@herbertgao/pi-extensions 2026.8.6 → 2026.8.8

package/node_modules/pi-web-access/README.md

@@ -4,7 +4,7 @@
 
 # Pi Web Access
 
-**Web search, content extraction, and video understanding for Pi agent. OpenAI/Codex search, zero-config Exa search, Brave, Parallel, TinyFish, Search1API, Searchinfinity, Querit, Tavily, Firecrawl, Jina, SERPdive, Kagi, Bocha, Ollama, AnySearch, xAI/Grok, Bright Data SERP, SerpBase, self-hosted SearXNG, keyless DuckDuckGo, optional browser-cookie Gemini Web, or bring your own API keys.**
+**Web search, content extraction, and video understanding for Pi agent. OpenAI/Codex search, zero-config Exa search, Brave, Parallel, TinyFish, Search1API, Searchinfinity, Querit, Tavily, Firecrawl, Jina, SERPdive, Kagi, Bocha, Ollama, AnySearch, Valyu, xAI/Grok, Bright Data SERP, SerpBase, Serper, self-hosted SearXNG, keyless DuckDuckGo, optional browser-cookie Gemini Web, or bring your own API keys.**
 
 [![npm version](https://img.shields.io/npm/v/pi-web-access?style=for-the-badge)](https://www.npmjs.com/package/pi-web-access)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg?style=for-the-badge)](https://opensource.org/licenses/MIT)
@@ -14,7 +14,7 @@
 
 ## Why Pi Web Access
 
-**Zero Config** — Works out of the box with Exa MCP (no API key needed). If you're signed into Pi with a Codex subscription, OpenAI web search can reuse that auth. Add API keys or endpoints for OpenAI, Brave, Parallel, TinyFish, Search1API, Searchinfinity, Querit, Tavily, Firecrawl, Jina, SERPdive, Kagi, Bocha, Ollama, SerpBase, Exa, Perplexity, or Gemini API for more control; configure a self-hosted SearXNG endpoint for private search; or opt into browser-cookie access for Gemini Web.
+**Zero Config** — Works out of the box with Exa MCP (no API key needed). If you're signed into Pi with a Codex subscription, OpenAI web search can reuse that auth. Add API keys or endpoints for OpenAI, Brave, Parallel, TinyFish, Search1API, Searchinfinity, Querit, Tavily, Firecrawl, Jina, SERPdive, Kagi, Bocha, Ollama, Valyu, SerpBase, Serper, Exa, Perplexity, or Gemini API for more control; configure a self-hosted SearXNG endpoint for private search; or opt into browser-cookie access for Gemini Web.
 
 **Video Understanding** — Point it at a YouTube video or local screen recording and ask questions about what's on screen. Full transcripts, visual descriptions, and frame extraction at exact timestamps.
 
@@ -46,7 +46,7 @@ Works immediately with no API keys — Exa MCP provides zero-config search. If P
 }
 ```
 
-In `auto` mode (default), `web_search` tries a configured SearXNG endpoint first for local/private search, then OpenAI when suitable and available, Exa (direct API if keyed, MCP if not), Brave, Parallel, TinyFish, Search1API, Searchinfinity, Querit, Tavily, Firecrawl, Jina, SERPdive, Perplexity, Gemini API, and Gemini Web when browser-cookie access is enabled. With no SearXNG configured, the existing zero-config order is unchanged. Exa handles search; curator summary drafts are generated separately by the configured Pi summary model. Slow summary drafts fall back to a deterministic result summary after a bounded deadline.
+In `auto` mode (default), `web_search` tries a configured SearXNG endpoint first for local/private search, then OpenAI when suitable and available, Exa (direct API if keyed, MCP if not), Brave, Parallel, TinyFish, Search1API, Searchinfinity, Querit, Tavily, Firecrawl, Jina, SERPdive, Perplexity, Gemini API, and Gemini Web when browser-cookie access is enabled. With no SearXNG configured, the existing zero-config order is unchanged. Exa handles search; curator summary drafts are generated separately by the configured Pi summary model, defaulting to Claude Haiku, Codex Luna, Codex Terra, Gemini 3.6 Flash, GPT-5 mini, then DeepSeek V4 Flash when available. Slow summary drafts fall back to a deterministic result summary after a bounded deadline.
 
 If your OpenAI key belongs to a third-party Responses-compatible gateway, set `openaiResponsesUrl` to that gateway's full Responses endpoint. The default remains `https://api.openai.com/v1/responses`.
 
@@ -96,7 +96,7 @@ fetch_content({ url: "/path/to/recording.mp4", prompt: "What error appears on sc
 
 ### web_search
 
-Search the web via OpenAI, Brave, Parallel, TinyFish, Search1API, Searchinfinity, Querit, Tavily, Firecrawl, Jina, SERPdive, Kagi, Bocha, Ollama, AnySearch, xAI, Bright Data SERP, SerpBase, self-hosted SearXNG, keyless DuckDuckGo, Exa, Perplexity AI, or Gemini. Returns a synthesized answer with source citations.
+Search the web via OpenAI, Brave, Parallel, TinyFish, Search1API, Searchinfinity, Querit, Tavily, Firecrawl, Jina, SERPdive, Kagi, Bocha, Ollama, AnySearch, Valyu, xAI, Bright Data SERP, SerpBase, Serper, self-hosted SearXNG, keyless DuckDuckGo, Exa, Perplexity AI, or Gemini. Returns a synthesized answer with source citations.
 
 ```typescript
 web_search({ query: "rust async programming" })
@@ -117,7 +117,7 @@ web_search({ queries: ["query 1", "query 2"], workflow: "auto-summary" })
 | `numResults` | Results per query (default: 5, max: 20) |
 | `recencyFilter` | `day`, `week`, `month`, or `year` |
 | `domainFilter` | Limit to domains (prefix with `-` to exclude) |
-| `provider` | Configured provider when omitted or set to `auto`; `all` searches every eligible provider except DuckDuckGo, AnySearch, xAI, Bright Data, and SerpBase simultaneously; otherwise `openai`, `brave`, `parallel`, `tinyfish`, `search1api`, `searchinfinity`, `querit`, `tavily`, `firecrawl`, `jina`, `serpdive`, `kagi`, `bocha`, `ollama`, `anysearch`, `xai`, `brightdata`, `serpbase`, `searxng`, `duckduckgo`, `exa`, `perplexity`, or `gemini` (auto-selects when no provider or routing is configured; DuckDuckGo, AnySearch, xAI, Bright Data, and SerpBase are explicit-only) |
+| `provider` | Configured provider when omitted or set to `auto`; `all` searches every eligible provider except Parallel MCP, DuckDuckGo, AnySearch, Valyu, xAI, Bright Data, SerpBase, and Serper simultaneously; otherwise `openai`, `brave`, `parallel`, `parallel-mcp`, `tinyfish`, `search1api`, `searchinfinity`, `querit`, `tavily`, `firecrawl`, `jina`, `serpdive`, `kagi`, `bocha`, `ollama`, `anysearch`, `valyu`, `xai`, `brightdata`, `serpbase`, `serper`, `searxng`, `duckduckgo`, `exa`, `perplexity`, or `gemini` (auto-selects when no provider or routing is configured; Parallel MCP, DuckDuckGo, AnySearch, Valyu, xAI, Bright Data, SerpBase, and Serper are explicit-only) |
 | `includeContent` | Fetch full page content from sources in background |
 | `workflow` | `none` (skip curator), `summary-review` (open curator and auto-generate a summary draft, default), or `auto-summary` (generate a summary without opening the curator) |
 
@@ -233,6 +233,7 @@ Configure Datalab via the web-search config:
   "datalabApiKey": "$DATALAB_API_KEY",
   "pdf": {
     "maxSizeMB": 20,
+    "maxPages": 100,
     "provider": "auto",      // "auto" | "gemini" | "datalab" | "unpdf"
     "datalabMode": "balanced", // "fast" | "balanced" | "accurate"
     "datalabTimeoutMs": 120000
@@ -250,7 +251,7 @@ Raw and direct-image HTTP requests use the same SSRF validation, hostname domain
 
 `fetch_content` can opt into local browser-cookie auth with `auth: "profile"`, or `auth: true` when exactly one `authFetch` profile exists. Configure profiles in `~/.pi/web-search.json`, for example `{ "authFetch": { "social": ["x.com", "instagram.com"], "work": { "hosts": ["docs.company.com"], "chromeProfile": "Profile 2", "cache": "off" } } }`. Auth fetch uses only the local direct HTTP path, requires HTTPS, allows only configured hosts and their subdomains, refuses cross-origin redirects, and never sends cookies or authenticated content to hosted extraction providers. Browser cookie extraction remains opt-in through `allowBrowserCookies: true` or `PI_ALLOW_BROWSER_COOKIES=1`.
 
