Release abstractgateway 0.2.25

Author: lpalbou

CHANGELOG.md

@@ -7,6 +7,16 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.2.25] - 2026-05-31
+
+### Changed
+- Set Gateway container defaults for host-native LM Studio and Ollama endpoints so named provider discovery does not default to `localhost` inside the container.
+- Updated Docker deployment docs to use `LMSTUDIO_BASE_URL` for LM Studio and `OPENAI_BASE_URL` for generic OpenAI-compatible endpoints.
+
+### Fixed
+- Fixed Gateway Console capability-default model discovery so the Base URL field is forwarded to the provider model catalog before saving.
+- Fixed Docker Compose/OpenAI-compatible documentation drift where `OPENAI_COMPATIBLE_BASE_URL` was shown as the primary AbstractCore discovery variable even though AbstractCore uses `OPENAI_BASE_URL`.
+
 ## [0.2.24] - 2026-05-31
 
 ### Added

README.md

@@ -95,15 +95,15 @@ Release images are published to GHCR. The default image is the light,
 portable server image:
 
 ```bash
-docker pull ghcr.io/lpalbou/abstractgateway:0.2.24
+docker pull ghcr.io/lpalbou/abstractgateway:0.2.25
 ```
 
 NVIDIA hosts can try the experimental full GPU image when local
 vLLM/HuggingFace/Diffusers engines are wanted. This image is published
 best-effort until it has a real CUDA build and smoke gate:
 
 ```bash
-docker pull ghcr.io/lpalbou/abstractgateway:0.2.24-gpu
+docker pull ghcr.io/lpalbou/abstractgateway:0.2.25-gpu
 ```
 
 Legacy `abstractgateway-server` and `abstractgateway-server-nvidia` GHCR aliases
@@ -129,7 +129,7 @@ docker run --rm --name abstractgateway \
   -p 8080:8080 \
   -e ABSTRACTGATEWAY_DATA_DIR=/data \
   -e ABSTRACTGATEWAY_USER_AUTH=1 \
-  -e OPENAI_COMPATIBLE_BASE_URL="http://host.docker.internal:1234/v1" \
+  -e LMSTUDIO_BASE_URL="http://host.docker.internal:1234/v1" \
   -v "$PWD/runtime:/data" \
   ghcr.io/lpalbou/abstractgateway:latest
 ```
@@ -142,17 +142,18 @@ Configure framework model defaults through execution-host capability routes:
 
