pi-goal-list-loop-audit 0.27.5 → 0.27.6

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "pi-goal-list-loop-audit",
-  "version": "0.27.5",
-  "description": "Goal. Loop. Audit. Done. — a pi-coding-agent extension that supervises long-running work, with isolated auditor on each completion. Beat bamboozling by design: the auditor runs in a fresh session with no extensions, no skills, no editor — only the read tools needed to verify your goal.",
+  "version": "0.27.6",
+  "description": "Goal. Loop. Audit. Done. \u2014 a pi-coding-agent extension that supervises long-running work, with isolated auditor on each completion. Beat bamboozling by design: the auditor runs in a fresh session with no extensions, no skills, no editor \u2014 only the read tools needed to verify your goal.",
   "license": "MIT",
   "author": "dracon",
   "type": "module",
@@ -43,7 +43,9 @@
   },
   "scripts": {
     "check": "tsc --noEmit",
-    "test": "node --experimental-strip-types --test tests/*.test.ts"
+    "test": "bun test",
+    "test:node": "node --experimental-strip-types --test tests/*.test.ts",
+    "test:all": "bun test && tsc --noEmit"
   },
   "peerDependencies": {
     "@earendil-works/pi-agent-core": "*",

package/prompts/goal-loop-continuation.md

@@ -52,6 +52,7 @@ When the agent calls any of these, the orchestrator tracks the call and persists
 - **Default to subagents.** For any task that decomposes into independent chunks, spawn `Agent` subagents. Use `Explore` for read-only research, `general-purpose` for implementation, `Plan` for architecture. Spawn multiple in PARALLEL — don't serialise through your own context. You remain the single writer: synthesize findings and apply edits yourself.
 - **Eager continuation.** When in doubt, KEEP GOING on sub-tasks. If a subagent fails, retry with a different approach. Don't ask permission to continue — just continue. Pause only when you are genuinely blocked on information that does not exist in the repo, or the user explicitly pauses you.
 - **Bound every long command.** Wrap test suites, builds, and dev servers in `timeout <seconds>` (e.g. `timeout 120 bun test src/lib`). An unbounded command that hangs burns an hour; a bounded one burns two minutes and tells you it hung. If a command produces no output for many minutes, treat it as hung: kill it, diagnose why, rerun bounded.
+- **Chunk output near context-full.** When the conversation is heavy (long-running audit, deep debug, big rollout), prefer smaller commits, smaller tool outputs, and focused reasoning — one or two punchy paragraphs, one well-scoped tool call at a time. Don't try to fit a thousand lines of work into one reply. glla's 0.27.2 auto-continue fires on `stop_reason="length"` (the output-token cap) and will reschedule you anyway; pre-empting by chunking is cheaper than recovering from the cap. Save large file writes for their own turns; emit them only when you have the next read step ready to follow.
 
 ## WHEN THE AUDITOR DISAPPROVES