dsh-pstack 0.3.0-beta.1 → 0.3.1

package/dist/skills/authored/docs-drift/SKILL.md

@@ -25,7 +25,7 @@ Apply explicit paths, globs, narrowing, and exclusions to the candidate set. A w
 
 Classify every candidate using project pointers, governing instructions, and ownership and update conventions:
 
-- **Maintained:** owned by this project and updated as its implementation or workflows evolve. Apply all five checks.
+- **Maintained:** owned by this project and updated as its implementation or workflows evolve. Apply every check below.
 - **Reference-only:** documentation of a dependency, host product, library, or other external system, even when stored inside the repository. Use it as evidence without auditing its own drift.
 - **Excluded:** outside the requested scope or otherwise excluded by an explicit rule.
 - **Unresolved:** maintenance ownership is unclear. Ask before including it and continue classifying unrelated candidates.
@@ -44,7 +44,7 @@ Distinguish current facts, intended requirements, and historical statements. Cur
 
 Complete this step when every checkable claim in every maintained document has a source-backed disposition or an explicit evidence limitation.
 
-## 3. Apply all five checks
+## 3. Apply every check
 
 **Implementation drift.** Find stale statements or statements contradicted by current evidence about architecture, behavior, paths, commands, interfaces, configuration, dependencies, counts, and status.
 
@@ -54,11 +54,11 @@ Complete this step when every checkable claim in every maintained document has a
 
 **Links and pointers.** Resolve repository-relative links, referenced paths, and anchors from their containing document. Check external links when feasible; classify network or access failures as unverified rather than dead.
 
-**Redundancy and unsupported elaboration.** Find semantic duplication, scattered rules, obsolete passages, and unsupported facts, assumptions, or invented elaboration accumulated during iteration. Examples include fabricated module responsibilities, command behavior, configuration defaults, design rationale, compatibility, performance conclusions, test coverage, and acceptance status. Shrink disproven or unsupported elaboration to the smallest evidence-backed statement. Insufficient evidence alone makes a claim unverified, not a deletion candidate. Preserve the context of historical statements and explicit future plans.
+**Redundancy and unsupported elaboration.** Find semantic duplication, scattered rules, obsolete passages, and incidental guidance mirroring another document's current headings, inventory, or wording when its responsibility alone would suffice. Before flagging such coupling, establish whether a skill intentionally owns and maintains that structure as a discovery, parsing, generation, or record-format contract; check these contracts for consistency rather than proposing to generalize or remove them. A skill's own template or fixed pointer location is likewise intentional when its consumers rely on it; validate it against those consumers rather than presenting it as a removable-duplication example. Find unsupported facts, assumptions, or invented elaboration accumulated during iteration. Examples include fabricated module responsibilities, command behavior, configuration defaults, design rationale, compatibility, performance conclusions, test coverage, and acceptance status. Shrink disproven or unsupported elaboration to the smallest evidence-backed statement. Insufficient evidence alone makes a claim unverified, not a deletion candidate. Preserve the context of historical statements and explicit future plans.
 
 Before proposing consolidation, identify an authoritative location. Preserve intentional summaries, audience-specific views, language variants, and unique qualifications.
 
-Report style, formatting, or completeness preferences only when they substantiate one of these findings. Complete this step when every class has been applied to every maintained document and every potential finding has a location, observed statement, supporting evidence or evidence boundary, and proposed action.
+Report style, formatting, or completeness preferences only when they substantiate one of these findings. Complete this step when every check has been applied to every maintained document and every potential finding has a location, observed statement, supporting evidence or evidence boundary, and proposed action.
 
 ## 4. Resolve authority and classify findings
 

package/dist/skills/authored/docs-drift/SKILL.zh.md

@@ -25,7 +25,7 @@ disable-model-invocation: true
 
 根据项目指针、管辖指令、归属及更新约定给每个候选文档分类：
 
-- **维护文档：**由本项目所有，并随项目实现或工作流迭代更新。执行全部五类检查。
+- **维护文档：**由本项目所有，并随项目实现或工作流迭代更新。执行下列全部检查。
 - **仅作参考：**依赖、宿主产品、程序库或其他外部系统的说明文档，即使存放在仓库内。只用作证据，不检查其自身漂移。
 - **已排除：**不在请求范围内，或被显式规则排除。
 - **未决：**维护归属不明确。纳入前先询问，同时继续分类无关候选文档。
@@ -44,7 +44,7 @@ disable-model-invocation: true
 
