pi-minimal-dispatch 0.2.0 → 0.2.1

package/CHANGELOG.md

@@ -1,5 +1,16 @@
 # Changelog
 
+## 0.2.1 — 2026-10-26
+
+- Status lines (`lanes` status/wait, `/lanes`) tag each lane with its model:
+  `[short-id think:level]` after the name — provider prefix dropped, thinking
+  level only when set. The tag shows the actual model from the lane's last
+  assistant message, falling back to the pinned value until the first answer;
+  `LaneStatus` carries `model`/`thinkingLevel` (full ids) for structured
+  consumers.
+- `dispatch`'s `model` param documents pi's `id:thinking` suffix
+  (e.g. `zai/glm-4.6:high`), which the tag renders split off the id.
+
 ## 0.2.0 — 2026-10-23
 
 Requires pi ≥ 1.4.0 (the MCP reach rules the validator encodes are pi

package/README.md

@@ -10,8 +10,8 @@ never guessed from empty files.
 
 ```
 wave 'survey':
-  docs   · running · 2 turns · tok 5703in/90out, $0.0009 · stop:toolUse · last 3.1s ago
-  review · settled · 4 turns · tok 12021in/310out, $0.0041 · stop:stop · last 12s ago
+  docs [glm-4.6 think:high] · running · 2 turns · tok 5703in/90out, $0.0009 · stop:toolUse · last 3.1s ago
+  review [glm-5.3-flash] · settled · 4 turns · tok 12021in/310out, $0.0041 · stop:stop · last 12s ago
 ```
 
 ## Why
@@ -75,8 +75,8 @@ pi decides when to call the tools. A real session looks like:
   manifest: /abs/path/to/.pi/work/survey-manifest.json
 
 > lanes     wave="survey" action="wait"
-  docs · settled · 2 turns · tok 5703in/90out, $0.0009 · stop:stop · last 0.8s ago
-  review · settled · 4 turns · tok 12021in/310out, $0.0041 · stop:stop · last 2.1s ago
+  docs [glm-5.3-flash] · settled · 2 turns · tok 5703in/90out, $0.0009 · stop:stop · last 0.8s ago
+  review [glm-4.6] · settled · 4 turns · tok 12021in/310out, $0.0041 · stop:stop · last 2.1s ago
 
 > lanes     wave="survey" action="collect"
   collect wave 'survey':
@@ -139,8 +139,11 @@ While any tracked lane runs, the footer shows one line — e.g. `lanes: 2 runnin
 — updated at the `pollMs` cadence and cleared when nothing is in flight.
 `/lanes` (optionally `/lanes <wave>`) prints the full status table for waves
 seen this session — an untracked wave name is resolved from the default
-workDir — and completes wave names. Both are TUI conveniences over the same
-derived state the `lanes` tool reports.
+workDir — and completes wave names. Each line tags the lane with its model —
+short id (provider prefix dropped), thinking level appended as `think:<level>`
+when set — the actual model from the event stream once answers exist, the pinned
+value before that. Both are TUI conveniences over the same derived state the
+`lanes` tool reports.
 
 ## State model
 

package/docs/API.md

@@ -20,7 +20,7 @@ the leash. Events stream to `<workDir>/<wave>-<name>.events.jsonl`.
 | `lanes` | array | — | One entry per lane (min 1); lane slugs unique within the wave |
 | `lanes[].name` | string | — | Lane slug: `kebab-case`, max 64 chars |
 | `lanes[].briefPath` | string | — | Path to the lane's brief file (its `@file` prompt) |
-| `lanes[].model` | string? | pi default | Pin a model id; omitted: pi's **configured default model** — not the dispatcher session's active model |
+| `lanes[].model` | string? | pi default | Pin a model id; omitted: pi's **configured default model** — not the dispatcher session's active model. Accepts pi's `id:thinking` suffix (e.g. `zai/glm-4.6:high`) |
 | `lanes[].deadlineSec` | number? | `deadlineSec` config (900) | Leash in seconds; holds even if the dispatcher is gone. Minimum 1 |
 | `lanes[].tools` | string? | `read,grep,find,ls` | Tool allowlist for `--tools` — plain names or `*` patterns; no `+name`/`-name` modifiers, no shell quoting, not empty. Add `bash` when a lane must run commands (bash can still invoke git). With MCP enabled, reach requires `codemode` or `tool_search` here — see [MCP and web reach](#mcp-and-web-reach) |
 | `lanes[].noExtensions` | boolean? | false | Pass `-ne` (drop extensions incl. MCP in the lane) |
@@ -98,6 +98,8 @@ Per-lane `structuredContent` entries. Note: `settled` only means the
 | `overdue` | boolean? | alive past its deadline (leash misfire) — informational |
 | `turns` | number | turn count so far |
 | `usage` | object | run totals summed over assistant messages: `{input, output, cacheRead, cacheWrite, cost}` |
+| `model` | string? | model answering the last assistant message; until the first assistant message, the pinned model with pi's `:thinking` suffix split off (last colon, valid level word only) |
+| `thinkingLevel` | string? | thinking level of the last assistant message (`off`–`max`) — absent for models without thinking |
 | `stopReason` | string? | last assistant stop reason (`stop` is clean) |
 | `lastEventAgeSec` | number? | seconds since the events file last grew — the stuck-lane signal |
 | `spawnError` | string? | why a `spawn`-failed lane never started |

