From 3558dba4854e7296e7c0ccafb559b46d5e3c76e4 Mon Sep 17 00:00:00 2001 From: Ilker Manap Date: Mon, 5 Oct 2026 12:29:05 +0200 Subject: [PATCH] v0.11.4 The OpenAPI document carries serve's tools field. Co-Authored-By: Claude Opus 5.5 (1M context) --- CHANGELOG.md | 2 +- docs/admin-api.openapi.json | 6 +++++- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index f6588178..283196ae 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -21,7 +21,7 @@ is only released once its **exit criterion** is met, not when its code lands. Until v1.0.0 the minor version is the breaking one: configuration formats and Go APIs change between minors without a deprecation period. -## Unreleased +## v0.11.4 — 2026-10-05 Two control planes, run in anger on the reference cluster. diff --git a/docs/admin-api.openapi.json b/docs/admin-api.openapi.json index 6693c38d..4219f346 100644 --- a/docs/admin-api.openapi.json +++ b/docs/admin-api.openapi.json @@ -7001,11 +7001,15 @@ }, "ctx_pool": { "type": "integer", - "description": "CtxPool is llama.cpp's --ctx-size; ContextLength what one request may use. They default to 16384 and 4096, what four parallel slots divide." + "description": "CtxPool is llama.cpp's --ctx-size; ContextLength what one request may use. They default to 16384 and 4096, what four parallel slots divide; llama.cpp is given as many slots as the pool holds requests." }, "context_length": { "type": "integer" }, + "tools": { + "type": "boolean", + "description": "Tools says the model makes tool calls the engine returns as calls: it is written into the catalog, where clients and editors read it. Check a running replica with llmgw ctl tool-check before saying so." + }, "cpu_cores": { "type": "integer", "description": "CPUCores is what a replica computes on; zero takes half the smallest node it fits on."