fix(tool_parsing): Qwen bare-marker regex strips remove \nend\n

[shuwudow]

Summary

Chat messages that have end statements, for example in the context of coding languages, cut off the \nend\n part.
The QWEN_BARE_MARKER_RE regex used optional pipe delimiters around end (\|?end\|?), which matched the bare keyword end on its own line. Chat messages containing Ruby code that closes blocks with a lone end — had those lines stripped from the rendered message in the front-end. The \nend\n part disappeared both from sent and received messages.

Fix: require the pipes (|end|) so the pattern only matches Qwen's actual turn marker. The |end| and /|end| cases still strip correctly, so Qwen artifact cleanup is unchanged.

Applied to the duplicate regex in both src/tool_parsing.py (backend) and static/js/chatRenderer.js (frontend).

Target branch

• This PR targets dev, not main.

Linked Issue

Fixes #5547

Linked to #5546 because both commits modify the same file (tool_parsing.py), however changed areas do not match.

Type of Change

• Bug fix (non-breaking — fixes a confirmed issue)
• New feature (non-breaking — adds new behaviour)
• Breaking change (changes or removes existing behaviour)
• Refactor / cleanup (behaviour unchanged)
• Documentation only
• CI / tooling / configuration

Checklist

• I searched open issues and open PRs — this is not a duplicate.
• This PR targets dev
• My changes are limited to the scope described above — no unrelated refactors or whitespace changes mixed in.
• I actually ran the app (docker compose up or uvicorn app:app) and verified the change works end-to-end. Type-checks and unit tests are not enough.

How to Test

1. Start via docker compose up -d --build
2. Paste snippet, for example:

loop do
    puts "yo"
end

3. After sending out the message, the end fragment shouldn't disappear anymore.

Since this change affects qwen models, I must mention that I verified its originally intended stripping functionality only by AI agent, I rebuilt Docker image, agent ran runtime regex substitution tests (Python + JS) showing bare end is preserved while |end|, /|end|>, </|end|>, and bare assistant are still stripped identically to pre-fix.
I did not test live Qwen model end-to-end. Should be Qwen-compatible — real Qwen markers are wrapped in | characters (like |end|), and those are still stripped correctly, unless I'm missing something.

Visual / UI changes — REQUIRED if you touched anything that renders

Anything that changes what the UI looks like — buttons, icons, padding, colors, fonts, spacing, layout, CSS, HTML, SVG, or any static/js/ module that draws to the DOM — needs all of the following. PRs that change rendering without these WILL be closed.

• Screenshot or short clip of the change in the running app, attached below. Mobile screenshot too if the change affects mobile.
• Style match: the change uses Odysseus's existing visual language. Specifically:
  • Reuse existing CSS variables (--red, --fg, --bg, --card, --border, etc.) — do not introduce new color values, font sizes, or spacing units.
  • Reuse existing button/input/card/border classes. Don't invent parallel styling.
  • No Unicode emoji in UI or code. Use inline SVG (matching the monochrome icon style already in static/index.html) or plain text.
  • Monospaced font (Fira Code) for primary UI text. Don't override.
  • Dark theme is the default; any light-mode work must be wired through the existing theme system, not hard-coded.
• No new component patterns. If a similar widget already exists in the app, extend it instead of writing a parallel one.
• I am not an LLM agent submitting a bulk PR. It is human-reviewed fix, used an agent one to spot it.

Screenshots / clips

before:

after: