Impossible to set specific prompts for Crew with prompt_file

[baleksey]

Feature Area

Core functionality

Is your feature request related to a an existing bug? Please link it here.

Setting crew like this:

crew = Crew(
        agents=[agent], 
        tasks=[task], 
        prompt_file="/path/to/new_prompts.json")

do absolutely nothing. In source code it uses prompt_file only in _create_manager_agent function. It doesn't change prompts for current crew/agents.

Is there any workarounds/hacks to set specific prompts for specific agent/crew/task (not globally with ../translations/en.json) before this bug will be fixed?

Describe the solution you'd like

It must function as expected: setting prompt_file for specific crew will change prompts for this crew/agents/tasks.

Describe alternatives you've considered

No response

Additional context

No response

Willingness to Contribute

I can test the feature once it's implemented

[norika1207-lab]

One practical way to make this easier to evaluate is to turn the report into a small contract test around the runtime boundary, not only the user-facing symptom.

For specific prompts for Crew with prompt_file, I would check three things: first, the failing input is preserved as a minimal fixture; second, the SDK emits the same observable event/result shape before and after the fix except for the intended change; third, the trace or serialized session contains enough metadata to explain what happened after a resume or retry.

The part that matters for agent systems is durability: if a tool call, memory write, handoff, or structured-output step fails, downstream code should not have to infer state from natural-language output. A focused regression test around that boundary would make the issue much easier to close with confidence.