pi-magi-theme 0.3.0 → 0.3.1

package/README.md

@@ -36,8 +36,8 @@ Clone the repo and point pi at it instead (edits in the repo are live on the nex
 
 | Command | What it does |
 |---------|--------------|
-| `/magi <question>` | the council answers a question (recent conversation as context) |
-| `/magi review [focus]` | the council reviews your pending changes (`git diff HEAD` plus untracked file names) before you commit |
+| `/magi council <question>` | the council answers a question (recent conversation as context) |
+| `/magi council review [focus]` | the council reviews your pending changes (`git diff HEAD` plus untracked file names) before you commit |
 | `/magi config` | pick a model for each MAGI |
 | `/magi mecha` | MECHA SELECT: pick the llama-swap model to activate, each shown as a mecha head lit by its real state |
 | `/magi compact` | toggle the compact side panel (basic info and animations only); remembered across sessions |
@@ -120,7 +120,7 @@ When the limit is reached llama.cpp does not abort the reply: it inserts the clo
 
 ## The council
 
-`/magi <question>` asks three models in parallel, each with its own nature, then shows the votes and a majority verdict:
+`/magi council <question>` asks three models in parallel, each with its own nature, then shows the votes and a majority verdict:
 
 | Unit | Nature | Looks at |
 |------|--------|----------|
@@ -130,7 +130,7 @@ When the limit is reached llama.cpp does not abort the reply: it inserts the clo
 
 Each nature is a lens, not a specialty, so the council answers any question, not only software ones. Every MAGI first answers the question, then judges it through its lens, naming concrete tools, numbers and scenarios from your question instead of generic advice. Votes: **APPROVE** = go ahead or clear recommendation; **CONDITIONAL** = only if the named conditions hold, or when information is missing (it says what it needs); **REJECT** = a concrete problem, with what to do instead. A MAGI never rejects because a topic is outside its nature. Answers come back in the language of your question.
 
-`/magi <question>` gives the MAGI the recent conversation as context; `/magi review` gives them the pending diff (truncated at 24k characters). Full opinions are added to the chat (not sent to the agent), and the last verdict stays under the MAGI in the side panel.
+`/magi council <question>` gives the MAGI the recent conversation as context; `/magi council review` gives them the pending diff (truncated at 24k characters). Full opinions are added to the chat (not sent to the agent), and the last verdict stays under the MAGI in the side panel.
 
 ## Configuration
 
@@ -166,6 +166,8 @@ No token: npmjs is configured to trust this repository's `publish.yml` (npm trus
 
 ## llama-swap
 
+**Thinking levels.** [pi-llama-swap](https://www.npmjs.com/package/@danielmeneses/pi-llama-swap) registers every model with reasoning off, so `/thinking` only offers `off`. At session start MAGI reads the reasoning levels llama-swap publishes in `/v1/models` (`meta.llamaswap.reasoning.levels`) and re-registers those models with thinking on: `/thinking` then offers exactly those levels, sent as `chat_template_kwargs` (`enable_thinking`, `reasoning_effort`). Aliases (e.g. the Instruct twin of a Thinking model) stay off, and image input follows `architecture.input_modalities`. A new or renamed model works without a `modelOverrides` entry in `models.json`; entries you keep there still apply on top (e.g. `samplingParams`). The starting level is pi's usual one for a model switch: the level saved for that model (`Ctrl+S` in `/thinking`), else `defaultThinkingLevel`.
+
 When the session model uses the `llama-swap` provider, the side panel:
 
 - loads nothing at startup: a new session opens MECHA SELECT, a resumed one shows whether its model is already in VRAM;

package/extensions/magi/index.ts

@@ -907,6 +907,56 @@ async function swapAliases(): Promise<Map<string, string>> {
 	return aliases;
 }
 
+const PI_THINKING_LEVELS = ["minimal", "low", "medium", "high", "xhigh", "max"];
+
+/**
+ * pi-llama-swap registers every model with reasoning off, so /thinking only offers "off".
+ * llama-swap publishes each model's reasoning levels in /v1/models: re-register the provider with them,
+ * sent as chat_template_kwargs (enable_thinking + reasoning_effort). Aliases (the Instruct twins) stay off.
+ * models.json modelOverrides still apply on top.
+ */
+async function enableSwapReasoning(pi: ExtensionAPI, ctx: ExtensionContext): Promise<void> {
+	const config = ctx.modelRegistry.getRegisteredProviderConfig("llama-swap") as any;
+	if (!config?.models?.length || !config.baseUrl) return;
+	try {
+		const headers: Record<string, string> = config.apiKey ? { Authorization: `Bearer ${config.apiKey}` } : {};
+		const res = await fetch(`${config.baseUrl.replace(/\/$/, "")}/models`, { headers, signal: AbortSignal.timeout(5000) });
+		const { data } = (await res.json()) as { data?: any[] };
+		const meta = new Map((data ?? []).map((m) => [m.id, m]));
+		let changed = false;
+		const models = config.models.map((m: any) => {
+			const entry = meta.get(m.id);
+			const levels: string[] | undefined = entry?.meta?.llamaswap?.reasoning?.levels;
+			const input = entry?.architecture?.input_modalities?.includes("image") ? ["text", "image"] : ["text"];
+			if (!levels?.length || entry.meta.llamaswap.type === "alias") return { ...m, input };
+			changed = true;
+			return {
+				...m,
+				input,
+				reasoning: true,
+				thinkingLevelMap: Object.fromEntries(PI_THINKING_LEVELS.map((l) => [l, levels.includes(l) ? l : null])),
+				compat: {
+					...m.compat,
+					thinkingFormat: "chat-template",
+					chatTemplateKwargs: {
+						enable_thinking: { $var: "thinking.enabled" },
+						preserve_thinking: true,
+						reasoning_effort: { $var: "thinking.effort", omitWhenOff: true },
+					},
+				},
+			};
+		});
+		// ponytail: a /llama-swap refresh re-registers the plain models until the next session start
+		if (!changed) return;
+		ctx.modelRegistry.registerProvider("llama-swap", { ...config, models });
+		// the session already holds the old model object: swap in the new one
+		const fresh = ctx.model?.provider === "llama-swap" ? ctx.modelRegistry.find("llama-swap", ctx.model.id) : undefined;
+		if (fresh?.reasoning) await pi.setModel(fresh);
+	} catch {
+		// server unreachable: models stay as pi-llama-swap registered them
+	}
+}
+
 /** Models llama-swap keeps in memory: real id → "ready" | "starting" | … (empty when the server is unreachable). */
 async function swapRunning(): Promise<Map<string, string>> {
 	try {
@@ -1545,10 +1595,11 @@ type MagiConfig = Partial<Record<MagiUnit, MagiUnitConfig>> & {
 
