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.
This commit is contained in:
Amos
@@ -5,3 +5,4 @@ data/
|
||||
.DS_Store
|
||||
*.tsbuildinfo
|
||||
.env.local
|
||||
.memory/
|
||||
|
||||
@@ -26,13 +26,11 @@ npx tsx scripts/bench-graph.ts # force-layout benchmark (synthetic graphs)
|
||||
|
||||
## Environment (`.env.local`)
|
||||
|
||||
Secrets and machine-specific paths only. Model choice and thinking budgets are product tuning, not environment — they live in **`config.ts` → `MODELS`** (teacher, researcher, demoBuilder, visualMaker, extractor, auditor; each with an OpenRouter model id + reasoning `effort`). The extraction trigger threshold is there too (`EXTRACTION.everyNQuizAnswers`).
|
||||
|
||||
| Variable | Purpose |
|
||||
|---|---|
|
||||
| `OPENROUTER_API_KEY` | required — all LLM calls go through OpenRouter |
|
||||
| `LH_MODEL` | teacher model (default `anthropic/claude-sonnet-4.5`) |
|
||||
| `LH_RESEARCH_MODEL`, `LH_DEMO_MODEL`, `LH_EXTRACT_MODEL` | per-sub-agent overrides (fall back to `LH_MODEL`) |
|
||||
| `LH_EXTRACT_N` | answered quizzes per chat before the extraction pipeline fires (default `3`) |
|
||||
| `LH_VISUAL_MODEL` | visual-maker model — must be **vision-capable** (it looks at rendered SVGs) |
|
||||
| `GOOGLE_SEARCH_API_KEY` + `GOOGLE_CSE_ID` | researcher's `web_search` (Google Custom Search) |
|
||||
| `CHROME_PATH` | optional explicit Chrome path for headless verification (puppeteer-core uses system Chrome; nothing is downloaded) |
|
||||
|
||||
@@ -161,9 +159,9 @@ data/ chats/ · graph/ · jobs/ — runtime state, git
|
||||
|
||||
**The formal plan tree.** The teacher authors the session's dependency tree with schema-validated tools (`plan_init`, `plan_add_node`, … `plan_set_current`, `plan_mark_done`). The tree persists in the chat record; the tree panel renders from the latest plan tool output in the transcript. Quiz calls can tag a `nodeId`, so outcomes feed the graph per-node.
|
||||
|
||||
**The async sub-agent protocol.** `research` / `demo` / `visual` are also client-side tools: the server turn ends at the call, `onFinish` spawns a background runner (fire-and-forget), the job store tracks a live activity line, the client polls `/api/jobs` while parts are pending, and on completion the runner rewrites the tool part in the chat record to `output-available` — the client re-syncs, the continuation fires, the teacher receives the result as a normal tool output. Sub-agents **verify, never one-shot**: the demo-builder headlessly executes its HTML in system Chrome before delivery; the visual-maker renders each SVG and looks at it (needs a vision-capable `LH_VISUAL_MODEL`).
|
||||
**The async sub-agent protocol.** `research` / `demo` / `visual` are also client-side tools: the server turn ends at the call, `onFinish` spawns a background runner (fire-and-forget), the job store tracks a live activity line, the client polls `/api/jobs` while parts are pending, and on completion the runner rewrites the tool part in the chat record to `output-available` — the client re-syncs, the continuation fires, the teacher receives the result as a normal tool output. Sub-agents **verify, never one-shot**: the demo-builder headlessly executes its HTML in system Chrome before delivery; the visual-maker renders each SVG and looks at it (needs a vision-capable model — `MODELS.visualMaker` in config.ts).
