@dreki-gg/pi-subagent 0.7.0 → 0.8.0

package/.fallowrc.json

@@ -0,0 +1,6 @@
+{
+  "$schema": "https://raw.githubusercontent.com/fallow-rs/fallow/main/schema.json",
+  "entry": [
+    "extensions/subagent/index.ts"
+  ]
+}

package/CHANGELOG.md

@@ -1,5 +1,21 @@
 # @dreki-gg/pi-subagent
 
+## 0.8.0
+
+### Minor Changes
+
+- [`3a246f3`](https://github.com/dreki-gg/pi-extensions/commit/3a246f3fd55b900ebfcfbea2eff2a7ab9f9f94cf) Thanks [@jalbarrang](https://github.com/jalbarrang)! - Refactor agent distribution from custom `pi.agents` to standard `pi.prompts`
+
+  - Rename `agents/` directory to `prompts/` to follow pi's standard resource type
+  - Use `pi.prompts` in package.json instead of non-standard `pi.agents`
+  - Remove legacy bundled-directory fallback — agent prompts are now resolved via pi's package manager
+  - Remove `/delegate-agents` command (unused; `/run-agent` and `subagent` tool cover all usage)
+  - Extract shared spawn logic into `spawn-utils.ts`, eliminating cross-file duplication between `agent-runner.ts` and `index.ts`
+  - Remove dead exports (`formatAgentList`, `buildSynthesisPrompt`, `SYNTHESIS_INSTRUCTION`)
+  - Clean up unused imports
+  - Maintainability score improved from 70.7 (moderate) to 90.6 (good)
+  - Model configuration (`model`, `thinking`, `tools` frontmatter) is unchanged
+
 ## 0.7.0
 
 ### Minor Changes

package/README.md

@@ -1,6 +1,6 @@
 # @dreki-gg/pi-subagent
 
-Subagent tool and direct agent runs for pi — isolated agents, parallel scouts, manager workflows, and bundled agents.
+Subagent tool and direct agent runs for pi — isolated agents, parallel scouts, manager workflows, and bundled prompts.
 
 ## Install
 
@@ -118,7 +118,7 @@ If the chosen agent frontmatter sets `sessionStrategy: fork-at`, the command clo
 
