feat: unified Claude API key and profile system with z.AI, MiniMax, OpenRouter support (#600)

* feat: add Claude API provider profiles for alternative endpoints

Add support for managing multiple Claude-compatible API endpoints
(z.AI GLM, AWS Bedrock, etc.) through provider profiles in settings.

Features:
- New ClaudeApiProfile type with base URL, API key, model mappings
- Pre-configured z.AI GLM template with correct model names
- Profile selector in Settings > Claude > API Profiles
- Clean switching between profiles and direct Anthropic API
- Immediate persistence to prevent data loss on restart

Profile support added to all execution paths:
- Agent service (chat)
- Ideation service
- Auto-mode service (feature agents, enhancements)
- Simple query service (title generation, descriptions, etc.)
- Backlog planning, commit messages, spec generation
- GitHub issue validation, suggestions

Environment variables set when profile is active:
- ANTHROPIC_BASE_URL, ANTHROPIC_AUTH_TOKEN/API_KEY
- ANTHROPIC_DEFAULT_HAIKU/SONNET/OPUS_MODEL
- API_TIMEOUT_MS, CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC

apps/server/src/routes/app-spec/generate-features-from-spec.ts

@@ -14,7 +14,11 @@ import { streamingQuery } from '../../providers/simple-query-service.js';
 import { parseAndCreateFeatures } from './parse-and-create-features.js';
 import { getAppSpecPath } from '@automaker/platform';
 import type { SettingsService } from '../../services/settings-service.js';
-import { getAutoLoadClaudeMdSetting, getPromptCustomization } from '../../lib/settings-helpers.js';
+import {
+  getAutoLoadClaudeMdSetting,
+  getPromptCustomization,
+  getActiveClaudeApiProfile,
+} from '../../lib/settings-helpers.js';
 import { FeatureLoader } from '../../services/feature-loader.js';
 
 const logger = createLogger('SpecRegeneration');
@@ -123,6 +127,13 @@ Generate ${featureCount} NEW features that build on each other logically. Rememb
 
   logger.info('Using model:', model);
 
+  // Get active Claude API profile for alternative endpoint configuration
+  const { profile: claudeApiProfile, credentials } = await getActiveClaudeApiProfile(
+    settingsService,
+    '[FeatureGeneration]',
+    projectPath
+  );
+
   // Use streamingQuery with event callbacks
   const result = await streamingQuery({
     prompt,
@@ -134,6 +145,8 @@ Generate ${featureCount} NEW features that build on each other logically. Rememb
     thinkingLevel,
     readOnly: true, // Feature generation only reads code, doesn't write
     settingSources: autoLoadClaudeMd ? ['user', 'project', 'local'] : undefined,
+    claudeApiProfile, // Pass active Claude API profile for alternative endpoint configuration
+    credentials, // Pass credentials for resolving 'credentials' apiKeySource
     onText: (text) => {
       logger.debug(`Feature text block received (${text.length} chars)`);
       events.emit('spec-regeneration:event', {

apps/server/src/routes/app-spec/generate-spec.ts

@@ -16,7 +16,11 @@ import { streamingQuery } from '../../providers/simple-query-service.js';
 import { generateFeaturesFromSpec } from './generate-features-from-spec.js';
 import { ensureAutomakerDir, getAppSpecPath } from '@automaker/platform';
 import type { SettingsService } from '../../services/settings-service.js';
-import { getAutoLoadClaudeMdSetting, getPromptCustomization } from '../../lib/settings-helpers.js';
+import {
+  getAutoLoadClaudeMdSetting,
+  getPromptCustomization,
+  getActiveClaudeApiProfile,
+} from '../../lib/settings-helpers.js';
 
 const logger = createLogger('SpecRegeneration');
 
@@ -100,6 +104,13 @@ ${prompts.appSpec.structuredSpecInstructions}`;
 
   logger.info('Using model:', model);
 
+  // Get active Claude API profile for alternative endpoint configuration
+  const { profile: claudeApiProfile, credentials } = await getActiveClaudeApiProfile(
+    settingsService,
+    '[SpecRegeneration]',
+    projectPath
+  );
+
   let responseText = '';
   let structuredOutput: SpecOutput | null = null;
 
