pi-ollama-cloud 0.6.0 → 0.7.0

package/CHANGELOG.md

@@ -2,6 +2,18 @@
 
 All notable changes to this project will be documented in this file.
 
+## [Unreleased]
+
+- Fix extension crash on pi 0.80.8+ where `AuthStorage` is no longer exported by `@earendil-works/pi-coding-agent`. Web tools now resolve the API key through the tool execution context's `modelRegistry.getApiKeyForProvider()`, preserving runtime/CLI overrides and the registered `apiKey: "$OLLAMA_API_KEY"` config. Thanks @badlogic for the cross-version analysis (#34, #35, #37).
+- Restore the `OLLAMA_API_KEY` env-var fallback in `ollama_web_search` and `ollama_web_fetch`. Thanks @cawilliamson (#26).
+- Add a 15s timeout to web search/fetch requests and preserve tool-cancellation by extending `fetchJsonWithTimeout` with an external `AbortSignal`.
+- Always target `https://ollama.com` and warn when `OLLAMA_API_BASE` is set to a non-cloud host, instead of silently querying a local Ollama daemon. Thanks @valueforvalue (#32, #33).
+- Add a `glm-5.2` thinking level map exposing `off`, `high`, and `xhigh` (`reasoning_effort: "none"`, `"high"`, `"max"`). Thanks @Thinkscape (#29).
+- Add estimated per-token pricing for Ollama Cloud models so `/cost` shows comparable usage. Prices are generated from [models.dev](https://models.dev) (the same source pi uses) via `scripts/generate-pricing.ts` into `pricing.generated.ts`, not hand-typed, and regenerate with the catalog via `npm run generate-models`. Prices are pinned to the installed package version: `/ollama-cloud-refresh` updates the model list and metadata but does not re-fetch prices, so newly added models register with zero cost until the next release. Not actual subscription charges. Thanks @DxTa (#9).
+- Refresh the generated model catalog from the live Ollama Cloud API. Adds `glm-5.2` (1M context, text-only) and `kimi-k2.7-code` (262K context, text + image). `deepseek-v4-pro` context window is now 524288 (was 1048576).
+- Retire models deprecated per https://docs.ollama.com/cloud#deprecations: July 15, 2026 batch (`deepseek-v3.1:671b`, `deepseek-v3.2`, `devstral-2:123b`, `devstral-small-2:24b`, `ministral-3:14b`, `ministral-3:3b`, `ministral-3:8b`, `gemini-3-flash-preview`, `gemma3:12b`, `gemma3:27b`, `gemma3:4b`, `glm-4.7`, `glm-5`, `minimax-m2.1`, `qwen3-coder-next`, `qwen3-coder:480b`) and June 30 (`rnj-1:8b`). The shipped catalog goes from 30 to 18 models.
+- Bump `@earendil-works/pi-coding-agent` runtime dependency to 0.80.10.
+
 ## [0.6.0] - 2026-06-05
 
 - Fix `apiKey` registered as a literal string instead of an environment variable reference. Changed `apiKey: "OLLAMA_API_KEY"` to `apiKey: "$OLLAMA_API_KEY"` in `registerProvider`, resolving the deprecation warning emitted by pi v0.77.0+ and making the `OLLAMA_API_KEY` env var work alongside `auth.json` (env var takes priority, falls back to `auth.json`). Thanks @mandusm (#21).

package/README.md

@@ -1,6 +1,6 @@
 # pi-ollama-cloud
 
-Ollama Cloud provider plugin for [Pi](https://github.com/badlogic/pi-mono) coding agent.
+Ollama Cloud provider plugin for the [Pi](https://pi.dev) coding agent.
 
 Registers Ollama Cloud as a model provider with dynamically fetched models, and provides `ollama_web_search` and `ollama_web_fetch` tools that use the [Ollama Cloud web search API](https://docs.ollama.com/capabilities/web-search) - no local Ollama server required.
 
@@ -14,7 +14,7 @@ Registers Ollama Cloud as a model provider with dynamically fetched models, and
 - **`/ollama-cloud-refresh` command** - Re-fetches the model list and updates the cache and provider registration live (no restart needed).
 - **`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.
-- **Zero cost tracking** - All models are registered with zero costs since Ollama Cloud uses a flat subscription model (Free, Pro, Max) rather than per-token billing. Per-request costs don't apply, so Pi's cost tracker always shows zero. See [ollama.com/pricing](https://ollama.com/pricing) for plan details.
+- **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.
 
