Swap the server engine to pi-ai/pi-agent-core (Band B+C of docs/pi-engine-swap.md)
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).
This commit is contained in:
amosblomqvist
@@ -1,6 +1,9 @@
|
||||
import { ToolLoopAgent, stepCountIs, tool, type LanguageModel, type UIMessage } from "ai";
|
||||
import type { UIMessage } from "ai";
|
||||
import type { Usage } from "@earendil-works/pi-ai";
|
||||
import { z } from "zod";
|
||||
import { modelFor } from "../models.ts";
|
||||
import { lhTool, toPiTools } from "../lh-tool.ts";
|
||||
import type { PiEngine } from "../models.ts";
|
||||
import { runSubagent } from "./pi-run.ts";
|
||||
import type {
|
||||
AuditResult,
|
||||
CallUsage,
|
||||
@@ -207,19 +210,50 @@ transcript). The auditor rejects anything unbacked. When in doubt, report; the a
|
||||
|
||||
Your entire deliverable is ONE submit_findings call.`;
|
||||
|
||||
function createExtractor(model: LanguageModel) {
|
||||
return new ToolLoopAgent({
|
||||
model,
|
||||
instructions: EXTRACTOR_INSTRUCTIONS,
|
||||
tools: {
|
||||
submit_findings: tool({
|
||||
/** One extractor run: the whole deliverable is ONE zod-validated submit
|
||||
* call (a pi agent purely so the model can retry a schema-invalid call).
|
||||
* Returns the submitted findings — captured from the execute seam, which
|
||||
* only fires on a schema-valid call. */
|
||||
async function runExtractor(
|
||||
engine: PiEngine | undefined,
|
||||
prompt: string,
|
||||
signal: AbortSignal | undefined,
|
||||
onStep: (usage: Usage, model: string, step: number, finishReason: string, tools: string) => void,
|
||||
): Promise<SessionFindings> {
|
||||
let submitted: SessionFindings | undefined;
|
||||
const result = await runSubagent(
|
||||
toPiTools({
|
||||
submit_findings: lhTool({
|
||||
name: "submit_findings",
|
||||
description: "Submit the session findings.",
|
||||
inputSchema: findingsSchema,
|
||||
execute: async (findings) => findings,
|
||||
schema: findingsSchema,
|
||||
execute: async (findings) => {
|
||||
submitted = findings;
|
||||
return findings;
|
||||
},
|
||||
}),
|
||||
}),
|
||||
{
|
||||
role: "extractor",
|
||||
engine,
|
||||
systemPrompt: EXTRACTOR_INSTRUCTIONS,
|
||||
prompt,
|
||||
maxTurns: 4,
|
||||
abortSignal: signal,
|
||||
onAssistantMessage: (message, step) =>
|
||||
onStep(
|
||||
message.usage,
|
||||
message.model,
|
||||
step,
|
||||
message.stopReason,
|
||||
message.content.filter((c) => c.type === "toolCall").map((c) => (c as { name: string }).name).join(", ") || "(none)",
|
||||
),
|
||||
shouldStop: (_message, toolResults) => toolResults.some((r) => r.toolName === "submit_findings" && !r.isError),
|
||||
},
|
||||
stopWhen: stepCountIs(4),
|
||||
});
|
||||
);
|
||||
void result;
|
||||
if (!submitted) throw new Error("the extractor never submitted findings");
|
||||
return submitted;
|
||||
}
|
||||
|
||||
// ─── the auditor ───────────────────────────────────────────────────────────
|
||||
@@ -290,19 +324,47 @@ function graphView(nodes: GraphNode[]): string {
|
||||
return lines.join("\n");
|
||||
}
|
||||
|
||||
function createAuditor(model: LanguageModel) {
|
||||
return new ToolLoopAgent({
|
||||
model,
|
||||
instructions: AUDITOR_INSTRUCTIONS,
|
||||
tools: {
|
||||
submit_review: tool({
|
||||
/** One auditor run — same single-submit shape as the extractor. */
|
||||
async function runAuditor(
|
||||
engine: PiEngine | undefined,
|
||||
prompt: string,
|
||||
signal: AbortSignal | undefined,
|
||||
onStep: (usage: Usage, model: string, step: number, finishReason: string, tools: string) => void,
|
||||
): Promise<AuditResult> {
|
||||
let submitted: AuditResult | undefined;
|
||||
const result = await runSubagent(
|
||||
toPiTools({
|
||||
submit_review: lhTool({
|
||||
