gsd-pi 2.17.0 → 2.19.0

package/src/resources/extensions/gsd/auto.ts

@@ -19,6 +19,7 @@ import type {
 import { deriveState, invalidateStateCache } from "./state.js";
 import type { BudgetEnforcementMode, GSDState } from "./types.js";
 import { loadFile, parseRoadmap, getManifestStatus, resolveAllOverrides } from "./files.js";
+import { loadPrompt } from "./prompt-loader.js";
 export { inlinePriorMilestoneSummary } from "./files.js";
 import { collectSecretsFromManifest } from "../get-secrets-from-user.js";
 import {
@@ -29,7 +30,7 @@ import {
   buildMilestoneFileName, buildSliceFileName, buildTaskFileName,
 } from "./paths.js";
 import { invalidateAllCaches } from "./cache.js";
-import { saveActivityLog } from "./activity-log.js";
+import { saveActivityLog, clearActivityLogState } from "./activity-log.js";
 import { synthesizeCrashRecovery, getDeepDiagnostic } from "./session-forensics.js";
 import { writeLock, clearLock, readCrashLock, formatCrashInfo, isLockProcessAlive } from "./crash-recovery.js";
 import {
@@ -39,9 +40,12 @@ import {
   readUnitRuntimeRecord,
   writeUnitRuntimeRecord,
 } from "./unit-runtime.js";
-import { resolveAutoSupervisorConfig, resolveModelWithFallbacksForUnit, loadEffectiveGSDPreferences, resolveSkillDiscoveryMode } from "./preferences.js";
+import { resolveAutoSupervisorConfig, resolveModelWithFallbacksForUnit, loadEffectiveGSDPreferences, resolveSkillDiscoveryMode, resolveDynamicRoutingConfig } from "./preferences.js";
 import { sendDesktopNotification } from "./notifications.js";
 import type { GSDPreferences } from "./preferences.js";
+import { classifyUnitComplexity, tierLabel } from "./complexity-classifier.js";
+import { resolveModelForComplexity } from "./model-router.js";
+import { initRoutingHistory, resetRoutingHistory, recordOutcome } from "./routing-history.js";
 import {
   checkPostUnitHooks,
   getActiveHook,
@@ -92,7 +96,9 @@ import {
   getAutoWorktreePath,
   getAutoWorktreeOriginalBase,
   mergeMilestoneToMain,
+  autoWorktreeBranch,
 } from "./auto-worktree.js";
+import { pruneQueueOrder } from "./queue-order.js";
 import { showNextAction } from "../shared/next-action-ui.js";
 import {
   resolveExpectedArtifactPath,
@@ -127,6 +133,7 @@ import {
   deregisterSigtermHandler as _deregisterSigtermHandler,
   detectWorkingTreeActivity,
 } from "./auto-supervisor.js";
+import { hasPendingCaptures, loadPendingCaptures, countPendingCaptures } from "./captures.js";
 
 // ─── State ────────────────────────────────────────────────────────────────────
 
@@ -196,6 +203,33 @@ function shouldUseWorktreeIsolation(): boolean {
   return true; // default: worktree
 }
 
+/**
+ * Detect and escape a stale worktree cwd (#608).
+ *
+ * After milestone completion + merge, the worktree directory is removed but
+ * the process cwd may still point inside `.gsd/worktrees/<MID>/`.
+ * When a new session starts, `process.cwd()` is passed as `base` to startAuto
+ * and all subsequent writes land in the wrong directory. This function detects
+ * that scenario and chdir back to the project root.
+ *
+ * Returns the corrected base path.
+ */
+function escapeStaleWorktree(base: string): string {
+  const marker = `${pathSep}.gsd${pathSep}worktrees${pathSep}`;
+  const idx = base.indexOf(marker);
+  if (idx === -1) return base;
+
+  // base is inside .gsd/worktrees/<something> — extract the project root
+  const projectRoot = base.slice(0, idx);
+  try {
+    process.chdir(projectRoot);
+  } catch {
+    // If chdir fails, return the original — caller will handle errors downstream
+    return base;
+  }
+  return projectRoot;
+}
+
 /** Crash recovery prompt — set by startAuto, consumed by first dispatchNextUnit */
 let pendingCrashRecovery: string | null = null;
 
@@ -204,6 +238,9 @@ let autoStartTime: number = 0;
 let completedUnits: { type: string; id: string; startedAt: number; finishedAt: number }[] = [];
 let currentUnit: { type: string; id: string; startedAt: number } | null = null;
 
