refactor(codemode): split runtime into focused interpreter modules

packages/codemode/interpreter-support.md

@@ -176,9 +176,9 @@ ultimate source of truth.
 ## Strings
 
 - [x] Case/normalization: `toLowerCase`, `toUpperCase`, `normalize`.
-- [x] Trimming: `trim`, `trimStart`, `trimEnd`, `trimLeft`, and `trimRight`.
+- [x] Trimming: `trim`, `trimStart`, and `trimEnd`.
 - [x] Searching/tests: `includes`, `startsWith`, `endsWith`, `indexOf`, `lastIndexOf`, and `search`.
-- [x] Slicing/access: `slice`, `substring`, `substr`, `at`, `charAt`, `charCodeAt`, and `codePointAt`.
+- [x] Slicing/access: `slice`, `substring`, `at`, `charAt`, `charCodeAt`, and `codePointAt`.
 - [x] Construction/transformation: `split`, `concat`, `repeat`, `padStart`, `padEnd`, `replace`, and `replaceAll`.
 - [x] Regular-expression integration: `match`, materialized `matchAll`, `replace`, `replaceAll`, `split`, and `search`.
 - [x] `localeCompare`; locale and options arguments are currently ignored.

packages/codemode/src/codemode.ts

@@ -1,5 +1,5 @@
 import { Effect, Schema } from "effect"
-import { executeWithLimits } from "./interpreter/runtime.js"
+import { executeWithLimits } from "./interpreter/execute.js"
 import { type HostTools, type Services, type ToolDescription, ToolRuntime } from "./tool-runtime.js"
 import type { Definition } from "./tool.js"
 
@@ -9,15 +9,15 @@ export type { ToolCall, ToolCallEnded, ToolCallHooks, ToolCallStarted, ToolDescr
 /** Resource budgets enforced independently during each CodeMode program execution. */
 export type ExecutionLimits = {
   /**
-   * Wall-clock milliseconds before execution is interrupted; result delivery additionally
-   * waits for tool interruption cleanup. No default: absent means no timeout.
+   * Wall-clock milliseconds before interruption. Result delivery waits for tool cleanup.
+   * No default: absent means no timeout.
    */
   readonly timeoutMs?: number
   /** Maximum number of tool calls admitted by the runtime. No default: absent means unlimited. */
   readonly maxToolCalls?: number
   /**
-   * Maximum UTF-8 bytes retained from the result value and logs; warnings have a separate
-   * budget of the same size. Fixed truncation notices and host formatting are additional.
+   * Maximum UTF-8 bytes retained from the result and logs. Warnings have a separate equal budget;
+   * truncation notices and host formatting are additional.
    */
   readonly maxOutputBytes?: number
 }
@@ -94,7 +94,6 @@ const ToolCallSchema = Schema.Struct({ name: Schema.String })
 export const Success = Schema.Struct({
   ok: Schema.Literal(true),
   value: Schema.Json,
-  // Runtime-authored non-fatal diagnostics; program console output stays in `logs`.
   warnings: Schema.optionalKey(Schema.Array(Diagnostic)),
   logs: Schema.optionalKey(Schema.Array(Schema.String)),
   truncated: Schema.optionalKey(Schema.Boolean),

