Merge branch 'main' into refactor/remove-token-usage-logic

The information given was not accurate for the model providers

public/api-docs.html

@@ -585,7 +585,7 @@
                             <p>Server-sent events (SSE) format with real-time updates. Content-Type: <code>text/event-stream</code></p>
 
                             <h4>Response (Non-Streaming)</h4>
-                            <p>JSON object containing session details, assistant messages only (filtered), and token usage summary. Content-Type: <code>application/json</code></p>
+                            <p>JSON object containing session details and assistant messages only (filtered). Content-Type: <code>application/json</code></p>
 
                             <h4>Error Response</h4>
                             <p>Returns error details with appropriate HTTP status code.</p>
@@ -674,21 +674,10 @@ data: {"type":"done"}</code></pre>
             "type": "text",
             "text": "I've completed the task..."
           }
-        ],
-        "usage": {
-          "input_tokens": 150,
-          "output_tokens": 50
-        }
+        ]
       }
     }
   ],
-  "tokens": {
-    "inputTokens": 150,
-    "outputTokens": 50,
-    "cacheReadTokens": 0,
-    "cacheCreationTokens": 0,
-    "totalTokens": 200
-  },
   "projectPath": "/path/to/project",
   "branch": {
     "name": "fix-authentication-bug-abc123",

server/claude-sdk.js

@@ -274,46 +274,6 @@ function transformMessage(sdkMessage) {
   return sdkMessage;
 }
 
-/**
- * Extracts token usage from SDK result messages
- * @param {Object} resultMessage - SDK result message
- * @returns {Object|null} Token budget object or null
- */
-function extractTokenBudget(resultMessage) {
-  if (resultMessage.type !== 'result' || !resultMessage.modelUsage) {
-    return null;
-  }
-
-  // Get the first model's usage data
-  const modelKey = Object.keys(resultMessage.modelUsage)[0];
-  const modelData = resultMessage.modelUsage[modelKey];
-
-  if (!modelData) {
-    return null;
-  }
-
-  // Use cumulative tokens if available (tracks total for the session)
-  // Otherwise fall back to per-request tokens
-  const inputTokens = modelData.cumulativeInputTokens || modelData.inputTokens || 0;
-  const outputTokens = modelData.cumulativeOutputTokens || modelData.outputTokens || 0;
-  const cacheReadTokens = modelData.cumulativeCacheReadInputTokens || modelData.cacheReadInputTokens || 0;
-  const cacheCreationTokens = modelData.cumulativeCacheCreationInputTokens || modelData.cacheCreationInputTokens || 0;
-
-  // Total used = input + output + cache tokens
-  const totalUsed = inputTokens + outputTokens + cacheReadTokens + cacheCreationTokens;
-
-  // Use configured context window budget from environment (default 160000)
-  // This is the user's budget limit, not the model's context window
-  const contextWindow = parseInt(process.env.CONTEXT_WINDOW) || 160000;
-
-  // Token calc logged via token-budget WS event
-
-  return {
-    used: totalUsed,
-    total: contextWindow
-  };
-}
-
 /**
  * Handles image processing for SDK queries
  * Saves base64 images to temporary files and returns modified prompt with file paths
@@ -657,18 +617,6 @@ async function queryClaudeSDK(command, options = {}, ws) {
         }
         ws.send(msg);
       }
-
-      // Extract and send token budget updates from result messages
-      if (message.type === 'result') {
-        const models = Object.keys(message.modelUsage || {});
-        if (models.length > 0) {
-          // Model info available in result message
-        }
-        const tokenBudgetData = extractTokenBudget(message);
-        if (tokenBudgetData) {
-          ws.send(createNormalizedMessage({ kind: 'status', text: 'token_budget', tokenBudget: tokenBudgetData, sessionId: capturedSessionId || sessionId || null, provider: 'claude' }));
-        }
-      }
     }
 
     // Clean up session on completion

server/index.js

@@ -2218,194 +2218,6 @@ app.post('/api/projects/:projectName/upload-images', authenticateToken, async (r
     }
 });
 