 ## Prerequisites
 
@@ -142,11 +142,11 @@ Model metadata is derived from the cached data:
 | Field | Source |
 |---|---|
 | `reasoning` | `capabilities` includes `"thinking"` |
-| `thinkingLevelMap` | [`thinking-levels.ts`](thinking-levels.ts) with 4 maps (DEFAULT, GPT_OSS, QWEN3, NO_OFF) based on API testing |
+| `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` | All zeros (Ollama Cloud uses subscription plans, not per-token billing - see [pricing](https://ollama.com/pricing)) |
+| `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: `/ollama-cloud-refresh` updates the model list and metadata but does not re-fetch prices, so newly added models register with zero cost until the next release. |
 
 ### Thinking level mapping
 
@@ -157,6 +157,7 @@ Pi's thinking levels are mapped to Ollama Cloud's OpenAI-compatible `reasoning_e
 | `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 |
 
 See [docs/think-experiment.md](docs/think-experiment.md) for the testing methodology and results.
@@ -182,7 +183,7 @@ Both tools use the same Ollama Cloud API key configured for the provider. No loc
 
 | Command | Description |
 |---|---|
-| `/ollama-cloud-refresh` | Fetch models from the Ollama Cloud API, update cache, and re-register the provider |
+| `/ollama-cloud-refresh` | Fetch models from the Ollama Cloud API, update cache, and re-register the provider. Updates the model list and metadata but not estimated prices (those are pinned to the installed package version). |
 | `/ollama-webtools [on\|off\|enable\|disable]` | Enable or disable the `ollama_web_search` and `ollama_web_fetch` tools. Toggles if no argument given. |
 
 ## Development

package/index.ts

@@ -124,9 +124,8 @@ export default async function (pi: ExtensionAPI) {
   // When cache is missing, GENERATED_MODELS serves as the cache —
   // it is manually generated via `npm run generate-models` and committed to the repo.
   const needsStartupRefresh = cacheState.status === "stale";
-  // GENERATED_MODELS ships with the package (36 tool-capable models from
-  // the build script). Used when no local cache exists. A fresh user cache
-  // from /ollama-cloud-refresh takes precedence over the generated list.
+  // GENERATED_MODELS ships with the package. Used when no local cache exists. A
+  // fresh user cache from /ollama-cloud-refresh takes precedence over the generated list.
   const models = cacheState.status === "missing" ? GENERATED_MODELS : assembleModels(cacheState.models);
 
   registerProvider(pi, models);

package/models.generated.ts

@@ -1,91 +1,11 @@
 // Auto-generated by scripts/generate-models.ts
 // Do not edit manually.
-// Generated: 2026-06-05T15:26:51.472Z
-// Model count: 30
+// Generated: 2026-07-17T19:55:27.551Z
+// Model count: 18
 
 import type { ProviderModelConfig } from "@earendil-works/pi-coding-agent";
 
