feat(advisor) 3/4: wire activation into the query layer

[ericleepi314]

3/4 in the /advisor stack. Stacked on PR 2.

Summary

With helpers + provider preservation in place, this is the actual server-side parity wiring — same beta header, same schema, same instructions, same cache-preserving order as typescript/src/services/api/claude.ts.

• src/state/app_state.py — adds advisor_model: str | None = None + _on_advisor_model_change handler. The handler persists to settings.advisor_model via the shared default ConfigManager AND invalidates the settings cache, so mid-session toggles via the reactive store reach the next API call without a process restart. Registered in _FIELD_HANDLERS to satisfy the coverage contract.
• src/query/query.py — _call_model_sync now:
  1. Computes advisor_active via a single try/except wrapper: first-party Anthropic + env not disabled + settings.advisor_model set + model_supports_advisor(provider.model) + is_valid_advisor_model(candidate). Any exception → inactive (caught + logged).
  2. When inactive, strips historical advisor blocks via strip_advisor_blocks (API 400s on advisor blocks without the beta header).
  3. When active, appends the advisor schema AFTER the cached tool list (preserves the cache_control marker position), sets betas=[ADVISOR_BETA_HEADER], and appends ADVISOR_TOOL_INSTRUCTIONS to the system prompt's tail. The append order mirrors TS claude.ts:1395, 1411-1421 — toggling /advisor doesn't bust the cache prefix.
  4. After the response, preserves raw_content_blocks (from PR 2) into assistant_blocks so the pair survives history replay.

A stale advisor_model setting under a non-supporting base model is silently ignored — never sent to the API. Mirrors the TS "skipping advisor — base model X does not support advisor" branch.

Stack

• PR 1 (feat(advisor) 1/4: helpers + settings field + orphan tool_use guard #176) — helpers + settings + orphan guard
• PR 2 — provider raw_content_blocks
• PR 3 (this PR) → PR 2
• PR 4 (slash command + TUI) → this branch

Test plan

• tests/test_advisor_request_wiring.py — 12 tests: full activation matrix on first-party Anthropic + defensive activation (synthetic exception in the gate → turn proceeds without advisor). Verifies the beta header attaches, schema appends AFTER regular tools, instructions append to both string and block-list system prompts, advisor blocks survive in history when active. Negative: env disabled, custom base_url, unsupported base model, invalid advisor model, settings unset.
• tests/integration/test_advisor_smoke.py — 3 tests: mocked Anthropic stream with the full advisor pair preserved across turns. Interrupt scenario: orphan use stripped on next-turn replay even when beta IS active.

🤖 Generated with Claude Code