mirror of
https://github.com/badlogic/pi-mono.git
synced 2026-11-05 23:37:25 +00:00
6536f80129
pi-schema: opt-in coercion, compile(schema, { coerce: true }) with coerce() and
parse(), the superset of TypeBox's Value.Convert rules and pi-ai's old coercion;
unresolvedRefs option; url and json-pointer-uri-fragment formats.
pi-ai: Tool takes any JSON Schema; validation through pi-schema; Type, Static
and TSchema are no longer exported (breaking). pi-agent-core and pi-durable:
tools on pi-schema, no TypeBox dependency. Coding agent: extensions keep Type,
Static, TSchema and StringEnum through an extension view of pi-ai; built-in
tools stay on TypeBox.
223 lines
10 KiB
TypeScript
223 lines
10 KiB
TypeScript
import type { Api, ImageContent, Model, ModelImageResizeOptions, TextContent } from "@earendil-works/pi-ai";
|
|
import { constants } from "fs";
|
|
import { access as fsAccess, readFile as fsReadFile } from "fs/promises";
|
|
import { type Static, Type } from "typebox";
|
|
import { processImage } from "../../utils/image-process.ts";
|
|
import { detectSupportedImageMimeTypeFromFile } from "../../utils/mime.ts";
|
|
import type { ExtensionContext, ToolDefinition } from "../extensions/types.ts";
|
|
import { resolveReadPathAsync } from "./path-utils.ts";
|
|
import { readRenderers } from "./renderers/read.ts";
|
|
import { type TypeBoxAgentTool, wrapToolDefinition } from "./tool-definition-wrapper.ts";
|
|
import { DEFAULT_MAX_BYTES, DEFAULT_MAX_LINES, formatSize, type TruncationResult, truncateHead } from "./truncate.ts";
|
|
|
|
const readSchema = Type.Object({
|
|
path: Type.String({ description: "Path to the file to read (relative or absolute)" }),
|
|
offset: Type.Optional(Type.Number({ description: "Line number to start reading from (1-indexed)" })),
|
|
limit: Type.Optional(Type.Number({ description: "Maximum number of lines to read" })),
|
|
});
|
|
|
|
export const readToolSystemPromptContribution = {
|
|
snippet: "Read file contents",
|
|
guidelines: ["Use read to examine files instead of cat or sed."],
|
|
} as const;
|
|
|
|
export type ReadToolInput = Static<typeof readSchema>;
|
|
|
|
/**
|
|
* Result for programmatic callers such as codemode scripts: the text for text files, and an image
|
|
* block for images that codemode's `image()` accepts. `note` is the text that goes with the image,
|
|
* such as resize hints. Property descriptions are left out so the type stays on one line in tool
|
|
* descriptions.
|
|
*/
|
|
const readOutputSchema = Type.Union([
|
|
Type.String(),
|
|
Type.Object({ type: Type.Literal("image"), data: Type.String(), mimeType: Type.String(), note: Type.String() }),
|
|
]);
|
|
|
|
export type ReadToolOutput = Static<typeof readOutputSchema>;
|
|
|
|
export interface ReadToolDetails {
|
|
truncation?: TruncationResult;
|
|
}
|
|
|
|
/**
|
|
* Pluggable operations for the read tool.
|
|
* Override these to delegate file reading to remote systems (for example SSH).