 export const GENERATED_MODELS: ProviderModelConfig[] = [
-  {
-    id: "deepseek-v3.1:671b",
-    name: "deepseek-v3.1:671b",
-    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: 163840,
-    cost: {
-      cacheRead: 0,
-      cacheWrite: 0,
-      input: 0,
-      output: 0,
-    },
-    input: ["text"],
-    maxTokens: 32768,
-    reasoning: true,
-    thinkingLevelMap: {
-      high: "high",
-      low: "low",
-      medium: "medium",
-      minimal: null,
-      off: "none",
-      xhigh: "max",
-    },
-  },
-  {
-    id: "deepseek-v3.2",
-    name: "deepseek-v3.2",
-    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: 163840,
-    cost: {
-      cacheRead: 0,
-      cacheWrite: 0,
-      input: 0,
-      output: 0,
-    },
-    input: ["text"],
-    maxTokens: 32768,
-    reasoning: true,
-    thinkingLevelMap: {
-      high: "high",
-      low: "low",
-      medium: "medium",
-      minimal: null,
-      off: "none",
-      xhigh: "max",
-    },
-  },
   {
     id: "deepseek-v4-flash",
     name: "deepseek-v4-flash",
@@ -109,10 +29,10 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
     contextWindow: 1048576,
     cost: {
-      cacheRead: 0,
+      cacheRead: 0.0028,
       cacheWrite: 0,
-      input: 0,
-      output: 0,
+      input: 0.14,
+      output: 0.28,
     },
     input: ["text"],
     maxTokens: 32768,
@@ -147,119 +67,15 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       vercelGatewayRouting: {},
       zaiToolStream: false,
     },
-    contextWindow: 1048576,
-    cost: {
-      cacheRead: 0,
-      cacheWrite: 0,
-      input: 0,
-      output: 0,
-    },
-    input: ["text"],
-    maxTokens: 32768,
-    reasoning: true,
-    thinkingLevelMap: {
-      high: "high",
-      low: "low",
-      medium: "medium",
-      minimal: null,
-      off: "none",
-      xhigh: "max",
-    },
-  },
-  {
-    id: "devstral-2:123b",
-    name: "devstral-2:123b",
-    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: 262144,
+    contextWindow: 524288,
     cost: {
-      cacheRead: 0,
+      cacheRead: 0.003625,
       cacheWrite: 0,
-      input: 0,
-      output: 0,
+      input: 0.435,
+      output: 0.87,
     },
     input: ["text"],
     maxTokens: 32768,
-    reasoning: false,
-  },
-  {
-    id: "devstral-small-2:24b",
-    name: "devstral-small-2:24b",
-    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: 262144,
-    cost: {
-      cacheRead: 0,
-      cacheWrite: 0,
-      input: 0,
-      output: 0,
-    },
-    input: ["text", "image"],
-    maxTokens: 32768,
-    reasoning: false,
-  },
-  {
-    id: "gemini-3-flash-preview",
-    name: "gemini-3-flash-preview",
-    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,
-      cacheWrite: 0,
-      input: 0,
-      output: 0,
-    },
-    input: ["text", "image"],
-    maxTokens: 32768,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -293,10 +109,10 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
     contextWindow: 262144,
     cost: {
-      cacheRead: 0,
+      cacheRead: 0.12,
       cacheWrite: 0,
-      input: 0,
-      output: 0,
+      input: 0.22,
+      output: 0.55,
     },
     input: ["text", "image"],
     maxTokens: 32768,
@@ -311,48 +127,8 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
   },
   {
-    id: "glm-4.7",
-    name: "glm-4.7",
-    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: 202752,
-    cost: {
-      cacheRead: 0,
-      cacheWrite: 0,
-      input: 0,
-      output: 0,
-    },
-    input: ["text"],
-    maxTokens: 32768,
-    reasoning: true,
-    thinkingLevelMap: {
-      high: "high",
-      low: "low",
-      medium: "medium",
-      minimal: null,
-      off: "none",
-      xhigh: "max",
-    },
-  },
-  {
-    id: "glm-5",
-    name: "glm-5",
+    id: "glm-5.1",
+    name: "glm-5.1",
     compat: {
       maxTokensField: "max_tokens",
       openRouterRouting: {},
@@ -373,10 +149,10 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
     contextWindow: 202752,
     cost: {
-      cacheRead: 0,
+      cacheRead: 0.26,
       cacheWrite: 0,
-      input: 0,
-      output: 0,
+      input: 1.4,
+      output: 4.4,
     },
     input: ["text"],
     maxTokens: 32768,
@@ -391,8 +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: {},
@@ -411,20 +187,20 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       vercelGatewayRouting: {},
       zaiToolStream: false,
     },
-    contextWindow: 202752,
+    contextWindow: 1000000,
     cost: {
-      cacheRead: 0,
+      cacheRead: 0.26,
       cacheWrite: 0,
-      input: 0,
-      output: 0,
+      input: 1.4,
+      output: 4.4,
     },
     input: ["text"],
     maxTokens: 32768,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
-      low: "low",
-      medium: "medium",
+      low: null,
+      medium: null,
       minimal: null,
       off: "none",
       xhigh: "max",
@@ -455,8 +231,8 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     cost: {
       cacheRead: 0,
       cacheWrite: 0,
-      input: 0,
-      output: 0,
+      input: 0.037,
+      output: 0.17,
     },
     input: ["text"],
     maxTokens: 32768,
@@ -493,10 +269,10 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
     contextWindow: 131072,
     cost: {
-      cacheRead: 0,
+      cacheRead: 0.03,
       cacheWrite: 0,
-      input: 0,
-      output: 0,
+      input: 0.03,
+      output: 0.13,
     },
     input: ["text"],
     maxTokens: 32768,
@@ -533,10 +309,10 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
     contextWindow: 262144,
     cost: {
-      cacheRead: 0,
+      cacheRead: 0.1,
       cacheWrite: 0,
-      input: 0,
-      output: 0,
+      input: 0.6,
+      output: 3,
     },
     input: ["text", "image"],
     maxTokens: 32768,
@@ -573,10 +349,10 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
