saeeol 1.1.0 → 1.1.1

package/src/tool/task.txt

@@ -0,0 +1,57 @@
+Launch a new agent to handle complex, multistep tasks autonomously.
+
+When using the Task tool, you must specify a subagent_type parameter to select which agent type to use.
+
+When to use the Task tool:
+- When you are instructed to execute custom slash commands. Use the Task tool with the slash command invocation as the entire prompt. The slash command can take arguments. For example: Task(description="Check the file", prompt="/check-file path/to/file.py")
+
+When NOT to use the Task tool:
+- If you want to read a specific file path, use the Read or Glob tool instead of the Task tool, to find the match more quickly
+- If you are searching for a specific class definition like "class Foo", use the Glob tool instead, to find the match more quickly
+- If you are searching for code within a specific file or set of 2-3 files, use the Read tool instead of the Task tool, to find the match more quickly
+- Other tasks that are not related to the agent descriptions above
+
+
+Usage notes:
+1. Launch multiple agents concurrently whenever possible, to maximize performance; to do that, use a single message with multiple tool uses
+2. When the agent is done, it will return a single message back to you. The result returned by the agent is not visible to the user. To show the user the result, you should send a text message back to the user with a concise summary of the result. The output includes a task_id you can reuse later to continue the same subagent session.
+3. Each agent invocation starts with a fresh context unless you provide task_id to resume the same subagent session (which continues with its previous messages and tool outputs). When starting fresh, your prompt should contain a highly detailed task description for the agent to perform autonomously and you should specify exactly what information the agent should return back to you in its final and only message to you.
+4. The agent's outputs should generally be trusted
+5. Clearly tell the agent whether you expect it to write code or just to do research (search, file reads, web fetches, etc.), since it is not aware of the user's intent. Tell it how to verify its work if possible (e.g., relevant test commands).
+6. If the agent description mentions that it should be used proactively, then you should try your best to use it without the user having to ask for it first. Use your judgement.
+
+Example usage (NOTE: The agents below are fictional examples for illustration only - use the actual agents listed above):
+
+<example_agent_descriptions>
+"code-reviewer": use this agent after you are done writing a significant piece of code
+"greeting-responder": use this agent when to respond to user greetings with a friendly joke
+</example_agent_description>
+
+<example>
+user: "Please write a function that checks if a number is prime"
+assistant: Sure let me write a function that checks if a number is prime
+assistant: First let me use the Write tool to write a function that checks if a number is prime
+assistant: I'm going to use the Write tool to write the following code:
+<code>
+function isPrime(n) {
+  if (n <= 1) return false
+  for (let i = 2; i * i <= n; i++) {
+    if (n % i === 0) return false
+  }
+  return true
+}
+</code>
+<commentary>
+Since a significant piece of code was written and the task was completed, now use the code-reviewer agent to review the code
+</commentary>
+assistant: Now let me use the code-reviewer agent to review the code
+assistant: Uses the Task tool to launch the code-reviewer agent
+</example>
+
+<example>
+user: "Hello"
+<commentary>
+Since the user is greeting, use the greeting-responder agent to respond with a friendly joke
+</commentary>
+assistant: "I'm going to use the Task tool to launch the with the greeting-responder agent"
+</example>

package/src/tool/todo.ts

@@ -0,0 +1,62 @@
+import { Effect, Schema } from "effect"
+import * as Tool from "./tool"
+import DESCRIPTION_WRITE from "./todowrite.txt"
+import { Todo } from "../session/todo"
+import { TodoView } from "../saeeol/todo-view"
+
+// Todo.Info is still a zod schema (session/todo.ts). Inline the field shape
+// here rather than referencing its `.shape` — the LLM-visible JSON Schema is
+// identical, and it removes the last zod dependency from this tool.
+const TodoItem = Schema.Struct({
+  content: Schema.String.annotate({ description: "Brief description of the task" }),
+  status: Schema.String.annotate({
+    description: "Current status of the task: pending, in_progress, completed, cancelled",
+  }),
+  priority: Schema.String.annotate({ description: "Priority level of the task: high, medium, low" }),
+})
+
+export const Parameters = Schema.Struct({
+  todos: Schema.mutable(Schema.Array(TodoItem)).annotate({ description: "The updated todo list" }),
+})
+
+type Metadata = {
+  todos: Todo.Info[]
+  view?: TodoView.Info
+}
+
+export const TodoWriteTool = Tool.define<typeof Parameters, Metadata, Todo.Service>(
+  "todowrite",
+  Effect.gen(function* () {
+    const todo = yield* Todo.Service
+
+    return {
+      description: DESCRIPTION_WRITE,
+      parameters: Parameters,
+      execute: (params: Schema.Schema.Type<typeof Parameters>, ctx: Tool.Context<Metadata>) =>
+        Effect.gen(function* () {
+          yield* ctx.ask({
+            permission: "todowrite",
+            patterns: ["*"],
+            always: ["*"],
+            metadata: {},
+          })
+          const before = yield* todo.get(ctx.sessionID)
+          const view = TodoView.calculate(before, params.todos)
+
+          yield* todo.update({
+            sessionID: ctx.sessionID,
+            todos: params.todos,
+          })
+
+          return {
+            title: `${params.todos.filter((x) => x.status !== "completed").length} todos`,
+            output: JSON.stringify(params.todos, null, 2),
+            metadata: {
+              todos: params.todos,
+              view,
+            },
+          }
+        }),
+    } satisfies Tool.DefWithoutID<typeof Parameters, Metadata>
+  }),
+)