 ```bash
 docker exec abstractgateway abstractgateway-config set-default output.text \
-  --provider openai-compatible \
+  --provider lmstudio \
   --model your-model \
   --base-url http://host.docker.internal:1234/v1
 ```
 
 On Apple Silicon, keep Metal/MLX inference native on macOS and run the
 lightweight Gateway container as the transport/control plane. Point
-`OPENAI_COMPATIBLE_BASE_URL` at a host-native OpenAI-compatible endpoint such
-as Docker Model Runner (`http://model-runner.docker.internal/engines/v1`), LM
-Studio (`http://host.docker.internal:1234/v1`), Ollama
-(`http://host.docker.internal:11434/v1`), or `mlx_lm.server` on a host port.
+`OPENAI_BASE_URL` at a generic host-native OpenAI-compatible endpoint such as
+Docker Model Runner (`http://model-runner.docker.internal/engines/v1`) or
+`mlx_lm.server` on a host port. For named providers, use
+`LMSTUDIO_BASE_URL=http://host.docker.internal:1234/v1` or
+`OLLAMA_BASE_URL=http://host.docker.internal:11434`.
 For native non-Docker installs with local engines, use
 `pip install "abstractgateway[apple]"` on Apple Silicon, and
 `pip install "abstractgateway[gpu]"` on GPU workstations or NVIDIA Docker builds.

docker/abstractgateway-server/.env.example

@@ -51,7 +51,9 @@ PORTKEY_CONFIG=
 # http://model-runner.docker.internal/engines/v1, http://host.docker.internal:1234/v1,
 # or http://host.docker.internal:11434/v1.
 # LM Studio/Ollama text endpoints are not assumed to expose image generation.
-OPENAI_COMPATIBLE_BASE_URL=http://host.docker.internal:1234/v1
+OPENAI_BASE_URL=http://host.docker.internal:1234/v1
+# Legacy/compatibility alias used by some operators; AbstractCore discovery uses OPENAI_BASE_URL.
+OPENAI_COMPATIBLE_BASE_URL=
 OPENAI_COMPATIBLE_API_KEY=
 LMSTUDIO_BASE_URL=http://host.docker.internal:1234/v1
 OLLAMA_BASE_URL=http://host.docker.internal:11434

docker/abstractgateway-server/Dockerfile

@@ -14,7 +14,9 @@ ENV PYTHONDONTWRITEBYTECODE=1 \
     ABSTRACTGATEWAY_USER_AUTH=1 \
     ABSTRACTGATEWAY_WORKFLOW_SOURCE=bundle \
     ABSTRACTGATEWAY_STORE_BACKEND=file \
-    ABSTRACTGATEWAY_ALLOWED_ORIGINS=http://localhost:*,http://127.0.0.1:*
+    ABSTRACTGATEWAY_ALLOWED_ORIGINS=http://localhost:*,http://127.0.0.1:* \
+    LMSTUDIO_BASE_URL=http://host.docker.internal:1234/v1 \
+    OLLAMA_BASE_URL=http://host.docker.internal:11434
 
 RUN addgroup --system abstractgateway \
     && adduser --system --ingroup abstractgateway --home /home/abstractgateway abstractgateway \

docker/abstractgateway-server/README.md

@@ -4,15 +4,15 @@ This image packages the AbstractGateway HTTP/SSE server for durable
 AbstractRuntime runs:
 
 ```bash
-ghcr.io/lpalbou/abstractgateway:0.2.24
+ghcr.io/lpalbou/abstractgateway:0.2.25
 ```
 
 Release images are published for `linux/amd64` and `linux/arm64`.
 A separate experimental full NVIDIA image is published best-effort for
 `linux/amd64`:
 
 ```bash
-ghcr.io/lpalbou/abstractgateway:0.2.24-gpu
+ghcr.io/lpalbou/abstractgateway:0.2.25-gpu
 ```
 
 Legacy aliases `ghcr.io/lpalbou/abstractgateway-server:*` and
@@ -67,8 +67,12 @@ OPENROUTER_API_KEY=sk-or-...
 ANTHROPIC_API_KEY=sk-ant-...
 PORTKEY_API_KEY=pk_...
 PORTKEY_CONFIG=pcfg_...
-OPENAI_COMPATIBLE_BASE_URL=http://host.docker.internal:1234/v1
+OPENAI_BASE_URL=http://host.docker.internal:1234/v1
+# Legacy/compatibility alias used by some operators; AbstractCore discovery uses OPENAI_BASE_URL.
+OPENAI_COMPATIBLE_BASE_URL=
 OPENAI_COMPATIBLE_API_KEY=optional
+LMSTUDIO_BASE_URL=http://host.docker.internal:1234/v1
+OLLAMA_BASE_URL=http://host.docker.internal:11434
 ABSTRACTVISION_BASE_URL=https://api.openai.com/v1
 ABSTRACTVISION_API_KEY=optional
 ABSTRACTVISION_MODEL_ID=gpt-image-1
@@ -106,8 +110,22 @@ docker run --rm --name abstractgateway \
   -e ABSTRACTGATEWAY_USER_AUTH=1 \
   -e ABSTRACTGATEWAY_PROVIDER="openai-compatible" \
   -e ABSTRACTGATEWAY_MODEL="your-model" \
-  -e OPENAI_COMPATIBLE_BASE_URL="http://host.docker.internal:1234/v1" \
-  -e OPENAI_COMPATIBLE_API_KEY="$OPENAI_COMPATIBLE_API_KEY" \
+  -e OPENAI_BASE_URL="http://host.docker.internal:1234/v1" \
+  -e OPENAI_API_KEY="$OPENAI_API_KEY" \
+  -v "$PWD/runtime:/data" \
+  ghcr.io/lpalbou/abstractgateway:latest
+```
+
+For LM Studio specifically, prefer the named provider so Gateway model
+discovery uses `LMSTUDIO_BASE_URL`:
+
+```bash
+docker run --rm --name abstractgateway \
+  -p 8080:8080 \
+  -e ABSTRACTGATEWAY_USER_AUTH=1 \
+  -e ABSTRACTGATEWAY_PROVIDER="lmstudio" \
+  -e ABSTRACTGATEWAY_MODEL="your-loaded-model-id" \
+  -e LMSTUDIO_BASE_URL="http://host.docker.internal:1234/v1" \
   -v "$PWD/runtime:/data" \
   ghcr.io/lpalbou/abstractgateway:latest
 ```
@@ -158,7 +176,7 @@ For unreleased local checkouts, build the image from this repository:
 
 ```bash
 ABSTRACTGATEWAY_INSTALL_MODE=local \
-ABSTRACTGATEWAY_IMAGE_TAG=0.2.24-local \
+ABSTRACTGATEWAY_IMAGE_TAG=0.2.25-local \
 docker compose -f docker/abstractgateway-server/compose.yml up -d --build
 ```
 