 ## Agent Definitions
 
-Create agent files in `~/.pi/agent/agents/` or `.pi/agents/` as markdown with YAML frontmatter:
+Create agent prompt files in `~/.pi/agent/prompts/` or `.pi/prompts/` as markdown with YAML frontmatter:
 
 ```markdown
 ---
@@ -153,22 +153,13 @@ Notes:
 - `worker`, `reviewer`, `bug-prover`, and `manager` default to `sessionStrategy: fork-at`.
 - "Default reasoning level" maps to the frontmatter field `thinking` and can be overridden per run.
 
-Resolution order is: bundled → user (`~/.pi/agent/agents/`) → project (`.pi/agents/`). Project agents override user and bundled agents by name.
+Resolution order is: bundled → user (`~/.pi/agent/prompts/`) → project (`.pi/prompts/`). Project agents override user and bundled agents by name.
 
 Optional frontmatter:
 - `thinking` — default reasoning effort for the spawned pi process
 - `sessionStrategy: fork-at` — when used with `/run-agent`, clone the current active branch into a new session before running
 
-> Note: pi now supports package-shipped agents via `pi.agents` (or conventional `agents/` directories). This package publishes its bundled agents that way, while user agents in `~/.pi/agent/agents/` and project agents in `.pi/agents/` still override them by name.
-
-### Managing Agents
-
-```
-/delegate-agents              # list all agents with source
-/delegate-agents reset scout  # restore bundled version
-/delegate-agents reset --all  # restore all bundled versions
-/delegate-agents edit scout   # copy bundled to user dir for customization
-```
+> Note: pi supports package-shipped prompts via `pi.prompts` (or conventional `prompts/` directories). This package publishes its bundled agent prompts that way, while user prompts in `~/.pi/agent/prompts/` and project prompts in `.pi/prompts/` still override them by name.
 
 ## Bundled Resources
 

package/docs/plans/01_structured-handoffs-and-synthesis.plan.md

@@ -39,12 +39,12 @@ Current relevant file tree on disk:
 - `packages/subagent/extensions/subagent/agent-result-utils.ts`
 - `packages/subagent/extensions/subagent/run-agent-args.ts`
 - `packages/subagent/extensions/subagent/synthesis.ts`
-- `packages/subagent/agents/docs-scout.md`
-- `packages/subagent/agents/planner.md`
-- `packages/subagent/agents/reviewer.md`
-- `packages/subagent/agents/scout.md`
-- `packages/subagent/agents/ux-designer.md`
-- `packages/subagent/agents/worker.md`
+- `packages/subagent/prompts/docs-scout.md`
+- `packages/subagent/prompts/planner.md`
+- `packages/subagent/prompts/reviewer.md`
+- `packages/subagent/prompts/scout.md`
+- `packages/subagent/prompts/ux-designer.md`
+- `packages/subagent/prompts/worker.md`
 - `packages/subagent/prompts/implement.md`
 - `packages/subagent/prompts/implement-and-review.md`
 - `packages/subagent/prompts/scout-and-plan.md`
@@ -326,10 +326,10 @@ export function buildHandoffFromResult(input: {
 ## 3. Tighten bundled prompts so handoffs have stable sections to summarize
 
 ### Files
-- Modify `packages/subagent/agents/scout.md`
-- Modify `packages/subagent/agents/docs-scout.md`
-- Modify `packages/subagent/agents/planner.md`
-- Modify `packages/subagent/agents/worker.md`
+- Modify `packages/subagent/prompts/scout.md`
+- Modify `packages/subagent/prompts/docs-scout.md`
+- Modify `packages/subagent/prompts/planner.md`
+- Modify `packages/subagent/prompts/worker.md`
 - Modify `packages/subagent/prompts/implement.md`
 - Modify `packages/subagent/prompts/scout-and-plan.md`
 
@@ -352,10 +352,10 @@ export function buildHandoffFromResult(input: {
 # Files to modify
 
 - `packages/subagent/extensions/subagent/index.ts` — switch chain substitution from raw final text to rendered structured handoff
-- `packages/subagent/agents/scout.md` — make scout output easier to summarize deterministically
-- `packages/subagent/agents/docs-scout.md` — make docs handoff more consistent
-- `packages/subagent/agents/planner.md` — preserve plan structure but expose constraints explicitly
-- `packages/subagent/agents/worker.md` — add explicit decision / unresolved sections for downstream agents
+- `packages/subagent/prompts/scout.md` — make scout output easier to summarize deterministically
+- `packages/subagent/prompts/docs-scout.md` — make docs handoff more consistent
+- `packages/subagent/prompts/planner.md` — preserve plan structure but expose constraints explicitly
+- `packages/subagent/prompts/worker.md` — add explicit decision / unresolved sections for downstream agents
 - `packages/subagent/prompts/implement.md` — document structured `{previous}` expectations
 - `packages/subagent/prompts/scout-and-plan.md` — document structured `{previous}` expectations
 

package/docs/plans/02_clean-context-review-loop.plan.md

@@ -28,8 +28,8 @@ Improve the bundled review loop so the reviewer reasons from a fresh, diff-first
 
 Current relevant file tree on disk:
 
-- `packages/subagent/agents/reviewer.md`
-- `packages/subagent/agents/worker.md`
+- `packages/subagent/prompts/reviewer.md`
+- `packages/subagent/prompts/worker.md`
 - `packages/subagent/prompts/implement-and-review.md`
 - `packages/subagent/skills/spawn-subagents/SKILL.md`
 - `packages/subagent/extensions/subagent/index.ts`
@@ -43,10 +43,10 @@ Actual current behavior on disk:
   3. run `worker` again to apply review feedback from `{previous}`
 - Chain execution in `packages/subagent/extensions/subagent/index.ts:658-716` performs raw `{previous}` replacement with the previous step’s final assistant text. There is no review-specific minimization layer in code today.
 - The current reviewer prompt already points in the right direction:
-  - `packages/subagent/agents/reviewer.md:12-18` restricts bash to read-only commands and tells the agent to start with `git diff`, then read modified files.
+  - `packages/subagent/prompts/reviewer.md:12-18` restricts bash to read-only commands and tells the agent to start with `git diff`, then read modified files.
   - But the prompt does **not** explicitly tell the reviewer to distrust or deprioritize the worker’s implementation narrative when that narrative is also passed through `{previous}`.
 - The current worker prompt includes a helpful but minimal handoff hint:
-  - `packages/subagent/agents/worker.md:13-26` asks for `Completed`, `Files Changed`, and `Notes`, and says that if handing off to another agent it should include exact file paths changed and key functions/types touched.
+  - `packages/subagent/prompts/worker.md:13-26` asks for `Completed`, `Files Changed`, and `Notes`, and says that if handing off to another agent it should include exact file paths changed and key functions/types touched.
   - There is no required section for validation run, constraints, or unresolved risk, so the review handoff is underspecified.
 - The `spawn-subagents` skill currently recommends a `reviewer` loop after implementation and says the main agent may apply fixes directly or send a focused follow-up to `worker` (`packages/subagent/skills/spawn-subagents/SKILL.md:44-58`). It does not yet describe “clean context” review explicitly.
 - There is no additional workflow prompt for “clean review”; the current `/implement-and-review` prompt is the only bundled implementation review loop.
@@ -55,7 +55,7 @@ Actual current behavior on disk:
 
 ## Existing reviewer and worker contracts
 
-From `packages/subagent/agents/reviewer.md`:
+From `packages/subagent/prompts/reviewer.md`:
 