-When Readability fails or returns only a cookie notice, the extension can retry configured Firecrawl extraction, Jina Reader (handles JS rendering server-side, no API key needed), TinyFish, Search1API, Querit, Kagi Extract, Ollama Web Fetch, Parallel, Bright Data Web Unlocker, Gemini URL Context API, and Gemini Web extraction when browser cookies are enabled. Configure `fetchRouting.providers` to change the order or set of `fetch_content` providers. Supported values are `http`, `firecrawl`, `jina`, `tinyfish`, `search1api`, `querit`, `kagi`, `ollama`, `parallel`, `brightdata`, and `gemini`; when absent, the default order is unchanged. For remote HTTP(S) targets, third-party hosted providers are disabled unless `fetchRouting.allowRemoteHostedProviders` is `true`, because hosted services perform their own fetch and can see a different redirect chain than the local safety gate. Firecrawl stays available as a configured extraction service. Firecrawl requests are cache-only by default and require an explicit fresh-scrape opt-in before the Firecrawl server can fetch target URLs. Bright Data Web Unlocker runs last of the remote scraping providers, ahead of only the Gemini fallbacks, because it is billed per request against a paid account; it is skipped unless both a key and an `unblocker` zone are configured. It applies no minimum-length check, so any non-empty body it returns — including a short consent or paywall stub — is the final answer for that URL and the Gemini fallbacks are not tried. Handles SPAs, JS-heavy pages, and anti-bot protections transparently. Also parses Next.js RSC flight data when present. HTML extraction also surfaces registered discovery relations (`service-desc`, `service-doc`, `service-meta`, `api-catalog`, `describedby`) from the HTTP `Link` header and matching `link`/`a[rel]` markup. Readable or rendered content remains primary; on an empty shell, the normal extraction fallbacks run before declared links are returned on their own.
+When Readability fails or returns only a cookie notice, the extension can retry configured Firecrawl extraction, Jina Reader (handles JS rendering server-side, no API key needed), TinyFish, Search1API, Querit, Kagi Extract, Ollama Web Fetch, Parallel, Bright Data Web Unlocker, Gemini URL Context API, and Gemini Web extraction when browser cookies are enabled. Configure `fetchRouting.providers` to change the order or set of `fetch_content` providers. Supported values are `http`, `firecrawl`, `jina`, `tinyfish`, `search1api`, `querit`, `kagi`, `ollama`, `parallel`, `parallel-mcp`, `brightdata`, and `gemini`; when absent, the default order is unchanged. `parallel-mcp` is not in the default fetch order and must be listed explicitly. For remote HTTP(S) targets, third-party hosted providers are disabled unless `fetchRouting.allowRemoteHostedProviders` is `true`, because hosted services perform their own fetch and can see a different redirect chain than the local safety gate. Firecrawl stays available as a configured extraction service. Firecrawl requests are cache-only by default and require an explicit fresh-scrape opt-in before the Firecrawl server can fetch target URLs. Bright Data Web Unlocker runs last of the remote scraping providers, ahead of only the Gemini fallbacks, because it is billed per request against a paid account; it is skipped unless both a key and an `unblocker` zone are configured. It applies no minimum-length check, so any non-empty body it returns — including a short consent or paywall stub — is the final answer for that URL and the Gemini fallbacks are not tried. Handles SPAs, JS-heavy pages, and anti-bot protections transparently. Also parses Next.js RSC flight data when present. HTML extraction also surfaces registered discovery relations (`service-desc`, `service-doc`, `service-meta`, `api-catalog`, `describedby`) from the HTTP `Link` header and matching `link`/`a[rel]` markup. Readable or rendered content remains primary; on an empty shell, the normal extraction fallbacks run before declared links are returned on their own.
 
 ## How It Works
 
@@ -322,17 +323,22 @@ Config defaults to `~/.pi/web-search.json`, or `web-search.json` under `PI_CODIN
   "openaiApiKey": "sk-...",
   "openaiResponsesUrl": "https://gateway.example.com/v1/responses",
   "braveApiKey": "BSA_...",
+  "braveBaseUrl": "https://gateway.example.com/brave/res/v1",
   "exaApiKey": "exa-...",
+  "exaBaseUrl": "https://gateway.example.com/exa",
   "parallelApiKey": "...",
   "tinyfishApiKey": "sk-tinyfish-...",
   "search1apiApiKey": "...",
   "tavilyApiKey": "tvly-...",
+  "tavilyBaseUrl": "https://gateway.example.com/tavily",
   "jinaApiKey": "$JINA_API_KEY",
   "serpdiveApiKey": "sd_live_...",
   "serpdiveModel": "krill",
   "kagiApiKey": "$KAGI_API_KEY",
   "ollamaApiKey": "$OLLAMA_API_KEY",
+  "valyuApiKey": "$VALYU_API_KEY",
   "serpbaseApiKey": "$SERPBASE_API_KEY",
+  "serperApiKey": "$SERPER_API_KEY",
   "brightdataApiKey": "$BRIGHTDATA_API_KEY",
   "brightdataSerpZone": "pi_serp",
   "searxngBaseUrl": "https://search.example.com",
@@ -426,6 +432,8 @@ Config defaults to `~/.pi/web-search.json`, or `web-search.json` under `PI_CODIN
 }
 ```
 
+`summaryModel` accepts an optional thinking-level suffix, such as `anthropic/claude-haiku-4-5:low`. Supported suffixes are `off`, `minimal`, `low`, `medium`, `high`, `xhigh`, and `max`.
+
 All provider API-key fields (`openaiApiKey`, `braveApiKey`, `parallelApiKey`, `tinyfishApiKey`, `search1apiApiKey`, `searchinfinityApiKey`, `queritApiKey`, `tavilyApiKey`, `jinaApiKey`, `serpdiveApiKey`, `kagiApiKey`, `bochaApiKey`, `ollamaApiKey`, `serpbaseApiKey`, `anysearchApiKey`, `xaiApiKey`, `brightdataApiKey`, `firecrawlApiKey`, `exaApiKey`, `perplexityApiKey`, `geminiApiKey`, `datalabApiKey`, and `cloudflareApiKey`) accept explicit credential sources. Use `$NAME` or `${NAME}` to read one named environment variable, or prefix a trusted local shell command with `!` to resolve one value at provider request time. Escape `$$` as a literal leading `$` and `$!` as a literal leading `!`:
 