 每份维护文档中的每项可核验陈述都有来源依据的处置结果或明确的证据限制时，本步完成。
 
-## 3. 执行全部五类检查
+## 3. 执行全部检查
 
 **实现漂移。** 查找关于架构、行为、路径、命令、接口、配置、依赖、数量和状态的过时段落，或与当前证据冲突的陈述。
 
@@ -54,11 +54,11 @@ disable-model-invocation: true
 
 **链接与指针。** 从引用所在文档解析仓库相对链接、路径与锚点。条件允许时检查外链；网络或访问失败归为未核验，不直接判为死链。
 
-**冗余与无依据扩写。** 查找语义重复、规则散落、过时段落，以及持续迭代中积累的无依据事实、假设与臆造扩写。例子包括虚构的模块职责、命令行为、配置默认值、设计理由、兼容性、性能结论、测试覆盖与验收状态。将已证伪或无依据的扩写收缩为有证据支持的最小陈述；仅证据不足时标为未核验，不作为删除候选。历史陈述和明确的未来计划保留其语境。
+**冗余与无依据扩写。** 查找语义重复、规则散落、过时段落，以及职责说明已经足够却仍镜像其他文档当前标题、清单或措辞的偶发指引。报告这类耦合前，先确认它是否属于技能有意维护的发现、解析、生成或记录格式契约；此类契约应检查一致性，不建议泛化或删除。技能自有模板或固定指针位置在消费者依赖时同样属于刻意设计；应核对它与消费者的一致性，不把它作为可消除冗余的示例。查找持续迭代中积累的无依据事实、假设与臆造扩写。例子包括虚构的模块职责、命令行为、配置默认值、设计理由、兼容性、性能结论、测试覆盖与验收状态。将已证伪或无依据的扩写收缩为有证据支持的最小陈述；仅证据不足时标为未核验，不作为删除候选。历史陈述和明确的未来计划保留其语境。
 
 提出合并前确定权威位置。保留有意的摘要、面向不同读者的视图、语言版本与独有限定条件。
 
-文风、格式或完整性偏好只有构成上述发现时才报告。每份维护文档都执行过全部五类检查，且每项潜在发现都有位置、当前陈述、支持证据或证据边界及建议动作时，本步完成。
+文风、格式或完整性偏好只有构成上述发现时才报告。每份维护文档都执行过上述全部检查，且每项潜在发现都有位置、当前陈述、支持证据或证据边界及建议动作时，本步完成。
 
