gsd-pi 2.80.0-dev.c5c38454b → 2.80.0-dev.cf9433f56

package/src/resources/extensions/gsd/bootstrap/exec-tools.ts

@@ -6,23 +6,36 @@
 import { Type } from "@sinclair/typebox";
 import type { ExtensionAPI } from "@gsd/pi-coding-agent";
 
+async function loadContextModePreferences(baseDir: string) {
+  const [{ loadEffectiveGSDPreferences }, { logWarning }] = await Promise.all([
+    import("../preferences.js"),
+    import("../workflow-logger.js"),
+  ]);
+  try {
+    return loadEffectiveGSDPreferences(baseDir)?.preferences ?? null;
+  } catch (err) {
+    logWarning("tool", `Context Mode tool could not load preferences: ${err instanceof Error ? err.message : String(err)}`);
+    return null;
+  }
+}
+
 export function registerExecTools(pi: ExtensionAPI): void {
   pi.registerTool({
     name: "gsd_exec",
     label: "Exec (Sandboxed)",
     description:
-      "Run a short script (bash/node/python) in a subprocess. Full stdout/stderr persist to " +
+      "Run a short script (bash/node/python) in a subprocess. Capped stdout/stderr and metadata persist to " +
       ".gsd/exec/<id>.{stdout,stderr,meta.json}; only a short digest returns in context. Use " +
       "this instead of reading many files or emitting large tool outputs — e.g. have the script " +
       "count/grep/summarize and log the finding. Enabled by default; opt out via " +
       "preferences.context_mode.enabled=false.",
     promptSnippet:
-      "Run a bash/node/python script in a sandbox; full output is saved to disk and only a digest returns",
+      "Run a bash/node/python script in a sandbox; capped output is saved to disk and only a digest returns",
     promptGuidelines: [
       "Prefer gsd_exec for analyses that would otherwise read >3 files or produce large tool output.",
       "Write scripts that log the finding (counts, matches, summaries) rather than raw dumps.",
       "The digest is the last ~300 chars of stdout — size your log output accordingly.",
-      "Need the full output? Read the stdout_path returned in details (file on local disk).",
+      "Need persisted output? Read the stdout_path returned in details (file on local disk).",
     ],
     parameters: Type.Object({
       runtime: Type.Union(
@@ -40,20 +53,11 @@ export function registerExecTools(pi: ExtensionAPI): void {
       ),
     }),
     async execute(_toolCallId, params, _signal, _onUpdate, _ctx) {
-      const [{ executeGsdExec }, { loadEffectiveGSDPreferences }, { logWarning }] = await Promise.all([
-        import("../tools/exec-tool.js"),
-        import("../preferences.js"),
-        import("../workflow-logger.js"),
-      ]);
-      let prefs: ReturnType<typeof loadEffectiveGSDPreferences> | null = null;
-      try {
-        prefs = loadEffectiveGSDPreferences();
-      } catch (err) {
-        logWarning("tool", `gsd_exec could not load preferences: ${err instanceof Error ? err.message : String(err)}`);
-      }
+      const { executeGsdExec } = await import("../tools/exec-tool.js");
+      const baseDir = process.cwd();
       return executeGsdExec(params as Parameters<typeof executeGsdExec>[0], {
-        baseDir: process.cwd(),
-        preferences: prefs?.preferences ?? null,
+        baseDir,
+        preferences: await loadContextModePreferences(baseDir),
       });
     },
   });
@@ -67,7 +71,7 @@ export function registerExecTools(pi: ExtensionAPI): void {
     promptSnippet: "Search prior gsd_exec runs by substring, runtime, or failing-only filter",
     promptGuidelines: [
       "Use this before re-running an expensive analysis — the prior run's stdout file may still answer.",
-      "The preview shows the trailing ~300 chars of stdout; read stdout_path for the full transcript.",
+      "The preview shows the trailing ~300 chars of stdout; read stdout_path for persisted output.",
     ],
     parameters: Type.Object({
       query: Type.Optional(Type.String({ description: "Substring matched against id and purpose (case-insensitive)." })),
@@ -81,8 +85,10 @@ export function registerExecTools(pi: ExtensionAPI): void {
     }),
     async execute(_toolCallId, params, _signal, _onUpdate, _ctx) {
       const { executeExecSearch } = await import("../tools/exec-search-tool.js");
+      const baseDir = process.cwd();
       return executeExecSearch(params as Parameters<typeof executeExecSearch>[0], {
-        baseDir: process.cwd(),
+        baseDir,
+        preferences: await loadContextModePreferences(baseDir),
       });
     },
   });
@@ -102,8 +108,10 @@ export function registerExecTools(pi: ExtensionAPI): void {
     parameters: Type.Object({}),
     async execute(_toolCallId, params, _signal, _onUpdate, _ctx) {
       const { executeResume } = await import("../tools/resume-tool.js");
+      const baseDir = process.cwd();
       return executeResume(params as Parameters<typeof executeResume>[0], {
-        baseDir: process.cwd(),
+        baseDir,
+        preferences: await loadContextModePreferences(baseDir),
       });
     },
   });

