@openlines/opl-pi-sht 0.2.2 → 0.2.4

package/README.md

@@ -14,6 +14,14 @@
 
 A portable collection of various Pi coding agent extensions. Repository directories and config files use `opl-`; established Pi-facing commands and tool names stay compatible.
 
+<div align="center">
+
+>
+> ## v0.2.4 (22 Sept 2026) - Pi 0.87 host-loader smoke test now runs in CI<br/>see [CHANGELOG.md](CHANGELOG.md) for more details.
+>
+
+</div>
+
 ## Installation
 
 ### Pi package
@@ -105,7 +113,7 @@ Cold prompt-cache write, measured /init session (opl-modes lazy tools + MCP adap
 
 ### Run the agent without babysitting it
 
-- **`opl-modes`** chat and plan modes swap the active toolset for read-only lists and gate Bash to safe inspection patterns **per shell segment**, so `cat f && node -e '...'`, `cat x & rm -rf /tmp/x`, and `echo "$(node -e ...)"` can no longer ride the first command's allowance. Destructive checks still fire inside otherwise-safe commands (anchored to command position, so `du -sh` and `find . -name '*.sh'` stay allowed; `find -delete`, `find -fprint`, `git log --output`, `sort -o`, `npm audit fix`, `git clean`, `sudo`, and quote-obfuscated `r"m"`/`-del"ete"` are blocked; `env`/`printenv` are not safe-listed). The plan to execute lifecycle keeps exploration and mutation cleanly separated. Add custom modes (like below) for your workflow needs.
+- **`opl-modes`** chat and plan modes swap the active toolset for read-only lists and gate Bash to safe inspection patterns **per shell segment**, so `cat f && node -e '...'`, `cat x & rm -rf /tmp/x`, and `echo "$(node -e ...)"` can no longer ride the first command's allowance. Destructive checks still fire inside otherwise-safe commands (anchored to command position, so `du -sh` and `find . -name '*.sh'` stay allowed; `find -delete`, `find -fprint`, `git log --output`, `sort -o`, `npm audit fix`, `git clean`, `sudo`, and quote-obfuscated `r"m"`/`-del"ete"` are blocked; `env`/`printenv` are not safe-listed). The plan to execute lifecycle keeps exploration and mutation cleanly separated. Add custom modes (like below) for your workflow needs. Execute-mode auto-exit needs pi >= 0.87.0 (the `agent_before_settle` boundary).
 ![custom mode sample](images/ss-mode-custom.png)
 - `load_tools` activation is bounded by the current mode, so a read-only mode cannot be tricked into enabling a write-capable tool.
 - **`opl-guardian`** stops a malformed provider tool-call record from poisoning the session: it removes calls missing an ID or name before Pi persists or replays them, while preserving dropped records in `err/guardian.jsonl` for an upstream report.
@@ -221,4 +229,4 @@ A Pi package (npm or Git) still needs the one-time `npx playwright install chrom
 npm test
 ```
 
-Run one extension suite with `npm run test:opl-<name>` for `browser`, `footer`, `guardian`, `init`, `input`, `modes`, `questionnaire`, `todo`, `webaccess`, `simplebench`, or `ctxtrim`. Every helper, functional, and selected-entrypoint smoke check uses Bun's named-test reporter; output includes per-test status, timings, and pass/fail totals. Functional tests cover deterministic helpers where practical; smoke tests bundle entrypoints and parse config. They do not test live TUI behavior, provider credentials, network access, or PDF extraction.
+Run one extension suite with `npm run test:opl-<name>` for `browser`, `footer`, `guardian`, `init`, `input`, `modes`, `questionnaire`, `todo`, `webaccess`, `simplebench`, or `ctxtrim`. `npm run test:pi-host` uses Pi 0.87.0's real extension loader to load every entrypoint and assert no loader errors. Every helper, functional, and selected-entrypoint smoke check uses Bun's named-test reporter; output includes per-test status, timings, and pass/fail totals. Functional tests cover deterministic helpers where practical; smoke tests bundle entrypoints and parse config. They do not test live TUI behavior, provider credentials, network access, or PDF extraction.