+/** Track dynamic routing decision for the current unit (for metrics) */
+let currentUnitRouting: { tier: string; modelDowngraded: boolean } | null = null;
+
 /** Track current milestone to detect transitions */
 let currentMilestoneId: string | null = null;
 let lastBudgetAlertLevel: BudgetAlertLevel = 0;
@@ -228,6 +265,9 @@ const DISPATCH_GAP_TIMEOUT_MS = 5_000; // 5 seconds
 /** SIGTERM handler registered while auto-mode is active — cleared on stop/pause. */
 let _sigtermHandler: (() => void) | null = null;
 
+/** Tool calls currently being executed — prevents false idle detection during long-running tools. */
+const inFlightTools = new Set<string>();
+
 type BudgetAlertLevel = 0 | 75 | 90 | 100;
 
 export function getBudgetAlertLevel(budgetPct: number): BudgetAlertLevel {
@@ -269,6 +309,15 @@ export { type AutoDashboardData } from "./auto-dashboard.js";
 export function getAutoDashboardData(): AutoDashboardData {
   const ledger = getLedger();
   const totals = ledger ? getProjectTotals(ledger.units) : null;
+  // Pending capture count — lazy check, non-fatal
+  let pendingCaptureCount = 0;
+  try {
+    if (basePath) {
+      pendingCaptureCount = countPendingCaptures(basePath);
+    }
+  } catch {
+    // Non-fatal — captures module may not be loaded
+  }
   return {
     active,
     paused,
@@ -280,6 +329,7 @@ export function getAutoDashboardData(): AutoDashboardData {
     basePath,
     totalCost: totals?.cost ?? 0,
     totalTokens: totals?.tokens.total ?? 0,
+    pendingCaptureCount,
   };
 }
 
@@ -293,6 +343,22 @@ export function isAutoPaused(): boolean {
   return paused;
 }
 
+/**
+ * Mark a tool execution as in-flight. Called from index.ts on tool_execution_start.
+ * Prevents the idle watchdog from declaring the agent idle while tools are executing.
+ */
+export function markToolStart(toolCallId: string): void {
+  if (!active) return;
+  inFlightTools.add(toolCallId);
+}
+
+/**
+ * Mark a tool execution as completed. Called from index.ts on tool_execution_end.
+ */
+export function markToolEnd(toolCallId: string): void {
+  inFlightTools.delete(toolCallId);
+}
+
 /**
  * Return the base path to use for the auto.lock file.
  * Always uses the original project root (not the worktree) so that
@@ -345,6 +411,7 @@ function clearUnitTimeout(): void {
     clearInterval(idleWatchdogHandle);
     idleWatchdogHandle = null;
   }
+  inFlightTools.clear();
   clearDispatchGapWatchdog();
 }
 
@@ -426,14 +493,18 @@ export async function stopAuto(ctx?: ExtensionContext, pi?: ExtensionAPI): Promi
         `Auto-worktree teardown failed: ${err instanceof Error ? err.message : String(err)}`,
         "warning",
       );
-      // Force basePath back to original even if teardown failed
-      if (originalBasePath) {
-        basePath = originalBasePath;
-        try { process.chdir(basePath); } catch { /* best-effort */ }
-      }
     }
   }
 
+  // Always restore cwd to project root on stop (#608).
+  // Even if isInAutoWorktree returned false (e.g., module state was already
+  // cleared by mergeMilestoneToMain), the process cwd may still be inside
+  // the worktree directory. Force it back to originalBasePath.
+  if (originalBasePath) {
+    basePath = originalBasePath;
+    try { process.chdir(basePath); } catch { /* best-effort */ }
+  }
+
   const ledger = getLedger();
   if (ledger && ledger.units.length > 0) {
     const totals = getProjectTotals(ledger.units);
@@ -451,6 +522,7 @@ export async function stopAuto(ctx?: ExtensionContext, pi?: ExtensionAPI): Promi
   }
 
   resetMetrics();
+  resetRoutingHistory();
   resetHookState();
   if (basePath) clearPersistedHookState(basePath);
   active = false;
@@ -458,12 +530,15 @@ export async function stopAuto(ctx?: ExtensionContext, pi?: ExtensionAPI): Promi
   stepMode = false;
   unitDispatchCount.clear();
   unitRecoveryCount.clear();
+  inFlightTools.clear();
   lastBudgetAlertLevel = 0;
   unitLifetimeDispatches.clear();
   currentUnit = null;
   currentMilestoneId = null;
   originalBasePath = "";
+  completedUnits = [];
   clearSliceProgressCache();
+  clearActivityLogState();
   pendingCrashRecovery = null;
   _handlingAgentEnd = false;
   ctx?.ui.setStatus("gsd-auto", undefined);
@@ -519,6 +594,11 @@ export async function startAuto(
 ): Promise<void> {
   const requestedStepMode = options?.step ?? false;
 
