[pull] main from microsoft:main

cli/src/commands/serve_web.rs

@@ -348,7 +348,9 @@ async fn forward_ws_req_to_server(
 			Err(e) => return response::connection_err(e),
 		};
 
-	tokio::spawn(connection);
+	// `.with_upgrades()` is required so that `hyper::upgrade::on` can later
+	// take over the connection for websocket traffic.
+	tokio::spawn(connection.with_upgrades());
 
 	let mut proxied_req = Request::builder().uri(req.uri());
 	for (k, v) in req.headers() {

extensions/copilot/package.json

@@ -1162,8 +1162,7 @@
 				"displayName": "Memory",
 				"toolReferenceName": "memory",
 				"userDescription": "Manage persistent memory across conversations",
-				"when": "config.github.copilot.chat.tools.memory.enabled",
-				"modelDescription": "Manage a persistent memory system with three scopes for storing notes and information across conversations.\n\nMemory is organized under /memories/ with three tiers:\n- `/memories/` — User memory: persistent notes that survive across all workspaces and conversations. Store preferences, patterns, and general insights here.\n- `/memories/session/` — Session memory: notes scoped to the current conversation. Store task-specific context and in-progress notes here. Cleared after the conversation ends.\n- `/memories/repo/` — Repository memory: repository-scoped facts stored via Copilot. Only the `create` command is supported for this path.\n\nIMPORTANT: Before creating new memory files, first view the /memories/ directory to understand what already exists. This helps avoid duplicates and maintain organized notes.\n\nCommands:\n- `view`: View contents of a file or list directory contents. Can be used on files or directories (e.g., \"/memories/\" to see all top-level items).\n- `create`: Create a new file at the specified path with the given content. Fails if the file already exists.\n- `str_replace`: Replace an exact string in a file with a new string. The old_str must appear exactly once in the file.\n- `insert`: Insert text at a specific line number in a file. Line 0 inserts at the beginning.\n- `delete`: Delete a file or directory (and all its contents).\n- `rename`: Rename or move a file or directory from path to new_path. Cannot rename across scopes.",
+				"modelDescription": "Manage a persistent memory system with three scopes for storing notes and information across conversations.\n\nMemory is organized under /memories/ with three tiers:\n- `/memories/` — User memory: persistent notes that survive across all workspaces and conversations. Store preferences, patterns, and general insights here.\n- `/memories/session/` — Session memory: notes scoped to the current conversation. Store task-specific context and in-progress notes here. Cleared after the conversation ends.\n- `/memories/repo/` — Repository memory: repository-scoped notes stored locally in the workspace. Store codebase conventions, build commands, project structure facts, and verified practices here.\n\nIMPORTANT: Before creating new memory files, first view the /memories/ directory to understand what already exists. This helps avoid duplicates and maintain organized notes.\n\nCommands:\n- `view`: View contents of a file or list directory contents. Can be used on files or directories (e.g., \"/memories/\" to see all top-level items).\n- `create`: Create a new file at the specified path with the given content. Fails if the file already exists.\n- `str_replace`: Replace an exact string in a file with a new string. The old_str must appear exactly once in the file.\n- `insert`: Insert text at a specific line number in a file. Line 0 inserts at the beginning.\n- `delete`: Delete a file or directory (and all its contents).\n- `rename`: Rename or move a file or directory from path to new_path. Cannot rename across scopes.",
 				"inputSchema": {
 					"type": "object",
 					"properties": {
@@ -3282,22 +3281,6 @@
 						],
 						"markdownDescription": "%github.copilot.config.codesearch.enabled%"
 					},
-					"github.copilot.chat.copilotMemory.enabled": {
-						"type": "boolean",
-						"default": false,
-						"markdownDescription": "%github.copilot.config.copilotMemory.enabled%",
-						"tags": [
-							"preview"
-						]
-					},
-					"github.copilot.chat.tools.memory.enabled": {
-						"type": "boolean",
-						"default": true,
-						"markdownDescription": "%github.copilot.config.tools.memory.enabled%",
-						"tags": [
-							"preview"
-						]
-					},
 					"github.copilot.chat.tools.viewImage.enabled": {
 						"type": "boolean",
 						"default": true,
@@ -3842,15 +3825,6 @@
 							"onExp"
 						]
 					},
-					"github.copilot.chat.responsesApi.toolSearchTool.enabled": {
-						"type": "boolean",
-						"default": false,
-						"markdownDescription": "%github.copilot.config.responsesApi.toolSearchTool.enabled%",
-						"tags": [
-							"experimental",
-							"onExp"
-						]
-					},
 					"github.copilot.chat.updated53CodexPrompt.enabled": {
 						"type": "boolean",
 						"default": true,
@@ -3905,6 +3879,24 @@
 							"onExp"
 						]
 					},
+					"github.copilot.chat.gpt55EconomicalSearchAndEdit.enabled": {
+						"type": "boolean",
+						"default": false,
+						"markdownDescription": "%github.copilot.config.gpt55EconomicalSearchAndEdit.enabled%",
+						"tags": [
+							"experimental",
+							"onExp"
+						]
+					},
+					"github.copilot.chat.gpt55LargePromptSections.enabled": {
+						"type": "boolean",
+						"default": false,
+						"markdownDescription": "%github.copilot.config.gpt55LargePromptSections.enabled%",
+						"tags": [
+							"experimental",
+							"onExp"
+						]
+					},
 					"github.copilot.chat.anthropic.tools.websearch.enabled": {
 						"type": "boolean",
 						"default": false,
@@ -5523,14 +5515,6 @@
 					"command": "github.copilot.nes.captureExpected.submit",
 					"when": "github.copilot.inlineEditsEnabled"
 				},
-				{
-					"command": "github.copilot.chat.tools.memory.showMemories",
-					"when": "config.github.copilot.chat.tools.memory.enabled"
-				},
-				{
-					"command": "github.copilot.chat.tools.memory.clearMemories",
-					"when": "config.github.copilot.chat.tools.memory.enabled"
-				},
 				{
 					"command": "github.copilot.sessions.commit",
 					"when": "false"