@@ -132,6 +143,8 @@ Your entire response should be valid JSON starting with { and ending with }. No
     thinkingLevel,
     readOnly: true, // Spec generation only reads code, we write the spec ourselves
     settingSources: autoLoadClaudeMd ? ['user', 'project', 'local'] : undefined,
+    claudeApiProfile, // Pass active Claude API profile for alternative endpoint configuration
+    credentials, // Pass credentials for resolving 'credentials' apiKeySource
     outputFormat: useStructuredOutput
       ? {
           type: 'json_schema',

apps/server/src/routes/app-spec/sync-spec.ts

@@ -15,7 +15,10 @@ import { resolvePhaseModel } from '@automaker/model-resolver';
 import { streamingQuery } from '../../providers/simple-query-service.js';
 import { getAppSpecPath } from '@automaker/platform';
 import type { SettingsService } from '../../services/settings-service.js';
-import { getAutoLoadClaudeMdSetting } from '../../lib/settings-helpers.js';
+import {
+  getAutoLoadClaudeMdSetting,
+  getActiveClaudeApiProfile,
+} from '../../lib/settings-helpers.js';
 import { FeatureLoader } from '../../services/feature-loader.js';
 import {
   extractImplementedFeatures,
@@ -157,6 +160,13 @@ export async function syncSpec(
     settings?.phaseModels?.specGenerationModel || DEFAULT_PHASE_MODELS.specGenerationModel;
   const { model, thinkingLevel } = resolvePhaseModel(phaseModelEntry);
 
+  // Get active Claude API profile for alternative endpoint configuration
+  const { profile: claudeApiProfile, credentials } = await getActiveClaudeApiProfile(
+    settingsService,
+    '[SpecSync]',
+    projectPath
+  );
+
   // Use AI to analyze tech stack
   const techAnalysisPrompt = `Analyze this project and return ONLY a JSON object with the current technology stack.
 
@@ -185,6 +195,8 @@ Return ONLY this JSON format, no other text:
       thinkingLevel,
       readOnly: true,
       settingSources: autoLoadClaudeMd ? ['user', 'project', 'local'] : undefined,
+      claudeApiProfile, // Pass active Claude API profile for alternative endpoint configuration
+      credentials, // Pass credentials for resolving 'credentials' apiKeySource
       onText: (text) => {
         logger.debug(`Tech analysis text: ${text.substring(0, 100)}`);
       },

apps/server/src/routes/backlog-plan/generate-plan.ts

@@ -25,7 +25,11 @@ import {
   saveBacklogPlan,
 } from './common.js';
 import type { SettingsService } from '../../services/settings-service.js';
-import { getAutoLoadClaudeMdSetting, getPromptCustomization } from '../../lib/settings-helpers.js';
+import {
+  getAutoLoadClaudeMdSetting,
+  getPromptCustomization,
+  getActiveClaudeApiProfile,
+} from '../../lib/settings-helpers.js';
 
 const featureLoader = new FeatureLoader();
 
@@ -161,6 +165,13 @@ ${userPrompt}`;
       finalSystemPrompt = undefined; // System prompt is now embedded in the user prompt
     }
 
+    // Get active Claude API profile for alternative endpoint configuration
+    const { profile: claudeApiProfile, credentials } = await getActiveClaudeApiProfile(
+      settingsService,
+      '[BacklogPlan]',
+      projectPath
+    );
+
     // Execute the query
     const stream = provider.executeQuery({
       prompt: finalPrompt,
@@ -173,6 +184,8 @@ ${userPrompt}`;
       settingSources: autoLoadClaudeMd ? ['user', 'project'] : undefined,
       readOnly: true, // Plan generation only generates text, doesn't write files
       thinkingLevel, // Pass thinking level for extended thinking
+      claudeApiProfile, // Pass active Claude API profile for alternative endpoint configuration
+      credentials, // Pass credentials for resolving 'credentials' apiKeySource
     });
 
     let responseText = '';

apps/server/src/routes/context/routes/describe-file.ts

@@ -22,6 +22,7 @@ import type { SettingsService } from '../../../services/settings-service.js';
 import {
   getAutoLoadClaudeMdSetting,
   getPromptCustomization,
+  getActiveClaudeApiProfile,
 } from '../../../lib/settings-helpers.js';
 
 const logger = createLogger('DescribeFile');
@@ -165,6 +166,13 @@ ${contentToAnalyze}`;
 
       logger.info(`Resolved model: ${model}, thinkingLevel: ${thinkingLevel}`);
 
