Wave A: pi-native tool layer — delete LhTool/toPiTool, TypeBox everywhere, terminate on questions
- src/agent/lh-tool.ts deleted: the zod-wrapped LhTool + toPiTool bridge (z.toJSONSchema per call, clientQuestion flag, hand-rolled result mapping) is gone. Tools are pi-agent-core native AgentTools now. - New src/agent/tool-execute.ts owns what the wrapper added: the abort guard (runWithAbortGuard: run signal + 30s per-call timeout + 250ms grace, 'Operation aborted' / timeout wording preserved), ToolInputError (the retryable '- problem at path' format), result mapping (string verbatim / object JSON / image parts, details rides the record's tool part output), and questionResult() — placeholder + terminate:true (owner Option A: belt of terminate + slim makeQuestionStopper with the clean-question rule; maxTurns deleted from the teaching turn entirely per owner). - All 11 tool files + tools.ts registries converted to TypeBox parameters (typebox@1.3.7, pinned to pi-agent-core's copy). zod refinements (quizInputProblems, askOptionProblems, live-nodeId) moved from schemas into execute — the model sees the same retryable error shape. - question-core + contracts/probe TypeBox-authored (single source shared with the UI); tool-parts parse seam runs the boundary's full chain (Convert → Check → Clean → refinement), fixing the live-smoke lockout: pi's boundary Value.Converts correctAnswer: 17 → '17' but the record keeps raw args, so a parse without Convert rejected a posed quiz (invisible pending question, turn ended). Pinned with the real smoke emission shape. - Subagents converted: demo-builder/researcher AgentTool-native, visual-maker/pdf-reader declaration-only pi-ai Tools with local execute fns, extraction submit schemas re-authored in TypeBox (owner option 2: zod defaults → Type.Optional + fill at the submit seam). - Accepted delta, flagged: TypeBox-native schemas skip pi's JSON-Schema primitive coercion fast path... (boundary still Value.Converts), and prober-quiz unknown keys ride through (Value.Clean strips at display). - Tests: 988 passing (was 967 at the recon baseline); tool-abort and read-tool rewritten against the native seams; question-core/question- tools/tool-parts/demos/web-search/graph-tools/plan-tree/probe-done/ tool-toggles converted to Value.Check/execute pins. Live smoke (PORT=3004, real model): native ls turn streams end-to-end; a real quiz pose (first attempt missing correctAnswer → tool-input-error → model retry → posed) terminates the turn cleanly and persists pending.
This commit is contained in:
amosblomqvist
@@ -1,6 +1,5 @@
|
||||
import type { AssistantMessage, Message, ToolResultMessage, Usage } from "@earendil-works/pi-ai";
|
||||
import { z } from "zod";
|
||||
import { lhTool, piToolDeclarations, type LhTool } from "../lh-tool.ts";
|
||||
import type { AssistantMessage, Message, ToolResultMessage, Usage, Tool } from "@earendil-works/pi-ai";
|
||||
import { Type } from "typebox";
|
||||
import { piEngineFor, type PiEngine, type ThinkingLevel } from "../models.ts";
|
||||
import type { PdfResult, PdfToolInput } from "../../core/contracts.ts";
|
||||
import { getHeadless, type HeadlessApi } from "./headless.ts";
|
||||
@@ -70,79 +69,75 @@ export interface PdfReaderOptions {
|
||||
|
||||
export interface PdfReaderInput extends PdfToolInput {}
|
||||
|
||||
export function createPdfTools(
|
||||
pdfPath: string,
|
||||
): {
|
||||
pdf_info: LhTool<any, any>;
|
||||
pdf_extract: LhTool<any, any>;
|
||||
pdf_render: LhTool<any, any>;
|
||||
pdf_search: LhTool<any, any>;
|
||||
} {
|
||||
/** The wire declarations (pi-ai Tool, TypeBox parameters). This loop owns
|
||||
* execution itself — pdf_info/pdf_extract run via the plain pdfInfoText/
|
||||
* pdfExtractText bodies below, pdf_search/pdf_render dispatch inline in
|
||||
* the loop (search hits must join the citation set; renders feed the
|
||||
* image-in-the-loop message) — so the declarations carry no execute.