 ```json
@@ -437,10 +445,12 @@ All provider API-key fields (`openaiApiKey`, `braveApiKey`, `parallelApiKey`, `t
 }
 ```
 
-This syntax applies to provider credentials only; other configuration fields are not interpolated. `firecrawlApiKey`, `kagiApiKey`, `ollamaApiKey`, `serpbaseApiKey`, and `brightdataApiKey` use the same credential-source rules, while `firecrawlBaseUrl`, `firecrawlApiVersion`, `firecrawlFreshScrape`, `brightdataSerpZone`, and `brightdataUnlockerZone` are literal config values.
+This syntax applies to provider credentials only; other configuration fields are not interpolated. `firecrawlApiKey`, `kagiApiKey`, `ollamaApiKey`, `valyuApiKey`, `serpbaseApiKey`, `serperApiKey`, and `brightdataApiKey` use the same credential-source rules, while `braveBaseUrl`, `exaBaseUrl`, `tavilyBaseUrl`, `firecrawlBaseUrl`, `firecrawlApiVersion`, `firecrawlFreshScrape`, `brightdataSerpZone`, and `brightdataUnlockerZone` are literal config values.
 
 A command source is not run while the extension loads or registers tools. Each selected provider request runs it again with a five-second timeout, a 16 KiB output limit, a minimized environment, and a one-line non-empty stdout requirement. Command text and stderr are omitted from errors. These commands are trusted local configuration, not a same-user process isolation boundary; use absolute executable paths and protect the config file. `OP_SESSION_*` variables are forwarded to trusted resolver commands so shell-local 1Password sessions can be reused without storing them in config. An explicit source overrides legacy provider environment variables and fails that provider locally rather than falling back with a stale credential. Direct Google Gemini API requests send the resolved key only in the `x-goog-api-key` header, never in the URL.
 
+Set `braveBaseUrl`, `exaBaseUrl`, or `tavilyBaseUrl` to route those providers through a compatible HTTPS API gateway. `BRAVE_BASE_URL`, `EXA_BASE_URL`, and `TAVILY_BASE_URL` are the environment-variable equivalents and take precedence over config. Brave appends `/web/search`, Exa appends `/answer` or `/search`, and Tavily appends `/search`. Defaults remain the providers' official API roots. `exaBaseUrl` applies only to keyed direct API calls; zero-config Exa MCP search continues to use Exa's hosted MCP endpoint. Invalid overrides fail before a request is sent instead of falling back to an official endpoint, and credential headers are removed if a gateway redirects to another origin.
+
 `authFetch` configures named local browser-cookie auth profiles for explicit `fetch_content` calls. A profile can be a host array (`"work": ["docs.company.com"]`) or an object with `hosts`, optional `chromeProfile`, `redirects: "same-origin"`, and `cache: "session" | "off"`.
 
 `fetchContent.domainPolicy` is an optional hostname allow/deny policy for `fetch_content` target URLs. It is off when omitted. Each bare hostname matches itself and its subdomains; `deny` wins when a hostname matches both lists. The policy is checked before HTTP(S) target handling and before each redirect followed by this extension's own fetch path. Local file paths and non-HTTP sources are not subject to this policy. It is an additional restriction: the existing SSRF guard still blocks private and internal destinations. Remote extraction services can still perform their own DNS, redirects, and egress after this extension preflights the submitted target URL, so third-party hosted HTTP(S) fallbacks stay disabled unless `fetchRouting.allowRemoteHostedProviders` is enabled for separately isolated provider deployments.
@@ -449,7 +459,7 @@ Set `searxngBaseUrl` or `SEARXNG_BASE_URL` to use a self-hosted SearXNG JSON API
 
 **DuckDuckGo.** DuckDuckGo HTML search is keyless and explicit-only. Select it with `provider: "duckduckgo"` or place it in `searchRouting`; it is never chosen by `auto` and never participates in `provider: "all"`. Domain filters are enforced locally after DuckDuckGo redirect URLs are decoded. `recencyFilter` is not guaranteed because the HTML endpoint has no documented stable time parameter. A 200 page with no parseable results is reported as an invalid response, so routing can continue when `fallbackOn` includes `"invalid-response"`.
 
-Set `firecrawlBaseUrl` or `FIRECRAWL_BASE_URL` to use Firecrawl for `web_search` and as an extraction fallback for `fetch_content`. Search calls `/v2/search` by default, requests `sources: ["web"]`, maps `numResults` to `limit`, maps `recencyFilter` to Firecrawl's `tbs`, and maps domain filters to `includeDomains` or `excludeDomains` when possible. With `includeContent: true`, Firecrawl search adds Markdown scrape options and returns successful result Markdown as inline content. Fetch extraction calls `/v2/scrape` by default. Set `firecrawlApiVersion` or `FIRECRAWL_API_VERSION` to `v1` for older self-hosted images. Firecrawl page scraping is cache-only by default (`lockdown: true`), so the Firecrawl server does not make fresh outbound target requests unless you explicitly set `firecrawlFreshScrape: true` or `FIRECRAWL_FRESH_SCRAPE=1`. Enable fresh scraping only for a Firecrawl deployment whose own egress, redirects, DNS rebinding behavior, and internal-network access are isolated or allowlisted; this extension can preflight submitted fetch URLs but cannot control network requests made by the Firecrawl server. The configured Firecrawl API base URL and redirects are still validated by the same SSRF guard as other remote requests, and Firecrawl credentials are stripped from cross-origin API redirects.
+Set `firecrawlBaseUrl` or `FIRECRAWL_BASE_URL` to use Firecrawl for `web_search` and as an extraction fallback for `fetch_content`. Search calls `/v2/search` by default, requests `sources: ["web"]`, maps `numResults` to `limit`, maps `recencyFilter` to Firecrawl's `tbs`, and maps domain filters to `includeDomains` or `excludeDomains` when possible. With `includeContent: true`, Firecrawl search adds Markdown scrape options and returns successful result Markdown as inline content. Fetch extraction calls `/v2/scrape` by default. Set `firecrawlApiVersion` or `FIRECRAWL_API_VERSION` to `v1` for older self-hosted images. Firecrawl page scraping is cache-only by default (`lockdown: true`), so the Firecrawl server does not make fresh outbound target requests unless you explicitly set `firecrawlFreshScrape: true` or `FIRECRAWL_FRESH_SCRAPE=1`. Enable fresh scraping only for a Firecrawl deployment whose own egress, redirects, DNS rebinding behavior, and internal-network access are isolated or allowlisted; this extension can preflight submitted fetch URLs but cannot control network requests made by the Firecrawl server. A configured Firecrawl API base URL may use `localhost`, `127.0.0.0/8`, or `::1` without adding those loopback ranges to global `ssrf.allowRanges`; that exception is only for Firecrawl API calls, not submitted fetch/search target URLs. The configured Firecrawl API base URL and redirects are otherwise still validated by the same SSRF guard as other remote requests, and Firecrawl credentials are stripped from cross-origin API redirects.
 
 **Bright Data.** Set `brightdataApiKey` or `BRIGHTDATA_API_KEY` to use Bright Data-backed features. The SERP search provider also requires `brightdataSerpZone` or `BRIGHTDATA_SERP_ZONE`, and the Web Unlocker extraction fallback also requires `brightdataUnlockerZone` or `BRIGHTDATA_UNLOCKER_ZONE`. These zone settings are separate and are never substituted for each other: SERP requires a Bright Data zone of type `serp`, while Web Unlocker requires a zone of type `unblocker`. Leaving either zone unset keeps that product unavailable, so enabling one Bright Data feature does not opt into the other.
 
@@ -463,11 +473,18 @@ Bright Data Web Unlocker is a paid `fetch_content` fallback after Parallel and b
 
