@link-assistant/hive-mind 0.53.0 → 0.53.2

package/CHANGELOG.md

@@ -1,5 +1,28 @@
 # @link-assistant/hive-mind
 
+## 0.53.2
+
+### Patch Changes
+
+- 5030fe1: Fix --auto-continue-on-limit-reset flag not working
+
+  When Claude hit its usage limit with --auto-continue-on-limit-reset enabled, the code would exit early
+  via the failure branch before reaching showSessionSummary() where autoContinueWhenLimitResets() is called.
+
+  This patch adds a condition to skip the failure exit when limit is reached with auto-continue enabled,
+  allowing the code to properly wait for the limit to reset and resume the session.
+
+## 0.53.1
+
+### Patch Changes
+
+- 6d7fb43: Add --auto-continue-on-limit-reset option to hive command
+
+  The hive command was missing the --auto-continue-on-limit-reset option that is available
+  in the solve command. This caused yargs strict mode to reject the option with an
+  "Unknown arguments" error. The option is now properly defined in hive.config.lib.mjs
+  and passed to the solve command when spawning workers.
+
 ## 0.53.0
 
 ### Minor Changes

package/README.md

@@ -15,6 +15,33 @@ It is also possible to connect this AI to collective human intelligence, meaning
 
 Inspired by [konard/problem-solving](https://github.com/konard/problem-solving)
 
+## Why Hive Mind?
+
+**Hive Mind is the most autonomous, cloud-ready AI issue solver that eliminates developer babysitting while maintaining human oversight on critical decisions.**
+
+Hive Mind is a **generalist AI** (mini-AGI) capable of working on a wide range of tasks - not just programming. Almost anything that can be done with files in a repository can be automated.
+
+| Feature                      | What It Means For You                                                                              |
+| ---------------------------- | -------------------------------------------------------------------------------------------------- |
+| **No Babysitting**           | Full autonomous mode with sudo access. AI has creative freedom like a real programmer.             |
+| **Cloud Isolation**          | Runs on dedicated VMs or Docker. Easy to restore if broken.                                        |
+| **Full Internet + Sudo**     | AI can install packages, fetch docs, and configure the system as needed.                           |
+| **Pre-installed Toolchain**  | 25GB+ ready: 10 language runtimes, 2 theorem provers, build tools. Can install more.               |
+| **Token Efficiency**         | Routine tasks automated in code, so AI tokens focus on creative problem-solving.                   |
+| **Time Freedom**             | What takes humans 2-8 hours, AI completes in 10-25 minutes. "The code is written while you sleep." |
+| **Scale with Orchestration** | Parallel workers feel like a team of developers, all for ~$200/month.                              |
+| **Human Control**            | AI creates draft PRs - you decide what merges. Quality gates where they matter.                    |
+| **Any Device Programming**   | Manage AI from any device with `/solve` and `/hive`. No PC, IDE, or laptop required.               |
+| **100% Open Source**         | Unlicense (public domain). Full transparency, no vendor lock-in.                                   |
+
+> _"Compared to Codex for $200, this solution is fire."_ - User feedback
+
+**Cost**: Claude MAX subscription (~$200/month, currently 50% off = $400 value) provides almost unlimited usage for Hive Mind - the best value/quality balance on the market.
+
+Hive Mind has high creativity indistinguishable from average programmers. It asks questions if requirements are unclear, and you can clarify on the go via PR comments.
+
+For detailed features and comparisons, see [docs/FEATURES.md](./docs/FEATURES.md) and [docs/COMPARISON.md](./docs/COMPARISON.md).
+
 ## ⚠️ WARNING
 
 It is UNSAFE to run this software on your developer machine.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@link-assistant/hive-mind",
-  "version": "0.53.0",
+  "version": "0.53.2",
   "description": "AI-powered issue solver and hive mind for collaborative problem solving",
   "main": "src/hive.mjs",
   "type": "module",

package/src/hive.config.lib.mjs

@@ -202,6 +202,11 @@ export const createYargsConfig = yargsInstance => {
       description: 'Pass --auto-continue to solve for each issue (continues with existing PRs instead of creating new ones)',
       default: true,
     })
+    .option('auto-continue-on-limit-reset', {
+      type: 'boolean',
+      description: 'Automatically continue when AI tool limit resets (calculates reset time and waits). Passed to solve command.',
+      default: false,
+    })
     .option('think', {
       type: 'string',
       description: 'Thinking level: low (Think.), medium (Think hard.), high (Think harder.), max (Ultrathink.)',