+  // Escape stale worktree cwd from a previous milestone (#608).
+  // After milestone merge + worktree removal, the process cwd may still point
+  // inside .gsd/worktrees/<MID>/ — detect and chdir back to project root.
+  base = escapeStaleWorktree(base);
+
   // If resuming from paused state, just re-activate and dispatch next unit.
   // The conversation is still intact — no need to reinitialize everything.
   if (paused) {
@@ -569,17 +649,17 @@ export async function startAuto(
     ctx.ui.setFooter(hideFooter);
     ctx.ui.notify(stepMode ? "Step-mode resumed." : "Auto-mode resumed.", "info");
     // Restore hook state from disk in case session was interrupted
-    restoreHookState(base);
+    restoreHookState(basePath);
     // Rebuild disk state before resuming — user interaction during pause may have changed files
-    try { await rebuildState(base); } catch { /* non-fatal */ }
+    try { await rebuildState(basePath); } catch { /* non-fatal */ }
     try {
-      const report = await runGSDDoctor(base, { fix: true });
+      const report = await runGSDDoctor(basePath, { fix: true });
       if (report.fixesApplied.length > 0) {
         ctx.ui.notify(`Resume: applied ${report.fixesApplied.length} fix(es) to state.`, "info");
       }
     } catch { /* non-fatal */ }
     // Self-heal: clear stale runtime records where artifacts already exist
-    await selfHealRuntimeRecords(base, ctx, completedKeySet);
+    await selfHealRuntimeRecords(basePath, ctx, completedKeySet);
     invalidateAllCaches();
     await dispatchNextUnit(ctx, pi);
     return;
@@ -748,6 +828,9 @@ export async function startAuto(
   // Initialize metrics — loads existing ledger from disk
   initMetrics(base);
 
+  // Initialize routing history for adaptive learning
+  initRoutingHistory(base);
+
   // Snapshot installed skills so we can detect new ones after research
   if (resolveSkillDiscoveryMode() !== "off") {
     snapshotSkills();
@@ -950,7 +1033,7 @@ export async function handleAgentEnd(
       const hookStartedAt = Date.now();
       if (currentUnit) {
         const modelId = ctx.model?.id ?? "unknown";
-        snapshotUnitMetrics(ctx, currentUnit.type, currentUnit.id, currentUnit.startedAt, modelId);
+        snapshotUnitMetrics(ctx, currentUnit.type, currentUnit.id, currentUnit.startedAt, modelId, currentUnitRouting ?? undefined);
         saveActivityLog(ctx, basePath, currentUnit.type, currentUnit.id);
       }
       currentUnit = { type: hookUnit.unitType, id: hookUnit.unitId, startedAt: hookStartedAt };
@@ -1045,6 +1128,108 @@ export async function handleAgentEnd(
     }
   }
 
