Run jobs on Windows runners (windows-* labels) under native pwsh. Native Windows build and process checks contribute to the pull-request all checks passed verdict; Wine runs Windows Node on hosted Linux only in ci-master.yml. Python runtime CI checks Linux/Windows x64 on pull requests and Linux ARM64 plus both macOS architectures on master pushes; releases retain all five targets (platform policy). ci.yml is pull-request-only. Master-only platform checks, Linux/Windows self-hosted standbys, and manual runner benchmarks live in ci-master.yml, which listens to master…
This workspace owns @deepseek-ai/node-addon-system: the Linux landlock-run confinement executable and the POSIX system.node binding. It shares the root pnpm workspace and lockfile; native packages have one independent version and release workflow. packages/entry/ owns JavaScript, types, and auditable C sources. Platform packages hold only binaries and metadata. scripts/ owns native builds, packing, validation, and release; test/ owns real process and lock behavior. Run pnpm build:ts, pnpm build:native, pnpm build:test-oracle, pnpm typecheck, and pnpm test in this directory. Linux full builds require…
Rules for packages/client/* (the browser side of the dsh web GUI) plus its build entry apps/web. They supplement the repo-wide conventions and the package rules. Read the current Web Client architecture, Slots reference, and Conversation reference before changing the corresponding layer. Packages here are named with the directory prefix: @deepseek-ai/dsh-client-<name>. The Slots reference owns the current design; these are the rules you must not violate when writing or reviewing client code: How live data reaches render code,
These rules supplement the package rules. The experimental publication decision owns the publication policy; the Agent Teams package decision owns dependency isolation and promotion rationale.
Use when writing or reading a Cordis bundle patch or agent preset for this harness and you need the Loader YAML dialect (insert, override by id, group, disabled, isolate, !!js) or the list of installable Harness plugin packages and what each provides.
Use when adding, enabling, disabling, installing, configuring, or debugging a plugin, bundle, feature, page, panel, tool, or MCP connection in the current Harness profile, including a shipped plugin that is disabled by default, and for any visual object, decoration, or widget request that names no other destination, which means an installed UI plugin rendered in the Harness Web UI.
Use when creating, changing, or validating an agent preset or other Cordis composition for this harness, including deciding host versus preset placement and checking that an authored preset mounts.
Create, read, edit, and check Word documents (.docx), including reports, letters, and formatted tables. Use when a DOCX file is an input or requested deliverable. Load this skill before running Office commands. Use only bundled LibreOffice unless the user explicitly opts out; without that opt-out, do not search for another LibreOffice executable.
Create, read, edit, and check PowerPoint presentations (.pptx), including slide text, tables, images, and charts. Use when a PPTX file is an input or requested deliverable. Load this skill before running Office commands. Use only bundled LibreOffice unless the user explicitly opts out; without that opt-out, do not search for another LibreOffice executable.
Read, create, and modify Excel workbooks (.xlsx), including data, formulas, formatting, and pandas analysis. Use for Excel inputs or deliverables. Load before running Office commands. Data and formula tasks skip visual inspection; inspect only for formatting or layout needs. Use only bundled LibreOffice unless the user explicitly opts out; without that opt-out, do not search for another LibreOffice executable.
Gate scripts invoke pnpm shell-free, normalize repository-relative glob paths to / at ingestion, and keep platform adaptation in the gate that needs it instead of a shared platform layer. Source-ownership gates use syntax-aware discovery, guard against an empty or narrowed corpus, and test every admitted/excluded form that changes their detection boundary. Script specs run in forked workers beside the rest of the suite and beside the other gate processes in their job, so own every port, temporary path, and child…
This tree contains only tests whose committed session JSONL is replay input and expected persisted output. Keep non-session ARIA, geometry, generator, CLI, and unit expected output with its owning app, script, or package; use test:expected, test:web, or test for its owning tier. Every process under test starts through the dsh CLI with a shipped profile and optional scenario patches. Test clients may drive a public protocol or browser interface; do not add another application entrypoint, hidden CLI mode, or executable…
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
DeepSeekAGENTS.md