@link-assistant/hive-mind 1.34.3 → 1.34.4

package/CHANGELOG.md

@@ -1,5 +1,15 @@
 # @link-assistant/hive-mind
 
+## 1.34.4
+
+### Patch Changes
+
+- c3806b5: Fix missing log upload on tool failure and make HTTP 529 overload error retryable (Issue #1439)
+
+  Two fixes:
+  1. When `--attach-logs` is enabled and the tool execution fails during an auto-restart session, the failure log was not being uploaded to GitHub. Now the log is attached before stopping on both tool execution failure paths.
+  2. HTTP 529 (Anthropic "Overloaded") errors were not recognized as transient/retryable by the outer retry loop. The code only matched `API Error: 500` + `Overloaded`, but 529 uses `API Error: 529` + `overloaded_error`. Now both 500 and 529 overload errors trigger the retry logic with exponential backoff.
+
 ## 1.34.3
 
 ### Patch Changes

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@link-assistant/hive-mind",
-  "version": "1.34.3",
+  "version": "1.34.4",
   "description": "AI-powered issue solver and hive mind for collaborative problem solving",
   "main": "src/hive.mjs",
   "type": "module",

package/src/claude.lib.mjs

@@ -129,8 +129,8 @@ export const validateClaudeConnection = async (model = 'haiku-3') => {
         return null;
       };
       const jsonError = checkForJsonError(stdout) || checkForJsonError(stderr);
-      // Check for API overload error pattern
-      const isOverloadError = (stdout.includes('API Error: 500') && stdout.includes('Overloaded')) || (stderr.includes('API Error: 500') && stderr.includes('Overloaded')) || (jsonError && jsonError.type === 'api_error' && jsonError.message === 'Overloaded');
+      // Check for API overload error pattern (Issue #1439: also detect 529 overloaded_error)
+      const isOverloadError = (stdout.includes('API Error: 500') && stdout.includes('Overloaded')) || (stdout.includes('API Error: 529') && stdout.includes('Overloaded')) || (stderr.includes('API Error: 500') && stderr.includes('Overloaded')) || (stderr.includes('API Error: 529') && stderr.includes('Overloaded')) || (jsonError && (jsonError.type === 'api_error' || jsonError.type === 'overloaded_error') && jsonError.message === 'Overloaded');
       // Handle overload errors with retry
       if (isOverloadError) {
         if (retryCount < maxRetries) {
@@ -168,7 +168,7 @@ export const validateClaudeConnection = async (model = 'haiku-3') => {
       }
       // Check for error patterns in successful response
       if (jsonError) {
-        if (jsonError.type === 'api_error' && jsonError.message === 'Overloaded') {
+        if ((jsonError.type === 'api_error' || jsonError.type === 'overloaded_error') && jsonError.message === 'Overloaded') {
           if (retryCount < maxRetries) {
             const delay = baseDelay * Math.pow(2, retryCount);
             await log(`⚠️ API overload error in response. Retrying in ${delay / 1000} seconds...`, {
@@ -193,7 +193,7 @@ export const validateClaudeConnection = async (model = 'haiku-3') => {
       return true;
     } catch (error) {
       const errorStr = error.message || error.toString();
-      if ((errorStr.includes('API Error: 500') && errorStr.includes('Overloaded')) || (errorStr.includes('api_error') && errorStr.includes('Overloaded'))) {
+      if ((errorStr.includes('API Error: 500') && errorStr.includes('Overloaded')) || (errorStr.includes('API Error: 529') && errorStr.includes('Overloaded')) || (errorStr.includes('api_error') && errorStr.includes('Overloaded')) || (errorStr.includes('overloaded_error') && errorStr.includes('Overloaded'))) {
         if (retryCount < maxRetries) {
           const delay = baseDelay * Math.pow(2, retryCount);
           await log(`⚠️ API overload error during validation. Retrying in ${delay / 1000} seconds...`, {
@@ -1067,11 +1067,11 @@ export const executeClaudeCommand = async params => {
                 const content = Array.isArray(data.message.content) ? data.message.content : [data.message.content];
                 for (const item of content) {
                   if (item.type === 'text' && item.text) {
-                    // Check for the specific 500 overload error pattern
-                    if (item.text.includes('API Error: 500') && item.text.includes('api_error') && item.text.includes('Overloaded')) {
+                    // Check for the specific 500/529 overload error pattern (Issue #1439: 529 is also an overload)
+                    if ((item.text.includes('API Error: 500') || item.text.includes('API Error: 529')) && (item.text.includes('api_error') || item.text.includes('overloaded_error')) && item.text.includes('Overloaded')) {
                       isOverloadError = true;
                       lastMessage = item.text;
-                      await log('⚠️ Detected API overload error', { verbose: true });
+                      await log(`⚠️ Detected API overload error${item.text.includes('529') ? ' (529)' : ' (500)'}`, { verbose: true });
                     }
                     if (item.text.includes('API Error: 500') && item.text.includes('Internal server error') && !item.text.includes('Overloaded')) {
                       isInternalServerError = true;
@@ -1194,7 +1194,7 @@ export const executeClaudeCommand = async params => {
 
