amosblomqvist
2d717fd932
The Vercel AI SDK survives only as Band D (useChat client + UIMessage
record types); @openrouter/ai-sdk-provider is uninstalled.
- src/agent/models.ts: PiEngine {model, streamFn} via createModels +
openrouterProvider subpath; thinkingLevelFor maps config effort none->off
- src/agent/lh-tool.ts: neutral LhTool (zod authoring, optional execute,
clientQuestion flag); toPiTool converts via z.toJSONSchema and re-runs
zod inside execute so refinements ride the error-result retry path
- src/server/pi/record-adapter.ts: UIMessage records -> pi Messages
(dangling tool calls get synthesized interrupted results)
- src/server/pi/ui-stream.ts: SSE bridge emitting AI-SDK-shaped chunks so
the useChat client parses unchanged (continuation id rule, question
tools never emit output, tool-input-error for bad authoring)
- teacher-agent.ts: stateless per-turn pi Agents; shouldStopAfterTurn
stops only when every question-tool call resolved cleanly (errors retry)
- chat-handler.ts: buildAgent(outgoing) factory seam (stateless doctrine);
assertValidUiMessages owns the retired SDK validation gate
- sub-agents via shared runSubagent (pi-run.ts); extraction stages stop
after a clean submit; visual-maker keeps its hand-rolled loop over
direct streamSimple calls; aborted model calls bill no usage
- tests: all model seams ported to pi-ai faux provider (scripted
FauxResponseSteps, agent factories); handleChatRequest second param
is now an agent factory
Gates: tsc, lint, build, 305/305. Live GLM smoke (disposable driver,
deleted): prober streaming + persistence, question seam, turn-2
continuation same message id, per-turn real token usage - ALL PASS.
Data wiped at the pivot (chats/graph/jobs, .gitkeeps kept).
89 lines
3.5 KiB
TypeScript
89 lines
3.5 KiB
TypeScript
import type { AgentTool } from "@earendil-works/pi-agent-core";
|
|
import type { Usage } from "@earendil-works/pi-ai";
|
|
import { webTools } from "../tools/web.ts";
|
|
import { toPiTools } from "../lh-tool.ts";
|
|
import type { PiEngine } from "../models.ts";
|
|
import { runSubagent } from "./pi-run.ts";
|
|
|
|
/**
|
|
* The researcher sub-agent (vision §2.5): a SEPARATE ToolLoopAgent instance
|
|
* from the teacher — an isolated loop with only web_search + web_fetch, so
|
|
* raw search/fetch churn never touches the teacher's context window.
|
|
*
|
|
* System prompt adapted from the pi researcher agent
|
|
* (~/.pi/agent/extensions/interactive-subagents/agents/researcher.md).
|
|
* The engine is injectable so tests run the loop with a scripted faux engine.
|
|
*/
|
|
|
|
const INSTRUCTIONS = `You are a research specialist. You work for a teacher agent inside a learning
|
|
application: given a research question, conduct thorough web research and produce a focused,
|
|
well-sourced brief that the teacher can teach from.
|
|
|
|
You operate in an isolated context with no knowledge of the lesson or any prior conversation.
|
|
All necessary context is in the task description.
|
|
|
|
Process:
|
|
1. Break the question into 2-4 searchable facets.
|
|
2. Search with web_search using varied angles:
|
|
- the direct answer query (the obvious one)
|
|
- an authoritative-source query (official docs, specs, primary sources)
|
|
- a practical-experience query (case studies, benchmarks, real-world usage)
|
|
- a recent-developments query (only if the topic is time-sensitive)
|
|
3. Read the results. Identify what's well-covered and what has gaps. If the first round
|
|
doesn't fully answer the question, search again with refined queries targeting the gaps.
|
|
4. For the 2-3 most promising source URLs, use web_fetch to get the full page content.
|
|
5. Synthesize everything into a brief that directly answers the question.
|
|
|
|
Evaluation — what to keep vs drop:
|
|
- Official docs and primary sources outweigh blog posts and forum threads.
|
|
- Recent sources outweigh stale ones.
|
|
- Sources that directly address the question outweigh tangentially related ones.
|
|
- Drop SEO filler, outdated info, and beginner tutorials (unless that's the audience).
|
|
|
|
Tool outputs may be error strings (e.g. search unconfigured, a page that failed to fetch).
|
|
Adapt: try another URL or another search angle; if research is genuinely impossible, say so
|
|
in the brief instead of inventing facts.
|
|
|
|
Your FINAL assistant message is your entire deliverable — it must stand alone, using this format:
|
|
|
|
## Summary
|
|
2-3 sentence direct answer.
|
|
|
|
## Findings
|
|
Numbered findings with inline source citations:
|
|
1. **Finding** — explanation. [Source](url)
|
|
|
|
## Sources
|
|
- Kept: Source Title (url) — why relevant
|
|
- Dropped: Source Title — why excluded
|
|
|
|
## Gaps
|
|
What couldn't be answered. Suggested next steps.`;
|
|
|
|
export interface ResearcherRunOptions {
|
|
engine?: PiEngine;
|
|
abortSignal?: AbortSignal;
|
|
onUsage?: (usage: Usage) => void;
|
|
onToolStart?: (toolName: string, args: unknown) => void;
|
|
}
|
|
|
|
/**
|
|
* Run the researcher to completion: isolated context, web tools only, final
|
|
* text = the brief. The engine is injectable so tests run the loop scripted.
|
|
*/
|
|
export async function runResearcherAgent(prompt: string, opts: ResearcherRunOptions = {}): Promise<string> {
|
|
const { text } = await runSubagent(toPiTools(webTools) as AgentTool<any, any>[], {
|
|
role: "researcher",
|
|
prompt,
|
|
engine: opts.engine,
|
|
systemPrompt: INSTRUCTIONS,
|
|
maxTurns: 12,
|
|
abortSignal: opts.abortSignal,
|
|
onUsage: opts.onUsage,
|
|
onToolStart: opts.onToolStart,
|
|
});
|
|
return text;
|
|
}
|
|
|
|
export type ResearcherAgent = ReturnType<typeof runResearcherAgent>;
|