extensions/copilot/package.nls.json

@@ -343,13 +343,14 @@
 	"github.copilot.config.responsesApiReasoningSummary": "Sets the reasoning summary style used for the Responses API. Requires `#github.copilot.chat.useResponsesApi#`.",
 	"github.copilot.config.responsesApiContextManagement.enabled": "Enables context management for the Responses API. Requires `#github.copilot.chat.useResponsesApi#`.",
 	"github.copilot.config.responsesApi.promptCacheKey.enabled": "Enables prompt cache key being set for the Responses API.",
-	"github.copilot.config.responsesApi.toolSearchTool.enabled": "Enable tool search for OpenAI Responses API models. When enabled, tools are dynamically discovered and loaded on-demand using embeddings-based search, reducing context window usage when many tools are available.",
 	"github.copilot.config.updated53CodexPrompt.enabled": "Enables the updated prompt for gpt-5.3-codex model.",
 	"github.copilot.config.claude47OpusPrompt.enabled": "Enables the updated system prompt tuned for the Claude Opus 4.7 model.",
 	"github.copilot.config.gpt54ConcisePrompt.enabled": "Enables the concise prompt experiment for gpt-5.4 model.",
 	"github.copilot.config.gpt54LargePrompt.enabled": "Enables the large prompt experiment for gpt-5.4 model.",
 	"github.copilot.config.gpt55GetChangedFilesTool.enabled": "Enables the Get Changed Files tool for gpt-5.5 models.",
 	"github.copilot.config.gpt55ReadFileTool.enabled": "Enables the Read File tool for gpt-5.5 models.",
+	"github.copilot.config.gpt55EconomicalSearchAndEdit.enabled": "Enables economical search and edit instructions for gpt-5.5 models.",
+	"github.copilot.config.gpt55LargePromptSections.enabled": "Enables additional gpt-5.4 large prompt sections for gpt-5.5 models.",
 	"github.copilot.config.anthropic.tools.websearch.enabled": "Enable Anthropic's native web search tool for BYOK Claude models. When enabled, allows Claude to search the web for current information. \n\n**Note**: This is an experimental feature only available for BYOK Anthropic Claude models.",
 	"github.copilot.config.anthropic.tools.websearch.maxUses": "Maximum number of web searches allowed per request. Valid range is 1 to 20. Prevents excessive API calls within a single interaction. If Claude exceeds this limit, the response returns an error.",
 	"github.copilot.config.anthropic.tools.websearch.allowedDomains": "List of domains to restrict web search results to (e.g., `[\"example.com\", \"docs.example.com\"]`). Domains should not include the HTTP/HTTPS scheme. Subdomains are automatically included. Cannot be used together with `#github.copilot.chat.anthropic.tools.websearch.blockedDomains#`; configuring both will cause web search requests to fail.",
@@ -422,8 +423,6 @@
 	"github.copilot.config.cli.remote.enabled": "Enable the /remote command for Copilot CLI sessions, allowing you to view and steer from GitHub.com and the GitHub mobile app.",
 	"github.copilot.config.backgroundAgent.enabled": "Enable the Copilot CLI. When disabled, the Copilot CLI will not be available in 'Continue In' context menus.",
 	"github.copilot.config.cloudAgent.enabled": "Enable the Cloud Agent. When disabled, the Cloud Agent will not be available in 'Continue In' context menus.",
-	"github.copilot.config.copilotMemory.enabled": "Enable agentic memory for GitHub Copilot. When enabled, Copilot can store repository-scoped facts about your codebase conventions, structure, and preferences remotely on GitHub, and recall them in future conversations to provide more contextually relevant assistance. [Learn more](https://docs.github.com/en/copilot/how-tos/use-copilot-agents/copilot-memory).",
-	"github.copilot.config.tools.memory.enabled": "Enable the memory tool to let the agent save and recall notes during a conversation. Memories are stored locally in VS Code storage — user-scoped memories persist across workspaces and sessions, while session-scoped memories are cleared when the conversation ends.",
 	"github.copilot.config.gpt5AlternativePatch": "Enable GPT-5 alternative patch format.",
 	"github.copilot.config.inlineEdits.triggerOnEditorChangeAfterSeconds": "Trigger inline edits after editor has been idle for this many seconds.",
 	"github.copilot.config.inlineEdits.nextCursorPrediction.displayLine": "Display predicted cursor line for next edit suggestions.",