-// Get token usage for a specific session
-app.get('/api/projects/:projectName/sessions/:sessionId/token-usage', authenticateToken, async (req, res) => {
-    try {
-        const { projectName, sessionId } = req.params;
-        const { provider = 'claude' } = req.query;
-        const homeDir = os.homedir();
-
-        // Allow only safe characters in sessionId
-        const safeSessionId = String(sessionId).replace(/[^a-zA-Z0-9._-]/g, '');
-        if (!safeSessionId || safeSessionId !== String(sessionId)) {
-            return res.status(400).json({ error: 'Invalid sessionId' });
-        }
-
-        // Handle Cursor sessions - they use SQLite and don't have token usage info
-        if (provider === 'cursor') {
-            return res.json({
-                used: 0,
-                total: 0,
-                breakdown: { input: 0, cacheCreation: 0, cacheRead: 0 },
-                unsupported: true,
-                message: 'Token usage tracking not available for Cursor sessions'
-            });
-        }
-
-        // Handle Gemini sessions - they are raw logs in our current setup
-        if (provider === 'gemini') {
-            return res.json({
-                used: 0,
-                total: 0,
-                breakdown: { input: 0, cacheCreation: 0, cacheRead: 0 },
-                unsupported: true,
-                message: 'Token usage tracking not available for Gemini sessions'
-            });
-        }
-
-        // Handle Codex sessions
-        if (provider === 'codex') {
-            const codexSessionsDir = path.join(homeDir, '.codex', 'sessions');
-
-            // Find the session file by searching for the session ID
-            const findSessionFile = async (dir) => {
-                try {
-                    const entries = await fsPromises.readdir(dir, { withFileTypes: true });
-                    for (const entry of entries) {
-                        const fullPath = path.join(dir, entry.name);
-                        if (entry.isDirectory()) {
-                            const found = await findSessionFile(fullPath);
-                            if (found) return found;
-                        } else if (entry.name.includes(safeSessionId) && entry.name.endsWith('.jsonl')) {
-                            return fullPath;
-                        }
-                    }
-                } catch (error) {
-                    // Skip directories we can't read
-                }
-                return null;
-            };
-
-            const sessionFilePath = await findSessionFile(codexSessionsDir);
-
-            if (!sessionFilePath) {
-                return res.status(404).json({ error: 'Codex session file not found', sessionId: safeSessionId });
-            }
-
-            // Read and parse the Codex JSONL file
-            let fileContent;
-            try {
-                fileContent = await fsPromises.readFile(sessionFilePath, 'utf8');
-            } catch (error) {
-                if (error.code === 'ENOENT') {
-                    return res.status(404).json({ error: 'Session file not found', path: sessionFilePath });
-                }
-                throw error;
-            }
-            const lines = fileContent.trim().split('\n');
-            let totalTokens = 0;
-            let contextWindow = 200000; // Default for Codex/OpenAI
-
-            // Find the latest token_count event with info (scan from end)
-            for (let i = lines.length - 1; i >= 0; i--) {
-                try {
-                    const entry = JSON.parse(lines[i]);
-
-                    // Codex stores token info in event_msg with type: "token_count"
-                    if (entry.type === 'event_msg' && entry.payload?.type === 'token_count' && entry.payload?.info) {
-                        const tokenInfo = entry.payload.info;
-                        if (tokenInfo.total_token_usage) {
-                            totalTokens = tokenInfo.total_token_usage.total_tokens || 0;
-                        }
-                        if (tokenInfo.model_context_window) {
-                            contextWindow = tokenInfo.model_context_window;
-                        }
-                        break; // Stop after finding the latest token count
-                    }
-                } catch (parseError) {
-                    // Skip lines that can't be parsed
-                    continue;
-                }
-            }
-
-            return res.json({
-                used: totalTokens,
-                total: contextWindow
-            });
-        }
-
-        // Handle Claude sessions (default)
-        // Extract actual project path
-        let projectPath;
-        try {
-            projectPath = await extractProjectDirectory(projectName);
-        } catch (error) {
-            console.error('Error extracting project directory:', error);
-            return res.status(500).json({ error: 'Failed to determine project path' });
-        }
-
-        // Construct the JSONL file path
-        // Claude stores session files in ~/.claude/projects/[encoded-project-path]/[session-id].jsonl
-        // The encoding replaces any non-alphanumeric character (except -) with -
-        const encodedPath = projectPath.replace(/[^a-zA-Z0-9-]/g, '-');
-        const projectDir = path.join(homeDir, '.claude', 'projects', encodedPath);
-
-        const jsonlPath = path.join(projectDir, `${safeSessionId}.jsonl`);
-
-        // Constrain to projectDir
-        const rel = path.relative(path.resolve(projectDir), path.resolve(jsonlPath));
-        if (rel.startsWith('..') || path.isAbsolute(rel)) {
-            return res.status(400).json({ error: 'Invalid path' });
-        }
-
-        // Read and parse the JSONL file
-        let fileContent;
-        try {
-            fileContent = await fsPromises.readFile(jsonlPath, 'utf8');
-        } catch (error) {
-            if (error.code === 'ENOENT') {
-                return res.status(404).json({ error: 'Session file not found', path: jsonlPath });
-            }
-            throw error; // Re-throw other errors to be caught by outer try-catch
-        }
-        const lines = fileContent.trim().split('\n');
-
-        const parsedContextWindow = parseInt(process.env.CONTEXT_WINDOW, 10);
-        const contextWindow = Number.isFinite(parsedContextWindow) ? parsedContextWindow : 160000;
-        let inputTokens = 0;
-        let cacheCreationTokens = 0;
-        let cacheReadTokens = 0;
-
-        // Find the latest assistant message with usage data (scan from end)
-        for (let i = lines.length - 1; i >= 0; i--) {
-            try {
-                const entry = JSON.parse(lines[i]);
-
-                // Only count assistant messages which have usage data
-                if (entry.type === 'assistant' && entry.message?.usage) {
-                    const usage = entry.message.usage;
-
-                    // Use token counts from latest assistant message only
-                    inputTokens = usage.input_tokens || 0;
-                    cacheCreationTokens = usage.cache_creation_input_tokens || 0;
-                    cacheReadTokens = usage.cache_read_input_tokens || 0;
-
-                    break; // Stop after finding the latest assistant message
-                }
-            } catch (parseError) {
-                // Skip lines that can't be parsed
-                continue;
-            }
-        }
-
-        // Calculate total context usage (excluding output_tokens, as per ccusage)
-        const totalUsed = inputTokens + cacheCreationTokens + cacheReadTokens;
-
-        res.json({
-            used: totalUsed,
-            total: contextWindow,
-            breakdown: {
-                input: inputTokens,
-                cacheCreation: cacheCreationTokens,
-                cacheRead: cacheReadTokens
-            }
-        });
-    } catch (error) {
-        console.error('Error reading session token usage:', error);
-        res.status(500).json({ error: 'Failed to read session token usage' });
-    }
-});
-
 // Serve React app for all other routes (excluding static files)
 app.get('*', (req, res) => {
     // Skip requests for static assets (files with extensions)

