@sayknow-cli/coding-agent 0.3.6 → 0.3.8

package/src/prompts/tools/ssh.md

@@ -1,7 +1,8 @@
 Runs commands on remote hosts.
 
 <instruction>
-You MUST build commands from the reference below
+You MUST build commands from the reference below.
+The local coreutils restrictions (`cat`/`grep`/`find`/`head`/`tail` bans) do NOT apply on remote hosts — `read`/`search`/`find` cannot reach them, so these shell commands are the only tools available there.
 </instruction>
 
 <commands>

package/src/prompts/tools/subagent.md

@@ -2,12 +2,12 @@ Lists, inspects, awaits, pauses, resumes, steers, or cancels detached task subag
 
 Task launches return immediately. Use this tool when you need direct control over those running subagents. Prefer `subagent` for task subagents; generic `job` remains available for non-subagent jobs and compatibility fallback access.
 
-`verbosity` controls output size: `receipt` (default) returns status metadata plus a single <=280-character result/error preview and an `agent://<id>` output ref when available; `preview` returns <=2000 characters; `full` returns <=12000 characters and requires explicit `ids`.
+`verbosity` controls output size: `receipt` (default) returns status metadata plus a single ≤280-character result/error preview and an `agent://<id>` output ref when available; `preview` returns ≤2000 characters; `full` returns ≤12000 characters and requires explicit `ids`.
 
 # Operations
 
 ## `action: "list"`
-Snapshot your visible detached subagents, including `running`, `paused`, `queued`, and terminal subagents when retained. Output is receipt-only by default; use `verbosity: "preview"` for a bounded preview or inspect explicit `ids` with `verbosity: "full"` when fuller retained text is necessary.
+Snapshot your visible detached subagents, including `running`, `paused`, `queued`, and terminal subagents when retained. Optional `limit` (1–50) caps how many subagents are returned. Output is receipt-only by default; use `verbosity: "preview"` for a bounded preview or inspect explicit `ids` with `verbosity: "full"` when fuller retained text is necessary.
 
 ## `action: "inspect"`
 Inspect selected subagents by `ids`; omit `ids` to inspect current running subagents. Terminal subagents return receipt-only output by default, with an `agent://<id>` ref when a verified output artifact is available. `verbosity: "full"` requires explicit `ids`.

package/src/prompts/tools/task.md

@@ -3,12 +3,11 @@ Launches subagents to parallelize workflows.
 - Results are delivered automatically when complete.
 - The tool result lists the assigned task ids (e.g. `0-AuthLoader`) — those are the live agent ids.
 {{#if ircEnabled}}
-- Coordinate with running tasks via `irc` using those ids. `subagent` cancel terminates a task and **cannot carry a message** — never cancel because an await timed out; cancel only when the task has actually failed, gone off-track, or become unrecoverably wrong.
-- If genuinely blocked on completion, wait with `subagent` action `await` and a timeout; timeout only bounds your wait and does not stop or fail the subagent.
+- Coordinate with running tasks via `irc` using those ids. `subagent` cancel terminates a task and **cannot carry a message**.
 {{else}}
-- If genuinely blocked on completion, wait with `subagent` action `await` and a timeout; timeout only bounds your wait and does not stop or fail the subagent.
-- Use `subagent` action `inspect` or `list` to snapshot manager state; `cancel` only when a task has actually failed, gone off-track, or become unrecoverably wrong.
+- Use `subagent` action `inspect` or `list` to snapshot manager state.
 {{/if}}
+- To wait or cancel, use the `subagent` tool; its await/cancel doctrine applies (never cancel just because an await timed out).
 
 {{#if ircEnabled}}
 Subagents have no conversation history, but they can reach you and their siblings live via the `irc` tool. Front-load every fact, file path, and direction they need in {{#if contextEnabled}}`context` or `assignment`{{else}}each `assignment`{{/if}}.
@@ -19,7 +18,7 @@ Subagents have no conversation history. Every fact, file path, and direction the
 <parameters>
 - `agent`: agent type for all tasks
 - `tasks`: tasks to execute in parallel
- - `.id`: CamelCase, ≤32 chars
+ - `.id`: filesystem-safe, ≤48 chars, matching `[A-Za-z0-9][A-Za-z0-9_-]*`; prefer CamelCase
  - `.description`: UI label only — subagent never sees it
  - `.assignment`: complete self-contained instructions; one-liners and missing acceptance criteria are PROHIBITED
 {{#if contextEnabled}}- `context`: shared background prepended to every assignment; session-specific only{{/if}}