     contextWindow: 262144,
     cost: {
-      cacheRead: 0,
+      cacheRead: 0.16,
       cacheWrite: 0,
-      input: 0,
-      output: 0,
+      input: 0.95,
+      output: 4,
     },
     input: ["text", "image"],
     maxTokens: 32768,
@@ -591,8 +367,8 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
   },
   {
-    id: "minimax-m2.1",
-    name: "minimax-m2.1",
+    id: "kimi-k2.7-code",
+    name: "kimi-k2.7-code",
     compat: {
       maxTokensField: "max_tokens",
       openRouterRouting: {},
@@ -611,14 +387,14 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       vercelGatewayRouting: {},
       zaiToolStream: false,
     },
-    contextWindow: 204800,
+    contextWindow: 262144,
     cost: {
-      cacheRead: 0,
+      cacheRead: 0.19,
       cacheWrite: 0,
-      input: 0,
-      output: 0,
+      input: 0.95,
+      output: 4,
     },
-    input: ["text"],
+    input: ["text", "image"],
     maxTokens: 32768,
     reasoning: true,
     thinkingLevelMap: {
@@ -626,7 +402,7 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       low: "low",
       medium: "medium",
       minimal: null,
-      off: null,
+      off: "none",
       xhigh: "max",
     },
   },
@@ -653,10 +429,10 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
     contextWindow: 196608,
     cost: {
-      cacheRead: 0,
-      cacheWrite: 0,
-      input: 0,
-      output: 0,
+      cacheRead: 0.03,
+      cacheWrite: 0.375,
+      input: 0.3,
+      output: 1.2,
     },
     input: ["text"],
     maxTokens: 32768,
@@ -693,10 +469,10 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
     contextWindow: 196608,
     cost: {
-      cacheRead: 0,
-      cacheWrite: 0,
-      input: 0,
-      output: 0,
+      cacheRead: 0.06,
+      cacheWrite: 0.375,
+      input: 0.3,
+      output: 1.2,
     },
     input: ["text"],
     maxTokens: 32768,
@@ -733,10 +509,10 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
     contextWindow: 524288,
     cost: {
-      cacheRead: 0,
+      cacheRead: 0.06,
       cacheWrite: 0,
-      input: 0,
-      output: 0,
+      input: 0.3,
+      output: 1.2,
     },
     input: ["text", "image"],
     maxTokens: 32768,
@@ -750,102 +526,6 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       xhigh: "max",
     },
   },
-  {
-    id: "ministral-3:14b",
-    name: "ministral-3:14b",
-    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: 262144,
-    cost: {
-      cacheRead: 0,
-      cacheWrite: 0,
-      input: 0,
-      output: 0,
-    },
-    input: ["text", "image"],
-    maxTokens: 32768,
-    reasoning: false,
-  },
-  {
-    id: "ministral-3:3b",
-    name: "ministral-3:3b",
-    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: 262144,
-    cost: {
-      cacheRead: 0,
-      cacheWrite: 0,
-      input: 0,
-      output: 0,
-    },
-    input: ["text", "image"],
-    maxTokens: 32768,
-    reasoning: false,
-  },
-  {
-    id: "ministral-3:8b",
-    name: "ministral-3:8b",
-    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: 262144,
-    cost: {
-      cacheRead: 0,
-      cacheWrite: 0,
-      input: 0,
-      output: 0,
-    },
-    input: ["text", "image"],
-    maxTokens: 32768,
-    reasoning: false,
-  },
   {
     id: "mistral-large-3:675b",
     name: "mistral-large-3:675b",
@@ -871,8 +551,8 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     cost: {
       cacheRead: 0,
       cacheWrite: 0,
-      input: 0,
-      output: 0,
+      input: 0.5,
+      output: 1.5,
     },
     input: ["text", "image"],
     maxTokens: 32768,
@@ -903,8 +583,8 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     cost: {
       cacheRead: 0,
       cacheWrite: 0,
-      input: 0,
-      output: 0,
+      input: 0.05,
+      output: 0.2,
     },
     input: ["text"],
     maxTokens: 32768,
@@ -943,8 +623,8 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     cost: {
       cacheRead: 0,
       cacheWrite: 0,
-      input: 0,
-      output: 0,
+      input: 0.2,
+      output: 0.8,
     },
     input: ["text"],
     maxTokens: 32768,
@@ -981,10 +661,10 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
     contextWindow: 262144,
     cost: {
-      cacheRead: 0,
+      cacheRead: 0.15,
       cacheWrite: 0,
-      input: 0,
-      output: 0,
+      input: 0.5,
+      output: 2.5,
     },
     input: ["text"],
     maxTokens: 32768,
@@ -998,70 +678,6 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       xhigh: "max",
     },
   },
-  {
-    id: "qwen3-coder-next",
-    name: "qwen3-coder-next",
-    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: 262144,
-    cost: {
-      cacheRead: 0,
-      cacheWrite: 0,
-      input: 0,
-      output: 0,
-    },
-    input: ["text"],
-    maxTokens: 32768,
-    reasoning: false,
-  },
-  {
-    id: "qwen3-coder:480b",
-    name: "qwen3-coder:480b",
-    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: 262144,
-    cost: {
-      cacheRead: 0,
-      cacheWrite: 0,
-      input: 0,
-      output: 0,
-    },
-    input: ["text"],
-    maxTokens: 32768,
-    reasoning: false,
-  },
   {
     id: "qwen3.5:397b",
     name: "qwen3.5:397b",
@@ -1087,8 +703,8 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     cost: {
       cacheRead: 0,
       cacheWrite: 0,
-      input: 0,
-      output: 0,
+      input: 0.6,
+      output: 3.6,
     },
     input: ["text", "image"],
     maxTokens: 32768,
@@ -1102,36 +718,4 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       xhigh: null,
     },
   },
-  {
-    id: "rnj-1:8b",
-    name: "rnj-1:8b",
-    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: 32768,
-    cost: {
-      cacheRead: 0,
-      cacheWrite: 0,
-      input: 0,
-      output: 0,
-    },
-    input: ["text"],
-    maxTokens: 32768,
-    reasoning: false,
-  },
 ];