 **SerpBase.** Set `serpbaseApiKey` or `SERPBASE_API_KEY` and select `provider: "serpbase"` to query SerpBase's Google Search Results API. SerpBase is explicit-only: it is never chosen by `auto` and never participates in `provider: "all"`, because each request can consume paid Google SERP credits. Domain filters are sent as Google `site:` clauses and reapplied locally; recency maps to Google's `tbs` time filter.
 
-Without an explicit `$` or `!` source, `OPENAI_API_KEY`, `BRAVE_API_KEY`, `PARALLEL_API_KEY`, `TINYFISH_API_KEY`, `SEARCH1API_KEY`, `SEARCHINFINITY_API_KEY`, `QUERIT_API_KEY`, `TAVILY_API_KEY`, `JINA_API_KEY`, `SERPDIVE_API_KEY`, `KAGI_API_KEY`, `BOCHA_API_KEY`, `OLLAMA_API_KEY`, `SERPBASE_API_KEY`, `ANYSEARCH_API_KEY`, `XAI_API_KEY`, `BRIGHTDATA_API_KEY`, `FIRECRAWL_API_KEY`, `EXA_API_KEY`, `GEMINI_API_KEY`, `DATALAB_API_KEY`, `DATALAB_PROCESSING_LOCATION`, `DATALAB_MODE`, `DATALAB_API_BASE`, `PERPLEXITY_API_KEY`, `GOOGLE_GEMINI_BASE_URL`, and `CLOUDFLARE_API_KEY` env vars retain their existing precedence over literal config file values. `openaiResponsesUrl` can point OpenAI `web_search` and `source_check` at a third-party gateway that supports the OpenAI Responses API and web search tool; it is an explicit endpoint override, not derived from Pi model provider settings, and defaults to `https://api.openai.com/v1/responses`. `openaiSearchModel` pins the model id used for OpenAI `web_search`, bypassing automatic selection (newest terra-tier model); the id is sent verbatim with whichever OpenAI auth resolves, so gateway-only model ids work too. `xaiSearchModel` similarly pins the xAI search model. Configured Exa API keys use Exa's own account limits directly; any legacy local `exa-usage.json` file is ignored. `GOOGLE_GEMINI_BASE_URL` overrides the Gemini API host for Gemini generate-content calls such as search, URL context, YouTube, and local video analysis. Set it to a bare host with no trailing slash and no version segment, for example `https://my-gateway.example.com/gemini`; `geminiBaseUrl` is the config-file equivalent. When the configured host contains `gateway.ai.cloudflare.com`, authentication uses `cf-aig-authorization: Bearer <token>` from `CLOUDFLARE_API_KEY` or `cloudflareApiKey`, and `GEMINI_API_KEY` is not required for generate-content calls. Local video file upload still uses Google's Files API directly, so gateway-only video extraction falls back to Gemini Web unless a `GEMINI_API_KEY` is also configured. `provider` or `searchProvider` sets the default search provider and is used when a tool call omits `provider` or sends `"auto"`: `"all"`, `"openai"`, `"brave"`, `"parallel"`, `"tinyfish"`, `"search1api"`, `"searchinfinity"`, `"querit"`, `"tavily"`, `"firecrawl"`, `"jina"`, `"serpdive"`, `"kagi"`, `"bocha"`, `"ollama"`, `"anysearch"`, `"xai"`, `"brightdata"`, `"serpbase"`, `"searxng"`, `"exa"`, `"perplexity"`, or `"gemini"`. AnySearch, xAI, Bright Data, and SerpBase are never selected by `auto`; choose them explicitly or place them in `searchRouting`. If either single-provider field is configured, it takes precedence over `searchRouting`. Otherwise, `searchRouting` can opt into an ordered `providers` list and an explicit `fallbackOn` list containing `"transient"`, `"quota"`, `"network"`, and/or `"invalid-response"`; only those typed failures continue to the next available candidate. `"all"` is not valid inside `searchRouting.providers`, because that list defines sequential fallback rather than multi-provider aggregation. Named providers remain strict, and exhausted routes return per-provider diagnostics. `provider` can also be a non-empty array of named providers such as `["brave", "exa"]`; those providers run concurrently using the same aggregation path as `"all"`, while `"auto"` and `"all"` are invalid inside arrays. Random, weighted, sticky, and cooldown routing are not enabled. This is also updated automatically when you change the provider in the curator UI. Set `webSearch.enabled` to `false` to unregister the configured search and source-check tools while leaving fetch/content tools available. `toolNames` can opt into alternate public tool names for environments where another extension or model reserves the defaults, without changing behavior: `webSearch`, `sourceCheck`, `fetchContent`, and `getSearchContent` default to `web_search`, `source_check`, `fetch_content`, and `get_search_content`. `workflow` sets the default search workflow: `"summary-review"` (default, opens curator with auto-generated summary draft), `"auto-summary"` (returns a model-generated summary without opening the curator), or `"none"` (raw results, no curator). Overridden per-call via the `workflow` parameter on the configured search tool, or toggled at runtime with `/curator`. `chromeProfile` pins Gemini Web cookie lookup to a specific Chromium profile. When omitted, detected Chromium profiles are scanned in stable order and the first profile containing the required Gemini cookies is used. macOS discovery supports Helium, Chrome, Brave, and Arc; Linux discovery supports Chromium and Chrome. `allowBrowserCookies` enables Chromium cookie extraction for Gemini Web; it defaults to `false` to avoid browser data access and surprise macOS Keychain prompts. You can also set `PI_ALLOW_BROWSER_COOKIES=1`. Cookie databases are copied to a temporary read-only working copy; the reader uses `node:sqlite` when available and otherwise tries the `sqlite3` CLI or Python's standard-library SQLite module. `searchModel` overrides the Gemini API model used by the configured search tool without changing URL, YouTube, or video extraction defaults. Gemini API grounded search uses `gemini-3.6-flash` by default; set `searchModel` to choose another model. Gemini Web browser-cookie fallback uses its separate `gemini-3.1-pro` default because Gemini Web relies on private header values; explicitly configured unsupported Web models fail instead of silently falling back to 2.5 Flash. `summaryModel` sets the default model used for generating summary drafts in the curator UI and `auto-summary` mode (e.g. `"anthropic/claude-haiku-4-5"`, `"openai-codex/gpt-5.3-codex-spark"`, or `"openrouter/nvidia/nemotron-3-super-120b-a12b:free"`). Preferred summary and query-rewrite models also resolve through routed provider registrations such as OpenRouter when the native provider is unavailable. When Pi `enabledModels` is configured, summaries are limited to that allowlist; if no enabled summary model is available, the tool returns a deterministic summary instead of calling an unrelated model. `summaryGenerationDeadlineMs` sets the maximum time for one summary model attempt in the curator UI and `auto-summary` mode. It defaults to `30000`, must be a positive integer, and is capped at `600000`. `maxInlineContentChars` sets the direct `fetch_content` content slice and the default and maximum `get_search_content` slice. It defaults to `30000`, must be a positive integer, and is capped at `200000`; full fetched content remains stored for later retrieval. `curatorTimeoutSeconds` controls the initial curator idle timeout (default `20`, max `600`); users can still adjust the timer in the curator UI. `ssrf.allowRanges` lists CIDR ranges (e.g. `"198.18.0.0/15"`, `"fd00::/8"`) exempted from the SSRF guard that otherwise blocks private/reserved IP ranges. This unblocks `fetch_content`/`web_search` on hosts whose network proxy runs in TUN + fake-IP mode (Surge, Clash, Mihomo, Stash, ...), where public domains resolve into a synthetic reserved range. It is **off by default** — the guard stays fully enabled unless you list ranges here. Use the narrowest range that covers your proxy's fake-IP pool. All-address CIDRs such as `0.0.0.0/0` and `::/0` are rejected. `ssrf.trustEnvProxy` is a separate opt-in for sandboxed environments with valid HTTP(S) proxy env vars; it skips local DNS preflight only for proxied hostnames and still blocks localhost, literal private IPs, and `NO_PROXY` matches. It does not configure proxy transport.
+**Valyu.** Set `valyuApiKey` or `VALYU_API_KEY` and select `provider: "valyu"` to query Valyu's research search API. Valyu is explicit-only: it is never chosen by `auto` or `provider: "all"`, but it can be configured as the named provider or added to `searchRouting`. Returned page bodies provide result snippets and optional inline content, capped at 2,500 and 4,000 characters per result.
+
+**Serper.** Set `serperApiKey` or `SERPER_API_KEY` and select `provider: "serper"` to query Serper's Google Search API. Serper is explicit-only: it is never chosen by `auto` or `provider: "all"`, but it can be configured as the named provider or added to `searchRouting`.
+
+**Parallel MCP.** Select `provider: "parallel-mcp"` to use Parallel Search MCP without an API key, or add it to `searchRouting`. It is explicit-only and is never chosen by `auto` or `provider: "all"`; the existing `parallel` provider remains the key-required REST API. A configured `parallelApiKey` or `PARALLEL_API_KEY` is sent as an optional Bearer token for higher MCP limits. To use MCP `web_fetch`, add `parallel-mcp` to `fetchRouting.providers` and set `fetchRouting.allowRemoteHostedProviders` to `true`; it is not part of the default fetch route.
+