+      // Get active Claude API profile for alternative endpoint configuration
+      const { profile: claudeApiProfile, credentials } = await getActiveClaudeApiProfile(
+        settingsService,
+        '[DescribeFile]',
+        cwd
+      );
+
       // Use simpleQuery - provider abstraction handles routing to correct provider
       const result = await simpleQuery({
         prompt,
@@ -175,6 +183,8 @@ ${contentToAnalyze}`;
         thinkingLevel,
         readOnly: true, // File description only reads, doesn't write
         settingSources: autoLoadClaudeMd ? ['user', 'project', 'local'] : undefined,
+        claudeApiProfile, // Pass active Claude API profile for alternative endpoint configuration
+        credentials, // Pass credentials for resolving 'credentials' apiKeySource
       });
 
       const description = result.text;

apps/server/src/routes/context/routes/describe-image.ts

@@ -22,6 +22,7 @@ import type { SettingsService } from '../../../services/settings-service.js';
 import {
   getAutoLoadClaudeMdSetting,
   getPromptCustomization,
+  getActiveClaudeApiProfile,
 } from '../../../lib/settings-helpers.js';
 
 const logger = createLogger('DescribeImage');
@@ -284,6 +285,13 @@ export function createDescribeImageHandler(
       // Get customized prompts from settings
       const prompts = await getPromptCustomization(settingsService, '[DescribeImage]');
 
+      // Get active Claude API profile for alternative endpoint configuration
+      const { profile: claudeApiProfile, credentials } = await getActiveClaudeApiProfile(
+        settingsService,
+        '[DescribeImage]',
+        cwd
+      );
+
       // Build the instruction text from centralized prompts
       const instructionText = prompts.contextDescription.describeImagePrompt;
 
@@ -325,6 +333,8 @@ export function createDescribeImageHandler(
         thinkingLevel,
         readOnly: true, // Image description only reads, doesn't write
         settingSources: autoLoadClaudeMd ? ['user', 'project', 'local'] : undefined,
+        claudeApiProfile, // Pass active Claude API profile for alternative endpoint configuration
+        credentials, // Pass credentials for resolving 'credentials' apiKeySource
       });
 
       logger.info(`[${requestId}] simpleQuery completed in ${Date.now() - queryStart}ms`);

apps/server/src/routes/enhance-prompt/routes/enhance.ts

@@ -12,7 +12,10 @@ import { resolveModelString } from '@automaker/model-resolver';
 import { CLAUDE_MODEL_MAP, type ThinkingLevel } from '@automaker/types';
 import { simpleQuery } from '../../../providers/simple-query-service.js';
 import type { SettingsService } from '../../../services/settings-service.js';
-import { getPromptCustomization } from '../../../lib/settings-helpers.js';
+import {
+  getPromptCustomization,
+  getActiveClaudeApiProfile,
+} from '../../../lib/settings-helpers.js';
 import {
   buildUserPrompt,
   isValidEnhancementMode,
@@ -33,6 +36,8 @@ interface EnhanceRequestBody {
   model?: string;
   /** Optional thinking level for Claude models */
   thinkingLevel?: ThinkingLevel;
+  /** Optional project path for per-project Claude API profile */
+  projectPath?: string;
 }
 
 /**
@@ -62,7 +67,7 @@ export function createEnhanceHandler(
 ): (req: Request, res: Response) => Promise<void> {
   return async (req: Request, res: Response): Promise<void> => {
     try {
-      const { originalText, enhancementMode, model, thinkingLevel } =
+      const { originalText, enhancementMode, model, thinkingLevel, projectPath } =
         req.body as EnhanceRequestBody;
 
       // Validate required fields
@@ -126,6 +131,14 @@ export function createEnhanceHandler(
 
       logger.debug(`Using model: ${resolvedModel}`);
 
