feat(rag): pass chat history with prior thinking to the LLM

Phase 74 (TODO.md L4): a follow-up question now reaches the model WITH
the conversation so far — every prior user/brain turn and the prior
thinking blocks on brain turns (preserve-thinking) — while
POST /api/chat stays stateless (A10): the client provides the history
in the request body and the server stores nothing new.

Server (task 01):
- ChatRequest.history: optional list[HistoryTurn] (who: user|brain,
  text, optional thinking) — absent/empty keeps the request
  byte-identical to pre-phase-74 (the two-message [system, user]
  request; the kill-switch semantics are pinned in the integration
  suite).
- app.rag.prompts.history_to_messages: pure mapper — walks the turns
  newest-first against the settings budgets (history_max_turns=40 /
  history_max_chars=24000, BOR_HISTORY_MAX_TURNS /
  BOR_HISTORY_MAX_CHARS); a capped turn is dropped WHOLE (never cut
  mid-answer); the kept window is returned oldest-first; brain turns
  carry their thinking as reasoning_content (A4) only when
  non-empty.
- Both branches feed it: the deflected path splices it between the
  system prompt and the current user message (the phase-71 recovery
  still rebuilds from messages[1:]), the grounded agent receives
  run_agent(..., history=hist); llm.py's message params widen to
  list[dict[str, Any]] (string-only messages stay byte-identical on
  the wire — the SDK passes message dicts through verbatim).
- The per-turn log line (PLAN §9) gains history_msgs=N after
  kb_chars=N.
- Pins: tests/unit/test_history.py (mapper: mapping, reasoning
  gating, both budgets, drop-whole, ordering, empty default),
  tests/unit/test_config.py (the two settings + env overrides),
  tests/unit/test_agent.py (the history splice + the default),
  tests/integration/test_chat_api.py (deflected AND grounded forward
  the history incl. reasoning_content, no-history byte-identity, 422
  pins, the log field).

Client (task 02):
- runTurn — the single funnel for fresh send / phase-49 retry /
  phase-53 stale-regen — sends history = the conversation record
  minus the current question, with thinking only on brain records
  that streamed one (undefined drops the key from the JSON, the
  record's convention); the question is never duplicated into the
  history.

Wire proof (task 03):
- The mock's echo my history marker (HISTORY_TRIGGER) answers with
  the deterministic history echo — history: N prior messages; last
  answer tail: <last 24 chars>; thinking: yes|no — checked BEFORE
  the DEFLECT_MODE branch (like TABLE_TRIGGER), so it fires on both
  turn branches whatever the gate says; the module docstring records
  the user/assistant-only history invariant that keeps every
  existing (tool-result-classified) marker flow unaffected.
- tests/e2e/test_llm_history.py (isolated): a grounded follow-up and
  a deflected follow-up both receive history: 2 prior messages +
  thinking: yes + the byte-exact tail of turn 1's answer (derived
  from the persisted bor.chat.v1 record — the same array the client
  maps into the body); a cold start receives history: 0 prior
  messages / last answer tail: none / thinking: no.
- Regressions green in isolation: chat_rag, chat_history (phase 50),
  agent_document_tools, harness_aligned_tools, stop_generation,
  retry_answer, response_to_docs.

frontend/assets/app.js

@@ -1972,10 +1972,31 @@ async function runTurn(text, { reask = false } = {}) {
       setUiState(UI_STATE.error, "That's taking a long time — the answer may be stuck.");
     });
 
+    // Phase 74 (TODO L4): the conversation so far travels WITH the
+    // question — the `conversation` record minus the current question.
+    // The invariant every caller holds at fetch time: a fresh send just
+    // pushed the question (save point 1 above); the phase-49 retry and
+    // the phase-53 stale-regen (both through retryLastTurn) popped the
+    // old answer and keep the question as the last entry — so slice(0,
+    // -1) is exactly the prior turns, oldest first, and the question is
+    // never duplicated into the history. `thinking` rides only brain
+    // records that actually streamed one (phase 17's optional key —
+    // `undefined` drops it from the JSON, the record's convention);
+    // user turns and old/restored records without thinking send none
+    // (the server maps those to plain assistant messages). No other
+    // record key (`sources`, `tools`, `deflected`, `suggestions`,
+    // `stopped`) travels in the body — the server schema (task 01)
+    // accepts exactly {who, text, thinking}; `tools` metadata is
+    // display-only and was never part of the LLM wire.
+    const history = conversation.slice(0, -1).map((m) => ({
+      who: m.who,
+      text: m.text,
+      thinking: m.who === "brain" ? m.thinking || undefined : undefined,
+    }));
     res = await fetch("/api/chat", {
       method: "POST",
       headers: { "Content-Type": "application/json" },
-      body: JSON.stringify({ message: text }),
+      body: JSON.stringify({ message: text, history }),
       signal: turnAbort.signal, // phase 48: the Stop button aborts the fetch
     });
     if (!res.ok || !res.body) {