package/models.ts

@@ -1,16 +1,55 @@
 import { existsSync, mkdirSync, readFileSync, rmSync, writeFileSync } from "node:fs";
 import { join } from "node:path";
 import { type ExtensionCommandContext, getAgentDir, type ProviderModelConfig } from "@earendil-works/pi-coding-agent";
+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
+// 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.
+
+/** Resolve the estimated 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 };
+}
+
 // --- Constants ---
 const CACHE_DIR = join(getAgentDir(), "cache");
 const CACHE_FILE = join(CACHE_DIR, "ollama-cloud-models.json");
 const CACHE_MAX_AGE_MS = 30 * 24 * 60 * 60 * 1000;
 const FETCH_TIMEOUT_MS = 10000;
 
-export const OLLAMA_BASE = (process.env.OLLAMA_API_BASE || "https://ollama.com").replace(/\/+$/, "");
+// The cloud extension always targets ollama.com; local Ollama daemons (typically
+// pointed at via OLLAMA_API_BASE for the local CLI) are a different product and
+// must not silently redirect cloud requests. Warn once at module load if the
+// env var looks like a non-cloud target so the misconfiguration is visible.
+const CLOUD_BASE_URL = "https://ollama.com";
+const envBase = typeof process !== "undefined" ? process.env?.OLLAMA_API_BASE : undefined;
+if (envBase) {
+  // Warn when OLLAMA_API_BASE is set to anything other than the cloud host.
+  // Parse the URL so lookalikes (e.g. https://ollama.com.evil.com) are not
+  // mistaken for the cloud base. OLLAMA_API_BASE is otherwise ignored: this
+  // extension always targets CLOUD_BASE_URL.
+  let isCloudBase = false;
+  try {
+    const url = new URL(envBase);
+    isCloudBase = url.protocol === "https:" && url.hostname === "ollama.com";
+  } catch {
+    // Invalid URL: not the cloud base.
+  }
+  if (!isCloudBase) {
+    console.warn(
+      `[pi-ollama-cloud] Ignoring OLLAMA_API_BASE=${envBase}; ` +
+        `this extension always targets ${CLOUD_BASE_URL}. ` +
+        `Unset OLLAMA_API_BASE (or set it to the cloud URL) to silence this warning.`,
+    );
+  }
+}
+export const OLLAMA_BASE = CLOUD_BASE_URL.replace(/\/+$/, "");
 
 // --- Raw API types ---
 /** Response from POST /api/show */
@@ -105,7 +144,7 @@ export function assembleModels(raw: Record<string, CachedOllamaModel>): Provider
       reasoning: data.capabilities?.includes("thinking") ?? false,
       thinkingLevelMap: resolveThinkingLevelMap(id, data.capabilities ?? []),
       input: (data.capabilities?.includes("vision") ? ["text", "image"] : ["text"]) as ("text" | "image")[],
-      cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+      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.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-ollama-cloud",
-  "version": "0.6.0",
+  "version": "0.7.0",
   "type": "module",
   "keywords": [
     "pi-package"
@@ -10,6 +10,7 @@
     "config.ts",
     "models.ts",
     "models.generated.ts",
+    "pricing.generated.ts",
     "thinking-levels.ts",
     "utils.ts",
     "web-tools.ts",
@@ -26,7 +27,8 @@
     "lint": "biome check .",
     "format": "biome format --write .",
     "test": "vitest run",
-    "generate-models": "tsx scripts/generate-models.ts && biome format --write models.generated.ts"
+    "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"
   },
   "pi": {
     "extensions": [

package/pricing.generated.ts

@@ -0,0 +1,32 @@
+// Auto-generated by scripts/generate-pricing.ts
+// Do not edit manually.
+// Generated: 2026-07-17T19:55:25.388Z
+// Model count: 18
+
+export interface ModelPrice {
+  input: number;
+  output: number;
+  cacheRead: number;
+  cacheWrite: number;
+}
+
+export const MODEL_PRICING: Record<string, ModelPrice> = {
+  "deepseek-v4-flash": { 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: 0.22, output: 0.55, cacheRead: 0.12, cacheWrite: 0 },
+  "glm-5.1": { input: 1.4, output: 4.4, cacheRead: 0.26, 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 },
+  "kimi-k2.5": { input: 0.6, output: 3, cacheRead: 0.1, 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 },
+  "minimax-m2.5": { input: 0.3, output: 1.2, cacheRead: 0.03, cacheWrite: 0.375 },
+  "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, 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 },
+};

package/thinking-levels.ts

@@ -14,6 +14,7 @@
  *   - GPT-OSS: no off mode, only low/medium/high
  *   - Qwen 3.x (non-VL): binary-only (think/nothink) - off works
  *   - Qwen 3 VL: "none" doesn't disable thinking - off is hidden
+ *   - GLM 5.2: off/high/max are exposed; low/medium are hidden
  *   - Kimi K2 Thinking: "none" doesn't disable thinking - off is hidden
  *   - MiniMax M2.x: "none" doesn't disable thinking - off is hidden
  *
@@ -56,6 +57,17 @@ export const QWEN3: ThinkingLevelMap = {
   xhigh: null,
 };
 
