feat(T2b): sources v0 — read tool + pdf-reader sub-agent
Learner source files, on the teacher's own terms (nothing auto-injects): - read tool (src/agent/tools/read.ts): pi-read port — path/offset/limit, 2000-line/50KB truncation with use-offset continuation notices, image files (jpg/png/gif/webp/bmp) returned as native image content parts (new LhToolImageResult escape hatch in lh-tool.ts). Always-on in both the prober and teacher registries (user-decided 2026-09). - pdf-reader sub-agent (JobKind 'pdf', toggleable, ack-and-steer): triage via pdf_info (pdfjs text layer: per-page text/image/math-density), targeted pdf_extract, regex pdf_search (hits count as consultation), and pdf_render — pages painted by pdfjs onto a canvas shim in headless Chrome (the pdfium viewer doesn't paint headless), screenshot fed back image-in-the-loop (visual-maker idiom, providerSafePng applied). The unread-finish gate bounces a zero-consultation brief once. Teacher gets a text brief with page citations only; renders never leave the loop. - MODELS.pdfReader = qwen/qwen3.8-flash (user override 2026-09-19: the look-at-renders workload wants the vision-proven model; catalog listed glm-5.3-flash as image-capable but qwen is the known-good daily driver). - UI: PdfCompleteBadge + PdfBriefCard (steer-card, job-card), dispatch card + activity-dock kind entries (type-forced, flagged for UI review). - Prompts: 'Learner source files' section in teacher/30-jobs.md; read line in prober/10-probe-doctrine.md. Doctrine rides tool descriptions per the self-contained-tools principle.
This commit is contained in:
+28
-2
@@ -21,7 +21,7 @@ export interface JobToolContext {
|
||||
/** Fire the background runner for a fresh job — fire-and-forget. The
|
||||
* input rides along because the spawn happens MID-STREAM, before
|
||||
* onFinish persists the tool part — a transcript scan would race it. */
|
||||
spawn: (job: JobRecord, input: ResearchInput | DemoInput | VisualInput) => void;
|
||||
spawn: (job: JobRecord, input: ResearchInput | DemoInput | VisualInput | PdfInput) => void;
|
||||
}
|
||||
|
||||
export const researchInputSchema = z.object({
|
||||
@@ -53,6 +53,16 @@ export const visualInputSchema = z.object({
|
||||
),
|
||||
});
|
||||
|
||||
export const pdfInputSchema = z.object({
|
||||
path: z.string().describe("Path to the learner's PDF (relative or absolute), exactly as they gave it."),
|
||||
question: z
|
||||
.string()
|
||||
.describe(
|
||||
"What you need from the document — the specific content, explanation, or answer to extract and brief. " +
|
||||
"The reader sees NOTHING else of the lesson.",
|
||||
),
|
||||
});
|
||||
|
||||
/**
|
||||
* The per-call dispatch: create the job (idempotent by toolCallId), fire the
|
||||
* runner, and return the ack. Shared by all three tools — only kind differs.
|
||||
@@ -62,7 +72,7 @@ function dispatch(
|
||||
kind: JobRecord["kind"],
|
||||
toolCallId: string,
|
||||
ack: string,
|
||||
input: ResearchInput | DemoInput | VisualInput,
|
||||
input: ResearchInput | DemoInput | VisualInput | PdfInput,
|
||||
): string {
|
||||
const existing = ctx.jobStore.findJobByToolCallId(ctx.chatId, toolCallId);
|
||||
const job = existing ?? ctx.jobStore.createJob({ kind, chatId: ctx.chatId, toolCallId });
|
||||
@@ -79,6 +89,9 @@ const DEMO_ACK =
|
||||
const VISUAL_ACK =
|
||||
"This call is fire-and-forget: continue your turn and keep teaching — do not wait, poll, or mention waiting. " +
|
||||
"The verified figure arrives as a new message when ready and is rendered in the lesson; reference it then.";
|
||||
const PDF_ACK =
|
||||
"This call is fire-and-forget: continue your turn and keep teaching — do not wait, poll, or mention waiting. " +
|
||||
"The document brief arrives as a new message when ready; weave it into the lesson and cite its pages.";
|
||||
|
||||
const RESEARCH_DESCRIPTION =
|
||||
"Dispatch a background web-research agent: fact verification, current data, or niche specifics you are not certain about. " +
|
||||
@@ -97,6 +110,12 @@ const VISUAL_DESCRIPTION =
|
||||
"function plots, physical layouts. For flows/relations/taxonomies write mermaid inline instead. " +
|
||||
"The call is ASYNC and fire-and-forget — it resolves immediately and your turn continues; the verified figure arrives later " +
|
||||
"as a new message.";
|
||||
const PDF_DESCRIPTION =
|
||||
"Dispatch a background sub-agent that READS a learner-provided PDF on your behalf (triage, targeted extraction, visual page " +
|
||||
"reading for equations and diagrams) and returns a brief with page citations. Use it when the learner gives you a PDF path " +
|
||||
"and you need its CONTENT for the lesson. The call is ASYNC and fire-and-forget — it resolves immediately and your turn " +
|
||||
"continues; the brief arrives later as a new message. For quick looks at plain text or image files, use the read tool " +
|
||||
"directly instead of dispatching.";
|
||||
|
||||
/**
|
||||
* Per-request job tool registry: each tool closes over the composition root's
|
||||
@@ -123,9 +142,16 @@ export function jobTools(ctx: JobToolContext): Record<string, LhTool<any, any>>
|
||||
schema: visualInputSchema,
|
||||
execute: async (input, { toolCallId }) => dispatch(ctx, "visual", toolCallId, VISUAL_ACK, input),
|
||||
}),
|
||||
pdf: lhTool({
|
||||
name: "pdf",
|
||||
description: PDF_DESCRIPTION,
|
||||
schema: pdfInputSchema,
|
||||
execute: async (input, { toolCallId }) => dispatch(ctx, "pdf", toolCallId, PDF_ACK, input),
|
||||
}),
|
||||
};
|
||||
}
|
||||
|
||||
export type ResearchInput = z.infer<typeof researchInputSchema>;
|
||||
export type DemoInput = z.infer<typeof demoInputSchema>;
|
||||
export type VisualInput = z.infer<typeof visualInputSchema>;
|
||||
export type PdfInput = z.infer<typeof pdfInputSchema>;
|
||||
|
||||
Reference in New Issue
Block a user