Three separate paths in the CPython child allocated state proportional to a value's width or a string's length, so a legitimate input the byte budgets admit could die as the program's own MemoryError. `_lossless_json_violation` enqueued one traversal tuple per member while running, in `dispatch`, over MODEL-CONSTRUCTED binding arguments that no child-side byte budget bounds first. It now uses the same (kind, container, iterator) cursor the other two walks already had, checking dict keys as the cursor pulls each entry. Measured over `[0] * 6_000_000` (~17 MB of JSON): 459.1 MiB of traversal tuples before, 0.0 MiB after. `_decode_json_plain` matched JSON strings with a `(?:[^"\\]|\\.)*` repetition, which makes CPython's engine retain backtracking state proportional to the string's width: 146 MiB for a 1 MiB string, 557.8 MiB for 4 MiB. A legitimate multi-megabyte binding reply raised MemoryError inside `_pump_replies`, and because that pump is the only settler of the call's future, the run stranded until the wall clock reported `timeout`. Strings now scan chunk-to-chunk over a character class, which the engine matches without backtracking state; the same 4 MiB decode peaks at the 4.0 MiB result. `_check_done_value` charged strings and dict keys what `_dump_string(...).encode()` returned, building the escaped copy plus its encode to MEASURE it -- ~6x the original each for control-heavy text, so metering a value the budget then rejects could itself breach RLIMIT_AS and report `exception` where the seam promises `output-limit`. The new `_json_str_cost` counts instead, reusing `_json_string_cost`'s C-level passes and reproducing `_dump_string`'s exact surrogate rules (fold spelled-out pairs, charge six ASCII bytes per lone surrogate). Identical values, 228.9 MiB -> 19.1 MiB of peak on a 20M-NUL string. Each fix ships a regression test. The two RLIMIT_AS repros are Linux-only: Darwin does not apply the limit, so the peaks above are measured directly and recorded in the test comments. |
||
|---|---|---|
| .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.