package/src/tool/todowrite.txt

@@ -0,0 +1,167 @@
+Use this tool to create and manage a structured task list for your current coding session. This helps you track progress, organize complex tasks, and demonstrate thoroughness to the user.
+It also helps the user understand the progress of the task and overall progress of their requests.
+
+## When to Use This Tool
+Use this tool proactively in these scenarios:
+
+1. Complex multistep tasks - When a task requires 3 or more distinct steps or actions
+2. Non-trivial and complex tasks - Tasks that require careful planning or multiple operations
+3. User explicitly requests todo list - When the user directly asks you to use the todo list
+4. User provides multiple tasks - When users provide a list of things to be done (numbered or comma-separated)
+5. After receiving new instructions - Immediately capture user requirements as todos. Feel free to edit the todo list based on new information.
+6. After completing a task - Mark it complete and add any new follow-up tasks
+7. When you start working on a new task, mark the todo as in_progress. Ideally you should only have one todo as in_progress at a time. Complete existing tasks before starting new ones.
+
+## When NOT to Use This Tool
+
+Skip using this tool when:
+1. There is only a single, straightforward task
+2. The task is trivial and tracking it provides no organizational benefit
+3. The task can be completed in less than 3 trivial steps
+4. The task is purely conversational or informational
+
+NOTE that you should not use this tool if there is only one trivial task to do. In this case you are better off just doing the task directly.
+
+## Examples of When to Use the Todo List
+
+<example>
+User: I want to add a dark mode toggle to the application settings. Make sure you run the tests and build when you're done!
+Assistant: I'll help add a dark mode toggle to your application settings. Let me create a todo list to track this implementation.
+*Creates todo list with the following items:*
+1. Create dark mode toggle component in Settings page
+2. Add dark mode state management (context/store)
+3. Implement CSS-in-JS styles for dark theme
+4. Update existing components to support theme switching
+5. Run tests and build process, addressing any failures or errors that occur
+*Begins working on the first task*
+
+<reasoning>
+The assistant used the todo list because:
+1. Adding dark mode is a multi-step feature requiring UI, state management, and styling changes
+2. The user explicitly requested tests and build be run afterward
+3. The assistant inferred that tests and build need to pass by adding "Ensure tests and build succeed" as the final task
+</reasoning>
+</example>
+
+<example>
+User: Help me rename the function getCwd to getCurrentWorkingDirectory across my project
+Assistant: Let me first search through your codebase to find all occurrences of 'getCwd'.
+*Uses grep or search tools to locate all instances of getCwd in the codebase*
+Assistant: I've found 15 instances of 'getCwd' across 8 different files. Let me create a todo list to track these changes.
+*Creates todo list with specific items for each file that needs updating*
+
+<reasoning>
+The assistant used the todo list because:
+1. First, the assistant searched to understand the scope of the task
+2. Upon finding multiple occurrences across different files, it determined this was a complex task with multiple steps
+3. The todo list helps ensure every instance is tracked and updated systematically
+4. This approach prevents missing any occurrences and maintains code consistency
+</reasoning>
+</example>
+
+
+<example>
+User: I need to implement these features for my e-commerce site: user registration, product catalog, shopping cart, and checkout flow.
+Assistant: I'll help implement these features. First, let's add all the features to the todo list.
+*Creates a todo list breaking down each feature into specific tasks based on the project architecture*
+Assistant: Let's start with user registration. This will involve creating database models, API endpoints, and frontend forms that integrate with your existing authentication system.
+
+<reasoning>
+The assistant used the todo list because:
+1. The user provided multiple complex features to implement in a comma separated list
+2. The todo list helps organize these large features into manageable tasks
+3. This approach allows for tracking progress across the entire implementation
+</reasoning>
+</example>
+
+<example>