package/src/prompts/tools/todo-write.md

@@ -12,7 +12,7 @@ Allowed `op` values are only `init`, `start`, `done`, `drop`, `rm`, `append`, an
 |`start`|`task`|Mark in progress|
 |`done`|`task` or `phase`|Mark completed|
 |`drop`|`task` or `phase`|Mark abandoned|
-|`rm`|`task` or `phase`|Remove|
+|`rm`|`task` or `phase` or *(none = clear all tasks)*|Remove a task; with `phase`, empties the phase (the phase entry remains); bare `rm` clears every task in every phase|
 |`append`|`phase`, `items: string[]`|Append tasks to `phase`; lazily creates phase|
 |`note`|`task`, `text`|Append a note to a task. Reminders for future-you only.|
 

package/src/prompts/tools/vim.md

@@ -1,6 +1,7 @@
 Vim-style `edit` mode. The tool name stays `edit`; every call requires `file`, and the buffer loads automatically on first use.
 - `{"file": "path"}` - view file
 - `{"file": "path", "steps": [{"kbd": ["…"], "insert": "…"}]}` - edit file
+- `pause` (optional boolean) - a "paused" call skips the auto-save after its steps and may leave the last step in INSERT mode; the buffer stays open for the next call. Non-paused calls auto-save once after all steps complete.
 
 **Multi-location edits: always edit highest line number first (bottom-up).** Each insert shifts lines below it.
 

package/src/prompts/tools/web-search.md

@@ -3,9 +3,11 @@ Searches the web for up-to-date information beyond knowledge cutoff.
 <instruction>
 - You SHOULD prefer primary sources (papers, official docs) and corroborate key claims with multiple sources
 - You MUST include links for cited sources in the final response
+- Provider-neutral params: `recency` (freshness window), `limit`/`num_search_results` (result counts), `max_tokens`, `temperature`
 </instruction>
 
 <xai>
+The parameters below apply ONLY when the active search provider is `xai`; ignore them (and never pass them) on any other provider.
 - With provider `xai`, use `xai_search_mode: "web"` for normal web search, `"x"` for X/Twitter search, or `"web_and_x"` when both surfaces are relevant.
 - xAI web filters: `allowed_domains` or `excluded_domains` (max 5, mutually exclusive), plus `enable_image_understanding` and `enable_image_search`.
 - xAI X filters: `allowed_x_handles` or `excluded_x_handles` (max 20, mutually exclusive), `from_date`, `to_date`, `enable_image_understanding`, and `enable_video_understanding`.

package/src/prompts/tools/write.md

@@ -3,10 +3,16 @@ Creates or overwrites file at specified path.
 <conditions>
 - Creating new files explicitly required by task
 - Replacing entire file contents when editing would be more complex
-- Supports `.tar`, `.tar.gz`, `.tgz`, and `.zip` archive entries via `archive.ext:path/inside/archive`
-- Supports SQLite row operations via `db.sqlite:table` (insert), `db.sqlite:table:key` (update with JSON content, delete with empty content)
 </conditions>
 
+<instruction>
+- Archives: write entries inside `.tar`, `.tar.gz`, `.tgz`, and `.zip` via `archive.ext:path/inside/archive`.
+- SQLite rows:
+  - `db.sqlite:table` with JSON content — insert a row
+  - `db.sqlite:table:key` with JSON content — update the row with that primary key
+  - `db.sqlite:table:key` with empty content — DELETE that row (destructive; double-check the key)
+</instruction>
+
 <critical>
 - You SHOULD use Edit tool for modifying existing files (more precise, preserves formatting)
 - You NEVER create documentation files (*.md, README) unless explicitly requested

package/src/runtime-api-key.ts

@@ -0,0 +1,16 @@
+export interface RuntimeApiKeyTarget {
+	setRuntimeApiKey(provider: string, apiKey: string): void;
+}
+
+export interface RuntimeApiKeyModel {
+	provider: string;
+}
+
+export function applyCliRuntimeApiKeyOverride(
+	target: RuntimeApiKeyTarget,
+	apiKey: string | undefined,
+	model: RuntimeApiKeyModel | undefined,
+): void {
+	if (!apiKey || !model) return;
+	target.setRuntimeApiKey(model.provider, apiKey);
+}

package/src/runtime-mcp/config-writer.ts

@@ -237,6 +237,34 @@ export async function listMCPServers(filePath: string): Promise<string[]> {
 	return Object.keys(config.mcpServers ?? {});
 }
 