       // Issues #1331, #1353: Unified handler for transient API errors (Overloaded, 503, Internal Server Error,
       // Request timed out). All use exponential backoff with session preservation via --resume.
-      const isTransientError = isOverloadError || isInternalServerError || is503Error || isRequestTimeout || (lastMessage.includes('API Error: 500') && (lastMessage.includes('Overloaded') || lastMessage.includes('Internal server error'))) || (lastMessage.includes('api_error') && lastMessage.includes('Overloaded')) || lastMessage.includes('API Error: 503') || (lastMessage.includes('503') && (lastMessage.includes('upstream connect error') || lastMessage.includes('remote connection failure'))) || lastMessage === 'Request timed out' || lastMessage.includes('Request timed out');
+      const isTransientError = isOverloadError || isInternalServerError || is503Error || isRequestTimeout || (lastMessage.includes('API Error: 500') && (lastMessage.includes('Overloaded') || lastMessage.includes('Internal server error'))) || (lastMessage.includes('API Error: 529') && (lastMessage.includes('overloaded_error') || lastMessage.includes('Overloaded'))) || (lastMessage.includes('api_error') && lastMessage.includes('Overloaded')) || (lastMessage.includes('overloaded_error') && lastMessage.includes('Overloaded')) || lastMessage.includes('API Error: 503') || (lastMessage.includes('503') && (lastMessage.includes('upstream connect error') || lastMessage.includes('remote connection failure'))) || lastMessage === 'Request timed out' || lastMessage.includes('Request timed out');
       if ((commandFailed || isTransientError) && isTransientError) {
         // Issue #1353: Timeouts use longer backoff (5min–1hr) vs general transient (2min–30min)
         const maxRetries = isRequestTimeout ? retryLimits.maxRequestTimeoutRetries : retryLimits.maxTransientErrorRetries;
@@ -1222,7 +1222,7 @@ export const executeClaudeCommand = async params => {
         }
         if (retryCount < maxRetries) {
           const delay = Math.min(initialDelay * Math.pow(retryLimits.retryBackoffMultiplier, retryCount), maxDelay);
-          const errorLabel = isRequestTimeout ? 'Request timeout' : isOverloadError || (lastMessage.includes('API Error: 500') && lastMessage.includes('Overloaded')) ? 'API overload (500)' : isInternalServerError || lastMessage.includes('Internal server error') ? 'Internal server error (500)' : '503 network error';
+          const errorLabel = isRequestTimeout ? 'Request timeout' : isOverloadError || (lastMessage.includes('API Error: 500') && lastMessage.includes('Overloaded')) || (lastMessage.includes('API Error: 529') && lastMessage.includes('Overloaded')) ? `API overload (${lastMessage.includes('529') ? '529' : '500'})` : isInternalServerError || lastMessage.includes('Internal server error') ? 'Internal server error (500)' : '503 network error';
           const notRetryableHint = apiMarkedNotRetryable ? ' (API says not retryable — will stop early if no progress)' : '';
           await log(`\n⚠️ ${errorLabel} detected. Retry ${retryCount + 1}/${maxRetries} in ${Math.round(delay / 60000)} min (session preserved)${notRetryableHint}...`, { level: 'warning' });
           await log(`   Error: ${lastMessage.substring(0, 200)}`, { verbose: true });
@@ -1393,7 +1393,7 @@ export const executeClaudeCommand = async params => {
       // Issue #1353: Also handle "Request timed out" in exception block
       // (Overloaded, 503, Internal Server Error, Request timed out) - all with session preservation
       const isTimeoutException = errorStr === 'Request timed out' || errorStr.includes('Request timed out');
-      const isTransientException = isTimeoutException || (errorStr.includes('API Error: 500') && (errorStr.includes('Overloaded') || errorStr.includes('Internal server error'))) || (errorStr.includes('api_error') && errorStr.includes('Overloaded')) || errorStr.includes('API Error: 503') || (errorStr.includes('503') && (errorStr.includes('upstream connect error') || errorStr.includes('remote connection failure')));
+      const isTransientException = isTimeoutException || (errorStr.includes('API Error: 500') && (errorStr.includes('Overloaded') || errorStr.includes('Internal server error'))) || (errorStr.includes('API Error: 529') && (errorStr.includes('overloaded_error') || errorStr.includes('Overloaded'))) || (errorStr.includes('api_error') && errorStr.includes('Overloaded')) || (errorStr.includes('overloaded_error') && errorStr.includes('Overloaded')) || errorStr.includes('API Error: 503') || (errorStr.includes('503') && (errorStr.includes('upstream connect error') || errorStr.includes('remote connection failure')));
       if (isTransientException) {
         // Issue #1353: Use timeout-specific backoff for request timeouts
         const maxRetries = isTimeoutException ? retryLimits.maxRequestTimeoutRetries : retryLimits.maxTransientErrorRetries;
@@ -1401,7 +1401,7 @@ export const executeClaudeCommand = async params => {
         const maxDelay = isTimeoutException ? retryLimits.maxRequestTimeoutDelayMs : retryLimits.maxTransientErrorDelayMs;
         if (retryCount < maxRetries) {
           const delay = Math.min(initialDelay * Math.pow(retryLimits.retryBackoffMultiplier, retryCount), maxDelay);
-          const errorLabel = isTimeoutException ? 'Request timeout' : errorStr.includes('Overloaded') ? 'API overload (500)' : errorStr.includes('Internal server error') ? 'Internal server error (500)' : '503 network error';
+          const errorLabel = isTimeoutException ? 'Request timeout' : errorStr.includes('Overloaded') ? `API overload (${errorStr.includes('529') ? '529' : '500'})` : errorStr.includes('Internal server error') ? 'Internal server error (500)' : '503 network error';
           await log(`\n⚠️ ${errorLabel} in exception. Retry ${retryCount + 1}/${maxRetries} in ${Math.round(delay / 60000)} min (session preserved)...`, { level: 'warning' });
           if (sessionId && !argv.resume) argv.resume = sessionId;
           await waitWithCountdown(delay, log);

