gsd-pi 2.82.0 → 3.0.0

package/dist/resources/extensions/gsd/auto/phases.js

@@ -44,6 +44,7 @@ import { resolveManifest } from "../unit-context-manifest.js";
 import { createWorktreeSafetyModule } from "../worktree-safety.js";
 import { isSuspiciousGhostCompletion } from "../auto-unit-closeout.js";
 import { decideVerificationRetry, verificationRetryKey } from "./verification-retry-policy.js";
+import { buildPhaseHandoffOutcome, setAutoOutcomeWidget } from "../auto-dashboard.js";
 // ─── Path Comparison Helper ───────────────────────────────────────────────
 /** Compare two paths for physical identity, tolerating trailing slashes and symlinks. */
 function isSamePathLocal(a, b) {
@@ -103,6 +104,12 @@ function unitWritesSource(unitType) {
 function formatWorktreeSafetyFailure(result) {
     return `Worktree Safety failed (${result.kind}): ${result.reason} ${result.remediation}`;
 }
+function formatWorktreeSafetyStopReason(result) {
+    if (result.kind === "empty-worktree-with-project-content") {
+        return `Worktree Safety failed (${result.kind}). Run /gsd doctor fix, then /gsd auto.`;
+    }
+    return `Worktree Safety failed (${result.kind}).`;
+}
 function resolveEmptyWorktreeWithProjectContent(unitRoot, projectRoot) {
     if (isSamePathLocal(unitRoot, projectRoot))
         return false;
@@ -176,7 +183,7 @@ async function validateSourceWriteWorktreeSafety(ic, unitType, unitId, milestone
         projectRoot,
     });
     ctx.ui.notify(msg, "error");
-    await deps.stopAuto(ctx, pi, msg);
+    await deps.stopAuto(ctx, pi, formatWorktreeSafetyStopReason(result));
     return { action: "break", reason: result.kind };
 }
 // ─── Session timeout auto-resume state ────────────────────────────────────────
@@ -968,7 +975,14 @@ export async function runDispatch(ic, preData, loopState) {
         prompt = preDispatchResult.prompt;
     }
     const guardBasePath = _resolveDispatchGuardBasePath(s);
-    const priorSliceBlocker = deps.getPriorSliceCompletionBlocker(guardBasePath, deps.getMainBranch(guardBasePath), unitType, unitId);
+    let mainBranch = "main";
+    try {
+        mainBranch = deps.getMainBranch(guardBasePath);
+    }
+    catch (err) {
+        debugLog("autoLoop", { phase: "getMainBranch-failed", error: String(err) });
+    }
+    const priorSliceBlocker = deps.getPriorSliceCompletionBlocker(guardBasePath, mainBranch, unitType, unitId);
     if (priorSliceBlocker) {
         await deps.stopAuto(ctx, pi, priorSliceBlocker);
         debugLog("autoLoop", { phase: "exit", reason: "prior-slice-blocker" });
@@ -1324,35 +1338,8 @@ export async function runUnitPhase(ic, iterData, loopState, sidecarItem) {
         s.currentUnit.type === unitType &&
         s.currentUnit.id === unitId);
     const previousTier = s.currentUnitRouting?.tier;
-    // Scope workflow-logger buffer to this unit so post-finalize drains are
-    // per-unit. Without this, the module-level _buffer accumulates across every
-    // unit in the same Node process (see workflow-logger.ts module header).
-    _resetLogs();
     const dispatchKey = `${unitType}/${unitId}`;
-    s.unitDispatchCount.set(dispatchKey, (s.unitDispatchCount.get(dispatchKey) ?? 0) + 1);
-    s.currentUnit = { type: unitType, id: unitId, startedAt: Date.now() };
-    s.lastGitActionFailure = null;
-    s.lastGitActionStatus = null;
-    s.lastUnitAgentEndMessages = null;
-    setCurrentPhase(unitType, {
-        basePath: s.basePath,
-        traceId: ic.flowId,
-        turnId: `iter-${ic.iteration}`,
-        causedBy: "unit-start",
-    });
