fix(claude): derive context token budget from the Claude model in Claude Code mode

[herikwebb]

Problem

In Claude Code mode, ai_service_manager.chat_model reflects the user's most recent non-Claude provider selection and is None on a Claude-only setup. The attachment token budget in on_message fell through to the legacy 100-token floor (80 tokens after the 0.8 factor), which:

• silently skipped cell-output attachments (their estimate always exceeds 80 tokens), and
• dropped every attachment after the first via the remaining_token_budget <= 0 break.

Change

• New _resolve_context_token_limit helper: in Claude Code mode the budget comes from the configured Claude model via model_info_from_id (200K-window fallback for unknown/default ids); other modes keep the existing behavior.
• 6 regression tests, including an end-to-end on_message test proving a >80-token output context survives on a Claude-only setup.

Testing

Full Python suite passes (1298 tests).

[github-actions]

Automated PR Review

Model: gpt-5.5
Verdict: APPROVE

Changed files:

notebook_intelligence/extension.py
tests/test_websocket_handler_integration.py

Review result:

No automated findings were found in the changed code.

Residual risks: this review is based on the provided diff only; behavior still depends on model_info_from_id consistently returning a valid context_window and on nbi_config.claude_settings always being present in real runtime configurations.

[herikwebb]

Raised upstream as plmbr#390; closing this fork PR. Review history retained here.