]` — the argv tuple that launches the bundled runtime: `(exe_path,)` in exe mode, `(node_path, bin_js_path)` in node mode. Mode selection: explicit argument > `DSH_RUNTIME_MODE` env var (`exe` | `node`) > automatic. Automatic resolution finds the production exe ONLY — the dev-only node carrier must be opted into explicitly so a production deployment can never silently ride on a source build.
- `bundled_runtime_path() -> Path` — the platform exe path (exe carrier only; the node carrier has no single-path equivalent and launches via the argv tuple above).
- `bundled_default_config_path() -> Path` — the checked-in default config (see below).
- `bundled_package_dir() -> Path` — the installed package data root.
## Zero-config design
The runtime binary always demands an explicit config (`$DSH_CORDIS_CONFIG`, or a config path as an argv positional argument) and exits loudly without one — that hard semantic is part of the runtime's design and this package does not soften it. The bin (`dsh-jsonrpc-agent`) boots only the plugins the config lists; the serving surface (the stdio JSON-RPC server) is itself one of its entries (`@deepseek-ai/dsh-jsonrpc`), and without it the booted agent has no channel to the outside. This package checks in `runtime/cordis.yml` (the JSON-RPC serving entry, agent core, preloaded DeepSeek adapter, JSONL session persistence, local bash, each parameterized by the `DSH_*` env vars the SDK sets); when the caller uses no explicit config channel, the `deepseek_harness` client injects that file's path via `DSH_CORDIS_CONFIG` (injection conditions: [sdk README](../sdk/README.md)). Zero-config is thus an explicit, visible parameter pass in the wrapper, not a hidden fallback in the runtime.
python/sdk-runtime/README.zh.md
+29
View File
@@ -0,0 +1,29 @@
# DeepSeek Harness 运行时 wheel 包
[English](README.md) | 中文
Python SDK 的运行时载体包（分发名 `deepseek-harness-runtime-bin`，模块名 `deepseek_harness_runtime`）：它定位 `deepseek-harness` 客户端要 spawn 的内置运行时二进制，并附带支撑零配置运行的默认配置。
## 运行时载体
两种载体并存于 `src/deepseek_harness_runtime/runtime/` 之下，均由仓库的 `scripts/build-exe-for-python-sdk.ts` 构建注入，且均被 git 忽略：
- **exe（生产）**——单文件可执行程序 `dsh-jsonrpc-agent-pkg-<platform>-<arch>`（platform：`linux`/`macos`；arch：`x64`/`arm64`）。目标机器无需安装 Node。这是唯一随 wheel 包分发的载体；本包不发布 sdist。
- **`node`（仅限开发）**——`runtime/node/` 下的完整部署闭包（`package.json` + `node_modules/`），在系统 Node >= 22.19 上以 `node runtime/node/node_modules/@deepseek-ai/dsh-jsonrpc-agent/lib/bin.js` 执行。它是当前检出的源码构建，仅用于仓库本地的开发与验证；不会被自动选中，也不进入分发物。
两种载体承载相同的内容，且只定义一次：本包根目录的 [package.json](package.json) 是 single-exe 流水线的部署根目录——一份零代码的纯依赖 manifest，其依赖闭包既是编译进 exe 的插件集，也是物化到 `runtime/node/` 的文件树。往分发物里加插件，就是在那里加一行依赖再重新构建。
载体缺失时抛出 `FileNotFoundError` 并写明获取途径：在 deepseek-harness 检出中经 `scripts/build-exe-for-python-sdk.ts` 构建，或安装 `build-exe-for-python-sdk` CI 工作流生成的对应平台运行时 wheel 包。该工作流只保留 wheel 包，不保留独立 exe 归档。获取策略与查找接口刻意分离，之后可以换成按需下载而不改动任何调用方。
每个 wheel 包只包含一个可执行文件。固定标签为 `py3-none-manylinux_2_28_x86_64`、`py3-none-manylinux_2_28_aarch64` 与 `py3-none-macosx_11_0_arm64`；构建钩子会拒绝 `py3-none-any`、可执行文件缺失或重复以及不支持的平台标签。仓库根目录的 `package.json` 为本包和 SDK 提供共同版本，`python-vX.Y.Z` 发布标签必须与其匹配。
## 解析 API
- `resolve_bundled_launch_args(mode=None) -> tuple[str, ...]`——启动内置运行时的 argv 元组：exe 模式下为 `(exe_path,)`，`node` 模式下为 `(node_path, bin_js_path)`。模式选择：显式参数 > `DSH_RUNTIME_MODE` 环境变量（`exe` | `node`）> 自动。自动解析只找生产 exe——仅限开发的 `node` 载体必须显式选用，从而生产部署绝不会悄悄跑在源码构建上。
