mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
a2aa567371
core.md claimed to be the packages/core reference but opened on repo-wide type patterns and never documented the ownership vocabulary: AgentHandle, CreateAgentOptions, ResumeAgentOptions, and AgentFactory were TYPE_LINK_EXEMPTIONS pointing at a package README, invisible to the folder that calls itself the type reference. The page now reads spine map -> creation and ownership (AgentHandle pasted; the options and factory summarized with links into the generated registry section) -> the Agent handle (AgentStatus, AgentOptions, SteeringOutcome, SteeringReceipt, and SettleReason now pasted; the one settlement prose wall split by topic; delivery vocabulary ordered as a message travels) -> initiator -> interception -> a Sessions summary -> the ToolDefinition pointer -> an explicitly framed repo-wide patterns tail (the ...Map pattern, branded ids). The duplicate SessionEvent paste is gone -- session.md owns it and LINK_MAP follows -- the four ownership types moved from TYPE_LINK_EXEMPTIONS into LINK_MAP -> core.md, and three dead LINK_MAP entries (ContinuationDecision, ContinuationStop, HookContext) no longer name types absent from the source tree. The "what this page owns" meta-section folds into the intro. The subsystems README index silently lost tasks.md and session-reference.md on both language sides during a base absorption; the rows are restored and scripts/project-doc-site.spec.ts now fails when any page misses either side of the index (proven red on a removed row). tools.md links ToolSchema to its llm-streaming.md declaration instead of calling it core; subagent.md links AgentHandle and CreateAgentOptions.seed to the new section. A new Agent Note records the package-anchored page-scoping decision; the 2026-06-20 catalog note marks its spine-vs-seam rule superseded as the page-scoping rule while keeping the type-equiv mechanism current, and docs/AGENTS.md cites the new note.
1.7 KiB
1.7 KiB
interaction/ — the human-collaboration plane
English | 中文
The seams through which a human collaborates with a running agent — questions, approvals, permission presets, commands. These are product packages: real interfaces a person drives.
| Package | Role | ctx key |
|---|---|---|
commands/ |
Registers and dispatches human commands for interactive adapters. | ctx.commands |
user-approval/ |
Coordinates one-shot approval decisions. | ctx.approval |
permission/ |
Presents and persists user-facing permission presets. | ctx.permission |
user-interaction/ |
Defines the provider-neutral human question/answer seam. | ctx.userInteraction |
tool-ask-user/ |
Exposes human questions to the model. | (registers on ctx.tools) |
These packages integrate through existing agent and session contracts rather than changing the loop. Interactive applications provide the concrete command, approval, and question adapters; automation uses acp/, and runnable demo bundles live under examples/. The product dsh CLI composes these packages directly.
The subsystem references: approval.md, permission.md, user-interaction.md, and commands.md. The automation-only ACP transport is acp/, the SDK's JSON-RPC server half scaffold/server, and the shared bin boot glue boot/.