pi-ollama-cloud 0.10.0 → 0.12.0

package/CHANGELOG.md

@@ -2,7 +2,21 @@
 
 All notable changes to this project will be documented in this file.
 
-## [Unreleased]
+## [0.12.0] - 2026-09-11
+
+- Source per-model thinking levels from models.dev instead of hardcoded maps. `scripts/generate-reasoning.ts` fetches the `ollama-cloud` provider's `reasoning_options` into `reasoning.generated.ts`, and `thinking-levels.ts` maps each model's effort values onto Pi's levels (toggle-only models become a binary on/off map; models with no models.dev entry fall back to `DEFAULT`). The `off` switch is handled by a small override table for models verified not to honor `reasoning_effort:"none"` (`gpt-oss:20b`, `gpt-oss:120b`, `minimax-m2.7`). Removed the now-stale per-family maps and the `docs/think-experiment.md` doc.
+- `generate-models` now also refreshes `reasoning.generated.ts` (runs `generate-pricing`, `generate-reasoning`, then `generate-models`).
+- Fix `generate-pricing` mis-dropping models whose pricing-page cached-input cell is `-` (no cache rate): those rows now match and their `cacheRead` equals `input`. This restored pricing for `mistral-large-3:675b`, `nemotron-3-nano:30b`, and `qwen3.5:397b`, which the earlier regex had left at zero cost.
+- Refresh the model catalog: added `deepseek-v4.1-flash` (probed max output 393216).
+
+## [0.11.0] - 2026-09-07
+
+- Fix `/ollama-cloud-usage` and the usage status bar failing with "unexpected response shape" after the undocumented `/api/usage` endpoint flipped between a single `limits.monthly` bucket and `limits.session` plus `limits.weekly` (the shape has flip-flopped repeatedly as of 2026-09). Any bucket present (`monthly`, `session`, `weekly`) is accepted alone or in combination, and whichever are present are displayed as `5h`/`7d`/`30d` segments. Thanks @johanngyger (#56).
+- Cache `ollama_web_search` results (24h) and `ollama_web_fetch` pages (24h success / 15 min failure) on disk under the pi agent home, so repeated queries and page reads cost 0 API calls. Expired entries are pruned on write, the cache is capped at 500 entries per kind (oldest evicted beyond the cap; `PI_OLLAMA_SEARCH_MAX_ENTRIES`), a partially corrupted cache file is validated per entry and degrades to "no cache" instead of crashing tool calls, and the file is written with `0600` permissions since it stores page content and URLs that can embed credentials. Tune with `PI_OLLAMA_SEARCH_TTL_HOURS`, `PI_OLLAMA_SEARCH_FAIL_TTL_MINUTES`, `PI_OLLAMA_SEARCH_MAX_ENTRIES`, and `PI_OLLAMA_SEARCH_CACHE_PATH`.
+- Bound web tool context usage: search snippets truncate to 500 chars with `[truncated]`/`[complete]` markers, `expand=<index>` returns a truncated result's full content from the cached search (0 extra API calls), and `ollama_web_fetch` pages long pages in 3000-char chunks via `offset`/`full` with a `Continue:` hint for the next offset (`PI_OLLAMA_SEARCH_SNIPPET_CHARS`/`PI_OLLAMA_SEARCH_CHUNK_CHARS` to tune).
+- Add `refresh=true` to both web tools to bypass the cache (including a cached failure) and re-call the API; the fresh result replaces the cache entry.
+- Failed page fetches are negative-cached for 15 min with a diagnostic message (likely cause + next steps) instead of a bare error. Auth (401/403), rate-limit (429), transport (timeout/abort/network), server (5xx), and unexpected-response-shape failures are never cached — search reports transport errors as `transport error` instead of a confusing `status 0` — so retrying after a fixed key, an expired rate-limit window, or a transient server blip re-calls the API immediately.
+- Note: `ollama_web_fetch` tool results now carry `details: { title, totalChars, links }` (previously `{ title, content, links }`); paged content is read via the tool output text, not `details.content`.
 