+Without an explicit `$` or `!` source, `OPENAI_API_KEY`, `BRAVE_API_KEY`, `PARALLEL_API_KEY`, `TINYFISH_API_KEY`, `SEARCH1API_KEY`, `SEARCHINFINITY_API_KEY`, `QUERIT_API_KEY`, `TAVILY_API_KEY`, `JINA_API_KEY`, `SERPDIVE_API_KEY`, `KAGI_API_KEY`, `BOCHA_API_KEY`, `OLLAMA_API_KEY`, `SERPBASE_API_KEY`, `ANYSEARCH_API_KEY`, `XAI_API_KEY`, `BRIGHTDATA_API_KEY`, `FIRECRAWL_API_KEY`, `EXA_API_KEY`, `GEMINI_API_KEY`, `DATALAB_API_KEY`, `DATALAB_PROCESSING_LOCATION`, `DATALAB_MODE`, `DATALAB_API_BASE`, `PERPLEXITY_API_KEY`, `GOOGLE_GEMINI_BASE_URL`, and `CLOUDFLARE_API_KEY` env vars retain their existing precedence over literal config file values. `openaiResponsesUrl` can point OpenAI `web_search` and `source_check` at a third-party gateway that supports the OpenAI Responses API and web search tool; it is an explicit endpoint override, not derived from Pi model provider settings, and defaults to `https://api.openai.com/v1/responses`. `openaiSearchModel` pins the model id used for OpenAI `web_search`, bypassing automatic selection (newest terra-tier model); the id is sent verbatim with whichever OpenAI auth resolves, so gateway-only model ids work too. `xaiSearchModel` similarly pins the xAI search model. `openaiSearchProviders` sets which Pi model providers OpenAI `web_search` resolves login credentials from, in priority order; it defaults to `["openai-codex", "openai"]`, entries that are not registered or not signed in are skipped, and an empty array skips Pi credentials entirely so the `openaiApiKey` / `OPENAI_API_KEY` fallback applies. Useful for choosing between multiple Codex accounts (for example a second account registered by an extension) or forcing API-key billing while signed into Codex. Configured Exa API keys use Exa's own account limits directly; any legacy local `exa-usage.json` file is ignored. `GOOGLE_GEMINI_BASE_URL` overrides the Gemini API host for Gemini generate-content calls such as search, URL context, YouTube, and local video analysis. Set it to a bare host with no trailing slash and no version segment, for example `https://my-gateway.example.com/gemini`; `geminiBaseUrl` is the config-file equivalent. When the configured host contains `gateway.ai.cloudflare.com`, authentication uses `cf-aig-authorization: Bearer <token>` from `CLOUDFLARE_API_KEY` or `cloudflareApiKey`, and `GEMINI_API_KEY` is not required for generate-content calls. Local video file upload still uses Google's Files API directly, so gateway-only video extraction falls back to Gemini Web unless a `GEMINI_API_KEY` is also configured. `provider` or `searchProvider` sets the default search provider and is used when a tool call omits `provider` or sends `"auto"`: `"all"`, `"openai"`, `"brave"`, `"parallel"`, `"parallel-mcp"`, `"tinyfish"`, `"search1api"`, `"searchinfinity"`, `"querit"`, `"tavily"`, `"firecrawl"`, `"jina"`, `"serpdive"`, `"kagi"`, `"bocha"`, `"ollama"`, `"anysearch"`, `"valyu"`, `"xai"`, `"brightdata"`, `"serpbase"`, `"serper"`, `"searxng"`, `"exa"`, `"perplexity"`, or `"gemini"`. Parallel MCP, AnySearch, Valyu, xAI, Bright Data, SerpBase, and Serper are never selected by `auto`; choose them explicitly or place them in `searchRouting`. If either single-provider field is configured, it takes precedence over `searchRouting`. Otherwise, `searchRouting` can opt into an ordered `providers` list and an explicit `fallbackOn` list containing `"transient"`, `"quota"`, `"network"`, and/or `"invalid-response"`; only those typed failures continue to the next available candidate. `"all"` is not valid inside `searchRouting.providers`, because that list defines sequential fallback rather than multi-provider aggregation. Named providers remain strict, and exhausted routes return per-provider diagnostics. `provider` can also be a non-empty array of named providers such as `["brave", "exa"]`; those providers run concurrently using the same aggregation path as `"all"`, while `"auto"` and `"all"` are invalid inside arrays. Random, weighted, sticky, and cooldown routing are not enabled. This is also updated automatically when you change the provider in the curator UI. Set `webSearch.enabled` to `false` to unregister the configured search and source-check tools while leaving fetch/content tools available. `toolNames` can opt into alternate public tool names for environments where another extension or model reserves the defaults, without changing behavior: `webSearch`, `sourceCheck`, `fetchContent`, and `getSearchContent` default to `web_search`, `source_check`, `fetch_content`, and `get_search_content`. `workflow` sets the default search workflow: `"summary-review"` (default, opens curator with auto-generated summary draft), `"auto-summary"` (returns a model-generated summary without opening the curator), or `"none"` (raw results, no curator). Overridden per-call via the `workflow` parameter on the configured search tool, or toggled at runtime with `/curator`. `chromeProfile` pins Gemini Web cookie lookup to a specific Chromium profile. When omitted, detected Chromium profiles are scanned in stable order and the first profile containing the required Gemini cookies is used. macOS discovery supports Helium, Chrome, Brave, and Arc; Linux discovery supports Chromium and Chrome. `allowBrowserCookies` enables Chromium cookie extraction for Gemini Web; it defaults to `false` to avoid browser data access and surprise macOS Keychain prompts. You can also set `PI_ALLOW_BROWSER_COOKIES=1`. Cookie databases are copied to a temporary read-only working copy; the reader uses `node:sqlite` when available and otherwise tries the `sqlite3` CLI or Python's standard-library SQLite module. `searchModel` overrides the Gemini API model used by the configured search tool without changing URL, YouTube, or video extraction defaults. Gemini API grounded search uses `gemini-3.6-flash` by default; set `searchModel` to choose another model. Gemini Web browser-cookie fallback uses its separate `gemini-3.1-pro` default because Gemini Web relies on private header values; explicitly configured unsupported Web models fail instead of silently falling back to 2.5 Flash. `summaryModel` sets the default model used for generating summary drafts in the curator UI and `auto-summary` mode (e.g. `"anthropic/claude-haiku-4-5"`, `"openai-codex/gpt-5.3-codex-spark"`, or `"openrouter/nvidia/nemotron-3-super-120b-a12b:free"`). Preferred summary and query-rewrite models also resolve through routed provider registrations such as OpenRouter when the native provider is unavailable. When Pi `enabledModels` is configured, summaries are limited to that allowlist; if no enabled summary model is available, the tool returns a deterministic summary instead of calling an unrelated model. `summaryGenerationDeadlineMs` sets the maximum time for one summary model attempt in the curator UI and `auto-summary` mode. It defaults to `30000`, must be a positive integer, and is capped at `600000`. `maxInlineContentChars` sets the direct `fetch_content` content slice and the default and maximum `get_search_content` slice. It defaults to `30000`, must be a positive integer, and is capped at `200000`; full fetched content remains stored for later retrieval. `curatorTimeoutSeconds` controls the initial curator idle timeout (default `20`, max `600`); users can still adjust the timer in the curator UI. `ssrf.allowRanges` lists CIDR ranges (e.g. `"198.18.0.0/15"`, `"fd00::/8"`) exempted from the SSRF guard that otherwise blocks private/reserved IP ranges. This unblocks `fetch_content`/`web_search` on hosts whose network proxy runs in TUN + fake-IP mode (Surge, Clash, Mihomo, Stash, ...), where public domains resolve into a synthetic reserved range. It is **off by default** — the guard stays fully enabled unless you list ranges here. Use the narrowest range that covers your proxy's fake-IP pool. All-address CIDRs such as `0.0.0.0/0` and `::/0` are rejected. `ssrf.trustEnvProxy` is a separate opt-in for sandboxed environments with valid HTTP(S) proxy env vars; it skips local DNS preflight only for proxied hostnames and still blocks localhost, literal private IPs, and `NO_PROXY` matches. It does not configure proxy transport.
+`VALYU_API_KEY` and `SERPER_API_KEY` also retain this precedence. `provider` and `searchProvider` also accept `"parallel-mcp"`, `"valyu"`, and `"serper"`; all three remain explicit-only.
 
 ### All providers
 
-Set `provider: "all"` on `web_search` or `source_check`, or configure `"provider": "all"` as the default, to run the same query against every eligible search provider simultaneously. DuckDuckGo, AnySearch, xAI, Bright Data, and SerpBase are always excluded because they are explicit-only; Bright Data and SerpBase are paid Google SERP providers, so `all` never spends on them. Exa remains eligible through its zero-config MCP path, OpenAI can use Pi auth, and other API-backed search providers participate when their API key, local endpoint, or gateway makes them available. Browser-cookie access alone does not opt Gemini into `all`; select Gemini explicitly or configure its API/gateway.
+Set `provider: "all"` on `web_search` or `source_check`, or configure `"provider": "all"` as the default, to run the same query against every eligible search provider simultaneously. Parallel MCP, DuckDuckGo, AnySearch, Valyu, xAI, Bright Data, SerpBase, and Serper are always excluded because they are explicit-only; Bright Data, SerpBase, and Serper are paid Google SERP providers, so `all` never spends on them. Exa remains eligible through its zero-config MCP path, OpenAI can use Pi auth, and other API-backed search providers participate when their API key, local endpoint, or gateway makes them available. Browser-cookie access alone does not opt Gemini into `all`; select Gemini explicitly or configure its API/gateway.
 