name: "submit_review",
|
||||
description: "Submit the verified findings subset (with identity verdicts) + the dropped list.",
|
||||
inputSchema: auditSchema,
|
||||
execute: async (review) => review,
|
||||
schema: auditSchema,
|
||||
execute: async (review) => {
|
||||
submitted = review;
|
||||
return review;
|
||||
},
|
||||
}),
|
||||
}),
|
||||
{
|
||||
role: "auditor",
|
||||
engine,
|
||||
systemPrompt: AUDITOR_INSTRUCTIONS,
|
||||
prompt,
|
||||
maxTurns: 4,
|
||||
abortSignal: signal,
|
||||
onAssistantMessage: (message, step) =>
|
||||
onStep(
|
||||
message.usage,
|
||||
message.model,
|
||||
step,
|
||||
message.stopReason,
|
||||
message.content.filter((c) => c.type === "toolCall").map((c) => (c as { name: string }).name).join(", ") || "(none)",
|
||||
),
|
||||
shouldStop: (_message, toolResults) => toolResults.some((r) => r.toolName === "submit_review" && !r.isError),
|
||||
},
|
||||
stopWhen: stepCountIs(4),
|
||||
});
|
||||
);
|
||||
void result;
|
||||
if (!submitted) throw new Error("the auditor never submitted a review");
|
||||
return submitted;
|
||||
}
|
||||
|
||||
// ─── the pipeline status registry ─────────────────────────────────────────────
|
||||
@@ -346,10 +408,9 @@ export function abortExtraction(chatId: string): boolean {
|
||||
// ─── the pipeline ───────────────────────────────────────────────────────────
|
||||
|
||||
export interface ExtractionModels {
|
||||
/** The extractor's model (tests inject a MockLanguageModelV4). */
|
||||
extractor?: LanguageModel;
|
||||
/** The auditor's model. */
|
||||
auditor?: LanguageModel;
|
||||
/** Test seam: a scripted engine per stage (production uses the roles). */
|
||||
extractor?: PiEngine;
|
||||
auditor?: PiEngine;
|
||||
}
|
||||
|
||||
export interface ExtractionPipelineDeps extends GraphDeps, ExtractionModels {}
|
||||
@@ -362,8 +423,6 @@ export interface ExtractionPipeline {
|
||||
|
||||
export function createExtractionPipeline(deps: ExtractionPipelineDeps): ExtractionPipeline {
|
||||
const { chatStore, graphStore } = deps;
|
||||
const extractorAgent = createExtractor(deps.extractor ?? modelFor("extractor"));
|
||||
const auditorAgent = createAuditor(deps.auditor ?? modelFor("auditor"));
|
||||
const inFlight = new Set<string>();
|
||||
|
||||
function setPhase(chatId: string, phase: ExtractionPhase): void {
|
||||
@@ -385,22 +444,17 @@ export function createExtractionPipeline(deps: ExtractionPipelineDeps): Extracti
|
||||
run.usage[stage]!.steps.push(usage);
|
||||
}
|
||||
|
||||
/** The SDK's per-step usage, flattened to the persisted CallUsage fields
|
||||
/** pi's per-step usage, flattened to the persisted CallUsage fields
|
||||
* (the money channel's capture shape, contracts/chat.ts). */
|
||||
function callUsage(usage: {
|
||||
inputTokens: number | undefined;
|
||||
outputTokens: number | undefined;
|
||||
inputTokenDetails?: { cacheReadTokens?: number; cacheWriteTokens?: number };
|
||||
outputTokenDetails?: { reasoningTokens?: number };
|
||||
}): CallUsage {
|
||||
// Optional-chained: the SDK types the detail objects as required, but
|
||||
// providers (and mocks) may leave them unset.
|
||||
function callUsage(usage: Usage): CallUsage {
|
||||
return {
|
||||
inputTokens: usage.inputTokens,
|
||||
outputTokens: usage.outputTokens,
|
||||
cacheReadTokens: usage.inputTokenDetails?.cacheReadTokens,
|
||||
cacheWriteTokens: usage.inputTokenDetails?.cacheWriteTokens,
|
||||
reasoningTokens: usage.outputTokenDetails?.reasoningTokens,
|
||||
inputTokens: usage.input,
|
||||
outputTokens: usage.output,
|
||||
cacheReadTokens: usage.cacheRead,
|
||||
cacheWriteTokens: usage.cacheWrite,
|
||||
// Optional in pi's Usage (providers that never emit reasoning
|
||||
// tokens leave it unset) — persisted as 0, never dropped.