|
||||
* dpi/context_lines/literal carry the old zod `.default()`s as schema
|
||||
* descriptions + loop-side ??-fills (the loop reads them via numOr). */
|
||||
export function createPdfTools(_pdfPath: string): Record<string, Tool> {
|
||||
return {
|
||||
pdf_info: lhTool({
|
||||
pdf_info: {
|
||||
name: "pdf_info",
|
||||
description: "Metadata + per-page triage signals for the PDF (page count, text length, image count, math density). ALWAYS call this first.",
|
||||
schema: z.object({}),
|
||||
execute: async () => {
|
||||
const info = await pdfInfo(pdfPath);
|
||||
const lines = [
|
||||
`File: ${info.path}`,
|
||||
`Pages: ${info.page_count} (mean text length/page: ${info.mean_text_length})`,
|
||||
...info.pages.map(
|
||||
(p) =>
|
||||
`p${p.page}: len=${p.text_length} img=${p.image_count} math=${p.math_density.toFixed(2)}`,
|
||||
),
|
||||
];
|
||||
return lines.join("\n");
|
||||
},
|
||||
}),
|
||||
pdf_extract: lhTool({
|
||||
parameters: Type.Object({}),
|
||||
},
|
||||
pdf_extract: {
|
||||
name: "pdf_extract",
|
||||
description: "Extract text from pages (spec: 'all', '1-5', '1,3,7', '3'). Use pdf_info first; narrow the spec for big documents.",
|
||||
schema: z.object({ pages: z.string().describe("Page spec, e.g. 'all', '1-5', '1,3,7'") }),
|
||||
execute: async ({ pages }) => {
|
||||
const text = await pdfExtract(pdfPath, pages);
|
||||
if (text.length > EXTRACT_CAP) {
|
||||
return `${text.slice(0, EXTRACT_CAP)}\n\n[Output truncated at ${EXTRACT_CAP} chars — narrow the page spec and extract in smaller batches.]`;
|
||||
}
|
||||
return text;
|
||||
},
|
||||
}),
|
||||
pdf_render: lhTool({
|
||||
parameters: Type.Object({
|
||||
pages: Type.String({ description: "Page spec, e.g. 'all', '1-5', '1,3,7'" }),
|
||||
}),
|
||||
},
|
||||
pdf_render: {
|
||||
name: "pdf_render",
|
||||
description:
|
||||
"Render pages to images and show them to you for visual reading (equations, diagrams, layout). DPI: 100 text, 150 default, 200 dense small print. Max 6 pages per call.",
|
||||
schema: z.object({
|
||||
pages: z.string().describe("Page spec, e.g. '1-3' or '2,5,8'"),
|
||||
dpi: z.number().int().min(72).max(300).default(150).describe("Render DPI (100 text / 150 default / 200 dense)"),
|
||||
parameters: Type.Object({
|
||||
pages: Type.String({ description: "Page spec, e.g. '1-3' or '2,5,8'" }),
|
||||
dpi: Type.Optional(
|
||||
Type.Integer({ minimum: 72, maximum: 300, description: "Render DPI (100 text / 150 default / 200 dense)" }),
|
||||
),
|
||||
}),
|
||||
execute: async () => {
|
||||
// Actual rendering happens OUTSIDE execute — the loop appends the
|
||||
// images as a user message after the tool results (the
|
||||
// image-in-the-loop idiom). execute returns the plan the loop uses.