|
|
*/
|
|
export interface ReadOperations {
|
|
/** Read file contents as a Buffer */
|
|
readFile: (absolutePath: string) => Promise<Buffer>;
|
|
/** Check if file is readable (throw if not) */
|
|
access: (absolutePath: string) => Promise<void>;
|
|
/** Detect image MIME type, return null or undefined for non-images */
|
|
detectImageMimeType?: (absolutePath: string) => Promise<string | null | undefined>;
|
|
}
|
|
|
|
const defaultReadOperations: ReadOperations = {
|
|
readFile: (path) => fsReadFile(path),
|
|
access: (path) => fsAccess(path, constants.R_OK),
|
|
detectImageMimeType: detectSupportedImageMimeTypeFromFile,
|
|
};
|
|
|
|
export interface ReadToolOptions {
|
|
/** Whether to auto-resize images. Default: true */
|
|
autoResizeImages?: boolean;
|
|
/** Fallback resize profile when the execution context has no model metadata. */
|
|
resizeOptions?: ModelImageResizeOptions;
|
|
/** Custom operations for file reading. Default: local filesystem */
|
|
operations?: ReadOperations;
|
|
}
|
|
|
|
/** The image block and its note, or the text for text files and images that could not be processed. */
|
|
function toReadOutput(content: (TextContent | ImageContent)[]): ReadToolOutput {
|
|
const text = content.find((block) => block.type === "text")?.text ?? "";
|
|
const image = content.find((block) => block.type === "image");
|
|
return image ? { type: "image", data: image.data, mimeType: image.mimeType, note: text } : text;
|
|
}
|
|
|
|
function getNonVisionImageNote(model: Model<Api> | undefined): string | undefined {
|
|
if (!model || model.input.includes("image")) {
|
|
return undefined;
|
|
}
|
|
return "[Current model does not support images. The image will be omitted from this request.]";
|
|
}
|
|
|
|
export function createReadToolDefinition(
|
|
cwd: string,
|
|
options?: ReadToolOptions,
|
|
): ToolDefinition<typeof readSchema, ReadToolDetails | undefined> {
|
|
const autoResizeImages = options?.autoResizeImages ?? true;
|
|
const fallbackResizeOptions = options?.resizeOptions;
|
|
const ops = options?.operations ?? defaultReadOperations;
|
|
return {
|
|
name: "read",
|
|
label: "read",
|
|
description: `Read the contents of a file. Supports text files and images (jpg, png, gif, webp, bmp). Images are sent as attachments. For text files, output is truncated to ${DEFAULT_MAX_LINES} lines or ${DEFAULT_MAX_BYTES / 1024}KB (whichever is hit first). Use offset/limit for large files. When you need the full file, continue with offset until complete.`,
|
|
promptSnippet: readToolSystemPromptContribution.snippet,
|
|
promptGuidelines: [...readToolSystemPromptContribution.guidelines],
|
|
parameters: readSchema,
|
|
outputSchema: readOutputSchema,
|
|
constrainedSampling: { type: "json_schema", strict: "prefer" },
|
|
async execute(
|
|
_toolCallId,
|
|
{ path, offset, limit }: { path: string; offset?: number; limit?: number },
|
|
signal?: AbortSignal,
|
|
_onUpdate?,
|
|
ctx?: ExtensionContext,
|
|
) {
|
|
return new Promise<{ content: (TextContent | ImageContent)[]; details: ReadToolDetails | undefined }>(
|
|
(resolve, reject) => {
|
|
if (signal?.aborted) {
|
|
reject(new Error("Operation aborted"));
|
|
return;
|
|
}
|
|
let aborted = false;
|
|
const onAbort = () => {
|
|
aborted = true;
|
|
reject(new Error("Operation aborted"));
|
|
};
|
|
signal?.addEventListener("abort", onAbort, { once: true });
|
|
|
|
(async () => {
|
|
try {
|
|
const absolutePath = await resolveReadPathAsync(path, ctx?.cwd || cwd);
|
|
if (aborted) return;
|
|
// Check if file exists and is readable.
|
|
await ops.access(absolutePath);
|
|
if (aborted) return;
|
|
const mimeType = ops.detectImageMimeType ? await ops.detectImageMimeType(absolutePath) : undefined;
|
|
let content: (TextContent | ImageContent)[];
|
|
let details: ReadToolDetails | undefined;
|
|
const nonVisionImageNote = getNonVisionImageNote(ctx?.model);
|
|
if (mimeType) {
|
|
// Read image as binary.
|
|
const buffer = await ops.readFile(absolutePath);
|
|
const processed = await processImage(buffer, mimeType, {
|
|
autoResizeImages,
|
|
resizeOptions: ctx?.model?.inputLimits?.images?.resize ?? fallbackResizeOptions,
|
|
});
|
|
if (!processed.ok) {
|
|
let textNote = `Read image file [${mimeType}]\n${processed.message}`;
|
|
if (nonVisionImageNote) textNote += `\n${nonVisionImageNote}`;
|
|
content = [{ type: "text", text: textNote }];
|
|
} else {
|
|
let textNote = `Read image file [${processed.mimeType}]`;
|
|
if (processed.hints.length > 0) textNote += `\n${processed.hints.join("\n")}`;
|
|
if (nonVisionImageNote) textNote += `\n${nonVisionImageNote}`;
|
|
content = [
|
|
{ type: "text", text: textNote },
|
|
{ type: "image", data: processed.data, mimeType: processed.mimeType },
|
|
];
|
|
}
|
|
} else {
|
|
// Read text content.
