mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
Merge branch 'master' into worktree-windows-runtime
This commit is contained in:
@@ -1,7 +1,7 @@
|
||||
name: Build single-exe
|
||||
|
||||
# Native builds for the release targets; see
|
||||
# docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md.
|
||||
# .agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md.
|
||||
# A full target run retains one SDK wheel and three runtime wheels; subset
|
||||
# dispatch retains the SDK wheel and selected runtime wheels. Bare executables
|
||||
# and source closures are test inputs. Run manually or label a PR
|
||||
|
||||
2
.github/workflows/e2e.yml
vendored
2
.github/workflows/e2e.yml
vendored
@@ -23,7 +23,7 @@ name: E2E (real DeepSeek API)
|
||||
# in the BASE repo's context WITH secrets while still able to check out untrusted
|
||||
# fork code — a textbook key-leak vector, especially once this repo is public.
|
||||
# The fork/secret model and its public-repo implications are recorded in
|
||||
# docs/rfc/implemented/testing/2026-06-19-real-api-e2e-ci.md.
|
||||
# .agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.md.
|
||||
#
|
||||
# Note: scheduled triggers are auto-disabled after 60 days of repo inactivity;
|
||||
# push/pull_request/workflow_dispatch act as backstops.
|
||||
|
||||
21
.github/workflows/expected-filenames.yml
vendored
Normal file
21
.github/workflows/expected-filenames.yml
vendored
Normal file
@@ -0,0 +1,21 @@
|
||||
name: Expected filenames
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
paths:
|
||||
- '*[gG][oO][lL][dD][eE][nN]*'
|
||||
- '**/*[gG][oO][lL][dD][eE][nN]*'
|
||||
- '!vendor/**'
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
jobs:
|
||||
expected-filenames:
|
||||
name: no golden filenames
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v6
|
||||
|
||||
- name: Check tracked filenames
|
||||
run: scripts/check-expected-filenames.sh
|
||||
127
.github/workflows/landlock-run.yml
vendored
Normal file
127
.github/workflows/landlock-run.yml
vendored
Normal file
@@ -0,0 +1,127 @@
|
||||
# Manually-dispatched CI for the landlock-run source of record
|
||||
# (native/landlock-run). A separate workflow from ci.yml on purpose: the
|
||||
# subtree is a self-contained pnpm workspace with its own gates, exercised on
|
||||
# demand — per-architecture native legs (build + behavioral tests + pack
|
||||
# rehearsal on real kernels) plus one darwin leg proving the documented
|
||||
# degradation on hosts without a platform package. Legs derive from the
|
||||
# subtree's checked-in package matrix (scripts/github-matrix.mjs). Packing
|
||||
# for npm happens in the release mirror (node-addon-landlock-run) after an
|
||||
# export — see native/README.md; this workflow never packs for release.
|
||||
name: Landlock Run
|
||||
|
||||
on:
|
||||
workflow_dispatch:
|
||||
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ github.ref }}
|
||||
cancel-in-progress: true
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
defaults:
|
||||
run:
|
||||
working-directory: native/landlock-run
|
||||
|
||||
jobs:
|
||||
matrix:
|
||||
name: Matrix
|
||||
runs-on: ubuntu-24.04
|
||||
outputs:
|
||||
ci: ${{ steps.matrix.outputs.ci }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- id: matrix
|
||||
run: echo "ci=$(node ./scripts/github-matrix.mjs ci)" >> "$GITHUB_OUTPUT"
|
||||
|
||||
native:
|
||||
name: ${{ matrix.platform }}
|
||||
needs: matrix
|
||||
runs-on: ${{ matrix.runner }}
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix: ${{ fromJson(needs.matrix.outputs.ci) }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- uses: pnpm/action-setup@v4
|
||||
with:
|
||||
package_json_file: native/landlock-run/package.json
|
||||
|
||||
- uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: 24
|
||||
cache: pnpm
|
||||
cache-dependency-path: native/landlock-run/pnpm-lock.yaml
|
||||
|
||||
- name: Install dependencies
|
||||
run: pnpm install --frozen-lockfile
|
||||
|
||||
- name: Install musl toolchain
|
||||
run: |
|
||||
sudo apt-get update -q
|
||||
sudo apt-get install -yq musl-tools
|
||||
|
||||
- name: Build TypeScript
|
||||
run: pnpm build:ts
|
||||
|
||||
- name: Typecheck
|
||||
run: pnpm typecheck
|
||||
|
||||
- name: Build native binaries (this architecture is the builder of record)
|
||||
run: pnpm build:native
|
||||
|
||||
- name: Entry tests (keyless)