+/**
+ * Set a server's autoload flag (connect automatically at session startup).
+ *
+ * Autoload defaults to true, so turning it on removes the key to keep the
+ * config file free of redundant fields; turning it off writes `autoload: false`.
+ *
+ * @throws Error if the server doesn't exist
+ */
+export async function setServerAutoload(filePath: string, name: string, autoload: boolean): Promise<void> {
+	const existing = await readMCPConfigFile(filePath);
+	const server = existing.mcpServers?.[name];
+	if (!server) {
+		throw new Error(`Server "${name}" not found in ${filePath}`);
+	}
+
+	const { autoload: _removed, ...rest } = server;
+	const updatedServer = (autoload ? rest : { ...rest, autoload: false }) as MCPServerConfig;
+	const updated: MCPConfigFile = {
+		...existing,
+		mcpServers: {
+			...existing.mcpServers,
+			[name]: updatedServer,
+		},
+	};
+
+	await writeMCPConfigFile(filePath, updated);
+}
+
 /**
  * Read the disabled servers list from a config file.
  */

package/src/runtime-mcp/config.ts

@@ -20,6 +20,8 @@ export interface LoadMCPConfigsOptions {
 	filterExa?: boolean;
 	/** Whether to filter out browser MCP servers when builtin browser tool is enabled (default: false) */
 	filterBrowser?: boolean;
+	/** Only include servers eligible for startup connection, i.e. autoload !== false (default: false) */
+	autoloadOnly?: boolean;
 }
 
 /** Result of loading MCP configs */
@@ -40,6 +42,7 @@ function convertToLegacyConfig(server: MCPServer): MCPServerConfig {
 	const transport = server.transport ?? (server.command ? "stdio" : server.url ? "http" : "stdio");
 	const shared = {
 		enabled: server.enabled,
+		autoload: server.autoload,
 		timeout: server.timeout,
 		auth: server.auth,
 		oauth: server.oauth,
@@ -96,6 +99,7 @@ export async function loadAllMCPConfigs(cwd: string, options?: LoadMCPConfigsOpt
 	const enableProjectConfig = options?.enableProjectConfig ?? true;
 	const filterExa = options?.filterExa ?? true;
 	const filterBrowser = options?.filterBrowser ?? false;
+	const autoloadOnly = options?.autoloadOnly ?? false;
 
 	// Load MCP servers via capability system
 	const result = await loadCapability<MCPServer>(mcpCapability.id, { cwd });
@@ -115,6 +119,9 @@ export async function loadAllMCPConfigs(cwd: string, options?: LoadMCPConfigsOpt
 		if (config.enabled === false || disabledServers.has(server.name)) {
 			continue;
 		}
+		if (autoloadOnly && config.autoload === false) {
+			continue;
+		}
 		configs[server.name] = config;
 		sources[server.name] = server._source;
 	}

package/src/runtime-mcp/loader.ts

@@ -34,6 +34,8 @@ export interface MCPToolsLoadOptions {
 	filterExa?: boolean;
 	/** Whether to filter out browser MCP servers when builtin browser tool is enabled (default: false) */
 	filterBrowser?: boolean;
+	/** Only connect servers with autoload !== false (default: false) */
+	autoloadOnly?: boolean;
 	/** SQLite storage for MCP tool cache (null disables cache) */
 	cacheStorage?: AgentStorage | null;
 	/** Auth storage used to resolve OAuth credentials before initial MCP connect */
@@ -72,6 +74,7 @@ export async function discoverAndLoadMCPTools(cwd: string, options?: MCPToolsLoa
 			enableProjectConfig: options?.enableProjectConfig,
 			filterExa: options?.filterExa,
 			filterBrowser: options?.filterBrowser,
+			autoloadOnly: options?.autoloadOnly,
 		});
 	} catch (error) {
 		// If discovery fails entirely, return empty result

