archgw: bump to latest

inference-platforms/archgw/README.md

@@ -14,10 +14,16 @@ Start ollama and the otel collector via this repository's [README](../../README.
 ## Run Arch Gateway
 
 Arch Gateway is a python command that internally runs Docker. Hence, you need a
-working Docker configuration. Run `archgw` using `uvx` from [uv][uv].
+working Docker configuration. Run `archgw` using `uv run` from [uv][uv]:
 
 ```bash
-uvx archgw up --service archgw --foreground
+uv run --with archgw -- archgw up arch_config.yaml
+```
+
+When finished, clean up like this:
+
+```bash
+uv run --with archgw -- archgw down
 ```
 
 ## Start Prometheus Scraping
@@ -71,3 +77,4 @@ Just run it again until we find a way to make the results idempotent.
 [archgw-wasm]: https://github.com/katanemo/archgw/blob/main/arch/README.md
 [uv]: https://docs.astral.sh/uv/getting-started/installation/
 [openai-responses]: https://github.com/katanemo/archgw/issues/476
+[otel-tui]: https://github.com/ymtdzzz/otel-tui

inference-platforms/archgw/arch_config.yaml

@@ -1,4 +1,4 @@
-version: "0.1-beta"
+version: v0.1.0
 
 listeners:
   egress_traffic:
@@ -8,11 +8,10 @@ listeners:
     timeout: 30s
 
 llm_providers:
-  - name: qwen3:0.6b
+  - model: ollama/qwen3:0.6b
     provider_interface: openai
     # This configuration is converted to Envoy and run inside Docker.
-    endpoint: host.docker.internal:11434
-    model: qwen3:0.6b
+    base_url: http://host.docker.internal:11434
     default: true
 
 tracing:

inference-platforms/archgw/docker-compose-elastic.yml

@@ -48,8 +48,7 @@ configs:
 services:
   # prometheus-pump is an OpenTelemetry Collector that scrapes Prometheus metrics
   prometheus-pump:
-    # TODO: docker.elastic.co/elastic-agent/elastic-otel-collector:9.0.3
-    image: docker.elastic.co/elastic-agent/elastic-otel-collector:9.0.3-SNAPSHOT
+    image: docker.elastic.co/elastic-agent/elastic-otel-collector:9.1.3
     container_name: prometheus-pump
     command: [
       "--config=/etc/otel/config.yaml",