 ## [0.10.0] - 2026-09-03
 

package/README.md

@@ -7,7 +7,7 @@ Registers Ollama Cloud as a model provider with dynamically fetched models, and
 ## Features
 
 - **Dynamic model discovery** - Fetches the full model list from `ollama.com/v1/models`, then fetches per-model details via `/api/show` to determine capabilities, context length, and tool support.
-- **Curated thinking levels** - Maps Pi's thinking levels to Ollama Cloud's OpenAI-compatible `reasoning_effort` values via `thinking-levels.ts`, with per-model exceptions based on API testing.
+- **Data-driven thinking levels** - Maps Pi's thinking levels to Ollama Cloud's OpenAI-compatible `reasoning_effort` values via `thinking-levels.ts`, sourced from models.dev per-model reasoning options with a small override table for the models where `none` doesn't disable thinking.
 - **Baked-in model list** - A generated fallback list (`models.generated.ts`) ships with the extension so models are available on first launch without any network calls. It is only a fallback: pi refreshes the live catalog at runtime, so shipping a new release for catalog freshness is no longer needed.
 - **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.
@@ -132,7 +132,7 @@ Model metadata is derived from the `/api/show` response:
 | Field | Source |
 |---|---|
 | `reasoning` | `capabilities` includes `"thinking"` |
-| `thinkingLevelMap` | [`thinking-levels.ts`](thinking-levels.ts) with 5 maps (DEFAULT, GPT_OSS, QWEN3, GLM_52, NO_OFF) based on API testing |
+| `thinkingLevelMap` | [`thinking-levels.ts`](thinking-levels.ts) + [`reasoning.generated.ts`](reasoning.generated.ts) (models.dev reasoning options), with an `off` override table for models that ignore `none` |
 | `input` | `["text", "image"]` if `capabilities` includes `"vision"`, else `["text"]` |
 | `contextWindow` | `model_info.*.context_length` (falls back to 128000) |
 | `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. |
@@ -146,17 +146,11 @@ Cache pricing is informational only: the `/pricing` page lists a "Cached input"
 
 ### Thinking level mapping
 
-Pi's thinking levels are mapped to Ollama Cloud's OpenAI-compatible `reasoning_effort` parameter in [`thinking-levels.ts`](thinking-levels.ts). The API accepts `none`, `low`, `medium`, `high`, and `max`. Effects of `max` over `high` vary by model and prompt difficulty - see [`docs/think-experiment.md`](docs/think-experiment.md) for details.
+Pi's thinking levels are mapped to Ollama Cloud's OpenAI-compatible `reasoning_effort` parameter in [`thinking-levels.ts`](thinking-levels.ts). The API accepts `none`, `low`, `medium`, `high`, `xhigh`, and `max`. Effects of `max` over `high` vary by model and prompt difficulty.
 
-| Map | Models | Levels exposed | Notes |
-|---|---|---|---|
-| `DEFAULT` | Most thinking models | off, low, medium, high, xhigh | `minimal` hidden (duplicate of low) |
-| `GPT_OSS` | `gpt-oss*` | low, medium, high | Can't disable thinking, no off or xhigh |
-| `QWEN3` | `qwen3*` (except `qwen3-vl*`) | off, medium | Binary-only (think/nothink), no gradation |
-| `GLM_52` | `glm-5.2` | off, high, xhigh | GLM supports disabled thinking; Ollama's model page confirms `high` and `max` reasoning efforts |
-| `NO_OFF` | `qwen3-vl*`, `kimi-k2-thinking`, `minimax*` | low, medium, high, xhigh | "none" doesn't disable thinking on these models |
+Per-model support is sourced from models.dev: [`scripts/generate-reasoning.ts`](scripts/generate-reasoning.ts) fetches the `ollama-cloud` provider's `reasoning_options` into `reasoning.generated.ts`, and `resolve()` maps each model's effort values onto Pi's levels. Models with `effort` values expose those grades; `toggle`-only models expose a single on/off level. Models with no models.dev entry fall back to `DEFAULT`.
 
-See [docs/think-experiment.md](docs/think-experiment.md) for the testing methodology and results.
+Because the API reports only a boolean `thinking` capability and models.dev does not reliably encode the `none` behavior, the `off` switch is handled via a small override table in `thinking-levels.ts`: it defaults to enabled, and is hidden only for models verified (by live probing) not to honor `reasoning_effort:"none"` - currently `gpt-oss:20b`, `gpt-oss:120b`, and `minimax-m2.7`. The per-model metadata gaps behind the models.dev sourcing are tracked upstream in [ollama/ollama#18385](https://github.com/ollama/ollama/issues/18385).
 