package/src/runtime-mcp/manager.ts

@@ -147,6 +147,8 @@ export interface MCPDiscoverOptions {
 	filterExa?: boolean;
 	/** Whether to filter out browser MCP servers when builtin browser tool is enabled (default: false) */
 	filterBrowser?: boolean;
+	/** Only connect servers with autoload !== false (default: false) */
+	autoloadOnly?: boolean;
 	/** Called when starting to connect to servers */
 	onConnecting?: (serverNames: string[]) => void;
 }
@@ -325,6 +327,7 @@ export class MCPManager {
 			enableProjectConfig: options?.enableProjectConfig,
 			filterExa: options?.filterExa,
 			filterBrowser: options?.filterBrowser,
+			autoloadOnly: options?.autoloadOnly,
 		});
 		const result = await this.connectServers(configs, sources, options?.onConnecting);
 		result.exaApiKeys = exaApiKeys;

package/src/runtime-mcp/types.ts

@@ -61,6 +61,12 @@ export interface MCPAuthConfig {
 interface MCPServerConfigBase {
 	/** Whether this server is enabled (default: true) */
 	enabled?: boolean;
+	/**
+	 * Whether to connect this server automatically at session startup (default: true).
+	 * When false the server stays configured-but-disconnected until connected
+	 * explicitly (e.g. `/mcp connect <name>`).
+	 */
+	autoload?: boolean;
 	/** Connection timeout in milliseconds (default: 30000) */
 	timeout?: number;
 	/** Authentication configuration (optional) */

package/src/sdk.ts

@@ -4,7 +4,7 @@ import {
 	type AgentMessage,
 	type AgentTelemetryConfig,
 	type AgentTool,
-	AppendOnlyContextManager,
+	type AppendOnlyContextManager,
 	INTENT_FIELD,
 	type ThinkingLevel,
 } from "@sayknow-cli/agent-core";
@@ -32,7 +32,11 @@ import {
 	prompt,
 	Snowflake,
 } from "@sayknow-cli/utils";
-
+import {
+	createAppendOnlyContextManager,
+	providerSupportsAppendOnlyAuto,
+	resolveAppendOnlyMode,
+} from "./append-only-mode";
 import { type AsyncJob, AsyncJobManager, isBackgroundJobSupportEnabled, jobElapsedMs } from "./async";
 import { loadCapability } from "./capability";
 import { type Rule, ruleCapability, setActiveRules } from "./capability/rule";
@@ -121,6 +125,7 @@ import { AgentOutputManager } from "./task/output-manager";
 import { parseThinkingLevel, resolveThinkingLevelForModel, toReasoningEffort } from "./thinking";
 import { collectDiscoverableTools, type DiscoverableTool } from "./tool-discovery/tool-index";
 import {
+	applyConfiguredSearchTimeout,
 	BashTool,
 	BUILTIN_TOOLS,
 	computeEssentialBuiltinNames,
@@ -129,10 +134,10 @@ import {
 	EditTool,
 	EvalTool,
 	FindTool,
+	getConfiguredSearchProviderPreference,
 	getSearchTools,
 	HIDDEN_TOOLS,
 	isConfigurableSearchProviderId,
-	isSearchProviderPreference,
 	type LspStartupServerInfo,
 	loadSshTool,
 	ReadTool,
@@ -142,7 +147,6 @@ import {
 	setPreferredImageProvider,
 	setPreferredSearchProvider,
 	setSearchFallbackProviders,
-	setSearchHardTimeoutMs,
 	type Tool,
 	type ToolSession,
 	WebSearchTool,
@@ -257,7 +261,7 @@ export interface CreateAgentSessionOptions {
 	thinkingLevel?: ThinkingLevel;
 	/** Runtime substitution metadata for the initial model_change session event. */
 	modelSubstitution?: { requestedModel: Model; reason: string };
-	/** Models available for cycling (Ctrl+P in interactive mode) */
+	/** Models available for cycling (Alt+N in interactive mode) */
 	scopedModels?: ScopedModelSelection[];
 
 	/** System prompt blocks. Array replaces default, function receives default blocks and returns final blocks. */
@@ -617,23 +621,12 @@ function registerJsVmCleanup(): void {
 	postmortem.register("js-vm-cleanup", disposeAllVmContexts);
 }
 