|
||||
|
||||
**The knowledge graph (the two channels).** The write channel: the extraction pipeline — extractor (LLM: propositions, edges, probe attribution, each with verbatim evidence) → auditor (LLM: drops anything unbacked) → merger (`mergeFindings`, deterministic: exact/alias identity resolution, event rebuild from the transcript's tool parts, dedupe, checkpoint). Triggered once a chat accumulates `EXTRACTION.everyNQuizAnswers` (default 3, `LH_EXTRACT_N`) new answered quizzes — a v1 placeholder trigger isolated in one seam (`turn-service.ts`), swappable without touching the pipeline. Failure checkpoints nothing; the next trigger re-runs. The read channel: the home view derives node states from the ledgers (`GET /api/graph` is a pure read — forceAtlas2 run-then-freeze, no idle simulation), and at session start the derived graph is rendered into a compact markdown block appended to the teacher's instructions (`buildGraphContext`) — whole graph while small, hotspots + 1-hop neighborhood past 150 nodes.
|
||||
**The knowledge graph (the two channels).** The write channel: the extraction pipeline — extractor (LLM: propositions, edges, probe attribution, each with verbatim evidence) → auditor (LLM: drops anything unbacked) → merger (`mergeFindings`, deterministic: exact/alias identity resolution, event rebuild from the transcript's tool parts, dedupe, checkpoint). Triggered once a chat accumulates `EXTRACTION.everyNQuizAnswers` (default 3, config.ts) new answered quizzes — a v1 placeholder trigger isolated in one seam (`turn-service.ts`), swappable without touching the pipeline. Failure checkpoints nothing; the next trigger re-runs. The read channel: the home view derives node states from the ledgers (`GET /api/graph` is a pure read — forceAtlas2 run-then-freeze, no idle simulation), and at session start the derived graph is rendered into a compact markdown block appended to the teacher's instructions (`buildGraphContext`) — whole graph while small, hotspots + 1-hop neighborhood past 150 nodes.
|
||||
|
||||
## Testing
|
||||
|
||||
|
||||
@@ -14,15 +14,48 @@ export const PATHS = {
|
||||
graph: path.join(ROOT, "data", "graph"),
|
||||
} as const;
|
||||
|
||||
// ─── Models ────────────────────────────────────────────────────────────────
|
||||
// THE single place every LLM is chosen and tuned. .env stays for secrets
|
||||
// (API keys) only — model choice and thinking budget are product tuning,
|
||||
// not deployment environment, and this section is the one place they grow.
|
||||
// `effort` is OpenRouter's reasoning scale (docs: reasoning-tokens):
|
||||
// "none" | "minimal" | "low" | "medium" | "high" | "xhigh".
|
||||
// "none" disables reasoning tokens entirely.
|
||||
|
||||
export type ReasoningEffort = "none" | "minimal" | "low" | "medium" | "high" | "xhigh";
|
||||
|
||||
export interface ModelSpec {
|
||||
/** OpenRouter model id (e.g. "z-ai/glm-5.3-flash"). */
|
||||
model: string;
|
||||
/** Thinking budget — what the model may spend on reasoning tokens. */
|
||||
effort: ReasoningEffort;
|
||||
}
|
||||
|
||||
export const MODELS = {
|
||||
/** The teacher — streaming, lesson-facing: smart, but keep it lively. */
|
||||
teacher: { model: "z-ai/glm-5.3-flash", effort: "medium" },
|
||||
/** Background sub-agents: fast and cheap beats deep thought. */
|
||||
researcher: { model: "z-ai/glm-5.3-flash", effort: "low" },
|
||||
demoBuilder: { model: "z-ai/glm-5.3-flash", effort: "low" },
|
||||
/** Must be vision-capable: it looks at rendered SVGs. */
|
||||
visualMaker: { model: "anthropic/claude-sonnet-4.5", effort: "low" },
|
||||
/** Extraction is judgment over given evidence — light thinking suffices. */
|
||||
extractor: { model: "z-ai/glm-5.3-flash", effort: "low" },
|
||||
/** The auditor verifies evidence exists; keep it cheap. */
|
||||
auditor: { model: "z-ai/glm-5.3-flash", effort: "low" },
|
||||
} satisfies Record<string, ModelSpec>;
|
||||
|
||||
export type ModelRole = keyof typeof MODELS;
|
||||
|
||||
/**
|
||||
* The extraction pipeline (vision §1 construction): the sole graph writer.