package/extensions/opl-modes/README.md

@@ -11,7 +11,7 @@ Unified mode manager for Pi. It provides normal, read-only chat, read-only plann
 - `--chat` and `--plan` start Pi in the corresponding read-only mode.
 - The configured cycle shortcut rotates through enabled visible modes. Execute mode is excluded from cycling because it requires an active plan. The default `shift+tab` is also Pi's built-in `app.thinking.cycle`, so both fire on one press; rebind either action in `~/.pi/agent/keybindings.json` (or pick another `shortcuts.cycleMode`) if you want them separate.
 
-Plans are Markdown files under `.pi/plans/` with the `plan-` filename prefix. A plan name must contain at least one letter or digit, so `/plan .` or `/plan --` is rejected instead of producing an untitled `plan-.md`. `plan_complete` is available in execute mode and in any mode that sets `allowPlanComplete`. On completion, the plan file is deleted when `cleanup.cleanupOnComplete` is enabled. If execution ends without `plan_complete`, execute mode is exited automatically — but only when a turn actually finished: an aborted (ESC) or errored turn keeps execute mode active so the plan can be resumed.
+Plans are Markdown files under `.pi/plans/` with the `plan-` filename prefix. A plan name must contain at least one letter or digit, so `/plan .` or `/plan --` is rejected instead of producing an untitled `plan-.md`. `plan_complete` is available in execute mode and in any mode that sets `allowPlanComplete`. On completion, the plan file is deleted when `cleanup.cleanupOnComplete` is enabled. If execution ends without `plan_complete`, execute mode is exited automatically at Pi's `agent_before_settle` boundary (added in Pi 0.87.0) — but only when the run settled as `completed`: an aborted (ESC) or errored run keeps execute mode active so the plan can be resumed. On Pi < 0.87.0 this auto-exit is unavailable because the boundary is never emitted; `plan_complete` still exits the mode on any version.
 
 ## Extension features
 

package/extensions/opl-modes/index.ts

@@ -23,6 +23,7 @@ import type {
   ToolCallEventResult,
   ToolResultEvent,
   AgentEndEvent,
+  AgentBeforeSettleEvent,
 } from "@earendil-works/pi-coding-agent";
 import { DynamicBorder } from "@earendil-works/pi-coding-agent";
 import type { Model } from "@earendil-works/pi-ai";
@@ -668,26 +669,23 @@ export default function modeSwitcher(pi: ExtensionAPI) {
     enterOffMode(ctx, "Plan implemented. Plan mode OFF.");
   });
 
-  // ─── Event: agent_end (extract plan text in PLAN mode; auto-exit execute) ───
-
-  pi.on("agent_end", async (event: AgentEndEvent, ctx: ExtensionContext) => {
-    // If plan_complete was never called, exit execute mode automatically.
-    // (If it was called, mode is already "off" here — this check is a no-op.)
-    if (getMode() === "execute") {
-      // An aborted turn (ESC) is a pause, not a finished execution: stay in execute mode
-      // so the plan can be resumed instead of silently dropping out mid-plan. Pi emits an
-      // assistant message with stopReason "aborted" even when the abort lands before the
-      // first token, so there is always a message to read here.
-      const lastAssistant = [...event.messages].reverse().find((m) => m.role === "assistant") as
-        | { stopReason?: string }
-        | undefined;
-      // Only a turn that actually finished counts as done: "aborted"/"error" (and a missing
