refactor(worker): rename claude-executor to pi-executor

apps/worker/src/services/agent-execution.ts

@@ -12,7 +12,7 @@
  * - Load prompt template using AGENTS[agentName].promptTemplate
  * - Create git checkpoint
  * - Start audit logging
- * - Invoke Claude SDK via runClaudePrompt
+ * - Invoke the pi agent via runPiPrompt
  * - Spending cap check using isSpendingCapBehavior
  * - Handle failure (rollback, audit)
  * - Validate output using AGENTS[agentName].deliverableFilename
@@ -22,7 +22,7 @@
  */
 
 import { fs, path } from 'zx';
-import { type ClaudePromptResult, runClaudePrompt, validateAgentOutput } from '../ai/claude-executor.js';
+import { type PiPromptResult, runPiPrompt, validateAgentOutput } from '../ai/pi-executor.js';
 import { createQueueSubmitTool, getQueueFilename } from '../ai/queue-schemas.js';
 import type { AuditSession } from '../audit/index.js';
 import { authStateFile } from '../audit/utils.js';
@@ -59,7 +59,7 @@ export interface AgentExecutionInput {
 
 interface FailAgentOpts {
   attemptNumber: number;
-  result: ClaudePromptResult;
+  result: PiPromptResult;
   rollbackReason: string;
   errorMessage: string;
   errorCode: ErrorCode;
@@ -167,7 +167,7 @@ export class AgentExecutionService {
     //    exploitation queue (pi has no JSON-schema output format).
     const submitTool = createQueueSubmitTool(agentName, distributedConfig?.exploit ?? true);
     const callerTools = [...(customTools ?? []), ...(submitTool ? [submitTool.tool] : [])];
-    const result: ClaudePromptResult = await runClaudePrompt(
+    const result: PiPromptResult = await runPiPrompt(
       prompt,
       repoPath,
       '', // context
@@ -309,7 +309,7 @@ export class AgentExecutionService {
   /**
    * Convert AgentEndResult to AgentMetrics for workflow state.
    */
-  static toMetrics(endResult: AgentEndResult, result: ClaudePromptResult): AgentMetrics {
+  static toMetrics(endResult: AgentEndResult, result: PiPromptResult): AgentMetrics {
     return {
       durationMs: endResult.duration_ms,
       inputTokens: null, // Not currently exposed by SDK wrapper

apps/worker/src/services/error-handling.ts

@@ -62,7 +62,7 @@ const RETRYABLE_PATTERNS = [
   'internal server error',
   'service unavailable',
   'bad gateway',
-  // Claude API errors
+  // Provider API errors
   'model unavailable',
   'service temporarily unavailable',
   'api error',

apps/worker/src/services/index.ts

@@ -11,8 +11,8 @@
  * Services are pure domain logic with no Temporal dependencies.
  */
 
-export type { ClaudePromptResult } from '../ai/claude-executor.js';
-export { runClaudePrompt } from '../ai/claude-executor.js';
+export type { PiPromptResult } from '../ai/pi-executor.js';
+export { runPiPrompt } from '../ai/pi-executor.js';
 export type { AgentExecutionInput } from './agent-execution.js';
 export { AgentExecutionService } from './agent-execution.js';
 export { ConfigLoaderService } from './config-loader.js';

apps/worker/src/services/preflight.ts

@@ -350,7 +350,7 @@ async function probeCredentialsWithPi(authType: string, baseUrl?: string): Promi
   return ok(undefined);
 }
 
-/** Validate credentials via a minimal Claude Agent SDK query. */
+/** Validate credentials via a minimal pi session. */
 async function validateCredentials(
   logger: ActivityLogger,
   apiKey?: string,

apps/worker/src/services/validate-authentication.ts

@@ -15,7 +15,7 @@
 import { readFile, rm } from 'node:fs/promises';
 import { defineTool, type ToolDefinition } from '@earendil-works/pi-coding-agent';
 import { Type } from 'typebox';
-import { runClaudePrompt } from '../ai/claude-executor.js';
+import { runPiPrompt } from '../ai/pi-executor.js';
 import type { AuditSession } from '../audit/index.js';
 import { authStateFile } from '../audit/utils.js';
 import type { ActivityLogger } from '../types/activity-logger.js';
@@ -123,7 +123,7 @@ export async function validateAuthentication(input: ValidateAuthInput): Promise<
   const startTime = Date.now();
 
   const submit = createAuthSubmitTool();
-  const result = await runClaudePrompt(
+  const result = await runPiPrompt(
     prompt,
     repoPath,
     '',
@@ -219,7 +219,7 @@ function countStorageEntries(parsed: unknown, key: 'cookies' | 'origins'): numbe
 }
 
 function classifyResult(
-  result: import('../ai/claude-executor.js').ClaudePromptResult,
+  result: import('../ai/pi-executor.js').PiPromptResult,
   authentication: NonNullable<DistributedConfig['authentication']>,
 ): Result<void, PentestError> {
   if (!result.success) {