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
+46
-34
@@ -1,5 +1,6 @@
|
||||
import { Agent } from "@earendil-works/pi-agent-core";
|
||||
import type { AgentEvent, AgentMessage, AgentTool } from "@earendil-works/pi-agent-core";
|
||||
import { questionResult, ToolInputError } from "./tool-execute.ts";
|
||||
import type { Usage } from "@earendil-works/pi-ai";
|
||||
import { PATHS } from "../../config.ts";
|
||||
import { piEngineFor, type PiEngine } from "./models.ts";
|
||||
@@ -12,7 +13,6 @@ import {
|
||||
type ProberToolContext,
|
||||
type TeacherToolContext,
|
||||
} from "./tools.ts";
|
||||
import { toPiTools, type LhTool } from "./lh-tool.ts";
|
||||
import { quizInputObject, quizInputProblems } from "../core/question-core.ts";
|
||||
import { QUESTION_TOOLS, type EnabledTools } from "../core/pending.ts";
|
||||
|
||||
@@ -93,11 +93,9 @@ export interface AgentBuildOptions {
|
||||
messages?: AgentMessage[];
|
||||
/** Money channel: one call per model request. */
|
||||
onUsage?: StepUsageCollector;
|
||||
/** Safety net (the old stepCountIs). Default 20 turns. */
|
||||
maxTurns?: number;
|
||||
/** Tests may pass a bare tool registry to drive deterministic flows.
|
||||
* An explicit registry is NEVER toggle-filtered — the caller owns it. */
|
||||
tools?: Record<string, LhTool<any, any>>;
|
||||
tools?: Record<string, AgentTool<any>>;
|
||||
/** The resolved per-user tool toggles (core/pending EnabledTools — the
|
||||
* 2026-09-19 P2 bridge: Platform's chat-handler passes
|
||||
* effective.agent.tools; the factories drop any tool explicitly false.
|
||||
@@ -113,22 +111,29 @@ export interface AgentBuildOptions {
|
||||
}
|
||||
|
||||
/**
|
||||
* The turn's stop rule (docs/pi-engine-swap.md §2):
|
||||
* - a question tool call (quiz / ask_user_question) that RESOLVED — its
|
||||
* synthetic "question posed" result is not an error — ends the run: the
|
||||
* learner's answer arrives as the next POST. A call that FAILED authoring
|
||||
* validation (error result) must NOT stop the run — the model retries
|
||||
* within the same turn, exactly the InvalidToolInputError semantics.
|
||||
* - the maxTurns safety net replaces stepCountIs(20).
|
||||
* The turn's question-stop rule (docs/pi-engine-swap.md §2; Wave A
|
||||
* 2026-09-26, owner Option A): a question tool call (quiz /
|
||||
* ask_user_question) that RESOLVED — its synthetic "question posed" result
|
||||
* is not an error — ends the run: the learner's answer arrives as the next
|
||||
* POST. A call that FAILED authoring validation (error result) must NOT
|
||||
* stop the run — the model retries within the same turn, exactly the old
|
||||
* InvalidToolInputError semantics.
|
||||
*
|
||||
* Question results also carry terminate: true (tool-execute's
|
||||
* questionResult), so single-question batches stop natively at the pi
|
||||
* loop's own batch check; this shouldStopAfterTurn hook is the
|
||||
* belt-and-suspenders HALF for the mixed batch (a question + other calls
|
||||
* in one message) that terminate-only semantics would let run on — the
|
||||
* learner cannot answer while a turn is in flight (per-chat 409), so a
|
||||
* cleanly-posed question MUST always end the turn. maxTurns is gone
|
||||
* (owner ruling 2026-09-25: no maximum-agent-turns net on the teaching
|
||||
* turn).
|
||||
*/
|
||||
function makeStopper(maxTurns: number) {
|
||||
let turns = 0;
|
||||
function makeQuestionStopper() {
|
||||
return (context: {
|
||||
message: { content: Array<{ type: string; id?: string; name?: string }> };
|
||||
toolResults: Array<{ toolCallId: string; isError?: boolean }>;
|
||||
}): boolean => {
|
||||
turns++;
|
||||
if (turns >= maxTurns) return true;
|
||||
const called = new Set(
|
||||
context.message.content
|
||||
.filter((c) => c.type === "toolCall" && c.name !== undefined && (QUESTION_TOOLS as readonly string[]).includes(c.name!))