 ## Tools
 
@@ -167,19 +161,60 @@ See [docs/think-experiment.md](docs/think-experiment.md) for the testing methodo
 
 Both tools use the same Ollama Cloud API key configured for the provider. No local Ollama server is needed.
 
+### Caching
+
+Both tools cache results on disk (under the pi agent home, `~/.pi/agent/cache/pi-ollama-cloud/cache.json`). A repeated search query or page fetch within the TTL is served from cache and costs 0 API calls:
+
+- Successful searches and pages: cached for 24h
+- Failed page fetches: negative-cached for 15 min, so retrying a dead page does not re-call the API. Auth (401/403), rate-limit (429), transport (timeouts, aborts, network errors), and server (5xx) failures are not cached — fixing the key, waiting out the limit, or a transient blip lets a retry through immediately
+- Expired entries are pruned on write and the cache is capped at 500 entries per kind (searches/pages), evicting the oldest first. This bounds entry count, not file size: full page and search content can still make `cache.json` large, and loading it parses the whole file
+- The cache file is written with `0600` permissions. It stores full page content and raw URLs, which can embed credentials in query strings — avoid fetching URLs that carry secrets in the query string, or set a custom `PI_OLLAMA_SEARCH_CACHE_PATH`
+- Concurrent pi processes share the cache file on a last-writer-wins basis (no cross-process locking): one process's save can drop another's fresh entries, at the cost of a redundant API call
+- `refresh=true` on either tool bypasses the cache (including a cached failure) and re-calls the API; the fresh result replaces the cache entry
+
+### `ollama_web_search`
+
+Returns up to 5 results by default (`max_results`, max 10; title, URL, 500-char snippet). Snippets are marked `[truncated]` when the source is longer than the snippet. Output ends with `# live query` or `# from cache` to show whether the API was called.
+
+The search API returns each result's full content; it is cached in full, so a truncated result can be expanded without a separate fetch:
+
+- `expand=<index>` — return the full content of that result (1-based) from the cached search, 0 extra API calls. The cache key includes `max_results`, so expanding hits the cache only when the query was searched with the same `max_results`; otherwise the search runs live first.
+- Use `ollama_web_fetch` only when the search result's content is not enough (e.g. you need a different page, or the search excerpt is shorter than the full page).
+
+### `ollama_web_fetch`
+
+Returns the page title, a 3000-char slice of the content, and links. Long pages are read in chunks to keep the context window small:
+
+- `offset=N` — continue reading from character N (the output tells you the next offset)
+- `full=true` — return all remaining content from `offset` in one call
+
+A failed fetch throws a diagnostic message (likely cause + next steps) instead of a bare error.
+
+### Tuning
+
+| Env var | Default | Meaning |
+|---|---|---|
+| `PI_OLLAMA_SEARCH_TTL_HOURS` | `24` | Success cache TTL |
+| `PI_OLLAMA_SEARCH_FAIL_TTL_MINUTES` | `15` | Failure (negative) cache TTL |
+| `PI_OLLAMA_SEARCH_CACHE_PATH` | `<pi agent home>/cache/pi-ollama-cloud/cache.json` | Cache file location |
+| `PI_OLLAMA_SEARCH_MAX_ENTRIES` | `500` | Max cached entries per kind (searches/pages); oldest evicted beyond the cap |
+| `PI_OLLAMA_SEARCH_SNIPPET_CHARS` | `500` | Search snippet length |
+| `PI_OLLAMA_SEARCH_CHUNK_CHARS` | `3000` | Fetch chunk size |
+
 ## Commands
 
 | 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-cloud-usage` | Show Ollama Cloud usage limits (one section per limit bucket the API reports), 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
+live usage readout with one segment per limit bucket the API reports
+(`5h ▕███░░░░░░░▏ 34% 7d ▕█░░░░░░░░░▏ 7%`, or a single `30d` segment) 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.