server/openai-codex.js

@@ -129,8 +129,7 @@ function transformCodexEvent(event) {
 
     case 'turn.completed':
       return {
-        type: 'turn_complete',
-        usage: event.usage
+        type: 'turn_complete'
       };
 
     case 'turn.failed':
@@ -279,12 +278,6 @@ export async function queryCodex(command, options = {}, ws) {
           error: terminalFailure
         });
       }
-
-      // Extract and send token usage if available (normalized to match Claude format)
-      if (event.type === 'turn.completed' && event.usage) {
-        const totalTokens = (event.usage.input_tokens || 0) + (event.usage.output_tokens || 0);
-        sendMessage(ws, createNormalizedMessage({ kind: 'status', text: 'token_budget', tokenBudget: { used: totalTokens, total: 200000 }, sessionId: currentSessionId, provider: 'codex' }));
-      }
     }
 
     // Send completion event

server/projects.js

@@ -1618,7 +1618,6 @@ async function getCodexSessionMessages(sessionId, limit = null, offset = 0) {
     }
 
     const messages = [];
-    let tokenUsage = null;
     const fileStream = fsSync.createReadStream(sessionFilePath);
     const rl = readline.createInterface({
       input: fileStream,
@@ -1647,17 +1646,6 @@ async function getCodexSessionMessages(sessionId, limit = null, offset = 0) {
         try {
           const entry = JSON.parse(line);
 
-          // Extract token usage from token_count events (keep latest)
-          if (entry.type === 'event_msg' && entry.payload?.type === 'token_count' && entry.payload?.info) {
-            const info = entry.payload.info;
-            if (info.total_token_usage) {
-              tokenUsage = {
-                used: info.total_token_usage.total_tokens || 0,
-                total: info.model_context_window || 200000
-              };
-            }
-          }
-          
           // Use event_msg.user_message for user-visible inputs.
           if (entry.type === 'event_msg' && isVisibleCodexUserMessage(entry.payload)) {
             messages.push({
@@ -1820,11 +1808,10 @@ async function getCodexSessionMessages(sessionId, limit = null, offset = 0) {
         hasMore,
         offset,
         limit,
-        tokenUsage
       };
     }
 
-    return { messages, tokenUsage };
+    return { messages };
 
   } catch (error) {
     console.error(`Error reading Codex session messages for ${sessionId}:`, error);

server/providers/codex/adapter.js

@@ -214,7 +214,6 @@ export const codexAdapter = {
     const rawMessages = Array.isArray(result) ? result : (result.messages || []);
     const total = Array.isArray(result) ? rawMessages.length : (result.total || 0);
     const hasMore = Array.isArray(result) ? false : Boolean(result.hasMore);
-    const tokenUsage = result.tokenUsage || null;
 
     const normalized = [];
     for (const raw of rawMessages) {
@@ -242,7 +241,6 @@ export const codexAdapter = {
       hasMore,
       offset,
       limit,
-      tokenUsage,
     };
   },
 };

server/providers/gemini/adapter.js

@@ -53,14 +53,7 @@ export function normalizeMessage(raw, sessionId) {
   }
 
   if (raw.type === 'result') {
-    const msgs = [createNormalizedMessage({ sessionId, timestamp: ts, provider: PROVIDER, kind: 'stream_end' })];
-    if (raw.stats?.total_tokens) {
-      msgs.push(createNormalizedMessage({
-        sessionId, timestamp: ts, provider: PROVIDER,
-        kind: 'status', text: 'Complete', tokens: raw.stats.total_tokens, canInterrupt: false,
-      }));
-    }
-    return msgs;
+    return [createNormalizedMessage({ sessionId, timestamp: ts, provider: PROVIDER, kind: 'stream_end' })];
   }
 
   if (raw.type === 'error') {

server/providers/types.js

@@ -41,7 +41,7 @@
  * - stream_end:           (no extra fields)
  * - error:                content
  * - complete:             (no extra fields)
- * - status:               text, tokens?, canInterrupt?
+ * - status:               text, canInterrupt?
  * - permission_request:   requestId, toolName, input, context?
  * - permission_cancelled: requestId
  * - session_created:      newSessionId
@@ -66,7 +66,6 @@
  * @property {boolean} hasMore - Whether more messages exist before the current page
  * @property {number} offset - Current offset
  * @property {number|null} limit - Page size used
- * @property {object} [tokenUsage] - Token usage data (provider-specific)
  */
 