 ## 4. 判定权威并分类发现
 

package/dist/skills/vendored/control-cli/SKILL.md

@@ -0,0 +1,109 @@
+---
+name: control-cli
+description: Build or adapt a local harness to drive, inspect, and profile an interactive CLI or TUI without external services. Use for CLI UX checks, startup regressions, memory leaks, hangs, prompt flows, or terminal demos.
+---
+
+# Control CLI
+
+Use a repeatable local harness to exercise an interactive CLI instead of poking at it manually. First reuse the repo's own test/demo harness if it exists; otherwise assemble a temporary harness from standard local tools.
+
+## What It Is Used For
+
+- Reproducing CLI/TUI bugs with deterministic input.
+- Verifying keyboard flows, prompts, interrupts, resize behavior, and terminal layout.
+- Capturing before/after transcripts for bug fixes.
+- Profiling startup time, slow operations, hangs, or memory growth.
+- Recording a short terminal demo when output is easier to show than explain.
+
+## Harness Loop
+
+1. Identify the command under test and the smallest reproducible workspace.
+2. Discover existing local harnesses: package scripts, e2e tests, demo recorders, expect scripts, or PTY helpers.
+3. If no harness exists, launch the CLI in an isolated terminal session with deterministic env vars.
+4. Capture the current screen before interacting.
+5. Send one action at a time: text, Enter, arrows, Escape, Ctrl-C, resize.
+6. Wait for a concrete screen pattern or prompt before the next action.
+7. Save the transcript and any profile artifacts.
+8. Kill the session cleanly.
+
+## Harness Options
+
+- Repo-native harness: prefer checked-in scripts because they know the app's startup, env, and prompts.
+- `tmux`: managed sessions, `capture-pane`, `send-keys`, attach/detach.
+- PTY probe: use a short Python, Node, or Expect script when tmux is unavailable.
+- Runtime inspector: use Node or Bun inspector for CPU profiles, heap snapshots, and live evaluation.
+- Terminal recorder: use repo-local demo tools or asciinema-compatible tools when the user asks for a demo.
+
+## Minimal tmux Harness
+
+```bash
+SESSION="cli-harness-$(date +%s)"
+tmux new-session -d -s "$SESSION" -- <command-under-test>
+tmux capture-pane -pt "$SESSION"
+tmux send-keys -t "$SESSION" "help" Enter
+tmux capture-pane -pt "$SESSION"
+tmux kill-session -t "$SESSION"
+```
+
+For Node CLIs:
+
+```bash
+NODE_OPTIONS="--inspect=127.0.0.1:0" tmux new-session -d -s "$SESSION" -- <node-cli-command>
+```
+
+Read the terminal output to find the inspector URL, then use Chrome DevTools-compatible tooling if profiling is needed.
+
+## Minimal PTY Harness
+
+Use a PTY script when you need deterministic waits in a repo that does not have tmux or a demo harness. Keep it temporary unless the user asks to add a reusable test.
+
+```python
+import os
+import pty
+import select
+import subprocess
+import time
+
+master_fd, slave_fd = pty.openpty()
+proc = subprocess.Popen(
+    ["<command>", "<arg>"],
+    stdin=slave_fd,
+    stdout=slave_fd,
+    stderr=slave_fd,
+    close_fds=True,
+)
+os.close(slave_fd)
+
+deadline = time.time() + 30
+buffer = b""
+while time.time() < deadline:
+    ready, _, _ = select.select([master_fd], [], [], 0.25)
+    if not ready:
+        continue
+    chunk = os.read(master_fd, 4096)
+    buffer += chunk
+    if b"<ready text>" in buffer:
+        os.write(master_fd, b"help\n")
+        break
+
+print(buffer.decode(errors="replace"))
+proc.terminate()
+os.close(master_fd)
+```
+
+If the CLI needs richer terminal control, use `pty.fork()` or an existing PTY library.
+
+## Profiling Recipes
+
+- Startup regression: capture baseline and treatment startup timings under the same machine, env, and command.
+- Slow operation: start a CPU profile, perform the operation, stop the profile, and compare top self-time functions.
+- Memory leak: force GC if available, take a heap snapshot, perform the operation repeatedly, force GC again, and take another snapshot.
+- Hang: capture the screen, active handles/resources, and a stack/CPU sample before interrupting.
+
+## Guardrails
+
+- Prefer deterministic waits over sleeps. If you must sleep, explain why.
+- Do not send credentials or destructive commands into a controlled session.
+- Keep the harness in `/tmp` unless the repo already has a testing/demo harness.
+- Do not hard-code paths from another repository. Adapt commands to the current repo's scripts and runtime.
+- Clean up tmux sessions, temp dirs, inspector processes, and demo artifacts unless the user asks to keep them.

