pi-ollama-cloud 0.8.0 → 0.10.0

package/CHANGELOG.md

@@ -2,6 +2,22 @@
 
 All notable changes to this project will be documented in this file.
 
+## [Unreleased]
+
+## [0.10.0] - 2026-09-03
+
+- **Breaking:** Adapt to the changed `/api/usage` response shape. The endpoint now returns a single `limits.monthly` bucket (replacing `limits.session` and `limits.weekly`) and adds an `activity.models` array. `UsageData`, `isUsageResponse`, `formatUsage`, and `formatUsageStatusColored` now read the monthly limit; the status bar shows a single `30d` segment instead of `5h`/`7d`.
+- Refreshed the generated catalog from the live API: added `deepseek-v4-pro:0813`, `glm-5.3`, and `glm-5.3-flash`; removed `deepseek-v4-flash:preview` and `deepseek-v4-pro`, which are no longer listed.
+- Source per-token pricing from the official model table on ollama.com/pricing instead of models.dev estimates, which no longer track Ollama's published rates (up to ~13x off per model). `scripts/generate-pricing.ts` now scrapes the pricing page (the table is server-rendered; no JSON endpoint exists) and matches catalog IDs to pricing rows by exact or `:tag`-family match, replacing the `OLLAMA_TO_MODELSDEV` mapping. Regenerated `pricing.generated.ts` with the official rates, including new models (`glm-5.3`, `glm-5.3-flash`, `deepseek-v4-pro:0813`). Fixes #51. Thanks @Hackbard (#52).
+- Probe per-model max output tokens against the live API via `scripts/generate-limits.ts` into `limits.generated.ts`, replacing the fixed 32768 default for known models (unprobed models still fall back to 32768). The probe timeout is 60s so slow first-token models are not dropped from the table. Thanks @f440 (#49).
+
+## [0.9.0] - 2026-08-11
+
+- Add `/ollama-cloud-usage` command to show Ollama Cloud session (5h) and weekly (7d) usage limits, per-model request counts, and the 4-week activity cost, fetched from the undocumented `/api/usage` endpoint with the already-resolved API key.
+- Add a footer usage status bar (`5h ▕███░░░░░░░▏ 34% 7d ▕████░░░░░░▏ 45%`) while an `ollama-cloud` model is active, refreshing every 5 minutes and after each agent turn (throttled so it never exceeds one /api/usage call per 5 minutes). Segments are colored by usage level (green <60%, yellow 60-79%, red 80%+). The quota-bar concept is inspired by `@entelligentsia/pi-ollama-cloud-usage-tracker`. Off by default; enable with `/ollama-usage-status on` or `"usageStatus": true` in `ollama-cloud.json`.
+- Add `/ollama-usage-status [on|off|enable|disable]` to toggle the footer usage status bar at runtime (toggles without an argument).
+- Document the exported usage API (`fetchUsage`, `formatUsageStatusColored`, `getCloudApiKey`, validators) so custom status bars can reuse it.
+
 ## [0.8.0] - 2026-08-09
 
 - **Breaking:** Migrate model refresh to pi's native `refreshModels` mechanism. Remove the `/ollama-cloud-refresh` command and the manual `~/.pi/agent/cache/ollama-cloud-models.json` cache. The catalog now refreshes automatically on startup, on `/model` open, and via `pi update --models`, persisted through pi's own `FileModelsStore`. Users should delete the orphaned cache file after upgrade: `rm ~/.pi/agent/cache/ollama-cloud-models.json`.

package/README.md

@@ -12,7 +12,7 @@ Registers Ollama Cloud as a model provider with dynamically fetched models, and
 - **Automatic model refresh** - On startup, `/model` open, and `pi update --models`, pi calls the extension's `refreshModels` callback to fetch the latest models from the API and persists them through pi's own model store. No manual refresh command.
 - **`ollama_web_search` tool** - Search the web for real-time information using Ollama Cloud's `/api/web_search` endpoint. Returns titles, URLs, and content snippets.
 - **`ollama_web_fetch` tool** - Fetch and extract text content from a web page URL using Ollama Cloud's `/api/web_fetch` endpoint. Returns page title, content, and links.
-- **Estimated cost tracking** - Models are registered with estimated per-token costs sourced from [models.dev](https://models.dev) (the same catalog pi uses), so Pi's `/cost` shows comparable usage. Ollama Cloud is subscription-billed (Free, Pro, Max), so these are equivalent pay-as-you-go estimates, not actual charges. See [ollama.com/pricing](https://ollama.com/pricing) for plan details.
+- **Per-token cost tracking** - Models are registered with the official per-token prices from [ollama.com/pricing](https://ollama.com/pricing), so Pi's `/cost` shows comparable usage. Ollama Cloud is subscription-billed, so these are equivalent pay-as-you-go rates, not actual charges.
 
 ## Prerequisites
 
@@ -97,12 +97,14 @@ Extension settings can be set via JSON config files. Project-local settings over
 | Setting | Type | Default | Description |
 |---|---|---|---|
 | `webTools` | boolean | `true` | Set to `false` to prevent `ollama_web_search` and `ollama_web_fetch` from being registered |
+| `usageStatus` | boolean | `false` | Set to `true` to show the footer usage status bar (opt-in; enable at runtime with `/ollama-usage-status`) |
 
 Example `ollama-cloud.json`:
 
 ```json
 {
-  "webTools": false
+  "webTools": false,
+  "usageStatus": true
 }
 ```
 
@@ -133,8 +135,14 @@ Model metadata is derived from the `/api/show` response:
 | `thinkingLevelMap` | [`thinking-levels.ts`](thinking-levels.ts) with 5 maps (DEFAULT, GPT_OSS, QWEN3, GLM_52, NO_OFF) based on API testing |
 | `input` | `["text", "image"]` if `capabilities` includes `"vision"`, else `["text"]` |
 | `contextWindow` | `model_info.*.context_length` (falls back to 128000) |
-| `maxTokens` | Fixed at 32768 |
-| `cost` | Estimated per-1M-token prices from [models.dev](https://models.dev), generated by `scripts/generate-pricing.ts` into `pricing.generated.ts`. Ollama Cloud is subscription-billed, so these are equivalent pay-as-you-go estimates, not actual charges. Unmapped models default to zero. Prices are pinned to the installed package version and only update on a new release, so newly added models register with zero cost until then. |
+| `maxTokens` | Probed per-model limits from [`limits.generated.ts`](limits.generated.ts), generated by `scripts/generate-limits.ts` (requires `OLLAMA_API_KEY`). Models without a probed limit fall back to 32768. |
+| `cost` | Official per-1M-token prices from the [ollama.com/pricing](https://ollama.com/pricing) model table, generated by `scripts/generate-pricing.ts` into `pricing.generated.ts`. Ollama Cloud is subscription-billed, so these are equivalent pay-as-you-go rates, not actual charges. Catalog IDs with no matching pricing row default to zero. Prices are pinned to the installed package version and only update on a new release, so newly added models register with zero cost until then. |
+
+The per-model max output token table (`limits.generated.ts`) is probed against the live API by `scripts/generate-limits.ts`, since `/api/show` does not expose the limit. It needs an API key: `OLLAMA_API_KEY=<key> npm run generate-limits`. Limits ship with the package, so regenerated values take effect on the next release.
+
+The API itself returns no cost data: completion responses report only token counts (`prompt_tokens`/`completion_tokens`/`total_tokens`, including the final usage chunk when streaming), and `/api/show` exposes no pricing fields. The prices above come from the static `/pricing` page table and are only as fresh as the last regeneration.
+
+Cache pricing is informational only: the `/pricing` page lists a "Cached input" column, but the completion API does not report cache token usage (there is no `prompt_tokens_details.cached_tokens` or equivalent in any response, verified against the live API in September 2026), so pi never sees cache hits and `/cost` estimates do not reflect them. `cacheWrite` is always zero because the pricing table has no cache-write column.
 