-/**
- * Resolve whether to enable append-only context mode based on the setting and provider.
- *
- * - `"on"` → always enable
- * - `"off"` → never enable
- * - `"auto"` → enable for DeepSeek (prefix-caching provider)
+/*
+ * Append-only context-mode resolution + manager construction live in
+ * ./append-only-mode so the initial build, the runtime model/setting-change
+ * path, and the status UI share one implementation. Re-exported for importers/tests.
  */
-function resolveAppendOnlyMode(setting: "auto" | "on" | "off" | undefined, provider: string): boolean {
-	switch (setting ?? "auto") {
-		case "on":
-			return true;
-		case "off":
-			return false;
-		default:
-			return provider === "deepseek";
-	}
-}
+export { createAppendOnlyContextManager, providerSupportsAppendOnlyAuto, resolveAppendOnlyMode };
 
 function customToolToDefinition(tool: CustomTool): ToolDefinition {
 	const definition: ToolDefinition & { [TOOL_DEFINITION_MARKER]: true } = {
@@ -868,6 +861,10 @@ function withEmbeddedDefaultSkcSkills(skills: Skill[]): Skill[] {
 	return [...byName.values()];
 }
 
+export function resolveIntentTracingEnabled(intentTracingSetting: boolean | undefined, hasUI: boolean): boolean {
+	return (!!intentTracingSetting || $flag("PI_INTENT_TRACING")) && hasUI;
+}
+
 export async function createAgentSession(options: CreateAgentSessionOptions = {}): Promise<CreateAgentSessionResult> {
 	const cwd = options.cwd ?? getProjectDir();
 	const agentDir = options.agentDir ?? getDefaultAgentDir();
@@ -934,20 +931,15 @@ export async function createAgentSession(options: CreateAgentSessionOptions = {}
 	slashCommandsPromise.catch(() => {});
 
 	// Initialize provider preferences from settings
-	const webSearchProvider = settings.get("providers.webSearch");
-	if (typeof webSearchProvider === "string" && isSearchProviderPreference(webSearchProvider)) {
-		setPreferredSearchProvider(webSearchProvider);
-	}
+	const webSearchProvider = getConfiguredSearchProviderPreference(settings);
+	setPreferredSearchProvider(webSearchProvider);
 	const webSearchFallback = settings.get("web_search.fallback");
 	if (Array.isArray(webSearchFallback)) {
 		setSearchFallbackProviders(
 			webSearchFallback.filter(value => typeof value === "string" && isConfigurableSearchProviderId(value)),
 		);
 	}
-	const webSearchTimeout = settings.get("web_search.timeout");
-	if (typeof webSearchTimeout === "number" && Number.isFinite(webSearchTimeout) && webSearchTimeout > 0) {
-		setSearchHardTimeoutMs(webSearchTimeout * 1000);
-	}
+	applyConfiguredSearchTimeout(settings);
 
 	const imageProvider = settings.get("providers.image");
 	if (
@@ -1132,8 +1124,15 @@ export async function createAgentSession(options: CreateAgentSessionOptions = {}
 				rulebookRules.push(rule);
 			}
 		}
-		if (existingSession.injectedTtsrRules.length > 0) {
-			ttsrManager.restoreInjected(existingSession.injectedTtsrRules);
+		if (ttsrManager.getSettings().enabled !== false) {
+			if ((existingSession.ttsrMessageCount ?? 0) > 0) {
+				ttsrManager.restoreMessageCount(existingSession.ttsrMessageCount ?? 0);
+			}
+			if (existingSession.injectedTtsrRuleRecords && existingSession.injectedTtsrRuleRecords.length > 0) {
+				ttsrManager.restoreInjected(existingSession.injectedTtsrRuleRecords);
+			} else if (existingSession.injectedTtsrRules.length > 0) {
+				ttsrManager.restoreInjected(existingSession.injectedTtsrRules);
+			}
 		}
 		return { ttsrManager, rulebookRules, alwaysApplyRules };
 	});
@@ -1221,8 +1220,8 @@ export async function createAgentSession(options: CreateAgentSessionOptions = {}
 
 	const agentRegistry = options.agentRegistry ?? AgentRegistry.global();
 	const resolvedAgentId = options.agentId ?? options.parentTaskPrefix ?? MAIN_AGENT_ID;
-	const resolvedAgentDisplayName =
-		options.agentDisplayName ?? ((options.taskDepth ?? 0) > 0 || options.parentTaskPrefix ? "sub" : "main");
+	const isSubSession = taskDepth > 0 || Boolean(options.parentTaskPrefix) || Boolean(options.currentAgentType);
+	const resolvedAgentDisplayName = options.agentDisplayName ?? (isSubSession ? "sub" : "main");
 	const evalKernelOwnerId = `agent-session:${Snowflake.next()}`;
 
