selftune 0.2.13 → 0.2.14

package/cli/selftune/schedule.ts

@@ -19,6 +19,25 @@ import { parseArgs } from "node:util";
 
 import { DEFAULT_CRON_JOBS } from "./cron/setup.js";
 
+// ---------------------------------------------------------------------------
+// Binary resolution — launchd runs with minimal PATH, so we need full paths
+// ---------------------------------------------------------------------------
+
+/**
+ * Resolve the absolute path to the `selftune` binary.
+ * 1. Bun.which (Bun-native, no spawn)
+ * 2. Fallback: ~/.bun/bin/selftune (common bun global install location)
+ */
+export function resolveSelftuneBin(): string {
+  try {
+    const resolved = Bun.which("selftune");
+    if (resolved) return resolved;
+  } catch {
+    // Bun.which may throw in edge cases — fall through
+  }
+  return join(homedir(), ".bun", "bin", "selftune");
+}
+
 // ---------------------------------------------------------------------------
 // Schedule definitions — derived from the shared DEFAULT_CRON_JOBS
 // ---------------------------------------------------------------------------
@@ -137,6 +156,8 @@ function toSystemdExecStart(command: string): string {
 // ---------------------------------------------------------------------------
 
 export function generateCrontab(): string {
+  const resolvedBin = resolveSelftuneBin();
+  const home = homedir();
   const lines = [
     "# selftune automation — add to your crontab with: crontab -e",
     "#",
@@ -144,10 +165,13 @@ export function generateCrontab(): string {
     "# status remains a reporting job; orchestrate handles sync, candidate",
     "# selection, low-risk description evolution, and watch/rollback follow-up.",
     "#",
+    `PATH=${home}/.bun/bin:/opt/homebrew/bin:/usr/local/bin:/usr/bin:/bin`,
+    "",
   ];
   for (const entry of SCHEDULE_ENTRIES) {
+    const resolvedCommand = entry.command.replace(/\bselftune\b/g, resolvedBin);
     lines.push(`# ${entry.description}`);
-    lines.push(`${entry.schedule}  ${entry.command}`);
+    lines.push(`${entry.schedule}  ${resolvedCommand}`);
     lines.push("");
   }
   return lines.join("\n");
@@ -177,10 +201,17 @@ export function mergeManagedCrontab(existing: string, managedContent: string): s
   return `${withoutExistingBlock}\n\n${managedBlock}`;
 }
 
-function buildLaunchdDefinition(entry: ScheduleEntry): { label: string; content: string } {
+function buildLaunchdDefinition(
+  entry: ScheduleEntry,
+  binPath?: string,
+): { label: string; content: string } {
   const label = `com.selftune.${entry.name.replace("selftune-", "")}`;
-  const args = toLaunchdArgs(entry.command);
+  const resolvedBin = binPath ?? resolveSelftuneBin();
+  // Replace bare `selftune` with the resolved absolute path
+  const resolvedCommand = entry.command.replace(/\bselftune\b/g, resolvedBin);
+  const args = toLaunchdArgs(resolvedCommand);
   const schedule = cronToLaunchdSchedule(entry.schedule);
+  const home = homedir();
 
   return {
     label,
@@ -198,6 +229,13 @@ function buildLaunchdDefinition(entry: ScheduleEntry): { label: string; content:
 <dict>
   <key>Label</key>
   <string>${label}</string>
+  <key>EnvironmentVariables</key>
+  <dict>
+    <key>PATH</key>
+    <string>${home}/.bun/bin:/opt/homebrew/bin:/usr/local/bin:/usr/bin:/bin</string>
+    <key>HOME</key>
+    <string>${home}</string>
+  </dict>
   <key>ProgramArguments</key>
   <array>
 ${args}
@@ -222,14 +260,20 @@ export function generateLaunchd(): string {
   return plists.join("\n\n");
 }
 