 ### Thinking level mapping
 
@@ -164,6 +172,58 @@ Both tools use the same Ollama Cloud API key configured for the provider. No loc
 | Command | Description |
 |---|---|
 | `/ollama-webtools [on\|off\|enable\|disable]` | Enable or disable the `ollama_web_search` and `ollama_web_fetch` tools. Toggles if no argument given. |
+| `/ollama-cloud-usage` | Show Ollama Cloud monthly usage limits, per-model request counts, and the 4-week activity cost. |
+| `/ollama-usage-status [on\|off\|enable\|disable]` | Enable or disable the footer usage status bar. Toggles if no argument given. |
+
+## Usage status bar
+
+While an `ollama-cloud` model is the active provider, the footer shows a compact
+live usage readout (`30d ▕███░░░░░░░▏ 34%`) that refreshes
+every 5 minutes and after each agent turn (but no more often than every 5 minutes). It is colored by how close
+it is to the cap: green below 60%, yellow at 60-79%, red at 80%+. It reads the
+same undocumented `/api/usage` endpoint as `/ollama-cloud-usage` and clears
+itself on transient errors or when you switch to a non-Ollama-Cloud provider.
+
+It is off by default. Enable it at runtime with `/ollama-usage-status on`, or
+enable it by default with `"usageStatus": true` in `ollama-cloud.json`. If the
+bar never appears after enabling, run `/ollama-cloud-usage` to see the
+underlying error (e.g. a misconfigured API key).
+
+The quota-bar concept is inspired by
+[`@entelligentsia/pi-ollama-cloud-usage-tracker`](https://github.com/Entelligentsia/pi-ollama-cloud-usage-tracker),
+but this extension fetches usage from the `/api/usage` endpoint with the API key
+it already resolves, rather than scraping the settings page with Chrome cookies.
+
+## Usage API for custom status bars
+
+The usage data plane is exported so you can plug it into your own footer or
+status bar instead of (or alongside) the built-in one. The relevant modules ship
+with the package and are importable directly:
+
+```ts
+import { fetchUsage, formatUsage, formatUsageStatusColored } from "pi-ollama-cloud/usage.ts";
+import { getCloudApiKey } from "pi-ollama-cloud/utils.ts";
+import type { UsageData } from "pi-ollama-cloud/usage.ts";
+```
+
+| Export | Description |
+|---|---|
+| `fetchUsage(apiKey, signal?)` | Fetch the raw `/api/usage` data, returning a typed `UsageData`. Throws a status-mapped error on 401/403/429/404/5xx. |
+| `formatUsageStatusColored(theme, data)` | One-line status string with quota bars, colored by usage level. Takes a `Theme` (e.g. `ctx.ui.theme`). |
+| `formatUsage(data)` | Multi-line human-readable output (percentages, per-model request counts, activity cost). |
+| `getCloudApiKey(ctx)` | Resolve the Ollama Cloud API key the same way the extension does. |
+| `isUsageResponse(data)` / `isUsageLimit(data)` | Validators for parsing the raw response yourself. |
+
+Example custom status bar:
+
+```ts
+const apiKey = await getCloudApiKey(ctx);
+const data = await fetchUsage(apiKey);
+ctx.ui.setStatus("my-usage", formatUsageStatusColored(ctx.ui.theme, data));
+```
+
+Note that the package ships raw TypeScript sources (no build step), so submodule
+imports use the `.ts` extension, matching how the extension imports internally.
 
 ## Development
 
@@ -173,6 +233,7 @@ npm run check        # lint + format + type-check (auto-fix)
 npm run lint         # lint only (no fixes)
 npm run typecheck    # type-check only (tsgo --noEmit)
 npm run format       # format only
+OLLAMA_API_KEY=<key> npm run generate-limits   # probe max output tokens (writes limits.generated.ts)
 ```
 
 The project uses [Biome](https://biomejs.dev/) for linting and formatting (2-space indent, line width 120) and [tsgo](https://github.com/microsoft/typescript-go) for type-checking.
@@ -192,7 +253,7 @@ Live smoke against the real API (needs an `OLLAMA_API_KEY` or an `ollama-cloud`
 ```bash
 # Run pi with the local extension, no install required. The --no-* flags isolate
 # the run from other installed extensions, skills, prompt templates, themes,
-# context files, and session storage so only the local checkout is exercised.
+# context files, and session storage so only the local checkout is exercised
 pi --no-extensions --no-skills --no-prompt-templates --no-themes --no-context-files --no-session \
   -e ./index.ts --model "ollama-cloud/gemma4:31b" --no-tools -p "Say hi in one word"
 
@@ -241,7 +302,8 @@ git push --tags
 Because the model catalog refreshes automatically at runtime, a release is **not** needed to ship new models. Publish only when:
 
 - A model is retired and still listed by the API: add it to `RETIRED_MODEL_IDS` in `scripts/generate-models.ts` (check https://docs.ollama.com/cloud#retirements, then regenerate `models.generated.ts`).
-- Pricing changes: models.dev prices updated, or a new model needs an `OLLAMA_TO_MODELSDEV` mapping line (regenerate `pricing.generated.ts`).
+- Pricing changes: Ollama updates the model pricing table, or a new model needs a pricing row (regenerate `pricing.generated.ts`).
+- Max output token limits changed: run `OLLAMA_API_KEY=<key> npm run generate-limits` locally and commit.
 