 ```md
 Strategy:
@@ -80,7 +80,7 @@ Output format:
 Overall assessment in 2-3 sentences.
 ```
 
-From `packages/subagent/agents/worker.md`:
+From `packages/subagent/prompts/worker.md`:
 
 ```md
 Output format when finished:
@@ -126,7 +126,7 @@ This means the review workflow can be improved significantly even with prompt-on
 ## 1. Tighten the reviewer prompt so review starts from `git diff` and re-discovered code context
 
 ### Files
-- Modify `packages/subagent/agents/reviewer.md`
+- Modify `packages/subagent/prompts/reviewer.md`
 
 ### What to change
 - Keep the reviewer read-only.
@@ -149,7 +149,7 @@ This means the review workflow can be improved significantly even with prompt-on
 ## 2. Change the worker output contract so implementation handoff becomes a compact review packet
 
 ### Files
-- Modify `packages/subagent/agents/worker.md`
+- Modify `packages/subagent/prompts/worker.md`
 
 ### What to change
 - Keep the worker autonomous and implementation-focused.
@@ -217,8 +217,8 @@ This means the review workflow can be improved significantly even with prompt-on
 
 # Files to modify
 
-- `packages/subagent/agents/reviewer.md` — make clean-context review an explicit prompt rule
-- `packages/subagent/agents/worker.md` — emit a compact review packet instead of only freeform notes
+- `packages/subagent/prompts/reviewer.md` — make clean-context review an explicit prompt rule
+- `packages/subagent/prompts/worker.md` — emit a compact review packet instead of only freeform notes
 - `packages/subagent/prompts/implement-and-review.md` — encode diff-first review semantics in the bundled workflow
 
 # Testing notes
@@ -233,8 +233,8 @@ This means the review workflow can be improved significantly even with prompt-on
 
 # Patterns to follow
 
-- `packages/subagent/agents/reviewer.md:12-18` — existing diff-first reviewer stance to strengthen, not replace
-- `packages/subagent/agents/worker.md:24-26` — current handoff hints to make mandatory and more compact
+- `packages/subagent/prompts/reviewer.md:12-18` — existing diff-first reviewer stance to strengthen, not replace
+- `packages/subagent/prompts/worker.md:24-26` — current handoff hints to make mandatory and more compact
 - `packages/subagent/prompts/implement-and-review.md:4-10` — current workflow entry point to refine
 - `packages/subagent/skills/spawn-subagents/SKILL.md:44-58` — current review-loop guidance
 - `packages/subagent/skills/write-an-agent/SKILL.md:15-20` and `:62-67` — keep prompt files sharp, minimal, and output-contract-driven

package/docs/plans/03_parallel-recon-single-writer-docs.plan.md

@@ -33,10 +33,10 @@ Current relevant file tree on disk:
 - `packages/subagent/prompts/implement.md`
 - `packages/subagent/prompts/scout-and-plan.md`
 - `packages/subagent/prompts/implement-and-review.md`
-- `packages/subagent/agents/scout.md`
-- `packages/subagent/agents/planner.md`
-- `packages/subagent/agents/reviewer.md`
-- `packages/subagent/agents/worker.md`
+- `packages/subagent/prompts/scout.md`
+- `packages/subagent/prompts/planner.md`
+- `packages/subagent/prompts/reviewer.md`
+- `packages/subagent/prompts/worker.md`
 - `packages/subagent/package.json`
 - `packages/subagent/CHANGELOG.md`
 

package/docs/plans/04_manager-workflow.plan.md

@@ -28,11 +28,11 @@ Introduce a first-class manager workflow that can decompose larger tasks into bo
 