 // ─── Provider Adapter Interface ──────────────────────────────────────────────

server/routes/agent.js

@@ -546,7 +546,12 @@ class ResponseCollector {
           const parsed = JSON.parse(msg);
           // Only include claude-response messages with assistant type
           if (parsed.type === 'claude-response' && parsed.data && parsed.data.type === 'assistant') {
-            assistantMessages.push(parsed.data);
+            const assistantMessage = { ...parsed.data };
+            if (assistantMessage.message?.usage) {
+              assistantMessage.message = { ...assistantMessage.message };
+              delete assistantMessage.message.usage;
+            }
+            assistantMessages.push(assistantMessage);
           }
         } catch (e) {
           // Not JSON, skip
@@ -556,49 +561,6 @@ class ResponseCollector {
 
     return assistantMessages;
   }
-
-  /**
-   * Calculate total tokens from all messages
-   */
-  getTotalTokens() {
-    let totalInput = 0;
-    let totalOutput = 0;
-    let totalCacheRead = 0;
-    let totalCacheCreation = 0;
-
-    for (const msg of this.messages) {
-      let data = msg;
-
-      // Parse if string
-      if (typeof msg === 'string') {
-        try {
-          data = JSON.parse(msg);
-        } catch (e) {
-          continue;
-        }
-      }
-
-      // Extract usage from claude-response messages
-      if (data && data.type === 'claude-response' && data.data) {
-        const msgData = data.data;
-        if (msgData.message && msgData.message.usage) {
-          const usage = msgData.message.usage;
-          totalInput += usage.input_tokens || 0;
-          totalOutput += usage.output_tokens || 0;
-          totalCacheRead += usage.cache_read_input_tokens || 0;
-          totalCacheCreation += usage.cache_creation_input_tokens || 0;
-        }
-      }
-    }
-
-    return {
-      inputTokens: totalInput,
-      outputTokens: totalOutput,
-      cacheReadTokens: totalCacheRead,
-      cacheCreationTokens: totalCacheCreation,
-      totalTokens: totalInput + totalOutput + totalCacheRead + totalCacheCreation
-    };
-  }
 }
 
 // ===============================
@@ -789,13 +751,6 @@ class ResponseCollector {
  *     success: true,
  *     sessionId: "session-123",
  *     messages: [...],        // Assistant messages only (filtered)
- *     tokens: {
- *       inputTokens: 150,
- *       outputTokens: 50,
- *       cacheReadTokens: 0,
- *       cacheCreationTokens: 0,
- *       totalTokens: 200
- *     },
  *     projectPath: "/path/to/project",
  *     branch: {               // Only if createBranch=true
  *       name: "feature/xyz",
@@ -1173,15 +1128,13 @@ router.post('/', validateExternalApiKey, async (req, res) => {
       // Streaming mode: end the SSE stream
       writer.end();
     } else {
-      // Non-streaming mode: send filtered messages and token summary as JSON
+      // Non-streaming mode: send filtered messages as JSON
       const assistantMessages = writer.getAssistantMessages();
-      const tokenSummary = writer.getTotalTokens();
 
       const response = {
         success: true,
         sessionId: writer.getSessionId(),
         messages: assistantMessages,
-        tokens: tokenSummary,
         projectPath: finalProjectPath
       };
 

server/routes/commands.js

@@ -97,12 +97,6 @@ const builtInCommands = [
     namespace: 'builtin',
     metadata: { type: 'builtin' }
   },
-  {
-    name: '/cost',
-    description: 'Display token usage and cost information',
-    namespace: 'builtin',
-    metadata: { type: 'builtin' }
-  },
   {
     name: '/memory',
     description: 'Open CLAUDE.md memory file for editing',
@@ -209,86 +203,6 @@ Custom commands can be created in:
     };
   },
 