 The tag version must match the version in `package.json` - `npm version` handles this automatically. The workflow at `.github/workflows/publish.yml` verifies the match before publishing to npm.
 

package/config.ts

@@ -25,12 +25,15 @@ import { getAgentDir } from "@earendil-works/pi-coding-agent";
 export interface OllamaCloudConfig {
   /** When false, ollama_web_search and ollama_web_fetch tools are not registered. Default: true. */
   webTools?: boolean;
+  /** When true, the footer usage status bar is shown. Default: false (opt-in; enable with /ollama-usage-status). */
+  usageStatus?: boolean;
 }
 
 // --- Defaults ---
 
 const DEFAULT_CONFIG: OllamaCloudConfig = {
   webTools: true,
+  usageStatus: false,
 };
 
 // --- Validation ---
@@ -38,6 +41,7 @@ const DEFAULT_CONFIG: OllamaCloudConfig = {
 /** Allowed config keys and their expected types for runtime validation. */
 const CONFIG_SCHEMA: Record<keyof OllamaCloudConfig, "boolean"> = {
   webTools: "boolean",
+  usageStatus: "boolean",
 };
 
 /**

package/index.ts

@@ -24,12 +24,29 @@
  * Only models with "tools" capability are registered.
  */
 
-import type { ExtensionAPI } from "@earendil-works/pi-coding-agent";
+import type { ExtensionAPI, ExtensionContext } from "@earendil-works/pi-coding-agent";
 import { loadConfig, resolveWebToolsEnv } from "./config.ts";
 import { GENERATED_MODELS } from "./models.generated.ts";
 import { OLLAMA_BASE, refreshOllamaCatalog } from "./models.ts";
+import { fetchUsage, formatUsage, formatUsageStatusColored } from "./usage.ts";
+import { getCloudApiKey } from "./utils.ts";
 import { registerWebFetchTool, registerWebSearchTool } from "./web-tools.ts";
 
+/**
+ * Resolve the new enabled state for /ollama-usage-status from its argument.
+ * Exported for unit testing.
+ */
+export function resolveUsageStatusToggle(arg: string, current: boolean): { enabled: boolean; error?: string } {
+  const a = arg.trim().toLowerCase();
+  if (a === "on" || a === "enable") return { enabled: true };
+  if (a === "off" || a === "disable") return { enabled: false };
+  if (a === "") return { enabled: !current };
+  return {
+    enabled: current,
+    error: `Unknown argument "${arg.trim()}". Usage: /ollama-usage-status [on|off|enable|disable]`,
+  };
+}
+
 // --- Main ---
 
 export default async function (pi: ExtensionAPI) {
@@ -82,21 +99,25 @@ export default async function (pi: ExtensionAPI) {
     }
   }
 
-  // Module-level tracking across session restarts within the same extension
-  // instance. The config file is read once, on the first session_start;
-  // later sessions reuse webToolsEnabled (including any /ollama-webtools
-  // override). Restart pi or /reload to pick up config file changes.
-  let webToolsConfigured = false;
+  // Config is read once per extension factory invocation (on the first
+  // session_start). The factory is re-invoked on /new, /fork, /resume, and
+  // /reload, so runtime toggles (e.g. /ollama-webtools, /ollama-usage-status)
+  // reset to the config default on each session restart. Restart pi or /reload
+  // to pick up config file changes.
+  let configLoaded = false;
   let webToolsEnabled = false;
+  let usageStatusEnabled = false;
 
   pi.on("session_start", async (_event, ctx) => {
-    if (!webToolsConfigured) {
-      webToolsConfigured = true;
+    if (!configLoaded) {
+      configLoaded = true;
       const config = loadConfig(ctx.cwd);
       if (config.webTools !== false) {
         webToolsEnabled = true;
         ensureWebToolsRegistered();
       }
+      // The status bar is opt-in: enabled only when the config explicitly sets it true.
+      usageStatusEnabled = config.usageStatus === true;
     }
     // On every session start (including resume/fork/new), re-apply the
     // runtime state. Tools may have been unregistered during teardown.
@@ -104,6 +125,126 @@ export default async function (pi: ExtensionAPI) {
       ensureWebToolsRegistered();
       setWebToolsActive(true);
     }
+    // Start the usage status bar when ollama-cloud is the active provider.
+    if (usageStatusEnabled && isOllamaCloud(ctx)) {
+      startUsageStatus(ctx);
+    }
+  });
+
+  // --- Usage Command ---
+
+  pi.registerCommand("ollama-cloud-usage", {
+    description: "Show Ollama Cloud monthly usage limits.",
+    handler: async (_args, ctx) => {
+      const apiKey = await getCloudApiKey(ctx);
+      if (!apiKey) {
+        ctx.ui.notify("No Ollama Cloud API key configured. Set OLLAMA_API_KEY or add to auth.json.", "error");
+        return;
+      }
+      try {
+        const data = await fetchUsage(apiKey);
+        ctx.ui.notify(formatUsage(data), "info");
+      } catch (err) {
+        ctx.ui.notify(err instanceof Error ? err.message : String(err), "error");
+      }
+    },
+  });
+
+  // --- Usage Status Bar ---
+
+  // Footer status showing live monthly usage while ollama-cloud is the
+  // active provider. Refreshes on a 5-minute timer; agent_end also triggers a
+  // refresh but is throttled to the same cooldown so a turn never hammers the
+  // undocumented /api/usage endpoint. The quota-bar concept is inspired by
+  // @entelligentsia/pi-ollama-cloud-usage-tracker.
+  const USAGE_STATUS_KEY = "ollama-usage";
+  const USAGE_REFRESH_MS = 5 * 60_000;
+  let usageTimer: ReturnType<typeof setInterval> | null = null;
+  let usageActive = false;
+  // Timestamp (ms) of the most recent refresh attempt; gates the agent_end
+  // refresh so it fires at most once per cooldown. Set when a fetch starts, so
+  // a failing endpoint is also throttled, not just a successful one.
+  let lastRefreshAt = 0;
+
+  async function refreshUsageStatus(ctx: ExtensionContext) {
+    try {
+      const apiKey = await getCloudApiKey(ctx);
+      if (!apiKey) {
+        ctx.ui.setStatus(USAGE_STATUS_KEY, undefined);
+        return;
+      }
+      lastRefreshAt = Date.now();
+      const data = await fetchUsage(apiKey);
+      ctx.ui.setStatus(USAGE_STATUS_KEY, formatUsageStatusColored(ctx.ui.theme, data));
+    } catch {
+      // Transient errors (undocumented endpoint, network) should not spam the
+      // footer; clear the status and retry on the next refresh.
+      ctx.ui.setStatus(USAGE_STATUS_KEY, undefined);
+    }
+  }
+
+  function startUsageStatus(ctx: ExtensionContext) {
+    if (usageActive) return;
+    // The status bar is TUI-only; skip the fetch and timer in print/json/rpc.
+    if (ctx.mode !== "tui") return;
+    usageActive = true;
+    refreshUsageStatus(ctx);
+    usageTimer = setInterval(() => refreshUsageStatus(ctx), USAGE_REFRESH_MS);
+  }
+
+  function stopUsageStatus(ctx: ExtensionContext) {
+    usageActive = false;
+    if (usageTimer) {
+      clearInterval(usageTimer);
+      usageTimer = null;
+    }
+    ctx.ui.setStatus(USAGE_STATUS_KEY, undefined);
+  }
+
+  function isOllamaCloud(ctx: ExtensionContext): boolean {
+    return ctx.model?.provider === "ollama-cloud";
+  }
+
+  pi.on("model_select", async (_event, ctx) => {
+    if (usageStatusEnabled && isOllamaCloud(ctx)) {
+      startUsageStatus(ctx);
+    } else {
+      stopUsageStatus(ctx);
+    }
+  });
+
+  pi.on("agent_end", async (_event, ctx) => {
+    // Throttle the after-turn refresh to the same cooldown as the timer so a
+    // burst of turns never exceeds one /api/usage call per 5 minutes.
+    if (usageActive && isOllamaCloud(ctx) && Date.now() - lastRefreshAt >= USAGE_REFRESH_MS) {
+      await refreshUsageStatus(ctx);
+    }
+  });
+
+  pi.on("session_shutdown", async (_event, ctx) => {
+    stopUsageStatus(ctx);
+  });
+
+  pi.registerCommand("ollama-usage-status", {
+    description:
+      "Enable or disable the Ollama Cloud usage status bar. " +
+      "Accepts optional argument: on/off/enable/disable. Without argument, toggles.",
+    handler: async (args, ctx) => {
+      const { enabled, error } = resolveUsageStatusToggle(args, usageStatusEnabled);
+      if (error) {
+        ctx.ui.notify(error, "error");
+        return;
+      }
+      usageStatusEnabled = enabled;
+
+      if (usageStatusEnabled && isOllamaCloud(ctx)) {
+        startUsageStatus(ctx);
+      } else {
+        stopUsageStatus(ctx);
+      }
+
+      ctx.ui.notify(`Ollama Cloud usage status: ${usageStatusEnabled ? "enabled" : "disabled"}`, "info");
+    },
   });
 