|
||||
* Triggered per chat once this many NEW quiz answers have landed since the
|
||||
* chat's last extraction checkpoint (LH_EXTRACT_N). The trigger mechanism is
|
||||
* a v1 placeholder — deliberately isolated behind one seam
|
||||
* chat's last extraction checkpoint. The trigger mechanism is a v1
|
||||
* placeholder — deliberately isolated behind one seam
|
||||
* (server/turn-service.ts) so it can be swapped without touching the
|
||||
* pipeline.
|
||||
*/
|
||||
export const EXTRACTION = { everyNQuizAnswers: Number(process.env.LH_EXTRACT_N ?? 3) } as const;
|
||||
export const EXTRACTION = { everyNQuizAnswers: 3 } as const;
|
||||
|
||||
/**
|
||||
* The LIVE graph store (src/store/graph.ts) — owned by the app's extraction
|
||||
|
||||
@@ -81,7 +81,7 @@ chat record ──▶ EXTRACTOR (LLM) ──▶ AUDITOR (LLM) ──▶ MERGER (
|
||||
|
||||
**Probe attribution** (vision open question, resolved structurally): tagged events (quiz `nodeId`, `plan_mark_done`'s tree node) resolve deterministically through the proposition mapping. The extractor's judgment is consulted only for **untagged probe quizzes** — retroactively, against the whole transcript, so a pre-tree probe maps to a proposition the tree only articulates later. Attribution can also rescue a tagged-but-unknown id; genuinely unattributable probes land `nodeId: null` with the question text, exactly as they always have.
|
||||
|
||||
**The trigger is a v1 placeholder, isolated in ONE seam.** `src/server/turn-service.ts` (`triggerExtraction`) counts answered quizzes not yet in the ledger (`pendingQuizAnswers`, core) and fires the pipeline async once a chat crosses `EXTRACTION.everyNQuizAnswers` (`LH_EXTRACT_N`, default 3) — single-flight per chat. The pipeline is trigger-agnostic: when a better mechanism lands (session end, idle, explicit flush), only this seam changes.
|
||||
**The trigger is a v1 placeholder, isolated in ONE seam.** `src/server/turn-service.ts` (`triggerExtraction`) counts answered quizzes not yet in the ledger (`pendingQuizAnswers`, core) and fires the pipeline async once a chat crosses `EXTRACTION.everyNQuizAnswers` (default 3, config.ts) — single-flight per chat. The pipeline is trigger-agnostic: when a better mechanism lands (session end, idle, explicit flush), only this seam changes.
|
||||
|
||||
**The read channel is pure derivation.** `GET /api/graph` reads the ledgers (`graphSnapshot`: merged edges, derived node states, session provenance) — the home view never triggers a write. At session start, `buildGraphContext` renders the derived graph into a compact markdown block appended to the teacher's instructions (whole graph while small; diagnostic hotspots + 1-hop neighborhood past 150 nodes) — this is what makes probing precise and personalization compound. `store events, derive state`: node states are always recomputed from the ledger, never stored.
|
||||
|
||||
|
||||
Vendored
+2
-2
@@ -1,7 +1,7 @@
|
||||
/// <reference types="next" />
|
||||
/// <reference types="next/image-types/global" />
|
||||
import "./.next/types/routes.d.ts";
|
||||
import "./.next/types/root-params.d.ts";
|
||||
import "./.next/dev/types/routes.d.ts";
|
||||
import "./.next/dev/types/root-params.d.ts";
|
||||
|
||||
// NOTE: This file should not be edited
|
||||
// see https://nextjs.org/docs/app/api-reference/config/typescript for more information.
