feat(chat): implement web chat interface with accessibility

Core implementation:
- chat_app.py: Chainlit entry point with @cl.on_chat_start,
  @cl.on_message (streaming via llm.stream_complete), @cl.on_chat_end
  Reuses Config, KnowledgeBase, ConversationStore, AdminNotifier from src/
  Handles registration completion, post-completion updates, new-child flow

- src/llm.py: add stream_complete() generator (litellm stream=True)
  alongside existing complete(); tests added in tests/test_llm.py

- src/agent/response_parser.py: extract parse_llm_response(),
  apply_updates(), fallback_message() from EmailAgent into shared module
  EmailAgent now delegates to these functions (no logic change)

Chainlit configuration:
- chainlit.toml: telemetry off, German default, custom CSS + JS paths
- chainlit.md: German welcome page with playgroup info

Accessibility (WCAG 2.1 AA):
- public/custom.css: contrast overrides (≥4.5:1), prefers-reduced-motion
  (static "…" replaces animated dots), skip link styles, 100dvh fix
- public/accessibility.js: MutationObserver injects aria-live="polite"
  on message list, focus management after agent replies, skip link element

Other:
- .gitignore: add .chainlit/ (Chainlit runtime, auto-generated)
- openspec/config.yaml: populate context field with tech stack
- openspec/changes/implement-web-chat/tasks.md: mark completed tasks

95 tests pass.

https://claude.ai/code/session_01SUWzMzFvSfWiHXA2p6rPg9

src/llm.py

@@ -1,5 +1,7 @@
 """LLM completion via litellm — supports any provider with a single call."""
 
+from collections.abc import Generator
+
 import litellm
 
 
@@ -20,3 +22,27 @@ def complete(model: str, system: str, messages: list) -> str:
     api_messages += [{"role": m.role, "content": m.content} for m in messages]
     response = litellm.completion(model=model, messages=api_messages, max_tokens=2048)
     return response.choices[0].message.content
+
+
+def stream_complete(
+    model: str, system: str, messages: list
+) -> Generator[str, None, None]:
+    """Call any LLM with streaming and yield text chunks as they arrive.
+
+    Args:
+        model: litellm model string (same format as ``complete``).
+        system: System prompt text.
+        messages: List of objects with .role and .content attributes.
+
+    Yields:
+        Non-empty text chunks from the model's streamed response.
+    """
+    api_messages = [{"role": "system", "content": system}]
+    api_messages += [{"role": m.role, "content": m.content} for m in messages]
+    response = litellm.completion(
+        model=model, messages=api_messages, max_tokens=2048, stream=True
+    )
+    for chunk in response:
+        delta = chunk.choices[0].delta.content
+        if delta:
+            yield delta