package/cache.ts

@@ -0,0 +1,181 @@
+import { createHash, randomBytes } from "node:crypto";
+import { chmodSync, mkdirSync, readFileSync, renameSync, rmSync, writeFileSync } from "node:fs";
+import { dirname, join } from "node:path";
+import { getAgentDir } from "@earendil-works/pi-coding-agent";
+import { envInt } from "./utils.ts";
+
+export const CACHE_PATH =
+  process.env.PI_OLLAMA_SEARCH_CACHE_PATH ?? join(getAgentDir(), "cache", "pi-ollama-cloud", "cache.json");
+export const CACHE_TTL_MS = envInt("PI_OLLAMA_SEARCH_TTL_HOURS", 24) * 60 * 60 * 1000;
+export const FAIL_TTL_MS = envInt("PI_OLLAMA_SEARCH_FAIL_TTL_MINUTES", 15) * 60 * 1000;
+/** Max entries per map (searches/pages); oldest-ts entries are evicted beyond this. */
+export const MAX_ENTRIES = envInt("PI_OLLAMA_SEARCH_MAX_ENTRIES", 500);
+
+export interface SearchResult {
+  title: string;
+  url: string;
+  content: string;
+}
+
+export interface SearchCacheEntry {
+  ts: number;
+  q: string;
+  results: SearchResult[];
+}
+
+export interface PageCacheEntry {
+  ts: number;
+  status?: number;
+  title?: string;
+  content?: string;
+  links?: string[] | null;
+  error?: string;
+  errorType?: "response-shape";
+}
+
+export interface CacheData {
+  searches: Record<string, SearchCacheEntry>;
+  pages: Record<string, PageCacheEntry>;
+}
+
+interface CacheOptions {
+  path: string;
+  ttlMs: number;
+  failTtlMs: number;
+  maxEntries: number;
+}
+
+function isRecord(v: unknown): v is Record<string, unknown> {
+  return typeof v === "object" && v !== null && !Array.isArray(v);
+}
+
+/** Keys that must never come from a parsed JSON file (prototype pollution). */
+const UNSAFE_KEYS = new Set(["__proto__", "constructor", "prototype"]);
+
+export function isSafeKey(key: string): boolean {
+  return !UNSAFE_KEYS.has(key);
+}
+
+/** Shallow shape checks so a partially corrupted cache file degrades instead of crashing tool calls. */
+function isSearchEntry(v: unknown): v is SearchCacheEntry {
+  return (
+    isRecord(v) &&
+    typeof v.ts === "number" &&
+    typeof v.q === "string" &&
+    Array.isArray(v.results) &&
+    v.results.every(
+      (r) => isRecord(r) && typeof r.title === "string" && typeof r.url === "string" && typeof r.content === "string",
+    )
+  );
+}
+
+function isPageEntry(v: unknown): v is PageCacheEntry {
+  if (!isRecord(v) || typeof v.ts !== "number") return false;
+  const fieldsValid =
+    (v.status === undefined || typeof v.status === "number") &&
+    (v.title === undefined || typeof v.title === "string") &&
+    (v.content === undefined || typeof v.content === "string") &&
+    (v.links === null ||
+      v.links === undefined ||
+      (Array.isArray(v.links) && v.links.every((l) => typeof l === "string"))) &&
+    (v.error === undefined || (typeof v.error === "string" && v.error !== "")) &&
+    (v.errorType === undefined || v.errorType === "response-shape");
+  if (!fieldsValid) return false;
+  // Must be either a real failure or a real success; anything else (e.g. an
+  // entry with neither content nor a non-empty error) would render as a fake
+  // empty success.
+  return (
+    (typeof v.error === "string" && v.error !== "") || (typeof v.title === "string" && typeof v.content === "string")
+  );
+}
+
+export interface CacheStore {
+  loadCache(): CacheData;
+  saveCache(): void;
+  isFresh(entry: { ts: number; error?: string } | undefined): boolean;
+}
+
+export function createCache(options: Partial<CacheOptions> = {}): CacheStore {
+  const path = options.path ?? CACHE_PATH;