+User: Can you help optimize my React application? It's rendering slowly and has performance issues.</user>
+Assistant: I'll help optimize your React application. First, let me examine your codebase to identify potential performance bottlenecks.
+*Reviews component structure, render patterns, state management, and data fetching*
+Assistant: After analyzing your codebase, I've identified several performance issues. Let me create a todo list to track our optimization efforts.
+*Creates todo list with items like: 1) Implement memoization for expensive calculations in ProductList, 2) Add virtualization for long lists in Dashboard, 3) Optimize image loading in Gallery component, 4) Fix state update loops in ShoppingCart, 5) Review bundle size and implement code splitting*
+Let's start by implementing memoization for the expensive calculations in your ProductList component.</assistant>
+
+<reasoning>
+The assistant used the todo list because:
+1. First, the assistant examined the codebase to identify specific performance issues
+2. Based on this analysis, it identified multiple optimization opportunities
+3. Performance optimization is a non-trivial task requiring multiple steps
+4. The todo list helps methodically track improvements across different components
+5. This systematic approach ensures all performance bottlenecks are addressed
+</reasoning>
+</example>
+
+## Examples of When NOT to Use the Todo List
+
+<example>
+User: How do I print 'Hello World' in Python?
+Assistant: In Python, you can print "Hello World" with this simple code:
+
+python
+print("Hello World")
+
+This will output the text "Hello World" to the console when executed.</assistant>
+
+<reasoning>
+The assistant did not use the todo list because this is a single, trivial task that can be completed in one step. There's no need to track multiple tasks or steps for such a straightforward request.
+</reasoning>
+</example>
+
+<example>
+User: What does the git status command do?
+Assistant: The git status command shows the current state of your working directory and staging area. It displays which changes have been staged, which haven't, and which files aren't being tracked by Git. This is a fundamental command for understanding the current state of your repository before making commits.
+
+<reasoning>
+The assistant did not use the todo list because this is an informational request with no actual coding task to complete. The user is simply asking for an explanation, not for the assistant to perform multiple steps or tasks.
+</reasoning>
+</example>
+
+<example>
+User: Can you add a comment to the calculateTotal function to explain what it does?
+Assistant: Sure, let me add a comment to the calculateTotal function to explain what it does.
+* Uses the Edit tool to add a comment to the calculateTotal function *
+
+<reasoning>
+The assistant did not use the todo list because this is a single, straightforward task confined to one location in the code. Adding a comment doesn't require tracking multiple steps or systematic organization.
+</reasoning>
+</example>
+
+<example>
+User: Run npm install for me and tell me what happens.
+Assistant: I'll run the npm install command for you.
+
+*Executes: npm install*
+
+The command completed successfully. Here's the output:
+[Output of npm install command]
+
+All dependencies have been installed according to your package.json file.
+
+<reasoning>
+The assistant did not use the todo list because this is a single command execution with immediate results. There are no multiple steps to track or organize, making the todo list unnecessary for this straightforward task.
+</reasoning>
+</example>
+
+## Task States and Management
+
+1. **Task States**: Use these states to track progress:
+   - pending: Task not yet started
+   - in_progress: Currently working on (limit to ONE task at a time)
+   - completed: Task finished successfully
+   - cancelled: Task no longer needed
+
+2. **Task Management**:
+   - Update task status in real-time as you work
+   - Mark tasks complete IMMEDIATELY after finishing (don't batch completions)
+   - Only have ONE task in_progress at any time
+   - Complete current tasks before starting new ones
+   - Cancel tasks that become irrelevant
+
+3. **Task Breakdown**:
+   - Create specific, actionable items
+   - Break complex tasks into smaller, manageable steps
+   - Use clear, descriptive task names
+
+When in doubt, use this tool. Being proactive with task management demonstrates attentiveness and ensures you complete all requirements successfully.
+