|
||||
|
||||
@@ -0,0 +1,17 @@
|
||||
import { openrouter } from "@openrouter/ai-sdk-provider";
|
||||
import type { LanguageModel } from "ai";
|
||||
import { MODELS, type ModelRole } from "../../config.ts";
|
||||
|
||||
/**
|
||||
* The one factory every agent's model comes from. Model choice and thinking
|
||||
* budget live in config.ts (MODELS) — the single tuning table; this module
|
||||
* only wires them to OpenRouter. `effort: "none"` is OpenRouter's off-switch
|
||||
* for reasoning tokens; higher levels let the model think longer (and bill
|
||||
* accordingly).
|
||||
*/
|
||||
export function modelFor(role: ModelRole): LanguageModel {
|
||||
const spec = MODELS[role];
|
||||
return openrouter(spec.model, {
|
||||
reasoning: { enabled: true, effort: spec.effort },
|
||||
});
|
||||
}
|
||||
@@ -1,6 +1,6 @@
|
||||
import { ToolLoopAgent, stepCountIs, tool, type LanguageModel, type ToolSet } from "ai";
|
||||
import { openrouter } from "@openrouter/ai-sdk-provider";
|
||||
import { z } from "zod";
|
||||
import { modelFor } from "../models.ts";
|
||||
import type { DemoResult } from "../../core/contracts.ts";
|
||||
import { getHeadless, type DemoRunResult, type HeadlessApi } from "./headless.ts";
|
||||
|
||||
@@ -20,9 +20,6 @@ import { getHeadless, type DemoRunResult, type HeadlessApi } from "./headless.ts
|
||||
* The job wrapper treats html === "" as failure and marks the job error.
|
||||
*/
|
||||
|
||||
const DEFAULT_DEMO_MODEL =
|
||||
process.env.LH_DEMO_MODEL ?? process.env.LH_MODEL ?? "anthropic/claude-sonnet-4.5";
|
||||
|
||||
export interface DemoBuilderInput {
|
||||
title: string;
|
||||
brief: string;
|
||||
@@ -174,7 +171,7 @@ export async function runDemoBuilder(input: DemoBuilderInput, opts: DemoBuilderO
|
||||
|
||||
const state: BuilderState = { html: null, testedHtml: null, lastResult: null };
|
||||
const agent = new ToolLoopAgent({
|
||||
model: opts.model ?? openrouter(DEFAULT_DEMO_MODEL),
|
||||
model: opts.model ?? modelFor("demoBuilder"),
|
||||
instructions: INSTRUCTIONS,
|
||||
tools: createDemoBuilderTools(state, headless, opts.onActivity),
|
||||
stopWhen: stepCountIs(opts.maxSteps ?? 24),
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import { ToolLoopAgent, stepCountIs, tool, type LanguageModel, type UIMessage } from "ai";
|
||||
import { openrouter } from "@openrouter/ai-sdk-provider";
|
||||
import { z } from "zod";
|
||||
import { modelFor } from "../models.ts";
|
||||
import type { AuditResult, ChatRecord, SessionFindings } from "../../core/contracts.ts";
|
||||
import { mergeFindings, type EmissionStats, type GraphDeps } from "../../core/graph.ts";
|
||||
|
||||
@@ -27,9 +27,6 @@ import { mergeFindings, type EmissionStats, type GraphDeps } from "../../core/gr
|
||||
* the next trigger re-runs the whole thing.
|
||||
*/
|
||||
|
||||
const DEFAULT_EXTRACTION_MODEL =
|
||||
process.env.LH_EXTRACT_MODEL ?? process.env.LH_MODEL ?? "anthropic/claude-sonnet-4.5";
|
||||
|
||||
// ─── the transcript view (what the LLM sees) ────────────────────────────────
|
||||
|
||||
/**
|
||||
@@ -175,6 +172,12 @@ function createExtractor(model: LanguageModel) {
|
||||
}),
|
||||
},
|
||||
stopWhen: stepCountIs(4),
|
||||
// One line per step: a background worker's progress must be legible
|
||||
// from the server log (§5 observability baseline).