-  '/cost': async (args, context) => {
-    const tokenUsage = context?.tokenUsage || {};
-    const provider = context?.provider || 'claude';
-    const model =
-      context?.model ||
-      (provider === 'cursor'
-        ? CURSOR_MODELS.DEFAULT
-        : provider === 'codex'
-          ? CODEX_MODELS.DEFAULT
-          : CLAUDE_MODELS.DEFAULT);
-
-    const used = Number(tokenUsage.used ?? tokenUsage.totalUsed ?? tokenUsage.total_tokens ?? 0) || 0;
-    const total =
-      Number(
-        tokenUsage.total ??
-          tokenUsage.contextWindow ??
-          parseInt(process.env.CONTEXT_WINDOW || '160000', 10),
-      ) || 160000;
-    const percentage = total > 0 ? Number(((used / total) * 100).toFixed(1)) : 0;
-
-    const inputTokensRaw =
-      Number(
-        tokenUsage.inputTokens ??
-          tokenUsage.input ??
-          tokenUsage.cumulativeInputTokens ??
-          tokenUsage.promptTokens ??
-          0,
-      ) || 0;
-    const outputTokens =
-      Number(
-        tokenUsage.outputTokens ??
-          tokenUsage.output ??
-          tokenUsage.cumulativeOutputTokens ??
-          tokenUsage.completionTokens ??
-          0,
-      ) || 0;
-    const cacheTokens =
-      Number(
-        tokenUsage.cacheReadTokens ??
-          tokenUsage.cacheCreationTokens ??
-          tokenUsage.cacheTokens ??
-          tokenUsage.cachedTokens ??
-          0,
-      ) || 0;
-
-    // If we only have total used tokens, treat them as input for display/estimation.
-    const inputTokens =
-      inputTokensRaw > 0 || outputTokens > 0 || cacheTokens > 0 ? inputTokensRaw + cacheTokens : used;
-
-    // Rough default rates by provider (USD / 1M tokens).
-    const pricingByProvider = {
-      claude: { input: 3, output: 15 },
-      cursor: { input: 3, output: 15 },
-      codex: { input: 1.5, output: 6 },
-    };
-    const rates = pricingByProvider[provider] || pricingByProvider.claude;
-
-    const inputCost = (inputTokens / 1_000_000) * rates.input;
-    const outputCost = (outputTokens / 1_000_000) * rates.output;
-    const totalCost = inputCost + outputCost;
-
-    return {
-      type: 'builtin',
-      action: 'cost',
-      data: {
-        tokenUsage: {
-          used,
-          total,
-          percentage,
-        },
-        cost: {
-          input: inputCost.toFixed(4),
-          output: outputCost.toFixed(4),
-          total: totalCost.toFixed(4),
-        },
-        model,
-      },
-    };
-  },
-
   '/status': async (args, context) => {
     // Read version from package.json
     const packageJsonPath = path.join(path.dirname(__dirname), '..', 'package.json');

src/components/chat/hooks/useChatComposerState.ts

@@ -42,7 +42,6 @@ interface UseChatComposerStateArgs {
   geminiModel: string;
   isLoading: boolean;
   canAbortSession: boolean;
-  tokenBudget: Record<string, unknown> | null;
   sendMessage: (message: unknown) => void;
   sendByCtrlEnter?: boolean;
   onSessionActive?: (sessionId?: string | null) => void;
@@ -57,7 +56,7 @@ interface UseChatComposerStateArgs {
   rewindMessages: (count: number) => void;
   setIsLoading: (loading: boolean) => void;
   setCanAbortSession: (canAbort: boolean) => void;
-  setClaudeStatus: (status: { text: string; tokens: number; can_interrupt: boolean } | null) => void;
+  setClaudeStatus: (status: { text: string; can_interrupt: boolean } | null) => void;
   setIsUserScrolledUp: (isScrolledUp: boolean) => void;
   setPendingPermissionRequests: Dispatch<SetStateAction<PendingPermissionRequest[]>>;
 }
@@ -114,7 +113,6 @@ export function useChatComposerState({
   geminiModel,
   isLoading,
   canAbortSession,
-  tokenBudget,
   sendMessage,
   sendByCtrlEnter,
   onSessionActive,
@@ -176,12 +174,6 @@ export function useChatComposerState({
           });
           break;
 
-        case 'cost': {
-          const costMessage = `**Token Usage**: ${data.tokenUsage.used.toLocaleString()} / ${data.tokenUsage.total.toLocaleString()} (${data.tokenUsage.percentage}%)\n\n**Estimated Cost**:\n- Input: $${data.cost.input}\n- Output: $${data.cost.output}\n- **Total**: $${data.cost.total}\n\n**Model**: ${data.model}`;
-          addMessage({ type: 'assistant', content: costMessage, timestamp: Date.now() });
-          break;
-        }
-
         case 'status': {
           const statusMessage = `**System Status**\n\n- Version: ${data.version}\n- Uptime: ${data.uptime}\n- Model: ${data.model}\n- Provider: ${data.provider}\n- Node.js: ${data.nodeVersion}\n- Platform: ${data.platform}`;
           addMessage({ type: 'assistant', content: statusMessage, timestamp: Date.now() });
@@ -282,7 +274,6 @@ export function useChatComposerState({
           sessionId: currentSessionId,
           provider,
           model: provider === 'cursor' ? cursorModel : provider === 'codex' ? codexModel : provider === 'gemini' ? geminiModel : claudeModel,
-          tokenUsage: tokenBudget,
         };
 
         const response = await authenticatedFetch('/api/commands/execute', {
@@ -339,7 +330,6 @@ export function useChatComposerState({
       provider,
       selectedProject,
       addMessage,
-      tokenBudget,
     ],
   );
 
