feat: probe/teach agent split — explicit phase markers, position-only plan map

Diagnosis (2026-09-11 user testing, minimal-effort GLM): sessions stuck on
'plan' forever. Two causes: (1) the three-phase view read the stored tree's
currentNodeId, which nothing ever writes post author-once (2026-09-03) — a
structural dead seam; (2) the teacher stochastically left quiz.nodeId
untagged, and done-by-quiz-result semantics would have falsely completed
nodes anyway.

The redesign (docs/probe-teach-split.md) abolishes derived occupancy in
favor of explicit events:

- Two agents over one transcript: createProberAgent (quiz without a
  nodeId field, ask, probe_done) and createTeacherAgent (full toolset,
  plan_init onward). The chat-handler construction branch keys on a
  probe_done part in the transcript. MODELS.prober added.
- probe_done: server-side seam tool — carries the learner assessment
  (strands + free-form edge read), refuses while a question is open or
  the probe is already concluded, and queues a handoff steer through the
  generalized wake pipeline (steers now dedupe by id, not jobId; job
  finalization only for job steers). The teacher auto-wakes and authors
  the plan; the learner sees the assessment via the probe-done card.
- phases: probe ends at a concluded probe_done, plan ends at a
  successful plan_init — strictly sequential, no skipping, no legacy
  compatibility (data wiped at the pivot per doctrine).
- Plan map = position, not completion: derivePlanStatuses reads only
  tagged quiz CALLS (state/outcome feed nothing); current = latest
  tagged node with consecutive duplicates collapsed, visited = earlier
  distinct stays (a revisit stays in both — current wins at render).
  PlanTree is structure-only; currentNodeId/doneNodeIds and the dead
  mutation helpers are gone. No fallback current.
- Prompts split per agent (prompts/prober/, prompts/teacher/ over the
  trimmed shared base); graph-context injection removed entirely
  (shelved, docs/probe-teach-split.md §5); knowledge-graph context no
  longer reaches either agent.
- Plan blocks are full-only snapshots at plan_init (neighborhood
  machinery retired; the persistent DAG window is the future UI wave);
  usage capture unchanged.

Gates: tsc clean, 294/294 tests (phases/plan-tree/plan-blocks/question-
tools rewritten to the new semantics; probe-done + handoff-wake tests
added), lint, build. Live GLM smoke PASS: prober concluded with an honest
assessment, teacher auto-woke, authored a 10-node plan with the block
attached, then tagged checks on slope-instinct → secant derived current/
visited exactly as designed; grading honest both ways (driver off-by-one
proved a wrong answer grades false).

src/server/turn-service.ts

@@ -4,7 +4,6 @@
  * implementing. Each takes its dependencies explicitly (storage ports, the
  * job runner) — no module here imports an adapter.
  *
- *   buildTeacherContext — graph → instructions block (the W8 read channel)
  *   persistTurn        — the canonical state write (client + agent messages)
  *   triggerExtraction  — the graph write channel: fires the extraction
  *                        pipeline (the sole graph writer) once a chat
@@ -18,28 +17,11 @@
 
 import type { UIMessage } from "ai";
 import { withPlanBlocks } from "../core/plan-blocks.ts";
-import { buildGraphContext } from "../core/graph-context.ts";
-import { getGraph, pendingQuizAnswers } from "../core/graph.ts";
+import { pendingQuizAnswers } from "../core/graph.ts";
 import type { ChatStore, GraphStore } from "../core/ports.ts";
 import { EXTRACTION } from "../../config.ts";
 import type { ExtractionPipeline } from "../agent/subagents/extraction.ts";
 
-/**
- * W8 (vision §1 "the graph as session context"): the learner's knowledge
- * graph rides along as part of the teacher's instructions. Built per request
- * — stateless, and self-updating as the graph grows mid-session. A read
- * failure must never take the lesson down: the block is context, not a
- * dependency.
- */
-export function buildTeacherContext(graphStore: GraphStore, chatId: string): string | null {
-	try {
-		return buildGraphContext(getGraph(graphStore));
-	} catch (err) {
-		console.error(`[chat ${chatId}] graph context build failed:`, err);
-		return null;
-	}
-}
-
 /**
  * The canonical state write: the client owns the message list between turns
  * (useChat); this persists client messages + the agent response. Persists