|
||||
@@ -145,7 +150,7 @@ function makeStopper(maxTurns: number) {
|
||||
|
||||
function baseAgentOptions(kind: AgentKind, opts: AgentBuildOptions, tools: AgentTool<any, any>[]) {
|
||||
const engine = opts.engine ?? piEngineFor(kind);
|
||||
const stopper = makeStopper(opts.maxTurns ?? 20);
|
||||
const stopper = makeQuestionStopper();
|
||||
const systemPrompt = opts.promptSwitches
|
||||
? composeInstructions(kind, opts.promptSwitches)
|
||||
: composedInstructions[kind]!;
|
||||
@@ -181,7 +186,7 @@ function baseAgentOptions(kind: AgentKind, opts: AgentBuildOptions, tools: Agent
|
||||
* handler keys teacher construction on.
|
||||
*/
|
||||
export function createProberAgent(ctx: ProberToolContext, opts: AgentBuildOptions = {}) {
|
||||
return baseAgentOptions("prober", opts, toPiTools(createProberTools(ctx, opts.toolToggles)));
|
||||
return baseAgentOptions("prober", opts, Object.values(createProberTools(ctx, opts.toolToggles)));
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -197,26 +202,33 @@ export function createTeacherAgent(
|
||||
ctx?: TeacherToolContext,
|
||||
opts: AgentBuildOptions = {},
|
||||
) {
|
||||
const tools =
|
||||
opts.tools ?? (ctx ? createTeacherTools(ctx, opts.toolToggles) : bareQuestionTools());
|
||||
return baseAgentOptions("teacher", opts, toPiTools(tools));
|
||||
const tools = opts.tools ?? (ctx ? createTeacherTools(ctx, opts.toolToggles) : bareQuestionTools());
|
||||
return baseAgentOptions("teacher", opts, Object.values(tools));
|
||||
}
|
||||
|
||||
/** The validation-free teach question set (tests, bare agents): quiz with
|
||||
* the shared authoring refinement but NO per-session nodeId check (no
|
||||
* record to read), plus ask. */
|
||||
export function bareQuestionTools(): Record<string, LhTool<any, any>> {
|
||||
return {
|
||||
quiz: {
|
||||
name: "quiz",
|
||||
description: "Ask the learner a graded question.",
|
||||
clientQuestion: true,
|
||||
schema: quizInputObject.superRefine((input, add) => {
|
||||
for (const problem of quizInputProblems(input)) {
|
||||
add.addIssue({ code: "custom", message: problem });
|
||||
}
|
||||
}),
|
||||
/** The bare teach question set (tests, bare agents): quiz with the shared
|
||||
* authoring refinement (quizInputProblems, run in execute — throws
|
||||
* ToolInputError, which pi's loop converts to the error tool result the
|
||||
* model retries on) but NO per-session nodeId check (no record to read),
|
||||
* plus ask. */
|
||||
export function bareQuestionTools(): Record<string, AgentTool<any>> {
|
||||
// A typed const (not an inline literal): the specific AgentTool typing
|
||||
// gives execute its precise Static input; heterogeneous records take
|
||||
// AgentTool<any>, whose loose Static would smudge it to unknown.
|
||||
const quiz: AgentTool<typeof quizInputObject> = {
|
||||
name: "quiz",
|
||||
label: "quiz",
|
||||
description: "Ask the learner a graded question.",
|
||||
parameters: quizInputObject,
|
||||
executionMode: "sequential",
|
||||
execute: async (_toolCallId, input) => {
|
||||
const problems = quizInputProblems(input);
|
||||
if (problems.length > 0) throw new ToolInputError("quiz", problems);
|
||||
return questionResult();
|
||||
},
|
||||
};
|
||||
return {
|
||||
quiz,
|
||||
ask_user_question: askUserQuestionTool,
|
||||
};
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user