extensions/copilot/src/extension/byok/vscode-node/anthropicProvider.ts

@@ -12,7 +12,7 @@ import { CustomDataPartMimeTypes } from '../../../platform/endpoint/common/endpo
 import { modelSupportsToolSearch } from '../../../platform/endpoint/common/chatModelCapabilities';
 import { buildToolInputSchema } from '../../../platform/endpoint/node/messagesApi';
 import { ILogService } from '../../../platform/log/common/logService';
-import { ContextManagementResponse, CUSTOM_TOOL_SEARCH_NAME, getContextManagementFromConfig, isAnthropicContextEditingEnabled, isAnthropicMemoryToolEnabled } from '../../../platform/networking/common/anthropic';
+import { ContextManagementResponse, CUSTOM_TOOL_SEARCH_NAME, getContextManagementFromConfig, isAnthropicContextEditingEnabled, modelSupportsMemory } from '../../../platform/networking/common/anthropic';
 import { IToolDeferralService } from '../../../platform/networking/common/toolDeferralService';
 import { IResponseDelta, OpenAiFunctionTool } from '../../../platform/networking/common/fetch';
 import { APIUsage } from '../../../platform/networking/common/openai';
@@ -140,7 +140,7 @@ export class AnthropicLMProvider extends AbstractLanguageModelChatProvider {
 					},
 				});
 
-			const memoryToolEnabled = isAnthropicMemoryToolEnabled(model.id, this._configurationService, this._experimentationService);
+			const memoryToolEnabled = modelSupportsMemory(model.id);
 
 			// Requires the client-side tool_search tool in the request: without it, defer-loaded tools can't be retrieved.
 			// If the user disables tool_search in the tool picker, it won't be present here and tool search is skipped.

extensions/copilot/src/extension/chatSessions/copilotcli/node/copilotcliSession.ts

@@ -30,6 +30,7 @@ import { truncate } from '../../../../util/vs/base/common/strings';
 import { ThemeIcon } from '../../../../util/vs/base/common/themables';
 import { IInstantiationService } from '../../../../util/vs/platform/instantiation/common/instantiation';
 import { ChatResponseMarkdownPart, ChatResponseThinkingProgressPart, ChatSessionStatus, ChatToolInvocationPart, EventEmitter, MarkdownString, Uri } from '../../../../vscodeTypes';
+import { getQuotaMessageForPlan } from '../../../../platform/chat/common/commonTypes';
 import { IToolsService } from '../../../tools/common/toolsService';
 import { IChatSessionMetadataStore } from '../../common/chatSessionMetadataStore';
 import { ExternalEditTracker } from '../../common/externalEditTracker';
@@ -57,6 +58,13 @@ export type CopilotCLICommand = 'compact' | 'plan' | 'fleet' | 'remote';
  */
 export const copilotCLICommands: readonly CopilotCLICommand[] = ['compact', 'plan', 'fleet', 'remote'] as const;
 
