local: plugin init, reasoning_content stripping, debug logging, pvrdrxtd submodule

- Strip reasoning_content/reasoning_details from messages for providers that
  don't support interleaved reasoning (e.g. Cerebras)
- Add plugin.init() calls in Agent.state and Command layer so plugins load
  before skills/commands are built
- Add LLM param debug logging for model introspection
- Add pvrdrxtd submodule and .gitignore entries for local paths

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Author: rustybret

packages/opencode/src/session/llm.ts

@@ -212,8 +212,39 @@ const live: Layer.Layer<
           })
         : undefined
 
-      // Runtime seam: native is an opt-in adapter over @opencode-ai/llm. It
-      // either returns a ready LLMEvent stream or a concrete fallback reason.
+      l.info("params", {
+        temperature: params.temperature,
+        topP: params.topP,
+        topK: params.topK,
+        maxOutputTokens: params.maxOutputTokens,
+        variant: input.user.model.variant,
+        providerOptions: ProviderTransform.providerOptions(input.model, params.options),
+        limit: input.model.limit,
+        capabilities: input.model.capabilities,
+      })
+
+      const opencodeProjectID = input.model.providerID.startsWith("opencode")
+        ? (yield* InstanceState.context).project.id
+        : undefined
+
+      const requestHeaders = {
+        ...(input.model.providerID.startsWith("opencode")
+          ? {
+              ...(opencodeProjectID ? { "x-opencode-project": opencodeProjectID } : {}),
+              "x-opencode-session": input.sessionID,
+              "x-opencode-request": input.user.id,
+              "x-opencode-client": flags.client,
+              "User-Agent": `opencode/${InstallationVersion}`,
+            }
+          : {
+              "x-session-affinity": input.sessionID,
+              ...(input.parentSessionID ? { "x-parent-session-id": input.parentSessionID } : {}),
+              "User-Agent": `opencode/${InstallationVersion}`,
+            }),
+        ...input.model.headers,
+        ...headers,
+      }
+
       if (flags.experimentalNativeLlm) {
         const native = LLMNativeRuntime.stream({
           model: input.model,