@@ -543,7 +533,6 @@ export function useChatComposerState({
       setCanAbortSession(true);
       setClaudeStatus({
         text: 'Processing',
-        tokens: 0,
         can_interrupt: true,
       });
 

src/components/chat/hooks/useChatRealtimeHandlers.ts

@@ -38,9 +38,7 @@ type LatestChatMessage = {
   provider?: string;
   content?: string;
   text?: string;
-  tokens?: number;
   canInterrupt?: boolean;
-  tokenBudget?: unknown;
   newSessionId?: string;
   aborted?: boolean;
   [key: string]: any;
@@ -55,8 +53,7 @@ interface UseChatRealtimeHandlersArgs {
   setCurrentSessionId: (sessionId: string | null) => void;
   setIsLoading: (loading: boolean) => void;
   setCanAbortSession: (canAbort: boolean) => void;
-  setClaudeStatus: (status: { text: string; tokens: number; can_interrupt: boolean } | null) => void;
-  setTokenBudget: (budget: Record<string, unknown> | null) => void;
+  setClaudeStatus: (status: { text: string; can_interrupt: boolean } | null) => void;
   setPendingPermissionRequests: Dispatch<SetStateAction<PendingPermissionRequest[]>>;
   pendingViewSessionRef: MutableRefObject<PendingViewSession | null>;
   streamBufferRef: MutableRefObject<string>;
@@ -85,7 +82,6 @@ export function useChatRealtimeHandlers({
   setIsLoading,
   setCanAbortSession,
   setClaudeStatus,
-  setTokenBudget,
   setPendingPermissionRequests,
   pendingViewSessionRef,
   streamBufferRef,
@@ -140,7 +136,6 @@ export function useChatRealtimeHandlers({
           if (status) {
             const statusInfo = {
               text: status.text || 'Working...',
-              tokens: status.tokens || 0,
               can_interrupt: status.can_interrupt !== undefined ? status.can_interrupt : true,
             };
             setClaudeStatus(statusInfo);
@@ -311,7 +306,7 @@ export function useChatRealtimeHandlers({
         });
         setIsLoading(true);
         setCanAbortSession(true);
-        setClaudeStatus({ text: 'Waiting for permission', tokens: 0, can_interrupt: true });
+        setClaudeStatus({ text: 'Waiting for permission', can_interrupt: true });
         break;
       }
 
@@ -323,12 +318,9 @@ export function useChatRealtimeHandlers({
       }
 
       case 'status': {
-        if (msg.text === 'token_budget' && msg.tokenBudget) {
-          setTokenBudget(msg.tokenBudget as Record<string, unknown>);
-        } else if (msg.text) {
+        if (msg.text) {
           setClaudeStatus({
             text: msg.text,
-            tokens: msg.tokens || 0,
             can_interrupt: msg.canInterrupt !== undefined ? msg.canInterrupt : true,
           });
           setIsLoading(true);
@@ -352,7 +344,6 @@ export function useChatRealtimeHandlers({
     setIsLoading,
     setCanAbortSession,
     setClaudeStatus,
-    setTokenBudget,
     setPendingPermissionRequests,
     pendingViewSessionRef,
     streamBufferRef,

src/components/chat/hooks/useChatSessionState.ts

@@ -1,6 +1,5 @@
 import { useCallback, useEffect, useLayoutEffect, useMemo, useRef, useState } from 'react';
 import type { MutableRefObject } from 'react';
-import { authenticatedFetch } from '../../../utils/api';
 import type { ChatMessage, Provider } from '../types/types';
 import type { Project, ProjectSession, SessionProvider } from '../../../types/app';
 import { createCachedDiffCalculator, type DiffCalculator } from '../utils/messageTransforms';
@@ -108,9 +107,8 @@ export function useChatSessionState({
   const [totalMessages, setTotalMessages] = useState(0);
   const [canAbortSession, setCanAbortSession] = useState(false);
   const [isUserScrolledUp, setIsUserScrolledUp] = useState(false);
-  const [tokenBudget, setTokenBudget] = useState<Record<string, unknown> | null>(null);
   const [visibleMessageCount, setVisibleMessageCount] = useState(INITIAL_VISIBLE_MESSAGES);
-  const [claudeStatus, setClaudeStatus] = useState<{ text: string; tokens: number; can_interrupt: boolean } | null>(null);
+  const [claudeStatus, setClaudeStatus] = useState<{ text: string; can_interrupt: boolean } | null>(null);
   const [allMessagesLoaded, setAllMessagesLoaded] = useState(false);
   const [isLoadingAllMessages, setIsLoadingAllMessages] = useState(false);
   const [loadAllJustFinished, setLoadAllJustFinished] = useState(false);
@@ -319,7 +317,6 @@ export function useChatSessionState({
       messagesOffsetRef.current = 0;
       setHasMoreMessages(false);
       setTotalMessages(0);
-      setTokenBudget(null);
       lastLoadedSessionKeyRef.current = null;
       return;
     }
@@ -355,7 +352,6 @@ export function useChatSessionState({
     if (loadAllFinishedTimerRef.current) clearTimeout(loadAllFinishedTimerRef.current);
 
     if (sessionChanged) {
-      setTokenBudget(null);
       setIsLoading(false);
     }
 