 Successful provider answers are preserved separately while source URLs and inline content are deduplicated, and one provider failure does not discard the other results. If every participating provider fails, the tool returns per-provider diagnostics. Configured Firecrawl participates in `all` like other eligible providers. In the Curator, **All** can also be selected like the other provider buttons. Each participating provider gets its own result card, including a provider badge and independent selection checkbox; failed providers get their own disabled error card. The final summary is generated from the selected provider cards and is what Pi receives. Outside the Curator, the same provider answers remain available as labeled sections in one tool response.
 
@@ -794,12 +811,12 @@ Values use the same format as pi keybindings (e.g. `ctrl+s`, `ctrl+shift+s`, `al
 
 Set `"enabled": false` under `tools`, `commands`, `image`, or `pdf` to disable that feature. Tool-specific settings override the legacy `webSearch.enabled` shorthand; without an override, it still disables `web_search` and `source_check`. `image.enabled: false` blocks direct image fetches and video frame extraction, and prevents video thumbnails. `pdf.enabled: false` blocks PDF extraction. For GitHub specifically, `githubClone.enabled: false` only skips clone/API specialization; it does not unregister `fetch_content` or block generic URL extraction. Pi restart is required for tool and command registration changes.
 
-Rate limits: Perplexity is capped at 10 requests/minute (client-side). Jina Search, TinyFish, Search1API, and Searchinfinity apply the plan limits documented by their APIs. Querit Search and Contents subscriptions are independent. Content fetches run 3 concurrent with a 30s timeout for the direct HTTP fetch of each URL. Remote extraction fallbacks carry their own budgets and are not covered by that number: Jina Reader 30s, Firecrawl 60s, Kagi Extract 60s, Ollama Web Fetch 60s, Bright Data Web Unlocker 60s, TinyFish up to 150s, Gemini 120s, Datalab 120s (capped at 300s, rate-limited to 25 requests/minute on the free tier). `pdf.maxSizeMB` defaults to 20 and is capped at 50.
+Rate limits: Perplexity is capped at 10 requests/minute (client-side). Jina Search, TinyFish, Search1API, and Searchinfinity apply the plan limits documented by their APIs. Querit Search and Contents subscriptions are independent. Content fetches run 3 concurrent with a 30s timeout for the direct HTTP fetch of each URL. Remote extraction fallbacks carry their own budgets and are not covered by that number: Jina Reader 30s, Firecrawl 60s, Kagi Extract 60s, Ollama Web Fetch 60s, Bright Data Web Unlocker 60s, TinyFish up to 150s, Gemini 120s, Datalab 120s (capped at 300s, rate-limited to 25 requests/minute on the free tier). `pdf.maxSizeMB` defaults to 20 and is capped at 50. `pdf.maxPages` defaults to 100 and limits every PDF provider to the first N pages.
 
 ## Limitations
 
 - If the curator cannot open a browser automatically, such as in Docker, WSL, SSH, or headless environments, the running curator URL is shown in the tool output. Copy it into a browser that can reach the Pi host, or use a tunnel/port-forward when needed.
-- Chromium cookie extraction for Gemini Web is opt-in via `allowBrowserCookies: true` or `PI_ALLOW_BROWSER_COOKIES=1`; no browser data or password store is touched while it is disabled. On macOS, enabling it may trigger a Keychain dialog. Required cookie names are checked before password-store access, and browser encryption passwords are cached only in-process. If `node:sqlite` is unavailable, the reader falls back to the `sqlite3` CLI or Python stdlib; `/google-account` reports a sanitized SQLite/profile/password diagnostic when extraction fails.
+- Chromium cookie extraction for Gemini Web is opt-in via `allowBrowserCookies: true` or `PI_ALLOW_BROWSER_COOKIES=1`; no browser data or password store is touched while it is disabled. On macOS, enabling it may trigger a Keychain dialog. On Windows, Chrome and Edge v10 cookies use the current user's DPAPI key; v20 app-bound cookies are not supported. Required cookie names are checked before password-store access, and browser encryption passwords are cached only in-process. If `node:sqlite` is unavailable, the reader falls back to the `sqlite3` CLI or Python stdlib; `/google-account` reports a sanitized SQLite/profile/password diagnostic when extraction fails.
 - YouTube private/age-restricted videos may fail on all extraction paths.
 - Gemini can process videos up to ~1 hour; longer videos may be truncated.
 - PDFs are text-extracted only (no OCR for scanned documents).
@@ -831,7 +848,9 @@ Rate limits: Perplexity is capped at 10 requests/minute (client-side). Jina Sear
 | `ollama.ts` | Ollama Cloud Web Search provider and Web Fetch fallback |
 | `brightdata.ts` | Explicit-only Bright Data SERP search provider |
 | `serpbase.ts` | Explicit-only SerpBase Google SERP provider |
+| `serper.ts` | Explicit-only Serper Google SERP provider |
 | `anysearch.ts` | Explicit-only AnySearch search provider |
+| `valyu.ts` | Explicit-only Valyu research search provider |
 | `xai-search.ts` | Explicit-only xAI (Grok) hosted web_search provider |
 | `searxng.ts` | Self-hosted SearXNG JSON API search provider |
 | `duckduckgo.ts` | Explicit-only keyless DuckDuckGo HTML search provider |
@@ -844,7 +863,7 @@ Rate limits: Perplexity is capped at 10 requests/minute (client-side). Jina Sear
 | `gemini-web.ts` | Gemini Web client (cookie auth, StreamGenerate) |
 | `gemini-web-config.ts` | Gemini Web profile and browser-cookie opt-in config |
 | `gemini-api.ts` | Gemini REST API client (generateContent) |
-| `chrome-cookies.ts` | macOS/Linux Chromium-based cookie extraction (Keychain/secret-tool + SQLite) |
+| `chrome-cookies.ts` | Chromium-based cookie extraction (macOS Keychain, Linux secret-tool, Windows DPAPI + SQLite) |
 | `youtube-extract.ts` | YouTube detection, three-tier extraction, frame extraction |
 | `video-extract.ts` | Local video detection, Files API upload, Gemini analysis |
 | `github-extract.ts` | GitHub URL parsing, clone cache, content generation |

package/node_modules/pi-web-access/anysearch.ts

@@ -103,9 +103,11 @@ function parseResponse(value: unknown): AnySearchResponse {
 		if (typeof title !== "string") throw invalidResponse(`expected data.results[${index}].title string`);
 		if (typeof url !== "string") throw invalidResponse(`expected data.results[${index}].url string`);
 		if (typeof snippet !== "string") throw invalidResponse(`expected data.results[${index}].snippet string`);
-		if (typeof content !== "string") throw invalidResponse(`expected data.results[${index}].content string`);
+		if (content !== undefined && content !== null && typeof content !== "string") {
+			throw invalidResponse(`expected data.results[${index}].content string`);
+		}
 		if (!url) throw invalidResponse(`expected data.results[${index}].url to be non-empty`);
-		results.push({ title, url, snippet, content });
+		results.push({ title, url, snippet, content: typeof content === "string" ? content : "" });
 	}
 
 	return { code: 0, data: { results, metadata: data.metadata as Record<string, unknown> } };

package/node_modules/pi-web-access/brave.ts

@@ -2,14 +2,15 @@ import { existsSync, readFileSync } from "node:fs";
 import { activityMonitor } from "./activity.ts";
 import type { SearchOptions, SearchResult, SearchResponse } from "./perplexity.ts";
 import { hasCredentialSource, redactCredential, resolveCredential } from "./credential-source.ts";
-import { getWebSearchConfigPath } from "./utils.ts";
+import { fetchWithCredentialRedirects, getWebSearchConfigPath, resolveApiBaseUrl } from "./utils.ts";
 
-const BRAVE_API_URL = "https://api.search.brave.com/res/v1/web/search";
+const BRAVE_API_BASE_URL = "https://api.search.brave.com/res/v1";
 const CONFIG_PATH = getWebSearchConfigPath();
 const SEARCH_TIMEOUT_MS = 30_000;
 
 interface WebSearchConfig {
 	braveApiKey?: unknown;
+	braveBaseUrl?: unknown;
 }
 
 interface NormalizedDomainFilters {
@@ -45,6 +46,16 @@ async function getApiKey(signal?: AbortSignal): Promise<string | null> {
 	});
 }
 
+function getApiUrl(): string {
+	return `${resolveApiBaseUrl({
+		configKey: "braveBaseUrl",
+		configuredValue: loadConfig().braveBaseUrl,
+		defaultValue: BRAVE_API_BASE_URL,
+		environmentKey: "BRAVE_BASE_URL",
+		environmentValue: process.env.BRAVE_BASE_URL,
+	})}/web/search`;
+}
+
 function normalizeCount(value: number | undefined): number {
 	if (typeof value !== "number" || !Number.isFinite(value)) return 5;
 	return Math.max(1, Math.min(Math.floor(value), 20));
@@ -129,6 +140,7 @@ export async function searchWithBrave(
 	query: string,
 	options: SearchOptions = {},
 ): Promise<SearchResponse> {
+	const apiUrl = getApiUrl();
 	const apiKey = await getApiKey(options.signal);