+/** GLM 5.2: Ollama's model page confirms support for "high" and "max" reasoning efforts.
+ *  https://ollama.com/library/glm-5.2 */
+export const GLM_52: ThinkingLevelMap = {
+  off: "none",
+  minimal: null,
+  low: null,
+  medium: null,
+  high: "high",
+  xhigh: "max",
+};
+
 /** "none" doesn't disable thinking - off is hidden.
  *  Used by kimi and minimax families. */
 export const NO_OFF: ThinkingLevelMap = {
@@ -75,6 +87,7 @@ export function resolve(id: string, capabilities: string[]): ThinkingLevelMap |
   if (!capabilities.includes("thinking")) return undefined;
 
   if (id.startsWith("gpt-oss")) return GPT_OSS;
+  if (id === "glm-5.2") return GLM_52;
   if (id.startsWith("qwen3-vl")) return NO_OFF;
   if (id.startsWith("qwen3")) return QWEN3;
   if (id === "kimi-k2-thinking") return NO_OFF;

package/utils.ts

@@ -2,9 +2,23 @@ export async function fetchJsonWithTimeout<T>(
   url: string,
   init: RequestInit,
   timeoutMs: number,
+  externalSignal?: AbortSignal,
 ): Promise<{ ok: boolean; status: number; data: T | null; error?: string }> {
   const controller = new AbortController();
   const timeout = setTimeout(() => controller.abort(), timeoutMs);
+
+  // Link an external abort signal (e.g. a tool's cancellation signal) so the
+  // request aborts on either the timeout or the caller aborting. Cleanup runs
+  // in the finally block on both the happy and error paths.
+  const onExternalAbort = () => controller.abort();
+  if (externalSignal) {
+    if (externalSignal.aborted) {
+      controller.abort();
+    } else {
+      externalSignal.addEventListener("abort", onExternalAbort, { once: true });
+    }
+  }
+
   try {
     const res = await fetch(url, { ...init, signal: controller.signal });
     const text = await res.text();
@@ -25,6 +39,9 @@ export async function fetchJsonWithTimeout<T>(
     return { ok: false, status: 0, data: null, error: error instanceof Error ? error.message : String(error) };
   } finally {
     clearTimeout(timeout);
+    if (externalSignal && !externalSignal.aborted) {
+      externalSignal.removeEventListener("abort", onExternalAbort);
+    }
   }
 }
 

package/web-tools.ts

@@ -3,15 +3,30 @@
  *
  * Self-contained module. Depends on:
  *   - models.ts       - only for OLLAMA_BASE URL constant
- *   - pi-coding-agent - AuthStorage, ExtensionAPI, keyHint, truncateToVisualLines
+ *   - pi-coding-agent - ExtensionAPI, ExtensionContext, keyHint, truncateToVisualLines
  *   - pi-tui          - Text, truncateToWidth
+ *   - utils.ts        - fetchJsonWithTimeout
  * Does NOT depend on provider registration or model fetching internals.
+ *
+ * API key resolution: each tool's execute() receives an ExtensionContext whose
+ * modelRegistry resolves the registered provider's key (runtime/CLI overrides,
+ * the registered apiKey: "$OLLAMA_API_KEY" config, and stored auth.json). The
+ * OLLAMA_API_KEY env var is a fallback for when the provider is not yet
+ * registered at tool-call time. This avoids direct AuthStorage access, which is
+ * not part of the public pi-coding-agent API on 0.80.8+.
  */
 
-import { AuthStorage, type ExtensionAPI, keyHint, truncateToVisualLines } from "@earendil-works/pi-coding-agent";
-import { Text, truncateToWidth } from "@earendil-works/pi-tui";
+import {
+  type ExtensionAPI,
+  type ExtensionContext,
+  keyHint,
+  type Theme,
+  truncateToVisualLines,
+} from "@earendil-works/pi-coding-agent";
+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";
 
 // --- Types ---
 
@@ -31,10 +46,21 @@ interface FetchResponse {
 
 // --- Helpers ---
 
-const authStorage = AuthStorage.create();
+const WEB_TOOLS_TIMEOUT_MS = 15000;
 
