Agents: add fallback error observations (#41337)

Merged via squash.

Prepared head SHA: 852469c82f
Co-authored-by: altaywtf <9790196+altaywtf@users.noreply.github.com>
Co-authored-by: altaywtf <9790196+altaywtf@users.noreply.github.com>
Reviewed-by: @altaywtf

src/auto-reply/reply/agent-runner-execution.ts

@@ -199,6 +199,7 @@ export async function runAgentTurnWithFallback(params: {
       const onToolResult = params.opts?.onToolResult;
       const fallbackResult = await runWithModelFallback({
         ...resolveModelFallbackOptions(params.followupRun.run),
+        runId,
         run: (provider, model, runOptions) => {
           // Notify that model selection is complete (including after fallback).
           // This allows responsePrefix template interpolation with the actual model.

src/auto-reply/reply/agent-runner-memory.ts

@@ -474,6 +474,7 @@ export async function runMemoryFlushIfNeeded(params: {
   try {
     await runWithModelFallback({
       ...resolveModelFallbackOptions(params.followupRun.run),
+      runId: flushRunId,
       run: async (provider, model, runOptions) => {
         const { authProfile, embeddedContext, senderContext } = buildEmbeddedRunContexts({
           run: params.followupRun.run,

src/auto-reply/reply/followup-runner.ts

@@ -159,6 +159,7 @@ export function createFollowupRunner(params: {
           cfg: queued.run.config,
           provider: queued.run.provider,
           model: queued.run.model,
+          runId,
           agentDir: queued.run.agentDir,
           fallbacksOverride: resolveRunModelFallbacksOverride({
             cfg: queued.run.config,