package/src/tool/tool.ts

@@ -0,0 +1,162 @@
+import { Effect, Schema } from "effect"
+import type { MessageV2 } from "../session/message-v2"
+import type { Permission } from "../permission"
+import type { SessionID, MessageID } from "../session/schema"
+import * as Truncate from "./truncate"
+import { Agent } from "@/agent/agent"
+
+interface Metadata {
+  [key: string]: any
+}
+
+// TODO: remove this hack
+export type DynamicDescription = (agent: Agent.Info) => Effect.Effect<string>
+
+export type Context<M extends Metadata = Metadata> = {
+  sessionID: SessionID
+  messageID: MessageID
+  agent: string
+  abort: AbortSignal
+  callID?: string
+  extra?: { [key: string]: unknown }
+  messages: MessageV2.WithParts[]
+  metadata(input: { title?: string; metadata?: M }): Effect.Effect<void>
+  ask(input: Omit<Permission.Request, "id" | "sessionID" | "tool">): Effect.Effect<void>
+}
+
+export interface ExecuteResult<M extends Metadata = Metadata> {
+  title: string
+  metadata: M
+  output: string
+  attachments?: Omit<MessageV2.FilePart, "id" | "sessionID" | "messageID">[]
+}
+
+export interface Def<
+  Parameters extends Schema.Decoder<unknown> = Schema.Decoder<unknown>,
+  M extends Metadata = Metadata,
+> {
+  id: string
+  description: string
+  parameters: Parameters
+  execute(args: Schema.Schema.Type<Parameters>, ctx: Context): Effect.Effect<ExecuteResult<M>>
+  formatValidationError?(error: unknown): string
+}
+export type DefWithoutID<
+  Parameters extends Schema.Decoder<unknown> = Schema.Decoder<unknown>,
+  M extends Metadata = Metadata,
+> = Omit<Def<Parameters, M>, "id">
+
+export interface Info<
+  Parameters extends Schema.Decoder<unknown> = Schema.Decoder<unknown>,
+  M extends Metadata = Metadata,
+> {
+  id: string
+  init: () => Effect.Effect<DefWithoutID<Parameters, M>>
+}
+
+type Init<Parameters extends Schema.Decoder<unknown>, M extends Metadata> =
+  | DefWithoutID<Parameters, M>
+  | (() => Effect.Effect<DefWithoutID<Parameters, M>>)
+
+export type InferParameters<T> =
+  T extends Info<infer P, any>
+    ? Schema.Schema.Type<P>
+    : T extends Effect.Effect<Info<infer P, any>, any, any>
+      ? Schema.Schema.Type<P>
+      : never
+export type InferMetadata<T> =
+  T extends Info<any, infer M> ? M : T extends Effect.Effect<Info<any, infer M>, any, any> ? M : never
+
+export type InferDef<T> =
+  T extends Info<infer P, infer M>
+    ? Def<P, M>
+    : T extends Effect.Effect<Info<infer P, infer M>, any, any>
+      ? Def<P, M>
+      : never
+
+function wrap<Parameters extends Schema.Decoder<unknown>, Result extends Metadata>(
+  id: string,
+  init: Init<Parameters, Result>,
+  truncate: Truncate.Interface,
+  agents: Agent.Interface,
+) {
+  return () =>
+    Effect.gen(function* () {
+      const toolInfo = typeof init === "function" ? { ...(yield* init()) } : { ...init }
+      // Compile the parser closure once per tool init; `decodeUnknownEffect`
+      // allocates a new closure per call, so hoisting avoids re-closing it for
+      // every LLM tool invocation.
+      const decode = Schema.decodeUnknownEffect(toolInfo.parameters)
+      const execute = toolInfo.execute
+      toolInfo.execute = (args, ctx) => {
+        const attrs = {
+          "tool.name": id,
+          "session.id": ctx.sessionID,
+          "message.id": ctx.messageID,
+          ...(ctx.callID ? { "tool.call_id": ctx.callID } : {}),
+        }
+        return Effect.gen(function* () {
+          const decoded = yield* decode(args).pipe(
+            Effect.mapError((error) =>
+              toolInfo.formatValidationError
+                ? new Error(toolInfo.formatValidationError(error), { cause: error })
+                : new Error(
+                    `The ${id} tool was called with invalid arguments: ${error}.\nPlease rewrite the input so it satisfies the expected schema.`,
+                    { cause: error },
+                  ),
+            ),
+          )
+          const result = yield* execute(decoded as Schema.Schema.Type<Parameters>, ctx)
+          if (result.metadata.truncated !== undefined) {
+            return result
+          }
+          const agent = yield* agents.get(ctx.agent)
+          const truncated = yield* truncate.output(result.output, {}, agent)
+          return {
+            ...result,
+            output: truncated.content,
+            metadata: {
+              ...result.metadata,
+              truncated: truncated.truncated,
+              ...(truncated.truncated && { outputPath: truncated.outputPath }),
+            },
+          }
+        }).pipe(Effect.orDie, Effect.withSpan("Tool.execute", { attributes: attrs }))
+      }
+      return toolInfo
+    })
+}
+
+export function define<
+  Parameters extends Schema.Decoder<unknown>,
+  Result extends Metadata,
+  R,
+  ID extends string = string,
+>(
+  id: ID,
+  init: Effect.Effect<Init<Parameters, Result>, never, R>,
+): Effect.Effect<Info<Parameters, Result>, never, R | Truncate.Service | Agent.Service> & { id: ID } {
+  return Object.assign(
+    Effect.gen(function* () {
+      const resolved = yield* init
+      const truncate = yield* Truncate.Service
+      const agents = yield* Agent.Service
+      return { id, init: wrap(id, resolved, truncate, agents) }
+    }),
+    { id },
+  )
+}
+
+export function init<P extends Schema.Decoder<unknown>, M extends Metadata>(
+  info: Info<P, M>,
+): Effect.Effect<Def<P, M>> {
+  return Effect.gen(function* () {
+    const init = yield* info.init()
+    return {
+      ...init,
+      id: info.id,
+    }
+  })
+}
+
+export * as Tool from "./tool"