package/dist/skills/vendored/control-ui/SKILL.md

@@ -0,0 +1,109 @@
+---
+name: control-ui
+description: Build or adapt a local browser/CDP harness to drive and inspect a web, IDE, or Electron UI. Use for local UI verification, screenshots, accessibility snapshots, perf profiles, visual diffs, or reproducing UI bugs.
+---
+
+# Control UI
+
+Use local browser automation to verify UI behavior with evidence. First reuse the repo's own Playwright, browser, or Electron harness if it exists; otherwise assemble a temporary local harness around the app's dev server or Chromium debug port.
+
+## What It Is Used For
+
+- Reproducing UI bugs that depend on real browser focus, keyboard input, scrolling, resizing, or rendering.
+- Verifying visual or accessibility changes with screenshots and snapshots.
+- Checking local web, IDE, or Electron behavior before shipping.
+- Capturing console logs, network logs, CPU profiles, traces, or heap snapshots.
+- Creating before/after evidence for `verify-this`.
+
+## Setup Pattern
+
+1. Start the app locally using the repo's documented dev command.
+2. Discover existing local harnesses: Playwright tests, Cypress specs, Storybook, browser scripts, Electron launch scripts, or snapshot tools.
+3. For a web app, connect to the local URL with the existing browser tooling.
+4. For Electron/Chromium, enable a remote debugging port when supported.
+5. Select the correct page by stable app markers, not by tab order alone.
+6. Prefer accessibility roles, labels, and stable `data-*` selectors over coordinates.
+
+## Generic Web Harness
+
+Use the repo's installed browser tooling when possible. If the repo already has Playwright, a minimal one-off probe looks like:
+
+```javascript
+import { chromium } from "playwright";
+
+const browser = await chromium.launch();
+const page = await browser.newPage({ viewport: { width: 1280, height: 800 } });
+await page.goto("http://127.0.0.1:<port>");
+await page.getByRole("button", { name: /submit/i }).click();
+await page.screenshot({ path: "/tmp/ui-harness-after.png", fullPage: true });
+await browser.close();
+```
+
+Do not add Playwright as a project dependency just for this probe unless the user asks. Prefer existing dev dependencies or external browser tools already available in the environment.
+
+## Generic CDP Harness
+
+For Electron or a Chromium app launched with `--remote-debugging-port=<port>`, connect over CDP:
+
+```javascript
+import { chromium } from "playwright";
+
+const browser = await chromium.connectOverCDP("http://127.0.0.1:<debug-port>");
+const pages = browser.contexts().flatMap((context) => context.pages());
+let page;
+for (const candidate of pages) {
+  if (await candidate.locator("<app-root-selector>").count()) {
+    page = candidate;
+    break;
+  }
+}
+
+if (!page) {
+  console.log(await Promise.all(pages.map(async (p) => ({
+    title: await p.title(),
+    url: p.url(),
+  }))));
+  throw new Error("No matching app page found");
+}
+
+await page.screenshot({ path: "/tmp/ui-harness-cdp.png", fullPage: true });
+await browser.close();
+```
+
+Replace `<app-root-selector>` with a stable marker from the current repo, such as a root app node, landmark, or product-specific `data-*` attribute.
+
+## Interaction Loop
+
+1. Capture a page snapshot or screenshot before acting.
+2. Choose a target from the latest page structure.
+3. Perform exactly one structural action: click, type, keypress, drag, scroll, navigate, or resize.
+4. Capture a fresh snapshot/screenshot.
+5. Verify the expected state change.
+6. Save artifacts for before/after comparisons when the user asked for proof.
+
+## CDP Capabilities
+
+Use raw CDP only when higher-level browser APIs are insufficient:
+
+- Performance: CPU profiles, traces, paint flashing, FPS meter, layout shift inspection.
+- Memory: heap snapshots and forced GC for leak investigations.
+- Network: request blocking, throttling, cache disablement, request/response logs.
+- Rendering: viewport changes, color scheme emulation, reduced motion, accessibility checks.
+- Debugging: console streaming, exception capture, DOM snapshots.
+
+## Page Selection
+
+When multiple app windows/tabs share a debug port:
+
+- Prefer a positive marker for the surface under test, such as an app root selector.
+- Use a negative marker to avoid the wrong surface when necessary.
+- If no page matches, list available page titles and URLs instead of guessing.
+
+## Guardrails
+
+- Do not rely on stale element references after navigation or structural changes.
+- Avoid coordinate clicks unless a fresh screenshot was captured immediately before the click.
+- Keep test data local and disposable.
+- Do not store screenshots or heap snapshots from privacy-sensitive workspaces unless the user explicitly agrees.
+- Do not hard-code selectors, ports, or script paths from another repository. Discover the current repo's local app markers.
+- Clean up dev servers, debug sessions, and temp profiles when done.

package/dist/skills/vendored/deslop/SKILL.md

@@ -0,0 +1,22 @@
+---
+name: deslop
+description: Remove AI-generated code slop and clean up code style
+---
+
+# Remove AI code slop
+
+Check the diff against main and remove AI-generated slop introduced in the branch.
+
+## Focus Areas
+
+- Extra comments that are unnecessary or inconsistent with local style
+- Defensive checks or try/catch blocks that are abnormal for trusted code paths
+- Casts to `any` used only to bypass type issues
+- Deeply nested code that should be simplified with early returns
+- Other patterns inconsistent with the file and surrounding codebase
+
+## Guardrails
+
+- Keep behavior unchanged unless fixing a clear bug.
+- Prefer minimal, focused edits over broad rewrites.
+- Keep the final summary concise (1-3 sentences).