+  const ttlMs = options.ttlMs ?? CACHE_TTL_MS;
+  const failTtlMs = options.failTtlMs ?? FAIL_TTL_MS;
+  const maxEntries = options.maxEntries ?? MAX_ENTRIES;
+  let cacheData: CacheData | null = null;
+
+  function loadCache(): CacheData {
+    if (cacheData) return cacheData;
+    try {
+      const raw: unknown = JSON.parse(readFileSync(path, "utf8"));
+      if (isRecord(raw) && isRecord(raw.searches) && isRecord(raw.pages)) {
+        // Per-entry validation: drop poisoned entries so a partially corrupt
+        // file degrades to "those entries are gone" instead of crashing calls.
+        cacheData = { searches: {}, pages: {} };
+        for (const [key, entry] of Object.entries(raw.searches)) {
+          if (isSafeKey(key) && isSearchEntry(entry)) cacheData.searches[key] = entry;
+        }
+        for (const [key, entry] of Object.entries(raw.pages)) {
+          if (isSafeKey(key) && isPageEntry(entry)) cacheData.pages[key] = entry;
+        }
+        return cacheData;
+      }
+    } catch {
+      // First run or corrupt file, start fresh.
+    }
+    cacheData = { searches: {}, pages: {} };
+    return cacheData;
+  }
+
+  function isFresh(entry: { ts: number; error?: string } | undefined): boolean {
+    if (!entry) return false;
+    // A future ts (hand-edited file) would otherwise be fresh forever; treat as stale.
+    if (entry.ts > Date.now()) return false;
+    return Date.now() - entry.ts < (entry.error ? failTtlMs : ttlMs);
+  }
+
+  function evictOldest(map: Record<string, { ts: number }>): void {
+    const keys = Object.keys(map);
+    if (keys.length <= maxEntries) return;
+    const overflow = keys.sort((a, b) => map[a].ts - map[b].ts).slice(0, keys.length - maxEntries);
+    for (const key of overflow) delete map[key];
+  }
+
+  function saveCache(): void {
+    const data = loadCache();
+    for (const [key, entry] of Object.entries(data.searches)) if (!isFresh(entry)) delete data.searches[key];
+    for (const [key, entry] of Object.entries(data.pages)) if (!isFresh(entry)) delete data.pages[key];
+    // TTL bounds entry age; the cap bounds entry count so an aggressive session
+    // cannot grow the file without limit.
+    evictOldest(data.searches);
+    evictOldest(data.pages);
+    try {
+      mkdirSync(dirname(path), { recursive: true, mode: 0o700 });
+      // Use a unique temporary path so concurrent processes cannot overwrite
+      // one another's in-progress writes.
+      const tmp = `${path}.${process.pid}.${randomBytes(8).toString("hex")}.tmp`;
+      try {
+        // 0o600: the cache stores full page content and URLs, which can embed
+        // credentials in query strings; it should not be world-readable.
+        writeFileSync(tmp, JSON.stringify(data), { mode: 0o600 });
+        renameSync(tmp, path);
+        // Fix perms of a file written by a pre-0600 version.
+        chmodSync(path, 0o600);
+      } catch (error) {
+        rmSync(tmp, { force: true });
+        throw error;
+      }
+    } catch {
+      // Cache is best-effort; a failed write must not break the tool call.
+    }
+  }
+
+  return { loadCache, saveCache, isFresh };
+}
+
+export const defaultCache = createCache();
+export const loadCache = defaultCache.loadCache;
+export const saveCache = defaultCache.saveCache;
+export const isFresh = defaultCache.isFresh;
+
+export function searchCacheKey(query: string, maxResults: number): string {
+  return createHash("sha1").update(`${query}\n${maxResults}`).digest("hex");
+}

