Evenfire is an intelligence layer platform for running LLM agents that take real actions, on your infrastructure
TypeScript
docs(llm-proxy): state that the eight stream slots are per proxy process
Alfredo Lopezd967d906efdd
diff --git a/docs/architecture/codex-subscription-transport-contract.md b/docs/architecture/codex-subscription-transport-contract.mdindex 606342e1d..5bc29bcb5 100644--- a/docs/architecture/codex-subscription-transport-contract.md+++ b/docs/architecture/codex-subscription-transport-contract.md@@ -183,6 +183,9 @@ must still be `authorized`, and the consuming `UPDATE` matches only| maxRetriesPerAttempt | 1 || executionTicketTtlMs | 60000 |+`maxConcurrentStreams` is 8 slots per proxy process, shared by every Host;+per-Host fairness is tracked in #767.+Tool definitions have no independent count ceiling in the Evenfire requestcontract. The entire serialized request, including all definitions, remainsbounded by `maxRequestBodyBytes`. Every definition still undergoesdiff --git a/docs/architecture/grok-subscription-transport-contract.md b/docs/architecture/grok-subscription-transport-contract.mdindex 39ed6af4d..c8e1ebfde 100644--- a/docs/architecture/grok-subscription-transport-contract.md+++ b/docs/architecture/grok-subscription-transport-contract.md@@ -152,6 +152,9 @@ The limit values live only in the table above, whichsame suite pins the fixture to the contract `LIMITS` and the proxy`STREAM_LIMITS`.+`maxConcurrentStreams` is 8 slots per proxy process, shared by every Host;+per-Host fairness is tracked in #767.+All three enforcement points read this module — the control-api authorizer,`grok-llm-proxy` and the Host — so a deployment that mixes versions rejectsrequests that fall between the old and the new bounds. Which code the caller