Fix PET timeout telemetry attribution (#1695)

## Summary

Correct PET/setup telemetry so timeout investigations retain numeric
context and reliable binary attribution.

- send refresh, configure, and restart counts through telemetry
measurements
- classify PET JSON-RPC timeouts by method and preserve refresh failure
context
- retain partial locator timing on failed refreshes
- retry transient PET `info` timeouts while retaining metadata only for
an unchanged binary
- derive Conda counts from the caller-owned enum identity
- regression-test setup stage duration, timeout categories, refresh
measures, retry bounds, and binary attribution

## Validation

- `npm run lint`
- `npm run compile-tests`
- `npm run unittest` (1504 passing, 5 pending)
- `npm run compile`

Fixes microsoft/python-environment-tools#478

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Author: karthiknadig

src/common/telemetry/constants.ts

@@ -601,27 +601,10 @@ export interface IEventNamePropertyMapping {
             "<duration>": { "classification": "SystemMetaData", "purpose": "FeatureInsight", "isMeasurement": true, "owner": "eleanorjboyd" }
         }
     */
+    // Numeric fields declared in the GDPR block are sent through the measurements payload.
     [EventNames.PET_REFRESH]: {
         result: 'success' | 'timeout' | 'error';
-        envCount?: number;
-        /** Number of discovered environments whose kind is Conda. Lets us slice refresh duration by conda footprint. */
-        condaEnvCount?: number;
-        /** Number of discovered environment managers (conda/pyenv/poetry/etc.). */
-        managerCount?: number;
-        unresolvedCount?: number;
-        workspaceDirCount?: number;
-        searchPathCount?: number;
-        attempt: number;
         errorType?: string;
-        // breakdown* fields go through the measures payload (numeric); listed here for GDPR only.
-        /** ms in the Locators phase. */
-        breakdownLocators?: number;
-        /** ms walking PATH env var entries (not a file path). */
-        breakdownPathEnv?: number;
-        /** ms scanning global virtual-env dirs. */
-        breakdownGlobalVirtualEnvs?: number;
-        /** ms scanning workspace dirs. */
-        breakdownWorkspaces?: number;
         /** JSON-serialized Record<locatorName, ms>. Parse with parse_json() in Kusto. */
         locatorsJson?: string;
         /** PET crate version reported by the `info` RPC. 'unknown' if the call failed or the PET binary doesn't implement it. */
@@ -638,14 +621,14 @@ export interface IEventNamePropertyMapping {
             "workspaceDirCount": { "classification": "SystemMetaData", "purpose": "FeatureInsight", "isMeasurement": true, "owner": "eleanorjboyd" },
             "envDirCount": { "classification": "SystemMetaData", "purpose": "FeatureInsight", "isMeasurement": true, "owner": "eleanorjboyd" },
             "retryCount": { "classification": "SystemMetaData", "purpose": "FeatureInsight", "isMeasurement": true, "owner": "eleanorjboyd" },
+            "errorType": { "classification": "SystemMetaData", "purpose": "FeatureInsight", "owner": "eleanorjboyd" },
             "<duration>": { "classification": "SystemMetaData", "purpose": "FeatureInsight", "isMeasurement": true, "owner": "eleanorjboyd" }
         }
     */
+    // Numeric fields declared in the GDPR block are sent through the measurements payload.
     [EventNames.PET_CONFIGURE]: {
         result: 'success' | 'timeout' | 'error' | 'skipped';
-        workspaceDirCount?: number;
-        envDirCount?: number;
-        retryCount: number;
+        errorType?: string;
     };
 
     /* __GDPR__
@@ -660,8 +643,8 @@ export interface IEventNamePropertyMapping {
             "<duration>": { "classification": "SystemMetaData", "purpose": "FeatureInsight", "isMeasurement": true, "owner": "eleanorjboyd" }
         }
     */
+    // `attempt` is declared in the GDPR block and sent through the measurements payload.
     [EventNames.PET_PROCESS_RESTART]: {
-        attempt: number;
         result: 'success' | 'error';
         errorType?: string;
         /**

src/common/telemetry/errorClassifier.ts

@@ -13,10 +13,20 @@ export type DiscoveryErrorType =
     | 'command_failed'
     | 'connection_error'
     | 'rpc_error'
+    | 'rpc_timeout'
+    | 'rpc_configure_timeout'
+    | 'rpc_refresh_timeout'
+    | 'rpc_resolve_timeout'
     | 'process_crash'
     | 'already_registered'
     | 'unknown';
 
+/** Returns true for spawn and JSON-RPC timeout telemetry categories. */
+export function isTimeoutErrorType(errorType: DiscoveryErrorType): boolean {
+    return errorType === 'spawn_timeout' || errorType === 'rpc_timeout' ||
+        (errorType.startsWith('rpc_') && errorType.endsWith('_timeout'));
+}
+
 /**
  * Classifies an error into a telemetry-safe category for the `errorType` property.
  * Does NOT include raw error messages — only the category.
@@ -27,7 +37,16 @@ export function classifyError(ex: unknown): DiscoveryErrorType {
     }
 
     if (ex instanceof RpcTimeoutError) {
-        return 'spawn_timeout';
+        switch (ex.method) {
+            case 'configure':
+                return 'rpc_configure_timeout';
+            case 'refresh':
+                return 'rpc_refresh_timeout';
+            case 'resolve':
+                return 'rpc_resolve_timeout';
+            default:
+                return 'rpc_timeout';
+        }
     }
 
     // JSON-RPC connection errors (e.g., PET process died mid-request, connection closed/disposed)

src/internal.api.ts

@@ -34,7 +34,7 @@ import { CreateEnvironmentNotSupported, RemoveEnvironmentNotSupported } from './
 import { traceWarn } from './common/logging';
 import { StopWatch } from './common/stopWatch';
 import { EventNames } from './common/telemetry/constants';
-import { classifyError } from './common/telemetry/errorClassifier';
+import { classifyError, isTimeoutErrorType } from './common/telemetry/errorClassifier';
 import { sendTelemetryEvent } from './common/telemetry/sender';
 
 export type EnvironmentManagerScope = undefined | string | Uri | PythonEnvironment;
@@ -242,7 +242,7 @@ export class InternalEnvironmentManager implements EnvironmentManager {
                 duration,
                 {
                     managerId: this.id,
-                    result: errorType === 'canceled' || errorType === 'spawn_timeout' ? 'timeout' : 'error',
+                    result: errorType === 'canceled' || isTimeoutErrorType(errorType) ? 'timeout' : 'error',
                     errorType,
                 },
                 ex instanceof Error ? ex : undefined,