package/src/tool/truncate.ts

@@ -0,0 +1,160 @@
+import { NodePath } from "@effect/platform-node"
+import { Cause, Duration, Effect, Layer, Option, Schedule, Context } from "effect"
+import path from "path"
+import type { Agent } from "../agent/agent"
+import { AppFileSystem } from "@saeeol/core/filesystem"
+import { evaluate } from "@/permission/evaluate"
+import { Config } from "@/config/config"
+import { Identifier } from "../id/id"
+import * as Log from "@saeeol/core/util/log"
+import { ToolID } from "./schema"
+import { TRUNCATION_DIR } from "./truncation-dir"
+
+const log = Log.create({ service: "truncation" })
+const RETENTION = Duration.days(7)
+
+export const MAX_LINES = 2000
+export const MAX_BYTES = 50 * 1024
+export const DIR = TRUNCATION_DIR
+export const GLOB = path.join(TRUNCATION_DIR, "*")
+
+export type Result = { content: string; truncated: false } | { content: string; truncated: true; outputPath: string }
+
+export interface Options {
+  maxLines?: number
+  maxBytes?: number
+  direction?: "head" | "tail"
+}
+
+function hasTaskTool(agent?: Agent.Info) {
+  if (!agent?.permission) return false
+  return evaluate("task", "*", agent.permission).action !== "deny"
+}
+
+export interface Interface {
+  readonly cleanup: () => Effect.Effect<void>
+  readonly write: (text: string) => Effect.Effect<string>
+  /**
+   * Returns output unchanged when it fits within the limits, otherwise writes the full text
+   * to the truncation directory and returns a preview plus a hint to inspect the saved file.
+   */
+  readonly output: (text: string, options?: Options, agent?: Agent.Info) => Effect.Effect<Result>
+  /**
+   * Resolved truncation limits: values from `tool_output` in saeeol config, or MAX_LINES / MAX_BYTES if unset.
+   */
+  readonly limits: () => Effect.Effect<{ maxLines: number; maxBytes: number }>
+}
+
+export class Service extends Context.Service<Service, Interface>()("@saeeol/Truncate") {}
+
+export const layer = Layer.effect(
+  Service,
+  Effect.gen(function* () {
+    const fs = yield* AppFileSystem.Service
+
+    const cleanup = Effect.fn("Truncate.cleanup")(function* () {
+      const cutoff = Identifier.timestamp(
+        Identifier.create("tool", "ascending", Date.now() - Duration.toMillis(RETENTION)),
+      )
+      const entries = yield* fs.readDirectory(TRUNCATION_DIR).pipe(
+        Effect.map((all) => all.filter((name) => name.startsWith("tool_"))),
+        Effect.catch(() => Effect.succeed([])),
+      )
+      for (const entry of entries) {
+        if (Identifier.timestamp(entry) >= cutoff) continue
+        yield* fs.remove(path.join(TRUNCATION_DIR, entry)).pipe(Effect.catch(() => Effect.void))
+      }
+    })
+
+    const write = Effect.fn("Truncate.write")(function* (text: string) {
+      const file = path.join(TRUNCATION_DIR, ToolID.ascending())
+      yield* fs.ensureDir(TRUNCATION_DIR).pipe(Effect.orDie)
+      yield* fs.writeFileString(file, text).pipe(Effect.orDie)
+      return file
+    })
+
+    const limits = Effect.fn("Truncate.limits")(function* () {
+      const configSvc = yield* Effect.serviceOption(Config.Service)
+      if (Option.isNone(configSvc)) return { maxLines: MAX_LINES, maxBytes: MAX_BYTES }
+      const cfg = yield* configSvc.value.get().pipe(Effect.catch(() => Effect.succeed(undefined)))
