extension/llm/server: serving foundations (schemas, errors, templating, tools)

[mergennachin]

Add the OpenAI server's standalone control-plane building blocks, independent of
the HTTP layer and of any model runtime: OpenAI request/response schemas
(protocol.py), structured errors (errors.py), HF chat templating
(chat_template.py), and tool-call parsers (tool_parsers/) for Hermes-style JSON
and Qwen XML. The wire contract is documented in spec/README.md. Unit-tested
under tests/ (tool parsing).

The HTTP server builds on these.

Part of #20001

[mergennachin]

Stack from ghstack (oldest at bottom):

• Qwen3.5-MoE CUDA V2 foundation: one model, many isolated sessions #20117
• examples/models/qwen3_5_moe: CUDA Engine/Session adapter + OpenAI serving #20043
• extension/llm/server: document pi integration #19999
• extension/llm/server: worker-based OpenAI-compatible HTTP server #19994
• -> extension/llm/server: serving foundations (schemas, errors, templating, tools) #19993
• extension/llm/runner: Engine/Session C++ core + token-step primitives #19991

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19993

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

✅ No Failures

As of commit 1842447 with merge base eeb0646 ():
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.