   // Only register the runtime toggle command when the env var doesn't force tools off.

package/limits.generated.ts

@@ -0,0 +1,25 @@
+// Auto-generated by scripts/generate-limits.ts
+// Do not edit manually.
+// Probed models: 19 (0 failed)
+
+export const MODEL_MAX_OUTPUT_TOKENS: Record<string, number> = {
+  "deepseek-v4-flash:0731": 65536,
+  "deepseek-v4-pro:0813": 65536,
+  "gemma4:31b": 262144,
+  "glm-5.1": 131072,
+  "glm-5.2": 131072,
+  "glm-5.3": 524288,
+  "glm-5.3-flash": 524288,
+  "gpt-oss:120b": 131072,
+  "gpt-oss:20b": 131072,
+  "kimi-k2.6": 262144,
+  "kimi-k2.7-code": 262144,
+  "kimi-k3": 524288,
+  "minimax-m2.7": 131072,
+  "minimax-m3": 131072,
+  "mistral-large-3:675b": 262144,
+  "nemotron-3-nano:30b": 131072,
+  "nemotron-3-super": 65536,
+  "nemotron-3-ultra": 65536,
+  "qwen3.5:397b": 65536,
+};

package/models.generated.ts

@@ -1,7 +1,7 @@
 // Auto-generated by scripts/generate-models.ts
 // Do not edit manually.
-// Generated: 2026-08-08T04:19:46.959Z
-// Model count: 18
+// Generated: 2026-09-03T10:12:02.243Z
+// Model count: 19
 
 import type { ProviderModelConfig } from "@earendil-works/pi-coding-agent";
 
