@herbertgao/pi-extensions 2026.9.0 → 2026.9.1

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, XCrawl, Valyu, xAI/Grok, Bright Data SERP, SerpBase, Serper, self-hosted SearXNG, keyless DuckDuckGo, optional browser-cookie Gemini Web, Kimi Code Plan search, 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, XCrawl, Valyu, xAI/Grok, Mistral, Bright Data SERP, SerpBase, Serper, self-hosted SearXNG, keyless DuckDuckGo, optional browser-cookie Gemini Web, Kimi Code Plan search, 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. An active Kimi Code Plan signed in through `/login kimi-coding` enables explicit Kimi search without a separate Open Platform key. 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.
+**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. An active Kimi Code Plan signed in through `/login kimi-coding` enables explicit Kimi search without a separate Open Platform key. 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, Gemini API, or Mistral 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.
 
@@ -42,7 +42,8 @@ Works immediately with no API keys — Exa MCP provides zero-config search. If P
   "jinaApiKey": "jina_...",
   "bochaApiKey": "sk-...",
   "perplexityApiKey": "pplx-...",
-  "geminiApiKey": "AIza..."
+  "geminiApiKey": "AIza...",
+  "mistralApiKey": "..."
 }
 ```
 
@@ -85,6 +86,14 @@ brew install yt-dlp   # YouTube stream URLs for frame extraction
 
 Without these, video content analysis (transcripts, visual descriptions via Gemini) still works. The binaries are only needed for extracting individual frames as images.
 
+System dependency for curator browser launch on Linux:
+
+| Package | Purpose | Install |
+|---------|---------|---------|
+| `xdg-utils` | Opens the curator UI in your default browser | Debian/Ubuntu: `sudo apt install -y xdg-utils` · Fedora/RHEL: `sudo dnf install -y xdg-utils` · Arch: `sudo pacman -S xdg-utils` |
+
+Without `xdg-utils`, the curator URL is printed to the tool output so you can copy it into a browser.
+
 Requires Pi v0.37.3+.
 
 ## Quick Start
@@ -110,7 +119,7 @@ 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, XCrawl, Valyu, xAI, Bright Data SERP, SerpBase, Serper, self-hosted SearXNG, keyless DuckDuckGo, Exa, Perplexity AI, Gemini, or Kimi. 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, XCrawl, Valyu, xAI, Mistral, Bright Data SERP, SerpBase, Serper, self-hosted SearXNG, keyless DuckDuckGo, Exa, Perplexity AI, Gemini, or Kimi. Returns a synthesized answer with source citations.
 
 ```typescript
 web_search({ query: "rust async programming" })
@@ -119,6 +128,7 @@ web_search({ query: "latest news", numResults: 10, recencyFilter: "week" })
 web_search({ query: "...", domainFilter: ["github.com"] })
 web_search({ query: "...", provider: "openai" })
 web_search({ query: "...", provider: "kimi" })
+web_search({ query: "...", provider: "mistral" })
 web_search({ query: "...", provider: "all" })
 web_search({ query: "...", includeContent: true })
 web_search({ queries: ["query 1", "query 2"], workflow: "none" })
@@ -132,10 +142,12 @@ 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 Parallel MCP, DuckDuckGo, Kimi, AnySearch, XCrawl, 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`, `xcrawl`, `valyu`, `xai`, `brightdata`, `serpbase`, `serper`, `searxng`, `duckduckgo`, `exa`, `perplexity`, `gemini`, or `kimi` (auto-selects when no provider or routing is configured; Parallel MCP, DuckDuckGo, Kimi, AnySearch, XCrawl, Valyu, xAI, Bright Data, SerpBase, and Serper are explicit-only) |
+| `provider` | Configured provider when omitted or set to `auto`; `all` searches every eligible provider except Parallel MCP, DuckDuckGo, Kimi, AnySearch, XCrawl, Valyu, xAI, Mistral, Bright Data, SerpBase, and Serper simultaneously; otherwise `openai`, `brave`, `parallel`, `parallel-mcp`, `tinyfish`, `search1api`, `searchinfinity`, `querit`, `tavily`, `firecrawl`, `jina`, `serpdive`, `kagi`, `bocha`, `ollama`, `anysearch`, `xcrawl`, `valyu`, `xai`, `mistral`, `brightdata`, `serpbase`, `serper`, `searxng`, `duckduckgo`, `exa`, `perplexity`, `gemini`, or `kimi` (auto-selects when no provider or routing is configured; Parallel MCP, DuckDuckGo, Kimi, AnySearch, XCrawl, Valyu, xAI, Mistral, 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) |
 
+Batch searches run up to three queries concurrently. Provider routing and fallback within each query remain sequential.
+
 ### fetch_content
 
 Fetch URL(s) as readable markdown, exact textual HTTP bodies, direct images, or page-grounded answers. Automatically detects and handles GitHub repos, GitHub PRs and issues, YouTube videos, PDFs, local video files, images, and regular web pages.
@@ -281,6 +293,8 @@ Raw and direct-image HTTP requests use the same SSRF validation, hostname domain
 
 An empty string (`""`) forces a direct connection even when a config-level proxy is set. Omitting the parameter falls back to the global `proxy` in `~/.pi/web-search.json`.
 