 Current relevant file tree on disk:
 
-- `packages/subagent/agents/scout.md`
-- `packages/subagent/agents/docs-scout.md`
-- `packages/subagent/agents/planner.md`
-- `packages/subagent/agents/worker.md`
-- `packages/subagent/agents/reviewer.md`
+- `packages/subagent/prompts/scout.md`
+- `packages/subagent/prompts/docs-scout.md`
+- `packages/subagent/prompts/planner.md`
+- `packages/subagent/prompts/worker.md`
+- `packages/subagent/prompts/reviewer.md`
 - `packages/subagent/prompts/implement.md`
 - `packages/subagent/prompts/scout-and-plan.md`
 - `packages/subagent/prompts/implement-and-review.md`
@@ -65,7 +65,7 @@ Actual current state on disk:
   - `runSingleAgent()` in `index.ts:325-328` only passes `--tools` when the agent frontmatter declares a tool list.
   - `runAgent()` in `agent-runner.ts:73-76` behaves the same way.
   - This means a new `manager` agent can omit `tools:` in frontmatter if it needs access to the full tool set, including the `subagent` tool itself.
-- There is no project-local `.pi/agents/*.md` manager override in this repo right now; `.pi/agents/` exists but is empty.
+- There is no project-local `.pi/prompts/*.md` manager override in this repo right now; `.pi/prompts/` exists but is empty.
 
 # API inventory
 
@@ -154,7 +154,7 @@ Create a prompt contract that is directly usable by the main agent or a human:
 ## 1. Add a bundled `manager` agent with a narrow orchestration role
 
 ### Files
-- Create `packages/subagent/agents/manager.md`
+- Create `packages/subagent/prompts/manager.md`
 
 ### What to add
 Author a concise bundled agent prompt that:
@@ -221,7 +221,7 @@ The manager should:
 
 # Files to create
 
-- `packages/subagent/agents/manager.md`
+- `packages/subagent/prompts/manager.md`
 - `packages/subagent/prompts/manage.md`
 
 # Files to modify
@@ -243,6 +243,6 @@ The manager should:
 
 - `packages/subagent/skills/spawn-subagents/SKILL.md:31-58` — existing orchestration philosophy to extend upward
 - `packages/subagent/skills/write-an-agent/SKILL.md:15-20` and `:46-67` — agent-authoring constraints for concise, high-signal prompts
-- `packages/subagent/agents/planner.md:9-38` — good example of a narrow role with a clear output contract
-- `packages/subagent/agents/worker.md:9-26` — example of a task-focused executor the manager should call, not replace
+- `packages/subagent/prompts/planner.md:9-38` — good example of a narrow role with a clear output contract
+- `packages/subagent/prompts/worker.md:9-26` — example of a task-focused executor the manager should call, not replace
 - `packages/subagent/README.md:88-124` — bundled-agent and bundled-prompt sections to update

package/docs/plans/05_advisor-routing.plan.md

@@ -28,10 +28,10 @@ Introduce a lightweight advisor pattern so primary agents can consult a strong s
 
 Current relevant file tree on disk:
 
-- `packages/subagent/agents/planner.md`
-- `packages/subagent/agents/reviewer.md`
-- `packages/subagent/agents/worker.md`
-- `packages/subagent/agents/docs-scout.md`
+- `packages/subagent/prompts/planner.md`
+- `packages/subagent/prompts/reviewer.md`
+- `packages/subagent/prompts/worker.md`
+- `packages/subagent/prompts/docs-scout.md`
 - `packages/subagent/prompts/implement.md`
 - `packages/subagent/prompts/implement-and-review.md`
 - `packages/subagent/README.md`
@@ -42,12 +42,12 @@ Current relevant file tree on disk:
 
 Actual current state on disk:
 