+  // ── Triage check: dispatch triage unit if pending captures exist ──────────
+  // Fires after hooks complete, before normal dispatch. Follows the same
+  // early-dispatch-and-return pattern as hooks and fix-merge.
+  // Skip for: step mode (shows wizard instead), triage units (prevent triage-on-triage),
+  // hook units (hooks run before triage conceptually).
+  if (
+    !stepMode &&
+    currentUnit &&
+    !currentUnit.type.startsWith("hook/") &&
+    currentUnit.type !== "triage-captures" &&
+    currentUnit.type !== "quick-task"
+  ) {
+    try {
+      if (hasPendingCaptures(basePath)) {
+        const pending = loadPendingCaptures(basePath);
+        if (pending.length > 0) {
+          const state = await deriveState(basePath);
+          const mid = state.activeMilestone?.id;
+          const sid = state.activeSlice?.id;
+
+          if (mid && sid) {
+            // Build triage prompt with current context
+            let currentPlan = "";
+            let roadmapContext = "";
+            const planFile = resolveSliceFile(basePath, mid, sid, "PLAN");
+            if (planFile) currentPlan = (await loadFile(planFile)) ?? "";
+            const roadmapFile = resolveMilestoneFile(basePath, mid, "ROADMAP");
+            if (roadmapFile) roadmapContext = (await loadFile(roadmapFile)) ?? "";
+
+            const capturesList = pending.map(c =>
+              `- **${c.id}**: "${c.text}" (captured: ${c.timestamp})`
+            ).join("\n");
+
+            const prompt = loadPrompt("triage-captures", {
+              pendingCaptures: capturesList,
+              currentPlan: currentPlan || "(no active slice plan)",
+              roadmapContext: roadmapContext || "(no active roadmap)",
+            });
+
+            ctx.ui.notify(
+              `Triaging ${pending.length} pending capture${pending.length === 1 ? "" : "s"}...`,
+              "info",
+            );
+
+            // Close out previous unit metrics
+            if (currentUnit) {
+              const modelId = ctx.model?.id ?? "unknown";
+              snapshotUnitMetrics(ctx, currentUnit.type, currentUnit.id, currentUnit.startedAt, modelId);
+              saveActivityLog(ctx, basePath, currentUnit.type, currentUnit.id);
+            }
+
+            // Dispatch triage as a new unit (early-dispatch-and-return)
+            const triageUnitType = "triage-captures";
+            const triageUnitId = `${mid}/${sid}/triage`;
+            const triageStartedAt = Date.now();
+            currentUnit = { type: triageUnitType, id: triageUnitId, startedAt: triageStartedAt };
+            writeUnitRuntimeRecord(basePath, triageUnitType, triageUnitId, triageStartedAt, {
+              phase: "dispatched",
+              wrapupWarningSent: false,
+              timeoutAt: null,
+              lastProgressAt: triageStartedAt,
+              progressCount: 0,
+              lastProgressKind: "dispatch",
+            });
+            updateProgressWidget(ctx, triageUnitType, triageUnitId, state);
+
+            const result = await cmdCtx!.newSession();
+            if (result.cancelled) {
+              await stopAuto(ctx, pi);
+              return;
+            }
+            const sessionFile = ctx.sessionManager.getSessionFile();
+            writeLock(basePath, triageUnitType, triageUnitId, completedUnits.length, sessionFile);
+
+            // Start unit timeout for triage (use same supervisor config as hooks)
+            clearUnitTimeout();
+            const supervisor = resolveAutoSupervisorConfig();
+            const triageTimeoutMs = (supervisor.hard_timeout_minutes ?? 30) * 60 * 1000;
+            unitTimeoutHandle = setTimeout(async () => {
+              unitTimeoutHandle = null;
+              if (!active) return;
+              ctx.ui.notify(
+                `Triage unit exceeded timeout. Pausing auto-mode.`,
+                "warning",
+              );
+              await pauseAuto(ctx, pi);
+            }, triageTimeoutMs);
+
+            if (!active) return;
+            pi.sendMessage(
+              { customType: "gsd-auto", content: prompt, display: verbose },
+              { triggerTurn: true },
+            );
+            return; // handleAgentEnd will fire again when triage session completes
+          }
+        }
+      }
+    } catch {
+      // Triage check failure is non-fatal — proceed to normal dispatch
+    }
+  }
+
   // In step mode, pause and show a wizard instead of immediately dispatching
   if (stepMode) {
     await showStepWizard(ctx, pi);
@@ -1166,7 +1351,10 @@ function updateProgressWidget(
   unitId: string,
   state: GSDState,
 ): void {
-  _updateProgressWidget(ctx, unitType, unitId, state, widgetStateAccessors);
+  const badge = currentUnitRouting?.tier
+    ? ({ light: "L", standard: "S", heavy: "H" }[currentUnitRouting.tier] ?? undefined)
+    : undefined;
+  _updateProgressWidget(ctx, unitType, unitId, state, widgetStateAccessors, badge);
 }
 