package/src/resources/extensions/gsd/bootstrap/register-hooks.ts

@@ -65,6 +65,26 @@ async function applyDisabledModelProviderPolicy(ctx: ExtensionContext): Promise<
   }
 }
 
+/**
+ * Bridge `context_management.compaction_threshold_percent` from GSD preferences
+ * into the agent's runtime compaction settings (#5475). The preference is
+ * validated to (0.5, 0.95) at load time, but defense-in-depth normalization
+ * here protects against a stale or hand-edited prefs file. Calling with
+ * `undefined` clears any prior override so a removed preference does not leak.
+ */
+async function applyCompactionThresholdOverride(ctx: ExtensionContext): Promise<void> {
+  try {
+    const { loadEffectiveGSDPreferences } = await import("../preferences.js");
+    const prefs = loadEffectiveGSDPreferences();
+    const raw = prefs?.preferences.context_management?.compaction_threshold_percent;
+    const value =
+      typeof raw === "number" && Number.isFinite(raw) && raw > 0 && raw < 1 ? raw : undefined;
+    ctx.setCompactionThresholdOverride(value);
+  } catch {
+    // Non-fatal: leave any existing override in place.
+  }
+}
+
 export function resolveNotificationStoreBasePath(cwd: string = process.cwd()): string {
   return resolveWorktreeProjectRoot(cwd);
 }
@@ -123,6 +143,7 @@ export function registerHooks(
     await resetAskUserQuestionsTurnCache();
     await syncServiceTierStatus(ctx);
     await applyDisabledModelProviderPolicy(ctx);
+    await applyCompactionThresholdOverride(ctx);
     // Skip MCP auto-prep when running inside an auto-worktree (see session_switch below).
     const { isInAutoWorktree } = await import("../auto-worktree.js");
     if (!isInAutoWorktree(process.cwd())) {
@@ -172,6 +193,7 @@ export function registerHooks(
     clearDiscussionFlowState(process.cwd());
     await syncServiceTierStatus(ctx);
     await applyDisabledModelProviderPolicy(ctx);
+    await applyCompactionThresholdOverride(ctx);
     // Skip MCP auto-prep when running inside an auto-worktree. The worktree
     // already has .mcp.json from createAutoWorktree, and re-running the writer
     // post-chdir rewrites the file mid-run (non-idempotent due to cwd-relative

package/src/resources/extensions/gsd/clean-root-preflight.ts

@@ -21,10 +21,34 @@ import { nativeHasChanges } from "./native-git-bridge.js";
 export interface PreflightResult {
   /** true when a stash was pushed and postflightPopStash should be called */
   stashPushed: boolean;
+  /** Unique marker embedded in the stash message for targeted restoration */
+  stashMarker?: string;
   /** human-readable summary of what happened (empty string for clean trees) */
   summary: string;
 }
 
