feat(parsing): add support for Qwen tool call tokens and AST parsing

[CodeRulerNo1]

Summary

When Qwen models emit tool calls in their native token format:
<|tool_call_start|>[tool_name(args)]<|tool_call_end|>

They were not parsed or executed by src/tool_parsing.py, causing them to fail and leak into user-facing assistant messages as raw text.

This PR fixes the issue by:

1. Adding a new _QWEN_TOOL_CALL_RE regex pattern matching the start/end tags and parsing the function name + arguments.
2. Implementing _parse_qwen_tool_call which extracts argument keys/values using safe Python AST parsing (wrapping arguments in a dummy function call to evaluate keyword arguments) and falling back to a regex parser on syntax errors.
3. Adding the Qwen pattern matchers into parse_tool_blocks and strip_tool_blocks so the call executes correctly and the raw tags/tokens are cleaned from user-facing text.
4. Adding a suite of unit tests (tests/test_qwen_tool_call.py) covering empty arguments, multiple arguments, type coercion, and syntax recovery.

Target branch

• This PR targets dev, not main. All PRs land in dev; main is curated by the maintainer at each release. If your PR is on main by accident, click "Edit" on this PR and change the base.

Linked Issue

Fixes #5545

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. Run the new unit tests in the Odysseus environment:
   venv/bin/pytest tests/test_qwen_tool_call.py
2. Ensure both tests pass, demonstrating correct parsing of list_email_accounts() and list_emails(account="Gmail", ...) as well as clean stripping of the tokens.

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. If you are, please open an issue describing the problem first — bulk auto-generated PRs that don't match the project's visual style are closed on sight, even when the underlying fix is correct.

Screenshots / clips

None (pure token parsing backend utility, UI layout remains unchanged).