Centralized model config (config.ts MODELS) + extraction seam logging

MODELS in config.ts is now THE single tuning table: model id + OpenRouter
reasoning effort for teacher/researcher/demoBuilder/visualMaker/extractor/
auditor. .env.local is secrets-only (LH_* model vars removed; all sub-agents
previously had NO reasoning setting -> provider-default unbounded thinking,
the extraction token burn). One factory (src/agent/models.ts modelFor) wires
all six call sites; test injection unchanged. EXTRACTION.everyNQuizAnswers
moved to a config literal too. Plus the §5 one-line-per-seam logging in the
extraction pipeline: pipeline start, extractor/auditor start + per-step,
audit kept, merged — previously silent until completion, which made live
runs look like they never fired.

src/agent/subagents/researcher.ts

@@ -1,6 +1,6 @@
 import { ToolLoopAgent, stepCountIs, type LanguageModel } from "ai";
-import { openrouter } from "@openrouter/ai-sdk-provider";
 import { webTools } from "../tools/web.ts";
+import { modelFor } from "../models.ts";
 
 /**
  * The researcher sub-agent (vision §2.5): a SEPARATE ToolLoopAgent instance
@@ -12,9 +12,6 @@ import { webTools } from "../tools/web.ts";
  * The model is injectable so tests run the loop with a MockLanguageModelV4.
  */
 
-const DEFAULT_RESEARCHER_MODEL =
-	process.env.LH_RESEARCH_MODEL ?? process.env.LH_MODEL ?? "anthropic/claude-sonnet-4.5";
-
 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.
@@ -61,7 +58,7 @@ What couldn't be answered. Suggested next steps.`;
 
 export function createResearcherAgent(model?: LanguageModel) {
 	return new ToolLoopAgent({
-		model: model ?? openrouter(DEFAULT_RESEARCHER_MODEL),
+		model: model ?? modelFor("researcher"),
 		instructions: INSTRUCTIONS,
 		tools: webTools,
 		stopWhen: stepCountIs(12),