@d3ara1n/pi-subagent 1.4.0 → 1.5.1

package/README.md

@@ -2,7 +2,7 @@
 
 Role-based subagent orchestration for [pi](https://github.com/earendil-works/pi).
 
-Provides a `subagent_delegate` tool that lets the main model offload tasks to specialized pi child processes with configurable model roles, real-time TUI progress, and AI-generated summaries. Runs can be foreground (blocking) or background (asynchronous, collected later via `subagent_wait`/`subagent_check`, cancellable via `subagent_cancel`).
+Provides a `subagent_delegate` tool that lets the main model offload tasks to specialized pi child processes with configurable model roles, real-time TUI progress, and AI-generated summaries. Runs can be foreground (blocking) or background (asynchronous, collected later via `subagent_wait`/`subagent_check`, cancellable via `subagent_cancel`). A centered live view (`/subagent:view`) shows every run's activity feed as it happens, and mid-run corrections can be queued into a running subagent from the view's input box or via `subagent_steer`.
 
 ## Design Philosophy
 
@@ -54,16 +54,18 @@ This means:
 
 | Command | Description |
 |---------|-------------|
-| `/subagent:view` | Open the live activity view: a continuous feed of every run's thinking, tool calls, and streamed output — with an input box to steer a running subagent mid-flight |
+| `/subagent:view` | Open the live view: a tabbed overlay showing one run's full activity feed at a time, with an input box to steer the focused run |
 | `/subagent:doctor` | Diagnose pi invocation, model-role resolution, configuration, and role references |
 | `/subagent:status` | List background runs (active + collected) and their current state |
 | `/subagent:cancel <id\|all> [reason]` | Cancel a live background run (or every live run); the optional reason is recorded with the run |
 
 ### Live view (`/subagent:view`)
 
-A continuous, append-only list: each entry is static text with a state icon; running entries carry an animated ellipsis (`.` → `..` → `...`) and freeze in place when they finish — position never changes. Multiple runs stack (one header line per run); streamed assistant text grows in place as the run's last line and freezes at the turn boundary.
+A centered overlay covering most of the screen. A tab row across the top lists every run (icon · id · role); `Tab` cycles the focused run, and the rest of the viewport belongs to it alone — its complete activity feed, tail-capped to the visible area with a `⋮ earlier activity` marker when older entries roll off.
 
-The bottom of the panel has a steer input box: type a correction and press Enter to queue it into the focused running subagent (Tab cycles targets when several are running). The message is delivered after the child finishes its current tool batch, before its next LLM call — the run keeps its progress. Esc closes the panel.
+The feed itself is a continuous, append-only list: each entry is static text with a state icon, and the only animated thing is the ellipsis on a running entry (`.` → `..` → `...`). Finishing freezes an entry in place — its position never changes, only the icon flips. Streamed assistant text grows in place as the run's last line and settles into plain terminal-colored text at the turn boundary. Both foreground and background runs appear here; a foreground run stays listed while its delegate call blocks the main agent.
+
+Below the feed sits a steer input box: type a correction and press Enter to queue it into the focused run (only while it is running). The message appears immediately in the feed as an `↩ steer:` entry and is delivered to the child after its current tool batch, before its next LLM call — the run keeps its progress. `Esc` closes the overlay.
 
 ## Dependencies
 
@@ -189,7 +191,7 @@ Three execution properties, kept separate:
 
 - **Foreground** (default): the call blocks until the run finishes and returns the final output directly. (Under the hood foreground and background share one async run engine — foreground is simply background-but-blocking.)
 - **Parallel**: multiple `subagent_delegate` calls in one turn run concurrently — foreground and background alike, no special flag.
-- **Background** (`background: true`): non-blocking — `subagent_delegate` returns immediately with a run id. Use it when you have your own work to do (or a discussion with the user to continue) while the run executes; three companion tools manage the outcome:
+- **Background** (`background: true`): non-blocking — `subagent_delegate` returns immediately with a run id. Use it when you have your own work to do (or a discussion with the user to continue) while the run executes; four companion tools manage the outcome:
 
 | Tool | Purpose | Returns to the model |
 |------|---------|---------------------|
@@ -228,6 +230,17 @@ Semantics worth knowing:
 - **Top-level only:** nested subagents cannot delegate in the background (a subagent process exits when its task finishes, which would orphan the run).
 - The run registry lives in the pi process: a `/reload` or restart orphans in-flight background runs (their ids stop resolving). `/subagent:status` lists every registered run (active + collected) and its current state.
 