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "pi-minimal-dispatch",
-	"version": "0.2.0",
+	"version": "0.2.1",
 	"description": "Minimal detached lane dispatch with visible state for the pi coding agent — dispatch/lanes tools over a manifest + JSON-event protocol",
 	"author": "Mike Cheung",
 	"keywords": [

package/src/derive.ts

@@ -45,6 +45,10 @@ export type LaneStatus = {
 	overdue?: boolean;
 	turns: number;
 	usage: Usage;
+	/** Model answering the last assistant message; before the first, the pinned model (pi's `id:thinking` suffix split off). */
+	model?: string;
+	/** Thinking level of the last assistant message; absent for models without thinking. */
+	thinkingLevel?: string;
 	stopReason?: string;
 	lastEventAgeSec: number | null;
 	spawnError?: string;
@@ -113,11 +117,16 @@ function errTailFor(lane: LaneRecord): string | undefined {
 
 /** Derive a lane's status from its events file, PID liveness, and manifest facts. Never stored. */
 export function deriveLane(lane: LaneRecord, now: number): LaneStatus {
+	// pi's --model splits a `:thinking` suffix only on the last colon and only for a valid
+	// level word (model-resolver's nSuffix) — ids like `qwen/qwen3-coder:exacto` keep their colon.
+	const pinned = lane.model?.match(/^(.+):(off|minimal|low|medium|high|xhigh|max)$/);
 	const base: LaneStatus = {
 		name: lane.name,
 		state: "failed",
 		turns: 0,
 		usage: emptyUsage(),
+		model: pinned?.[1] ?? lane.model,
+		thinkingLevel: pinned?.[2],
 		lastEventAgeSec: null,
 	};
 
@@ -135,6 +144,12 @@ export function deriveLane(lane: LaneRecord, now: number): LaneStatus {
 			base.usage.cacheWrite += u.cacheWrite ?? 0;
 			base.usage.cost += u.cost?.total ?? 0;
 			if (typeof message.stopReason === "string") base.stopReason = message.stopReason;
+			// The last assistant message is authoritative for identity — a message without
+			// thinkingLevel (model switch to a non-thinking model) clears a stale level.
+			if (typeof message.model === "string") {
+				base.model = message.model;
+				base.thinkingLevel = typeof message.thinkingLevel === "string" ? message.thinkingLevel : undefined;
+			}
 		}
 	}
 	if (fs.existsSync(lane.eventsPath)) {

package/src/events.ts

@@ -18,6 +18,8 @@ export type ContentBlock = { type: string; text?: string; thinking?: string };
 export type StreamMessage = {
 	role: string;
 	stopReason?: string;
+	model?: string;
+	thinkingLevel?: string;
 	usage?: UsageDelta;
 	content?: ContentBlock[];
 };

package/src/format.ts

@@ -7,7 +7,11 @@ import type { LaneStatus } from "./derive.ts";
 
 /** One status-table line per lane (two-space indent, err tail four-space indented). */
 export function formatLaneLine(s: LaneStatus): string {
-	const bits = [s.name, s.state];
+	// Short form: provider prefix dropped, thinking level labeled `think:` (a bare level word
+	// reads like a model variant) — the full ids live in the structured status payload.
+	const id = s.model ? s.model.split("/").pop() : undefined;
+	const tag = id === undefined ? "" : ` [${id}${s.thinkingLevel !== undefined ? ` think:${s.thinkingLevel}` : ""}]`;
+	const bits = [`${s.name}${tag}`, s.state];
 	if (s.cause) bits.push(`(${s.cause}${s.spawnError ? `: ${s.spawnError}` : ""})`);
 	if (s.overdue) bits.push("OVERDUE");
 	bits.push(s.turns === 1 ? "1 turn" : `${s.turns} turns`);

package/src/index.ts

@@ -108,7 +108,7 @@ const dispatchTool = defineTool({
 			Type.Object({
 				name: Type.String({ description: "Lane slug (kebab-case, max 64 chars, unique within the wave)" }),
 				briefPath: Type.String({ description: "Path to the lane's brief file (@file prompt)" }),
-				model: Type.Optional(Type.String({ description: "Pin a model id for this lane; omitted: pi's configured default model — not necessarily the dispatcher session's active model" })),
+				model: Type.Optional(Type.String({ description: "Pin a model id for this lane; omitted: pi's configured default model — not necessarily the dispatcher session's active model. Accepts pi's `id:thinking` suffix (e.g. 'zai/glm-4.6:high')" })),
 				deadlineSec: Type.Optional(Type.Number({ description: "Deadline leash in seconds (config default: 900)", minimum: 1 })),
 				tools: Type.Optional(Type.String({ description: "Tool allowlist for --tools; omitted: 'read,grep,find,ls' — add 'bash' when a lane must run commands (bash can still invoke git). Plain names or mcp__/tool patterns only: +name/-name modifiers, shell quoting, and empty lists are rejected. With mcp enabled, MCP/web tools are reachable only through 'codemode' or 'tool_search' named here ('mcp__server__*' entries declare tools directly only for direct-exposure servers)" })),
 				noExtensions: Type.Optional(Type.Boolean({ description: "Pass -ne (drop extensions incl. MCP)" })),
@@ -209,6 +209,7 @@ const lanesTool = defineTool({
 	description:
 		"Observe/control a dispatched wave. action=status (default): per-lane derived state " +
 		"(starting/running/settled/failed + cause spawn|killed|deadline|crashed), turns, run-total usage, " +
+		"model + thinking level (actual, from the last assistant message; pinned value before the first), " +
 		"stopReason, last-event age, .err tail for crashed lanes. action=wait: hold this call open, " +
 		"re-deriving at the pollMs cadence, until every lane is settled/failed or waitSec (default 300, " +
 		"max 3600) elapses — then return the status table; replaces blind sleep-then-status polling. " +