package/dist/subagent.d.mts

@@ -1,129 +1,33 @@
-import { _ as ToolsHost, g as ToolDefinition, h as SubagentsHost, m as SubagentCapabilities, n as AgentOptions, r as AgentsHost, s as LlmHost, t as Agent, v as WorkingDirectoryHost } from "./host-contract-CUPSpeNk.mjs";
-import { n as RoleSpec } from "./role-manifest-8OERX9-s.mjs";
-/** One resolved child route. */
-type Route = {
-  readonly kind: "inherit";
-  /** The spelling the file used; `undefined` for an implicit fallback. */
-  readonly alias?: "inherit-parent" | "auto";
-} | {
-  readonly kind: "route";
-  readonly provider: string;
-  readonly model: string;
-  readonly effort?: string;
-};
-/** How one role's value expands into children. */
-type RouteSelectionMode = "single" | "panel" | "selected";
-interface RouteSelection {
-  readonly role: RoleSpec;
-  readonly mode: RouteSelectionMode;
-  /** Whether the role came from the file or the inherit-parent fallback. */
-  readonly configured: boolean;
-  readonly routes: readonly Route[];
-  /** How many entries the role holds, before selection. */
-  readonly total: number;
-  readonly roleIndex?: number;
-}
-/** Cordis row name, used by Loader diagnostics. */
+import { n as Route } from "./route-7SqXDYrL.mjs";
+import { Context } from "@deepseek-ai/cordis";
+import { ToolDefinition } from "@deepseek-ai/dsh-tools";
+import { LlmRuntime } from "@deepseek-ai/dsh-llm";
+import { Agent, AgentOptions } from "@deepseek-ai/dsh-agent";
+import { WorkingDirectoryService } from "@deepseek-ai/dsh-working-directory";
+import { SubagentRuntime } from "@deepseek-ai/dsh-subagent";
 export declare const name = "pstack-subagent";
-/**
- * Delegation needs the tool registry, the subagent registry, the LLM adapters, and the
- * session directory. `agents` is not here: it is optional and read per call, so a
- * profile without it still delegates and the child simply keeps its starting effort.
- */
 export declare const inject: string[];
-/** Model-facing tool name. */
 export declare const TOOL_NAME = "pstack_subagent";
-/** Backend used when the row does not name one. */
-export declare const DEFAULT_SUBAGENT_PROVIDER = "spawn";
-/** The child kinds this tool knows how to brief. */
-export declare const AGENT_KINDS: readonly ["poteto-agent", "comment-sicko", "general"];
+/** Default backend when the row does not name one. */
+export declare const DEFAULT_PROVIDER = "spawn";
+/** Child kinds this tool can brief. */
+export declare const AGENT_KINDS: readonly ["poteto-agent", "comment-sicko", "readonly", "general"];
 export type AgentKind = (typeof AGENT_KINDS)[number];
 /** Row configuration. */
 export interface PstackSubagentConfig {
   readonly provider: string;
   readonly maxDepth?: number;
 }
-/**
- * Depth a child runs at when a call omits `maxDepth` or passes an unusable value.
- *
- * A child is always at least depth 1 (it is one level below its parent), so this is the
- * smallest value that can start a child while forbidding it from delegating further.
- */
-export declare const DEFAULT_CHILD_MAX_DEPTH = 1;
-/** What a call asked for, after every required argument has been validated. */
 export interface DelegationArgs {
   readonly description: string;
   readonly prompt: string;
   readonly agent: AgentKind;
   readonly role: string | null;
-  readonly cwd: string | null;
-  readonly maxDepth: number | null;
   readonly roleIndex: number | null;
   readonly reasoningEffort: string | null;
+  readonly cwd: string | null;
+  readonly maxDepth: number | null;
 }
-/** One child this call started. */
-export interface ChildRecord {
-  readonly childId: string;
-  readonly label: string;
-  readonly agent: string;
-  readonly role: string;
-  readonly route: string;
-  readonly effort?: string;
-  readonly maxDepth?: number;
-}
-export interface DelegationResult {
-  readonly kind: "activation" | "activations";
-  readonly children: readonly ChildRecord[];
-  readonly diagnostics: readonly string[];
-}
-/** Raised for a configuration or argument problem, before any child starts. */
-export declare class DelegationError extends Error {
-  constructor(message: string);
-}
-/** Raised when a child starts but a later entry in the same call fails. */
-export declare class PartialDelegationError extends DelegationError {
-  readonly startedChildren: readonly ChildRecord[];