+function findPreflightStashRef(basePath: string, milestoneId: string, stashMarker?: string): string | null {
+  const markerPrefix = `gsd-preflight-stash:${milestoneId}:`;
+  let fallbackRef: string | null = null;
+  try {
+    const list = execFileSync("git", ["stash", "list", "--format=%gd%x00%s"], {
+      cwd: basePath,
+      stdio: ["ignore", "pipe", "pipe"],
+      encoding: "utf-8",
+      env: GIT_NO_PROMPT_ENV,
+    });
+    for (const line of list.split("\n")) {
+      const [ref, subject] = line.split("\x00");
+      if (!ref || !subject) continue;
+      if (stashMarker && subject.includes(stashMarker)) return ref;
+      if (!fallbackRef && subject.includes(markerPrefix)) fallbackRef = ref;
+    }
+  } catch (err) {
+    logWarning("preflight", `stash list failed before restore: ${err instanceof Error ? err.message : String(err)}`);
+  }
+  return fallbackRef;
+}
+
 /**
  * Check the working tree for dirty files before a milestone merge.
  *
@@ -62,7 +86,8 @@ export function preflightCleanRoot(
 
   // Push the stash
   try {
-    execFileSync("git", ["stash", "push", "--include-untracked", "-m", "gsd-preflight-stash"], {
+    const stashMarker = `gsd-preflight-stash:${milestoneId}:${process.pid}:${Date.now()}:${process.hrtime.bigint().toString(36)}`;
+    execFileSync("git", ["stash", "push", "--include-untracked", "-m", `gsd-preflight-stash [${stashMarker}]`], {
       cwd: basePath,
       stdio: ["ignore", "pipe", "pipe"],
       encoding: "utf-8",
@@ -70,6 +95,7 @@ export function preflightCleanRoot(
     });
     return {
       stashPushed: true,
+      stashMarker,
       summary: `Stashed uncommitted changes before merge (milestone ${milestoneId}).`,
     };
   } catch (err) {
@@ -91,10 +117,19 @@ export function preflightCleanRoot(
 export function postflightPopStash(
   basePath: string,
   milestoneId: string,
+  stashMarker: string | undefined,
   notify: (message: string, level: "info" | "warning" | "error") => void,
 ): void {
+  let stashRef: string | null = null;
   try {
-    execFileSync("git", ["stash", "pop"], {
+    stashRef = findPreflightStashRef(basePath, milestoneId, stashMarker);
+    if (!stashRef) {
+      const msg = `No matching GSD preflight stash found for milestone ${milestoneId}; leaving stash list untouched.`;
+      logWarning("preflight", msg);
+      notify(msg, "warning");
+      return;
+    }
+    execFileSync("git", ["stash", "pop", stashRef], {
       cwd: basePath,
       stdio: ["ignore", "pipe", "pipe"],
       encoding: "utf-8",
@@ -104,7 +139,10 @@ export function postflightPopStash(
   } catch (err) {
     // Pop conflicts mean the merged code collides with the stashed changes.
     // Log a warning — the user needs to resolve manually, but the merge succeeded.
-    const msg = `git stash pop failed after merge of milestone ${milestoneId}: ${err instanceof Error ? err.message : String(err)}. Run "git stash pop" manually to restore your changes.`;
+    const restoreHint = stashRef
+      ? `Run "git stash pop ${stashRef}" or "git stash apply ${stashRef}" manually to restore the correct stash.`
+      : `Run "git stash list" to find the matching GSD preflight stash before restoring manually.`;
+    const msg = `git stash pop ${stashRef ?? ""}`.trim() + ` failed after merge of milestone ${milestoneId}: ${err instanceof Error ? err.message : String(err)}. ${restoreHint}`;
     logWarning("preflight", msg);
     notify(msg, "warning");
   }

package/src/resources/extensions/gsd/commands/dispatcher.ts

@@ -45,5 +45,11 @@ export async function handleGSDCommand(
 
   if (handled) return;
 
+  if (trimmed.includes(" ")) {
+    const { handleDo } = await import("../commands-do.js");
+    await handleDo(trimmed, ctx, pi);
+    return;
+  }
+
   ctx.ui.notify(`Unknown: /gsd ${trimmed}. Run /gsd help for available commands.`, "warning");
 }

package/src/resources/extensions/gsd/context-budget.ts

@@ -8,7 +8,12 @@
  * @see D001 (module location), D002 (200K fallback), D003 (section-boundary truncation)
  */
 
-import { type TokenProvider, getCharsPerToken } from "./token-counter.js";
+import {
+  type TokenProvider,
+  getCharsPerToken,
+  isAccurateCountingAvailable,
+  countTokensSync,
+} from "./token-counter.js";
 
 // ─── Budget ratio constants ──────────────────────────────────────────────────
 // Percentages of total context window allocated to each budget category.
@@ -32,6 +37,24 @@ const DEFAULT_CONTEXT_WINDOW = 200_000;
 /** Conservative effective context for Claude Code subscription routing (#4676) */
 const CLAUDE_CODE_EFFECTIVE_CONTEXT_WINDOW = 200_000;
 
+/**
+ * Cached empirical chars-per-token from a tiktoken probe, keyed by provider.
+ * countTokensSync's fallback path is provider-aware, so we cache per-provider
+ * to preserve that distinction once the encoder warms. The cl100k_base encoder
+ * itself gives a stable ratio for ASCII English so a single probe per provider
+ * key is sufficient. Empty map means "not yet probed" or "encoder unavailable".
+ */
+const _empiricalCharsPerTokenByProvider = new Map<string, number>();
+
+/**
+ * Test hook — clears the empirical chars-per-token cache so test cases that
+ * assert against the static char-ratio fallback aren't polluted by a prior
+ * tiktoken-warmed run in the same process. Production code must not call this.
+ */
+export function _resetEmpiricalCacheForTest(): void {
+  _empiricalCharsPerTokenByProvider.clear();
+}
+
 /** Percentage of context consumed before suggesting a continue-here checkpoint */
 const CONTINUE_THRESHOLD_PERCENT = 70;
 
@@ -101,7 +124,26 @@ export interface MinimalPreferences {
 export function computeBudgets(contextWindow: number, provider?: TokenProvider): BudgetAllocation {
   const effectiveWindow = contextWindow > 0 ? contextWindow : DEFAULT_CONTEXT_WINDOW;
   const charsPerToken = provider ? getCharsPerToken(provider) : CHARS_PER_TOKEN;
-  const totalChars = effectiveWindow * charsPerToken;
+
+  // Prefer the tiktoken encoder for total-char estimation when it has been
+  // warmed (initTokenCounter resolved). The cl100k_base ratio is stable for
+  // ASCII English, so probe once per provider and cache — computeBudgets is
+  // called multiple times per prompt build and the probe encode is otherwise
+  // wasted work.
+  let totalChars: number;
+  if (isAccurateCountingAvailable()) {
+    const providerKey = provider ?? "__default__";
+    let empirical = _empiricalCharsPerTokenByProvider.get(providerKey);
+    if (empirical === undefined) {
+      const probe = "the quick brown fox jumps over the lazy dog ".repeat(64);
+      const probeTokens = countTokensSync(probe, provider);
+      empirical = probeTokens > 0 ? probe.length / probeTokens : charsPerToken;
+      _empiricalCharsPerTokenByProvider.set(providerKey, empirical);
+    }
+    totalChars = effectiveWindow * empirical;
+  } else {
+    totalChars = effectiveWindow * charsPerToken;
+  }
 
   return {
     summaryBudgetChars: Math.floor(totalChars * SUMMARY_RATIO),

package/src/resources/extensions/gsd/crash-recovery.ts

@@ -38,6 +38,7 @@ import { _getAdapter, isDbAvailable } from "./gsd-db.js";
 import { gsdRoot, normalizeRealPath } from "./paths.js";
 import { atomicWriteSync } from "./atomic-write.js";
 import { effectiveLockFile } from "./session-lock.js";
+import { isInFlightRuntimePhase, listUnitRuntimeRecords, type AutoUnitRuntimeRecord } from "./unit-runtime.js";
 
 export interface LockData {
   pid: number;
@@ -103,10 +104,40 @@ function getLatestDispatchForWorker(workerId: string):
   return row ?? null;
 }
 
-function workerToLockData(worker: AutoWorkerRow): LockData {
+function latestInFlightRuntimeRecord(basePath: string): AutoUnitRuntimeRecord | null {
+  const records = listUnitRuntimeRecords(basePath).filter((record) =>
+    isInFlightRuntimePhase(record.phase),
+  );
+  if (records.length === 0) return null;
+  return records.sort((a, b) => {
+    const bTime = b.updatedAt || b.startedAt || 0;
+    const aTime = a.updatedAt || a.startedAt || 0;
+    return bTime - aTime;
+  })[0] ?? null;
+}
+
+function runtimeRecordToLockData(worker: AutoWorkerRow, record: AutoUnitRuntimeRecord, sessionFile?: string): LockData {
+  const startedAt = Number.isFinite(record.startedAt)
+    ? new Date(record.startedAt).toISOString()
+    : worker.started_at;
+  return {
+    pid: worker.pid,
+    startedAt: worker.started_at,
+    unitType: record.unitType,
+    unitId: record.unitId,
+    unitStartedAt: startedAt,
+    sessionFile,
+  };
+}
+
+function workerToLockData(basePath: string, worker: AutoWorkerRow): LockData {
   const dispatch = getLatestDispatchForWorker(worker.worker_id);
   const sessionFile =
     getRuntimeKv<string>("worker", worker.worker_id, SESSION_FILE_KV_KEY) ?? undefined;
+  if (!dispatch) {
+    const runtimeRecord = latestInFlightRuntimeRecord(basePath);
+    if (runtimeRecord) return runtimeRecordToLockData(worker, runtimeRecord, sessionFile);
+  }
   return {
     pid: worker.pid,
     startedAt: worker.started_at,
@@ -204,7 +235,7 @@ export function readCrashLock(basePath: string): LockData | null {
     try {
       const projectRoot = normalizeRealPath(basePath);
       const stale = findStaleWorkerForProject(projectRoot);
-      if (stale) return workerToLockData(stale);
+      if (stale) return workerToLockData(basePath, stale);
     } catch {
       // Fall through to the legacy lock-file compatibility path.
     }
@@ -260,25 +291,48 @@ export function formatCrashInfo(lock: LockData): string {
  */
 export function emitCrashRecoveredUnitEnd(basePath: string, lock: LockData): void {
   if (!lock.unitType || !lock.unitId || lock.unitType === "starting") return;
+  emitOpenUnitEndForUnit(basePath, lock.unitType, lock.unitId, "crash-recovered");
+}
 
+export function emitOpenUnitEndForUnit(
+  basePath: string,
+  unitType: string,
+  unitId: string,
+  status: string,
+  errorContext?: { message: string; category: string; stopReason?: string; isTransient?: boolean; retryAfterMs?: number },
+): boolean {
   try {
     const all = queryJournal(basePath);
 
     const starts = all.filter(
-      (e) => e.eventType === "unit-start" && e.data?.unitId === lock.unitId,
+      (e) =>
+        e.eventType === "unit-start" &&
+        e.data?.unitType === unitType &&
+        e.data?.unitId === unitId,
     );
-    if (starts.length === 0) return;
+    if (starts.length === 0) return false;
 
-    const lastStart = starts[starts.length - 1];
+    const lastStart = [...starts].reverse().find((start) => {
+      return !all.some(
+        (e) =>
+          e.eventType === "unit-end" &&
+          e.data?.unitType === unitType &&
+          e.data?.unitId === unitId &&
+          e.causedBy?.flowId === start.flowId &&
+          e.causedBy?.seq === start.seq,
+      );
+    });
+    if (!lastStart) return false;
 
     const alreadyClosed = all.some(
       (e) =>
         e.eventType === "unit-end" &&
-        e.data?.unitId === lock.unitId &&
+        e.data?.unitType === unitType &&
+        e.data?.unitId === unitId &&
         e.causedBy?.flowId === lastStart.flowId &&
         e.causedBy?.seq === lastStart.seq,
     );
-    if (alreadyClosed) return;
+    if (alreadyClosed) return false;
 
     const maxSeq = all
       .filter((e) => e.flowId === lastStart.flowId)
@@ -290,15 +344,18 @@ export function emitCrashRecoveredUnitEnd(basePath: string, lock: LockData): voi
       seq: maxSeq + 1,
       eventType: "unit-end",
       data: {
-        unitType: lock.unitType,
-        unitId: lock.unitId,
-        status: "crash-recovered",
+        unitType,
+        unitId,
+        status,
         artifactVerified: false,
+        ...(errorContext ? { errorContext } : {}),
       },
       causedBy: { flowId: lastStart.flowId, seq: lastStart.seq },
     });
+    return true;
   } catch {
     // Never throw from crash recovery path.
+    return false;
   }
 }
 

package/src/resources/extensions/gsd/db/unit-dispatches.ts

@@ -359,6 +359,47 @@ export function markCanceled(dispatchId: number, reason: string): void {
   ).run({ ":id": dispatchId, ":ended_at": now, ":reason": reason });
 }
 
