diff --git a/README.md b/README.md index 0b2f7298..ceb2ec0a 100644 --- a/README.md +++ b/README.md @@ -23,8 +23,8 @@ Most agent stacks treat the LLM as the runtime and stitch state around it — a ```toml [dependencies] -lash-runtime = "=0.1.0-alpha.111" -lash-provider-openai = "=0.1.0-alpha.111" +lash-runtime = "=0.1.0-alpha.112" +lash-provider-openai = "=0.1.0-alpha.112" anyhow = "1" tokio = { version = "1", features = ["full"] } ``` diff --git a/docs/index.html b/docs/index.html index e1f8e678..bbb61eb4 100644 --- a/docs/index.html +++ b/docs/index.html @@ -341,8 +341,8 @@
The facade ships on crates.io as lash-runtime and is imported as use lash::…. During the alpha series the versions carry an -alpha.N suffix, so the dep needs the explicit pre-release tag.
[dependencies]
-lash-runtime = "=0.1.0-alpha.111"
-lash-provider-openai = "=0.1.0-alpha.111"
+lash-runtime = "=0.1.0-alpha.112"
+lash-provider-openai = "=0.1.0-alpha.112"
anyhow = "1"
tokio = { version = "1", features = ["full"] }
diff --git a/docs/quickstart.html b/docs/quickstart.html
index 3a090c6e..e47620ac 100644
--- a/docs/quickstart.html
+++ b/docs/quickstart.html
@@ -66,8 +66,8 @@ Pin the alpha pre-release explicitly and add the provider crate you actually use.
[dependencies]
-lash-runtime = "=0.1.0-alpha.111"
-lash-provider-openai = "=0.1.0-alpha.111"
+lash-runtime = "=0.1.0-alpha.112"
+lash-provider-openai = "=0.1.0-alpha.112"
anyhow = "1"
tokio = { version = "1", features = ["full"] }
For ordinary projects the facade and provider crates are enough. Drop down to lash-core only for custom runtime hosts, explicit process registries, store implementations, or diagnostics that need internal state.
# In your downstream Cargo.toml — pull in lash-core with the otel-trace
# feature alongside the lash-runtime facade.
-lash-runtime = "=0.1.0-alpha.111"
-lash-core = { version = "=0.1.0-alpha.111", features = ["otel-trace"] }
+lash-runtime = "=0.1.0-alpha.112"
+lash-core = { version = "=0.1.0-alpha.112", features = ["otel-trace"] }
lash_core::OtelTraceSink wraps an opentelemetry tracer and converts every event to a span with payload attributes. Use in place of (or alongside) JsonlTraceSink:
use std::sync::Arc;