package/index.ts

@@ -134,7 +134,7 @@ export default async function (pi: ExtensionAPI) {
   // --- Usage Command ---
 
   pi.registerCommand("ollama-cloud-usage", {
-    description: "Show Ollama Cloud monthly usage limits.",
+    description: "Show Ollama Cloud usage limits.",
     handler: async (_args, ctx) => {
       const apiKey = await getCloudApiKey(ctx);
       if (!apiKey) {
@@ -152,7 +152,7 @@ export default async function (pi: ExtensionAPI) {
 
   // --- Usage Status Bar ---
 
-  // Footer status showing live monthly usage while ollama-cloud is the
+  // Footer status showing live 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

package/limits.generated.ts

@@ -1,10 +1,11 @@
 // Auto-generated by scripts/generate-limits.ts
 // Do not edit manually.
-// Probed models: 19 (0 failed)
+// Entries: 20
 
 export const MODEL_MAX_OUTPUT_TOKENS: Record<string, number> = {
   "deepseek-v4-flash:0731": 65536,
   "deepseek-v4-pro:0813": 65536,
+  "deepseek-v4.1-flash": 393216,
   "gemma4:31b": 262144,
   "glm-5.1": 131072,
   "glm-5.2": 131072,

package/models.generated.ts

@@ -1,7 +1,7 @@
 // Auto-generated by scripts/generate-models.ts
 // Do not edit manually.
-// Generated: 2026-09-03T10:12:02.243Z
-// Model count: 19
+// Generated: 2026-09-12T02:41:57.025Z
+// Model count: 20
 
 import type { ProviderModelConfig } from "@earendil-works/pi-coding-agent";
 
@@ -39,8 +39,8 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
-      low: "low",
-      medium: "medium",
+      low: null,
+      medium: null,
       minimal: null,
       off: "none",
       xhigh: "max",
@@ -77,10 +77,50 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     input: ["text"],
     maxTokens: 65536,
     reasoning: true,
+    thinkingLevelMap: {
+      high: "high",
+      low: null,
+      medium: null,
+      minimal: null,
+      off: "none",
+      xhigh: "max",
+    },
+  },
+  {
+    id: "deepseek-v4.1-flash",
+    name: "deepseek-v4.1-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: 0.006,
+      cacheWrite: 0,
+      input: 0.3,
+      output: 1.2,
+    },
+    input: ["text", "image"],
+    maxTokens: 393216,
+    reasoning: true,
     thinkingLevelMap: {
       high: "high",
       low: "low",
-      medium: "medium",
+      medium: null,
       minimal: null,
       off: "none",
       xhigh: "max",
@@ -118,12 +158,12 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     maxTokens: 262144,
     reasoning: true,
     thinkingLevelMap: {
-      high: "high",
-      low: "low",
+      high: null,
+      low: null,
       medium: "medium",
       minimal: null,
       off: "none",
-      xhigh: "max",
+      xhigh: null,
     },
   },
   {
@@ -158,12 +198,12 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     maxTokens: 131072,
     reasoning: true,
     thinkingLevelMap: {
-      high: "high",
-      low: "low",
+      high: null,
+      low: null,
       medium: "medium",
       minimal: null,
       off: "none",
-      xhigh: "max",
+      xhigh: null,
     },
   },
   {
@@ -240,7 +280,7 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     thinkingLevelMap: {
       high: "high",
       low: "low",
-      medium: "medium",
+      medium: null,
       minimal: null,
       off: "none",
       xhigh: "max",
@@ -280,7 +320,7 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     thinkingLevelMap: {
       high: "high",
       low: "low",
-      medium: "medium",
+      medium: null,
       minimal: null,
       off: "none",
       xhigh: "max",
@@ -398,12 +438,12 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     maxTokens: 262144,
     reasoning: true,
     thinkingLevelMap: {
-      high: "high",
-      low: "low",
+      high: null,
+      low: null,
       medium: "medium",
       minimal: null,
       off: "none",
-      xhigh: "max",
+      xhigh: null,
     },
   },
   {
@@ -438,12 +478,12 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     maxTokens: 262144,
     reasoning: true,
     thinkingLevelMap: {
-      high: "high",
-      low: "low",
+      high: null,
+      low: null,
       medium: "medium",
       minimal: null,
       off: "none",
-      xhigh: "max",
+      xhigh: null,
     },
   },
   {
@@ -480,7 +520,7 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     thinkingLevelMap: {
       high: "high",
       low: "low",
-      medium: "medium",
+      medium: null,
       minimal: null,
       off: "none",
       xhigh: "max",
@@ -518,12 +558,12 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     maxTokens: 131072,
     reasoning: true,
     thinkingLevelMap: {
-      high: "high",
-      low: "low",
+      high: null,
+      low: null,
       medium: "medium",
       minimal: null,
       off: null,
-      xhigh: "max",
+      xhigh: null,
     },
   },
   {
@@ -562,7 +602,7 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       low: "low",
       medium: "medium",
       minimal: null,
-      off: null,
+      off: "none",
       xhigh: "max",
     },
   },
@@ -630,12 +670,12 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     maxTokens: 131072,
     reasoning: true,
     thinkingLevelMap: {
-      high: "high",
-      low: "low",
+      high: null,
+      low: null,
       medium: "medium",
       minimal: null,
       off: "none",
-      xhigh: "max",
+      xhigh: null,
     },
   },
   {
@@ -670,12 +710,12 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     maxTokens: 65536,
     reasoning: true,
     thinkingLevelMap: {
-      high: "high",
-      low: "low",
+      high: null,
+      low: null,
       medium: "medium",
       minimal: null,
       off: "none",
-      xhigh: "max",
+      xhigh: null,
     },
   },
   {
@@ -710,12 +750,12 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     maxTokens: 65536,
     reasoning: true,
     thinkingLevelMap: {
-      high: "high",
-      low: "low",
+      high: null,
+      low: null,
       medium: "medium",
       minimal: null,
       off: "none",
-      xhigh: "max",
+      xhigh: null,
     },
   },
   {

