mirror of
https://github.com/deepseek-ai/deepseek-harness.git
synced 2026-09-09 04:02:35 +00:00
Run the dsh-archive-agent-notes audit over every active Agent Note on current master, judging each record by whether its rationale still guides work rather than by size or age. - Archive 453 implemented bilingual triplets (417,882 English words): completed UI chrome, narrow adapters, closed bug fixes, implementation walkthroughs whose package READMEs, docs pages, generators, or successor notes now carry the useful behavior, and 51 records fully superseded by a later active note. Keep 201 implemented notes whose ownership rules, negative guarantees, durable or wire semantics, security rules, reintroduction conditions, or still-tempting rejected alternatives remain useful. - Reject 7 proposals whose premise is gone or whose work shipped in amended form under other records; delete 2 rejected notes that no longer prevent a plausible mistake. - Retarget every remaining inbound link to the archived path, and repair active prose that named an archived record as the owner of a live fact: parenthetical citations drop, ownership sentences redirect to the README, docs page, or active note that states the fact, and history citations say so. Chinese files link the English archived path because the pairing gate treats the frozen tree as outside the bilingual corpus. - Seal 1,359 new frozen artifacts; existing seals are unchanged and outbound links from archived notes are neither inspected nor repaired. - Regenerate docs/config-catalog.md after the hook-bridge comment edits shifted two source line numbers.
description, kind
| description | kind |
|---|---|
| The workflow group map: model-authored orchestration scripts that fan out subagents, for users and maintainers navigating the group. | package-group |
packages/workflow
English | 中文
Summary
The workflow group lets an agent run a model-authored orchestration script that fans work out across many subagents and returns a final value. The workflow package provides the run service, the worker-thread package executes scripts in isolated threads, and two model-facing tools expose orchestration: the general workflow tool for scripted fan-out and the fixed ralph tool for fresh-agent iterative loops. The script coordinates agents with hooks while the agents do the actual work. The engine keeps a script's synchronous work off the host event loop but is containment, not a security boundary.
Table of Contents
Packages
| Package | Role | ctx key |
|---|---|---|
workflow |
Runs a model-written orchestration script that fans out subagents | ctx.workflowEngine |
workflow-worker-thread |
Executes each workflow script in its own worker thread, off the host event loop | registers on ctx.workflowEngine |
tool-workflow |
Gives the model the workflow tool for scripted multi-agent orchestration |
registers on ctx.tools |
tool-ralph |
Gives the model the ralph tool for fresh-agent iterative loops |
registers on ctx.tools |
Related documentation
- Workflow subsystem — the seam's types, start request, and
workflow/*events. - Generated tool catalog — the
workflowtool schema the model receives. - Generated tool catalog — the
ralphtool schema the model receives. - Generated configuration catalog — every accepted engine config field.
- Dynamic workflows Agent Note — the seam design and its decisions.
- Harness-level goal-based execution Agent Note — the fixed fresh-agent loop design and deferred work.
Dev Note
Working context for maintainers — click to expand
None.