+      return {
+        maxLines: cfg?.tool_output?.max_lines ?? MAX_LINES,
+        maxBytes: cfg?.tool_output?.max_bytes ?? MAX_BYTES,
+      }
+    })
+
+    const output = Effect.fn("Truncate.output")(function* (text: string, options: Options = {}, agent?: Agent.Info) {
+      const resolved = yield* limits()
+      const maxLines = options.maxLines ?? resolved.maxLines
+      const maxBytes = options.maxBytes ?? resolved.maxBytes
+      const direction = options.direction ?? "head"
+      const lines = text.split("\n")
+      const totalBytes = Buffer.byteLength(text, "utf-8")
+
+      if (lines.length <= maxLines && totalBytes <= maxBytes) {
+        return { content: text, truncated: false } as const
+      }
+
+      const out: string[] = []
+      let i = 0
+      let bytes = 0
+      let hitBytes = false
+
+      if (direction === "head") {
+        for (i = 0; i < lines.length && i < maxLines; i++) {
+          const size = Buffer.byteLength(lines[i], "utf-8") + (i > 0 ? 1 : 0)
+          if (bytes + size > maxBytes) {
+            hitBytes = true
+            break
+          }
+          out.push(lines[i])
+          bytes += size
+        }
+      } else {
+        for (i = lines.length - 1; i >= 0 && out.length < maxLines; i--) {
+          const size = Buffer.byteLength(lines[i], "utf-8") + (out.length > 0 ? 1 : 0)
+          if (bytes + size > maxBytes) {
+            hitBytes = true
+            break
+          }
+          out.unshift(lines[i])
+          bytes += size
+        }
+      }
+
+      const removed = hitBytes ? totalBytes - bytes : lines.length - out.length
+      const unit = hitBytes ? "bytes" : "lines"
+      const preview = out.join("\n")
+      const file = yield* write(text)
+
+      const hint = hasTaskTool(agent)
+        ? `The tool call succeeded but the output was truncated. Full output saved to: ${file}\nUse the Task tool to have explore agent process this file with Grep and Read (with offset/limit). Do NOT read the full file yourself - delegate to save context.`
+        : `The tool call succeeded but the output was truncated. Full output saved to: ${file}\nUse Grep to search the full content or Read with offset/limit to view specific sections.`
+
+      return {
+        content:
+          direction === "head"
+            ? `${preview}\n\n...${removed} ${unit} truncated...\n\n${hint}`
+            : `...${removed} ${unit} truncated...\n\n${hint}\n\n${preview}`,
+        truncated: true,
+        outputPath: file,
+      } as const
+    })
+
+    yield* cleanup().pipe(
+      Effect.catchCause((cause) => {
+        log.error("truncation cleanup failed", { cause: Cause.pretty(cause) })
+        return Effect.void
+      }),
+      Effect.repeat(Schedule.spaced(Duration.hours(1))),
+      Effect.delay(Duration.minutes(1)),
+      Effect.forkScoped,
+    )
+
+    return Service.of({ cleanup, write, output, limits })
+  }),
+)
+
+export const defaultLayer = layer.pipe(Layer.provide(AppFileSystem.defaultLayer), Layer.provide(NodePath.layer))
+
+export * as Truncate from "./truncate"

package/src/tool/truncation-dir.ts

@@ -0,0 +1,4 @@
+import path from "path"
+import { Global } from "@saeeol/core/global"
+
+export const TRUNCATION_DIR = path.join(Global.Path.data, "tool-output")