|
||||
reasoningTokens: usage.reasoning ?? 0,
|
||||
};
|
||||
}
|
||||
|
||||
@@ -413,23 +467,17 @@ export function createExtractionPipeline(deps: ExtractionPipelineDeps): Extracti
|
||||
console.info(`[extraction ${chatId}] extractor starting (${view.split("\n").length} transcript lines)`);
|
||||
const t0 = performance.now();
|
||||
|
||||
const extraction = await extractorAgent.generate({
|
||||
prompt: `Transcript:\n\n${view}`,
|
||||
abortSignal: signal,
|
||||
onStepFinish: (step) => {
|
||||
recordStep(chatId, "extractor", callUsage(step.usage), step.model.modelId);
|
||||
console.info(
|
||||
`[extraction] extractor step ${step.stepNumber}: ${step.finishReason}, tools: ${step.toolCalls.map((c) => c.toolName).join(", ") || "(none)"}`,
|
||||
);
|
||||
const findings = await runExtractor(
|
||||
deps.extractor,
|
||||
`Transcript:\n\n${view}`,
|
||||
signal,
|
||||
(usage, model, step, finishReason, tools) => {
|
||||
recordStep(chatId, "extractor", callUsage(usage), model);
|
||||
console.info(`[extraction] extractor step ${step}: ${finishReason}, tools: ${tools}`);
|
||||
},
|
||||
});
|
||||
for (const part of extraction.content) {
|
||||
if (part.type === "tool-result" && part.toolName === "submit_findings") {
|
||||
console.info(`[extraction ${chatId}] extractor done in ${Math.round(performance.now() - t0)}ms`);
|
||||
return part.output as SessionFindings;
|
||||
}
|
||||
}
|
||||
throw new Error("the extractor never submitted findings");
|
||||
);
|
||||
console.info(`[extraction ${chatId}] extractor done in ${Math.round(performance.now() - t0)}ms`);
|
||||
return findings;
|
||||
}
|
||||
|
||||
async function audit(chatId: string, findings: SessionFindings): Promise<AuditResult> {
|
||||
@@ -445,25 +493,16 @@ export function createExtractionPipeline(deps: ExtractionPipelineDeps): Extracti
|
||||
);
|
||||
const t0 = performance.now();
|
||||
|
||||
const review = await auditorAgent.generate({
|
||||
prompt:
|
||||
`Transcript:\n\n${view}\n\nProposed findings:\n\n${JSON.stringify(findings, null, 2)}\n\n` +
|
||||
const auditResult = await runAuditor(
|
||||
deps.auditor,
|
||||
`Transcript:\n\n${view}\n\nProposed findings:\n\n${JSON.stringify(findings, null, 2)}\n\n` +
|
||||
`Current knowledge graph (${graph.nodes.length} nodes):\n\n${graphView(graph.nodes)}`,
|
||||
abortSignal: signal,
|
||||
onStepFinish: (step) => {
|
||||
recordStep(chatId, "auditor", callUsage(step.usage), step.model.modelId);
|
||||
console.info(
|
||||
`[extraction] auditor step ${step.stepNumber}: ${step.finishReason}, tools: ${step.toolCalls.map((c) => c.toolName).join(", ") || "(none)"}`,
|
||||
);
|
||||
signal,
|
||||
(usage, model, step, finishReason, tools) => {
|
||||
recordStep(chatId, "auditor", callUsage(usage), model);
|
||||
console.info(`[extraction] auditor step ${step}: ${finishReason}, tools: ${tools}`);
|
||||
},
|
||||
});
|
||||
let auditResult: AuditResult | null = null;
|
||||
for (const part of review.content) {
|
||||
if (part.type === "tool-result" && part.toolName === "submit_review") {
|
||||
auditResult = part.output as AuditResult;
|
||||
}
|
||||
}
|
||||
if (!auditResult) throw new Error("the auditor never submitted a review");
|
||||
);
|
||||
if (auditResult.dropped.length > 0) {
|
||||
console.info(
|
||||
`[extraction ${chatId}] audit dropped ${auditResult.dropped.length}: ` +
|
||||
|
||||
Reference in New Issue
Block a user