 /** State accessors for the widget — closures over module globals. */
@@ -1245,12 +1433,90 @@ async function dispatchNextUnit(
       "info",
     );
     sendDesktopNotification("GSD", `Milestone ${currentMilestoneId} complete!`, "success", "milestone");
+    // Hint: visualizer available after milestone transition
+    const vizPrefs = loadEffectiveGSDPreferences()?.preferences;
+    if (vizPrefs?.auto_visualize) {
+      ctx.ui.notify("Run /gsd visualize to see progress overview.", "info");
+    }
     // Reset stuck detection for new milestone
     unitDispatchCount.clear();
     unitRecoveryCount.clear();
     unitLifetimeDispatches.clear();
-    // Capture integration branch for the new milestone and update git service
-    captureIntegrationBranch(originalBasePath || basePath, mid, { commitDocs: loadEffectiveGSDPreferences()?.preferences?.git?.commit_docs });
+    // Clear completed-units.json for the finished milestone
+    try {
+      const file = completedKeysPath(basePath);
+      if (existsSync(file)) writeFileSync(file, JSON.stringify([]), "utf-8");
+      completedKeySet.clear();
+    } catch { /* non-fatal */ }
+
+    // ── Worktree lifecycle on milestone transition (#616) ──────────────
+    // When transitioning from M_old to M_new inside a worktree, we must:
+    // 1. Merge the completed milestone's worktree back to main
+    // 2. Re-derive state from the project root
+    // 3. Create a new worktree for the incoming milestone
+    // Without this, M_new runs inside M_old's worktree on the wrong branch,
+    // and artifact paths resolve against the wrong .gsd/ directory.
+    if (isInAutoWorktree(basePath) && originalBasePath && shouldUseWorktreeIsolation()) {
+      try {
+        const roadmapPath = resolveMilestoneFile(originalBasePath, currentMilestoneId, "ROADMAP");
+        if (roadmapPath) {
+          const roadmapContent = readFileSync(roadmapPath, "utf-8");
+          const mergeResult = mergeMilestoneToMain(originalBasePath, currentMilestoneId, roadmapContent);
+          ctx.ui.notify(
+            `Milestone ${currentMilestoneId} merged to main.${mergeResult.pushed ? " Pushed to remote." : ""}`,
+            "info",
+          );
+        } else {
+          // No roadmap found — teardown worktree without merge
+          teardownAutoWorktree(originalBasePath, currentMilestoneId);
+          ctx.ui.notify(`Exited worktree for ${currentMilestoneId} (no roadmap for merge).`, "info");
+        }
+      } catch (err) {
+        ctx.ui.notify(
+          `Milestone merge failed during transition: ${err instanceof Error ? err.message : String(err)}`,
+          "warning",
+        );
+        // Force cwd back to project root even if merge failed
+        if (originalBasePath) {
+          try { process.chdir(originalBasePath); } catch { /* best-effort */ }
+        }
+      }
+
+      // Update basePath to project root (mergeMilestoneToMain already chdir'd)
+      basePath = originalBasePath;
+      gitService = new GitServiceImpl(basePath, loadEffectiveGSDPreferences()?.preferences?.git ?? {});
+      invalidateAllCaches();
+
+      // Re-derive state from project root before creating new worktree
+      state = await deriveState(basePath);
+      mid = state.activeMilestone?.id;
+      midTitle = state.activeMilestone?.title;
+
+      // Create new worktree for the incoming milestone
+      if (mid) {
+        captureIntegrationBranch(basePath, mid, { commitDocs: loadEffectiveGSDPreferences()?.preferences?.git?.commit_docs });
+        try {
+          const wtPath = createAutoWorktree(basePath, mid);
+          basePath = wtPath;
+          gitService = new GitServiceImpl(basePath, loadEffectiveGSDPreferences()?.preferences?.git ?? {});
+          ctx.ui.notify(`Created auto-worktree for ${mid} at ${wtPath}`, "info");
+        } catch (err) {
+          ctx.ui.notify(
+            `Auto-worktree creation for ${mid} failed: ${err instanceof Error ? err.message : String(err)}. Continuing in project root.`,
+            "warning",
+          );
+        }
+      }
+    } else {
+      // Not in worktree — just capture integration branch for the new milestone
+      captureIntegrationBranch(originalBasePath || basePath, mid, { commitDocs: loadEffectiveGSDPreferences()?.preferences?.git?.commit_docs });
+    }
+
+    // Prune completed milestone from queue order file
+    const pendingIds = state.registry
+      .filter(m => m.status !== "complete")
+      .map(m => m.id);
+    pruneQueueOrder(basePath, pendingIds);
   }
   if (mid) {
     currentMilestoneId = mid;
@@ -1261,7 +1527,7 @@ async function dispatchNextUnit(
     // Save final session before stopping
     if (currentUnit) {
       const modelId = ctx.model?.id ?? "unknown";
-      snapshotUnitMetrics(ctx, currentUnit.type, currentUnit.id, currentUnit.startedAt, modelId);
+      snapshotUnitMetrics(ctx, currentUnit.type, currentUnit.id, currentUnit.startedAt, modelId, currentUnitRouting ?? undefined);
       saveActivityLog(ctx, basePath, currentUnit.type, currentUnit.id);
     }
     sendDesktopNotification("GSD", "All milestones complete!", "success", "milestone");