-      // assistant message) are pauses, so execute mode survives ESC and provider failures.
-      const reason = lastAssistant?.stopReason;
-      if (reason && reason !== "aborted" && reason !== "error") enterOffMode(ctx, "Execution complete. Mode OFF.");
-      return;
+  // ─── Event: agent_before_settle (auto-exit execute when the run is truly done) ───
+
+  // Pi 0.87 boundary: fires after any automatic retry, compaction-and-retry, or queued
+  // follow-up work, so execute mode is not dropped mid-plan at an intermediate agent_end.
+  pi.on("agent_before_settle", async (event: AgentBeforeSettleEvent, ctx: ExtensionContext) => {
+    // If plan_complete was never called, exit execute mode automatically once Pi has fully
+    // settled. (If it was called, mode is already "off" here — this check is a no-op.)
+    // "aborted" (ESC) and "error" (provider failure) are pauses, not finished executions;
+    // only a completed run exits execute mode.
+    if (getMode() === "execute" && event.outcome === "completed") {
+      enterOffMode(ctx, "Execution complete. Mode OFF.");
     }
+  });
+
+  // ─── Event: agent_end (extract plan text in PLAN mode) ───
 
+  pi.on("agent_end", async (event: AgentEndEvent, ctx: ExtensionContext) => {
     if (getMode() !== "plan") return;
     if (!ctx.hasUI) return;
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@openlines/opl-pi-sht",
-  "version": "0.2.2",
+  "version": "0.2.4",
   "description": "opl-pi-sht (shouldHaveThat) Pi coding-agent extension kit: token-efficient context, safe modes, fingerprinted /init, model benchmarking, web access, and browser automation.",
   "repository": {
     "type": "git",
@@ -40,7 +40,7 @@
   },
   "type": "module",
   "scripts": {
-    "test": "npm run test:opl-browser && npm run test:opl-footer && npm run test:opl-guardian && npm run test:opl-init && npm run test:opl-input && npm run test:opl-modes && npm run test:opl-questionnaire && npm run test:opl-todo && npm run test:opl-webaccess && npm run test:opl-simplebench && npm run test:opl-ctxtrim",
+    "test": "npm run test:opl-browser && npm run test:opl-footer && npm run test:opl-guardian && npm run test:opl-init && npm run test:opl-input && npm run test:opl-modes && npm run test:opl-questionnaire && npm run test:opl-todo && npm run test:opl-webaccess && npm run test:opl-simplebench && npm run test:opl-ctxtrim && npm run test:pi-host",
     "test:opl-browser": "bun test tests/opl-browser-helpers.test.mjs && OPL_EXTENSION=opl-browser bun test tests/extension-smoke.test.mjs",
     "test:opl-footer": "bun test tests/opl-footer-helpers.test.mjs && OPL_EXTENSION=opl-footer bun test tests/extension-smoke.test.mjs",
     "test:opl-guardian": "bun test tests/opl-guardian.test.mjs && OPL_EXTENSION=opl-guardian bun test tests/extension-smoke.test.mjs",
@@ -51,6 +51,10 @@
     "test:opl-todo": "bun test tests/opl-todo-config.test.mjs tests/opl-todo-render.test.mjs && OPL_EXTENSION=opl-todo bun test tests/extension-smoke.test.mjs",
     "test:opl-webaccess": "bun test tests/opl-webaccess-helpers.test.mjs && OPL_EXTENSION=opl-webaccess bun test tests/extension-smoke.test.mjs",
     "test:opl-simplebench": "bun test tests/opl-simplebench.test.ts && OPL_EXTENSION=opl-simplebench bun test tests/extension-smoke.test.mjs",
-    "test:opl-ctxtrim": "bun test tests/opl-ctxtrim.test.ts && OPL_EXTENSION=opl-ctxtrim bun test tests/extension-smoke.test.mjs"
+    "test:opl-ctxtrim": "bun test tests/opl-ctxtrim.test.ts && OPL_EXTENSION=opl-ctxtrim bun test tests/extension-smoke.test.mjs",
+    "test:pi-host": "bun test tests/pi-host-loader.test.mjs"
+  },
+  "devDependencies": {
+    "@earendil-works/pi-coding-agent": "0.87.0"
   }
 }