packages/codemode/src/interpreter/errors.ts

@@ -0,0 +1,93 @@
+import type { Diagnostic } from "../codemode.js"
+import { ToolError } from "../tool-error.js"
+import { copyOut, ToolRuntimeError, type SafeObject } from "../tool-runtime.js"
+import { type AstNode, formatLocation, InterpreterRuntimeError, ProgramThrow, sourceLocation } from "./model.js"
+import { containsRuntimeReference } from "./references.js"
+import { spreadItems } from "../stdlib/collections.js"
+import { coerceToString, createAggregateErrorValue, createErrorValue, errorConstructors } from "../stdlib/value.js"
+
+export const normalizeError = (error: unknown): Diagnostic => {
+  if (error instanceof InterpreterRuntimeError) {
+    return {
+      kind: error.kind,
+      message: `${error.message}${formatLocation(error.node)}`,
+      ...(error.node?.loc ? { location: sourceLocation(error.node) } : {}),
+      ...(error.suggestions ? { suggestions: error.suggestions } : {}),
+    }
+  }
+
+  if (error instanceof ToolRuntimeError) {
+    return {
+      kind: error.kind,
+      message: error.message,
+      ...(error.suggestions.length > 0 ? { suggestions: error.suggestions } : {}),
+    }
+  }
+
+  if (error instanceof ToolError) {
+    return { kind: "ToolFailure", message: error.message }
+  }
+
+  if (error instanceof ProgramThrow) {
+    const value = error.value
+    let message: string
+    if (containsRuntimeReference(value)) {
+      // Never expose runtime reference internals through thrown values.
+      message = "a non-data value"
+    } else if (typeof value === "string") {
+      message = value
+    } else if (
+      value !== null &&
+      typeof value === "object" &&
+      typeof (value as { message?: unknown }).message === "string"
+    ) {
+      message = (value as { message: string }).message
+    } else {
+      try {
+        message = JSON.stringify(copyOut(value)) ?? String(value)
+      } catch {
+        message = String(value)
+      }
+    }
+    return { kind: "ExecutionFailure", message: `Uncaught: ${message}` }
+  }
+
+  if (error instanceof RangeError && /call stack|recursion/i.test(error.message)) {
+    return {
+      kind: "ExecutionFailure",
+      message: "Execution exceeded the maximum nesting depth.",
+    }
+  }
+
+  if (error instanceof Error) {
+    return {
+      kind: error.name === "SyntaxError" ? "ParseError" : "ExecutionFailure",
+      message: error.message,
+    }
+  }
+
+  return {
+    kind: "ExecutionFailure",
+    message: String(error),
+  }
+}
+
+export const caughtErrorValue = (thrown: unknown): unknown => {
+  if (thrown instanceof ProgramThrow) return thrown.value
+  if (thrown instanceof InterpreterRuntimeError) return createErrorValue(thrown.errorName, thrown.message)
+  const name = thrown instanceof Error && errorConstructors.has(thrown.name) ? thrown.name : "Error"
+  return createErrorValue(name, normalizeError(thrown).message)
+}
+
+export const constructErrorValue = (name: string, args: Array<unknown>, node: AstNode): SafeObject => {
+  if (name !== "AggregateError") return createErrorValue(name, args[0] === undefined ? "" : coerceToString(args[0]))
+  const errors = spreadItems(args[0])
+  if (errors === undefined) {
+    throw new InterpreterRuntimeError(
+      "new AggregateError(...) expects an array of errors (e.g. new AggregateError(errors, message?)).",
+      node,
+    ).as("TypeError")
+  }
+  // Error values must not alias caller-owned arrays.
+  return createAggregateErrorValue([...errors], args[1] === undefined ? "" : coerceToString(args[1]))
+}