|
||||
return "render requested";
|
||||
},
|
||||
}),
|
||||
pdf_search: lhTool({
|
||||
},
|
||||
pdf_search: {
|
||||
name: "pdf_search",
|
||||
description: "Search the PDF's text by keyword or regex (case-insensitive); returns hits with context lines. Use for long documents before reading anything at length.",
|
||||
schema: z.object({
|
||||
query: z.string().describe("Keyword or regex"),
|
||||
context_lines: z.number().int().min(0).max(8).default(3).describe("Context lines around each hit"),
|
||||
literal: z.boolean().default(false).describe("true = treat the query literally (no regex)"),
|
||||
parameters: Type.Object({
|
||||
query: Type.String({ description: "Keyword or regex" }),
|
||||
context_lines: Type.Optional(
|
||||
Type.Integer({ minimum: 0, maximum: 8, description: "Context lines around each hit (default 3)" }),
|
||||
),
|
||||
literal: Type.Optional(Type.Boolean({ description: "true = treat the query literally (no regex; default false)" })),
|
||||
}),
|
||||
execute: async ({ query, context_lines, literal }) => {
|
||||
const { hits } = await pdfSearch(pdfPath, query, { contextLines: context_lines, literal });
|
||||
if (hits.length === 0) return "No hits.";
|
||||
const cap = hits.slice(0, 40);
|
||||
const body = cap.map((h: PdfSearchHit) => `=== Page ${h.page}, line ${h.line} ===\n${h.context}`).join("\n");
|
||||
const more = hits.length > cap.length ? `\n\n[${hits.length - cap.length} more hits — narrow the query.]` : "";
|
||||
return body + more;
|
||||
},
|
||||
}),
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
/** pdf_info's body (the loop's dispatch target): the triage readout. */
|
||||
async function pdfInfoText(pdfPath: string): Promise<string> {
|
||||
const info = await pdfInfo(pdfPath);
|
||||
const lines = [
|
||||
`File: ${info.path}`,
|
||||
`Pages: ${info.page_count} (mean text length/page: ${info.mean_text_length})`,
|
||||
...info.pages.map(
|
||||
(p) =>
|
||||
`p${p.page}: len=${p.text_length} img=${p.image_count} math=${p.math_density.toFixed(2)}`,
|
||||
),
|
||||
];
|
||||
return lines.join("\n");
|
||||
}
|
||||
|
||||
/** pdf_extract's body: capped text extraction with the narrow-the-spec notice. */
|
||||
async function pdfExtractText(pdfPath: string, pages: string): Promise<string> {
|
||||
const text = await pdfExtract(pdfPath, pages);
|
||||
if (text.length > EXTRACT_CAP) {
|
||||
return `${text.slice(0, EXTRACT_CAP)}\n\n[Output truncated at ${EXTRACT_CAP} chars — narrow the page spec and extract in smaller batches.]`;
|
||||
}
|
||||
return text;
|
||||
}
|
||||
|
||||
function toolText(toolCallId: string, toolName: string, value: string): ToolResultMessage {
|
||||
return {
|
||||
role: "toolResult",
|
||||
@@ -179,7 +174,7 @@ export async function runPdfReaderAgent(
|
||||
// doctrine degrades to extract+search (render calls return an error note).
|
||||
|
||||
const tools = createPdfTools(pdfPath);
|
||||
const toolDeclarations = piToolDeclarations(tools);
|
||||
const toolDeclarations = Object.values(tools);
|
||||
const engine = opts.engine ?? piEngineFor("pdfReader");
|
||||
// BYOK (owner, 2026-09-22): the level rides the injected engine — no
|
||||
// factory pin to consult (engine.level is the resolved/clamped value).
|
||||
@@ -242,12 +237,12 @@ export async function runPdfReaderAgent(
|
||||
try {
|
||||
if (call.name === "pdf_info") {
|
||||
opts.onActivity?.("pdf_info: triaging");
|
||||
const r = await tools.pdf_info.execute!({}, { toolCallId: call.id });
|
||||
const r = await pdfInfoText(pdfPath);
|
||||
toolResults.push(toolText(call.id, call.name, String(r)));
|
||||
} else if (call.name === "pdf_extract") {
|
||||
const spec = String(args.pages ?? "all");
|
||||
opts.onActivity?.(`pdf_extract: ${spec}`);
|
||||
const r = await tools.pdf_extract.execute!({ pages: spec }, { toolCallId: call.id });
|
||||
const r = await pdfExtractText(pdfPath, spec);
|
||||
toolResults.push(toolText(call.id, call.name, String(r)));
|
||||
for (const p of specNumbers(spec, Infinity)) {
|
||||
consulted.add(p);
|
||||
@@ -393,7 +388,7 @@ async function streamOnce(
|
||||
engine: PiEngine,
|
||||
systemPrompt: string,
|
||||
messages: Message[],
|
||||
tools: ReturnType<typeof piToolDeclarations>,
|
||||
tools: Tool[],
|
||||
reasoning: ThinkingLevel | undefined,
|
||||
abortSignal?: AbortSignal,
|
||||
): Promise<AssistantMessage> {
|
||||
|
||||
Reference in New Issue
Block a user