@@ -29,13 +29,13 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
     contextWindow: 1048576,
     cost: {
-      cacheRead: 0.0028,
+      cacheRead: 0.014,
       cacheWrite: 0,
-      input: 0.14,
-      output: 0.28,
+      input: 0.44,
+      output: 1.32,
     },
     input: ["text"],
-    maxTokens: 32768,
+    maxTokens: 65536,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -47,8 +47,8 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
   },
   {
-    id: "deepseek-v4-flash:preview",
-    name: "deepseek-v4-flash:preview",
+    id: "deepseek-v4-pro:0813",
+    name: "deepseek-v4-pro:0813",
     compat: {
       maxTokensField: "max_tokens",
       openRouterRouting: {},
@@ -69,13 +69,13 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
     contextWindow: 1048576,
     cost: {
-      cacheRead: 0.0028,
+      cacheRead: 0.044,
       cacheWrite: 0,
-      input: 0.14,
-      output: 0.28,
+      input: 1.32,
+      output: 3.96,
     },
     input: ["text"],
-    maxTokens: 32768,
+    maxTokens: 65536,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -87,8 +87,8 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
   },
   {
-    id: "deepseek-v4-pro",
-    name: "deepseek-v4-pro",
+    id: "gemma4:31b",
+    name: "gemma4:31b",
     compat: {
       maxTokensField: "max_tokens",
       openRouterRouting: {},
@@ -107,15 +107,15 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       vercelGatewayRouting: {},
       zaiToolStream: false,
     },
-    contextWindow: 524288,
+    contextWindow: 262144,
     cost: {
-      cacheRead: 0.003625,
+      cacheRead: 0.05,
       cacheWrite: 0,
-      input: 0.435,
-      output: 0.87,
+      input: 0.14,
+      output: 0.4,
     },
-    input: ["text"],
-    maxTokens: 32768,
+    input: ["text", "image"],
+    maxTokens: 262144,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -127,8 +127,8 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
   },
   {
-    id: "gemma4:31b",
-    name: "gemma4:31b",
+    id: "glm-5.1",
+    name: "glm-5.1",
     compat: {
       maxTokensField: "max_tokens",
       openRouterRouting: {},
@@ -147,15 +147,15 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       vercelGatewayRouting: {},
       zaiToolStream: false,
     },
-    contextWindow: 262144,
+    contextWindow: 202752,
     cost: {
-      cacheRead: 0.1,
+      cacheRead: 0.2,
       cacheWrite: 0,
-      input: 0.1,
-      output: 0.34,
+      input: 1,
+      output: 3.2,
     },
-    input: ["text", "image"],
-    maxTokens: 32768,
+    input: ["text"],
+    maxTokens: 131072,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -167,8 +167,8 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
   },
   {
-    id: "glm-5.1",
-    name: "glm-5.1",
+    id: "glm-5.2",
+    name: "glm-5.2",
     compat: {
       maxTokensField: "max_tokens",
       openRouterRouting: {},
@@ -187,7 +187,7 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       vercelGatewayRouting: {},
       zaiToolStream: false,
     },
-    contextWindow: 202752,
+    contextWindow: 1048576,
     cost: {
       cacheRead: 0.26,
       cacheWrite: 0,
@@ -195,20 +195,20 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       output: 4.4,
     },
     input: ["text"],
-    maxTokens: 32768,
+    maxTokens: 131072,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
-      low: "low",
-      medium: "medium",
+      low: null,
+      medium: null,
       minimal: null,
       off: "none",
       xhigh: "max",
     },
   },
   {
-    id: "glm-5.2",
-    name: "glm-5.2",
+    id: "glm-5.3",
+    name: "glm-5.3",
     compat: {
       maxTokensField: "max_tokens",
       openRouterRouting: {},
@@ -227,7 +227,7 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       vercelGatewayRouting: {},
       zaiToolStream: false,
     },
-    contextWindow: 1000000,
+    contextWindow: 1048576,
     cost: {
       cacheRead: 0.26,
       cacheWrite: 0,
@@ -235,12 +235,52 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       output: 4.4,
     },
     input: ["text"],
-    maxTokens: 32768,
+    maxTokens: 524288,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
-      low: null,
-      medium: null,
+      low: "low",
+      medium: "medium",
+      minimal: null,
+      off: "none",
+      xhigh: "max",
+    },
+  },
+  {
+    id: "glm-5.3-flash",
+    name: "glm-5.3-flash",
+    compat: {
+      maxTokensField: "max_tokens",
+      openRouterRouting: {},
+      requiresAssistantAfterToolResult: false,
+      requiresReasoningContentOnAssistantMessages: false,
+      requiresThinkingAsText: false,
+      requiresToolResultName: false,
+      sendSessionAffinityHeaders: false,
+      supportsDeveloperRole: false,
+      supportsLongCacheRetention: false,
+      supportsReasoningEffort: true,
+      supportsStore: false,
+      supportsStrictMode: false,
+      supportsUsageInStreaming: true,
+      thinkingFormat: "openai",
+      vercelGatewayRouting: {},
+      zaiToolStream: false,
+    },
+    contextWindow: 1048576,
+    cost: {
+      cacheRead: 0.03,
+      cacheWrite: 0,
+      input: 0.15,
+      output: 0.5,
+    },
+    input: ["text", "image"],
+    maxTokens: 524288,
+    reasoning: true,
+    thinkingLevelMap: {
+      high: "high",
+      low: "low",
+      medium: "medium",
       minimal: null,
       off: "none",
       xhigh: "max",
@@ -269,13 +309,13 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
     contextWindow: 131072,
     cost: {
-      cacheRead: 0,
+      cacheRead: 0.014,
       cacheWrite: 0,
-      input: 0.037,
-      output: 0.17,
+      input: 0.15,
+      output: 0.6,
     },
     input: ["text"],
-    maxTokens: 32768,
+    maxTokens: 131072,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -309,13 +349,13 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
     contextWindow: 131072,
     cost: {
-      cacheRead: 0.03,
+      cacheRead: 0.035,
       cacheWrite: 0,
-      input: 0.03,
-      output: 0.13,
+      input: 0.07,
+      output: 0.3,
     },
     input: ["text"],
-    maxTokens: 32768,
+    maxTokens: 131072,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -355,7 +395,7 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       output: 4,
     },
     input: ["text", "image"],
-    maxTokens: 32768,
+    maxTokens: 262144,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -395,7 +435,7 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       output: 4,
     },
     input: ["text", "image"],
-    maxTokens: 32768,
+    maxTokens: 262144,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -435,7 +475,7 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       output: 15,
     },
     input: ["text", "image"],
-    maxTokens: 32768,
+    maxTokens: 524288,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -470,12 +510,12 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     contextWindow: 196608,
     cost: {
       cacheRead: 0.06,
-      cacheWrite: 0.375,
+      cacheWrite: 0,
       input: 0.3,
       output: 1.2,
     },
     input: ["text"],
-    maxTokens: 32768,
+    maxTokens: 131072,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -507,15 +547,15 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       vercelGatewayRouting: {},
       zaiToolStream: false,
     },
-    contextWindow: 524288,
+    contextWindow: 512000,
     cost: {
-      cacheRead: 0.06,
+      cacheRead: 0.12,
       cacheWrite: 0,
-      input: 0.3,
-      output: 1.2,
+      input: 0.6,
+      output: 2.4,
     },
     input: ["text", "image"],
-    maxTokens: 32768,
+    maxTokens: 131072,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -549,13 +589,13 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
     contextWindow: 262144,
     cost: {
-      cacheRead: 0,
+      cacheRead: 0.5,
       cacheWrite: 0,
       input: 0.5,
       output: 1.5,
     },
     input: ["text", "image"],
-    maxTokens: 32768,
+    maxTokens: 262144,
     reasoning: false,
   },
   {
@@ -581,13 +621,13 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
     contextWindow: 262144,
     cost: {
-      cacheRead: 0.03,
+      cacheRead: 0.06,
       cacheWrite: 0,
-      input: 0.05,
-      output: 0.2,
+      input: 0.06,
+      output: 0.24,
     },
     input: ["text"],
-    maxTokens: 32768,
+    maxTokens: 131072,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -621,13 +661,13 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
     contextWindow: 262144,
     cost: {
-      cacheRead: 0,
+      cacheRead: 0.015,
       cacheWrite: 0,
-      input: 0.2,
-      output: 0.8,
+      input: 0.015,
+      output: 0.6,
     },
     input: ["text"],
-    maxTokens: 32768,
+    maxTokens: 65536,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -661,13 +701,13 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
     contextWindow: 262144,
     cost: {
-      cacheRead: 0.15,
+      cacheRead: 0.1,
       cacheWrite: 0,
-      input: 0.5,
-      output: 2.5,
+      input: 0.1,
+      output: 3,
     },
     input: ["text"],
-    maxTokens: 32768,
+    maxTokens: 65536,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -701,13 +741,13 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
     contextWindow: 262144,
     cost: {
-      cacheRead: 0,
+      cacheRead: 0.6,
       cacheWrite: 0,
       input: 0.6,
       output: 3.6,
     },
     input: ["text", "image"],
-    maxTokens: 32768,
+    maxTokens: 65536,
     reasoning: true,
     thinkingLevelMap: {
       high: null,

package/models.ts

@@ -1,22 +1,34 @@
 import type { RefreshModelsContext } from "@earendil-works/pi-ai";
 import type { ProviderModelConfig } from "@earendil-works/pi-coding-agent";
+import { MODEL_MAX_OUTPUT_TOKENS } from "./limits.generated.ts";
 import { GENERATED_MODELS } from "./models.generated.ts";
 import { MODEL_PRICING, type ModelPrice } from "./pricing.generated.ts";
 import { resolve as resolveThinkingLevelMap } from "./thinking-levels.ts";
 import { concurrentMap, fetchJsonWithTimeout, getContextLength } from "./utils.ts";
 
 // --- Pricing ---
-// Estimated per-1M-token prices are generated from models.dev by
+// Per-1M-token prices are generated from the ollama.com/pricing model table by
 // scripts/generate-pricing.ts (see pricing.generated.ts, do not edit by hand).
 // Ollama Cloud is subscription-billed; these are equivalent pay-as-you-go
-// estimates so /cost shows comparable usage, not actual charges.
+// rates so /cost shows comparable usage, not actual charges.
 