-- There is no bundled `advisor` agent in `packages/subagent/agents/`.
+- There is no bundled `advisor` agent in `packages/subagent/prompts/`.
 - There is no advisor-oriented prompt template in `packages/subagent/prompts/`.
 - The current bundled roles are:
-  - `planner` for planning (`packages/subagent/agents/planner.md`)
-  - `worker` for implementation (`packages/subagent/agents/worker.md`)
-  - `reviewer` for verification (`packages/subagent/agents/reviewer.md`)
+  - `planner` for planning (`packages/subagent/prompts/planner.md`)
+  - `worker` for implementation (`packages/subagent/prompts/worker.md`)
+  - `reviewer` for verification (`packages/subagent/prompts/reviewer.md`)
   - plus `scout`, `docs-scout`, and `ux-designer`
 - The package runner already supports spawned agents consulting tools as needed:
   - in `packages/subagent/extensions/subagent/index.ts:325-328`, `runSingleAgent()` passes `--tools` only when frontmatter declares them
@@ -63,21 +63,21 @@ Actual current state on disk:
 
 ## Existing agent prompt contracts that may invoke advisor
 
-From `packages/subagent/agents/planner.md`:
+From `packages/subagent/prompts/planner.md`:
 
 ```md
 You are a planning specialist.
 You must NOT make any changes. Only read, analyze, and plan.
 ```
 
-From `packages/subagent/agents/worker.md`:
+From `packages/subagent/prompts/worker.md`:
 
 ```md
 You are a worker agent with full capabilities.
 Work autonomously to complete the assigned task. Use all available tools as needed.
 ```
 