packages/codemode/src/interpreter/execute.ts

@@ -0,0 +1,224 @@
+import { parse } from "acorn"
+import { Cause, Effect, Scope } from "effect"
+import { DiagnosticCategory, ModuleKind, ScriptTarget, flattenDiagnosticMessageText, transpileModule } from "typescript"
+import type { DataValue, Diagnostic, ExecuteOptions, ResolvedExecutionLimits, Result } from "../codemode.js"
+import { copyIn, copyOut, ToolRuntime, type HostTools, type Services } from "../tool-runtime.js"
+import { normalizeError } from "./errors.js"
+import { InterpreterRuntimeError, isRecord, type ProgramNode } from "./model.js"
+import { PromiseRuntime } from "./promises.js"
+import { Interpreter } from "./runtime.js"
+
+export const executeWithLimits = <const Tools extends Record<string, unknown>>(
+  options: ExecuteOptions<Tools>,
+  limits: ResolvedExecutionLimits,
+  searchIndex: ToolRuntime.DiscoveryPlan["searchIndex"],
+): Effect.Effect<Result, never, Services<Tools>> => {
+  if (options.code.trim().length === 0) {
+    return Effect.succeed({
+      ok: false,
+      error: { kind: "ParseError", message: "Code cannot be empty." },
+      toolCalls: [],
+    })
+  }
+
+  // Allocate execution state inside suspension so reused Effects never share it.
+  return Effect.suspend(() => {
+    const tools = ToolRuntime.make(
+      (options.tools ?? {}) as HostTools<Services<Tools>>,
+      limits.maxToolCalls,
+      searchIndex,
+      {
+        onToolCallStart: options.onToolCallStart,
+        onToolCallEnd: options.onToolCallEnd,
+      },
+    )
+    const logs: Array<string> = []
+    const logged = () => (logs.length > 0 ? { logs: [...logs] } : {})
+    // Set only after copy-out so timeouts cannot report invalid values as completed.
+    let returned: { value: DataValue; promises: PromiseRuntime<Services<Tools>> } | undefined
+
+    const base = Effect.acquireUseRelease(
+      Scope.make("parallel"),
+      (scope) =>
+        Effect.gen(function* () {
+          const program = parseProgram(options.code)
+          const promises = new PromiseRuntime<Services<Tools>>(scope)
+          const interpreter = new Interpreter<Services<Tools>>(tools.invoke, tools.search, tools.keys, promises, logs)
+          const value = yield* interpreter.run(program)
+          const result = copyOut(copyIn(value, "Execution result"), true) as DataValue
+          returned = { value: result, promises }
+          const warnings = yield* promises.interrupt()
+          return {
+            ok: true,
+            value: result,
+            ...(warnings.length > 0 ? { warnings } : {}),
+            ...logged(),
+            toolCalls: tools.calls,
+          } satisfies Result
+        }),
+      (scope, exit) => Scope.close(scope, exit),
+    )
+    const timeoutMs = limits.timeoutMs
+    const operation =
+      timeoutMs === undefined
+        ? base
+        : base.pipe(
+            Effect.timeoutOrElse({
+              duration: timeoutMs,
+              orElse: () =>
+                Effect.sync(() => {
+                  if (returned === undefined) {
+                    return {
+                      ok: false,
+                      error: { kind: "TimeoutExceeded", message: `Execution timed out after ${timeoutMs}ms.` },
+                      ...logged(),
+                      toolCalls: tools.calls,
+                    } satisfies Result
+                  }
+                  // Keep the timeout warning first so truncation preserves it.
+                  return {
+                    ok: true,
+                    value: returned.value,
+                    warnings: [
+                      {
+                        kind: "TimeoutExceeded",
+                        message: `The program returned, but background work was still running at the ${timeoutMs}ms timeout and was interrupted. Await all started promises.`,
+                      },
+                      ...returned.promises.diagnostics(),
+                    ],
+                    ...logged(),
+                    toolCalls: tools.calls,
+                  } satisfies Result
+                }),
+            }),
+          )
+
+    return operation.pipe(
+      Effect.catchCause((cause) =>
+        Cause.hasInterruptsOnly(cause)
+          ? Effect.interrupt
+          : Effect.succeed({