|
||||
run: node ./test/entry.test.js
|
||||
|
||||
# NALR_REQUIRE_LANDLOCK: a self-skip on the very platform that exists to
|
||||
# prove enforcement would be a false green, so an unenforcing kernel
|
||||
# fails the leg instead of skipping.
|
||||
- name: Launcher tests (real kernel enforcement)
|
||||
run: node ./test/launcher.test.js
|
||||
env:
|
||||
NALR_REQUIRE_LANDLOCK: 1
|
||||
|
||||
- name: Pack rehearsal (pack → install → confine, this platform only)
|
||||
run: |
|
||||
node ./scripts/pack-release.mjs .release/npm --current-platform-only
|
||||
node ./scripts/verify-packed-install.mjs .release/npm --current-platform-only
|
||||
env:
|
||||
NALR_REQUIRE_LANDLOCK: 1
|
||||
|
||||
darwin:
|
||||
name: darwin (no platform package — degradation proof)
|
||||
runs-on: macos-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- uses: pnpm/action-setup@v4
|
||||
with:
|
||||
package_json_file: native/landlock-run/package.json
|
||||
|
||||
- uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: 24
|
||||
cache: pnpm
|
||||
cache-dependency-path: native/landlock-run/pnpm-lock.yaml
|
||||
|
||||
- name: Install dependencies
|
||||
run: pnpm install --frozen-lockfile
|
||||
|
||||
- name: Build TypeScript
|
||||
run: pnpm build:ts
|
||||
|
||||
- name: Typecheck
|
||||
run: pnpm typecheck
|
||||
|
||||
- name: Entry tests (keyless)
|
||||
run: node ./test/entry.test.js
|
||||
|
||||
- name: Launcher tests (must self-skip cleanly)
|
||||
run: node ./test/launcher.test.js
|
||||
|
||||
- name: Pack rehearsal (entry only — fallback resolution + unusable probe)
|
||||
run: |
|
||||
node ./scripts/pack-release.mjs .release/npm --current-platform-only
|
||||
node ./scripts/verify-packed-install.mjs .release/npm --current-platform-only
|
||||
78
.github/workflows/pi-ai-provider-e2e.yml
vendored
Normal file
78
.github/workflows/pi-ai-provider-e2e.yml
vendored
Normal file
@@ -0,0 +1,78 @@
|
||||
name: E2E (pi-ai Azure OpenAI and Anthropic)
|
||||
|
||||
# This suite spends tokens against two external providers and is intentionally
|
||||
# opt-in. It has no push, pull_request, schedule, or workflow_call trigger.
|
||||
on:
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
azure_openai_model:
|
||||
description: Azure OpenAI model from pi-ai's installed catalog
|
||||
required: true
|
||||
default: gpt-5.5
|
||||
type: string
|
||||
anthropic_model:
|
||||
description: Anthropic model from pi-ai's installed catalog
|
||||
required: true
|
||||
default: claude-opus-4-8
|
||||
type: string
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
jobs:
|
||||
e2e:
|
||||
runs-on: ubuntu-latest
|
||||
name: Azure OpenAI Responses + Anthropic Messages
|
||||
timeout-minutes: 20
|
||||
steps:
|
||||
- uses: actions/checkout@v6
|
||||
|
||||
- uses: actions/setup-node@v6
|
||||
with:
|
||||
node-version: 24
|
||||
|
||||
- name: Enable corepack (pnpm)
|
||||
run: corepack enable
|
||||
|
||||
- name: Resolve pnpm store path
|
||||
id: pnpm-store
|
||||
run: echo "path=$(pnpm store path --silent)" >> "$GITHUB_OUTPUT"
|
||||
|
||||
- uses: actions/cache@v4
|
||||
with:
|
||||
path: ${{ steps.pnpm-store.outputs.path }}
|
||||
key: ${{ runner.os }}-node-24-pnpm-${{ hashFiles('pnpm-lock.yaml') }}
|
||||
restore-keys: |
|
||||
${{ runner.os }}-node-24-pnpm-
|
||||
|
||||
- name: Install (immutable)
|
||||
run: pnpm install --frozen-lockfile
|
||||
|
||||
# The tests self-skip locally when a credential is absent. A manually
|
||||
# dispatched CI run must fail instead of reporting an all-skipped green.
|
||||
- name: Preflight (require provider API keys)
|
||||
env:
|
||||
AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY_EXTERNAL }}
|
||||
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY_EXTERNAL }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
missing=0
|
||||
for name in AZURE_OPENAI_API_KEY ANTHROPIC_API_KEY; do
|
||||
if [ -z "${!name:-}" ]; then
|
||||
echo "::error::${name} is empty. Configure the corresponding *_EXTERNAL repository secret."
|
||||
missing=1
|
||||
fi
|
||||
done
|
||||
exit "$missing"
|
||||
|
||||
- name: E2E tests (real Azure OpenAI and Anthropic APIs)
|
||||
env:
|
||||
AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY_EXTERNAL }}
|
||||
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY_EXTERNAL }}
|
||||
DSH_PI_AI_OPENAI_MODEL: ${{ inputs.azure_openai_model }}
|
||||
DSH_PI_AI_OPENAI_BASE_URL: https://openai-routerhub-resource.services.ai.azure.com/api/projects/openai/openai/v1
|
||||
DSH_PI_AI_ANTHROPIC_MODEL: ${{ inputs.anthropic_model }}
|
||||
DSH_E2E_MAX_WORKERS: 2
|
||||
run: >-
|
||||
pnpm exec vitest run --config vitest.e2e.config.ts
|
||||
packages/llm/llm-pi-ai/tests/provider-apis.e2e.ts
|
||||
2
.github/workflows/sandbox.yml
vendored
2
.github/workflows/sandbox.yml
vendored
@@ -19,7 +19,7 @@ permissions:
|
||||
contents: read
|
||||
|
||||
jobs:
|
||||
# Keyless real-kernel sandbox proofs (sandbox RFC § Testing): each ladder
|
||||
# Keyless real-kernel sandbox proofs (sandbox Agent Note § Testing): each ladder
|
||||
# rung is only provable on a host where it enforces, so this job fans out
|
||||
# an OS×runner matrix — bwrap and Landlock on Linux (separate legs: the
|
||||
# Landlock files force the bwrap rung off, so each leg proves exactly one
|
||||
|
||||
Reference in New Issue
Block a user