@@ -1289,7 +1555,7 @@ async function dispatchNextUnit(
   if (!mid || !midTitle) {
     if (currentUnit) {
       const modelId = ctx.model?.id ?? "unknown";
-      snapshotUnitMetrics(ctx, currentUnit.type, currentUnit.id, currentUnit.startedAt, modelId);
+      snapshotUnitMetrics(ctx, currentUnit.type, currentUnit.id, currentUnit.startedAt, modelId, currentUnitRouting ?? undefined);
       saveActivityLog(ctx, basePath, currentUnit.type, currentUnit.id);
     }
     await stopAuto(ctx, pi);
@@ -1304,7 +1570,7 @@ async function dispatchNextUnit(
   if (state.phase === "complete") {
     if (currentUnit) {
       const modelId = ctx.model?.id ?? "unknown";
-      snapshotUnitMetrics(ctx, currentUnit.type, currentUnit.id, currentUnit.startedAt, modelId);
+      snapshotUnitMetrics(ctx, currentUnit.type, currentUnit.id, currentUnit.startedAt, modelId, currentUnitRouting ?? undefined);
       saveActivityLog(ctx, basePath, currentUnit.type, currentUnit.id);
     }
     // Clear completed-units.json for the finished milestone so it doesn't grow unbounded.
@@ -1331,6 +1597,39 @@ async function dispatchNextUnit(
           `Milestone merge failed: ${err instanceof Error ? err.message : String(err)}`,
           "warning",
         );
+        // Ensure cwd is restored even if merge failed partway through (#608).
+        // mergeMilestoneToMain may have chdir'd but then thrown, leaving us
+        // in an indeterminate location.
+        if (originalBasePath) {
+          basePath = originalBasePath;
+          try { process.chdir(basePath); } catch { /* best-effort */ }
+        }
+      }
+    } else if (currentMilestoneId && !isInAutoWorktree(basePath)) {
+      // Branch isolation mode (#603): no worktree, but we may be on a milestone/* branch.
+      // Squash-merge back to the integration branch (or main) before stopping.
+      try {
+        const currentBranch = getCurrentBranch(basePath);
+        const milestoneBranch = autoWorktreeBranch(currentMilestoneId);
+        if (currentBranch === milestoneBranch) {
+          const roadmapPath = resolveMilestoneFile(basePath, currentMilestoneId, "ROADMAP");
+          if (roadmapPath) {
+            const roadmapContent = readFileSync(roadmapPath, "utf-8");
+            // mergeMilestoneToMain handles: auto-commit, checkout integration branch,
+            // squash merge, commit, optional push, branch deletion.
+            const mergeResult = mergeMilestoneToMain(basePath, currentMilestoneId, roadmapContent);
+            gitService = new GitServiceImpl(basePath, loadEffectiveGSDPreferences()?.preferences?.git ?? {});
+            ctx.ui.notify(
+              `Milestone ${currentMilestoneId} merged (branch mode).${mergeResult.pushed ? " Pushed to remote." : ""}`,
+              "info",
+            );
+          }
+        }
+      } catch (err) {
+        ctx.ui.notify(
+          `Milestone merge failed (branch mode): ${err instanceof Error ? err.message : String(err)}`,
+          "warning",
+        );
       }
     }
     sendDesktopNotification("GSD", `Milestone ${mid} complete!`, "success", "milestone");
@@ -1341,7 +1640,7 @@ async function dispatchNextUnit(
   if (state.phase === "blocked") {
     if (currentUnit) {
       const modelId = ctx.model?.id ?? "unknown";
-      snapshotUnitMetrics(ctx, currentUnit.type, currentUnit.id, currentUnit.startedAt, modelId);
+      snapshotUnitMetrics(ctx, currentUnit.type, currentUnit.id, currentUnit.startedAt, modelId, currentUnitRouting ?? undefined);
       saveActivityLog(ctx, basePath, currentUnit.type, currentUnit.id);
     }
     await stopAuto(ctx, pi);
@@ -1449,7 +1748,7 @@ async function dispatchNextUnit(
   if (dispatchResult.action === "stop") {
     if (currentUnit) {
       const modelId = ctx.model?.id ?? "unknown";
-      snapshotUnitMetrics(ctx, currentUnit.type, currentUnit.id, currentUnit.startedAt, modelId);
+      snapshotUnitMetrics(ctx, currentUnit.type, currentUnit.id, currentUnit.startedAt, modelId, currentUnitRouting ?? undefined);
       saveActivityLog(ctx, basePath, currentUnit.type, currentUnit.id);
     }
     await stopAuto(ctx, pi);
@@ -1559,7 +1858,7 @@ async function dispatchNextUnit(
   if (lifetimeCount > MAX_LIFETIME_DISPATCHES) {
     if (currentUnit) {
       const modelId = ctx.model?.id ?? "unknown";
-      snapshotUnitMetrics(ctx, currentUnit.type, currentUnit.id, currentUnit.startedAt, modelId);
+      snapshotUnitMetrics(ctx, currentUnit.type, currentUnit.id, currentUnit.startedAt, modelId, currentUnitRouting ?? undefined);
     }
     saveActivityLog(ctx, basePath, unitType, unitId);
     const expected = diagnoseExpectedArtifact(unitType, unitId, basePath);
@@ -1573,7 +1872,7 @@ async function dispatchNextUnit(
   if (prevCount >= MAX_UNIT_DISPATCHES) {
     if (currentUnit) {
       const modelId = ctx.model?.id ?? "unknown";
-      snapshotUnitMetrics(ctx, currentUnit.type, currentUnit.id, currentUnit.startedAt, modelId);
+      snapshotUnitMetrics(ctx, currentUnit.type, currentUnit.id, currentUnit.startedAt, modelId, currentUnitRouting ?? undefined);
     }
     saveActivityLog(ctx, basePath, unitType, unitId);
 
