Framework-agent failures return `None` instead of the failed task's reason

[ambiorix2099]

File: src/conductor/ai/agents/runtime/runtime.py

Symptom:

$ CONDUCTOR_AGENT_LLM_MODEL=anthropic/claude-sonnet-4-6 python examples/agents/93_openai_runner_hello_world.py
Framework agent 'Assistant' execution FAILED
None

No reason, no task name, nothing actionable. Diagnosing it means walking the server API by hand:

curl -s localhost:8080/api/agent/executions?size=20
curl -s localhost:8080/api/workflow/<executionId>   # find FAILED tasks, read reasonForIncompletion

Cause: The helper already exists and works — _extract_failed_task_reason(wf) reads the first FAILED task's reasonForIncompletion and returns Task '<ref>' failed: <reason>. It is called by run() (line ~2534) and _run_by_name() (line ~2623), which is why native-agent failures do report properly, e.g. 54_software_bug_assistant prints ERROR: Task 'software_assistant_54_list_mcp_0' failed: Failed to list MCP tools ... HTTP 400.

_run_framework() never calls it. It uses status.reason alone (error=status.reason if raw_status in ("FAILED","TERMINATED") else None), and for these failures status.reason is empty — so the result is None.

Fix: Call _extract_failed_task_reason in _run_framework as a fallback when status.reason is empty, matching run().

Verify: Start the server without OPENAI_API_KEY, run 93 — it should name the failing task and its reason instead of printing None.

Possibly a second gap, unconfirmed: 59_coding_agent goes through run() yet also reported no reason, while its server-side SUB_WORKFLOW task did carry one (Anthropic Messages API failed with status 404). _extract_failed_task_reason only inspects the top-level workflow's tasks, so failures inside a sub-workflow may need the same treatment. Worth checking while fixing this.