gsd-pi 2.76.0-dev.97807402 → 2.76.0-dev.97f5583d9

package/dist/resources/extensions/gsd/safety/evidence-collector.js

@@ -3,9 +3,17 @@
  * Tracks every bash command, file write, and file edit during a unit execution.
  * Evidence is compared against LLM completion claims in evidence-cross-ref.ts.
  *
+ * Evidence is persisted to .gsd/safety/evidence-<mid>-<sid>-<tid>.json so it
+ * survives session restarts (pause/resume, crash recovery). On unit start,
+ * call resetEvidence() then loadEvidenceFromDisk(). On every new tool call,
+ * saveEvidenceToDisk() is called automatically by recordToolCall/recordToolResult.
+ *
  * Follows the same module-level Map pattern as auto-tool-tracking.ts.
  * Copyright (c) 2026 Jeremy McSpadden <jeremy@fluxlabs.net>
  */
+import { existsSync, mkdirSync, readFileSync, writeFileSync, renameSync, unlinkSync, } from "node:fs";
+import { join, dirname } from "node:path";
+import { randomBytes } from "node:crypto";
 // ─── Module State ───────────────────────────────────────────────────────────
 let unitEvidence = [];
 // ─── Public API ─────────────────────────────────────────────────────────────
@@ -27,6 +35,94 @@ export function getFilePaths() {
         .filter((e) => e.kind === "write" || e.kind === "edit")
         .map(e => e.path);
 }
+// ─── Persistence (Bug #4385 — evidence must survive session restarts) ────────
+/**
+ * Build the path for the evidence JSON file for a given unit.
+ * Lives under .gsd/safety/ which is gitignored and session-scoped.
+ */
+function evidencePath(basePath, milestoneId, sliceId, taskId) {
+    return join(basePath, ".gsd", "safety", `evidence-${milestoneId}-${sliceId}-${taskId}.json`);
+}
+/**
+ * Validate that a parsed value is an array of EvidenceEntry objects.
+ * Rejects corrupt / schema-mismatch data rather than letting it poison state.
+ */
+function isEvidenceArray(data) {
+    if (!Array.isArray(data))
+        return false;
+    return data.every((e) => {
+        if (e === null || typeof e !== "object")
+            return false;
+        const rec = e;
+        if (typeof rec.toolCallId !== "string")
+            return false;
+        if (typeof rec.timestamp !== "number")
+            return false;
+        if (rec.kind === "bash") {
+            return (typeof rec.command === "string" &&
+                typeof rec.exitCode === "number" &&
+                typeof rec.outputSnippet === "string");
+        }
+        if (rec.kind === "write" || rec.kind === "edit") {
+            return typeof rec.path === "string";
+        }
+        return false;
+    });
+}
+/**
+ * Persist the current in-memory evidence to disk so it survives a session
+ * restart. Called from saveEvidenceToDisk after recordToolCall/recordToolResult.
+ * Non-fatal — persistence failures must never break unit execution.
+ */
+export function saveEvidenceToDisk(basePath, milestoneId, sliceId, taskId) {
+    try {
+        const path = evidencePath(basePath, milestoneId, sliceId, taskId);
+        mkdirSync(dirname(path), { recursive: true });
+        const tmp = `${path}.tmp.${randomBytes(4).toString("hex")}`;
+        writeFileSync(tmp, JSON.stringify(unitEvidence, null, 2) + "\n", "utf-8");
+        renameSync(tmp, path);
+    }
+    catch {
+        // Non-fatal — don't let persistence failures break unit execution
+    }
+}
+/**
+ * Load persisted evidence from disk into the in-memory array.
+ * Call after resetEvidence() on session resume to restore context for a
+ * partially-executed unit. If the file does not exist (fresh unit), this
+ * is a no-op — getEvidence() will return [] which is correct.
+ */
+export function loadEvidenceFromDisk(basePath, milestoneId, sliceId, taskId) {
+    try {
+        const path = evidencePath(basePath, milestoneId, sliceId, taskId);
+        if (!existsSync(path))
+            return;
+        const raw = readFileSync(path, "utf-8");
+        const parsed = JSON.parse(raw);
+        if (isEvidenceArray(parsed)) {
+            unitEvidence = parsed;
+        }
+    }
+    catch {
+        // Non-fatal — corrupt / missing file is treated as empty evidence
+    }
+}
+/**
+ * Delete the persisted evidence file for a unit after it has been fully
+ * processed. Prevents stale evidence from affecting future retries of
+ * the same unit ID.
+ */
+export function clearEvidenceFromDisk(basePath, milestoneId, sliceId, taskId) {
+    try {
+        const path = evidencePath(basePath, milestoneId, sliceId, taskId);
+        if (existsSync(path)) {
+            unlinkSync(path);
+        }
+    }
+    catch {
+        // Non-fatal
+    }
+}
 // ─── Recording (called from register-hooks.ts) ─────────────────────────────
 /**
  * Record a tool call at dispatch time (before execution).