-  constructor(message: string, startedChildren: readonly ChildRecord[]);
-}
-/** The live services and locations one delegation reads. */
-export interface SubagentRuntime {
-  readonly subagents: SubagentsHost;
-  readonly llm: LlmHost;
-  /** Optional: absent means the child keeps the effort it was started with. */
-  readonly agents?: AgentsHost;
-  readonly workingDirectory: WorkingDirectoryHost;
-  readonly dshHome: string;
-}
-/**
- * Validate the row configuration without a Schemastery dependency.
- *
- * A typo must fail at activation rather than at the first delegation, and an omitted
- * `config` must be valid. Cordis passes the raw mapping because this row exports no
- * `Config` object; callers that object as `config` are still checked here.
- */
-export declare function normalizeConfig(value: unknown): PstackSubagentConfig;
-/** The preset id behind each pstack agent kind. `general` joins the parent preset. */
-export declare const AGENT_PRESETS: Readonly<Record<Exclude<AgentKind, "general">, string>>;
-/** The preset a child of this kind must mount, or undefined to join the parent preset. */
-export declare function agentPresetFor(agent: AgentKind): string | undefined;
-/** Compose the self-contained prompt one child receives. */
-export declare function composeChildPrompt(input: {
-  readonly injectedPaths?: readonly {
-    readonly label: string;
-    readonly path: string;
-  }[];
-  readonly task: string;
-}): string;
-export declare const DELEGATION_ARGUMENT_KEYS: readonly ["description", "prompt", "agent", "role", "roleIndex", "reasoningEffort", "cwd", "maxDepth"];
-/**
- * Keys a call must pass. `maxDepth` is accepted but not required: a missing or unusable
- * value resolves to `DEFAULT_CHILD_MAX_DEPTH` instead of forcing the caller to guess an
- * integer, which is where the reflexive `0` came from.
- */
-export declare const REQUIRED_DELEGATION_ARGUMENT_KEYS: readonly ["description", "prompt", "agent", "role", "roleIndex", "reasoningEffort", "cwd"];
-/** Validate every required model-facing argument. Null declines an optional setting. */
-export declare function parseDelegationArgs(raw: unknown): DelegationArgs;
-/** One planned child, before any Host call. */
 export interface ChildPlan {
   readonly index: number;
   readonly total: number;
@@ -132,75 +36,62 @@ export interface ChildPlan {
   readonly role: string;
   readonly route: Route;
   readonly routeLabel: string;
-  readonly effort?: string;
   readonly agentOptions?: AgentOptions;
-  /** Preset id that supplies this child's persona and tool composition. */
   readonly agentPreset?: string;
   readonly cwd?: string;
   readonly maxDepth?: number;
 }
 export interface DelegationPlan {
-  readonly agent: AgentKind;
-  readonly prompt: string;
   readonly provider: string;
   readonly role: string;
-  readonly mode: RouteSelection["mode"];
-  readonly roleIndex?: number;
-  readonly roleTotal: number;
-  readonly reasoningEffort?: string;
+  readonly prompt: string;
   readonly children: readonly ChildPlan[];
   readonly diagnostics: readonly string[];
 }
-/** Route text as reported to the model. */
-export declare function routeLabel(route: Route, effortOverride?: string): string;
-/** Take the smallest of the requested depth, this row's cap, and the Host setting. */
-export declare function resolveDelegationDepth(configured: number | undefined, requested: number | null | undefined, hostLimit: number | undefined): number | undefined;
-/**
- * Turn the per-call `maxDepth` request into an effective depth request.
- *
- * A child is always at least depth 1, so `0` can never start one: it is reported and
- * replaced with `DEFAULT_CHILD_MAX_DEPTH` rather than failing the whole call. Omitting
- * `maxDepth` (null) also uses the default, so a caller never has to guess an integer.
- */
-export declare function requestedChildDepth(requested: number | null, diagnostics: string[]): number;
-/** Resolve the role file, routes, prompt, and depth into one plan. Pure of service calls. */
-export declare function planDelegation(args: DelegationArgs, runtime: SubagentRuntime, config?: PstackSubagentConfig): DelegationPlan;
-/** Check the backend can enforce what this call asks for. */
-export declare function assertProviderCapabilities(capabilities: SubagentCapabilities, providerName: string, asks: {
