practice slice 4 — pipeline, registry, API, feed

src/agent/subagents/practice-pipeline.ts (sibling of practice.ts —
orchestration vs calls): createPracticePipeline(graphStore+practiceStore
+chatStore+PracticeModels). Fire-and-forget front doors returning
{set, done}: createProblemSet (refuse → resolve selection (chatId =
ANY-provenance membership per brief; nodeIds raw) → chains → snapshot →
createSet partitioning → registry row → runPartitioner → stubs land
(generating) → ONE generator per problem behind the process-wide
3-permit abort-aware semaphore (__lhPracticeSlots, extraction idiom) →
per-problem failure isolation → ready (errored problems included);
abortPractice (idempotent: controllers + 'Aborted' marks; dropped
grades keep answers, re-submittable); submitAnswers (ready-only,
already-graded rejects, one grading job per answer under the same
semaphore); deleteProblemSet (abort-first). Per-set write mutex on
globalThis (__lhPracticeLocks, audit-lock idiom); registry
__lhPracticeRuns one row per set per kind; boot sweep marks orphaned
partitioning/generating sets 'Interrupted (server restarted)'. Typed
errors: EmptySelection/UnknownChat/SetNotFound/SetNotReady/BadAnswers.
Usage folds stage logs into the registry row (v1: completion-folded).

src/server/practice.ts: thin service — strict params parsing, typed
error → response mapping (503 envelope family, 400/404/409), list/get.
Routes: POST+GET /api/practice/sets (202 {id}), GET+DELETE
/api/practice/sets/[id], POST /api/practice/sets/[id]/answers (202).
Composition root: chat-handler wires createPracticePipeline (engineFor
fresh + providerKeyMissing gate) exported as ; barrel re-
exports. Feed: observability activityFeed() += practice rows
(ActivityPractice); dock blobs (process 'practice', GraduationCap
icon, set-keyed abort); /api/activity/abort kind 'practice'.

tests/practice-pipeline.test.ts — 13 tests: end-to-end (stubs mid-
flight via gated generators, coverage complete), failure isolation,
3-permit semaphore pin, abort mid-generation, registry shape pins,
refusal-before-create, chatId any-provenance selection, typed errors,
answers→grades land + graded rejects, boot sweep (orphan + live-row),
delete. 1114/1114, tsc 0, lint 0, build 0.

src/server/chat-handler.ts

@@ -3,6 +3,7 @@ import { createProberAgent, createTeacherAgent, type AgentBuildOptions, type Tea
 import { piEngineForSpec, type PiEngine } from "../agent/models.ts";
 import { createJobRunner } from "../agent/subagents/runner.ts";
 import { createExtractionPipeline } from "../agent/subagents/extraction.ts";
+import { createPracticePipeline } from "../agent/subagents/practice-pipeline.ts";
 import type { ModelRole } from "../../config.ts";
 import {
 	deliverJobResult,
@@ -97,6 +98,24 @@ export const extraction = createExtractionPipeline({
 		providerKeyPresent(provider) ? null : providerKeyMissingEnvelope(provider, [tier]),
 });
 
+/** The app's ONE practice pipeline instance — the API routes reach it
+ *  through the server barrel / service, same discipline as extraction. */
+export const practice = createPracticePipeline({
+	graphStore: stores.graphStore,
+	practiceStore: stores.practiceStore,
+	chatStore: stores.chatStore,
+	// BYOK (owner, 2026-09-22): the practice stages resolve the chain —
+	// role override → slot → NOTHING — read FRESH per stage call; an empty
+	// chain flows through as undefined and the pipeline refuses the run
+	// with the typed ModelsNotConfiguredError. Direct test values still win.
+	engineFor: (role) =>
+		resolveEngine(role),
+	// Key-presence gate: same check extraction gets — a stage engine whose
+	// provider key is gone refuses BEFORE any set is created.
+	providerKeyMissing: (provider, tier) =>
+		providerKeyPresent(provider) ? null : providerKeyMissingEnvelope(provider, [tier]),
+});
+
 // Wake-pipeline wiring (contracts.ts "THE ASYNC PROTOCOL" §4): the pipeline
 // delivers its steers through THIS composition root (one event: the steer
 // marker, appended natively under the turn claim), and crash recovery