pi-quiver 3.4.0 → 3.4.1

package/CHANGELOG.md

@@ -8,6 +8,11 @@ Published to npm as `pi-quiver` (`pi install npm:pi-quiver`). Pushing a
 via OIDC trusted publishing. The release helper at
 `.agents/skills/release/scripts/release.sh` cuts the tag; CI publishes.
 
+## v3.4.1 - 2026-08-04
+
+- **`fast-mode` now corrects reported `usage.cost` to true 2x fast pricing for Opus 4.8/5** (statusline, persisted cost, and pi-cohort `Σ$` per load order) (#6).
+- **Documented Anthropic stall-retry activation.** A session trace confirmed Pi's existing 2/4/8-second exponential backoff was active and that the watchdog retained the retry budget resolved when its extension instance started. Local `retry.maxRetries: 5` now takes effect after a fresh session or explicit reload, with no watchdog cooldown, resubmission path, or runtime code change.
+
 ## v3.4.0 - 2026-07-30
 
 - **`provider-stall-watchdog`: new `firstEventMs` tier (default 20s) fast-fails a request that never streams.** A pre-first-event deadline is armed at every provider request and cleared by the first assistant `message_start`; on expiry the request is aborted and converted to a retryable error, cutting recovery for an unresponsive request from ~240s to ~22s (detection + Pi's 2s backoff). Previously only the 240s mid-stream `recoveryMs` timer caught this case.

package/README.md

@@ -150,6 +150,8 @@ These extensions are opt-in via `settings.json` (project `.pi/settings.json` ove
 
 `sessionAutoName.enabled` makes one extra short LLM call per session (once, after the first turn) to title it; `false` (default) makes no model calls. `fastMode` only affects `claude-opus-4-8` and `claude-opus-5` requests on Anthropic's `anthropic-messages` API; enabling it opts into premium fast-mode pricing. `--fast` forces it on for one launch; `/fast on|off` toggles live. Proxy providers (opencode, cloudflare-ai-gateway) are excluded. `fastMode`'s header injection needs the `before_provider_headers` hook (pi bundling `@earendil-works/pi-coding-agent` >= 0.80.5); on older pi the beta header is silently not sent. See [doc/fetch.md](doc/fetch.md) and [doc/doc-to-md.md](doc/doc-to-md.md) for the ingestion tools' full reference; session-name/sword-header behavior above is complete.
 
+`pi-ai` prices every fast request at standard rates - it has no `usage.speed` support and no request-level pricing modifier - so `fastMode` corrects the reported cost itself: a `message_end` handler scales all four `usage.cost` components by `FAST_MODE_COST_MULTIPLIER` (2x) and returns the corrected message. Persisted session JSONL and pi's own native cost display are always exact, since they're written from this corrected message. pi-cohort's live `Σ$` reflects the correction only when pi-quiver's `message_end` handler runs before pi-cohort's - best-effort, depending on extension load order - and is reconciled on pi-cohort's next `session_start` regardless. The upstream fix (teaching `pi-ai`'s `Usage`/`calculateCost` about `usage.speed`) is the better long-term path and is tracked separately.
+
 Recommended explicit retry and watchdog settings:
 
 ```json

package/fast-mode.ts

@@ -22,6 +22,7 @@
  */
 
 import type { ExtensionAPI, ExtensionContext } from "@earendil-works/pi-coding-agent";
+import type { Usage } from "@earendil-works/pi-ai";
 import { resolveConfig } from "./extension-config.ts";
 
 export const FAST_MODE_BETA = "fast-mode-2026-02-01";
@@ -29,6 +30,21 @@ export const FAST_SPEED = "fast";
 // Loose prefixes: match dated snapshots (claude-opus-4-8-*, claude-opus-5-*).
 // Opus 4.7 is out of scope (D1); a future model needs a one-line addition here.
 export const FAST_MODE_MODEL_PREFIXES = ["claude-opus-4-8", "claude-opus-5"];
+
+// Anthropic bills Opus 4.8/5 fast mode at exactly 2x standard rates; input,
+// output, and cache read/write all scale by the same factor because caching
+// multipliers "apply on top of fast mode pricing". Rate card:
+// https://docs.claude.com/en/docs/build-with-claude/fast-mode (retrieved 2026-08-04).
+export const FAST_MODE_COST_MULTIPLIER = 2;
+
+export function scaleCost(cost: Usage["cost"], multiplier: number): Usage["cost"] {
+	const input = cost.input * multiplier;
+	const output = cost.output * multiplier;
+	const cacheRead = cost.cacheRead * multiplier;
+	const cacheWrite = cost.cacheWrite * multiplier;
+	return { input, output, cacheRead, cacheWrite, total: input + output + cacheRead + cacheWrite };
+}
+
 export const OAUTH_IDENTITY_BETAS = ["claude-code-20250219", "oauth-2025-04-20"];
 const STATUS_KEY = "fast-mode";
 const BETA_HEADER = "anthropic-beta";
@@ -92,6 +108,10 @@ export function resolveEnabled(s: State): boolean {
 export default function (pi: ExtensionAPI) {
 	let liveOverride: boolean | null = null;
 	let enabled = false;
+	// Per-request snapshot. Safe as plain booleans because pi serializes provider
+	// requests per session (headers -> request -> message_end, awaited in order).
+	let pendingFastSpeed = false;
+	let pendingFastHeader = false;
 
 	const readFlag = (): boolean => pi.getFlag("fast") === true;
 
@@ -135,16 +155,43 @@ export default function (pi: ExtensionAPI) {
 	});
 
 	pi.on("before_provider_request", (event, ctx) => {
-		if (!shouldInject(enabled, ctx.model)) return;
-		return injectSpeed(event.payload);
+		if (!shouldInject(enabled, ctx.model)) {
+			pendingFastSpeed = false;
+			return;
+		}
+		const next = injectSpeed(event.payload);
+		pendingFastSpeed =
+			typeof next === "object" && next !== null && (next as Record<string, unknown>).speed === FAST_SPEED;
+		return next;
 	});
 
 	pi.on("before_provider_headers", async (event, ctx) => {
-		if (!shouldInject(enabled, ctx.model)) return;
-		if (!event.headers) return;
+		if (!shouldInject(enabled, ctx.model) || !event.headers) {
+			pendingFastHeader = false;
+			return;
+		}
 		const isOAuth = await detectOAuth(ctx);
-		if (isOAuth === null) return;
+		if (isOAuth === null) {
+			pendingFastHeader = false;
+			return;
+		}
 		event.headers[BETA_HEADER] = buildBetaHeader(event.headers[BETA_HEADER], isOAuth);
+		pendingFastHeader = true;
+	});
+
+	pi.on("message_end", (event) => {
+		const msg = event.message;
+		if (msg.role !== "assistant") return;
+		const corrected = pendingFastSpeed && pendingFastHeader && !!msg.usage?.cost;
+		pendingFastSpeed = false;
+		pendingFastHeader = false;
+		if (!corrected) return;
+		return {
+			message: {
+				...msg,
+				usage: { ...msg.usage, cost: scaleCost(msg.usage.cost, FAST_MODE_COST_MULTIPLIER) },
+			},
+		};
 	});
 
 	pi.registerCommand("fast", {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-quiver",
-  "version": "3.4.0",
+  "version": "3.4.1",
   "description": "Personal pack of Pi coding-agent extensions: context-safe fetch, doc_to_md PDF/DOCX/PPTX-to-Markdown conversion, session naming, a themed ASCII startup header, Opus 4.8 fast mode, and a provider-stall watchdog.",
   "author": "Jacek Juraszek",
   "license": "MIT",