-    s.lastToolInvocationError = null; // #2883: clear stale error from previous unit
-    const unitStartSeq = ic.nextSeq();
-    deps.emitJournalEvent({ ts: new Date().toISOString(), flowId: ic.flowId, seq: unitStartSeq, eventType: "unit-start", data: { unitType, unitId } });
-    deps.captureAvailableSkills();
-    writeUnitRuntimeRecord(s.basePath, unitType, unitId, s.currentUnit.startedAt, {
-        phase: "dispatched",
-        wrapupWarningSent: false,
-        timeoutAt: null,
-        lastProgressAt: s.currentUnit.startedAt,
-        progressCount: 0,
-        lastProgressKind: "dispatch",
-        recoveryAttempts: 0, // Reset so re-dispatched units get full recovery budget (#2322)
-    });
+    const nextDispatchCount = (s.unitDispatchCount.get(dispatchKey) ?? 0) + 1;
     // Status bar (widget + preconditions deferred until after model selection — see #2899)
     ctx.ui.setStatus("gsd-auto", "auto");
     if (mid)
@@ -1406,7 +1393,7 @@ export async function runUnitPhase(ic, iterData, loopState, sidecarItem) {
         finalPrompt = `${capped}\n\n---\n\n${finalPrompt}`;
         s.pendingCrashRecovery = null;
     }
-    else if ((s.unitDispatchCount.get(dispatchKey) ?? 0) > 1) {
+    else if (nextDispatchCount > 1) {
         const diagnostic = deps.getDeepDiagnostic(s.basePath);
         if (diagnostic) {
             const cappedDiag = diagnostic.length > MAX_RECOVERY_CHARS
@@ -1445,6 +1432,11 @@ export async function runUnitPhase(ic, iterData, loopState, sidecarItem) {
         logWarning("engine", "Prompt reorder failed", { error: msg });
     }
     // Select and apply model (with tier escalation on retry — normal units only)
+    const prevUnitRouting = s.currentUnitRouting;
+    const prevUnitModel = s.currentUnitModel;
+    const prevDispatchedModelId = s.currentDispatchedModelId;
+    const prevSessionModel = ctx.model;
+    const prevSessionThinkingLevel = pi.getThinkingLevel();
     const modelResult = await deps.selectAndApplyModel(ctx, pi, unitType, unitId, s.basePath, prefs, s.verbose, s.autoModeStartModel, sidecarItem ? undefined : { isRetry, previousTier }, undefined, s.manualSessionModelOverride, s.autoModeStartThinkingLevel);
     s.currentUnitRouting =
         modelResult.routing;
@@ -1488,12 +1480,58 @@ export async function runUnitPhase(ic, iterData, loopState, sidecarItem) {
                 ? ctx.modelRegistry.getProviderAuthMode(ctx.model.provider)
                 : undefined,
         baseUrl: s.currentUnitModel?.baseUrl ?? ctx.model?.baseUrl,
+        activeTools: typeof pi.getActiveTools === "function" ? pi.getActiveTools() : [],
     });
     if (compatibilityError) {
+        s.currentUnitRouting = prevUnitRouting;
+        s.currentUnitModel = prevUnitModel;
+        s.currentDispatchedModelId = prevDispatchedModelId;
+        if (s.checkpointSha) {
+            cleanupCheckpoint(s.basePath, unitId);
+            s.checkpointSha = null;
+        }
+        if (prevSessionModel) {
+            const ok = await pi.setModel(prevSessionModel, { persist: false });
+            if (!ok) {
+                ctx.ui.notify("Failed to restore previous session model after compatibility check failure.", "warning");
+            }
+            if (prevSessionThinkingLevel) {
+                pi.setThinkingLevel(prevSessionThinkingLevel);
+            }
+        }
         ctx.ui.notify(compatibilityError, "error");
         await deps.stopAuto(ctx, pi, compatibilityError);
         return { action: "break", reason: "workflow-capability" };
     }
