feat(uagents): add OrcaRouter as a named LLM provider for ChatAgent

[XiaoHuo888-hue]

This registers OrcaRouter the same way the existing asi1 provider is wired, so LLMConfig.orcarouter() joins LLMConfig.asi1() as a first-class factory and the model/config docs stay consistent. OrcaRouter is an OpenAI-compatible gateway: one ORCAROUTER_API_KEY (keys start with sk-orca-) unlocks 150+ models from OpenAI, Anthropic, Google, DeepSeek, Qwen, MiniMax and xAI behind a single https://api.orcarouter.ai/v1 endpoint. It also runs gateway-level, zero-trust security for AI agents on the same endpoint — screening every prompt/response and governing every tool call on a default-deny basis, with no application code changes.

I'm an engineer on the OrcaRouter team.

Proposed Changes

• python/src/uagents/experimental/chat_agent/llm.py — add LLMConfig.orcarouter() factory mirroring asi1(): reads ORCAROUTER_API_KEY (required), defaults to https://api.orcarouter.ai/v1 and model orcarouter/auto, both overridable via ORCAROUTER_BASE_URL and the model argument.
• python/src/uagents/experimental/chat_agent/README.md — document LLMConfig.orcarouter() in the LLM Configuration example.
• python/tests/test_chat_agent_llm.py (new) — 3 unit tests covering the missing-key error, defaults, and base_url/model overrides.

Linked Issues

None.

Types of changes

What type of change does this pull request make (put an x in the boxes that apply)?

• Bug fix (non-breaking change that fixes an issue).
• New feature added (non-breaking change that adds functionality).
• Breaking change (fix or feature that would cause existing functionality to stop working as expected).
• Documentation update.
• Something else (e.g., tests, scripts, example, deployment, infrastructure).

Checklist

Put an x in the boxes that apply:

• I have read the CONTRIBUTING guide
• Checks and tests pass locally

If applicable

• I have added tests that prove my fix is effective or that my feature works
• I have added/updated the documentation (executed the script in python/scripts/generate_api_docs.py)

Verification

• uv run ruff check and uv run ruff format --check: clean on all changed files.
• uv run pytest: 110 passed, 0 failed (includes the 3 new orcarouter tests).
• Live test with a real OrcaRouter key: LLMConfig.orcarouter() + LLM.complete() returns PONG via orcarouter/auto.