 	if (!apiKey) {
 		throw new Error(
@@ -160,7 +172,7 @@ export async function searchWithBrave(
 	}
 
 	try {
-		const response = await fetch(`${BRAVE_API_URL}?${params.toString()}`, {
+		const response = await fetchWithCredentialRedirects(`${apiUrl}?${params.toString()}`, {
 			method: "GET",
 			headers: {
 				"X-Subscription-Token": apiKey,
@@ -170,7 +182,7 @@ export async function searchWithBrave(
 			signal: options.signal
 				? AbortSignal.any([AbortSignal.timeout(SEARCH_TIMEOUT_MS), options.signal])
 				: AbortSignal.timeout(SEARCH_TIMEOUT_MS),
-		});
+		}, ["X-Subscription-Token"]);
 
 		if (!response.ok) {
 			activityMonitor.logError(activityId, `HTTP ${response.status}`);

package/node_modules/pi-web-access/chrome-cookies.ts

@@ -1,6 +1,6 @@
 import { execFile } from "node:child_process";
 import { pbkdf2Sync, createDecipheriv } from "node:crypto";
-import { copyFileSync, existsSync, mkdtempSync, readdirSync, realpathSync, rmSync } from "node:fs";
+import { copyFileSync, existsSync, mkdtempSync, readdirSync, readFileSync, realpathSync, rmSync } from "node:fs";
 import { tmpdir, homedir } from "node:os";
 import { isAbsolute, join, sep } from "node:path";
 import { isBrowserCookieAccessAllowed } from "./gemini-web-config.ts";
@@ -10,6 +10,7 @@ export type CookieMap = Record<string, string>;
 interface BrowserConfig {
 	name: string;
 	baseDir: string;
+	usesLocalAppData?: boolean;
 	keychainService?: string;
 	keychainAccount?: string;
 	secretToolApp?: string;
@@ -48,6 +49,11 @@ const LINUX_BROWSER_CONFIGS: BrowserConfig[] = [
 	{ name: "Chrome", baseDir: ".config/google-chrome", secretToolApp: "chrome" },
 ];
 
+const WINDOWS_BROWSER_CONFIGS: BrowserConfig[] = [
+	{ name: "Chrome", baseDir: "Google/Chrome/User Data", usesLocalAppData: true },
+	{ name: "Edge", baseDir: "Microsoft/Edge/User Data", usesLocalAppData: true },
+];
+
 const browserPasswordCache = new Map<string, Promise<string | null>>();
 let lastCookieDiagnostic: string | null = null;
 let sqliteModule: typeof import("node:sqlite") | null = null;
@@ -83,7 +89,7 @@ export async function getBrowserCookiesForHosts(
 	}
 
 	const currentPlatform = process.platform;
-	const configs = currentPlatform === "darwin" ? MACOS_BROWSER_CONFIGS : currentPlatform === "linux" ? LINUX_BROWSER_CONFIGS : [];
+	const configs = currentPlatform === "darwin" ? MACOS_BROWSER_CONFIGS : currentPlatform === "linux" ? LINUX_BROWSER_CONFIGS : currentPlatform === "win32" ? WINDOWS_BROWSER_CONFIGS : [];
 	if (configs.length === 0) {
 		lastCookieDiagnostic = "Chromium cookie extraction is unsupported on this platform.";
 		return null;
@@ -103,12 +109,13 @@ export async function getBrowserCookiesForHosts(
 		lastCookieDiagnostic = "No valid cookie hosts were requested.";
 		return null;
 	}
-	const home = homedir();
+	const home = currentPlatform === "win32" ? process.env.USERPROFILE || homedir() : homedir();
 	let sawCookieDatabase = false;
 	let sawRequiredCookies = false;
 	let sawAnyHostCookie = false;
 	let sawBackendFailure: SqliteFailure | undefined;
 	let sawUnsafeProfilePath = false;
+	let sawWindowsAppBoundCookie = false;
 
 	for (const config of configs) {
 		const profiles = requestedProfile ? [requestedProfile] : listBrowserProfiles(home, config);
@@ -119,7 +126,8 @@ export async function getBrowserCookiesForHosts(
 				continue;
 			}
 			if (!profilePath) continue;
-			const cookiesPath = join(profilePath, "Cookies");
+			const cookiesPath = cookieDatabasePath(profilePath, config);
+			if (!cookiesPath) continue;
 			sawCookieDatabase = true;
 
 			const tempDir = mkdtempSync(join(tmpdir(), "pi-chrome-cookies-"));
@@ -136,13 +144,15 @@ export async function getBrowserCookiesForHosts(
 					sawRequiredCookies = true;
 				}
 
-				const password = await readBrowserPassword(config, currentPlatform);
-				if (!password) {
-					warningSet.add(`Could not read ${config.name} cookie encryption password`);
+				const key = currentPlatform === "win32"
+					? await readWindowsEncryptionKey(config, home)
+					: await readBrowserPassword(config, currentPlatform).then((password) => password ? pbkdf2Sync(password, "saltysalt", currentPlatform === "darwin" ? 1003 : 1, 16, "sha1") : null);
+				if (!key) {
+					warningSet.add(currentPlatform === "win32"
+						? `Could not read ${config.name} Windows cookie encryption key`
+						: `Could not read ${config.name} cookie encryption password`);
 					continue;
 				}
-
-				const key = pbkdf2Sync(password, "saltysalt", currentPlatform === "darwin" ? 1003 : 1, 16, "sha1");
 				const metaVersion = await readMetaVersion(tempDb);
 				if (metaVersion.failure) sawBackendFailure = metaVersion.failure;
 				if (metaVersion.value === null) continue;
@@ -159,7 +169,11 @@ export async function getBrowserCookiesForHosts(
 					if (!name) continue;
 					let value = typeof row.value === "string" && row.value.length > 0 ? row.value : null;
 					if (!value && typeof row.encrypted_value_hex === "string" && /^[0-9a-f]*$/i.test(row.encrypted_value_hex)) {
-						value = decryptCookieValue(Buffer.from(row.encrypted_value_hex, "hex"), key, metaVersion.value >= 24);
+						const encrypted = Buffer.from(row.encrypted_value_hex, "hex");
+						if (currentPlatform === "win32" && encrypted.subarray(0, 3).toString("utf8") === "v20") sawWindowsAppBoundCookie = true;
+						value = currentPlatform === "win32"
+							? decryptWindowsCookieValue(encrypted, key, metaVersion.value >= 24)
+							: decryptCookieValue(encrypted, key, metaVersion.value >= 24);
 					}
 					if (!value) continue;
 					const path = typeof row.path === "string" && row.path.startsWith("/") ? row.path : "/";
@@ -194,6 +208,8 @@ export async function getBrowserCookiesForHosts(
 			: "No detected Chromium profile contains a cookie database.";
 	} else if (requiredCookies?.length && !sawRequiredCookies) {
 		lastCookieDiagnostic = `No detected Chromium profile contains the required ${options.requiredLabel ?? "browser"} cookies.`;
+	} else if (sawWindowsAppBoundCookie) {
+		lastCookieDiagnostic = "Windows Chromium v20 app-bound cookies are not supported.";
 	} else if (!sawAnyHostCookie) {
 		lastCookieDiagnostic = options.requestUrl
 			? "No detected Chromium profile contains cookies for the requested URL."
@@ -217,10 +233,9 @@ function normalizeProfileName(value: string | undefined): string | undefined {
 }
 
 function resolveProfilePath(home: string, config: BrowserConfig, profile: string): string | "outside-root" | null {
-	const basePath = join(home, config.baseDir);
+	const basePath = browserBasePath(home, config);
 	const profilePath = join(basePath, profile);
-	const cookiesPath = join(profilePath, "Cookies");
-	if (!existsSync(cookiesPath)) return null;
+	if (!cookieDatabasePath(profilePath, config)) return null;
 	try {
 		const baseRealPath = realpathSync(basePath);
 		const profileRealPath = realpathSync(profilePath);
@@ -231,6 +246,19 @@ function resolveProfilePath(home: string, config: BrowserConfig, profile: string
 	}
 }
 
+function cookieDatabasePath(profilePath: string, config: BrowserConfig): string | null {
+	const networkCookies = join(profilePath, "Network", "Cookies");
+	if (config.usesLocalAppData && existsSync(networkCookies)) return networkCookies;
+	const legacyCookies = join(profilePath, "Cookies");
+	return existsSync(legacyCookies) ? legacyCookies : null;
+}
+
+function browserBasePath(home: string, config: BrowserConfig): string {
+	return config.usesLocalAppData
+		? join(process.env.LOCALAPPDATA || join(home, "AppData", "Local"), config.baseDir)
+		: join(home, config.baseDir);
+}
+
 function normalizeCookieNames(names: string[] | undefined): string[] | undefined {
 	if (!names?.length) return undefined;
 	const normalized = names.filter((name): name is string => typeof name === "string").map((name) => name.trim()).filter(Boolean);
@@ -242,12 +270,12 @@ function normalizeHosts(hosts: string[]): string[] {
 }
 
 function listBrowserProfiles(home: string, config: BrowserConfig): string[] {
-	const basePath = join(home, config.baseDir);
+	const basePath = browserBasePath(home, config);
 	if (!existsSync(basePath)) return ["Default"];
 	const profiles = new Set<string>();
 	try {
 		for (const entry of readdirSync(basePath, { withFileTypes: true })) {
-			if (entry.isDirectory() && existsSync(join(basePath, entry.name, "Cookies"))) profiles.add(entry.name);
+			if (entry.isDirectory() && cookieDatabasePath(join(basePath, entry.name), config)) profiles.add(entry.name);
 		}
 	} catch {
 	}
@@ -288,6 +316,21 @@ function decryptCookieValue(encrypted: Uint8Array, key: Buffer, stripHash: boole
 	}
 }
 
+function decryptWindowsCookieValue(encrypted: Uint8Array, key: Buffer, stripHash: boolean): string | null {
+	const buf = Buffer.from(encrypted);
+	if (buf.subarray(0, 3).toString("utf8") !== "v10" || buf.length < 3 + 12 + 16) return null;
+	try {
+		const nonce = buf.subarray(3, 15);
+		const ciphertext = buf.subarray(15, -16);