+      // Get active Claude API profile for alternative endpoint configuration
+      // Uses project-specific profile if projectPath provided, otherwise global
+      const { profile: claudeApiProfile, credentials } = await getActiveClaudeApiProfile(
+        settingsService,
+        '[EnhancePrompt]',
+        projectPath
+      );
+
       // Use simpleQuery - provider abstraction handles routing to correct provider
       // The system prompt is combined with user prompt since some providers
       // don't have a separate system prompt concept
@@ -137,6 +150,8 @@ export function createEnhanceHandler(
         allowedTools: [],
         thinkingLevel,
         readOnly: true, // Prompt enhancement only generates text, doesn't write files
+        claudeApiProfile, // Pass active Claude API profile for alternative endpoint configuration
+        credentials, // Pass credentials for resolving 'credentials' apiKeySource
       });
 
       const enhancedText = result.text;

apps/server/src/routes/features/routes/generate-title.ts

@@ -10,12 +10,16 @@ import { createLogger } from '@automaker/utils';
 import { CLAUDE_MODEL_MAP } from '@automaker/model-resolver';
 import { simpleQuery } from '../../../providers/simple-query-service.js';
 import type { SettingsService } from '../../../services/settings-service.js';
-import { getPromptCustomization } from '../../../lib/settings-helpers.js';
+import {
+  getPromptCustomization,
+  getActiveClaudeApiProfile,
+} from '../../../lib/settings-helpers.js';
 
 const logger = createLogger('GenerateTitle');
 
 interface GenerateTitleRequestBody {
   description: string;
+  projectPath?: string;
 }
 
 interface GenerateTitleSuccessResponse {
@@ -33,7 +37,7 @@ export function createGenerateTitleHandler(
 ): (req: Request, res: Response) => Promise<void> {
   return async (req: Request, res: Response): Promise<void> => {
     try {
-      const { description } = req.body as GenerateTitleRequestBody;
+      const { description, projectPath } = req.body as GenerateTitleRequestBody;
 
       if (!description || typeof description !== 'string') {
         const response: GenerateTitleErrorResponse = {
@@ -60,6 +64,14 @@ export function createGenerateTitleHandler(
       const prompts = await getPromptCustomization(settingsService, '[GenerateTitle]');
       const systemPrompt = prompts.titleGeneration.systemPrompt;
 
+      // Get active Claude API profile for alternative endpoint configuration
+      // Uses project-specific profile if projectPath provided, otherwise global
+      const { profile: claudeApiProfile, credentials } = await getActiveClaudeApiProfile(
+        settingsService,
+        '[GenerateTitle]',
+        projectPath
+      );
+
       const userPrompt = `Generate a concise title for this feature:\n\n${trimmedDescription}`;
 
       // Use simpleQuery - provider abstraction handles all the streaming/extraction
@@ -69,6 +81,8 @@ export function createGenerateTitleHandler(
         cwd: process.cwd(),
         maxTurns: 1,
         allowedTools: [],
+        claudeApiProfile, // Pass active Claude API profile for alternative endpoint configuration
+        credentials, // Pass credentials for resolving 'credentials' apiKeySource
       });
 
       const title = result.text;

apps/server/src/routes/github/routes/validate-issue.ts

@@ -34,7 +34,11 @@ import {
   ValidationComment,
   ValidationLinkedPR,
 } from './validation-schema.js';
-import { getPromptCustomization } from '../../../lib/settings-helpers.js';
+import {
+  getPromptCustomization,
+  getAutoLoadClaudeMdSetting,
+  getActiveClaudeApiProfile,
+} from '../../../lib/settings-helpers.js';
 import {
   trySetValidationRunning,
   clearValidationStatus,
@@ -43,7 +47,6 @@ import {
   logger,
 } from './validation-common.js';
 import type { SettingsService } from '../../../services/settings-service.js';
-import { getAutoLoadClaudeMdSetting } from '../../../lib/settings-helpers.js';
 
 /**
  * Request body for issue validation
@@ -166,6 +169,13 @@ ${basePrompt}`;
 
     logger.info(`Using model: ${model}`);
 
