fix(consult): blank-line paragraphs, drop the H2 contract line, remove the assistant avatar

Acceptance fix for 28113fa0 (TASK-consult-conversational-answer-fix-20261006):
- F1: chat-answer-detail no longer pins 'Every H2 must start its own line'
  (first turns carry no H2), assertion change noted in three columns.
- F2: Good examples separate paragraphs with a blank line and the shape says
  so; .message p is pre-wrap, so a single newline only wraps.
- Product request: remove the assistant avatar on every surface (consult,
  rectification, onboarding); --assistant-content-inset back to 0px.

Full suite 4941 / fail 24, identical to baseline 86cafe68 minus a timing flake;
build keeps / Static; first-load gzip -0.1%.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8

frontend/DESIGN.md

@@ -370,7 +370,7 @@ The birth-time rectification session is the consultation transcript plus a house
 |---|---|---|
 | `opening` | live row “正在读取你的出生资料，准备第一个问题…”, then tool labels | enabled (typing queues), stop visible |
 | `empty` | “这段校正还没有开始。” and one primary action “开始提问” | enabled |
-| `question-live` | the asking message carries the embedded card or the spoken stem. An active spoken or choice focus without `asked_turn_id` hangs on the last assistant message, same avatar column. A deterministic reply streams “ack + stem” so the stem is readable before the card arrives; once the snapshot attaches the card, the bubble drops that sentence on the live transcript as well as on refresh (BUG-1045) | enabled, placeholder points at the card |
+| `question-live` | the asking message carries the embedded card or the spoken stem. An active spoken or choice focus without `asked_turn_id` hangs on the last assistant message, same text column. A deterministic reply streams “ack + stem” so the stem is readable before the card arrives; once the snapshot attaches the card, the bubble drops that sentence on the live transcript as well as on refresh (BUG-1045) | enabled, placeholder points at the card |
 | `question-gap`, persisted question | the snapshot's current question hangs on the latest settled assistant message (the client does this too, not only GET), and any other copy of the same `focus_id` comes off: one focus, one card (BUG-1046). The host question row (`data-testid="persisted-question"`) appears only when no assistant message can carry the prompt: there is none, or the latest one already carries a different question | enabled, placeholder “请回答上面的问题…” |
 | `question-live`, after a failed tap | the tapped option is taken back (question active again, nothing selected), the card remounts tappable, the Case is re-read, and the error line is “这次没提交上，请再点一次。” — never a second copy of the card below (BUG-1046) | enabled |
 | `question-gap`, retries left | one timeline live row “正在准备下一个问题…”, refetching on a 2s timer up to two retries | enabled |
@@ -479,7 +479,7 @@ The birth-time rectification session is the consultation transcript plus a house
 ### Message
 
 - **Variants:** assistant editorial text on canvas; user text on warm card surface; streaming; error. Streaming uses a timeline of completed steps plus the current step; the thinking body expands while streaming, collapses when answer text appears, and is stored with the assistant message.
-- **Identity:** neither role carries an avatar. The assistant reply is plain editorial text starting at the column edge; the user's turn is a right-aligned tinted bubble. The 32px Jyotisha logo used to sit beside every assistant message — at one avatar per turn it became the most repeated element in a long transcript, and it pushed the reply 44px in from the column the user reads down. `--assistant-content-inset` is `0px` now, so the follow-up chips and the run timeline line up with the reply text itself rather than with a mark that is gone.
+- **Identity:** neither role carries an avatar. The assistant reply is plain editorial text starting at the column edge; the user's turn is a right-aligned tinted bubble. The 32px Jyotisha logo used to sit beside every assistant message — at one avatar per turn it became the most repeated element in a long transcript, and it pushed the reply 44px in from the column the user reads down. `--assistant-content-inset` is `0px` now, so the follow-up chips and the run timeline line up with the reply text itself rather than with a mark that is gone. History: removed 2026-09-16 (R3), restored the same day after a real-device review because rectification narration had no visual owner (071317f7), removed again on 2026-10-06 at the product owner's request — on every surface, rectification and onboarding included. The rectification timeline bar and candidate cards use the same `0px` inset.
 - **Typography:** assistant body `--type-body-md` (16px) with serif subheadings; user body 14px.
 - **Tables:** three-column technique audit tables keep 状态 on one line. Below 768px they stack each row as title + status, then the note, instead of squeezing 已执行 into a vertical glyph column.
 - **Follow-up:** the latest settled consultation answer may offer two or three grounded next questions under that answer. Clicking one sends it in the current session. The composer never hosts suggestion chips. If the answer does not support a grounded continuation, nothing is shown.