package/src/solve.auto-merge.lib.mjs

@@ -739,6 +739,40 @@ Once the billing issue is resolved, you can re-run the CI checks or push a new c
                 await log('');
                 await log(formatAligned('❌', `${argv.tool.toUpperCase()} RESUME FAILED`, ''));
                 await log(formatAligned('', 'Action:', 'Stopping auto-restart — tool execution failed after limit reset', 2));
+                // Issue #1439: Attach failure log before stopping, so user can see what happened
+                const shouldAttachLogsOnResumeFail = argv.attachLogs || argv['attach-logs'];
+                if (prNumber && shouldAttachLogsOnResumeFail) {
+                  try {
+                    const logFile = getLogFile();
+                    if (logFile) {
+                      await attachLogToGitHub({
+                        logFile,
+                        targetType: 'pr',
+                        targetNumber: prNumber,
+                        owner,
+                        repo,
+                        $,
+                        log,
+                        sanitizeLogContent,
+                        verbose: argv.verbose,
+                        errorMessage: `${argv.tool.toUpperCase()} execution failed after limit reset`,
+                        sessionId: latestSessionId,
+                        tempDir,
+                        requestedModel: argv.model,
+                        tool: argv.tool || 'claude',
+                      });
+                    }
+                  } catch (logUploadError) {
+                    reportError(logUploadError, {
+                      context: 'attach_auto_restart_failure_log',
+                      prNumber,
+                      owner,
+                      repo,
+                      operation: 'upload_failure_log',
+                    });
+                    await log(formatAligned('', `⚠️  Failure log upload error: ${cleanErrorMessage(logUploadError)}`, '', 2));
+                  }
+                }
                 return { success: false, reason: 'tool_failure_after_resume', latestSessionId, latestAnthropicCost };
               }
             } else {
@@ -755,6 +789,40 @@ Once the billing issue is resolved, you can re-run the CI checks or push a new c
           await log('');
           await log(formatAligned('❌', `${argv.tool.toUpperCase()} EXECUTION FAILED`, ''));
           await log(formatAligned('', 'Action:', 'Stopping auto-restart — tool execution failed', 2));
+          // Issue #1439: Attach failure log before stopping, so user can see what happened
+          const shouldAttachLogsOnFail = argv.attachLogs || argv['attach-logs'];
+          if (prNumber && shouldAttachLogsOnFail) {
+            try {
+              const logFile = getLogFile();
+              if (logFile) {
+                await attachLogToGitHub({
+                  logFile,
+                  targetType: 'pr',
+                  targetNumber: prNumber,
+                  owner,
+                  repo,
+                  $,
+                  log,
+                  sanitizeLogContent,
+                  verbose: argv.verbose,
+                  errorMessage: `${argv.tool.toUpperCase()} execution failed`,
+                  sessionId: latestSessionId,
+                  tempDir,
+                  requestedModel: argv.model,
+                  tool: argv.tool || 'claude',
+                });
+              }
+            } catch (logUploadError) {
+              reportError(logUploadError, {
+                context: 'attach_auto_restart_failure_log',
+                prNumber,
+                owner,
+                repo,
+                operation: 'upload_failure_log',
+              });
+              await log(formatAligned('', `⚠️  Failure log upload error: ${cleanErrorMessage(logUploadError)}`, '', 2));
+            }
+          }
           return { success: false, reason: 'tool_failure', latestSessionId, latestAnthropicCost };
         } else {
           // Success - capture latest session data