@@ -1731,9 +2030,19 @@ async function dispatchNextUnit(
   // The session still holds the previous unit's data (newSession hasn't fired yet).
   if (currentUnit) {
     const modelId = ctx.model?.id ?? "unknown";
-    snapshotUnitMetrics(ctx, currentUnit.type, currentUnit.id, currentUnit.startedAt, modelId);
+    snapshotUnitMetrics(ctx, currentUnit.type, currentUnit.id, currentUnit.startedAt, modelId, currentUnitRouting ?? undefined);
     saveActivityLog(ctx, basePath, currentUnit.type, currentUnit.id);
 
+    // Record routing outcome for adaptive learning
+    if (currentUnitRouting) {
+      const isRetry = currentUnit.type === unitType && currentUnit.id === unitId;
+      recordOutcome(
+        currentUnit.type,
+        currentUnitRouting.tier as "light" | "standard" | "heavy",
+        !isRetry, // success = not being retried
+      );
+    }
+
     // Only mark the previous unit as completed if:
     // 1. We're not about to re-dispatch the same unit (retry scenario)
     // 2. The expected artifact actually exists on disk
@@ -1757,6 +2066,10 @@ async function dispatchNextUnit(
         startedAt: currentUnit.startedAt,
         finishedAt: Date.now(),
       });
+      // Cap to last 200 entries to prevent unbounded growth (#611)
+      if (completedUnits.length > 200) {
+        completedUnits = completedUnits.slice(-200);
+      }
       clearUnitRuntimeRecord(basePath, currentUnit.type, currentUnit.id);
       unitDispatchCount.delete(`${currentUnit.type}/${currentUnit.id}`);
       unitRecoveryCount.delete(`${currentUnit.type}/${currentUnit.id}`);
@@ -1832,7 +2145,54 @@ async function dispatchNextUnit(
   const modelConfig = resolveModelWithFallbacksForUnit(unitType);
   if (modelConfig) {
     const availableModels = ctx.modelRegistry.getAvailable();
-    const modelsToTry = [modelConfig.primary, ...modelConfig.fallbacks];
+
+    // ─── Dynamic Model Routing ─────────────────────────────────────────
+    // If enabled, classify unit complexity and potentially downgrade to a
+    // cheaper model. The user's configured model is the ceiling.
+    const routingConfig = resolveDynamicRoutingConfig();
+    let effectiveModelConfig = modelConfig;
+    let routingTierLabel = "";
+    currentUnitRouting = null;
+
+    if (routingConfig.enabled) {
+      // Compute budget pressure if budget ceiling is set
+      let budgetPct: number | undefined;
+      if (routingConfig.budget_pressure !== false) {
+        const budgetCeiling = prefs?.budget_ceiling;
+        if (budgetCeiling !== undefined && budgetCeiling > 0) {
+          const currentLedger = getLedger();
+          const totalCost = currentLedger ? getProjectTotals(currentLedger.units).cost : 0;
+          budgetPct = totalCost / budgetCeiling;
+        }
+      }
+
+      // Classify complexity (hook routing controlled by config.hooks)
+      const isHook = unitType.startsWith("hook/");
+      const shouldClassify = !isHook || routingConfig.hooks !== false;
+
+      if (shouldClassify) {
+        const classification = classifyUnitComplexity(unitType, unitId, basePath, budgetPct);
+        const availableModelIds = availableModels.map(m => m.id);
+        const routing = resolveModelForComplexity(classification, modelConfig, routingConfig, availableModelIds);
+
+        if (routing.wasDowngraded) {
+          effectiveModelConfig = {
+            primary: routing.modelId,
+            fallbacks: routing.fallbacks,
+          };
+          if (verbose) {
+            ctx.ui.notify(
+              `Dynamic routing [${tierLabel(classification.tier)}]: ${routing.modelId} (${classification.reason})`,
+              "info",
+            );
+          }
+        }
+        routingTierLabel = ` [${tierLabel(classification.tier)}]`;
+        currentUnitRouting = { tier: classification.tier, modelDowngraded: routing.wasDowngraded };
+      }
+    }
+
+    const modelsToTry = [effectiveModelConfig.primary, ...effectiveModelConfig.fallbacks];
     let modelSet = false;
 