+    // Scope workflow-logger buffer to this unit so post-finalize drains are
+    // per-unit. Without this, the module-level _buffer accumulates across every
+    // unit in the same Node process (see workflow-logger.ts module header).
+    _resetLogs();
+    const unitStartedAt = Date.now();
+    s.unitDispatchCount.set(dispatchKey, nextDispatchCount);
+    s.currentUnit = { type: unitType, id: unitId, startedAt: unitStartedAt };
+    s.lastGitActionFailure = null;
+    s.lastGitActionStatus = null;
+    s.lastUnitAgentEndMessages = null;
+    setCurrentPhase(unitType, {
+        basePath: s.basePath,
+        traceId: ic.flowId,
+        turnId: `iter-${ic.iteration}`,
+        causedBy: "unit-start",
+    });
+    s.lastToolInvocationError = null; // #2883: clear stale error from previous unit
+    const unitStartSeq = ic.nextSeq();
+    deps.emitJournalEvent({ ts: new Date().toISOString(), flowId: ic.flowId, seq: unitStartSeq, eventType: "unit-start", data: { unitType, unitId } });
+    deps.captureAvailableSkills();
+    writeUnitRuntimeRecord(s.basePath, unitType, unitId, unitStartedAt, {
+        phase: "dispatched",
+        wrapupWarningSent: false,
+        timeoutAt: null,
+        lastProgressAt: unitStartedAt,
+        progressCount: 0,
+        lastProgressKind: "dispatch",
+        recoveryAttempts: 0, // Reset so re-dispatched units get full recovery budget (#2322)
+    });
     // Progress widget + preconditions — deferred to after model selection so the
     // widget's first render tick shows the correct model (#2899).
     deps.updateProgressWidget(ctx, unitType, unitId, state);
@@ -1656,6 +1694,15 @@ export async function runUnitPhase(ic, iterData, loopState, sidecarItem) {
             await emitCancelledUnitEnd(ic, unitType, unitId, unitStartSeq, unitResult.errorContext);
             return { action: "break", reason: "session-timeout" };
         }
+        if (unitResult.errorContext?.isTransient &&
+            errorCategory === "aborted") {
+            ctx.ui.notify(`Unit ${unitType} ${unitId} was aborted by the user. Pausing auto-mode (recoverable).`, "warning");
+            debugLog("autoLoop", { phase: "unit-aborted-transient-pause", unitType, unitId, category: errorCategory });
+            await deps.pauseAuto(ctx, pi);
+            await deps.autoCommitUnit?.(s.basePath, unitType, unitId, ctx);
+            await emitCancelledUnitEnd(ic, unitType, unitId, unitStartSeq, unitResult.errorContext);
+            return { action: "break", reason: "unit-aborted-pause" };
+        }
         // All other cancelled states (structural errors, non-transient failures): hard stop
         if (s.currentUnit) {
             await deps.closeoutUnit(ctx, s.basePath, unitType, unitId, s.currentUnit.startedAt, deps.buildSnapshotOpts(unitType, unitId));
@@ -1914,6 +1961,18 @@ export async function runFinalize(ic, iterData, loopState, sidecarItem) {
             lastProgressAt: Date.now(),
             lastProgressKind: "finalize-success",
         });
+        if (!preUnitSnapshot.type.startsWith("hook/") &&
+            preUnitSnapshot.type !== "custom-step" &&
+            preUnitSnapshot.type !== "complete-milestone") {
+            setAutoOutcomeWidget(ctx, {
+                ...buildPhaseHandoffOutcome({
+                    unitType: preUnitSnapshot.type,
+                    unitId: preUnitSnapshot.id,
+                    agentEndMessages: s.lastUnitAgentEndMessages,
+                }),
+                startedAt: s.autoStartTime,
+            });
+        }
     }
     s.currentUnit = null;
     clearCurrentPhase();