+		const decipher = createDecipheriv("aes-256-gcm", key, nonce);
+		decipher.setAuthTag(buf.subarray(-16));
+		const plaintext = Buffer.concat([decipher.update(ciphertext), decipher.final()]);
+		return new TextDecoder("utf-8", { fatal: true }).decode(stripHash && plaintext.length >= 32 ? plaintext.subarray(32) : plaintext);
+	} catch {
+		return null;
+	}
+}
+
 function removePkcs7Padding(buf: Buffer): Buffer {
 	if (!buf.length) return buf;
 	const padding = buf[buf.length - 1];
@@ -316,6 +359,34 @@ function readBrowserPassword(config: BrowserConfig, currentPlatform: typeof proc
 	return passwordPromise;
 }
 
+async function readWindowsEncryptionKey(config: BrowserConfig, home: string): Promise<Buffer | null> {
+	try {
+		const localState = JSON.parse(readFileSync(join(browserBasePath(home, config), "Local State"), "utf8")) as { os_crypt?: { encrypted_key?: unknown } };
+		const encodedKey = localState.os_crypt?.encrypted_key;
+		if (typeof encodedKey !== "string") return null;
+		const protectedKey = Buffer.from(encodedKey, "base64");
+		if (protectedKey.subarray(0, 5).toString("utf8") !== "DPAPI") return null;
+		const decrypted = await unprotectWindowsData(protectedKey.subarray(5));
+		return decrypted?.length === 32 ? decrypted : null;
+	} catch {
+		return null;
+	}
+}
+
+function unprotectWindowsData(protectedData: Buffer): Promise<Buffer | null> {
+	return new Promise((resolve) => {
+		const script = "$data=[Convert]::FromBase64String($args[0]);$clear=[Security.Cryptography.ProtectedData]::Unprotect($data,$null,[Security.Cryptography.DataProtectionScope]::CurrentUser);[Console]::Write([Convert]::ToBase64String($clear))";
+		execFile("powershell.exe", ["-NoProfile", "-NonInteractive", "-Command", script, protectedData.toString("base64")], { timeout: 5000, maxBuffer: 1024 * 1024 }, (err, stdout) => {
+			if (err) { resolve(null); return; }
+			try {
+				resolve(Buffer.from(stdout.trim(), "base64"));
+			} catch {
+				resolve(null);
+			}
+		});
+	});
+}
+
 function readKeychainPassword(account: string, service: string): Promise<string | null> {
 	return new Promise((resolve) => {
 		execFile("security", ["find-generic-password", "-w", "-a", account, "-s", service], { timeout: 5000 }, (err, stdout) => {

package/node_modules/pi-web-access/curator-page.ts

@@ -8,7 +8,7 @@ function safeInlineJSON(data: unknown): string {
 }
 
 function buildProviderButtons(
-	available: { all: boolean; openai: boolean; brave: boolean; parallel: boolean; tinyfish: boolean; search1api: boolean; searchinfinity: boolean; querit: boolean; tavily: boolean; firecrawl: boolean; jina: boolean; serpdive: boolean; kagi: boolean; bocha: boolean; ollama: boolean; searxng: boolean; duckduckgo: boolean; perplexity: boolean; exa: boolean; gemini: boolean; anysearch: boolean; xai: boolean; brightdata: boolean; serpbase: boolean },
+	available: { all: boolean; openai: boolean; brave: boolean; parallel: boolean; "parallel-mcp": boolean; tinyfish: boolean; search1api: boolean; searchinfinity: boolean; querit: boolean; tavily: boolean; firecrawl: boolean; jina: boolean; serpdive: boolean; kagi: boolean; bocha: boolean; ollama: boolean; searxng: boolean; duckduckgo: boolean; perplexity: boolean; exa: boolean; gemini: boolean; anysearch: boolean; xai: boolean; brightdata: boolean; serpbase: boolean; serper: boolean; valyu: boolean },
 	selected: string,
 	hasInitialQueries: boolean,
 ): string {
@@ -18,6 +18,7 @@ function buildProviderButtons(
 		{ value: "exa", label: "Exa", available: available.exa },
 		{ value: "brave", label: "Brave", available: available.brave },
 		{ value: "parallel", label: "Parallel", available: available.parallel },
+		{ value: "parallel-mcp", label: "Parallel MCP", available: available["parallel-mcp"] },
 		{ value: "tinyfish", label: "TinyFish", available: available.tinyfish },
 		{ value: "search1api", label: "Search1API", available: available.search1api },
 		{ value: "searchinfinity", label: "Searchinfinity", available: available.searchinfinity },
@@ -37,6 +38,8 @@ function buildProviderButtons(
 		{ value: "xai", label: "xAI", available: available.xai },
 		{ value: "brightdata", label: "Bright Data", available: available.brightdata },
 		{ value: "serpbase", label: "SerpBase", available: available.serpbase },
+		{ value: "serper", label: "Serper", available: available.serper },
+		{ value: "valyu", label: "Valyu", available: available.valyu },
 	];
 
 	return providers
@@ -55,7 +58,7 @@ export function generateCuratorPage(
 	queries: string[],
 	sessionToken: string,
 	timeout: number,
-	availableProviders: { all: boolean; openai: boolean; brave: boolean; parallel: boolean; tinyfish: boolean; search1api: boolean; searchinfinity: boolean; querit: boolean; tavily: boolean; firecrawl: boolean; jina: boolean; serpdive: boolean; kagi: boolean; bocha: boolean; ollama: boolean; searxng: boolean; duckduckgo: boolean; perplexity: boolean; exa: boolean; gemini: boolean; anysearch: boolean; xai: boolean; brightdata: boolean; serpbase: boolean },
+	availableProviders: { all: boolean; openai: boolean; brave: boolean; parallel: boolean; "parallel-mcp": boolean; tinyfish: boolean; search1api: boolean; searchinfinity: boolean; querit: boolean; tavily: boolean; firecrawl: boolean; jina: boolean; serpdive: boolean; kagi: boolean; bocha: boolean; ollama: boolean; searxng: boolean; duckduckgo: boolean; perplexity: boolean; exa: boolean; gemini: boolean; anysearch: boolean; xai: boolean; brightdata: boolean; serpbase: boolean; serper: boolean; valyu: boolean },
 	defaultProvider: string,
 	searchProvider: string,
 	summaryModels: Array<{ value: string; label: string }>,
@@ -1456,7 +1459,7 @@ const SCRIPT = `(function() {
   var token = DATA.sessionToken;
   var timeoutSec = DATA.timeout;
   var queries = Array.isArray(DATA.queries) ? DATA.queries : [];
-  var providers = ["all", "openai", "exa", "brave", "parallel", "tinyfish", "search1api", "searchinfinity", "querit", "tavily", "firecrawl", "jina", "serpdive", "kagi", "bocha", "ollama", "searxng", "duckduckgo", "perplexity", "gemini", "anysearch", "xai", "brightdata", "serpbase"];
+  var providers = ["all", "openai", "exa", "brave", "parallel", "parallel-mcp", "tinyfish", "search1api", "searchinfinity", "querit", "tavily", "firecrawl", "jina", "serpdive", "kagi", "bocha", "ollama", "searxng", "duckduckgo", "perplexity", "gemini", "anysearch", "xai", "brightdata", "serpbase", "serper", "valyu"];
   var availProviders = DATA.availableProviders && typeof DATA.availableProviders === "object" ? DATA.availableProviders : {};
   var workflow = "summary-review";
   var initialDefaultProvider = typeof DATA.defaultProvider === "string" ? DATA.defaultProvider : "exa";

package/node_modules/pi-web-access/curator-server.ts

@@ -18,7 +18,7 @@ export interface CuratorServerOptions {
 	queries: string[];
 	sessionToken: string;
 	timeout: number;
-	availableProviders: { all: boolean; openai: boolean; brave: boolean; parallel: boolean; tinyfish: boolean; search1api: boolean; searchinfinity: boolean; querit: boolean; tavily: boolean; firecrawl: boolean; jina: boolean; serpdive: boolean; kagi: boolean; bocha: boolean; ollama: boolean; searxng: boolean; duckduckgo: boolean; perplexity: boolean; exa: boolean; gemini: boolean; anysearch: boolean; xai: boolean; brightdata: boolean; serpbase: boolean };
+	availableProviders: { all: boolean; openai: boolean; brave: boolean; parallel: boolean; "parallel-mcp": boolean; tinyfish: boolean; search1api: boolean; searchinfinity: boolean; querit: boolean; tavily: boolean; firecrawl: boolean; jina: boolean; serpdive: boolean; kagi: boolean; bocha: boolean; ollama: boolean; searxng: boolean; duckduckgo: boolean; perplexity: boolean; exa: boolean; gemini: boolean; anysearch: boolean; xai: boolean; brightdata: boolean; serpbase: boolean; serper: boolean; valyu: boolean };
 	defaultProvider: string;
 	searchProvider: string;
 	summaryModels: Array<{ value: string; label: string }>;
@@ -275,6 +275,7 @@ export function startCuratorServer(
 		if (provider === "openai") return availableProviders.openai;
 		if (provider === "brave") return availableProviders.brave;
 		if (provider === "parallel") return availableProviders.parallel;
+		if (provider === "parallel-mcp") return availableProviders["parallel-mcp"];
 		if (provider === "tinyfish") return availableProviders.tinyfish;
 		if (provider === "search1api") return availableProviders.search1api;
 		if (provider === "searchinfinity") return availableProviders.searchinfinity;
@@ -295,6 +296,8 @@ export function startCuratorServer(
 		if (provider === "xai") return availableProviders.xai;
 		if (provider === "brightdata") return availableProviders.brightdata;
 		if (provider === "serpbase") return availableProviders.serpbase;
+		if (provider === "serper") return availableProviders.serper;
+		if (provider === "valyu") return availableProviders.valyu;
 		return false;
 	}