-From `packages/subagent/agents/reviewer.md`:
+From `packages/subagent/prompts/reviewer.md`:
 
 ```md
 You are a senior code reviewer.
@@ -124,7 +124,7 @@ The advisor should not claim to have implemented or verified anything it did not
 ## 1. Add a bundled `advisor` agent with a focused consultative contract
 
 ### Files
-- Create `packages/subagent/agents/advisor.md`
+- Create `packages/subagent/prompts/advisor.md`
 
 ### What to add
 Create a concise bundled agent whose sole job is to provide focused second-opinion guidance.
@@ -150,9 +150,9 @@ Create a concise bundled agent whose sole job is to provide focused second-opini
 ## 2. Teach bundled prompts when to call the advisor and what context to send
 
 ### Files
-- Modify `packages/subagent/agents/worker.md`
-- Modify `packages/subagent/agents/planner.md`
-- Modify `packages/subagent/agents/reviewer.md`
+- Modify `packages/subagent/prompts/worker.md`
+- Modify `packages/subagent/prompts/planner.md`
+- Modify `packages/subagent/prompts/reviewer.md`
 
 ### What to change
 Add small, explicit escalation rules to the existing bundled roles.
@@ -215,14 +215,14 @@ The advisor should:
 
 # Files to create
 
-- `packages/subagent/agents/advisor.md`
+- `packages/subagent/prompts/advisor.md`
 - `packages/subagent/prompts/consult-advisor.md`
 
 # Files to modify
 
-- `packages/subagent/agents/worker.md` — add narrow escalation guidance
-- `packages/subagent/agents/planner.md` — add narrow escalation guidance
-- `packages/subagent/agents/reviewer.md` — add narrow escalation guidance
+- `packages/subagent/prompts/worker.md` — add narrow escalation guidance
+- `packages/subagent/prompts/planner.md` — add narrow escalation guidance
+- `packages/subagent/prompts/reviewer.md` — add narrow escalation guidance
 - `packages/subagent/README.md` — document the new advisor role and one or two examples
 - `packages/subagent/skills/spawn-subagents/SKILL.md` — explain when to use advisor vs. planner/reviewer
 
@@ -238,7 +238,7 @@ The advisor should:
 # Patterns to follow
 
 - `packages/subagent/skills/write-an-agent/SKILL.md:15-20` and `:46-67` — keep the new agent narrow, concise, and output-contract-driven
-- `packages/subagent/agents/planner.md:9-38` — example of a specialist planner role that the advisor should complement, not replace
-- `packages/subagent/agents/reviewer.md:10-37` — example of a verifier role that may occasionally need escalation
-- `packages/subagent/agents/worker.md:9-26` — example of a primary owner role that should remain in charge after consulting advisor
+- `packages/subagent/prompts/planner.md:9-38` — example of a specialist planner role that the advisor should complement, not replace
+- `packages/subagent/prompts/reviewer.md:10-37` — example of a verifier role that may occasionally need escalation
+- `packages/subagent/prompts/worker.md:9-26` — example of a primary owner role that should remain in charge after consulting advisor
 - `packages/subagent/skills/spawn-subagents/SKILL.md:23-58` — existing specialist-selection guidance to extend with optional escalation

package/extensions/subagent/agent-runner-types.ts

@@ -1,4 +1,4 @@
-import type { Message } from '@mariozechner/pi-ai';
+import type { Message } from '@earendil-works/pi-ai';
 
 export interface UsageStats {
   input: number;

package/extensions/subagent/agent-runner.ts

@@ -1,42 +1,7 @@
-import { spawn } from 'node:child_process';
-import * as fs from 'node:fs';
-import * as os from 'node:os';
-import * as path from 'node:path';
-import { withFileMutationQueue } from '@mariozechner/pi-coding-agent';
-import type { ResolvedPaths } from '@mariozechner/pi-coding-agent';
-import type { Message } from '@mariozechner/pi-ai';
-import { discoverAgentsWithPackages, type AgentScope } from './agents.js';
-import type { AgentResult, UsageStats } from './agent-runner-types.js';
-
-function emptyUsage(): UsageStats {
-  return { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, cost: 0, contextTokens: 0, turns: 0 };
-}
-
-function getPiInvocation(args: string[]): { command: string; args: string[] } {
-  const currentScript = process.argv[1];
-  if (currentScript && fs.existsSync(currentScript)) {
-    return { command: process.execPath, args: [currentScript, ...args] };
-  }
-
-  const execName = path.basename(process.execPath).toLowerCase();
-  const isGenericRuntime = /^(node|bun)(\.exe)?$/.test(execName);
-  if (!isGenericRuntime) return { command: process.execPath, args };
-
-  return { command: 'pi', args };
-}
-
-async function writePromptToTempFile(
-  agentName: string,
-  prompt: string,
-): Promise<{ dir: string; filePath: string }> {
-  const tmpDir = await fs.promises.mkdtemp(path.join(os.tmpdir(), 'pi-subagent-'));
-  const safeName = agentName.replace(/[^\w.-]+/g, '_');
-  const filePath = path.join(tmpDir, `prompt-${safeName}.md`);
-  await withFileMutationQueue(filePath, async () => {
-    await fs.promises.writeFile(filePath, prompt, { encoding: 'utf-8', mode: 0o600 });
-  });
-  return { dir: tmpDir, filePath };
-}
+import type { ResolvedPaths } from '@earendil-works/pi-coding-agent';
+import { discoverAgents, type AgentScope } from './agents.js';
+import type { AgentResult } from './agent-runner-types.js';
+import { emptyUsage, spawnPiAgent } from './spawn-utils.js';
 
 export type OnPhaseUpdate = (phaseName: string, agentName: string, result: AgentResult) => void;
 
@@ -57,7 +22,7 @@ export async function runAgent(
   task: string,
   options: RunAgentOptions = {},
 ): Promise<AgentResult> {
