docs(btw): plan the separate model classifier experiment

[YUZHEthefool]

Summary

Provide a separate bilingual experimental guide for routing through an additional model call. Define the common-baseline comparison, failure cases, costs and evidence required for this candidate's future implementation.

Related issue

Related: #134
Parent: #122
Design: #28

Stack

• Base: split/btw-skill-routes. Depends on PR #145.
• Sibling experiments on the same base: #146, #148. These are alternatives, not dependencies.
• Tested shared baseline: 54987c857178edae1c169f63f795fefbe169d3d0.

Pages

• docs/zh/dev/btw-model-classifier-experiment.md
• docs/en/dev/btw-model-classifier-experiment.md
• docs/.vitepress/config.mjs (matching navigation entries)

Implementation notes

Selecting this architecture in advance, adding providers, and introducing a production framework for switching all candidate classifiers are outside scope.

Experiment status

Base branch: split/btw-skill-routes. Depends on PR #145. This PR shows only this feature's changes relative to that dependency. The original prototype at 33ee103a62937db3e930c89ba47a648b75cc7772 is provenance; integration follows current master's owners and authorization contracts. The parent issue records review/integration order.

This is one of three sibling draft PRs on the same feature baseline. Candidate-specific missing work is listed below; the documentation-only experiment drafts do not claim an implemented classifier.

Validation

Separate VitePress /help/ build passed. The final sibling's pages and navigation are identical to that validated candidate; explicit Prettier, Markdown lint, navigation checks and git diff --check passed on the final branch. No classifier implementation or model evaluation is included.

Local Node was 24.11.1; CI must validate the pinned toolchain. Relevant scoped formatting and Markdown checks were run. The root tracker records the final combined validation. No live model evaluation is implied by deterministic tests or documentation checks.

Compatibility and risk

Draft experiment plan. The original #28 had no separate model classifier to extract. Implementation, shared labelled corpus, evaluator, measurements and acceptance thresholds remain open; this PR must not be treated as a completed classifier.

Checklist

• A corresponding development Issue exists and this PR contains one feature or experiment.
• Tests and bilingual documentation accompany the change, or missing experimental implementation is explicitly described.
• Existing authorization, current APIs/configuration, Python 3.14+, and integrated documentation constraints are retained.
• No dependencies, credentials, generated site output, or fork publication claims are introduced.
• A human maintainer review and separate AI-assisted review have approved merging.

Repository references: AGENTS.md, GOVERNANCE.md, AI_POLICY.md, and the docs PR template.

Agent note

Codex prepared this PR at the user's request to split the original #28 implementation into reviewable features, with only classifier experiments marked as drafts. AI assisted extraction, current-path adaptation, tests, and English descriptions. The validation above was performed locally; remaining limitations are stated explicitly. This note is not a maintainer approval. No PR has been merged.

[xero-team-bot]

⚠️ This PR conflicts with its base branch and needs a rebase.

git fetch origin split/btw-skill-routes
git rebase origin/split/btw-skill-routes
# after resolving the conflicts
git push --force-with-lease

The needs-rebase label is removed automatically once the conflicts are gone.
(Xero-Team/AstrBot · detected by xero-bot)