harness-everything 0.11.4 → 0.11.6

package/plugins/harness-everything/hooks/scripts/lib/workflow-runtime.js

@@ -43,6 +43,140 @@ function loadWorkflow(payload) {
 
 function saveWorkflow(context) { atomicWriteJson(context.file, context.workflow); }
 
+const MUTATION_PROBE_KEY = /^[a-f0-9]{64}$/;
+const MUTATION_PROBE_WAIT = new Int32Array(new SharedArrayBuffer(4));
+
+function mutationProbeDir(context) {
+  return path.join(context.sessionDir, 'mutation-probes');
+}
+
+function mutationProbeFile(context, key) {
+  if (!MUTATION_PROBE_KEY.test(String(key || ''))) throw new Error('invalid mutation probe identity');
+  return path.join(mutationProbeDir(context), key + '.json');
+}
+
+function withMutationProbeLock(context, callback) {
+  fs.mkdirSync(context.sessionDir, { recursive: true });
+  const lockDir = path.join(context.sessionDir, '.mutation-probes.lock');
+  let acquired = false;
+  for (let attempt = 0; attempt < 200; attempt++) {
+    try {
+      fs.mkdirSync(lockDir);
+      acquired = true;
+      break;
+    } catch (error) {
+      if (error.code !== 'EEXIST') throw error;
+      try {
+        const stat = fs.statSync(lockDir);
+        if (Date.now() - stat.mtimeMs > 30000) {
+          fs.rmSync(lockDir, { recursive: true, force: true });
+          continue;
+        }
+      } catch (_) { /* retry below */ }
+      Atomics.wait(MUTATION_PROBE_WAIT, 0, 0, 10);
+    }
+  }
+  if (!acquired) throw new Error('cannot acquire mutation probe lock');
+  try { return callback(); }
+  finally { fs.rmSync(lockDir, { recursive: true, force: true }); }
+}
+
+function mutationProbeReservations(context) {
+  const dir = mutationProbeDir(context);
+  let files = [];
+  try { files = fs.readdirSync(dir).filter(file => /^[a-f0-9]{64}\.json$/.test(file)); }
+  catch (_) { return 0; }
+  let count = 0;
+  for (const file of files) {
+    const probe = readJson(path.join(dir, file));
+    if (probe?.schemaVersion === 1 && probe.reserveIteration === true) count++;
+  }
+  return count;
+}
+
+function refreshWorkflowForProbe(context) {
+  const latest = readJson(context.file);
+  if (!latest || latest.sessionId !== context.sessionId) throw new Error('cannot refresh workflow for mutation probe');
+  context.workflow = latest;
+  return latest;
+}
+
+function assertIterationCapacity(context, evidence) {
+  const { workflow } = context;
+  if (!workflow) throw budgetError('no workflow available for iteration capacity');
+  const budget = ensureWorkflowBudget(workflow);
+  if (budget.state !== 'active') throw budgetError(`workflow budget is ${budget.state}: ${budget.reasonCode || 'unavailable'}`);
+  const limit = budget.limits.maxIterations;
+  if (limit === null) return { applicable: false, value: budget.counters.iterations, reserved: 0 };
+  const reserved = mutationProbeReservations(context);
+  if (budget.counters.iterations + reserved >= limit) {
+    return exhaustBudget(context, 'iteration-budget-exhausted', evidence || 'untrusted-shell-capacity');
+  }
+  return { applicable: true, value: budget.counters.iterations, reserved, limit };
+}
+
+function registerMutationProbe(context, key, fingerprint, reserveIteration) {
+  if (!MUTATION_PROBE_KEY.test(String(key || '')) || !MUTATION_PROBE_KEY.test(String(fingerprint || ''))) {
+    throw new Error('invalid mutation probe identity');
+  }
+  return withMutationProbeLock(context, () => {
+    refreshWorkflowForProbe(context);
+    if (reserveIteration) assertIterationCapacity(context, 'shell:untrusted');
+    const dir = mutationProbeDir(context);
+    fs.mkdirSync(dir, { recursive: true });
+    const file = mutationProbeFile(context, key);
+    if (fs.existsSync(file)) throw new Error('mutation probe is already pending for this tool call');
+    const probe = {
+      schemaVersion: 1,
+      fingerprint,
+      reserveIteration: Boolean(reserveIteration),
+      observedAt: Date.now(),
+    };
+    atomicWriteJson(file, probe);
+    return probe;
+  });
+}
+
+function peekMutationProbe(context, key) {
+  return readJson(mutationProbeFile(context, key));
+}
+
+function settleMutationProbe(context, key, afterFingerprint, tool) {
+  if (!MUTATION_PROBE_KEY.test(String(afterFingerprint || ''))) throw new Error('invalid mutation probe fingerprint');
+  return withMutationProbeLock(context, () => {
+    const file = mutationProbeFile(context, key);
+    const probe = readJson(file);
+    if (!probe || probe.schemaVersion !== 1) return null;
+    refreshWorkflowForProbe(context);
+    fs.unlinkSync(file);
+    const changed = afterFingerprint !== probe.fingerprint;
+    if (changed) {
+      context.workflow.lastMutationAt = Date.now();
+      if (probe.reserveIteration && context.workflow.strategy === 'iterative-single') {
+        recordBudgetEvent(context, 'iteration', { evidence: String(tool || 'shell') + ':observed-workspace-mutation' });
+      } else {
+        saveWorkflow(context);
+      }
+    }
+    return { changed, probe };
+  });
+}
+
+function discardMutationProbe(context, key) {
+  return withMutationProbeLock(context, () => {
+    const file = mutationProbeFile(context, key);
+    if (!fs.existsSync(file)) return false;
+    fs.unlinkSync(file);
+    return true;
+  });
+}
+
+function clearMutationProbes(context) {
+  return withMutationProbeLock(context, () => {
+    fs.rmSync(mutationProbeDir(context), { recursive: true, force: true });
+  });
+}
+
 function budgetLimits(workflow) {
   const limits = workflow?.workflowPlan?.limits || {};
   return {
@@ -123,7 +257,8 @@ function recordBudgetEvent(context, type, options = {}) {
   const consume = (counter, limitName, reasonCode) => {
     const limit = budget.limits[limitName];
     if (limit === null) return { applicable: false, value: budget.counters[counter] };
-    if (budget.counters[counter] >= limit) return exhaustBudget(context, reasonCode, evidence);
+    const reserved = type === 'iteration' ? mutationProbeReservations(context) : 0;
+    if (budget.counters[counter] + reserved >= limit) return exhaustBudget(context, reasonCode, evidence);
     budget.counters[counter]++;
     appendBudgetEvent(budget, { type, counter, value: budget.counters[counter], limit, evidence, observedAt: now });
     persistBudget(context);
@@ -175,6 +310,7 @@ function resetWorkflowBudget(context, evidence) {
     evidence: String(evidence).trim(),
     resetAt: now,
   }].slice(-16);
+  clearMutationProbes(context);
   workflow.budget = {
     schemaVersion: 1,
     epoch: previous.epoch + 1,
@@ -260,4 +396,4 @@ function readHookInput(decide) {
   process.stdin.on('error', finish);
 }
 