+The config-level `proxy` applies only to requests made by this extension's tools. Other traffic in the host process — such as the coding agent's own model API calls — is never routed through it, so a configured proxy that is temporarily down cannot break unrelated requests.
+
 ```jsonc
 // ~/.pi/web-search.json — global proxy for all tools
 {
@@ -355,7 +369,7 @@ Toggle with **Ctrl+Shift+W** to see live request/response activity:
 
 ## Configuration
 
-Config defaults to `~/.pi/web-search.json`, or `web-search.json` under `PI_CODING_AGENT_DIR` / `XDG_CONFIG_HOME/pi` when set. Every field is optional.
+Config defaults to `~/.pi/web-search.json`. `PI_CODING_AGENT_DIR` takes precedence when set; with `XDG_CONFIG_HOME`, an existing `XDG_CONFIG_HOME/pi/web-search.json` is preferred, an existing legacy `~/.pi/web-search.json` remains usable, and the XDG path is used as the new-config target when neither file exists. Every field is optional.
 
 ```json
 {
@@ -380,6 +394,11 @@ Config defaults to `~/.pi/web-search.json`, or `web-search.json` under `PI_CODIN
   "serperApiKey": "$SERPER_API_KEY",
   "brightdataApiKey": "$BRIGHTDATA_API_KEY",
   "brightdataSerpZone": "pi_serp",
+  "xaiApiKey": "xai-...",
+  "xaiSearchTools": ["web_search"],
+  "mistralApiKey": "$MISTRAL_API_KEY",
+  "mistralSearchModel": "mistral-small-latest",
+  "mistralSearchTool": "web_search",
   "searxngBaseUrl": "https://search.example.com",
   "searxngHeaders": {
     "CF-Access-Client-Id": "xxxxxxxx.access",
@@ -488,7 +507,7 @@ 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`, `xcrawlApiKey`, `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 `$$` as a literal leading `$` and `$!` as a literal leading `!`:
+All provider API-key fields (`openaiApiKey`, `braveApiKey`, `parallelApiKey`, `tinyfishApiKey`, `search1apiApiKey`, `searchinfinityApiKey`, `queritApiKey`, `tavilyApiKey`, `jinaApiKey`, `serpdiveApiKey`, `kagiApiKey`, `bochaApiKey`, `ollamaApiKey`, `serpbaseApiKey`, `anysearchApiKey`, `xcrawlApiKey`, `xaiApiKey`, `mistralApiKey`, `brightdataApiKey`, `firecrawlApiKey`, `exaApiKey`, `perplexityApiKey`, `geminiApiKey`, `datalabApiKey`, and `cloudflareApiKey`) accept explicit credential sources. Use `$NAME` or `${NAME}` to read one named environment variable, or prefix a trusted local shell command with `!` to resolve one value at provider request time. Escape `$$` as a literal leading `$` and `$!` as a literal leading `!`:
 
 ```json
 {
@@ -499,10 +518,12 @@ 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`, `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.
+This syntax applies to provider credentials only; other configuration fields are not interpolated. `firecrawlApiKey`, `kagiApiKey`, `ollamaApiKey`, `valyuApiKey`, `serpbaseApiKey`, `serperApiKey`, `mistralApiKey`, 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.
 
+`mistralSearchModel` defaults to `mistral-small-latest` and must be a non-empty string. `mistralSearchTool` defaults to `web_search` and accepts only `web_search` or the opt-in `web_search_premium` tool.
+
 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"`.
@@ -539,7 +560,7 @@ Bright Data Web Unlocker is a paid `fetch_content` fallback after Parallel and b
 
 **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`, `SERPER_API_KEY`, `ANYSEARCH_API_KEY`, `XCRAWL_API_KEY`, `VALYU_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. Alternatively, set `geminiAuth` to `"adc"` to authenticate Gemini generate-content calls with Google Application Default Credentials (ADC) instead of an API key; calls go to the Vertex AI endpoint (`aiplatform.googleapis.com`) with an OAuth bearer token minted from the ADC file (`GOOGLE_APPLICATION_CREDENTIALS` or `~/.config/gcloud/application_default_credentials.json`, i.e. `gcloud auth application-default login`). `geminiProject`/`geminiLocation` set the Vertex project and location and fall back to the `GOOGLE_CLOUD_PROJECT`/`GOOGLE_CLOUD_LOCATION` (or `GCLOUD_PROJECT`) env vars; project and location are required. ADC supports `authorized_user` (OAuth refresh token) and `service_account` (JWT assertion) credential files, and tokens are cached and refreshed from expiry. ADC mode covers search, URL context, and PDF/inline-data extraction; YouTube and local video analysis still go through the Gemini Files API, so they fall back to Gemini Web unless a `GEMINI_API_KEY` is also configured. The access token is treated as a credential and is redacted from errors. 