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/store/chats.ts

@@ -14,7 +14,7 @@ import type { ChatStore } from "../core/ports.ts";
 import type { ChatRecord, ChatSummary, ExtractionRunUsage, PlanTree, TurnUsage } from "../core/contracts.ts";
 import type { UIMessage } from "ai";
 import { findPendingToolCall } from "../core/pending.ts";
-import { phaseOfTree } from "../core/phases.ts";
+import { phaseAt3 } from "../core/phases.ts";
 
 function chatFile(id: string): string {
 	if (!/^[A-Za-z0-9_-]+$/.test(id)) throw new Error(`Invalid chat id: ${id}`);
@@ -58,10 +58,11 @@ function listChats(): ChatSummary[] {
 				...summary,
 				messageCount: messages.length,
 				// Record-derived status for the session picker: phase from the
-				// stored plan tree, pending question from the transcript's last
-			// unanswered quiz/ask part. Liveness (busy) is NOT record-derived —
-				// the API route merges it (contracts.ts ChatListItem).
-				phase: phaseOfTree(tree),
+				// transcript's explicit markers (probe_done / plan_init — the
+				// event-driven phases, docs/probe-teach-split.md §4), pending
+				// question from the last unanswered quiz/ask part. Liveness (busy)
+				// is NOT record-derived — the API route merges it (ChatListItem).
+				phase: phaseAt3(messages),
 				pendingQuestion: findPendingToolCall(messages) !== null,
 			}))
 			.sort((a, b) => b.updatedAt.localeCompare(a.updatedAt));