* Add Azure API Management AI Gateway instructions
APIM as a GenAI gateway for Microsoft Foundry and OpenAI-compatible LLM APIs:
llm-* token-limit/token-metric policies, managed-identity auth, backend pools
with circuit breakers, semantic caching, and content safety. Corrects the
azure-openai-*/api-key/element-ordering defaults the model produces unprompted.
Regenerates docs/README.instructions.md.
* Potential fix for pull request finding
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
* Address Copilot review feedback on APIM AI gateway instructions
* Fix AI gateway auth scope and Consumption-tier note per review
* Fix circuit-breaker 429, auth-role contradiction, and malformed XML per review
* Harden semantic cache isolation, logging privacy, and policy order per review
* Complete emit-token-metric prerequisites and Foundry private-networking requirement
* Fix Bicep array syntax and use supported JWT accessor per review
* Correct content-safety tier support and response-screening default per review
* Fix cache-partition identity, skeleton isolation, and metric cardinality per review
* Make policy expressions valid XML and clarify content-safety timing
---------
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>