package/src/hive.mjs

@@ -731,70 +731,24 @@ if (isDirectExecution) {
             }
 
             const startTime = Date.now();
-            const forkFlag = argv.fork ? ' --fork' : '';
-            const autoForkFlag = argv.autoFork ? ' --auto-fork' : '';
-            const verboseFlag = argv.verbose ? ' --verbose' : '';
-            const attachLogsFlag = argv.attachLogs ? ' --attach-logs' : '';
-            const targetBranchFlag = argv.targetBranch ? ` --target-branch ${argv.targetBranch}` : '';
-            const logDirFlag = argv.logDir ? ` --log-dir "${argv.logDir}"` : '';
-            const dryRunFlag = argv.dryRun ? ' --dry-run' : '';
-            const skipToolConnectionCheckFlag = argv.skipToolConnectionCheck || argv.toolConnectionCheck === false ? ' --skip-tool-connection-check' : '';
-            const toolFlag = argv.tool ? ` --tool ${argv.tool}` : '';
-            const autoContinueFlag = argv.autoContinue ? ' --auto-continue' : ' --no-auto-continue';
-            const thinkFlag = argv.think ? ` --think ${argv.think}` : '';
-            const promptPlanSubAgentFlag = argv.promptPlanSubAgent ? ' --prompt-plan-sub-agent' : '';
-            const noSentryFlag = !argv.sentry ? ' --no-sentry' : '';
-            const watchFlag = argv.watch ? ' --watch' : '';
-            const prefixForkNameWithOwnerNameFlag = argv.prefixForkNameWithOwnerName ? ' --prefix-fork-name-with-owner-name' : '';
-            const interactiveModeFlag = argv.interactiveMode ? ' --interactive-mode' : '';
-            const promptExploreSubAgentFlag = argv.promptExploreSubAgent ? ' --prompt-explore-sub-agent' : '';
-            const promptIssueReportingFlag = argv.promptIssueReporting ? ' --prompt-issue-reporting' : '';
-            const promptCaseStudiesFlag = argv.promptCaseStudies ? ' --prompt-case-studies' : '';
-            const promptPlaywrightMcpFlag = argv.promptPlaywrightMcp === true ? ' --prompt-playwright-mcp' : argv.promptPlaywrightMcp === false ? ' --no-prompt-playwright-mcp' : '';
             // Use spawn to get real-time streaming output while avoiding command-stream's automatic quote addition
             const { spawn } = await import('child_process');
-
             // Build arguments array to avoid shell parsing issues
             const args = [issueUrl, '--model', argv.model];
-            if (argv.tool) {
-              args.push('--tool', argv.tool);
-            }
-            if (argv.fork) {
-              args.push('--fork');
-            }
-            if (argv.autoFork) {
-              args.push('--auto-fork');
-            }
-            if (argv.verbose) {
-              args.push('--verbose');
-            }
-            if (argv.attachLogs) {
-              args.push('--attach-logs');
-            }
-            if (argv.targetBranch) {
-              args.push('--target-branch', argv.targetBranch);
-            }
-            if (argv.logDir) {
-              args.push('--log-dir', argv.logDir);
-            }
-            if (argv.dryRun) {
-              args.push('--dry-run');
-            }
-            if (argv.skipToolConnectionCheck || argv.toolConnectionCheck === false) {
-              args.push('--skip-tool-connection-check');
-            }
-            if (argv.autoContinue) {
-              args.push('--auto-continue');
-            } else {
-              args.push('--no-auto-continue');
-            }
-            if (argv.think) {
-              args.push('--think', argv.think);
-            }
+            if (argv.tool) args.push('--tool', argv.tool);
+            if (argv.fork) args.push('--fork');
+            if (argv.autoFork) args.push('--auto-fork');
+            if (argv.verbose) args.push('--verbose');
+            if (argv.attachLogs) args.push('--attach-logs');
+            if (argv.targetBranch) args.push('--target-branch', argv.targetBranch);
+            if (argv.logDir) args.push('--log-dir', argv.logDir);
+            if (argv.dryRun) args.push('--dry-run');
+            if (argv.skipToolConnectionCheck || argv.toolConnectionCheck === false) args.push('--skip-tool-connection-check');
+            args.push(argv.autoContinue ? '--auto-continue' : '--no-auto-continue');
+            if (argv.autoContinueOnLimitReset) args.push('--auto-continue-on-limit-reset');
+            if (argv.think) args.push('--think', argv.think);
             if (argv.promptPlanSubAgent) args.push('--prompt-plan-sub-agent');
-            if (!argv.sentry) {
-              args.push('--no-sentry');
-            }
+            if (!argv.sentry) args.push('--no-sentry');
             if (argv.watch) args.push('--watch');
             if (argv.prefixForkNameWithOwnerName) args.push('--prefix-fork-name-with-owner-name');
             if (argv.interactiveMode) args.push('--interactive-mode');
@@ -803,8 +757,7 @@ if (isDirectExecution) {
             if (argv.promptCaseStudies) args.push('--prompt-case-studies');
             if (argv.promptPlaywrightMcp !== undefined) args.push(argv.promptPlaywrightMcp ? '--prompt-playwright-mcp' : '--no-prompt-playwright-mcp');
             // Log the actual command being executed so users can investigate/reproduce
-            const command = `${solveCommand} "${issueUrl}" --model ${argv.model}${toolFlag}${forkFlag}${autoForkFlag}${verboseFlag}${attachLogsFlag}${targetBranchFlag}${logDirFlag}${dryRunFlag}${skipToolConnectionCheckFlag}${autoContinueFlag}${thinkFlag}${promptPlanSubAgentFlag}${noSentryFlag}${watchFlag}${prefixForkNameWithOwnerNameFlag}${interactiveModeFlag}${promptExploreSubAgentFlag}${promptIssueReportingFlag}${promptCaseStudiesFlag}${promptPlaywrightMcpFlag}`;
-            await log(`   📋 Command: ${command}`);
+            await log(`   📋 Command: ${solveCommand} ${args.join(' ')}`);
 
             let exitCode = 0;
             // Create promise to handle async spawn process

package/src/solve.mjs

@@ -1035,7 +1035,11 @@ try {
     }
   }
 
-  if (!success) {
+  // Handle failure cases, but skip exit if limit reached with auto-continue enabled
+  // This allows the code to continue to showSessionSummary() where autoContinueWhenLimitResets() is called
+  const shouldSkipFailureExitForAutoLimitContinue = limitReached && argv.autoContinueOnLimitReset;
+
+  if (!success && !shouldSkipFailureExitForAutoLimitContinue) {
     // Show claude resume command only for --tool claude (or default) on failure
     // Uses the (cd ... && claude --resume ...) pattern for a fully copyable, executable command
     const toolForFailure = argv.tool || 'claude';