package/dist/resources/extensions/gsd/auto/session.js

@@ -1,3 +1,5 @@
+// Project/App: GSD-2
+// File Purpose: Mutable auto-mode session state container.
 /**
  * AutoSession — encapsulates all mutable auto-mode state into a single instance.
  *
@@ -26,6 +28,7 @@ export class AutoSession {
     active = false;
     paused = false;
     completionStopInProgress = false;
+    preserveStepSurfaceAfterLoopExit = false;
     stepMode = false;
     verbose = false;
     activeEngineId = null;
@@ -210,6 +213,7 @@ export class AutoSession {
         this.active = false;
         this.paused = false;
         this.completionStopInProgress = false;
+        this.preserveStepSurfaceAfterLoopExit = false;
         this.stepMode = false;
         this.verbose = false;
         this.activeEngineId = null;

package/dist/resources/extensions/gsd/auto/workflow-kernel.js

@@ -66,6 +66,9 @@ export function decideEngineDispatch(input) {
 export function decideFinalizeResult(input) {
     if (input.action === "break") {
         const reason = input.reason ?? "unknown";
+        if (reason === "step-wizard") {
+            return { action: "complete-and-break" };
+        }
         return {
             action: "stop",
             failureClass: reason === "git-closeout-failure" ? "git" : "closeout",

package/dist/resources/extensions/gsd/auto/workflow-memory-pressure.js

@@ -4,6 +4,18 @@ import { createRequire } from "node:module";
 const require = createRequire(import.meta.url);
 const DEFAULT_MEMORY_PRESSURE_THRESHOLD = 0.85;
 const DEFAULT_HEAP_LIMIT_MB = 4096;
+/**
+ * Returns true on auto-mode startup, then every configured interval.
+ *
+ * Iteration 1 is checked explicitly so early session memory pressure cannot
+ * bypass the periodic interval guard.
+ */
+export function shouldCheckMemoryPressure(iteration, interval) {
+    if (!Number.isInteger(interval) || interval <= 0) {
+        throw new Error("Memory pressure check interval must be a positive integer");
+    }
+    return iteration === 1 || iteration % interval === 0;
+}
 function defaultHeapLimitBytes() {
     const v8 = require("node:v8");
     const limit = v8.getHeapStatistics?.().heap_size_limit;

package/dist/resources/extensions/gsd/auto-dashboard.js

@@ -27,6 +27,19 @@ export function extractUatSliceId(unitId) {
         return slice;
     return null;
 }
+export function buildPhaseHandoffOutcome(input) {
+    const phase = unitPhaseLabel(input.unitType);
+    const detail = extractLastAssistantSummary(input.agentEndMessages) ??
+        `Completed ${unitVerb(input.unitType)} ${input.unitId}.`;
+    return {
+        status: "complete",
+        title: `${phase} complete`,
+        detail,
+        unitLabel: `${unitVerb(input.unitType)} ${input.unitId}`,
+        nextAction: "Preparing the next phase. Review this handoff while the next session starts.",
+        commands: ["/gsd status for overview", "/gsd visualize to inspect", "/gsd notifications for history"],
+    };
+}
 // ─── Unit Description Helpers ─────────────────────────────────────────────────
 export function unitVerb(unitType) {
     if (unitType.startsWith("hook/"))
@@ -464,7 +477,6 @@ export function _resetWidgetModeForTests() {
 export function updateProgressWidget(ctx, unitType, unitId, state, accessors, tierBadge) {
     if (!ctx.hasUI)
         return;
-    ctx.ui.setWidget("gsd-outcome", undefined);
     // Welcome header is a startup-only banner — permanently suppress it once
     // auto-mode activates. The dashboard widget owns all status from here.
     // Note: setHeader(undefined) restores the built-in header (logo +
@@ -927,3 +939,56 @@ function normalizeRollupText(value) {
         return null;
     return clean;
 }
+function isAssistantMessage(value) {
+    if (!value || typeof value !== "object")
+        return false;
+    const record = value;
+    if (record.role === "assistant")
+        return true;
+    const message = record.message;
+    if (message && typeof message === "object") {
+        return message.role === "assistant";
+    }
+    return false;
+}
+function extractLastAssistantSummary(messages) {
+    if (!messages || messages.length === 0)
+        return null;
+    for (let i = messages.length - 1; i >= 0; i--) {
+        if (!isAssistantMessage(messages[i]))
+            continue;
+        const text = extractMessageText(messages[i]);
+        const clean = normalizeRollupText(text);
+        if (clean)
+            return truncateToWidth(clean, 220, "…");
+    }
+    return null;
+}
+function extractMessageText(value) {
+    if (typeof value === "string")
+        return value;
+    if (!value || typeof value !== "object")
+        return null;
+    const record = value;
+    if (typeof record.content === "string")
+        return record.content;
+    const message = record.message;
+    if (message && typeof message === "object") {
+        return extractMessageText(message);
+    }
+    const content = record.content;
+    if (Array.isArray(content)) {
+        const parts = content
+            .map((part) => {
+            if (typeof part === "string")
+                return part;
+            if (!part || typeof part !== "object")
+                return "";
+            const partRecord = part;
+            return typeof partRecord.text === "string" ? partRecord.text : "";
+        })
+            .filter(Boolean);
+        return parts.length > 0 ? parts.join(" ") : null;
+    }
+    return null;
+}

