packages/support/subagent-mock/README.md

# @deepseek-ai/dsh-subagent-mock

A scripted `SubagentProvider` for testing the [subagent seam](../../subagent/subagent/README.md) without a model or a real child agent — the subagent analog of [`dsh-llm-replay`](../llm-replay/README.md).

It lets a test drive `ctx.subagents` and the model-facing `dsh-tool-subagent` through the real Cordis loader/export path, exercising provider registration, async start, start-time capability validation, required-signal cancellation, `result`, `dispose`, and structured output deterministically and keylessly.

## Usage

Load it as a plugin (functional shape: `name`/`inject`/`Config`/`apply`, no default). Config (all optional):

| Key | Default | Meaning |
|---|---|---|
| `name` | `mock` | Registry name to register the provider under. |
| `reply` | `mock subagent reply` | The scripted child's final answer text. |
| `stopReason` | `completed` | The stop reason `result` settles with. |
| `capabilities` | all `true` | Which start-time capabilities (`outputSchema`, `depthLimit`, `toolFilter`, and `persona`) the provider advertises. |
| `inheritsParentContext` | `false` | Conversation-history descriptor: `false` means fresh, while `true` exercises seeded/fork wording. It says nothing about tool, service, scope, or authority inheritance. |
| `structured` | `{ reply }` | Structured value surfaced when a request carries an `outputSchema` and the capability is on. |

Aborting the required request signal or disposing before `result` settles flips the stop reason to `aborted`, so both holder-facing cancellation paths are observable.
Add subagent capability seam: interface, mock backend, model-facing tool 2026-06-21 22:31:56 +08:00			`# @deepseek-ai/dsh-subagent-mock`

			A scripted `SubagentProvider` for testing the [subagent seam](../../subagent/subagent/README.md) without a model or a real child agent — the subagent analog of [`dsh-llm-replay`](../llm-replay/README.md).

refactor(subagent): unify async readiness and cancellation 2026-07-12 22:41:59 +08:00			It lets a test drive `ctx.subagents` and the model-facing `dsh-tool-subagent` through the real Cordis loader/export path, exercising provider registration, async start, start-time capability validation, required-signal cancellation, `result`, `dispose`, and structured output deterministically and keylessly.
Add subagent capability seam: interface, mock backend, model-facing tool 2026-06-21 22:31:56 +08:00
			`## Usage`

			Load it as a plugin (functional shape: `name`/`inject`/`Config`/`apply`, no default). Config (all optional):

			`\| Key \| Default \| Meaning \|`
			`\|---\|---\|---\|`
			\| `name` \| `mock` \| Registry name to register the provider under. \|
			\| `reply` \| `mock subagent reply` \| The scripted child's final answer text. \|
			\| `stopReason` \| `completed` \| The stop reason `result` settles with. \|
refactor(subagent): unify async readiness and cancellation 2026-07-12 22:41:59 +08:00			\| `capabilities` \| all `true` \| Which start-time capabilities (`outputSchema`, `depthLimit`, `toolFilter`, and `persona`) the provider advertises. \|
fix(scope): align trust and input boundaries 2026-07-12 11:17:57 +08:00			\| `inheritsParentContext` \| `false` \| Conversation-history descriptor: `false` means fresh, while `true` exercises seeded/fork wording. It says nothing about tool, service, scope, or authority inheritance. \|
Add subagent capability seam: interface, mock backend, model-facing tool 2026-06-21 22:31:56 +08:00			\| `structured` \| `{ reply }` \| Structured value surfaced when a request carries an `outputSchema` and the capability is on. \|

refactor(subagent): unify async readiness and cancellation 2026-07-12 22:41:59 +08:00			Aborting the required request signal or disposing before `result` settles flips the stop reason to `aborted`, so both holder-facing cancellation paths are observable.