feat: support llmman as an Ollama-compatible local backend

[ericcurtin]

Pull Request

Description

llmman is a local model runner that serves the Ollama API on port 17434, so NativeMind's existing Ollama backend works with it once the Server Address is set to http://localhost:17434/api.

• utils/web-request.ts: widen the Chrome dynamic declarativeNetRequest Origin-stripping rule from :11434 to :(?:11434|17434); without it llmman hits the same CORS issue as Ollama from a chrome-extension:// origin. Same rule ID.
• public/rules.json: same widening for the static rule Firefox uses.
• README.md: llmman subsection under "AI Model Options" plus a troubleshooting line. No new UI or locale strings.

Type of change

• New feature (non-breaking change which adds functionality)
• Documentation update

How Has This Been Tested?

Testing: pnpm install --frozen-lockfile, pnpm wxt prepare, pnpm compile (vue-tsc --noEmit) and eslint utils/web-request.ts pass; both regexes checked in Node to match localhost:17434 / 127.0.0.1:11434 and reject other ports.

Checklist:

• My code follows the style guidelines of this project
• I have performed a self-review of my code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes
• Any dependent changes have been merged and published in downstream modules

AI-assisted, reviewed before submitting.