@openlines/opl-pi-sht 0.2.11 → 0.2.12

package/README.md

@@ -15,6 +15,8 @@
 A portable collection of various Pi coding agent extensions. Repository directories and config files use `opl-`; established Pi-facing commands and tool names stay compatible.
 
 >
+> ### v0.2.12 - refresh OpenRouter/Codex usage during agent runs
+> - `opl-footer` fixed usage refresh from agent_settled to after every turn/toolcall
 > ### v0.2.11 - OpenRouter key-limit usage in opl-footer
 > - `opl-footer` added an OpenRouter API key's used amount, cap, and percentage.
 > ### v0.2.10 - Codex subscription usage in opl-footer
@@ -141,7 +143,7 @@ Cold prompt-cache write, measured /init session (opl-modes lazy tools + MCP adap
 
 ### See what the agent is doing
 
-- **`opl-footer`** surfaces model, cost, token and cache activity, git state, agent status, per-turn timing, an optional exact remaining ChatGPT Codex subscription-quota segment, and optional OpenRouter API-key cap usage. The OpenRouter segment resolves Pi's active key locally and calls only OpenRouter's key endpoint; keys and response bodies are neither persisted nor logged. `/configure-opl` edits and reorders its layout interactively.
+- **`opl-footer`** surfaces model, cost, token and cache activity, git state, agent status, per-turn timing, optional exact remaining ChatGPT Codex subscription quota and OpenRouter API-key cap usage. Both usage segments refresh during agent runs after assistant responses and tool completions (30-second floor, coalesced trailing refresh). The OpenRouter segment resolves Pi's active key locally and calls only OpenRouter's key endpoint; keys and response bodies are neither persisted nor logged. `/configure-opl` edits and reorders its layout interactively.
 - **`opl-input`** is a configurable editor that reflects the active mode's identity, so you always know which mode you are typing into.
 ![input-footer](images/ss-input-footer.png)
 

package/extensions/opl-footer/README.md

@@ -100,7 +100,7 @@ See the tracked [`configs/opl-footer.json.sample`](../../configs/opl-footer.json
 
 ## Codex Subscription Usage
 
-Add `codex_usage` to any row through `/configure-opl` or `opl-footer.json`. While the active model is the OAuth-authenticated `openai-codex` provider, the footer asks Pi's model registry to resolve the same short-lived OAuth access token that Pi uses for the selected model, then sends `GET https://chatgpt.com/backend-api/wham/usage` directly from the local Pi process. The request carries `Authorization: Bearer <Pi OAuth token>`, `Accept: application/json`, a fixed `User-Agent: opl-footer-codex-usage`, and the token's `chatgpt_account_id` JWT claim as `chatgpt-account-id` when present. It runs after session start, model selection, and settled agent turns, with a 30-second refresh floor and a 15-second request timeout. It classifies the returned windows by duration rather than response order. This is ChatGPT subscription quota, not OpenAI Platform API-key usage or billing.
+Add `codex_usage` to any row through `/configure-opl` or `opl-footer.json`. While the active model is the OAuth-authenticated `openai-codex` provider, the footer asks Pi's model registry to resolve the same short-lived OAuth access token that Pi uses for the selected model, then sends `GET https://chatgpt.com/backend-api/wham/usage` directly from the local Pi process. The request carries `Authorization: Bearer <Pi OAuth token>`, `Accept: application/json`, a fixed `User-Agent: opl-footer-codex-usage`, and the token's `chatgpt_account_id` JWT claim as `chatgpt-account-id` when present. It refreshes after session start, model selection, each completed assistant response, each tool completion, and settled agent runs. Refreshes are non-blocking, with a 30-second floor and a 15-second request timeout; events within that floor coalesce into one trailing refresh, including events received during an in-flight request. Pending refreshes are cancelled on session reset, shutdown, or switching away from Codex, and recheck whether the segment is enabled before fetching. It classifies the returned windows by duration rather than response order. This is ChatGPT subscription quota, not OpenAI Platform API-key usage or billing.
 
 No OAuth token, account ID, or response body is written to disk, logged, added to the Pi session, or sent anywhere other than `chatgpt.com` for that request. **The footer retains only the parsed 5-hour/weekly percentage and reset time in process memory for the active session.** The endpoint is an internal ChatGPT backend API and can change without notice. A failed refresh keeps the most recent exact snapshot and marks it `(stale)`; if no request has ever succeeded, the segment stays hidden. Disabling the segment prevents future requests and discards any result from a request already in flight.
 
@@ -108,7 +108,7 @@ No OAuth token, account ID, or response body is written to disk, logged, added t
 
 Add `openrouter_usage` to any row through `/configure-opl` or `opl-footer.json`. While the selected model provider is `openrouter`, the footer resolves the same API key Pi uses for inference and sends `GET https://openrouter.ai/api/v1/key` from the local Pi process. It renders the configured per-key limit as `$<limit - limit_remaining> / $<limit> (<percent>%)`; an absent, malformed, or unlimited key cap leaves the segment hidden. The numerator deliberately uses OpenRouter's authoritative `limit_remaining`, rather than `usage` or `byok_usage`, because those ledgers may not both count against the key limit.
 
