feat(btw): submit explicit work tasks through builtin commands

[YUZHEthefool]

Summary

Register /work as a real built-in command that preserves its complete task argument and explicitly hands it to the work loop without automatic classification. Disabled work returns a localized explanation.

Related issue

Related: #124
Parent: #122
Design: #28

Stack

• Base: split/btw-result-delivery. Depends on PR #138.
• Follow-up PRs: #140.

Behavior

Register /work as a real built-in command with stable command identity. Preserve the complete task remainder and continue through the authorized Agent request path. Bare /work and the exact status argument are reserved for B5's status query.

Non-goals

Automatic classification, task persistence, and additional command namespaces are outside this slice.

Implementation notes

Base branch: split/btw-result-delivery. Depends on PR #138. 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.

No new HTTP contract or dependency changes. Feature settings and behavior are documented in both languages.

Validation

60 passed across built-in command, import-boundary, conversation-loop, and ProcessStage tests. Scoped Ruff, Prettier, i18n and Markdown checks passed.

Python checks used the existing Python 3.14.1 environment with python -m pytest and task-local --basetemp directories. 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

Depends on B4 for the runnable background submission path. Bare /work and the reserved status argument show usage in this slice; B5 adds the actual latest-task status query. Command identity and permissions use the current command catalog.

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 feat 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.