 const MAGI_CONFIG_PATH = join(homedir(), ".pi", "agent", "magi.json");
 /** /magi arguments that manage the theme instead of asking the council. */
-const UI_ARGS = /^(on|off|panel|compact|status|cost)$|^(hygiene|budget)(\s|$)/i; // anything else is a question
+const UI_ARGS = /^(on|off|panel|compact|status|cost)$|^(hygiene|budget)(\s|$)/i;
 /** /magi arguments offered by autocomplete: the full argument, and what it does. */
 const MAGI_ARGS: [string, string][] = [
-	["review", "the council reviews your pending changes before you commit"],
+	["council", "ask the three MAGI a question (recent conversation as context)"],
+	["council review", "the council reviews your pending changes before you commit"],
 	["config", "pick a model for each MAGI"],
 	["mecha", "MECHA SELECT: pick the llama-swap model to activate"],
 	["status", "llama-swap report: speed, tokens, cache hits, errors per model"],
@@ -1628,7 +1679,7 @@ function conversationExcerpt(ctx: ExtensionContext, maxChars = 6000): string {
 
 const REVIEW_MAX_CHARS = 24_000;
 
-/** The pending changes for /magi review: tracked changes against HEAD plus the names of untracked files. */
+/** The pending changes for /magi council review: tracked changes against HEAD plus the names of untracked files. */
 async function pendingChanges(cwd: string): Promise<{ diff: string; untracked: string[] }> {
 	const git = (args: string[]) => promisify(execFile)("git", args, { cwd, maxBuffer: 32 * 1024 * 1024 }).then((r) => r.stdout);
 	let diff: string;
@@ -2271,6 +2322,7 @@ export default function (pi: ExtensionAPI) {
 		fixedBudget = { planning: tb.planning ?? BUDGET_DEFAULTS.planning, acting: tb.acting ?? BUDGET_DEFAULTS.acting };
 		budgetMessage = tb.message ?? true;
 		learned = tb.learned ?? {};
+		await enableSwapReasoning(pi, ctx);
 		// the local-model rules live next to AGENTS.md, created once so the user can edit them
 		const rules = join(ctx.cwd, "MAGI.md");
 		if (!existsSync(rules)) {
@@ -2600,8 +2652,12 @@ export default function (pi: ExtensionAPI) {
 				return pickModel(ctx);
 			}
 
-			if (arg === "review" || arg.startsWith("review ")) {
-				const focus = arg.slice("review".length).trim();
+			if (arg !== "council" && !arg.startsWith("council ")) {
+				return ctx.ui.notify(arg ? `Unknown /magi command "${arg}": to ask the MAGI, /magi council <question>` : "Ask the MAGI with /magi council <question>; type /magi and a space to see every command", arg ? "warning" : "info");
+			}
+			const ask = arg.slice("council".length).trim();
+			if (ask === "review" || ask.startsWith("review ")) {
+				const focus = ask.slice("review".length).trim();
 				let changes: { diff: string; untracked: string[] };
 				try {
 					changes = await pendingChanges(ctx.cwd);
@@ -2624,7 +2680,7 @@ export default function (pi: ExtensionAPI) {
 				return runCouncil(ctx, question, "```diff\n" + diff + "\n```" + untracked, "Pending changes (git diff HEAD)");
 			}
 
-			const question = arg || (await ctx.ui.input("Question for the MAGI:", "should we …?"))?.trim() || "";
+			const question = ask || (await ctx.ui.input("Question for the MAGI:", "should we …?"))?.trim() || "";
 			if (!question) return;
 			return runCouncil(ctx, question, conversationExcerpt(ctx));
 		},

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-magi-theme",
-  "version": "0.3.0",
+  "version": "0.3.1",
   "description": "MAGI SYSTEM theme + extension for pi (Evangelion fan art): MAGI control screen panel, three-model /magi council, MECHA SELECT model picker, angel-attack loading, seven-seal context gauge, llama-swap telemetry",
   "keywords": [
     "pi-package",