-module.exports = { OPEN_STATES, SAFE_ID, WORKFLOW_CONTROLLER_COMMANDS, isMajorWorkflow, loadWorkflow, saveWorkflow, budgetLimits, ensureWorkflowBudget, recordBudgetEvent, resetWorkflowBudget, syncBudgetToRun, matchingRun, unresolvedStages, readHookInput };
+module.exports = { OPEN_STATES, SAFE_ID, WORKFLOW_CONTROLLER_COMMANDS, isMajorWorkflow, loadWorkflow, saveWorkflow, budgetLimits, ensureWorkflowBudget, mutationProbeReservations, assertIterationCapacity, registerMutationProbe, peekMutationProbe, settleMutationProbe, discardMutationProbe, clearMutationProbes, recordBudgetEvent, resetWorkflowBudget, syncBudgetToRun, matchingRun, unresolvedStages, readHookInput };

package/plugins/harness-everything/hooks/scripts/state-persist.js

@@ -2,6 +2,8 @@
 const fs = require('fs');
 const path = require('path');
 const { getWorkspaceRoot, getSessionDir } = require('./lib/harness-state');
+const { loadWorkflow, saveWorkflow, peekMutationProbe, settleMutationProbe } = require('./lib/workflow-runtime');
+const { cwdOf, shellProbeKey, workspaceFingerprint } = require('./lib/workflow-isolation');
 const { observeTool } = require('./lib/telemetry');
 