docker/abstractgateway-server/compose.nvidia.yml

@@ -2,13 +2,13 @@ services:
   abstractgateway:
     # Experimental CUDA overlay. Keep release-grade deployments on compose.yml
     # until this image has a real CUDA build/smoke gate.
-    image: ghcr.io/lpalbou/abstractgateway:${ABSTRACTGATEWAY_NVIDIA_IMAGE_TAG:-0.2.24-gpu}
+    image: ghcr.io/lpalbou/abstractgateway:${ABSTRACTGATEWAY_NVIDIA_IMAGE_TAG:-0.2.25-gpu}
     build:
       context: ../..
       dockerfile: docker/abstractgateway-server/Dockerfile.nvidia
       args:
         ABSTRACTGATEWAY_INSTALL_MODE: ${ABSTRACTGATEWAY_INSTALL_MODE:-pypi}
-        ABSTRACTGATEWAY_VERSION: ${ABSTRACTGATEWAY_VERSION:-0.2.24}
+        ABSTRACTGATEWAY_VERSION: ${ABSTRACTGATEWAY_VERSION:-0.2.25}
         ABSTRACTGATEWAY_EXTRAS: ${ABSTRACTGATEWAY_EXTRAS:-gpu}
     gpus: all
     environment:

docker/abstractgateway-server/compose.yml

@@ -2,13 +2,13 @@ name: abstractgateway-server
 
 services:
   abstractgateway:
-    image: ghcr.io/lpalbou/abstractgateway:${ABSTRACTGATEWAY_IMAGE_TAG:-0.2.24}
+    image: ghcr.io/lpalbou/abstractgateway:${ABSTRACTGATEWAY_IMAGE_TAG:-0.2.25}
     build:
       context: ../..
       dockerfile: docker/abstractgateway-server/Dockerfile
       args:
         ABSTRACTGATEWAY_INSTALL_MODE: ${ABSTRACTGATEWAY_INSTALL_MODE:-pypi}
-        ABSTRACTGATEWAY_VERSION: ${ABSTRACTGATEWAY_VERSION:-0.2.24}
+        ABSTRACTGATEWAY_VERSION: ${ABSTRACTGATEWAY_VERSION:-0.2.25}
         ABSTRACTGATEWAY_EXTRAS: ${ABSTRACTGATEWAY_EXTRAS:-}
     ports:
       - "${ABSTRACTGATEWAY_BIND_HOST:-127.0.0.1}:${ABSTRACTGATEWAY_PORT:-8080}:8080"
@@ -43,6 +43,7 @@ services:
       OPENROUTER_APP_NAME: ${OPENROUTER_APP_NAME:-AbstractGateway}
       PORTKEY_API_KEY: ${PORTKEY_API_KEY:-}
       PORTKEY_CONFIG: ${PORTKEY_CONFIG:-}
+      OPENAI_BASE_URL: ${OPENAI_BASE_URL:-}
       OPENAI_COMPATIBLE_BASE_URL: ${OPENAI_COMPATIBLE_BASE_URL:-}
       OPENAI_COMPATIBLE_API_KEY: ${OPENAI_COMPATIBLE_API_KEY:-}
       LMSTUDIO_BASE_URL: ${LMSTUDIO_BASE_URL:-http://host.docker.internal:1234/v1}