     for (const modelId of modelsToTry) {
@@ -1897,11 +2257,11 @@ async function dispatchNextUnit(
 
       const ok = await pi.setModel(model, { persist: false });
       if (ok) {
-        const fallbackNote = modelId === modelConfig.primary
+        const fallbackNote = modelId === effectiveModelConfig.primary
           ? ""
-          : ` (fallback from ${modelConfig.primary})`;
+          : ` (fallback from ${effectiveModelConfig.primary})`;
         const phase = unitPhaseLabel(unitType);
-        ctx.ui.notify(`Model [${phase}]: ${model.provider}/${model.id}${fallbackNote}`, "info");
+        ctx.ui.notify(`Model [${phase}]${routingTierLabel}: ${model.provider}/${model.id}${fallbackNote}`, "info");
         modelSet = true;
         break;
       } else {
@@ -1957,6 +2317,16 @@ async function dispatchNextUnit(
     if (!runtime) return;
     if (Date.now() - runtime.lastProgressAt < idleTimeoutMs) return;
 
+    // Agent has tool calls currently executing (await_job, long bash, etc.) —
+    // not idle, just waiting for tool completion.
+    if (inFlightTools.size > 0) {
+      writeUnitRuntimeRecord(basePath, unitType, unitId, currentUnit.startedAt, {
+        lastProgressAt: Date.now(),
+        lastProgressKind: "tool-in-flight",
+      });
+      return;
+    }
+
     // Before triggering recovery, check if the agent is actually producing
     // work on disk.  `git status --porcelain` is cheap and catches any
     // staged/unstaged/untracked changes the agent made since lastProgressAt.
@@ -1970,7 +2340,7 @@ async function dispatchNextUnit(
 
     if (currentUnit) {
       const modelId = ctx.model?.id ?? "unknown";
-      snapshotUnitMetrics(ctx, currentUnit.type, currentUnit.id, currentUnit.startedAt, modelId);
+      snapshotUnitMetrics(ctx, currentUnit.type, currentUnit.id, currentUnit.startedAt, modelId, currentUnitRouting ?? undefined);
     }
     saveActivityLog(ctx, basePath, unitType, unitId);
 
@@ -1996,7 +2366,7 @@ async function dispatchNextUnit(
         timeoutAt: Date.now(),
       });
       const modelId = ctx.model?.id ?? "unknown";
-      snapshotUnitMetrics(ctx, currentUnit.type, currentUnit.id, currentUnit.startedAt, modelId);
+      snapshotUnitMetrics(ctx, currentUnit.type, currentUnit.id, currentUnit.startedAt, modelId, currentUnitRouting ?? undefined);
     }
     saveActivityLog(ctx, basePath, unitType, unitId);