-function buildSystemdDefinition(entry: ScheduleEntry): {
+function buildSystemdDefinition(
+  entry: ScheduleEntry,
+  binPath?: string,
+): {
   baseName: string;
   timerContent: string;
   serviceContent: string;
 } {
   const unitName = entry.name;
   const calendar = cronToOnCalendar(entry.schedule);
-  const execStart = toSystemdExecStart(entry.command);
+  const resolvedBin = binPath ?? resolveSelftuneBin();
+  const resolvedCommand = entry.command.replace(/\bselftune\b/g, resolvedBin);
+  const execStart = toSystemdExecStart(resolvedCommand);
+  const home = homedir();
 
   return {
     baseName: unitName,
@@ -247,6 +291,8 @@ Description=${entry.description}
 
 [Service]
 Type=oneshot
+Environment="PATH=${home}/.bun/bin:/usr/local/bin:/usr/bin:/bin"
+Environment="HOME=${home}"
 ExecStart=${execStart}`,
   };
 }

package/cli/selftune/utils/jsonl.ts

@@ -90,6 +90,8 @@ export function readJsonlFrom<T = Record<string, unknown>>(
  * Append a single record to a JSONL file. Creates parent directories if needed.
  * When logType is provided, validates the record and logs warnings on failure
  * but still writes the record (fail-open: hooks must never block).
+ *
+ * @deprecated Phase 3: JSONL writes removed. Retained for materializer/test utilities only.
  */
 export function appendJsonl(path: string, record: unknown, logType?: LogType): void {
   if (logType) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "selftune",
-  "version": "0.2.13",
+  "version": "0.2.14",
   "description": "Self-improving skills CLI for AI agents",
   "keywords": [
     "agent",
@@ -73,12 +73,14 @@
     "prepublishOnly": "bun run sync-version && bun run build:dashboard",
     "typecheck:dashboard": "cd apps/local-dashboard && bunx tsc --noEmit",
     "check": "bun run lint && bun run format:check && bun run lint:arch && bun run typecheck:dashboard && bun run test",
+    "prepare": "bunx lefthook install || true",
     "start": "bun run cli/selftune/index.ts --help"
   },
   "dependencies": {
     "@selftune/telemetry-contract": "file:packages/telemetry-contract"
   },
   "devDependencies": {
+    "@evilmartians/lefthook": "^1.13.6",
     "@types/bun": "^1.1.0",
     "oxfmt": "^0.41.0",
     "oxlint": "^1.56.0"

package/packages/ui/src/components/RecentActivityFeed.tsx

@@ -0,0 +1,86 @@
+import { ZapIcon, CircleDotIcon } from "lucide-react";
+
+import { timeAgo } from "../lib/format";
+import { Badge } from "../primitives/badge";
+import { Card, CardContent, CardDescription, CardHeader, CardTitle } from "../primitives/card";
+
+export interface RecentActivityItem {
+  timestamp: string;
+  session_id: string;
+  skill_name: string;
+  query: string;
+  triggered: boolean;
+  is_live: boolean;
+}
+
+export function RecentActivityFeed({ items }: { items: RecentActivityItem[] }) {
+  if (items.length === 0) {
+    return (
+      <Card>
+        <CardHeader>
+          <CardTitle className="flex items-center gap-2 text-sm">
+            <ZapIcon className="size-4" />
+            Recent Activity
+          </CardTitle>
+        </CardHeader>
+        <CardContent>
+          <p className="text-sm text-muted-foreground text-center py-8">
+            No recent skill invocations
+          </p>
+        </CardContent>
+      </Card>
+    );
+  }
+
+  return (
+    <Card>
+      <CardHeader>
+        <CardTitle className="flex items-center gap-2 text-sm">
+          <ZapIcon className="size-4" />
+          Recent Activity
+        </CardTitle>
+        <CardDescription>Latest skill invocations across sessions</CardDescription>
+      </CardHeader>
+      <CardContent className="space-y-2.5">
+        {items.slice(0, 20).map((item, i) => (
+          <div
+            key={`${item.session_id}-${item.skill_name}-${i}`}
+            className="flex gap-3 rounded-md p-1.5"
+          >
+            <div
+              className={`mt-1 size-2 shrink-0 rounded-full ${
+                item.triggered ? "bg-emerald-500" : "bg-muted-foreground/40"
+              }`}
+            />
+            <div className="flex-1 min-w-0 space-y-0.5">
+              <div className="flex items-center gap-2 flex-wrap">
+                <span className="text-xs font-medium truncate">{item.skill_name}</span>
+                {item.is_live && (
+                  <Badge variant="outline" className="h-4 px-1 text-[10px] gap-1">
+                    <CircleDotIcon className="size-2.5 text-emerald-500" />
+                    live
+                  </Badge>
+                )}
+                {item.triggered ? (
+                  <Badge variant="default" className="h-4 px-1 text-[10px]">
+                    triggered
+                  </Badge>
+                ) : (
+                  <Badge variant="secondary" className="h-4 px-1 text-[10px]">
+                    checked
+                  </Badge>
+                )}
+                <span className="text-[10px] text-muted-foreground font-mono ml-auto shrink-0">
+                  {timeAgo(item.timestamp)}
+                </span>
+              </div>
+              {item.query && (
+                <p className="text-xs text-muted-foreground line-clamp-1 font-mono">{item.query}</p>
+              )}
+            </div>
+          </div>
+        ))}
+      </CardContent>
+    </Card>
+  );
+}