-It runs after session start, model selection, and settled agent turns, with a 30-second refresh floor and a 15-second request timeout. No API key or response body is written to disk, logged, added to the Pi session, or sent anywhere other than `openrouter.ai`. A failed refresh keeps the most recent exact snapshot and marks it `(stale)`; if no request has ever succeeded, the segment stays hidden. Disabling the segment prevents future requests and discards any result from a request already in flight.
+It refreshes after session start, model selection, each completed assistant response, each tool completion, and settled agent runs. Refreshes are non-blocking, with a 30-second floor and a 15-second request timeout; events within that floor coalesce into one trailing refresh, including events received during an in-flight request. Pending refreshes are cancelled on session reset, shutdown, or switching away from OpenRouter, and recheck whether the segment is enabled before fetching. No API key or response body is written to disk, logged, added to the Pi session, or sent anywhere other than `openrouter.ai`. A failed refresh keeps the most recent exact snapshot and marks it `(stale)`; if no request has ever succeeded, the segment stays hidden. Disabling the segment prevents future requests and discards any result from a request already in flight.
 
 ## Context Bar
 

package/extensions/opl-footer/index.ts

@@ -124,14 +124,31 @@ export default function footer(pi: ExtensionAPI) {
   let codexUsageLastAttempt = 0;
   let codexUsageGeneration = 0;
   let codexUsageInFlight: Promise<void> | null = null;
+  let codexUsageTimer: ReturnType<typeof setTimeout> | null = null;
+  let codexUsagePendingCtx: ExtensionContext | null = null;
+
+  const cancelCodexUsageRefresh = () => {
+    if (codexUsageTimer !== null) clearTimeout(codexUsageTimer);
+    codexUsageTimer = null;
+    codexUsagePendingCtx = null;
+  };
   let openRouterUsage: OpenRouterUsageSnapshot | null = null;
   let openRouterUsageLastAttempt = 0;
   let openRouterUsageGeneration = 0;
   let openRouterUsageInFlight: Promise<void> | null = null;
+  let openRouterUsageTimer: ReturnType<typeof setTimeout> | null = null;
+  let openRouterUsagePendingCtx: ExtensionContext | null = null;
+
+  const cancelOpenRouterUsageRefresh = () => {
+    if (openRouterUsageTimer !== null) clearTimeout(openRouterUsageTimer);
+    openRouterUsageTimer = null;
+    openRouterUsagePendingCtx = null;
+  };
 
   const refreshOpenRouterUsage = (ctx: ExtensionContext, force = false): Promise<void> => {
     const isOpenRouter = ctx.model?.provider === "openrouter";
     if (!isOpenRouter) {
+      cancelOpenRouterUsageRefresh();
       openRouterUsageGeneration++;
       openRouterUsageInFlight = null;
       openRouterUsage = null;
@@ -142,6 +159,7 @@ export default function footer(pi: ExtensionAPI) {
     const config = getEffectiveConfig();
     const enabled = LAYOUT_ROWS.some((row) => config[row]?.includes("openrouter_usage"));
     if (!enabled) {
+      cancelOpenRouterUsageRefresh();
       openRouterUsageGeneration++;
       openRouterUsageInFlight = null;
       openRouterUsage = null;
@@ -149,10 +167,23 @@ export default function footer(pi: ExtensionAPI) {
       tuiRef?.requestRender();
       return Promise.resolve();
     }
-    if (openRouterUsageInFlight) return openRouterUsageInFlight;
+    if (openRouterUsageInFlight) {
+      openRouterUsagePendingCtx = ctx;
+      return openRouterUsageInFlight;
+    }
 
     const now = Date.now();
-    if (!force && now - openRouterUsageLastAttempt < CODEX_USAGE_REFRESH_MS) return Promise.resolve();
+    const remaining = CODEX_USAGE_REFRESH_MS - (now - openRouterUsageLastAttempt);
+    if (!force && remaining > 0) {
+      if (openRouterUsageTimer === null) {
+        openRouterUsageTimer = setTimeout(() => {
+          openRouterUsageTimer = null;
+          void refreshOpenRouterUsage(ctx);
+        }, remaining);
+      }
+      return Promise.resolve();
+    }
+    cancelOpenRouterUsageRefresh();
     openRouterUsageLastAttempt = now;
     const generation = ++openRouterUsageGeneration;
 
