fix(runner): handle model-object tool calls in verbose logging

[Sai Asish Y (SAY-5)]

Fixes #54.

DedalusRunner(..., verbose=True).run(..., tools=[...]) crashes with AttributeError on the first response containing tool calls. The verbose print paths call .get("function", {}) on tool-call entries, which works for the ToolCall TypedDicts produced by _extract_tool_calls but not for the SDK model objects read straight off API responses (e.g. in _execute_turns_sync at the Tool calls in response log line, and the message-history dumps).

This adds a small _tool_call_name(tc) helper that accepts either dicts or attribute-style model objects, and uses it in the affected verbose print paths. Non-verbose behavior is unchanged.

Test plan

• New tests/test_runner_verbose.py: unit-tests _tool_call_name for dicts/model objects, and a regression test running runner.run(verbose=True, tools=[add]) against a mocked client returning model-style tool calls (fails on main, passes here).
• pytest tests/test_local_scheduler.py tests/test_runner_verbose.py green.
• ruff check/ruff format --check clean on changed files.

[cursor]

PR Summary

Low Risk
Changes are limited to verbose debug printing; tool execution and non-verbose paths are unchanged.

Overview
Fixes #54: DedalusRunner with verbose=True no longer crashes when the API returns tool calls as SDK model objects instead of dicts.

Adds _tool_call_name(tc) to resolve a tool’s function name from either dicts or attribute-style objects, and routes all verbose logging paths (sync/async turns, streaming summaries, message history dumps) through it instead of calling .get(...) on raw response tool calls.

Adds tests/test_runner_verbose.py with unit coverage for the helper and an end-to-end regression that runs verbose=True with mocked model-style tool calls.

^{Reviewed by Cursor Bugbot for commit 58cd1c9. Bugbot is set up for automated code reviews on this repo. Configure here.}

[Sai Asish Y (SAY-5)]

Good catch. Updated the two remaining verbose sites (the extracted-calls list and the end-of-stream summary) to go through _tool_call_name so model-object tool calls no longer fall back to an inconsistent value.

[cursor]

Cursor Bugbot has reviewed your changes and found 1 potential issue.

^{Bugbot Autofix is ON, but it could not run because the branch was deleted or merged before autofix could start.}

^{Reviewed by Cursor Bugbot for commit 69c4276. Configure here.}

[Sai Asish Y (SAY-5)]

Good catch, the loop in _execute_turns_async was the last inline copy. Switched it to the helper and dropped the dead non-dict branch for tc_id in 58cd1c9.