package/packages/ui/src/components/index.ts

@@ -3,5 +3,6 @@ export { EvidenceViewer } from "./EvidenceViewer";
 export { EvolutionTimeline } from "./EvolutionTimeline";
 export { InfoTip } from "./InfoTip";
 export { OrchestrateRunsPanel } from "./OrchestrateRunsPanel";
+export { RecentActivityFeed } from "./RecentActivityFeed";
 export { SectionCards } from "./section-cards";
 export { SkillHealthGrid } from "./skill-health-grid";

package/packages/ui/src/components/section-cards.tsx

@@ -21,6 +21,7 @@ interface SectionCardsProps {
   pendingCount: number;
   evidenceCount: number;
   hasEvolution?: boolean;
+  activeSessionsCount?: number;
 }
 
 export function SectionCards({
@@ -31,6 +32,7 @@ export function SectionCards({
   pendingCount,
   evidenceCount,
   hasEvolution = true,
+  activeSessionsCount = 0,
 }: SectionCardsProps) {
   const passRateStr = avgPassRate !== null ? `${Math.round(avgPassRate * 100)}%` : "--";
   const passRateGood = avgPassRate !== null && avgPassRate >= 0.7;
@@ -118,6 +120,17 @@ export function SectionCards({
           <CardTitle className="text-2xl font-semibold tabular-nums @[250px]/card:text-3xl">
             {sessionsCount}
           </CardTitle>
+          {activeSessionsCount > 0 && (
+            <CardAction>
+              <Badge variant="outline" className="gap-1.5">
+                <span className="relative flex size-2">
+                  <span className="absolute inline-flex size-full animate-ping rounded-full bg-emerald-400 opacity-75" />
+                  <span className="relative inline-flex size-2 rounded-full bg-emerald-500" />
+                </span>
+                {activeSessionsCount} in progress
+              </Badge>
+            </CardAction>
+          )}
         </CardHeader>
       </Card>
 

package/skill/SKILL.md

@@ -12,7 +12,7 @@ description: >
   even if they don't say "selftune" explicitly.
 metadata:
   author: selftune-dev
-  version: 0.2.13
+  version: 0.2.14
   category: developer-tools
 ---
 

package/skill/Workflows/Orchestrate.md

@@ -31,12 +31,14 @@ selftune orchestrate
 | `--max-skills <n>`          | Cap how many candidates are processed in one run           | `5`        |
 | `--recent-window <hours>`   | Window for post-deploy watch/rollback checks               | `48`       |
 | `--sync-force`              | Force a full source replay before candidate selection      | Off        |
+| `--max-auto-grade <n>`      | Max ungraded skills to auto-grade per run (0 to disable)   | `5`        |
 | `--loop`                    | Run as a long-lived process that cycles continuously       | Off        |
 | `--loop-interval <seconds>` | Pause between cycles (minimum 60)                          | `3600`     |
 