docs/configuration.md

@@ -341,12 +341,13 @@ Local heavy engines remain explicit opt-ins in the provider packages; Gateway
 does not implicitly install them.
 
 - `output.text` capability route: default text model for bundle LLM nodes
-- `OPENAI_COMPATIBLE_BASE_URL` / `OPENAI_COMPATIBLE_API_KEY`: OpenAI-compatible text endpoint for AbstractCore providers
+- `OPENAI_BASE_URL` / `OPENAI_API_KEY`: generic OpenAI-compatible text endpoint for AbstractCore providers
   - Apple/MLX Docker deployments should point the lightweight Gateway container
     at host-native inference, for example
     `http://model-runner.docker.internal/engines/v1`,
-    `http://host.docker.internal:1234/v1`, or
-    `http://host.docker.internal:11434/v1`.
+    `http://host.docker.internal:1234/v1`, or another `/v1` endpoint.
+- `LMSTUDIO_BASE_URL` / `OLLAMA_BASE_URL`: named local endpoint providers for
+  LM Studio and Ollama model discovery/routing from inside the Gateway container.
 - `ABSTRACTGATEWAY_VISION_BACKEND` / `ABSTRACTGATEWAY_VISION_BASE_URL` / `ABSTRACTGATEWAY_VISION_API_KEY` / `ABSTRACTGATEWAY_VISION_MODEL_ID`: Gateway-scoped image backend settings. Legacy `ABSTRACTVISION_*` names are still accepted by the lower package.
 - `ABSTRACTGATEWAY_VOICE_TTS_ENGINE` / `ABSTRACTGATEWAY_VOICE_STT_ENGINE`: Gateway-scoped voice engine settings. Legacy `ABSTRACTVOICE_*` names are still accepted by the lower package.
 - `ABSTRACTGATEWAY_VOICE_TTS_MODEL` / `ABSTRACTGATEWAY_VOICE_STT_MODEL`: Gateway-scoped TTS/STT model defaults.

docs/deployment.md

@@ -11,15 +11,15 @@ Release images are published to GHCR. The default image is the light,
 portable server image:
 
 ```bash
-docker pull ghcr.io/lpalbou/abstractgateway:0.2.24
+docker pull ghcr.io/lpalbou/abstractgateway:0.2.25
 ```
 
 NVIDIA hosts can try the experimental full GPU image when local
 vLLM/HuggingFace/Diffusers engines are wanted. This image is published
 best-effort until it has a real CUDA build and smoke gate:
 
 ```bash
-docker pull ghcr.io/lpalbou/abstractgateway:0.2.24-gpu
+docker pull ghcr.io/lpalbou/abstractgateway:0.2.25-gpu
 ```
 
 Legacy aliases `ghcr.io/lpalbou/abstractgateway-server:*` and
@@ -63,7 +63,7 @@ docker run --rm --name abstractgateway \
   -p 8080:8080 \
   -e ABSTRACTGATEWAY_DATA_DIR=/data \
   -e ABSTRACTGATEWAY_USER_AUTH=1 \
-  -e OPENAI_COMPATIBLE_BASE_URL="http://model-runner.docker.internal/engines/v1" \
+  -e OPENAI_BASE_URL="http://model-runner.docker.internal/engines/v1" \
   -v "$PWD/runtime:/data" \
   ghcr.io/lpalbou/abstractgateway:latest
 ```
@@ -78,9 +78,9 @@ docker exec abstractgateway abstractgateway-config set-default output.text \
 ```
 
