Simplify fn calling usage

[enyst]

Give a summary of what the PR does, explaining any non-trivial design decisions

This PR proposes to clean up mock_function_calling var from the agent. The llm knows if it supports it.
It's just a little clean-up, to help us read this code (part of refactoring towards message <-> event)

---

To run this PR locally, use the following command:

docker run -it --rm   -p 3000:3000   -v /var/run/docker.sock:/var/run/docker.sock   --add-host host.docker.internal:host-gateway   -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:cdb9248-nikolaik   --name openhands-app-cdb9248   docker.all-hands.dev/all-hands-ai/openhands:cdb9248

[enyst]

This isn't really used in the agent, it's used in llm.py

[github-actions]

Hi! I started running the integration tests on your PR. You will receive a comment with the results shortly.

[github-actions]

Trigger by: Pull Request (integration-test label on PR #6596)
Commit: 03f49ec
Integration Tests Report (Haiku)
Haiku LLM Test Results:
Success rate: 100.00% (7/7)

Total cost: USD 0.08

instance_id	success	reason	cost	error_message
t07_interactive_commands	True		0.005	nan
t04_git_staging	True		0.006	nan
t01_fix_simple_typo	True		0.015	nan
t03_jupyter_write_file	True		0.007	nan
t02_add_bash_hello	True		0.007	nan
t06_github_pr_browsing	True		0.031	nan
t05_simple_browsing	True		0.007	nan

---

Integration Tests Report (DeepSeek)
DeepSeek LLM Test Results:
Success rate: 85.71% (6/7)

Total cost: USD 0.02

instance_id	success	reason	cost	error_message
t05_simple_browsing	False	The answer is not found in any message. Total messages: 2.	0.003	nan
t04_git_staging	True		0.002	nan
t03_jupyter_write_file	True		0.002	nan
t01_fix_simple_typo	True		0.003	nan
t02_add_bash_hello	True		0.002	nan
t06_github_pr_browsing	True		0.005	nan
t07_interactive_commands	True		0.003	nan

---

Integration Tests Report Delegator (Haiku)
Success rate: 50.00% (1/2)

Total cost: USD 0.05

instance_id	success	reason	cost	error_message
t02_add_bash_hello	True		0.022	nan
t01_fix_simple_typo	False	File not fixed: This is a text with a typo.	0.028	nan
		Really?
		No more errors!
		Enjoy!

---

Integration Tests Report Delegator (DeepSeek)
Success rate: 100.00% (2/2)

Total cost: USD 0.00

instance_id	success	reason	cost	error_message
t01_fix_simple_typo	True		0.001	nan
t02_add_bash_hello	True		0.002	nan

---

Integration Tests Report VisualBrowsing (DeepSeek)
Success rate: 100.00% (1/1)

Total cost: USD 0.00

instance_id	success	reason	cost	error_message
t05_simple_browsing	True		0.001	nan

---

Download testing outputs (includes both Haiku and DeepSeek results): Download