kingwl de9d618f0c fix(mode): a failed flush re-parks the pending intent instead of dropping it
Review hardening (the finding's ordering premise did not hold — see the
PR thread — but its failure-path kernel did): onBoundary cleared the
pending intent BEFORE appending the mode/set, so a backend rejecting
that one write lost the switch forever while the picker kept showing it
optimistically. The intent is now cleared only after the append lands;
a failed flush stays parked and the next healthy boundary converges the
log with the picker. The containment test extends to pin the re-park
and the retry.

The bridge's re-notify keeps deriving from the logged event's value —
now documented in place: the service holds ONE coalesced pending slot
(every flush reads the latest selection, so a stale flush cannot
exist), and for any other writer the logged value is the truth the
picker should track, in log order.
2026-07-10 16:28:11 +08:00
2026-07-06 03:07:35 +08:00
2026-07-05 01:25:58 +08:00

DeepSeek Harness

English | 中文

The DeepSeek Harness SDK is a plugin-based SDK for building agent harnesses.

Development

This monorepo is built on the Cordis framework (vendored as source under vendor/), microkernel-style: everything is a plugin.

pnpm install
pnpm run test          # vitest
pnpm run demo:repl     # REPL agent demo (needs DEEPSEEK_API_KEY)
pnpm run demo:acp      # ACP server agent demo (needs DEEPSEEK_API_KEY)

For humans, start with the development guide for local setup, hooks, environment variables, and quality gates, then read the architecture design and documentation graph index before package work. Local context lives in packages/ and vendor/.

For agents, follow AGENTS.md.

S
Description
No description provided
Readme MIT
120 MiB
0 Stars 1 Watchers 0 Forks
Languages
TypeScript 96.9%
CSS 1.6%
JavaScript 0.7%
Python 0.7%