|
||||
onStepFinish: (step) =>
|
||||
console.info(
|
||||
`[extraction] extractor step ${step.stepNumber}: ${step.finishReason}, tools: ${step.toolCalls.map((c) => c.toolName).join(", ") || "(none)"}`,
|
||||
),
|
||||
});
|
||||
}
|
||||
|
||||
@@ -224,6 +227,10 @@ function createAuditor(model: LanguageModel) {
|
||||
}),
|
||||
},
|
||||
stopWhen: stepCountIs(4),
|
||||
onStepFinish: (step) =>
|
||||
console.info(
|
||||
`[extraction] auditor step ${step.stepNumber}: ${step.finishReason}, tools: ${step.toolCalls.map((c) => c.toolName).join(", ") || "(none)"}`,
|
||||
),
|
||||
});
|
||||
}
|
||||
|
||||
@@ -246,14 +253,15 @@ export interface ExtractionPipeline {
|
||||
|
||||
export function createExtractionPipeline(deps: ExtractionPipelineDeps): ExtractionPipeline {
|
||||
const { chatStore, graphStore } = deps;
|
||||
const extractorAgent = createExtractor(deps.extractor ?? openrouter(DEFAULT_EXTRACTION_MODEL));
|
||||
const auditorAgent = createAuditor(deps.auditor ?? openrouter(DEFAULT_EXTRACTION_MODEL));
|
||||
const extractorAgent = createExtractor(deps.extractor ?? modelFor("extractor"));
|
||||
const auditorAgent = createAuditor(deps.auditor ?? modelFor("auditor"));
|
||||
const inFlight = new Set<string>();
|
||||
|
||||
async function extract(chatId: string): Promise<SessionFindings> {
|
||||
const record = chatStore.getChat(chatId);
|
||||
if (!record) throw new Error(`Chat not found: ${chatId}`);
|
||||
const view = transcriptView(record);
|
||||
console.info(`[extraction ${chatId}] extractor starting (${view.split("\n").length} transcript lines)`);
|
||||
|
||||
const extraction = await extractorAgent.generate({ prompt: `Transcript:\n\n${view}` });
|
||||
for (const part of extraction.content) {
|
||||
@@ -268,6 +276,10 @@ export function createExtractionPipeline(deps: ExtractionPipelineDeps): Extracti
|
||||
const record = chatStore.getChat(chatId);
|
||||
if (!record) throw new Error(`Chat not found: ${chatId}`);
|
||||
const view = transcriptView(record);
|
||||
console.info(
|
||||
`[extraction ${chatId}] auditor starting (${findings.propositions.length} propositions, ${findings.edges.length} edges, ` +
|
||||
`${Object.keys(findings.attribution.quiz).length} attributions)`,
|
||||
);
|
||||
|
||||
const review = await auditorAgent.generate({
|
||||
prompt: `Transcript:\n\n${view}\n\nProposed findings:\n\n${JSON.stringify(findings, null, 2)}`,
|
||||
@@ -286,6 +298,10 @@ export function createExtractionPipeline(deps: ExtractionPipelineDeps): Extracti
|
||||
);
|
||||
}
|
||||
const { dropped: _dropped, ...verified } = auditResult;
|
||||
console.info(
|
||||
`[extraction ${chatId}] audit kept ${verified.propositions.length}/${findings.propositions.length} propositions, ` +
|
||||
`${verified.edges.length}/${findings.edges.length} edges`,
|
||||
);
|
||||
return verified;
|
||||
}
|
||||
|
||||
@@ -293,6 +309,7 @@ export function createExtractionPipeline(deps: ExtractionPipelineDeps): Extracti
|
||||
if (inFlight.has(chatId)) return { nodes: 0, edges: 0, events: 0 };
|
||||
inFlight.add(chatId);
|
||||
try {
|
||||
console.info(`[extraction ${chatId}] pipeline start`);
|
||||
const findings = await extract(chatId);
|
||||
const verified = await audit(chatId, findings);
|
||||
// The merger re-reads the chat record itself — events are rebuilt
|
||||
|
||||
@@ -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),
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import { generateText, tool, type LanguageModel, type ModelMessage, type ToolResultPart } from "ai";
|
||||
import { openrouter } from "@openrouter/ai-sdk-provider";
|
||||
import { z } from "zod";
|
||||
import { modelFor } from "../models.ts";
|
||||
import type { VisualResult } from "../../core/contracts.ts";
|
||||
import { getHeadless, type HeadlessApi } from "./headless.ts";
|
||||
|
||||
@@ -26,9 +26,6 @@ import { getHeadless, type HeadlessApi } from "./headless.ts";
|
||||
* Failure semantics mirror the demo-builder: { svg: "", notes: "FAILED: …" }.
