fix: SSE filter no longer drops content events for a different session

Bug: after switching to a new session via the SessionSelector, the
next /edit would not get a reply. Root cause: applyEvent dropped
ANY event whose sessionID didn't match the prompt's _sessionId,
including text deltas / reasoning / tool / idle. OpenCode's sessionID
extraction from event payloads is not perfectly consistent across
event types, so the prompt could end up with a stale _sessionId
that doesn't match the events coming in, and EVERY event got
filtered out -> no reply.

Fix: the cross-session filter is now strict ONLY for
permission.asked / question.asked (so the user can't accidentally
reply to another session's prompt). Content events always pass
through. The server's /events handler is the single source of
truth for session filtering (it has the URL ?session= param); the
client's filter would only ever mask the user's interaction with
their own active session.

Also: drop the cell-context auto-injection. The OpenCodeRequest
now carries only {notebookPath}. The user explicitly attaches
whatever they want via the new '📋 插入单元格内容' button
(inserts the cell source as a markdown code block into the input).
This makes the LLM context match user intent and stops the
OpenCode prompt from being polluted with stale previousCode /
traceback snapshots.

Backend
-------
- _build_request_body: now takes only the prompt, returns
  parts=[{text: prompt}]. No more <previous_cell>/<traceback>/<cell>
  tag wrapping.

Frontend
-------
- types.ts: CellContext collapsed to {notebookPath}. ErrorOutput /
  cellId / source / previousCode / error / cellIndex / totalCells
  / language all removed.
- opencode_cell_actions.ts: extractCellContextFromCell() replaced
  with extractNotebookPathFromCell(). _context field renamed to
  _notebookPath. NotebookPanel / extractCellContext / context/
  cell_context imports all removed.
- src/context/cell_context.ts + src/__tests__/cell_context.spec.ts:
  deleted.

New feature: '📋 插入单元格内容' button
----------------------------------------
The button sits at the start of the actions row (visually
left-aligned via margin-right:auto) and appends the current cell's
source as a markdown code fence to the textarea. Caret is moved
to the end so the user can keep typing. The fence info string is
the cell's model type (falls back to a plain fence if the type
isn't a clean language identifier). No-op for empty cells.

Tests
-----
- 72 jest (was 78: -8 cell-context tests + 1 SSE filter test +
  3 insert-cell tests + rewrites). 73 pytest (unchanged). Build
  green.

src/types.ts

@@ -10,21 +10,19 @@
  * a JSON object with a `type` string; consumers route on `type`.
  */
 
-export interface ErrorOutput {
-  ename: string;
-  evalue: string;
-  traceback: string[];
-}
-
+/**
+ * Minimal context carried with each edit request. Only the
+ * notebookPath is needed (so the server can pick the right OpenCode
+ * session). The cell source, previous-cell, and traceback are NO
+ * LONGER auto-injected into the LLM prompt — the user inserts them
+ * manually via the "📋 插入单元格内容" button (or pastes anything
+ * else they want) so the LLM only sees what they explicitly chose
+ * to send. v0.1.x used to pack a lot more here; that auto-wrap
+ * made the LLM context hard to reason about and made the user's
+ * intent ambiguous.
+ */
 export interface CellContext {
   notebookPath: string;
-  cellId: string;
-  language: string;
-  cellIndex: number;
-  totalCells: number;
-  source: string;
-  previousCode: string | null;
-  error: ErrorOutput | null;
 }
 
 export interface OpenCodeRequest {