feat: Add openqa-llm-investigate and integrate into auto-review hook

[okurz]

Motivation:
We want to integrate LLM analysis into the openQA investigation workflow to
provide concise summaries of test failures. This helps reviewers quickly
understand if an issue is a new product regression, a test regression, or an
infrastructure problem, without scheduling potentially costly openqa-investigate
jobs prematurely.

Design Choices:

• Created a standalone Python script openqa-llm-investigate using typer
  and httpx.
• The script acts as a gatekeeper in
  openqa-label-known-issues-and-investigate-hook: it parses the LLM's response
  and only outputs the job URL to trigger further bisections if the LLM
  determines it is necessary.
• Fetches job details, test results, and test history from the openQA API to
  build a comprehensive prompt.
• Used pytest and unittest.mock for unit testing the Python script.
• Updated the existing Bash test suite to mock and assert the execution of
  openqa-llm-investigate.

Example run openqa-llm-investigate -v https://openqa.opensuse.org/tests/5841514 --dry:

INFO: HTTP Request: GET https://openqa.opensuse.org/api/v1/jobs/5841514 "HTTP/1.1 200 OK"
INFO: HTTP Request: GET https://openqa.opensuse.org/tests/5841514/file/autoinst-log.txt "HTTP/1.1 200 OK"
INFO: HTTP Request: GET https://openqa.opensuse.org/tests/5841514/investigation_ajax "HTTP/1.1 200 OK"
INFO: HTTP Request: GET https://openqa.opensuse.org/api/v1/jobs?build=20260409-okurz-llm&test=extra_tests_gnome-okurz-llm&result=failed "HTTP/1.1 200 OK"
INFO: HTTP Request: POST http://localhost:8080/v1/chat/completions "HTTP/1.1 200 OK"
https://openqa.opensuse.org/tests/5841514
**LLM Investigation summary:**

The issue is an existing, recurring problem (failed 10 times in this build) that appears to be a product regression, as the failure is rooted in a low-level kernel panic/fatal page fault during the `multi_users_dm` test. Since the investigation info states "None available," we cannot determine if it is new compared to the last good build, but the high failure count suggests it is a persistent system instability. INVESTIGATE: YES, because the failure is a critical, low-level kernel crash affecting multiple runs in the current build, requiring deep system debugging.

Generated and posted example comment:
https://openqa.opensuse.org/tests/5841514#comment-887840

Benefits:

• Reduces the number of unnecessary and costly openqa-investigate jobs by
  filtering them through an LLM first.
• Provides immediate, actionable summaries of failures directly as openQA
  comments.
• Improves efficiency of test reviewers by providing context directly in the job
  page.

Related issue: https://progress.opensuse.org/issues/198056

[okurz]

included all suggestions from @d3flex