- `bundled_runtime_path() -> Path`——平台 exe 路径（仅 exe 载体；`node` 载体没有单一路径的等价物，经由上面的 argv 元组启动）。
- `bundled_default_config_path() -> Path`——检入的默认配置（见下文）。
- `bundled_package_dir() -> Path`——已安装包的数据根目录。
## 零配置设计
运行时二进制始终要求显式配置（`$DSH_CORDIS_CONFIG`，或作为 argv 位置参数的配置路径），缺了就报错退出——这一硬语义是运行时设计的一部分，本包不软化它。`bin`（`dsh-jsonrpc-agent`）只启动配置里列出的插件；对外服务接口（stdio JSON-RPC 服务器）也是其中一个条目（`@deepseek-ai/dsh-jsonrpc`），缺了它，启动出的 agent 就没有对外通道。本包检入 `runtime/cordis.yml`（JSON-RPC 服务条目、`agent-core`、预载的 DeepSeek 适配器、JSONL 会话持久化、本地 bash，各项由 SDK 设置的 `DSH_*` 环境变量参数化）；调用方未使用任何显式配置通道时，`deepseek_harness` 客户端把该文件路径注入 `DSH_CORDIS_CONFIG`（注入条件见 [sdk README](../sdk/README.md)）。因此，零配置是包装层中一次显式、可见的参数传递，而不是运行时中的隐藏回退。
python/sdk-runtime/hatch_build.py
+60
View File
@@ -0,0 +1,60 @@
from __future__ import annotations
import os
import platform
import stat
from pathlib import Path
from hatchling.builders.hooks.plugin.interface import BuildHookInterface
_PLATFORMS = {
"linux-x64": ("manylinux_2_28_x86_64", "dsh-jsonrpc-agent-pkg-linux-x64"),
"linux-arm64": ("manylinux_2_28_aarch64", "dsh-jsonrpc-agent-pkg-linux-arm64"),
"macos-arm64": ("macosx_11_0_arm64", "dsh-jsonrpc-agent-pkg-macos-arm64"),
}
def _host_platform_tag() -> str:
machine = platform.machine().lower()
arch = "arm64" if machine in {"arm64", "aarch64"} else "x64" if machine in {"x86_64", "amd64"} else machine
system = platform.system().lower()
key = f"macos-{arch}" if system == "darwin" else f"linux-{arch}" if system == "linux" else system
try:
return _PLATFORMS[key][0]
except KeyError as exc:
raise RuntimeError(f"unsupported deepseek-harness-runtime-bin build platform: {key}") from exc
class RuntimeBuildHook(BuildHookInterface):
"""Assign the native wheel tag and reject incomplete or mixed-platform payloads."""
def initialize(self, version: str, build_data: dict[str, object]) -> None:
if version == "editable":
return
if self.target_name == "sdist":
raise RuntimeError(
"deepseek-harness-runtime-bin is wheel-only; build and publish platform wheels only."
)
platform_tag = os.environ.get("DSH_RUNTIME_PLATFORM_TAG") or _host_platform_tag()
matches = [value for value in _PLATFORMS.values() if value[0] == platform_tag]
if len(matches) != 1:
supported = ", ".join(value[0] for value in _PLATFORMS.values())
raise RuntimeError(
f"unsupported DSH_RUNTIME_PLATFORM_TAG {platform_tag!r}; expected one of {supported}"
)
expected_executable = matches[0][1]
runtime_dir = Path(self.root) / "src" / "deepseek_harness_runtime" / "runtime"
executables = sorted(runtime_dir.glob("dsh-jsonrpc-agent-pkg-*") if runtime_dir.is_dir() else [])
if [path.name for path in executables] != [expected_executable]:
found = ", ".join(path.name for path in executables) or "none"
raise RuntimeError(
f"runtime wheel {platform_tag} must contain only {expected_executable}; found {found}"
)
if executables[0].stat().st_mode & stat.S_IXUSR == 0:
raise RuntimeError(f"runtime executable is not executable: {executables[0]}")
build_data["pure_python"] = False
build_data["infer_tag"] = False
build_data["tag"] = f"py3-none-{platform_tag}"

Some files were not shown because too many files have changed in this diff Show More