-  const { agents } = discoverAgentsWithPackages(cwd, options.agentScope ?? 'user', options.resolvedPaths);
+  const { agents } = discoverAgents(cwd, options.agentScope ?? 'user', options.resolvedPaths);
   const agent = agents.find((a) => a.name === agentName);
 
   if (!agent) {
@@ -75,14 +40,6 @@ export async function runAgent(
   const selectedModel = options.model ?? agent.model;
   const selectedThinking = options.thinking ?? agent.thinking;
 
-  const args: string[] = ['--mode', 'json', '-p', '--no-session'];
-  if (selectedModel) args.push('--model', selectedModel);
-  if (selectedThinking) args.push('--thinking', selectedThinking);
-  if (agent.tools && agent.tools.length > 0) args.push('--tools', agent.tools.join(','));
-
-  let tmpPromptDir: string | null = null;
-  let tmpPromptPath: string | null = null;
-
   const result: AgentResult = {
     agent: agentName,
     task,
@@ -93,110 +50,41 @@ export async function runAgent(
     model: selectedModel,
   };
 
-  try {
-    if (agent.systemPrompt.trim()) {
-      const tmp = await writePromptToTempFile(agent.name, agent.systemPrompt);
-      tmpPromptDir = tmp.dir;
-      tmpPromptPath = tmp.filePath;
-      args.push('--append-system-prompt', tmpPromptPath);
-    }
-
-    args.push(`Task: ${task}`);
-
-    const exitCode = await new Promise<number>((resolve) => {
-      const invocation = getPiInvocation(args);
-      const proc = spawn(invocation.command, invocation.args, {
-        cwd: options.cwd ?? cwd,
-        shell: false,
-        stdio: ['ignore', 'pipe', 'pipe'],
-      });
-
-      let buffer = '';
-
-      const processLine = (line: string) => {
-        if (!line.trim()) return;
-        let event: any;
-        try {
-          event = JSON.parse(line);
-        } catch {
-          return;
-        }
-
-        if (event.type === 'message_end' && event.message) {
-          const msg = event.message as Message;
-          result.messages.push(msg);
-
-          if (msg.role === 'assistant') {
-            result.usage.turns++;
-            const usage = msg.usage;
-            if (usage) {
-              result.usage.input += usage.input || 0;
-              result.usage.output += usage.output || 0;
-              result.usage.cacheRead += usage.cacheRead || 0;
-              result.usage.cacheWrite += usage.cacheWrite || 0;
-              result.usage.cost += usage.cost?.total || 0;
-              result.usage.contextTokens = usage.totalTokens || 0;
-            }
-            if (!result.model && msg.model) result.model = msg.model;
-            if (msg.stopReason) result.stopReason = msg.stopReason;
-            if (msg.errorMessage) result.errorMessage = msg.errorMessage;
-          }
-
-          if (options.onUpdate)
-            options.onUpdate(options.phaseName ?? 'unknown', agentName, { ...result });
-        }
-
-        if (event.type === 'tool_result_end' && event.message) {
-          result.messages.push(event.message as Message);
-          if (options.onUpdate)
-            options.onUpdate(options.phaseName ?? 'unknown', agentName, { ...result });
-        }
-      };
-
-      proc.stdout.on('data', (data: Buffer) => {
-        buffer += data.toString();
-        const lines = buffer.split('\n');
-        buffer = lines.pop() || '';
-        for (const line of lines) processLine(line);
-      });
-
-      proc.stderr.on('data', (data: Buffer) => {
-        result.stderr += data.toString();
-      });
-
-      proc.on('close', (code: number | null) => {
-        if (buffer.trim()) processLine(buffer);
-        resolve(code ?? 0);
-      });
-
-      proc.on('error', () => resolve(1));
-
-      if (options.signal) {
-        const killProc = () => {
-          proc.kill('SIGTERM');
-          setTimeout(() => {
-            if (!proc.killed) proc.kill('SIGKILL');
-          }, 5000);
-        };
-        if (options.signal.aborted) killProc();
-        else options.signal.addEventListener('abort', killProc, { once: true });
-      }
-    });
-
-    result.exitCode = exitCode;
-    return result;
-  } finally {
-    if (tmpPromptPath)
-      try {
-        fs.unlinkSync(tmpPromptPath);
-      } catch {
-        /* ignore */
+  const spawnResult = await spawnPiAgent({
+    cwd: options.cwd ?? cwd,
+    agentName: agent.name,
+    task,
+    systemPrompt: agent.systemPrompt,
+    model: selectedModel,
+    thinking: selectedThinking,
+    tools: agent.tools,
+    signal: options.signal,
+    onMessage: () => {
+      // Copy accumulated state for the phase update callback
+      if (options.onUpdate) {
+        result.messages = spawnResult.messages;
+        result.usage = spawnResult.usage;
+        result.model = spawnResult.model ?? result.model;
+        result.stopReason = spawnResult.stopReason;
+        result.errorMessage = spawnResult.errorMessage;
+        options.onUpdate(options.phaseName ?? 'unknown', agentName, { ...result });
       }
-    if (tmpPromptDir)
-      try {
-        fs.rmdirSync(tmpPromptDir);
-      } catch {
-        /* ignore */
+    },
+    onToolResult: () => {
+      if (options.onUpdate) {
+        result.messages = spawnResult.messages;
+        options.onUpdate(options.phaseName ?? 'unknown', agentName, { ...result });
       }
-  }
+    },
+  });
+
+  result.exitCode = spawnResult.exitCode;
+  result.messages = spawnResult.messages;
+  result.stderr = spawnResult.stderr;
+  result.usage = spawnResult.usage;
+  result.model = spawnResult.model ?? result.model;
+  result.stopReason = spawnResult.stopReason;
+  result.errorMessage = spawnResult.errorMessage;
+
+  return result;
 }