 // Commands that count as "verification ran" for the Stop gate
@@ -28,7 +30,31 @@ process.stdin.on('end', () => {
   }
 });
 
+function observeWorkspaceMutation(payload, root) {
+  const toolName = payload && (payload.tool_name || payload.tool);
+  if (toolName !== 'Bash' && toolName !== 'PowerShell' && toolName !== 'exec_command') return false;
+  const context = loadWorkflow(payload);
+  if (!context.workflow || context.workflow.state === 'deferred') return false;
+  const cwd = cwdOf(payload, root);
+  const probeKey = shellProbeKey(payload, cwd);
+  if (!peekMutationProbe(context, probeKey)) return false;
+  let after;
+  try {
+    after = workspaceFingerprint(cwd);
+  } catch (error) {
+    context.workflow.state = 'blocked';
+    context.workflow.blockReason = 'mutation-observation-failed';
+    saveWorkflow(context);
+    const critical = new Error('cannot verify whether shell execution changed workspace content');
+    critical.code = 'HARNESS_MUTATION_OBSERVATION';
+    throw critical;
+  }
+  const result = settleMutationProbe(context, probeKey, after, toolName);
+  return Boolean(result && result.changed);
+}
+
 function processState(payload) {
+  let exitCodeForHook = 0;
   try {
     const sessionId = payload && (payload.session_id || payload.sessionId);
     const root = getWorkspaceRoot(payload);
@@ -48,12 +74,16 @@ function processState(payload) {
       // it's actually a number; fall back to a stderr signal otherwise.
       const toolResponse = payload.tool_response || {};
       const stdout = toolResponse.stdout ?? payload.stdout ?? '';
-      const stderr = toolResponse.stderr ?? payload.stderr ?? '';
+      const stderr = toolResponse.stderr ?? payload.stderr ?? payload.error ?? '';
       const rawExitCode = toolResponse.exitCode ?? toolResponse.exit_code ?? payload.exitCode;
       const exitCode = typeof rawExitCode === 'number' ? rawExitCode : undefined;
       const stderrSignal = typeof stderr === 'string' && stderr.trim().length > 0;
-      const isFailed = (exitCode !== undefined && exitCode !== 0) || (exitCode === undefined && stderrSignal);
+      const hookEvent = payload.hook_event_name || payload.hookEventName || '';
+      const isFailed = hookEvent === 'PostToolUseFailure' ||
+        (exitCode !== undefined && exitCode !== 0) ||
+        (exitCode === undefined && stderrSignal);
       const toolName = payload.tool_name || payload.tool || 'command';
+      const observedMutation = observeWorkspaceMutation(payload, root);
 
       if (isFailed) {
         // Truncate output to avoid state bloat
@@ -78,9 +108,10 @@ function processState(payload) {
 
       // Milestones for the Stop gate: when did the last mutation happen, and
       // has any verification-ish command succeeded since.
-      if (toolName === 'Edit' || toolName === 'Write' || toolName === 'apply_patch') {
+      if (toolName === 'Edit' || toolName === 'Write' || toolName === 'apply_patch' || observedMutation) {
         state.lastEditAt = Date.now();
-      } else if ((toolName === 'Bash' || toolName === 'PowerShell') && !isFailed) {
+      }
+      if ((toolName === 'Bash' || toolName === 'PowerShell') && !isFailed) {
         const command = (payload.tool_input && payload.tool_input.command) || '';
         if (VERIFY_COMMAND_RE.test(command)) {
           state.lastVerifyAt = Date.now();
@@ -100,7 +131,11 @@ function processState(payload) {
       }
     }
   } catch (err) {
-    // Fail silently in hooks
+    if (err && (err.code === 'HARNESS_MUTATION_OBSERVATION' || err.code === 'HARNESS_WORKFLOW_BUDGET')) {
+      console.error('[State Persist] ' + err.message);
+      exitCodeForHook = 2;
+    }
+    // Non-critical persistence/telemetry failures remain fail-open.
   }
-  process.exit(0);
+  process.exit(exitCodeForHook);
 }