-  readonly agentOptions: boolean;
-  readonly agentPreset: boolean;
-  readonly maxDepth: boolean;
-}): void;
-/**
- * Resolve and validate one child's `cwd`.
- *
- * A child may run inside the session directory or inside an explicitly separate Git
- * worktree. Anything else is refused: this tool does not create isolation, so it will
- * not promise one.
- */
-export declare function resolveChildCwd(requested: string | undefined, sessionRoot: string): string | undefined;
-/**
- * Start the planned children. Everything rejectable has already been rejected; a
- * failure at entry N keeps children 1..N-1 running and reports their ids.
- */
-export declare function startPlannedChildren(parent: Agent, plan: DelegationPlan, runtime: SubagentRuntime, config: PstackSubagentConfig, signal: AbortSignal): Promise<DelegationResult>;
-/** Full delegation: plan, validate, start. */
-export declare function delegate(parent: Agent, args: DelegationArgs, runtime: SubagentRuntime, config?: PstackSubagentConfig, signal?: AbortSignal): Promise<DelegationResult>;
-/** Render one delegation result for the model. */
-export declare function renderDelegationResult(result: DelegationResult): string;
-/** Build the model-facing tool for one row. */
-export declare function createPstackSubagentTool(runtime: SubagentRuntime, config?: PstackSubagentConfig): ToolDefinition;
-/** The slices of the Cordis context this row uses. */
-export interface PstackSubagentHost {
-  readonly tools: ToolsHost;
-  readonly subagents: SubagentsHost;
-  readonly llm: LlmHost;
-  readonly workingDirectory: WorkingDirectoryHost;
+export interface ChildRecord {
+  readonly childId: string;
+  readonly label: string;
+  readonly agent: string;
+  readonly role: string;
+  readonly route: string;
+  readonly effort?: string;
+  readonly maxDepth?: number;
+}
+export interface DelegationFailure {
+  readonly index: number;
+  readonly total: number;
+  readonly label: string;
+  readonly routeLabel: string;
+  readonly reason: string;
+}
+export type DelegationResult = {
+  readonly kind: "activation" | "activations";
+  readonly children: readonly ChildRecord[];
+  readonly diagnostics: readonly string[];
+} | {
+  readonly kind: "partial";
+  readonly children: readonly ChildRecord[];
+  readonly diagnostics: readonly string[];
+  readonly failure: DelegationFailure;
+};
+/** The live services one delegation reads. */
+export interface DelegationRuntime {
+  readonly subagents: SubagentRuntime;
+  readonly llm: LlmRuntime;
+  readonly workingDirectory: WorkingDirectoryService;
+  readonly dshHome: string;
+  readonly potetoModeSkillPath: string;
 }
-/** Build the runtime a real Host call reads. */
-export declare function hostRuntime(ctx: PstackSubagentHost, getAgentRegistry?: () => AgentsHost | undefined): SubagentRuntime;
-/** Register `pstack_subagent` for this row. */
-export declare function apply(ctx: PstackSubagentHost & {
-  get?: (name: string) => AgentsHost | undefined;
-}, config?: unknown): void;
-export {};
+/** Validate the row's own config; omitted config uses the default provider. */
+export declare function normalizeConfig(value: unknown): PstackSubagentConfig;
+/** Validate every model-facing argument before doing any Host call. */
+export declare function parseDelegationArgs(raw: unknown): DelegationArgs;
+/** Resolve the role file, child routes, prompt, and depth before activation starts. */
+export declare function planDelegation(args: DelegationArgs, runtime: DelegationRuntime, config?: PstackSubagentConfig): DelegationPlan;
+/** Start every planned child after one final capability and route check. */
+export declare function startPlannedChildren(parent: Agent, plan: DelegationPlan, runtime: DelegationRuntime, signal: AbortSignal): Promise<DelegationResult>;
+/** Complete delegation: plan, check, start. */
+export declare function delegate(parent: Agent, args: DelegationArgs, runtime: DelegationRuntime, config: PstackSubagentConfig, signal: AbortSignal): Promise<DelegationResult>;
+export declare function apply(ctx: Context, rawConfig?: unknown): void;
+/** Build the model-facing tool. Exported for tests. */
+export declare function createPstackSubagentTool(runtime: DelegationRuntime, config?: PstackSubagentConfig): ToolDefinition;