|
||||
*/
|
||||
|
||||
const DEFAULT_VISUAL_MODEL =
|
||||
process.env.LH_VISUAL_MODEL ?? process.env.LH_MODEL ?? "anthropic/claude-sonnet-4.5";
|
||||
|
||||
export interface VisualMakerInput {
|
||||
brief: string;
|
||||
}
|
||||
@@ -127,7 +124,7 @@ export async function runVisualMaker(input: VisualMakerInput, opts: VisualMakerO
|
||||
|
||||
try {
|
||||
for (let iteration = 0; iteration < maxIterations; iteration++) {
|
||||
const result = await generateText({ model: opts.model ?? openrouter(DEFAULT_VISUAL_MODEL), system: INSTRUCTIONS, messages, tools });
|
||||
const result = await generateText({ model: opts.model ?? modelFor("visualMaker"), system: INSTRUCTIONS, messages, tools });
|
||||
messages = [...messages, ...result.response.messages];
|
||||
|
||||
const toolCalls = result.toolCalls;
|
||||
|
||||
@@ -1,9 +1,9 @@
|
||||
import * as fs from "node:fs";
|
||||
import * as path from "node:path";
|
||||
import { ToolLoopAgent, stepCountIs, type LanguageModel, type ToolSet } from "ai";
|
||||
import { openrouter } from "@openrouter/ai-sdk-provider";
|
||||
import { PATHS } from "../../config.ts";
|
||||
import { createTeacherTools, jobTools, questionTools } from "./tools.ts";
|
||||
import { modelFor } from "./models.ts";
|
||||
|
||||
/**
|
||||
* The teacher agent. Everything pi used to provide (agent loop, tool calling,
|
||||
@@ -22,8 +22,6 @@ import { createTeacherTools, jobTools, questionTools } from "./tools.ts";
|
||||
* fragments with a numeric order key: 10-plan-tree.md, 20-jobs.md, …
|
||||
*/
|
||||
|
||||
const DEFAULT_MODEL = process.env.LH_MODEL ?? "anthropic/claude-sonnet-4.5";
|
||||
|
||||
const PROMPTS_DIR = path.join(PATHS.root, "src", "agent", "prompts");
|
||||
|
||||
function composeInstructions(): string {
|
||||
@@ -54,13 +52,9 @@ function withGraphContext(graphContext: string | null | undefined): string {
|
||||
|
||||
export function createTeacherAgent(model?: LanguageModel, tools?: ToolSet, graphContext?: string | null) {
|
||||
return new ToolLoopAgent({
|
||||
model:
|
||||
model ??
|
||||
openrouter(DEFAULT_MODEL, {
|
||||
// Ask OpenRouter for reasoning tokens when the model supports them;
|
||||
// they stream as reasoning parts into the UI's collapsible block.
|
||||
reasoning: { enabled: true, effort: "medium" },
|
||||
}),
|
||||
// Model choice + thinking budget live in config.ts (MODELS.teacher).
|
||||
// Reasoning tokens stream as reasoning parts into the UI's collapsible block.
|
||||
model: model ?? modelFor("teacher"),
|
||||
instructions: withGraphContext(graphContext),
|
||||
// Tools are per-request (plan tools close over the injected ctx);
|
||||
// chat-handler passes createTeacherTools({ chatId, chatStore }). The
|
||||
|
||||
Reference in New Issue
Block a user