package/plugins/harness-everything/hooks/scripts/workflow-gate.js

@@ -3,8 +3,8 @@
 
 const path = require('path');
 const fs = require('fs');
-const { loadWorkflow, saveWorkflow, isMajorWorkflow, matchingRun, recordBudgetEvent, readHookInput, WORKFLOW_CONTROLLER_COMMANDS } = require('./lib/workflow-runtime');
-const { key, classifyShell, cwdOf, commandOf, mutationPaths, linkedWorktree, assertTargets, assertShellScope } = require('./lib/workflow-isolation');
+const { loadWorkflow, saveWorkflow, isMajorWorkflow, matchingRun, registerMutationProbe, recordBudgetEvent, readHookInput, WORKFLOW_CONTROLLER_COMMANDS } = require('./lib/workflow-runtime');
+const { key, classifyShell, workspaceFingerprint, shellProbeKey, cwdOf, commandOf, mutationPaths, linkedWorktree, assertTargets, assertShellScope } = require('./lib/workflow-isolation');
 
 const DIRECT = new Set(['Edit', 'Write', 'apply_patch']);
 const SHELL = new Set(['Bash', 'PowerShell', 'exec_command']);
@@ -27,8 +27,8 @@ function decide(payload) {
   const cwd = cwdOf(payload, root);
   const command = commandOf(payload);
   const commandClass = SHELL.has(tool) ? classifyShell(command) : 'direct-mutation';
-  if (commandClass === 'read-only' || commandClass === 'worktree-setup') return;
   if (SHELL.has(tool) && isController(command, cwd)) return;
+  if (commandClass === 'read-only' || commandClass === 'worktree-setup') return;
   // Only the stage specification is allowed before run entry. Other runtime
   // state, including workflow-run.json, cannot use this bootstrap exception.
   const targets = DIRECT.has(tool) ? mutationPaths(payload) : [];
@@ -47,11 +47,22 @@ function decide(payload) {
   if (String(workflow.strategy || '').startsWith('fable-') && !matchingRun(context)) {
     throw new Error('selected Fable workflow has no correlated run. Write workflow-stages.json at the displayed session path, then use workflow-disposition.js start.');
   }
-  if (workflow.strategy === 'iterative-single') {
-    recordBudgetEvent(context, 'iteration', { evidence: `${tool}:${commandClass}` });
+  if (DIRECT.has(tool)) {
+    if (workflow.strategy === 'iterative-single') {
+      recordBudgetEvent(context, 'iteration', { evidence: `${tool}:direct-mutation` });
+    }
+    workflow.lastMutationAt = Date.now();
+    saveWorkflow(context);
+    return;
   }
-  workflow.lastMutationAt = Date.now();
-  saveWorkflow(context);
+
+  // Shell safety and shell mutation accounting are intentionally separate.
+  // `untrusted` means "not proven read-only", not "a mutation occurred".
+  // Capture an opaque pre-execution workspace fingerprint; the post-tool
+  // observer consumes an iteration only when workspace content actually changed.
+  const fingerprint = workspaceFingerprint(cwd);
+  const probeKey = shellProbeKey(payload, cwd);
+  registerMutationProbe(context, probeKey, fingerprint, workflow.strategy === 'iterative-single');
 }
 
 readHookInput(decide);

package/plugins/harness-everything/hooks/scripts/workflow-mutation-denied.js

@@ -0,0 +1,17 @@
+#!/usr/bin/env node
+'use strict';
+
+const { loadWorkflow, discardMutationProbe, readHookInput } = require('./lib/workflow-runtime');
+const { cwdOf, shellProbeKey } = require('./lib/workflow-isolation');
+
+function discardDenied(payload) {
+  if (!payload) return;
+  const tool = payload.tool_name || payload.tool;
+  if (tool !== 'Bash' && tool !== 'PowerShell' && tool !== 'exec_command') return;
+  const context = loadWorkflow(payload);
+  if (!context.workflow || context.workflow.state === 'deferred') return;
+  const cwd = cwdOf(payload, context.root);
+  discardMutationProbe(context, shellProbeKey(payload, cwd));
+}
+
+readHookInput(discardDenied);

package/plugins/harness-everything/plugin.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
   "name": "harness-everything",
-  "version": "0.11.4",
+  "version": "0.11.6",
   "description": "Invariant-first engineering harness for routing, verification, and failure recovery while preserving agent autonomy.",
   "author": {
     "name": "Miya Daniel",