-async function getCloudApiKey(): Promise<string | undefined> {
-  return authStorage.getApiKey("ollama-cloud") ?? process.env.OLLAMA_API_KEY;
+/**
+ * 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;
 }
 
 function noApiKeyError() {
@@ -49,6 +75,58 @@ function noApiKeyError() {
   };
 }
 
+/** Search error response for a non-ok result, mapping distinct status codes. */
+function searchError(status: number, error?: string) {
+  if (status === 401 || status === 403) {
+    return {
+      content: [
+        {
+          type: "text" as const,
+          text:
+            "Ollama Cloud search failed: authentication error. " + "Check your API key in OLLAMA_API_KEY or auth.json.",
+        },
+      ],
+      isError: true,
+    };
+  }
+  if (status === 429) {
+    return {
+      content: [{ type: "text" as const, text: "Ollama Cloud search failed: rate limited. Try again shortly." }],
+      isError: true,
+    };
+  }
+  return {
+    content: [{ type: "text" as const, text: `Search API error (status ${status}): ${error || "unknown error"}` }],
+    isError: true,
+  };
+}
+
+/** Fetch error response for a non-ok result, mapping distinct status codes. */
+function fetchError(status: number, error?: string) {
+  if (status === 401 || status === 403) {
+    return {
+      content: [
+        {
+          type: "text" as const,
+          text:
+            "Ollama Cloud fetch failed: authentication error. " + "Check your API key in OLLAMA_API_KEY or auth.json.",
+        },
+      ],
+      isError: true,
+    };
+  }
+  if (status === 429) {
+    return {
+      content: [{ type: "text" as const, text: "Ollama Cloud fetch failed: rate limited. Try again shortly." }],
+      isError: true,
+    };
+  }
+  return {
+    content: [{ type: "text" as const, text: `Fetch API error (status ${status}): ${error || "unknown error"}` }],
+    isError: true,
+  };
+}
+
 const PREVIEW_LINES = 8;
 
 /**
@@ -59,10 +137,10 @@ function createRenderResult() {
   return (
     result: { content: Array<{ type: string; text: string }>; isError?: boolean },
     options: { expanded: boolean; isPartial: boolean },
-    theme: import("@earendil-works/pi-coding-agent").Theme,
+    theme: Theme,
     context: {
       invalidate: () => void;
-      lastComponent: import("@earendil-works/pi-tui").Component | undefined;
+      lastComponent: Component | undefined;
       state: { cachedWidth?: number; cachedLines?: string[]; cachedSkipped?: number };
     },
   ) => {
@@ -107,6 +185,18 @@ function createRenderResult() {
   };
 }
 
+/** Validate a parsed web_search response: must have a results array. */
+function isSearchResponse(data: unknown): data is SearchResponse {
+  return data != null && typeof data === "object" && Array.isArray((data as SearchResponse).results);
+}
+
+/** Validate a parsed web_fetch response: must have string title/content and a links array. */
+function isFetchResponse(data: unknown): data is FetchResponse {
+  if (data == null || typeof data !== "object") return false;
+  const d = data as FetchResponse;
+  return typeof d.title === "string" && typeof d.content === "string" && Array.isArray(d.links);
+}
+
 // --- Registrations ---
 
 export function registerWebSearchTool(pi: ExtensionAPI) {
@@ -128,12 +218,13 @@ export function registerWebSearchTool(pi: ExtensionAPI) {
         }),
       ),
     }),
-    async execute(_toolCallId, params, signal, _onUpdate, _ctx) {
-      const apiKey = await getCloudApiKey();
+    async execute(_toolCallId, params, signal, _onUpdate, ctx) {
+      const apiKey = await getCloudApiKey(ctx);
       if (!apiKey) return noApiKeyError();
 
-      try {
-        const res = await fetch(`${OLLAMA_BASE}/api/web_search`, {
+      const res = await fetchJsonWithTimeout<SearchResponse>(
+        `${OLLAMA_BASE}/api/web_search`,
+        {
           method: "POST",
           headers: {
             Authorization: `Bearer ${apiKey}`,
@@ -143,53 +234,27 @@ export function registerWebSearchTool(pi: ExtensionAPI) {
             query: params.query,
             max_results: params.max_results ?? 5,
           }),
-          signal,
-        });
-
-        if (!res.ok) {
-          const errorText = await res.text().catch(() => "");
-          if (res.status === 401 || res.status === 403) {
-            return {
-              content: [
-                {
-                  type: "text",
-                  text:
-                    "Ollama Cloud search failed: authentication error. " +
-                    "Check your API key in OLLAMA_API_KEY or auth.json.",
-                },
-              ],
-              isError: true,
-            };
-          }
-          if (res.status === 429) {
-            return {
-              content: [{ type: "text", text: "Ollama Cloud search failed: rate limited. Try again shortly." }],
-              isError: true,
-            };
-          }
-          return {
-            content: [
-              { type: "text", text: `Search API error (status ${res.status}): ${errorText || res.statusText}` },
-            ],
-            isError: true,
-          };
-        }
+        },
+        WEB_TOOLS_TIMEOUT_MS,
+        signal,
+      );
 
