fix(agent): respect auxiliary.title_generation.timeout config for title generation

[liuhao1024]

What does this PR do?

Fixes generate_title() to respect the auxiliary.title_generation.timeout config setting instead of always using a hardcoded 30-second timeout.

Related Issue

Fixes #41812

Type of Change

• 🐛 Bug fix (non-breaking change that fixes an issue)

Changes Made

• agent/title_generator.py: Changed generate_title() default timeout from 30.0 to None, so call_llm() reads auxiliary.title_generation.timeout from config.yaml via its built-in _get_task_timeout() resolution.
• tests/agent/test_title_generator.py: Added 2 regression tests — one verifying the default timeout is None (delegates to config), and one verifying an explicit timeout value is forwarded correctly.

How to Test

1. Set auxiliary.title_generation.timeout: 300 in config.yaml
2. Start a new session with a slow local model (e.g., Ollama)
3. Title generation should now wait up to 300s instead of timing out at 30s
4. Run pytest tests/agent/test_title_generator.py -v — all 22 tests pass

Checklist

Code

• I've read the Contributing Guide
• My commit messages follow Conventional Commits (fix(scope):, feat(scope):, etc.)
• I searched for existing PRs to make sure this isn't a duplicate
• My PR contains only changes related to this fix/feature (no unrelated commits)
• I've run pytest tests/agent/test_title_generator.py -v and all tests pass
• I've added tests for my changes (required for bug fixes, strongly encouraged for features)
• I've tested on my platform: macOS

Documentation & Housekeeping

• I've updated relevant documentation (README, docs/, docstrings) — or N/A
• I've updated cli-config.yaml.example if I added/changed config keys — or N/A
• I've updated CONTRIBUTING.md or AGENTS.md if I changed architecture or workflows — or N/A
• I've considered cross-platform impact (Windows, macOS) per the compatibility guide — or N/A
• I've updated tool descriptions/schemas if I changed tool behavior — or N/A

Code Intelligence

• Analyzed: agent/title_generator.py::generate_title (callers: 1 via auto_title_session)
• Analyzed: agent/auxiliary_client.py::call_llm (timeout resolution: _get_task_timeout())
• Blast radius: LOW — only affects title generation timeout, no control-flow changes
• Related patterns: call_llm config-driven timeout resolution (timeout=None → _get_task_timeout(task))

[teknium1]

Thanks for the focused report and regression tests. This is already resolved on current main; this is an automated hermes-sweeper review.

• Commit 5126902f1d77ccca0fb7b0f9c780d9b80e6a4fe2 (fix(title): honor configured auxiliary timeout) made the same production change and added equivalent coverage. It shipped in v2026.7.1.
• agent/title_generator.py:51-88 defaults timeout to None and forwards it with task="title_generation".
• agent/auxiliary_client.py:6052-6080 resolves an unspecified timeout from auxiliary.{task}.timeout, so auxiliary.title_generation.timeout is honored.
• tests/agent/test_title_generator.py:62-91 verifies default config delegation and explicit-timeout precedence.
• The linked discussion on fix(agent): make title generation timeout configurable via auxiliary.title_generation.timeout #18129 identifies fix(agent): respect auxiliary.title_generation.timeout config for title generation #41831 as a duplicate of the same fix.