+export class CopilotCLIQuotaExceededError extends Error {
+	constructor(message: string) {
+		super(message);
+		this.name = 'CopilotCLIQuotaExceededError';
+	}
+}
+
 /**
  * Shared Mission Control state keyed by SDK session ID.
  * CopilotCLISession instances are recreated per request, so MC state
@@ -1056,6 +1064,7 @@ export class CopilotCLISession extends DisposableStore implements ICopilotCLISes
 		const toolCalls = new Map<string, ToolCall>();
 		const editTracker = new ExternalEditTracker();
 		let sdkRequestId: string | undefined;
+		let isQuotaError = false;
 		const toolIdEditMap = new Map<string, Promise<string | undefined>>();
 		const remoteMode = isMissionControlCommandSource(input.source) ? this._mcState?.mcMode : undefined;
 		const effectivePermissionLevel = remoteMode ? (remoteMode === 'autopilot' ? 'autopilot' : undefined) : this._permissionLevel;
@@ -1406,7 +1415,12 @@ export class CopilotCLISession extends DisposableStore implements ICopilotCLISes
 			disposables.add(toDisposable(this._sdkSession.on('session.error', (event) => {
 				flushPendingInvocationMessages();
 				this.logService.error(`[CopilotCLISession]CopilotCLI error: (${event.data.errorType}), ${event.data.message}`);
-				requestStream?.markdown(l10n.t('\n\nError: ({0}) {1}', event.data.errorType, event.data.message));
+
+				if (event.data.errorType === 'quota' || event.data.statusCode === 402) {
+					isQuotaError = true;
+				} else {
+					requestStream?.markdown(l10n.t('\n\nError: ({0}) {1}', event.data.errorType, event.data.message));
+				}
 
 				const errorMarkdown = [`# Error Details`, `Type: ${event.data.errorType}`, `Message: ${event.data.message}`, `## Stack`, event.data.stack || ''].join('\n');
 				this._requestLogger.addEntry({
@@ -1460,6 +1474,15 @@ export class CopilotCLISession extends DisposableStore implements ICopilotCLISes
 			if (!token.isCancellationRequested) {
 				await this.sendRequestInternal(input, attachments, false, logStartTime);
 			}
+			if (isQuotaError) {
+				this._chatQuotaService.clearQuota();
+				let plan: string | undefined;
+				try {
+					const copilotToken = await this._authenticationService.getCopilotToken();
+					plan = copilotToken.copilotPlan;
+				} catch { /* token unavailable */ }
+				throw new CopilotCLIQuotaExceededError(getQuotaMessageForPlan(plan));
+			}
 			this.logService.trace(`[CopilotCLISession] Invoking session (completed) ${this.sessionId}`);
 			const resolvedToolIdEditMap: Record<string, string> = {};
 			await Promise.all(Array.from(toolIdEditMap.entries()).map(async ([toolId, editFilePromise]) => {
@@ -1487,18 +1510,32 @@ export class CopilotCLISession extends DisposableStore implements ICopilotCLISes
 			// Log the completed conversation
 			this._logConversation(prompt, assistantMessageChunks.join(''), modelId || '', attachments, logStartTime, 'Completed');
 		} catch (error) {
+			if (error instanceof CopilotCLIQuotaExceededError) {
+				throw error;
+			}
+			if (isQuotaError) {
+				this._chatQuotaService.clearQuota();
+				let plan: string | undefined;
+				try {
+					const copilotToken = await this._authenticationService.getCopilotToken();
+					plan = copilotToken.copilotPlan;
+				} catch { /* token unavailable */ }
+				throw new CopilotCLIQuotaExceededError(getQuotaMessageForPlan(plan));
+			}
 			this._status = ChatSessionStatus.Failed;
 			this._statusChange.fire(this._status);
 			this.logService.error(`[CopilotCLISession] Invoking session (error) ${this.sessionId}`, error);
-			requestStream?.markdown(l10n.t('\n\nError: {0}', error instanceof Error ? error.message : String(error)));
 