-        const data = (await res.json()) as SearchResponse;
-        const formatted = data.results
-          .map((r, i) => `${i + 1}. ${r.title}\n   URL: ${r.url}\n   ${r.content}`)
-          .join("\n\n");
-
-        return {
-          content: [{ type: "text", text: formatted || "No results found." }],
-          details: { results: data.results },
-        };
-      } catch (err) {
+      if (!res.ok) return searchError(res.status, res.error);
+      if (!isSearchResponse(res.data)) {
         return {
-          content: [{ type: "text", text: `Web search failed: ${err instanceof Error ? err.message : String(err)}` }],
+          content: [{ type: "text", text: "Web search failed: unexpected response shape from the API." }],
           isError: true,
         };
       }
+
+      const formatted = res.data.results
+        .map((r, i) => `${i + 1}. ${r.title}\n   URL: ${r.url}\n   ${r.content}`)
+        .join("\n\n");
+
+      return {
+        content: [{ type: "text", text: formatted || "No results found." }],
+        details: { results: res.data.results },
+      };
     },
     renderCall(args, theme, _context) {
       const display = args.query ? `ollama_web_search("${args.query}")` : "ollama_web_search";
@@ -210,69 +275,47 @@ export function registerWebFetchTool(pi: ExtensionAPI) {
     parameters: Type.Object({
       url: Type.String({ description: "URL to fetch and extract content from", format: "uri" }),
     }),
-    async execute(_toolCallId, params, signal, _onUpdate, _ctx) {
-      const apiKey = await getCloudApiKey();
+    async execute(_toolCallId, params, signal, _onUpdate, ctx) {
+      const apiKey = await getCloudApiKey(ctx);
       if (!apiKey) return noApiKeyError();
 
-      try {
-        const res = await fetch(`${OLLAMA_BASE}/api/web_fetch`, {
+      const res = await fetchJsonWithTimeout<FetchResponse>(
+        `${OLLAMA_BASE}/api/web_fetch`,
+        {
           method: "POST",
           headers: {
             Authorization: `Bearer ${apiKey}`,
             "Content-Type": "application/json",
           },
           body: JSON.stringify({ url: params.url }),
-          signal,
-        });
-
-        if (!res.ok) {
-          const errorText = await res.text().catch(() => "");
-          if (res.status === 401 || res.status === 403) {
-            return {
-              content: [
-                {
-                  type: "text",
-                  text:
-                    "Ollama Cloud fetch failed: authentication error. " +
-                    "Check your API key in OLLAMA_API_KEY or auth.json.",
-                },
-              ],
-              isError: true,
-            };
-          }
-          if (res.status === 429) {
-            return {
-              content: [{ type: "text", text: "Ollama Cloud fetch failed: rate limited. Try again shortly." }],
-              isError: true,
-            };
-          }
-          return {
-            content: [{ type: "text", text: `Fetch API error (status ${res.status}): ${errorText || res.statusText}` }],
-            isError: true,
-          };
-        }
+        },
+        WEB_TOOLS_TIMEOUT_MS,
+        signal,
+      );
 
-        const data = (await res.json()) as FetchResponse;
-        const formatted = [
-          `Title: ${data.title}`,
-          "",
-          "Content:",
-          data.content,
-          "",
-          `Links found: ${data.links?.length ?? 0}`,
-          ...(data.links?.slice(0, 10).map((l) => `  - ${l}`) ?? []),
-        ].join("\n");
-
-        return {
-          content: [{ type: "text", text: formatted }],
-          details: { title: data.title, content: data.content, links: data.links },
-        };
-      } catch (err) {
+      if (!res.ok) return fetchError(res.status, res.error);
+      if (!isFetchResponse(res.data)) {
         return {
-          content: [{ type: "text", text: `Web fetch failed: ${err instanceof Error ? err.message : String(err)}` }],
+          content: [{ type: "text", text: "Web fetch failed: unexpected response shape from the API." }],
           isError: true,
         };
       }
+
+      const data = res.data;
+      const formatted = [
+        `Title: ${data.title}`,
+        "",
+        "Content:",
+        data.content,
+        "",
+        `Links found: ${data.links?.length ?? 0}`,
+        ...(data.links?.slice(0, 10).map((l) => `  - ${l}`) ?? []),
+      ].join("\n");
+
+      return {
+        content: [{ type: "text", text: formatted }],
+        details: { title: data.title, content: data.content, links: data.links },
+      };
     },
     renderCall(args, theme, _context) {
       const display = args.url ? `ollama_web_fetch("${args.url}")` : "ollama_web_fetch";