Wave B: the native message record — input events, projection, adapter death

The chat record is now pi-native agent history (LhMessage[]), the AI SDK's
UIMessage transcript contract is gone from the server, and every client turn
arrives as ONE explicit input event.

Core (new):
- src/core/native-messages.ts — the LhMessage taxonomy (user/assistant/
  toolResult + lhMarker customs: verdict, probe-handoff, subagent-steer,
  subagent-abort, plan-block), constructors, and toLlmMessages — the single
  model-facing seam (convertToLlm): strips ids, flattens markers to user
  text, drops UI-only plan-blocks, synthesizes INTERRUPTED results for
  dangling aborted calls, never throws.
- src/core/projection.ts — projectNative: the one-way native → UIMessage
  projection (consecutive assistant+toolResult runs group into one
  assistant view message; toolResults attach backward by toolCallId;
  markers project to data parts; plan-blocks splice after the last
  successful plan_init). Every existing consumer reads through it.
- src/core/input-events.ts — the ChatInput union (text/answer/verdict/
  continue), parseChatInput validation, and inputAppends (answer targets
  the dangling question call or 400s; verdict = optional note user
  message + native verdict marker).

Server:
- chat-handler.ts — the turn root takes {chatId, input}; write-ahead
  persists input appends + claimed steers before the turn; claimSteers
  coalesces the whole queue with the handler's steerDelivered filter as
  the dedupe seam; teacher-vs-prober branch on hasProbeDone.
- turn-service.ts — persistTurn stamps ids, drops clean question
  placeholder toolResults (the record ends at the unanswered call),
  emits plan-block markers idempotently (plan-blocks.ts rewrite), and
  persists abort partials.
- ui-stream.ts — PiTurnSpec takes the native base; the wire dialect is
  unchanged. jobs.ts steers are native markers (steer_<jobId> dedup ids);
  waitForIdle reads danglingQuestionOf. teacher-agent.ts wires
  convertToLlm: toLlmMessages. record-adapter.ts DELETED wholesale.
- GET /api/chats/[id] serves messages: projectNative(record.messages).

Client:
- chat-transport.ts — the 409 retry is IDENTITY (re-POST the same event
  body after the turn settles — the event was never persisted
  pre-acceptance; the merge logic is gone). The transport consumes the
  stashed input event via prepareSendMessagesRequest and throws loudly on
  a missing stash.
- chat.tsx — every send call site stashes exactly one ChatInput event
  (text, answer, verdict, continue) before invoking the SDK send.

Tests: full native migration (chat-flow rewritten to input events and
native record pins; jobs/extraction/demos/graph/usage/plan-blocks/
probe-done/reattach-transport converted; record-adapter.test.ts deleted;
chat-transport tests pin the identity retry). 982/982, typecheck, lint,
build all green.

src/core/contracts/chat.ts

@@ -8,22 +8,27 @@
  */
 import type { UIMessage } from "ai";
 import type { ThinkingLevel } from "@earendil-works/pi-agent-core";
+import type { LhMessage } from "../native-messages.ts";
 import type { Phase3 } from "../phases.ts";
 import type { PlanNodeStatus, PlanTree } from "./plan.ts";
 import type { EmissionStats, UnderstandingLevel } from "./graph.ts";
 
 // ─── Chat records (the session store's on-disk format) ───────────────────────
 
-/** One persisted session: data/chats/<id>.json. The stored messages are full
- * AI SDK UIMessages (parts included) — the canonical session record: a
- * pending quiz is a tool part in `input-available` state, which is exactly
- * what makes resume-mid-question free. */
+/** One persisted session: data/chats/<id>.json. Wave B (owner-approved
+ * 2026-09-26): the stored messages are pi-NATIVE history (LhMessage — the
+ * agent loop's own shapes, provider/model/usage/thinkingSignature stamped
+ * by pi) — the canonical session record IS the agent state; replay is
+ * `state.messages = record.messages` + continue(). The client-shaped view
+ * is the one-way projection (core/projection.ts) — a pending quiz is an
+ * unanswered question tool call, which is exactly what makes
+ * resume-mid-question free. */
 export interface ChatRecord {
 	id: string;
 	title: string;
 	createdAt: string;
 	updatedAt: string;
-	messages: UIMessage[];
+	messages: LhMessage[];
 	/** The session's plan tree (vision §2) — written by plan tools via saveTree. */
 	tree?: PlanTree;
 	/** Append-only usage log (observability, 2026-09): one entry per model
@@ -152,8 +157,8 @@ export interface TurnUsage {
  *  both verdicts are real transcript events: accept sanctions teaching,
  *  decline asks for revision. The part is the message TYPE (the "custom
  *  message" scheme, 2026-09-12): the message carries no human-authored text,
- *  the model-facing wording is owned by the adapter (record-adapter.ts
- *  flattens it to VERDICT_TEXT below), and the UI renders the verdict
+ *  the model-facing wording is owned by toLlmMessages (native-messages.ts
+ *  flattens it to verdictText below), and the UI renders the verdict
  *  marker — never a user bubble. A learner who also typed a note sends the
  *  note as its own real user message first; the verdict message follows. */
 export interface PlanVerdictData {