-/** Resolve the estimated price for an Ollama Cloud model ID. Exact match only;
+/** Resolve the price for an Ollama Cloud model ID. Exact match only;
  *  unmapped models return zero. */
 function resolvePrice(id: string): ModelPrice {
   return MODEL_PRICING[id] ?? { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 };
 }
 
+// --- Max output tokens ---
+// Per-model limits are probed against the live API by scripts/generate-limits.ts
+// (see limits.generated.ts, do not edit by hand). /api/show does not expose the
+// limit, so models without a probed value fall back to 32768.
+
+/** Resolve the max output tokens for an Ollama Cloud model ID. Exact match only;
+ *  unmapped models fall back to 32768. */
+function resolveMaxTokens(id: string): number {
+  return MODEL_MAX_OUTPUT_TOKENS[id] ?? 32768;
+}
+
 // --- Constants ---
 const FETCH_TIMEOUT_MS = 10000;
 // How long a stored catalog is considered fresh before the next network refresh
@@ -127,9 +139,7 @@ export function assembleModels(raw: Record<string, OllamaShowResponse>): Provide
       input: (data.capabilities?.includes("vision") ? ["text", "image"] : ["text"]) as ("text" | "image")[],
       cost: resolvePrice(id),
       contextWindow: getContextLength(data.model_info ?? {}),
-      // No per-model limit exposed by the API (https://docs.ollama.com/api-reference/show-model-details,
-      // https://github.com/ollama/ollama/issues/7222). 32768 matches most Ollama Cloud context windows.
-      maxTokens: 32768,
+      maxTokens: resolveMaxTokens(id),
       compat: buildCompat(),
     }));
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-ollama-cloud",
-  "version": "0.8.0",
+  "version": "0.10.0",
   "type": "module",
   "keywords": [
     "pi-package"
@@ -8,10 +8,12 @@
   "files": [
     "index.ts",
     "config.ts",
+    "limits.generated.ts",
     "models.ts",
     "models.generated.ts",
     "pricing.generated.ts",
     "thinking-levels.ts",
+    "usage.ts",
     "utils.ts",
     "web-tools.ts",
     "CHANGELOG.md",
@@ -29,7 +31,8 @@
     "format": "biome format --write .",
     "test": "vitest run",
     "smoke:web-tools": "tsx scripts/smoke-web-tools.ts",
-    "generate-models": "tsx scripts/generate-pricing.ts && tsx scripts/generate-models.ts && biome format --write models.generated.ts pricing.generated.ts"
+    "generate-models": "tsx scripts/generate-pricing.ts && tsx scripts/generate-models.ts && biome format --write models.generated.ts pricing.generated.ts",
+    "generate-limits": "tsx scripts/generate-limits.ts && biome format --write limits.generated.ts"
   },
   "pi": {
     "extensions": [

package/pricing.generated.ts

@@ -1,7 +1,7 @@
 // Auto-generated by scripts/generate-pricing.ts
 // Do not edit manually.
-// Generated: 2026-08-08T04:19:45.594Z
-// Model count: 18
+// Generated: 2026-09-03T10:12:00.135Z
+// Model count: 19
 
 export interface ModelPrice {
   input: number;
@@ -11,22 +11,23 @@ export interface ModelPrice {
 }
 
 export const MODEL_PRICING: Record<string, ModelPrice> = {
-  "deepseek-v4-flash:0731": { input: 0.14, output: 0.28, cacheRead: 0.0028, cacheWrite: 0 },
-  "deepseek-v4-flash:preview": { input: 0.14, output: 0.28, cacheRead: 0.0028, cacheWrite: 0 },
-  "deepseek-v4-pro": { input: 0.435, output: 0.87, cacheRead: 0.003625, cacheWrite: 0 },
-  "gemma4:31b": { input: 0.1, output: 0.34, cacheRead: 0.1, cacheWrite: 0 },
-  "glm-5.1": { input: 1.4, output: 4.4, cacheRead: 0.26, cacheWrite: 0 },
+  "deepseek-v4-flash:0731": { input: 0.44, output: 1.32, cacheRead: 0.014, cacheWrite: 0 },
+  "deepseek-v4-pro:0813": { input: 1.32, output: 3.96, cacheRead: 0.044, cacheWrite: 0 },
+  "gemma4:31b": { input: 0.14, output: 0.4, cacheRead: 0.05, cacheWrite: 0 },
+  "glm-5.1": { input: 1, output: 3.2, cacheRead: 0.2, cacheWrite: 0 },
   "glm-5.2": { input: 1.4, output: 4.4, cacheRead: 0.26, cacheWrite: 0 },
-  "gpt-oss:120b": { input: 0.037, output: 0.17, cacheRead: 0, cacheWrite: 0 },
-  "gpt-oss:20b": { input: 0.03, output: 0.13, cacheRead: 0.03, cacheWrite: 0 },
+  "glm-5.3": { input: 1.4, output: 4.4, cacheRead: 0.26, cacheWrite: 0 },
+  "glm-5.3-flash": { input: 0.15, output: 0.5, cacheRead: 0.03, cacheWrite: 0 },
+  "gpt-oss:120b": { input: 0.15, output: 0.6, cacheRead: 0.014, cacheWrite: 0 },
+  "gpt-oss:20b": { input: 0.07, output: 0.3, cacheRead: 0.035, cacheWrite: 0 },
   "kimi-k2.6": { input: 0.95, output: 4, cacheRead: 0.16, cacheWrite: 0 },
   "kimi-k2.7-code": { input: 0.95, output: 4, cacheRead: 0.19, cacheWrite: 0 },
   "kimi-k3": { input: 3, output: 15, cacheRead: 0.3, cacheWrite: 0 },
-  "minimax-m2.7": { input: 0.3, output: 1.2, cacheRead: 0.06, cacheWrite: 0.375 },
-  "minimax-m3": { input: 0.3, output: 1.2, cacheRead: 0.06, cacheWrite: 0 },
-  "mistral-large-3:675b": { input: 0.5, output: 1.5, cacheRead: 0, cacheWrite: 0 },
-  "nemotron-3-nano:30b": { input: 0.05, output: 0.2, cacheRead: 0.03, cacheWrite: 0 },
-  "nemotron-3-super": { input: 0.2, output: 0.8, cacheRead: 0, cacheWrite: 0 },
-  "nemotron-3-ultra": { input: 0.5, output: 2.5, cacheRead: 0.15, cacheWrite: 0 },
-  "qwen3.5:397b": { input: 0.6, output: 3.6, cacheRead: 0, cacheWrite: 0 },
+  "minimax-m2.7": { input: 0.3, output: 1.2, cacheRead: 0.06, cacheWrite: 0 },
+  "minimax-m3": { input: 0.6, output: 2.4, cacheRead: 0.12, cacheWrite: 0 },
+  "mistral-large-3:675b": { input: 0.5, output: 1.5, cacheRead: 0.5, cacheWrite: 0 },
+  "nemotron-3-nano:30b": { input: 0.06, output: 0.24, cacheRead: 0.06, cacheWrite: 0 },
+  "nemotron-3-super": { input: 0.015, output: 0.6, cacheRead: 0.015, cacheWrite: 0 },
+  "nemotron-3-ultra": { input: 0.1, output: 3, cacheRead: 0.1, cacheWrite: 0 },
+  "qwen3.5:397b": { input: 0.6, output: 3.6, cacheRead: 0.6, cacheWrite: 0 },
 };