|
|
const buffer = await ops.readFile(absolutePath);
|
|
const textContent = buffer.toString("utf-8");
|
|
const allLines = textContent.split("\n");
|
|
const totalFileLines = allLines.length;
|
|
// Apply offset if specified. Convert from 1-indexed input to 0-indexed array access.
|
|
const startLine = offset ? Math.max(0, offset - 1) : 0;
|
|
const startLineDisplay = startLine + 1;
|
|
// Check if offset is out of bounds.
|
|
if (startLine >= allLines.length) {
|
|
throw new Error(`Offset ${offset} is beyond end of file (${allLines.length} lines total)`);
|
|
}
|
|
let selectedContent: string;
|
|
let userLimitedLines: number | undefined;
|
|
// If limit is specified by the user, honor it first. Otherwise truncateHead decides.
|
|
if (limit !== undefined) {
|
|
const endLine = Math.min(startLine + limit, allLines.length);
|
|
selectedContent = allLines.slice(startLine, endLine).join("\n");
|
|
userLimitedLines = endLine - startLine;
|
|
} else {
|
|
selectedContent = allLines.slice(startLine).join("\n");
|
|
}
|
|
// Apply truncation, respecting both line and byte limits.
|
|
const truncation = truncateHead(selectedContent);
|
|
let outputText: string;
|
|
if (truncation.firstLineExceedsLimit) {
|
|
// First line alone exceeds the byte limit. Point the model at a bash fallback.
|
|
const firstLineSize = formatSize(Buffer.byteLength(allLines[startLine], "utf-8"));
|
|
outputText = `[Line ${startLineDisplay} is ${firstLineSize}, exceeds ${formatSize(DEFAULT_MAX_BYTES)} limit. Use bash: sed -n '${startLineDisplay}p' ${path} | head -c ${DEFAULT_MAX_BYTES}]`;
|
|
details = { truncation };
|
|
} else if (truncation.truncated) {
|
|
// Truncation occurred. Build an actionable continuation notice.
|
|
const endLineDisplay = startLineDisplay + truncation.outputLines - 1;
|
|
const nextOffset = endLineDisplay + 1;
|
|
outputText = truncation.content;
|
|
if (truncation.truncatedBy === "lines") {
|
|
outputText += `\n\n[Showing lines ${startLineDisplay}-${endLineDisplay} of ${totalFileLines}. Use offset=${nextOffset} to continue.]`;
|
|
} else {
|
|
outputText += `\n\n[Showing lines ${startLineDisplay}-${endLineDisplay} of ${totalFileLines} (${formatSize(DEFAULT_MAX_BYTES)} limit). Use offset=${nextOffset} to continue.]`;
|
|
}
|
|
details = { truncation };
|
|
} else if (userLimitedLines !== undefined && startLine + userLimitedLines < allLines.length) {
|
|
// User-specified limit stopped early, but the file still has more content.
|
|
const remaining = allLines.length - (startLine + userLimitedLines);
|
|
const nextOffset = startLine + userLimitedLines + 1;
|
|
outputText = `${truncation.content}\n\n[${remaining} more lines in file. Use offset=${nextOffset} to continue.]`;
|
|
} else {
|
|
// No truncation and no remaining user-limited content.
|
|
outputText = truncation.content;
|
|
}
|
|
content = [{ type: "text", text: outputText }];
|
|
}
|
|
|
|
if (aborted) return;
|
|
signal?.removeEventListener("abort", onAbort);
|
|
resolve({ content, details });
|
|
} catch (error: any) {
|
|
signal?.removeEventListener("abort", onAbort);
|
|
if (!aborted) reject(error);
|
|
}
|
|
})();
|
|
},
|
|
).then((result) => ({ ...result, structuredContent: toReadOutput(result.content) }));
|
|
},
|
|
...readRenderers,
|
|
};
|
|
}
|
|
|
|
export function createReadTool(cwd: string, options?: ReadToolOptions): TypeBoxAgentTool<typeof readSchema> {
|
|
return wrapToolDefinition(createReadToolDefinition(cwd, options));
|
|
}
|