 	try {
@@ -1527,12 +1526,20 @@ export async function createAgentSession(options: CreateAgentSessionOptions = {}
 		}
 		let notificationCfg: NotificationConfig | undefined;
 		try {
-			notificationCfg = getNotificationConfig(Settings.instance);
+			notificationCfg = getNotificationConfig(settings);
 		} catch {
 			notificationCfg = undefined;
 		}
-		if (shouldRegisterNotificationsExtension({ env: process.env, cfg: notificationCfg })) {
-			inlineExtensions.push(createNotificationsExtension);
+		if (
+			shouldRegisterNotificationsExtension({
+				env: process.env,
+				cfg: notificationCfg,
+				taskDepth,
+				parentTaskPrefix: options.parentTaskPrefix,
+				currentAgentType: options.currentAgentType,
+			})
+		) {
+			inlineExtensions.push(api => createNotificationsExtension(api, { settings }));
 		}
 
 		// Extension/module discovery is quarantined; retain only the private
@@ -1660,6 +1667,12 @@ export async function createAgentSession(options: CreateAgentSessionOptions = {}
 				cwd,
 				sessionManager,
 				modelRegistry,
+				{
+					kind: isSubSession ? "sub" : "main",
+					taskDepth,
+					...(options.parentTaskPrefix ? { parentTaskPrefix: options.parentTaskPrefix } : {}),
+					...(options.currentAgentType ? { currentAgentType: options.currentAgentType } : {}),
+				},
 			);
 		}
 
@@ -1779,7 +1792,11 @@ export async function createAgentSession(options: CreateAgentSessionOptions = {}
 
 		const repeatToolDescriptions = settings.get("repeatToolDescriptions");
 		const eagerTasks = settings.get("task.eager");
-		const intentField = settings.get("tools.intentTracing") || $flag("PI_INTENT_TRACING") ? INTENT_FIELD : undefined;
+		const intentTracingEnabled = resolveIntentTracingEnabled(
+			settings.get("tools.intentTracing"),
+			options.hasUI ?? false,
+		);
+		const intentField = intentTracingEnabled ? INTENT_FIELD : undefined;
 		const rebuildSystemPrompt = async (
 			toolNames: string[],
 			tools: Map<string, AgentTool>,
@@ -1844,9 +1861,14 @@ export async function createAgentSession(options: CreateAgentSessionOptions = {}
 				intentField,
 				mcpDiscoveryMode: false,
 				mcpDiscoveryServerSummaries: [],
+				toolDiscoveryActive: effectiveDiscoveryMode === "all",
+				discoverableTools: discoverableBuiltinTools
+					.map(tool => ({ name: tool.name, summary: tool.summary }))
+					.sort((a, b) => a.name.localeCompare(b.name)),
 				eagerTasks,
 				secretsEnabled,
 				workspaceTree: workspaceTreePromise,
+				subagent: options.parentTaskPrefix !== undefined,
 			});
 
 			if (options.systemPrompt === undefined) {
@@ -1948,7 +1970,7 @@ export async function createAgentSession(options: CreateAgentSessionOptions = {}
 		agentRegistry.register({
 			id: resolvedAgentId,
 			displayName: resolvedAgentDisplayName,
-			kind: (options.taskDepth ?? 0) > 0 || options.parentTaskPrefix ? "sub" : "main",
+			kind: isSubSession ? "sub" : "main",
 			parentId: options.parentTaskPrefix,
 			session: null,
 			sessionFile: sessionManager.getSessionFile() ?? null,
@@ -2046,7 +2068,7 @@ export async function createAgentSession(options: CreateAgentSessionOptions = {}
 
 		const appendOnlyContext =
 			model && resolveAppendOnlyMode(settings.get("provider.appendOnlyContext"), model.provider)
-				? new AppendOnlyContextManager()
+				? createAppendOnlyContextManager(model.provider)
 				: undefined;
 		if (appendOnlyContext && options.forkContextSeed && !hasExistingSession) {
 			if (options.forkContextSeed.appendOnlyPrefixSnapshot) {
@@ -2217,6 +2239,7 @@ export async function createAgentSession(options: CreateAgentSessionOptions = {}
 			onResponse,
 			convertToLlm: convertToLlmFinal,
 			rebuildSystemPrompt,
+			workspaceTree: resolvedWorkspaceTree,
 			reloadSshTool,
 			requestedToolNames: requestedToolNameSet,
 			discoverableToolAllowedNames: options.discoverableToolAllowedNames,