chore(v0.3.0): rename fast-LLM env vars to TIMEWEB_* (match other projects)

Aligns with the user's other repos (proso) which use TIMEWEB_API_GROK /
TIMEWEB_URL_GROK. Single naming convention across projects avoids the
'which env var was it for this repo' mental tax.

  PEPA_FAST_LLM_BASE_URL → TIMEWEB_BASE_URL
  PEPA_FAST_LLM_API_KEY  → TIMEWEB_API_KEY
  PEPA_FAST_LLM_MODEL    → TIMEWEB_MODEL
  PEPA_FAST_LLM_TIMEOUT_MS → TIMEWEB_TIMEOUT_MS

Provider still works with any OpenAI-compatible endpoint — TimeWeb is
the default but the variable name doesn't lock us in. Tests + docs +
.env / .env.example updated.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

runtime/coach/fast-advisor.js

@@ -50,7 +50,7 @@ export async function advise({
 	force = false,
 } = {}) {
 	if (!isAvailable()) {
-		return { ok: false, code: "not_configured", detail: "set PEPA_FAST_LLM_API_KEY", latencyMs: 0 };
+		return { ok: false, code: "not_configured", detail: "set TIMEWEB_API_KEY", latencyMs: 0 };
 	}
 
 	const now = Date.now();

runtime/coach/fast-advisor.test.js

@@ -3,9 +3,9 @@ import assert from "node:assert/strict";
 
 import { advise, isAvailable, _resetForTest, __testing } from "./fast-advisor.js";
 
-const API_KEY = "PEPA_FAST_LLM_API_KEY";
-const MODEL = "PEPA_FAST_LLM_MODEL";
-const BASE = "PEPA_FAST_LLM_BASE_URL";
+const API_KEY = "TIMEWEB_API_KEY";
+const MODEL = "TIMEWEB_MODEL";
+const BASE = "TIMEWEB_BASE_URL";
 
 function withEnv(env, fn) {
 	const prev = {};
@@ -43,6 +43,7 @@ test("advise: not_configured without API key", async () => {
 		const res = await advise({ reason: "stuck" });
 		assert.equal(res.ok, false);
 		assert.equal(res.code, "not_configured");
+		assert.match(res.detail, /TIMEWEB_API_KEY/);
 	});
 });
 

runtime/llm/provider.js

@@ -6,19 +6,21 @@
 // right now ("I'm wedged in a pit, what should I do?").
 //
 // This provider opens a parallel path: any OpenAI-compatible HTTP endpoint
-// (TimeWeb, OpenAI direct, Groq, OpenRouter, local Ollama with the OpenAI
-// shim, …) producing a structured JSON answer in ≤8 seconds.
+// (TimeWeb is the default — same env var convention as the user's other
+// projects — but OpenAI direct, Groq, OpenRouter, and local Ollama with
+// the OpenAI shim all work with the same plumbing) producing a structured
+// JSON answer in ≤8 seconds.
 //
 // Configuration is strictly env-driven. The provider is a NO-OP unless
-// PEPA_FAST_LLM_API_KEY is set, so it's safe to ship the code disabled.
+// TIMEWEB_API_KEY is set, so it's safe to ship the code disabled.
 
 import { info, warn } from "../log.js";
 
 const ENV = {
-	BASE_URL: "PEPA_FAST_LLM_BASE_URL",
-	API_KEY: "PEPA_FAST_LLM_API_KEY",
-	MODEL: "PEPA_FAST_LLM_MODEL",
-	TIMEOUT_MS: "PEPA_FAST_LLM_TIMEOUT_MS",
+	BASE_URL: "TIMEWEB_BASE_URL",
+	API_KEY: "TIMEWEB_API_KEY",
+	MODEL: "TIMEWEB_MODEL",
+	TIMEOUT_MS: "TIMEWEB_TIMEOUT_MS",
 };
 
 const DEFAULT_BASE_URL = "https://api.openai.com/v1";
@@ -58,7 +60,7 @@ export async function complete({
 	}
 	const useModel = model || cfg.model;
 	if (!useModel) {
-		return { ok: false, code: "no_model", detail: `set ${ENV.MODEL} or pass model arg`, latencyMs: 0 };
+		return { ok: false, code: "no_model", detail: `set ${ENV.MODEL} env or pass model arg`, latencyMs: 0 };
 	}
 
 	const body = {