Pin published docs to alpha.112

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"] }
 ```

docs/index.html

@@ -341,8 +341,8 @@ <h2 class="stanza__title">embed it</h2>
 
         <p>The facade ships on crates.io as <code>lash-runtime</code> and is imported as <code>use lash::…</code>. During the alpha series the versions carry an <code>-alpha.N</code> suffix, so the dep needs the explicit pre-release tag.</p>
 <pre data-lang="cargo.toml"><code>[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"] }</code></pre>
 

docs/quickstart.html

@@ -66,8 +66,8 @@ <h2>Add The Crates</h2>
       <p>Pin the alpha pre-release explicitly and add the provider crate you actually use.</p>
     </div>
 <pre data-lang="cargo.toml"><code>[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"] }</code></pre>
     <p>For ordinary projects the facade and provider crates are enough. Drop down to <code>lash-core</code> only for custom runtime hosts, explicit process registries, store implementations, or diagnostics that need internal state.</p>

docs/released-version.txt

@@ -1 +1 @@
-0.1.0-alpha.111
+0.1.0-alpha.112

docs/tracing.html

@@ -315,8 +315,8 @@ <h2>OpenTelemetry Export</h2>
           </div>
           <pre data-lang="console"><code># 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"] }</code></pre>
+lash-runtime = "=0.1.0-alpha.112"
+lash-core    = { version = "=0.1.0-alpha.112", features = ["otel-trace"] }</code></pre>
           <p><code>lash_core::OtelTraceSink</code> wraps an <code>opentelemetry</code> tracer and converts every event to a span with payload attributes. Use in place of (or alongside) <code>JsonlTraceSink</code>:</p>
           <pre data-lang="rust" data-snippet="tracing#otel-trace-core"><code>use std::sync::Arc;