package/usage.ts

@@ -0,0 +1,161 @@
+/**
+ * Ollama Cloud usage data plane: fetch and format /api/usage.
+ *
+ * Self-contained module. Depends on:
+ *   - models.ts - only for OLLAMA_BASE URL constant
+ *   - utils.ts  - fetchJsonWithTimeout
+ * Does NOT depend on provider registration, model fetching, or API key
+ * resolution (the caller resolves the key and passes it in).
+ *
+ * The /api/usage endpoint is undocumented and could change or disappear. The
+ * fetch degrades gracefully: distinct HTTP statuses map to distinct
+ * user-facing errors, and a malformed body raises a clear error rather than
+ * crashing.
+ */
+
+import type { Theme } from "@earendil-works/pi-coding-agent";
+import { OLLAMA_BASE } from "./models.ts";
+import { fetchJsonWithTimeout, httpError } from "./utils.ts";
+
+// --- Types ---
+
+export interface UsageModel {
+  name: string;
+  request_count: number;
+}
+
+export interface UsageLimit {
+  /** Fraction of the plan's cap, 0-1 (not tokens). */
+  usage: number;
+  /** Per-model request counts (not token counts). */
+  models: UsageModel[];
+}
+
+export interface UsageActivity {
+  cost?: string;
+  period?: {
+    type?: string;
+    starting_at?: string;
+    ending_at?: string;
+  };
+  models?: UsageModel[];
+}
+
+export interface UsageData {
+  limits: {
+    monthly: UsageLimit;
+  };
+  activity?: UsageActivity;
+}
+
+// --- Constants ---
+
+const USAGE_TIMEOUT_MS = 10000;
+
+// --- Validation ---
+
+/** Validate a single usage limit: a 0-1 fraction plus per-model request counts. */
+export function isUsageLimit(data: unknown): data is UsageLimit {
+  if (data == null || typeof data !== "object") return false;
+  const d = data as UsageLimit;
+  return (
+    typeof d.usage === "number" &&
+    Array.isArray(d.models) &&
+    d.models.every(
+      (m) =>
+        m != null &&
+        typeof m === "object" &&
+        typeof (m as UsageModel).name === "string" &&
+        typeof (m as UsageModel).request_count === "number",
+    )
+  );
+}
+
+/** Validate a parsed /api/usage response: must have a monthly limit. */
+export function isUsageResponse(data: unknown): data is UsageData {
+  if (data == null || typeof data !== "object") return false;
+  const d = data as UsageData;
+  return d.limits != null && typeof d.limits === "object" && isUsageLimit(d.limits.monthly);
+}
+
+// --- Fetch ---
+
+/**
+ * Fetch Ollama Cloud usage from the undocumented /api/usage endpoint.
+ * The caller resolves the API key and passes it in.
+ */
+export async function fetchUsage(apiKey: string, externalSignal?: AbortSignal): Promise<UsageData> {
+  const res = await fetchJsonWithTimeout<UsageData>(
+    `${OLLAMA_BASE}/api/usage`,
+    {
+      method: "GET",
+      headers: { Authorization: `Bearer ${apiKey}` },
+    },
+    USAGE_TIMEOUT_MS,
+    externalSignal,
+  );
+
+  if (!res.ok) {
+    // The 404 case is specific to this undocumented endpoint: it may have
+    // changed or disappeared, so surface that distinctly before the shared
+    // status mapping.
+    if (res.status === 404) {
+      throw new Error(
+        "Ollama Cloud usage failed: the /api/usage endpoint is unavailable (status 404). " +
+          "It is undocumented and may have changed.",
+      );
+    }
+    httpError("usage", res.status, res.error);
+  }
+  if (!isUsageResponse(res.data)) {
+    throw new Error("Ollama Cloud usage failed: unexpected response shape from the API.");
+  }
+  return res.data;
+}
+
+// --- Formatting ---
+
+/** Clamp a 0-1 usage fraction to a 0-100 percentage for display. */
+function usagePercent(usage: number): number {
+  if (!Number.isFinite(usage)) return 0;
+  return Math.min(Math.max(Math.round(usage * 100), 0), 100);
+}
+
+/** Format usage for the /ollama-cloud-usage command output. */
+export function formatUsage(data: UsageData): string {
+  const lines: string[] = ["Ollama Cloud usage:"];
+
+  const monthlyPct = usagePercent(data.limits.monthly.usage);
+  lines.push(`  Monthly (30d): ${monthlyPct}%`);
+  for (const m of data.limits.monthly.models) {
+    lines.push(`    - ${m.name}: ${m.request_count} request${m.request_count === 1 ? "" : "s"}`);
+  }
+
+  if (typeof data.activity?.cost === "string") {
+    lines.push(`  Activity (4wk): $${data.activity.cost}`);
+  }
+
+  return lines.join("\n");
+}
+
+/** Render a 10-character quota bar for a 0-100 percentage. */
+function quotaBar(pct: number): string {
+  const filled = Math.min(Math.max(Math.floor(pct / 10), 0), 10);
+  return `▕${"█".repeat(filled)}${"░".repeat(10 - filled)}▏`;
+}
+
+/** Color a single usage segment by how close it is to the cap. */
+function colorSegment(theme: Theme, label: string, pct: number): string {
+  const color = pct >= 80 ? "error" : pct >= 60 ? "warning" : "success";
+  return theme.fg(color, `${label} ${quotaBar(pct)} ${pct}%`);
+}
+
+/**
+ * Compact one-line usage for the footer status bar, colored by usage level.
+ * The endpoint exposes a monthly reset period but not an exact timestamp, so
+ * the color reflects the usage fraction rather than pace.
+ */
+export function formatUsageStatusColored(theme: Theme, data: UsageData): string {
+  const monthly = usagePercent(data.limits.monthly.usage);
+  return colorSegment(theme, "30d", monthly);
+}