@@ -383,7 +379,6 @@ export function useChatSessionState({
       if (slot) {
         setHasMoreMessages(slot.hasMore);
         setTotalMessages(slot.total);
-        if (slot.tokenUsage) setTokenBudget(slot.tokenUsage as Record<string, unknown>);
       }
       setIsLoadingSessionMessages(false);
     }).catch(() => {
@@ -539,31 +534,6 @@ export function useChatSessionState({
   // eslint-disable-next-line react-hooks/exhaustive-deps
   }, [chatMessages.length, isLoadingSessionMessages, searchTarget]);
 
-  // Token usage fetch for Claude
-  useEffect(() => {
-    if (!selectedProject || !selectedSession?.id || selectedSession.id.startsWith('new-session-')) {
-      setTokenBudget(null);
-      return;
-    }
-    const sessionProvider = selectedSession.__provider || 'claude';
-    if (sessionProvider !== 'claude') return;
-
-    const fetchInitialTokenUsage = async () => {
-      try {
-        const url = `/api/projects/${selectedProject.name}/sessions/${selectedSession.id}/token-usage`;
-        const response = await authenticatedFetch(url);
-        if (response.ok) {
-          setTokenBudget(await response.json());
-        } else {
-          setTokenBudget(null);
-        }
-      } catch (error) {
-        console.error('Failed to fetch initial token usage:', error);
-      }
-    };
-    fetchInitialTokenUsage();
-  }, [selectedProject, selectedSession?.id, selectedSession?.__provider]);
-
   const visibleMessages = useMemo(() => {
     if (chatMessages.length <= visibleMessageCount) return chatMessages;
     return chatMessages.slice(-visibleMessageCount);
@@ -713,8 +683,6 @@ export function useChatSessionState({
     setCanAbortSession,
     isUserScrolledUp,
     setIsUserScrolledUp,
-    tokenBudget,
-    setTokenBudget,
     visibleMessageCount,
     visibleMessages,
     loadEarlierMessages,

src/components/chat/view/ChatInterface.tsx

@@ -96,8 +96,6 @@ function ChatInterface({
     setCanAbortSession,
     isUserScrolledUp,
     setIsUserScrolledUp,
-    tokenBudget,
-    setTokenBudget,
     visibleMessageCount,
     visibleMessages,
     loadEarlierMessages,
@@ -183,7 +181,6 @@ function ChatInterface({
     geminiModel,
     isLoading,
     canAbortSession,
-    tokenBudget,
     sendMessage,
     sendByCtrlEnter,
     onSessionActive,
@@ -227,7 +224,6 @@ function ChatInterface({
     setIsLoading,
     setCanAbortSession,
     setClaudeStatus,
-    setTokenBudget,
     setPendingPermissionRequests,
     pendingViewSessionRef,
     streamBufferRef,
@@ -352,7 +348,6 @@ function ChatInterface({
           onModeSwitch={cyclePermissionMode}
           thinkingMode={thinkingMode}
           setThinkingMode={setThinkingMode}
-          tokenBudget={tokenBudget}
           slashCommandsCount={slashCommandsCount}
           onToggleCommandMenu={handleToggleCommandMenu}
           hasInput={Boolean(input.trim())}

src/components/chat/view/subcomponents/ChatComposer.tsx

@@ -41,7 +41,7 @@ interface ChatComposerProps {
     decision: { allow?: boolean; message?: string; rememberEntry?: string | null; updatedInput?: unknown },
   ) => void;
   handleGrantToolPermission: (suggestion: { entry: string; toolName: string }) => { success: boolean };
-  claudeStatus: { text: string; tokens: number; can_interrupt: boolean } | null;
+  claudeStatus: { text: string; can_interrupt: boolean } | null;
   isLoading: boolean;
   onAbortSession: () => void;
   provider: Provider | string;
@@ -49,7 +49,6 @@ interface ChatComposerProps {
   onModeSwitch: () => void;
   thinkingMode: string;
   setThinkingMode: Dispatch<SetStateAction<string>>;
-  tokenBudget: { used?: number; total?: number } | null;
   slashCommandsCount: number;
   onToggleCommandMenu: () => void;
   hasInput: boolean;
@@ -106,7 +105,6 @@ export default function ChatComposer({
   onModeSwitch,
   thinkingMode,
   setThinkingMode,
-  tokenBudget,
   slashCommandsCount,
   onToggleCommandMenu,
   hasInput,
@@ -194,7 +192,6 @@ export default function ChatComposer({
           provider={provider}
           thinkingMode={thinkingMode}
           setThinkingMode={setThinkingMode}
-          tokenBudget={tokenBudget}
           slashCommandsCount={slashCommandsCount}
           onToggleCommandMenu={onToggleCommandMenu}
           hasInput={hasInput}