+              ok: false,
+              error: normalizeError(Cause.squash(cause)),
+              ...logged(),
+              toolCalls: tools.calls,
+            } satisfies Result),
+      ),
+      Effect.map((result) =>
+        limits.maxOutputBytes === undefined ? result : boundOutput(result, limits.maxOutputBytes),
+      ),
+    )
+  })
+}
+
+const parseProgram = (code: string): ProgramNode => {
+  const transpiled = transpileModule(`async function __codemode__() {\n${code}\n}`, {
+    reportDiagnostics: true,
+    compilerOptions: {
+      target: ScriptTarget.ESNext,
+      module: ModuleKind.ESNext,
+    },
+  })
+  const diagnostic = transpiled.diagnostics?.find((item) => item.category === DiagnosticCategory.Error)
+
+  if (diagnostic) {
+    throw new InterpreterRuntimeError(
+      `Failed to parse TypeScript: ${flattenDiagnosticMessageText(diagnostic.messageText, "\n")}`,
+      undefined,
+      "ParseError",
+    )
+  }
+
+  const bodyStart = transpiled.outputText.indexOf("{") + 1
+  const bodyEnd = transpiled.outputText.lastIndexOf("}")
+  const executableCode = transpiled.outputText.slice(bodyStart, bodyEnd)
+  const parsed = parse(executableCode, {
+    ecmaVersion: "latest",
+    sourceType: "script",
+    allowReturnOutsideFunction: true,
+    allowAwaitOutsideFunction: true,
+    locations: true,
+  }) as unknown
+
+  if (!isRecord(parsed) || parsed.type !== "Program" || !Array.isArray(parsed.body)) {
+    throw new InterpreterRuntimeError("Failed to parse script as a Program node.")
+  }
+
+  return parsed as ProgramNode
+}
+
+const utf8ByteLength = (value: string): number => new TextEncoder().encode(value).byteLength
+
+// Drop a replacement character produced by truncating inside a UTF-8 sequence.
+const utf8Truncate = (value: string, maxBytes: number): string => {
+  const bytes = new TextEncoder().encode(value)
+  if (bytes.byteLength <= maxBytes) return value
+  const text = new TextDecoder("utf-8").decode(bytes.slice(0, Math.max(0, maxBytes)))
+  return text.endsWith("\uFFFD") ? text.slice(0, -1) : text
+}
+
+// Warnings have a separate budget so result data cannot starve diagnostics.
+const boundOutput = (result: Result, maxOutputBytes: number): Result => {
+  let truncated = false
+
+  let value: DataValue = null
+  let valueBytes = 0
+  if (result.ok) {
+    const serialized = JSON.stringify(result.value) ?? "null"
+    const bytes = utf8ByteLength(serialized)
+    if (bytes > maxOutputBytes) {
+      truncated = true
+      value = `${utf8Truncate(serialized, maxOutputBytes)} [result truncated: ${bytes} bytes exceeds the ${maxOutputBytes}-byte output limit; return a smaller value]`
+      valueBytes = maxOutputBytes
+    } else {
+      value = result.value
+      valueBytes = bytes
+    }
+  }
+
+  const warnings = result.ok ? (result.warnings ?? []) : []
+  const keptWarnings: Array<Diagnostic> = []
+  let warningBytes = 0
+  for (const warning of warnings) {
+    const bytes = utf8ByteLength(JSON.stringify(warning)) + 1
+    if (warningBytes + bytes > maxOutputBytes) break
+    warningBytes += bytes
+    keptWarnings.push(warning)
+  }
+  if (keptWarnings.length < warnings.length) {
+    truncated = true
+    keptWarnings.push({
+      kind: "Truncated",
+      message: `${warnings.length - keptWarnings.length} additional warnings omitted by the output limit.`,
+    })
+  }
+
+  const logs = result.logs ?? []
+  const kept: Array<string> = []
+  const logBudget = Math.max(0, maxOutputBytes - valueBytes)
+  let logBytes = 0
+  for (const line of logs) {
+    const lineBytes = utf8ByteLength(line) + 1
+    if (logBytes + lineBytes > logBudget) break
+    logBytes += lineBytes
+    kept.push(line)
+  }
+  if (kept.length < logs.length) {
+    truncated = true
+    kept.push(`[logs truncated: showing ${kept.length} of ${logs.length} lines]`)
+  }
+
+  if (!truncated) return result
+  const warningsPart = keptWarnings.length > 0 ? { warnings: keptWarnings } : {}
+  const logsPart = kept.length > 0 ? { logs: kept } : {}
+  return result.ok
+    ? {
+        ok: true,
+        value,
+        ...warningsPart,
+        ...logsPart,
+        truncated: true,
+        toolCalls: result.toolCalls,
+      }
+    : { ok: false, error: result.error, ...logsPart, truncated: true, toolCalls: result.toolCalls }
+}