 Other host-native endpoints are also valid: LM Studio at
-`http://host.docker.internal:1234/v1`, Ollama's OpenAI-compatible API at
-`http://host.docker.internal:11434/v1`, or `mlx_lm.server` exposed on a host
-port. For fully native non-Docker installs with local engines, use
+`http://host.docker.internal:1234/v1` with `LMSTUDIO_BASE_URL`, Ollama at
+`http://host.docker.internal:11434` with `OLLAMA_BASE_URL`, or `mlx_lm.server`
+exposed on a host port. For fully native non-Docker installs with local engines, use
 `pip install "abstractgateway[apple]"` on Apple Silicon, and
 `pip install "abstractgateway[gpu]"` on GPU workstations or NVIDIA Docker builds.
 
@@ -147,7 +147,8 @@ Provider keys and endpoints:
 - `ANTHROPIC_API_KEY`
 - `OPENROUTER_API_KEY`
 - `PORTKEY_API_KEY` / `PORTKEY_CONFIG`
-- `OPENAI_COMPATIBLE_BASE_URL` / `OPENAI_COMPATIBLE_API_KEY`
+- `OPENAI_BASE_URL` / `OPENAI_API_KEY` for generic OpenAI-compatible endpoints
+- `OPENAI_COMPATIBLE_BASE_URL` / `OPENAI_COMPATIBLE_API_KEY` as legacy operator aliases; prefer `OPENAI_BASE_URL` for AbstractCore discovery
 - `LMSTUDIO_BASE_URL`
 - `OLLAMA_BASE_URL`
 - `VLLM_BASE_URL`
@@ -194,7 +195,7 @@ Before a version is published to PyPI, build from the checkout:
 
 ```bash
 ABSTRACTGATEWAY_INSTALL_MODE=local \
-ABSTRACTGATEWAY_IMAGE_TAG=0.2.24-local \
+ABSTRACTGATEWAY_IMAGE_TAG=0.2.25-local \
 docker compose -f docker/abstractgateway-server/compose.yml up -d --build
 ```
 

docs/getting-started.md

@@ -156,18 +156,18 @@ customization.
 
 On first start, the container creates `default/admin` and writes the token to
 `runtime/auth/bootstrap-admin-token`. NVIDIA hosts can try
-`ghcr.io/lpalbou/abstractgateway:0.2.24-gpu` with the compose overlay in
+`ghcr.io/lpalbou/abstractgateway:0.2.25-gpu` with the compose overlay in
 `docker/abstractgateway-server/compose.nvidia.yml`.
 It is experimental until a real CUDA build/smoke gate is part of release
 validation.
 Apple MLX inference should run natively on macOS rather than in Docker because
 Linux containers do not get access to Apple's Metal/MLX runtime. The container
 can still use native macOS inference through an OpenAI-compatible endpoint:
-point `OPENAI_COMPATIBLE_BASE_URL` at Docker Model Runner on
-`http://model-runner.docker.internal/engines/v1`, LM Studio on
-`http://host.docker.internal:1234/v1`, `mlx_lm.server`, or Ollama's
-OpenAI-compatible API on `http://host.docker.internal:11434/v1` when the
-native Ollama model path uses MLX. For native non-Docker installs, use
+point `OPENAI_BASE_URL` at Docker Model Runner on
+`http://model-runner.docker.internal/engines/v1` or `mlx_lm.server`. For named
+local providers, set `LMSTUDIO_BASE_URL=http://host.docker.internal:1234/v1` or
+`OLLAMA_BASE_URL=http://host.docker.internal:11434` when the native Ollama model
+path uses MLX. For native non-Docker installs, use
 `pip install "abstractgateway[apple]"` on Apple Silicon, and
 `pip install "abstractgateway[gpu]"` on GPU workstations or NVIDIA Docker builds.