package/models.ts

@@ -93,7 +93,7 @@ function buildCompat(): ProviderModelConfig["compat"] {
   return {
     // Ollama uses "system" role, not "developer" (ollama: docs.ollama.com/api/openai-compatibility, pi: types.ts#supportsDeveloperRole).
     supportsDeveloperRole: false,
-    // reasoning_effort works (ollama: docs.ollama.com/api/openai-compatibility, pi: types.ts#supportsReasoningEffort, tested in think-experiment.md).
+    // reasoning_effort works (ollama: docs.ollama.com/api/openai-compatibility, pi: types.ts#supportsReasoningEffort).
     supportsReasoningEffort: true,
     // "store" is not a supported field (ollama: docs.ollama.com/api/openai-compatibility, pi: types.ts#supportsStore).
     supportsStore: false,
@@ -109,7 +109,7 @@ function buildCompat(): ProviderModelConfig["compat"] {
     requiresThinkingAsText: false,
     // DeepSeek-specific, not needed for Ollama (pi: types.ts#requiresReasoningContentOnAssistantMessages).
     requiresReasoningContentOnAssistantMessages: false,
-    // reasoning_effort format works (pi: types.ts#thinkingFormat, tested in think-experiment.md).
+    // reasoning_effort format works (pi: types.ts#thinkingFormat).
     thinkingFormat: "openai",
     // Ollama does not support tool_choice, so strict mode is unavailable (ollama: docs.ollama.com/api/openai-compatibility, pi: types.ts#supportsStrictMode).
     supportsStrictMode: false,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-ollama-cloud",
-  "version": "0.10.0",
+  "version": "0.12.0",
   "type": "module",
   "keywords": [
     "pi-package"
@@ -8,10 +8,12 @@
   "files": [
     "index.ts",
     "config.ts",
+    "cache.ts",
     "limits.generated.ts",
     "models.ts",
     "models.generated.ts",
     "pricing.generated.ts",
+    "reasoning.generated.ts",
     "thinking-levels.ts",
     "usage.ts",
     "utils.ts",
@@ -31,8 +33,9 @@
     "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-limits": "tsx scripts/generate-limits.ts && biome format --write limits.generated.ts"
+    "generate-models": "tsx scripts/generate-pricing.ts && tsx scripts/generate-reasoning.ts && tsx scripts/generate-models.ts && biome format --write models.generated.ts pricing.generated.ts reasoning.generated.ts",
+    "generate-limits": "tsx scripts/generate-limits.ts",
+    "generate-reasoning": "tsx scripts/generate-reasoning.ts && biome format --write reasoning.generated.ts"
   },
   "pi": {
     "extensions": [
@@ -50,6 +53,6 @@
     "@types/node": "^26.1.2",
     "@typescript/native-preview": "7.0.0-dev.20260707.2",
     "tsx": "^4.19.0",
-    "vitest": "^4.1.6"
+    "vitest": "^4.1.11"
   }
 }

package/pricing.generated.ts

@@ -1,7 +1,7 @@
 // Auto-generated by scripts/generate-pricing.ts
 // Do not edit manually.
-// Generated: 2026-09-03T10:12:00.135Z
-// Model count: 19
+// Generated: 2026-09-12T02:41:55.206Z
+// Model count: 20
 
 export interface ModelPrice {
   input: number;
@@ -13,6 +13,7 @@ export interface ModelPrice {
 export const MODEL_PRICING: Record<string, ModelPrice> = {
   "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 },
+  "deepseek-v4.1-flash": { input: 0.3, output: 1.2, cacheRead: 0.006, 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 },