package/dist/resources/extensions/gsd/safety/file-change-validator.js

@@ -4,7 +4,9 @@
  *
  * Uses tasks.expected_output (DB column, populated from per-task ## Expected Output)
  * and tasks.files (from slice PLAN.md - Files: subline) as the expected set.
- * Compares against git diff HEAD~1 --name-only after auto-commit.
+ * Compares against `git diff-tree --root --no-commit-id -r --name-only HEAD` after auto-commit.
+ * Using diff-tree --root handles initial commits, shallow clones, and merge commits correctly
+ * (Bug #4385 — git diff HEAD~1 failed on initial commits).
  *
  * Copyright (c) 2026 Jeremy McSpadden <jeremy@fluxlabs.net>
  */

package/dist/resources/extensions/gsd/safety/safety-harness.js

@@ -60,7 +60,7 @@ export function isHarnessEnabled(raw) {
     return DEFAULTS.enabled;
 }
 // ─── Re-exports ─────────────────────────────────────────────────────────────
-export { resetEvidence, getEvidence, getBashEvidence, getFilePaths, recordToolCall, recordToolResult, } from "./evidence-collector.js";
+export { resetEvidence, getEvidence, getBashEvidence, getFilePaths, recordToolCall, recordToolResult, saveEvidenceToDisk, loadEvidenceFromDisk, clearEvidenceFromDisk, } from "./evidence-collector.js";
 export { classifyCommand } from "./destructive-guard.js";
 export { validateFileChanges } from "./file-change-validator.js";
 export { crossReferenceEvidence } from "./evidence-cross-ref.js";

package/dist/resources/extensions/gsd/uok/plan-v2.js

@@ -22,6 +22,23 @@ function hasFileContent(path) {
         return false;
     }
 }
+function getArtifactLookupBases(basePath) {
+    const bases = [basePath];
+    const projectRoot = process.env.GSD_PROJECT_ROOT;
+    if (projectRoot && projectRoot.trim().length > 0 && projectRoot !== basePath) {
+        bases.push(projectRoot);
+    }
+    return bases;
+}
+function hasMilestoneFileContent(basePath, milestoneId, suffix) {
+    const bases = getArtifactLookupBases(basePath);
+    for (const candidateBase of bases) {
+        if (hasFileContent(resolveMilestoneFile(candidateBase, milestoneId, suffix))) {
+            return true;
+        }
+    }
+    return false;
+}
 function countSliceResearchArtifacts(basePath, milestoneId, slices) {
     let count = 0;
     for (const slice of slices) {
@@ -43,9 +60,9 @@ export function compileUnitGraphFromState(basePath, state) {
     const slices = getMilestoneSlices(mid).sort((a, b) => Number(a.sequence ?? 0) - Number(b.sequence ?? 0));
     const nodes = [];
     const clarifyRoundLimit = PLAN_V2_CLARIFY_ROUND_LIMIT;
-    const draftContextIncluded = hasFileContent(resolveMilestoneFile(basePath, mid, "CONTEXT-DRAFT"));
-    const finalizedContextIncluded = hasFileContent(resolveMilestoneFile(basePath, mid, "CONTEXT"));
-    const researchSynthesized = hasFileContent(resolveMilestoneFile(basePath, mid, "RESEARCH"))
+    const draftContextIncluded = hasMilestoneFileContent(basePath, mid, "CONTEXT-DRAFT");
+    const finalizedContextIncluded = hasMilestoneFileContent(basePath, mid, "CONTEXT");
+    const researchSynthesized = hasMilestoneFileContent(basePath, mid, "RESEARCH")
         || countSliceResearchArtifacts(basePath, mid, slices) > 0;
     if (isExecutionEntryPhase(state.phase) && !finalizedContextIncluded) {
         const reason = draftContextIncluded