🤖 fix: correct context usage display for multi-step tool calls

The Context Usage UI was showing inflated cachedInputTokens for plan
messages with multi-step tool calls (e.g., ~150k instead of ~50k).

Root cause: contextUsage was falling back to cumulative usage (summed
across all steps) when contextUsage was undefined. For multi-step
requests, cachedInputTokens gets summed because each step reads from
cache, but the actual context window only sees one step's worth.

Changes:
- Backend: Refactor getStreamMetadata() to fetch totalUsage (for costs)
  and contextUsage (last step, for context window) separately from AI SDK
- Backend: Add contextProviderMetadata from streamResult.providerMetadata
  for accurate cache creation token display
- Frontend: Remove fallback from contextUsage to usage - only use
  contextUsage for context window display

The fix ensures context window shows last step's inputTokens (actual
context size) while cost calculation still uses cumulative totals.

Author: ethanndickson

src/browser/stores/WorkspaceStore.ts

@@ -486,7 +486,7 @@ export class WorkspaceStore {
             if (msg.metadata?.compacted) {
               continue;
             }
-            const rawUsage = msg.metadata?.contextUsage ?? msg.metadata?.usage;
+            const rawUsage = msg.metadata?.contextUsage;
             const providerMeta =
               msg.metadata?.contextProviderMetadata ?? msg.metadata?.providerMetadata;
             if (rawUsage) {

src/browser/stories/mockFactory.ts

@@ -199,6 +199,7 @@ export function createAssistantMessage(
       timestamp: opts.timestamp ?? STABLE_TIMESTAMP,
       model: opts.model ?? DEFAULT_MODEL,
       usage: { inputTokens: 100, outputTokens: 50, totalTokens: 150 },
+      contextUsage: { inputTokens: 100, outputTokens: 50, totalTokens: 150 },
       duration: 1000,
     },
   };

src/node/services/streamManager.ts

@@ -334,22 +334,42 @@ export class StreamManager extends EventEmitter {
   private async getStreamMetadata(
     streamInfo: WorkspaceStreamInfo,
     timeoutMs = 1000
-  ): Promise<{ usage?: LanguageModelV2Usage; duration: number }> {
-    let usage = undefined;
+  ): Promise<{
+    totalUsage?: LanguageModelV2Usage;
+    contextUsage?: LanguageModelV2Usage;
+    contextProviderMetadata?: Record<string, unknown>;
+    duration: number;
+  }> {
+    let totalUsage: LanguageModelV2Usage | undefined;
+    let contextUsage: LanguageModelV2Usage | undefined;
+    let contextProviderMetadata: Record<string, unknown> | undefined;
+
     try {
-      // Race usage retrieval against timeout to prevent hanging on abort
-      // CRITICAL: Use totalUsage (sum of all steps) not usage (last step only)
-      // For multi-step tool calls, usage would severely undercount actual token consumption
-      usage = await Promise.race([
-        streamInfo.streamResult.totalUsage,
-        new Promise<undefined>((resolve) => setTimeout(() => resolve(undefined), timeoutMs)),
+      // Fetch all metadata in parallel with timeout
+      // - totalUsage: sum of all steps (for cost calculation)
+      // - usage: last step only (for context window display)
+      // - providerMetadata: last step (for context window cache display)
+      const [total, context, contextMeta] = await Promise.race([
+        Promise.all([
+          streamInfo.streamResult.totalUsage,
+          streamInfo.streamResult.usage,
+          streamInfo.streamResult.providerMetadata,
+        ]),
+        new Promise<[undefined, undefined, undefined]>((resolve) =>
+          setTimeout(() => resolve([undefined, undefined, undefined]), timeoutMs)
+        ),
       ]);
+      totalUsage = total;
+      contextUsage = context;
+      contextProviderMetadata = contextMeta;
     } catch (error) {
-      log.debug("Could not retrieve usage:", error);
+      log.debug("Could not retrieve stream metadata:", error);
     }
 
     return {
-      usage,
+      totalUsage,
+      contextUsage,
+      contextProviderMetadata,
       duration: Date.now() - streamInfo.startTime,
     };
   }
@@ -1071,17 +1091,20 @@ export class StreamManager extends EventEmitter {
 
       // Check if stream completed successfully
       if (!streamInfo.abortController.signal.aborted) {
-        // Get usage, duration, and provider metadata from stream result
-        // CRITICAL: Use totalUsage (via getStreamMetadata) and aggregated providerMetadata
-        // to correctly account for all steps in multi-tool-call conversations
-        const { usage, duration } = await this.getStreamMetadata(streamInfo);
+        // Get all metadata from stream result in one call
+        // - totalUsage: sum of all steps (for cost calculation)
+        // - contextUsage: last step only (for context window display)
+        // - contextProviderMetadata: last step (for context window cache tokens)
+        // Falls back to tracked values from finish-step if streamResult fails/times out
+        const streamMeta = await this.getStreamMetadata(streamInfo);
+        const totalUsage = streamMeta.totalUsage;
+        const contextUsage = streamMeta.contextUsage ?? streamInfo.lastStepUsage;
+        const contextProviderMetadata =
+          streamMeta.contextProviderMetadata ?? streamInfo.lastStepProviderMetadata;
+        const duration = streamMeta.duration;
+        // Aggregated provider metadata across all steps (for cost calculation with cache tokens)
         const providerMetadata = await this.getAggregatedProviderMetadata(streamInfo);
 
-        // For context window display, use last step's usage (inputTokens = current context size)
-        // This is stored in streamInfo during finish-step handling
-        const contextUsage = streamInfo.lastStepUsage;
-        const contextProviderMetadata = streamInfo.lastStepProviderMetadata;
-
         // Emit stream end event with parts preserved in temporal order
         const streamEndEvent: StreamEndEvent = {
           type: "stream-end",
@@ -1090,7 +1113,7 @@ export class StreamManager extends EventEmitter {
           metadata: {
             ...streamInfo.initialMetadata, // AIService-provided metadata (systemMessageTokens, etc)
             model: streamInfo.model,
-            usage, // Total across all steps (for cost calculation)
+            usage: totalUsage, // Total across all steps (for cost calculation)
             contextUsage, // Last step only (for context window display)
             providerMetadata, // Aggregated (for cost calculation)
             contextProviderMetadata, // Last step (for context window display)