package/utils.ts

@@ -1,3 +1,5 @@
+import type { ExtensionContext } from "@earendil-works/pi-coding-agent";
+
 export async function fetchJsonWithTimeout<T>(
   url: string,
   init: RequestInit,
@@ -75,3 +77,37 @@ export function getContextLength(modelInfo: Record<string, unknown>): number {
   }
   return 128000;
 }
+
+/**
+ * Resolve the Ollama Cloud API key for a tool execution or command.
+ *
+ * Prefers the canonical provider auth chain (ctx.modelRegistry.getApiKeyForProvider),
+ * which honors runtime/CLI key overrides, the registered
+ * apiKey: "$OLLAMA_API_KEY" config, and stored auth.json credentials. Falls back
+ * to the OLLAMA_API_KEY env var for the case where the provider is not yet
+ * registered at call time.
+ */
+export async function getCloudApiKey(ctx: Pick<ExtensionContext, "modelRegistry">): Promise<string | undefined> {
+  return (await ctx.modelRegistry.getApiKeyForProvider("ollama-cloud")) ?? process.env.OLLAMA_API_KEY;
+}
+
+/**
+ * Throw a user-facing error for a non-ok Ollama Cloud HTTP response, mapping
+ * distinct status codes. Shared by the web tools and the usage command.
+ */
+export function httpError(op: string, status: number, error?: string): never {
+  if (status === 401 || status === 403) {
+    throw new Error(
+      `Ollama Cloud ${op} failed: authentication error. Check your API key in OLLAMA_API_KEY or auth.json.`,
+    );
+  }
+  if (status === 429) {
+    throw new Error(`Ollama Cloud ${op} failed: rate limited. Try again shortly.`);
+  }
+  if (status >= 500) {
+    throw new Error(`Ollama Cloud ${op} failed: server error (status ${status}). Try again shortly.`);
+  }
+  throw new Error(
+    `Ollama Cloud ${op} failed: unexpected response (status ${status}${error ? `: ${error}` : ""}). Try again shortly.`,
+  );
+}

package/web-tools.ts

@@ -19,7 +19,6 @@
 import {
   type AgentToolResult,
   type ExtensionAPI,
-  type ExtensionContext,
   keyHint,
   type Theme,
   type ToolRenderResultOptions,
@@ -28,7 +27,7 @@ import {
 import { type Component, Text, truncateToWidth } from "@earendil-works/pi-tui";
 import { Type } from "@sinclair/typebox";
 import { OLLAMA_BASE } from "./models.ts";
-import { fetchJsonWithTimeout } from "./utils.ts";
+import { fetchJsonWithTimeout, getCloudApiKey, httpError } from "./utils.ts";
 
 // --- Types ---
 
@@ -50,62 +49,11 @@ interface FetchResponse {
 
 const WEB_TOOLS_TIMEOUT_MS = 15000;
 
-/**
- * Resolve the Ollama Cloud API key for a tool execution.
- *
- * Prefers the canonical provider auth chain (ctx.modelRegistry.getApiKeyForProvider),
- * which honors runtime/CLI key overrides, the registered
- * apiKey: "$OLLAMA_API_KEY" config, and stored auth.json credentials. Falls back
- * to the OLLAMA_API_KEY env var for the case where the provider is not yet
- * registered at tool-call time.
- *
- * Exported for unit testing.
- */
-export async function getCloudApiKey(ctx: Pick<ExtensionContext, "modelRegistry">): Promise<string | undefined> {
-  return (await ctx.modelRegistry.getApiKeyForProvider("ollama-cloud")) ?? process.env.OLLAMA_API_KEY;
-}
-
 /** Throw a no-API-key error. */
 function noApiKeyError(): never {
   throw new Error("No Ollama Cloud API key configured. Set OLLAMA_API_KEY or add to auth.json.");
 }
 
-/** Throw a search error for a non-ok result, mapping distinct status codes. */
-function searchError(status: number, error?: string): never {
-  if (status === 401 || status === 403) {
-    throw new Error(
-      "Ollama Cloud search failed: authentication error. " + "Check your API key in OLLAMA_API_KEY or auth.json.",
-    );
-  }
-  if (status === 429) {
-    throw new Error("Ollama Cloud search failed: rate limited. Try again shortly.");
-  }
-  if (status >= 500) {
-    throw new Error(`Ollama Cloud search failed: server error (status ${status}). Try again shortly.`);
-  }
-  throw new Error(
-    `Ollama Cloud search failed: unexpected response (status ${status}${error ? `: ${error}` : ""}). Try again shortly.`,
-  );
-}
-
-/** Throw a fetch error for a non-ok result, mapping distinct status codes. */
-function fetchError(status: number, error?: string): never {
-  if (status === 401 || status === 403) {
-    throw new Error(
-      "Ollama Cloud fetch failed: authentication error. " + "Check your API key in OLLAMA_API_KEY or auth.json.",
-    );
-  }
-  if (status === 429) {
-    throw new Error("Ollama Cloud fetch failed: rate limited. Try again shortly.");
-  }
-  if (status >= 500) {
-    throw new Error(`Ollama Cloud fetch failed: server error (status ${status}). Try again shortly.`);
-  }
-  throw new Error(
-    `Ollama Cloud fetch failed: unexpected response (status ${status}${error ? `: ${error}` : ""}). Try again shortly.`,
-  );
-}
-
 const PREVIEW_LINES = 8;
 
 /**
@@ -232,7 +180,7 @@ export function registerWebSearchTool(pi: ExtensionAPI) {
       );
 
       if (!res.ok) {
-        searchError(res.status, res.error);
+        httpError("search", res.status, res.error);
       }
       if (!isSearchResponse(res.data)) {
         throw new Error("Web search failed: unexpected response shape from the API.");
@@ -287,7 +235,7 @@ export function registerWebFetchTool(pi: ExtensionAPI) {
       );
 
       if (!res.ok) {
-        fetchError(res.status, res.error);
+        httpError("fetch", res.status, res.error);
       }
       if (!isFetchResponse(res.data)) {
         throw new Error("Web fetch failed: unexpected response shape from the API.");