 ## Default Behavior
 
 - Sync source-truth telemetry first
+- Auto-grade up to 5 ungraded skills that have session data (enables evolution on first run after ingest)
 - Prioritize critical/warning/ungraded skills with real missed-query signal
 - Deploy validated low-risk description changes automatically
 - Watch recent deployments and roll back regressions automatically
@@ -78,10 +80,11 @@ A phased decision report printed to stderr so you can see exactly what happened
 
 1. **Phase 1: Sync** — which sources were scanned, how many records synced, repair counts
 2. **Phase 2: Status** — skill count, system health, breakdown by status category
-3. **Phase 3: Skill Decisions** — each skill with its action (EVOLVE / WATCH / SKIP) and reason
-4. **Phase 4: Evolution Results** — validation pass-rate changes (before → after), deployment status
-5. **Phase 5: Watch** — post-deploy monitoring with alert and rollback indicators
-6. **Summary** — evaluated/deployed/watched/skipped counts and elapsed time
+3. **Auto-grade** — how many ungraded skills were graded (logged to stderr, included in summary)
+4. **Phase 3: Skill Decisions** — each skill with its action (EVOLVE / WATCH / SKIP) and reason
+5. **Phase 4: Evolution Results** — validation pass-rate changes (before → after), deployment status
+6. **Phase 5: Watch** — post-deploy monitoring with alert and rollback indicators
+7. **Summary** — auto-graded/evaluated/deployed/watched/skipped counts and elapsed time
 
 A mode banner at the top shows DRY RUN, REVIEW, or AUTONOMOUS with rerun hints when applicable.
 
@@ -140,9 +143,10 @@ In autonomous mode, orchestrate calls sub-workflows in this fixed order:
 
 1. **Sync** — refresh source-truth telemetry across all supported agents (`selftune sync`)
 2. **Status** — compute skill health using existing grade results (reads `grading.json` outputs from previous sessions)
-3. **Evolve** — run evolution on selected candidates (pre-flight is skipped, cheap-loop mode enabled, defaults used)
-4. **Watch** — monitor recently evolved skills (auto-rollback enabled by default, `--recent-window` hours lookback)
-5. **Alpha Upload** — if enrolled in the alpha program (`config.alpha.enrolled === true`) and an API key is configured, stage new canonical records (sessions, invocations, evolution evidence, orchestrate runs) into `canonical_upload_staging`, build V2 push payloads, and flush to the cloud API (`POST /api/v1/push`) with Bearer auth. Fail-open: upload errors never block the orchestrate loop. Respects `--dry-run`.
+3. **Auto-grade** — grade up to `--max-auto-grade` (default 5) ungraded skills that have session data but no grades yet. Skipped during `--dry-run` (grading makes LLM calls). After grading, status is recomputed so candidate selection sees updated grades. Fail-open: individual grading errors are logged but never block the loop.
+4. **Evolve** — run evolution on selected candidates (pre-flight is skipped, cheap-loop mode enabled, defaults used)
+5. **Watch** — monitor recently evolved skills (auto-rollback enabled by default, `--recent-window` hours lookback)
+6. **Alpha Upload** — if enrolled in the alpha program (`config.alpha.enrolled === true`) and an API key is configured, stage new canonical records (sessions, invocations, evolution evidence, orchestrate runs) into `canonical_upload_staging`, build V2 push payloads, and flush to the cloud API (`POST /api/v1/push`) with Bearer auth. Fail-open: upload errors never block the orchestrate loop. Respects `--dry-run`.
 
 Between candidate selection and evolution, orchestrate checks for
 **cross-skill eval set overlap**. When two or more evolution candidates

package/skill/Workflows/Schedule.md

@@ -53,6 +53,17 @@ Outputs examples for all three scheduling systems (cron, launchd, systemd).
 
 `selftune schedule` is now an alias for `selftune cron`. Both commands are interchangeable. See `Workflows/Cron.md` for the full cron workflow reference.
 