+    // Get active Claude API profile for alternative endpoint configuration
+    const { profile: claudeApiProfile, credentials } = await getActiveClaudeApiProfile(
+      settingsService,
+      '[IssueValidation]',
+      projectPath
+    );
+
     // Use streamingQuery with event callbacks
     const result = await streamingQuery({
       prompt: finalPrompt,
@@ -177,6 +187,8 @@ ${basePrompt}`;
       reasoningEffort: effectiveReasoningEffort,
       readOnly: true, // Issue validation only reads code, doesn't write
       settingSources: autoLoadClaudeMd ? ['user', 'project', 'local'] : undefined,
+      claudeApiProfile, // Pass active Claude API profile for alternative endpoint configuration
+      credentials, // Pass credentials for resolving 'credentials' apiKeySource
       outputFormat: useStructuredOutput
         ? {
             type: 'json_schema',

apps/server/src/routes/suggestions/generate-suggestions.ts

@@ -15,7 +15,11 @@ import { FeatureLoader } from '../../services/feature-loader.js';
 import { getAppSpecPath } from '@automaker/platform';
 import * as secureFs from '../../lib/secure-fs.js';
 import type { SettingsService } from '../../services/settings-service.js';
-import { getAutoLoadClaudeMdSetting, getPromptCustomization } from '../../lib/settings-helpers.js';
+import {
+  getAutoLoadClaudeMdSetting,
+  getPromptCustomization,
+  getActiveClaudeApiProfile,
+} from '../../lib/settings-helpers.js';
 
 const logger = createLogger('Suggestions');
 
@@ -192,6 +196,13 @@ ${prompts.suggestions.baseTemplate}`;
 
   logger.info('[Suggestions] Using model:', model);
 
+  // Get active Claude API profile for alternative endpoint configuration
+  const { profile: claudeApiProfile, credentials } = await getActiveClaudeApiProfile(
+    settingsService,
+    '[Suggestions]',
+    projectPath
+  );
+
   let responseText = '';
 
   // Determine if we should use structured output (Claude supports it, Cursor doesn't)
@@ -223,6 +234,8 @@ Your entire response should be valid JSON starting with { and ending with }. No
     thinkingLevel,
     readOnly: true, // Suggestions only reads code, doesn't write
     settingSources: autoLoadClaudeMd ? ['user', 'project', 'local'] : undefined,
+    claudeApiProfile, // Pass active Claude API profile for alternative endpoint configuration
+    credentials, // Pass credentials for resolving 'credentials' apiKeySource
     outputFormat: useStructuredOutput
       ? {
           type: 'json_schema',

apps/server/src/routes/worktree/routes/generate-commit-message.ts

@@ -10,7 +10,6 @@ import { exec } from 'child_process';
 import { promisify } from 'util';
 import { existsSync } from 'fs';
 import { join } from 'path';
-import { query } from '@anthropic-ai/claude-agent-sdk';
 import { createLogger } from '@automaker/utils';
 import { DEFAULT_PHASE_MODELS, isCursorModel, stripProviderPrefix } from '@automaker/types';
 import { resolvePhaseModel } from '@automaker/model-resolver';
@@ -18,6 +17,7 @@ import { mergeCommitMessagePrompts } from '@automaker/prompts';
 import { ProviderFactory } from '../../../providers/provider-factory.js';
 import type { SettingsService } from '../../../services/settings-service.js';
 import { getErrorMessage, logError } from '../common.js';
+import { getActiveClaudeApiProfile } from '../../../lib/settings-helpers.js';
 
 const logger = createLogger('GenerateCommitMessage');
 const execAsync = promisify(exec);
@@ -74,33 +74,6 @@ interface GenerateCommitMessageErrorResponse {
   error: string;
 }
 