@@ -165,6 +196,10 @@ export default function footer(pi: ExtensionAPI) {
       })
       .finally(() => {
         if (openRouterUsageInFlight === request) openRouterUsageInFlight = null;
+        if (generation !== openRouterUsageGeneration) return;
+        const pendingCtx = openRouterUsagePendingCtx;
+        openRouterUsagePendingCtx = null;
+        if (pendingCtx) void refreshOpenRouterUsage(pendingCtx);
       });
     openRouterUsageInFlight = request;
     return request;
@@ -174,6 +209,7 @@ export default function footer(pi: ExtensionAPI) {
     const model = ctx.model;
     const isCodexSubscription = model?.provider === "openai-codex" && ctx.modelRegistry.isUsingOAuth(model);
     if (!isCodexSubscription) {
+      cancelCodexUsageRefresh();
       codexUsageGeneration++;
       codexUsageInFlight = null;
       codexUsage = null;
@@ -184,6 +220,7 @@ export default function footer(pi: ExtensionAPI) {
     const config = getEffectiveConfig();
     const enabled = LAYOUT_ROWS.some((row) => config[row]?.includes("codex_usage"));
     if (!enabled) {
+      cancelCodexUsageRefresh();
       codexUsageGeneration++;
       codexUsageInFlight = null;
       codexUsage = null;
@@ -191,10 +228,23 @@ export default function footer(pi: ExtensionAPI) {
       tuiRef?.requestRender();
       return Promise.resolve();
     }
-    if (codexUsageInFlight) return codexUsageInFlight;
+    if (codexUsageInFlight) {
+      codexUsagePendingCtx = ctx;
+      return codexUsageInFlight;
+    }
 
     const now = Date.now();
-    if (!force && now - codexUsageLastAttempt < CODEX_USAGE_REFRESH_MS) return Promise.resolve();
+    const remaining = CODEX_USAGE_REFRESH_MS - (now - codexUsageLastAttempt);
+    if (!force && remaining > 0) {
+      if (codexUsageTimer === null) {
+        codexUsageTimer = setTimeout(() => {
+          codexUsageTimer = null;
+          void refreshCodexUsage(ctx);
+        }, remaining);
+      }
+      return Promise.resolve();
+    }
+    cancelCodexUsageRefresh();
     codexUsageLastAttempt = now;
     const generation = ++codexUsageGeneration;
 
@@ -207,6 +257,10 @@ export default function footer(pi: ExtensionAPI) {
       })
       .finally(() => {
         if (codexUsageInFlight === request) codexUsageInFlight = null;
+        if (generation !== codexUsageGeneration) return;
+        const pendingCtx = codexUsagePendingCtx;
+        codexUsagePendingCtx = null;
+        if (pendingCtx) void refreshCodexUsage(pendingCtx);
       });
     codexUsageInFlight = request;
     return request;
@@ -241,10 +295,12 @@ export default function footer(pi: ExtensionAPI) {
     currentCtx = ctx;
     lastBranchLength = 0;
     cachedUsageStats = null;
+    cancelCodexUsageRefresh();
     codexUsage = null;
     codexUsageLastAttempt = 0;
     codexUsageGeneration++;
     codexUsageInFlight = null;
+    cancelOpenRouterUsageRefresh();
     openRouterUsage = null;
     openRouterUsageLastAttempt = 0;
     openRouterUsageGeneration++;
@@ -267,6 +323,22 @@ export default function footer(pi: ExtensionAPI) {
     }
   });
 
+  pi.on("session_shutdown", async () => {
+    cancelCodexUsageRefresh();
+    codexUsageGeneration++;
+    codexUsageInFlight = null;
+    cancelOpenRouterUsageRefresh();
+    openRouterUsageGeneration++;
+    openRouterUsageInFlight = null;
+  });
+
+  pi.on("message_end", async (event, ctx) => {
+    if (event.message.role === "assistant") {
+      void refreshCodexUsage(ctx);
+      void refreshOpenRouterUsage(ctx);
+    }
+  });
+
   pi.on("model_select", async (_event: unknown, ctx: ExtensionContext) => {
     void refreshCodexUsage(ctx, true);
     void refreshOpenRouterUsage(ctx, true);
@@ -320,6 +392,8 @@ export default function footer(pi: ExtensionAPI) {
     }
     statusTracker.toolEnded(event.toolCallId);
     tuiRef?.requestRender();
+    void refreshCodexUsage(_ctx);
+    void refreshOpenRouterUsage(_ctx);
   });
 
   pi.on("message_update", async (_event: unknown, _ctx: ExtensionContext) => {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@openlines/opl-pi-sht",
-  "version": "0.2.11",
+  "version": "0.2.12",
   "description": "opl-pi-sht (shouldHaveThat) Pi coding-agent extension kit: token-efficient context, tool and session safety, fingerprinted /init, model benchmarking, web access, and browser automation.",
   "repository": {
     "type": "git",
@@ -8,7 +8,8 @@
   },
   "files": [
     "extensions/",
-    "configs/"
+    "configs/",
+    "images/"
   ],
   "keywords": [
     "pi",