+## PATH Resolution (All Platforms)
+
+All three scheduling formats resolve the absolute path to the `selftune` binary
+(via `Bun.which` with a `~/.bun/bin/selftune` fallback) and set explicit PATH
+environment variables. This prevents silent failures from minimal default
+environments that don't include homebrew, bun, or node binary locations.
+
+- **launchd** — Injects an `EnvironmentVariables` dict with PATH and HOME into each plist.
+- **systemd** — Adds `Environment="PATH=..."` and `Environment="HOME=..."` to each service unit.
+- **cron** — Prepends a `PATH=...` declaration at the top of the generated crontab.
+
 ## Common Patterns
 
 - **User wants quick setup on a Linux server** -- Run `selftune schedule --install --format cron`.

package/skill/references/logs.md

@@ -1,14 +1,17 @@
 # Log Format Reference
 
-selftune writes raw legacy logs plus a canonical event log. This reference
-describes each format in detail for the skill to use when parsing sessions,
-audit trails, and cloud-ingest exports.
-
-> **Note:** JSONL files are now backup/recovery only. SQLite (`~/.selftune/selftune.db`)
-> is the sole operational store for all runtime reads. JSONL writes are retained for
-> append-only durability, but all dashboard queries, hook reads, grading, monitoring,
-> and upload staging read from SQLite. JSONL reads only occur when custom log paths
-> are provided (e.g., `--telemetry-log`, `--skill-log`) for test isolation.
+selftune uses SQLite as its sole write target and operational store. This
+reference describes the legacy JSONL log formats that remain on disk for
+disaster recovery and export, plus the canonical event schema.
+
+> **Important (Phase 3 complete):** JSONL writes have been removed from all hooks,
+> ingestors, and normalization pipelines. New data is written exclusively to SQLite
+> (`~/.selftune/selftune.db`). Existing JSONL files are retained on disk but only
+> contain pre-cutover history. The materializer (`localdb/materialize.ts`) can
+> rebuild SQLite from these files but only for data written before Phase 3.
+> Post-cutover recovery requires `selftune export` snapshots or SQLite backups.
+> The file formats below are preserved as a reference for the materializer and
+> export tooling.
 
 ---
 
@@ -54,11 +57,11 @@ One JSON record per line. Each record is one completed agent session.
 
 ## ~/.claude/skill_usage_log.jsonl
 
-> **Deprecated.** The `skill_usage` and `skill_invocations` data paths have been
+> **Legacy.** The `skill_usage` and `skill_invocations` data paths have been
 > consolidated into a single `skill_invocations` table in SQLite. This JSONL file
-> is still written by hooks for backward compatibility, but the dashboard and
-> queries now read exclusively from `skill_invocations`. New consumers should use
-> the SQLite table via `localdb/queries.ts`.
+> is no longer written (Phase 3). The dashboard and all queries read exclusively
+> from `skill_invocations`. New consumers should use the SQLite table via
+> `localdb/queries.ts`.
 
 One record per skill trigger event. Populated by skill-eval.ts (PostToolUse hook).
 
@@ -208,10 +211,10 @@ This is operational state, not an analytics source of truth.
 
 ## ~/.claude/improvement_signals.jsonl
 
-One record per detected improvement signal. Written by `prompt-log.ts` when a
-user correction or explicit skill request is detected. Read by the orchestrator
-for signal-aware candidate selection, and by `session-stop.ts` to decide whether
-to spawn a reactive orchestrate run.
+One record per detected improvement signal. Previously written by `prompt-log.ts`;
+now written directly to SQLite (`improvement_signals` table). This JSONL file is
+no longer appended to (Phase 3). Read by the orchestrator for signal-aware
+candidate selection via SQLite queries.
 
 ```json
 {
@@ -225,10 +228,8 @@ to spawn a reactive orchestrate run.
 ```
 
 Signal records are append-only. When an orchestrate run processes a signal,
-the original record remains unchanged and the orchestrator rewrites the file
-with `consumed: true` set on processed entries. This is the one exception
-to strict append-only semantics in the log system — the rewrite is atomic
-and race-protected by the orchestrate lockfile.
+it sets `consumed: true` via `updateSignalConsumed()` in SQLite. The JSONL
+format below is retained as a reference for the materializer and export.
 
 Consumed signal example: