2nd dokployH
8e9d5467b0
Review findings on the CPython backend: a child that never reads fd 3 leaves
the reply pipe full forever, so the drain loop waits on 'drain' while every
call frame it keeps sending resolves a binding and queues another reply —
the backlog (and the binding results it pins) would grow until the wall
clock. sendReply now caps the pending backlog at MAX_PENDING_REPLIES and
settles the run as worker-exit past it, mirroring the frame cap; a child
flooding calls against a binding that never settles would otherwise bypass
that cap (pendingReplies grows only after the await), so the dispatcher
counts in-flight binding calls before dispatch and releases the slot in the
async body's finally, capping outstanding closures at the same bound. The
drain also compacts its consumed prefix (replyQueue.splice(0, head)) once
head reaches the bound, so a drain that stays alive without emptying cannot
grow the backing store linearly with cumulative throughput.
The completion-value meter counted lone surrogates with
_SURROGATE.findall(folded), materializing one single-character string per
surrogate: a surrogate-dense value near the budget (millions of surrogates,
each serializing to six bytes) allocated millions of objects before the meter
returned, defeating the meter's counting-without-building contract. The count
is now the length difference between folded and the without string the meter
already computes; a standalone equivalence check confirms it matches findall
across lone-high, lone-low, paired, astral, and mixed cases.
validateBindings read namespace.global/errorClass.name/memberNameProperty
several times and retained the original errorClass object for the boot
frame, whose JSON.stringify re-read it after validation: a stateful getter
could throw or change between the two stages, turning the seam-misuse
rejection into a worker-exit or injecting an unvalidated name. Each field is
now read once into a plain value and the bindings map stores a plain
{ name, memberNameProperty } copy, so validation and the boot frame see
identical values.
Regression tests: a hostile child floods 5000 sequential valid calls without
reading fd 3 and the run settles worker-exit with the reply-queue message
before maxWallMs; a 3,000,000-surrogate completion succeeds at an
18,000,002-byte budget and reports output-limit one byte under; a 5000-call
flood against a never-settling binding settles worker-exit with the
call-backlog message; getter-backed namespace metadata that throws or
changes on a second read boots and runs with each field read exactly once; a
two-wave flood whose replies exceed the writable high-water mark drives the
drain past the compaction bound mid-delivery and verifies all 1524 replies
arrive. README Known Limitations gains the reply-backlog and call-backlog
bounds (en/zh, pairing re-recorded); a new Agent Note registers the findings.
|
||
|---|---|---|
| .agents | ||
| .claude | ||
| .github | ||
| apps | ||
| docs | ||
| native | ||
| packages | ||
| patches | ||
| python | ||
| scripts | ||
| snapshots | ||
| vendor | ||
| website | ||
| .editorconfig | ||
| .gitattributes | ||
| .gitignore | ||
| .gitlab-ci.yml | ||
| .jscpd.json | ||
| .oxlintrc.json | ||
| .oxlintrc.staged.json | ||
| .rgignore | ||
| AGENTS.md | ||
| BENCHMARK.md | ||
| BRAND_GUIDELINES.i18n.yaml | ||
| BRAND_GUIDELINES.md | ||
| BRAND_GUIDELINES.zh.md | ||
| CLAUDE.md | ||
| CONTRIBUTING.i18n.yaml | ||
| CONTRIBUTING.md | ||
| CONTRIBUTING.zh.md | ||
| lefthook.yml | ||
| LICENSE | ||
| package.json | ||
| pnpm-lock.yaml | ||
| pnpm-workspace.yaml | ||
| pytest.ini | ||
| README.i18n.yaml | ||
| README.md | ||
| README.zh.md | ||
| SAFETY.i18n.yaml | ||
| SAFETY.md | ||
| SAFETY.zh.md | ||
| THIRD_PARTY_NOTICES.md | ||
| tsconfig.base.client.json | ||
| tsconfig.base.json | ||
| tsconfig.client.json | ||
| tsconfig.host.json | ||
| tsconfig.json | ||
| tsdown.config.ts | ||
| vitest.config.ts | ||
| vitest.e2e.config.ts | ||
| vitest.expected.config.ts | ||
| vitest.shared.ts | ||
| vitest.snapshot.config.ts | ||
| vitest.web-stress.config.ts | ||
| vitest.web.config.ts | ||
| vitest.web.perf.config.ts | ||
DeepSeek Harness
English | 中文
DeepSeek Harness (dsh) is an open-source agent harness developed by DeepSeek AI.
It is built on an everything-is-a-plugin architecture and powered by Cordis, whose design is described in A Programming Paradigm for Spatiotemporal Composability.
Documentation: https://deepseek-harness.github.io/deepseek-harness/
Developer preview
DeepSeek Harness is in developer preview and iterating rapidly. THERE WILL BE COMPATIBILITY-BREAKING CHANGES.
Review the safety notice before running the project.
Run
Run from npm
Install Node.js, then run:
npx @deepseek-ai/dsh web
The command starts the Web UI at http://127.0.0.1:3080 by default and opens it in the default browser for a local launch. An SSH launch only prints the host URL because the SSH client or editor owns the local forwarded address. Pass --no-open to run the server without opening a browser. See Web UI guide.
Run from source
To run from a repository checkout:
git clone https://github.com/deepseek-ai/deepseek-harness.git
cd deepseek-harness
pnpm install
pnpm run build
pnpm dsh web
pnpm run build prepares the repository artifacts. pnpm dsh web uses those built artifacts without rebuilding.
Community and support
- Submit feedback or bug reports through GitHub Discussions.
- Add the
dsh-plugintopic to your plugin repository for discoverability. - Join DeepSeek Harness Discord community.
Contributing
See CONTRIBUTING.md.
Development
Start with the development guide and architecture documentation.
For agents, follow AGENTS.md.
License
Third-party dependencies and their licenses are disclosed in THIRD_PARTY_NOTICES.md.