package/dist/resources/extensions/gsd/auto-direct-dispatch.js

@@ -224,6 +224,7 @@ export async function dispatchDirectPhase(ctx, pi, phase, base) {
         unitType,
         authMode: ctx.model?.provider ? ctx.modelRegistry.getProviderAuthMode(ctx.model.provider) : undefined,
         baseUrl: ctx.model?.baseUrl,
+        activeTools: typeof pi.getActiveTools === "function" ? pi.getActiveTools() : [],
     });
     if (compatibilityError) {
         ctx.ui.notify(compatibilityError, "error");

package/dist/resources/extensions/gsd/auto-dispatch.js

@@ -102,6 +102,9 @@ function missingSliceStop(mid, phase) {
         level: "error",
     };
 }
+function isRegistryMilestoneComplete(state, mid) {
+    return state.registry.some((milestone) => milestone.id === mid && milestone.status === "complete");
+}
 /**
  * Check for milestone slices missing SUMMARY files.
  * Returns array of missing slice IDs, or empty array if all present or DB unavailable.
@@ -247,6 +250,8 @@ export const DISPATCH_RULES = [
                 return null;
             if (!MILESTONE_ID_RE.test(mid))
                 return null;
+            if (isRegistryMilestoneComplete(state, mid))
+                return null;
             // Align with the plan-v2 gate's lookup semantics: whitespace-only counts
             // as missing, and an auto worktree may fall back to GSD_PROJECT_ROOT.
             if (hasFinalizedMilestoneContext(basePath, mid))
@@ -294,9 +299,7 @@ export const DISPATCH_RULES = [
             const attempts = incrementUatCount(basePath, mid, sliceId);
             if (attempts > MAX_UAT_ATTEMPTS) {
                 return {
-                    action: "stop",
-                    reason: `run-uat for ${mid}/${sliceId} has been dispatched ${attempts - 1} times without producing a verdict. Verification commands may be broken — fix the UAT spec or manually write an ASSESSMENT verdict.`,
-                    level: "warning",
+                    action: "skip",
                 };
             }
             const uatFile = resolveSliceFile(basePath, mid, sliceId, "UAT");
@@ -557,6 +560,8 @@ export const DISPATCH_RULES = [
         match: async ({ state, mid, midTitle, basePath, prefs, structuredQuestionsAvailable }) => {
             if (state.phase !== "pre-planning")
                 return null;
+            if (isRegistryMilestoneComplete(state, mid))
+                return null;
             const contextFile = resolveMilestoneFile(basePath, mid, "CONTEXT");
             const hasContext = !!(contextFile && (await loadFile(contextFile)));
             if (hasContext)
@@ -609,7 +614,7 @@ export const DISPATCH_RULES = [
         },
     },
     {
-        name: "planning (require_slice_discussion) → pause for discussion (#3454)",
+        name: "planning (require_slice_discussion) → pause for discussion",
         match: async ({ state, mid, basePath, prefs }) => {
             if (state.phase !== "planning")
                 return null;
@@ -1016,7 +1021,7 @@ export const DISPATCH_RULES = [
                         mkdirSync(mDir, { recursive: true });
                     const validationPath = join(mDir, buildMilestoneFileName(mid, "VALIDATION"));
                     const skipSource = trivialVariant
-                        ? "trivial-scope pipeline variant (#4781)"
+                        ? "trivial-scope pipeline variant"
                         : "`skip_milestone_validation` preference";
                     const skipValidationReason = trivialVariant ? "trivial-scope" : "preference";
                     const content = [
@@ -1091,19 +1096,19 @@ export const DISPATCH_RULES = [