-async function extractTextFromStream(
-  stream: AsyncIterable<{
-    type: string;
-    subtype?: string;
-    result?: string;
-    message?: {
-      content?: Array<{ type: string; text?: string }>;
-    };
-  }>
-): Promise<string> {
-  let responseText = '';
-
-  for await (const msg of stream) {
-    if (msg.type === 'assistant' && msg.message?.content) {
-      for (const block of msg.message.content) {
-        if (block.type === 'text' && block.text) {
-          responseText += block.text;
-        }
-      }
-    } else if (msg.type === 'result' && msg.subtype === 'success') {
-      responseText = msg.result || responseText;
-    }
-  }
-
-  return responseText;
-}
-
 export function createGenerateCommitMessageHandler(
   settingsService?: SettingsService
 ): (req: Request, res: Response) => Promise<void> {
@@ -195,57 +168,54 @@ export function createGenerateCommitMessageHandler(
       // Get the effective system prompt (custom or default)
       const systemPrompt = await getSystemPrompt(settingsService);
 
-      let message: string;
+      // Get active Claude API profile for alternative endpoint configuration
+      const { profile: claudeApiProfile, credentials } = await getActiveClaudeApiProfile(
+        settingsService,
+        '[GenerateCommitMessage]',
+        worktreePath
+      );
 
-      // Route to appropriate provider based on model type
-      if (isCursorModel(model)) {
-        // Use Cursor provider for Cursor models
-        logger.info(`Using Cursor provider for model: ${model}`);
+      // Get provider for the model type
+      const provider = ProviderFactory.getProviderForModel(model);
+      const bareModel = stripProviderPrefix(model);
 
-        const provider = ProviderFactory.getProviderForModel(model);
-        const bareModel = stripProviderPrefix(model);
+      // For Cursor models, combine prompts since Cursor doesn't support systemPrompt separation
+      const effectivePrompt = isCursorModel(model)
+        ? `${systemPrompt}\n\n${userPrompt}`
+        : userPrompt;
+      const effectiveSystemPrompt = isCursorModel(model) ? undefined : systemPrompt;
 
-        const cursorPrompt = `${systemPrompt}\n\n${userPrompt}`;
+      logger.info(`Using ${provider.getName()} provider for model: ${model}`);
 
-        let responseText = '';
-        const cursorStream = provider.executeQuery({
-          prompt: cursorPrompt,
-          model: bareModel,
-          cwd: worktreePath,
-          maxTurns: 1,
-          allowedTools: [],
-          readOnly: true,
-        });
+      let responseText = '';
+      const stream = provider.executeQuery({
+        prompt: effectivePrompt,
+        model: bareModel,
+        cwd: worktreePath,
+        systemPrompt: effectiveSystemPrompt,
+        maxTurns: 1,
+        allowedTools: [],
+        readOnly: true,
+        claudeApiProfile, // Pass active Claude API profile for alternative endpoint configuration
+        credentials, // Pass credentials for resolving 'credentials' apiKeySource
+      });
 
-        // Wrap with timeout to prevent indefinite hangs
-        for await (const msg of withTimeout(cursorStream, AI_TIMEOUT_MS)) {
-          if (msg.type === 'assistant' && msg.message?.content) {
-            for (const block of msg.message.content) {
-              if (block.type === 'text' && block.text) {
-                responseText += block.text;
-              }
+      // Wrap with timeout to prevent indefinite hangs
+      for await (const msg of withTimeout(stream, AI_TIMEOUT_MS)) {
+        if (msg.type === 'assistant' && msg.message?.content) {
+          for (const block of msg.message.content) {
+            if (block.type === 'text' && block.text) {
+              responseText += block.text;
             }
           }
+        } else if (msg.type === 'result' && msg.subtype === 'success' && msg.result) {
+          // Use result if available (some providers return final text here)
+          responseText = msg.result;
         }
-
-        message = responseText.trim();
-      } else {
-        // Use Claude SDK for Claude models
-        const stream = query({
-          prompt: userPrompt,
-          options: {
-            model,
-            systemPrompt,
-            maxTurns: 1,
-            allowedTools: [],
-            permissionMode: 'default',
-          },
-        });
-
-        // Wrap with timeout to prevent indefinite hangs
-        message = await extractTextFromStream(withTimeout(stream, AI_TIMEOUT_MS));
       }
 
+      const message = responseText.trim();
+
       if (!message || message.trim().length === 0) {
         logger.warn('Received empty response from model');
         const response: GenerateCommitMessageErrorResponse = {