+/**
+ * Best-effort signal/crash cleanup: cancel the latest active dispatch owned by
+ * a worker when the process is exiting before the normal loop can settle it.
+ */
+export function markLatestActiveForWorkerCanceled(workerId: string, reason: string): boolean {
+  if (!isDbAvailable()) return false;
+  const now = new Date().toISOString();
+  const db = _getAdapter()!;
+  const result = transaction(() => {
+    return db.prepare(
+      `UPDATE unit_dispatches
+       SET status = 'canceled', ended_at = :ended_at, exit_reason = :reason
+       WHERE id = (
+         SELECT id FROM unit_dispatches
+         WHERE worker_id = :worker_id
+           AND status IN ('pending','claimed','running')
+         ORDER BY id DESC
+         LIMIT 1
+       )`,
+    ).run({
+      ":ended_at": now,
+      ":reason": reason,
+      ":worker_id": workerId,
+    });
+  });
+  const changes =
+    typeof (result as { changes?: unknown }).changes === "number"
+      ? (result as { changes: number }).changes
+      : 0;
+  if (changes <= 0) return false;
+  insertAuditEvent({
+    eventId: randomUUID(),
+    traceId: workerId,
+    category: "orchestration",
+    type: "dispatch-canceled",
+    ts: now,
+    payload: { workerId, reason },
+  });
+  return true;
+}
+
 /**
  * Fetch the most recent N dispatches for a unit. Used by recordDispatchClaim
  * callers to compute attempt_n and by detect-stuck.ts (B3) to consult

package/src/resources/extensions/gsd/db-base-schema.ts

@@ -57,7 +57,8 @@ export function createBaseSchemaObjects(db: DbAdapter, hooks: BaseSchemaHooks):
       slice_id TEXT DEFAULT NULL,
       task_id TEXT DEFAULT NULL,
       full_content TEXT NOT NULL DEFAULT '',
-      imported_at TEXT NOT NULL DEFAULT ''
+      imported_at TEXT NOT NULL DEFAULT '',
+      content_hash TEXT DEFAULT NULL
     )
   `);
 
@@ -76,7 +77,8 @@ export function createBaseSchemaObjects(db: DbAdapter, hooks: BaseSchemaHooks):
       hit_count INTEGER NOT NULL DEFAULT 0,
       scope TEXT NOT NULL DEFAULT 'project',
       tags TEXT NOT NULL DEFAULT '[]',
-      structured_fields TEXT DEFAULT NULL
+      structured_fields TEXT DEFAULT NULL,
+      last_hit_at TEXT DEFAULT NULL
     )
   `);
 

package/src/resources/extensions/gsd/db-migration-steps.ts

@@ -416,6 +416,14 @@ export function applyMigrationV26MilestoneCommitAttributions(db: DbAdapter): voi
   db.exec("CREATE INDEX IF NOT EXISTS idx_milestone_commit_attr_milestone ON milestone_commit_attributions(milestone_id)");
 }
 
+export function applyMigrationV27ArtifactHash(db: DbAdapter): void {
+  ensureColumn(db, "artifacts", "content_hash", "ALTER TABLE artifacts ADD COLUMN content_hash TEXT DEFAULT NULL");
+}
+
+export function applyMigrationV28MemoryLastHitAt(db: DbAdapter): void {
+  ensureColumn(db, "memories", "last_hit_at", "ALTER TABLE memories ADD COLUMN last_hit_at TEXT DEFAULT NULL");
+}
+
 export interface MigrationV22Hooks {
   copyQualityGateRowsToRepairedTable(db: DbAdapter): void;
 }