src/components/chat/view/subcomponents/ChatInputControls.tsx

@@ -2,7 +2,6 @@ import React from 'react';
 import { useTranslation } from 'react-i18next';
 import type { PermissionMode, Provider } from '../../types/types';
 import ThinkingModeSelector from './ThinkingModeSelector';
-import TokenUsagePie from './TokenUsagePie';
 
 interface ChatInputControlsProps {
   permissionMode: PermissionMode | string;
@@ -10,7 +9,6 @@ interface ChatInputControlsProps {
   provider: Provider | string;
   thinkingMode: string;
   setThinkingMode: React.Dispatch<React.SetStateAction<string>>;
-  tokenBudget: { used?: number; total?: number } | null;
   slashCommandsCount: number;
   onToggleCommandMenu: () => void;
   hasInput: boolean;
@@ -26,7 +24,6 @@ export default function ChatInputControls({
   provider,
   thinkingMode,
   setThinkingMode,
-  tokenBudget,
   slashCommandsCount,
   onToggleCommandMenu,
   hasInput,
@@ -78,8 +75,6 @@ export default function ChatInputControls({
         <ThinkingModeSelector selectedMode={thinkingMode} onModeChange={setThinkingMode} onClose={() => {}} className="" />
       )}
 
-      <TokenUsagePie used={tokenBudget?.used || 0} total={tokenBudget?.total || parseInt(import.meta.env.VITE_CONTEXT_WINDOW) || 160000} />
-
       <button
         type="button"
         onClick={onToggleCommandMenu}

src/components/chat/view/subcomponents/ClaudeStatus.tsx

@@ -6,7 +6,6 @@ import SessionProviderLogo from '../../../llm-logo-provider/SessionProviderLogo'
 type ClaudeStatusProps = {
   status: {
     text?: string;
-    tokens?: number;
     can_interrupt?: boolean;
   } | null;
   onAbort?: () => void;
@@ -126,4 +125,4 @@ export default function ClaudeStatus({
       </div>
     </div>
   );
-}
+}

src/components/chat/view/subcomponents/TokenUsagePie.tsx

@@ -1,54 +0,0 @@
-type TokenUsagePieProps = {
-  used: number;
-  total: number;
-};
-
-export default function TokenUsagePie({ used, total }: TokenUsagePieProps) {
-  // Token usage visualization component
-  // Only bail out on missing values or non‐positive totals; allow used===0 to render 0%
-  if (used == null || total == null || total <= 0) return null;
-
-  const percentage = Math.min(100, (used / total) * 100);
-  const radius = 10;
-  const circumference = 2 * Math.PI * radius;
-  const offset = circumference - (percentage / 100) * circumference;
-
-  // Color based on usage level
-  const getColor = () => {
-    if (percentage < 50) return '#3b82f6'; // blue
-    if (percentage < 75) return '#f59e0b'; // orange
-    return '#ef4444'; // red
-  };
-
-  return (
-    <div className="flex items-center gap-2 text-xs text-gray-600 dark:text-gray-400">
-      <svg width="24" height="24" viewBox="0 0 24 24" className="-rotate-90 transform">
-        {/* Background circle */}
-        <circle
-          cx="12"
-          cy="12"
-          r={radius}
-          fill="none"
-          stroke="currentColor"
-          strokeWidth="2"
-          className="text-gray-300 dark:text-gray-600"
-        />
-        {/* Progress circle */}
-        <circle
-          cx="12"
-          cy="12"
-          r={radius}
-          fill="none"
-          stroke={getColor()}
-          strokeWidth="2"
-          strokeDasharray={circumference}
-          strokeDashoffset={offset}
-          strokeLinecap="round"
-        />
-      </svg>
-      <span title={`${used.toLocaleString()} / ${total.toLocaleString()} tokens`}>
-        {percentage.toFixed(1)}%
-      </span>
-    </div>
-  );
-}

src/stores/useSessionStore.ts

@@ -46,9 +46,7 @@ export interface NormalizedMessage {
   toolResult?: { content: string; isError: boolean; toolUseResult?: unknown } | null;
   isError?: boolean;
   text?: string;
-  tokens?: number;
   canInterrupt?: boolean;
-  tokenBudget?: unknown;
   requestId?: string;
   input?: unknown;
   context?: unknown;
@@ -81,7 +79,6 @@ export interface SessionSlot {
   total: number;
   hasMore: boolean;
   offset: number;
-  tokenUsage: unknown;
 }
 
 const EMPTY: NormalizedMessage[] = [];
@@ -98,7 +95,6 @@ function createEmptySlot(): SessionSlot {
     total: 0,
     hasMore: false,
     offset: 0,
-    tokenUsage: null,
   };
 }
 
@@ -208,9 +204,6 @@ export function useSessionStore() {
       slot.fetchedAt = Date.now();
       slot.status = 'idle';
       recomputeMergedIfNeeded(slot);
-      if (data.tokenUsage) {
-        slot.tokenUsage = data.tokenUsage;
-      }
 
       notify(sessionId);
       return slot;