                     return { action: "skip" };
                 }
             }
-            // Safety guard (#2675): block completion when VALIDATION verdict is
-            // needs-remediation. The state machine treats needs-remediation as
-            // terminal (to prevent validate-milestone loops per #832), but
-            // completing-milestone should NOT proceed — remediation work is needed.
+            // Safety guard (#2675, #5747, #5920): block completion when VALIDATION
+            // verdict is anything other than pass. The state machine treats these
+            // verdicts as terminal, but completing-milestone should NOT proceed —
+            // remediation or human attention is needed.
             const validationFile = resolveMilestoneFile(basePath, mid, "VALIDATION");
             if (validationFile) {
                 const validationContent = await loadFile(validationFile);
                 if (validationContent) {
                     const verdict = extractVerdict(validationContent);
-                    if (verdict === "needs-remediation") {
+                    if (verdict !== "pass") {
                         return {
                             action: "stop",
-                            reason: `Cannot complete milestone ${mid}: VALIDATION verdict is "needs-remediation". Address the remediation findings and re-run validation, or update the verdict manually.`,
+                            reason: `Cannot complete milestone ${mid}: VALIDATION verdict is "${verdict}". Address the validation findings and re-run validation, or run \`/gsd verdict pass --rationale "..."\` to override.`,
                             level: "warning",
                         };
                     }
@@ -1118,16 +1123,12 @@ export const DISPATCH_RULES = [
                     level: "error",
                 };
             }
-            // Safety guard (#1703): verify the milestone produced implementation
-            // artifacts (non-.gsd/ files). A milestone with only plan files and
-            // zero implementation code should not be marked complete.
+            // Safety signal (#1703, #5097): detect milestones with only .gsd/
+            // artifacts. This no longer hard-blocks completion because some
+            // milestones are intentionally planning/documentation-only.
             const artifactCheck = hasImplementationArtifacts(basePath, mid);
             if (artifactCheck === "absent") {
-                return {
-                    action: "stop",
-                    reason: `Cannot complete milestone ${mid}: no implementation files found outside .gsd/. The milestone has only plan files — actual code changes are required.`,
-                    level: "error",
-                };
+                logWarning("dispatch", `Milestone ${mid} has no implementation files outside .gsd/ — continuing complete-milestone dispatch (planning-only/documentation-only milestone).`);
             }
             if (artifactCheck === "unknown") {
                 logWarning("dispatch", `Implementation artifact check inconclusive for ${mid} — proceeding (git context unavailable)`);

package/dist/resources/extensions/gsd/auto-model-selection.js

@@ -494,6 +494,8 @@ autoModeStartThinkingLevel) {
  * Handles formats: "provider/model", "bare-id", "org/model-name" (OpenRouter).
  */
 export function resolveModelId(modelId, availableModels, currentProvider) {
+    if (!modelId)
+        return undefined;
     const slashIdx = modelId.indexOf("/");
     if (slashIdx !== -1) {
         const maybeProvider = modelId.substring(0, slashIdx);