+### Steering a running subagent
+
+Steering queues a correction into a running subagent without killing it — the middle ground between waiting it out and cancelling. The message is delivered after the child finishes its current tool batch, before its next LLM call, so the run keeps its progress and can change course. It is a suggestion injected between turns, not an interrupt: the child may comply immediately, finish what it was doing first, or ignore poor instructions entirely — to actually stop a run, cancel it.
+
+There are two channels into the same mechanism:
+
+- **The model** calls `subagent_steer(id, message)` — typically right after a `subagent_check` snapshot revealed the run heading down a wrong path (check → steer → check again later).
+- **The user** types into the input box of `/subagent:view`, targeting the focused run. Every accepted steer also appears in the run's activity feed as an `↩ steer:` entry, so whoever watches the view sees what was injected and when.
+
+Queued steers are visible in neither wait nor check results — they shape the run's subsequent behavior, not its transcript.
+
 ### Background TUI display
 
 Each tool row renders one aspect of the same decomposition the foreground row shows all at once (input · process · result · usage):

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@d3ara1n/pi-subagent",
-  "version": "1.4.0",
+  "version": "1.5.1",
   "type": "module",
   "description": "Role-based subagent orchestration for pi — delegates tasks to specialized pi child processes with configurable model roles",
   "main": "src/index.ts",

package/src/utils.test.ts

@@ -250,21 +250,18 @@ describe("previewArgs", () => {
   test("command -> $ prefix", () => {
     assert.equal(previewArgs({ command: "ls -la" }), "$ ls -la");
   });
-  test("command truncated at 60 chars", () => {
+  test("command is preserved for viewport-aware truncation", () => {
     const long = "x".repeat(70);
-    const r = previewArgs({ command: long });
-    assert.ok(r.startsWith("$ "));
-    assert.ok(r.endsWith("..."));
-    assert.ok(r.length < long.length);
+    assert.equal(previewArgs({ command: long }), `$ ${long}`);
   });
   test("file_path is shortened (home -> ~)", () => {
     const r = previewArgs({ file_path: "/home/user/foo.ts" });
     assert.ok(r.includes("foo.ts"));
   });
-  test("url passthrough (truncated when long)", () => {
+  test("url is preserved for viewport-aware truncation", () => {
     assert.equal(previewArgs({ url: "https://example.com" }), "https://example.com");
     const longUrl = "https://" + "x".repeat(70);
-    assert.ok(previewArgs({ url: longUrl }).endsWith("..."));
+    assert.equal(previewArgs({ url: longUrl }), longUrl);
   });
   test("query/pattern/regex/search -> /.../  form", () => {
     assert.equal(previewArgs({ query: "foo" }), "/foo/");

package/src/utils.ts

@@ -149,8 +149,7 @@ export function formatToolCall(
     }
     case "bash": {
       const command = (args.command as string) || "...";
-      const preview = command.length > 60 ? `${command.slice(0, 60)}...` : command;
-      return fg("muted", "$ ") + fg("toolOutput", preview);
+      return fg("muted", "$ ") + fg("toolOutput", command);
     }
     case "read": {
       const rawPath = (args.file_path || args.path || "...") as string;
@@ -271,10 +270,8 @@ export function taskPreview(task: string): string {
  * Width-aware collapsed-view component: renders each line truncated with "…"
  * to the actual viewport width (never wraps), padded full-width like Text(0,0).
  *
- * The char caps in taskPreview/formatToolCall/etc. stay as they are — they are
- * content limits shared with the LLM-facing text (check output, error
- * messages), which has no viewport semantics. This component is the TUI-side
- * final guard, applied where the folding affordance exists.
+ * Content formatters leave tool-call arguments intact; this component is the
+ * TUI-side final guard, applied where the folding affordance exists.
  */
 export function collapsedText(text: string): Component {
   const lines = text.split("\n");
@@ -586,15 +583,14 @@ export function freezeFrame(r: SubagentResult): SubagentResult {
  */
 export function previewArgs(args: Record<string, unknown>): string {
   const command = args.command as string | undefined;
-  if (command) return `$ ${command.length > 60 ? command.slice(0, 60) + "..." : command}`;
+  if (command) return `$ ${command}`;
   const fp = (args.file_path || args.path) as string | undefined;
   if (fp) return shortenPath(fp);
   const url = args.url as string | undefined;
-  if (url) return url.length > 60 ? url.slice(0, 60) + "..." : url;
+  if (url) return url;
   const query = (args.query || args.pattern || args.regex || args.search) as string | undefined;
-  if (query) return `/${query.length > 60 ? query.slice(0, 60) + "..." : query}/`;
-  const argsStr = JSON.stringify(args);
-  return argsStr.length > 50 ? argsStr.slice(0, 50) + "..." : argsStr;
+  if (query) return `/${query}/`;
+  return JSON.stringify(args);
 }
 
 // ── Numeric configuration ─────────────────────────────────────