-			invokeAgentSpan.setStatus(SpanStatusCode.ERROR, error instanceof Error ? error.message : String(error));
+			const errorMessage = error instanceof Error ? error.message : String(error);
+			requestStream?.markdown(l10n.t('\n\nError: {0}', errorMessage));
+
+			invokeAgentSpan.setStatus(SpanStatusCode.ERROR, errorMessage);
 			if (error instanceof Error) {
 				invokeAgentSpan.recordException(error);
 			}
 
 			// Log the failed conversation
-			this._logConversation(prompt, assistantMessageChunks.join(''), modelId || '', attachments, logStartTime, 'Failed', error instanceof Error ? error.message : String(error));
+			this._logConversation(prompt, assistantMessageChunks.join(''), modelId || '', attachments, logStartTime, 'Failed', errorMessage);
 		} finally {
 			cancelCancellationAbort?.();
 			// End the invoke_agent wrapper span

extensions/copilot/src/extension/chatSessions/vscode-node/copilotCLIChatSessions.ts

@@ -43,7 +43,7 @@ import { SessionIdForCLI } from '../copilotcli/common/utils';
 import { getCopilotCLISessionDir } from '../copilotcli/node/cliHelpers';
 import { ICopilotCLIModels, ICopilotCLISDK } from '../copilotcli/node/copilotCli';
 import { CopilotCLIPromptResolver } from '../copilotcli/node/copilotcliPromptResolver';
-import { builtinSlashSCommands, CopilotCLICommand, copilotCLICommands, ICopilotCLISession } from '../copilotcli/node/copilotcliSession';
+import { builtinSlashSCommands, CopilotCLICommand, copilotCLICommands, CopilotCLIQuotaExceededError, ICopilotCLISession } from '../copilotcli/node/copilotcliSession';
 import { ICopilotCLISessionItem, ICopilotCLISessionService } from '../copilotcli/node/copilotcliSessionService';
 import { buildMcpServerMappings } from '../copilotcli/node/mcpHandler';
 import { ICopilotCLISessionTracker } from '../copilotcli/vscode-node/copilotCLISessionTracker';
@@ -885,6 +885,9 @@ export class CopilotCLIChatSessionParticipant extends Disposable {
 			if (isCancellationError(ex)) {
 				return {};
 			}
+			if (ex instanceof CopilotCLIQuotaExceededError) {
+				return { errorDetails: { message: ex.message, isQuotaExceeded: true } };
+			}
 			throw ex;
 		} finally {
 			this._chatQuotaService.resetTurnCredits(request.id);

extensions/copilot/src/extension/chatSessions/vscode-node/copilotCLIChatSessionsContribution.ts

@@ -49,7 +49,7 @@ import { IChatDelegationSummaryService } from '../copilotcli/common/delegationSu
 import { getCopilotCLISessionDir } from '../copilotcli/node/cliHelpers';
 import { COPILOT_CLI_REASONING_EFFORT_PROPERTY, ICopilotCLIAgents, ICopilotCLIModels, ICopilotCLISDK, isWelcomeView } from '../copilotcli/node/copilotCli';
 import { CopilotCLIPromptResolver } from '../copilotcli/node/copilotcliPromptResolver';
-import { builtinSlashSCommands, CopilotCLICommand, copilotCLICommands, ICopilotCLISession } from '../copilotcli/node/copilotcliSession';
+import { builtinSlashSCommands, CopilotCLICommand, copilotCLICommands, CopilotCLIQuotaExceededError, ICopilotCLISession } from '../copilotcli/node/copilotcliSession';
 import { ICopilotCLISessionItem, ICopilotCLISessionService } from '../copilotcli/node/copilotcliSessionService';
 import { buildMcpServerMappings } from '../copilotcli/node/mcpHandler';
 import { ICopilotCLISessionTracker } from '../copilotcli/vscode-node/copilotCLISessionTracker';
@@ -1578,6 +1578,9 @@ export class CopilotCLIChatSessionParticipant extends Disposable {
 			if (isCancellationError(ex)) {
 				return {};
 			}
+			if (ex instanceof CopilotCLIQuotaExceededError) {
+				return { errorDetails: { message: ex.message, isQuotaExceeded: true } };
+			}
 			throw ex;
 		}
 		finally {