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"`, `"xcrawl"`, `"valyu"`, `"xai"`, `"brightdata"`, `"serpbase"`, `"serper"`, `"searxng"`, `"exa"`, `"perplexity"`, or `"gemini"`. Parallel MCP, AnySearch, XCrawl, 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`. `browserCookies.profile` 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.
+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`, `SERPER_API_KEY`, `ANYSEARCH_API_KEY`, `XCRAWL_API_KEY`, `VALYU_API_KEY`, `XAI_API_KEY`, `MISTRAL_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. Alternatively, set `geminiAuth` to `"adc"` to authenticate Gemini generate-content calls with Google Application Default Credentials (ADC) instead of an API key; calls go to the Vertex AI endpoint (`aiplatform.googleapis.com`) with an OAuth bearer token minted from the ADC file (`GOOGLE_APPLICATION_CREDENTIALS` or `~/.config/gcloud/application_default_credentials.json`, i.e. `gcloud auth application-default login`). `geminiProject`/`geminiLocation` set the Vertex project and location and fall back to the `GOOGLE_CLOUD_PROJECT`/`GOOGLE_CLOUD_LOCATION` (or `GCLOUD_PROJECT`) env vars; project and location are required. ADC supports `authorized_user` (OAuth refresh token) and `service_account` (JWT assertion) credential files, and tokens are cached and refreshed from expiry. ADC mode covers search, URL context, and PDF/inline-data extraction; YouTube and local video analysis still go through the Gemini Files API, so they fall back to Gemini Web unless a `GEMINI_API_KEY` is also configured. The access token is treated as a credential and is redacted from errors. 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"`, `"xcrawl"`, `"valyu"`, `"xai"`, `"mistral"`, `"brightdata"`, `"serpbase"`, `"serper"`, `"searxng"`, `"exa"`, `"perplexity"`, or `"gemini"`. Parallel MCP, AnySearch, XCrawl, Valyu, xAI, Mistral, 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 browser 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`. `browserCookies.profile` 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 IP targets, and `NO_PROXY` matches. It does not configure proxy transport.
 ### Kimi Code Plan
 
 Run `/login kimi-coding` in Pi and complete sign-in for an active Kimi Code Plan. Then select `provider: "kimi"`, include `"kimi"` in an explicit provider array, or add it to `searchRouting.providers`. The extension resolves a model with provider `kimi-coding` from Pi's model registry and reuses Pi's refreshed OAuth credential; no Moonshot Open Platform key is configured here.
@@ -550,7 +571,7 @@ Kimi is explicit-only: it is never chosen by `auto` and never participates in `p
 
 ### 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. Parallel MCP, DuckDuckGo, Kimi, AnySearch, XCrawl, 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, while Kimi draws from the user's shared Code Plan quota, so `all` never spends either resource without an explicit request. 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, Kimi, AnySearch, XCrawl, Valyu, xAI, Mistral, Bright Data, SerpBase, and Serper are always excluded because they are explicit-only; Bright Data, SerpBase, and Serper are paid Google SERP providers, while Kimi and Mistral may consume account quota or paid search-tool usage, so `all` never spends either resource without an explicit request. 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.
 
@@ -645,16 +666,41 @@ XCrawl is an explicit-only provider: it is never included in zero-config `auto`
 
 xAI is an explicit-only provider: it is never included in zero-config `auto` fallback or in `provider: "all"`, but it can be selected with `provider: "xai"`, configured as the named provider, or placed in `searchRouting`.
 
-It calls xAI's Agent Tools API — the hosted `web_search` tool on `https://api.x.ai/v1/responses` — so the search runs inside Grok's own inference rather than here. Auth resolves through Pi's model registry first, which means a **SuperGrok or X Premium subscription pays for its own searches** and no `xaiApiKey` has to be configured at all; `xaiApiKey` / `XAI_API_KEY` are the fallback for pay-as-you-go API keys.
+It calls xAI's Agent Tools API — the hosted `web_search` tool, with opt-in `x_search`, on `https://api.x.ai/v1/responses` — so the search runs inside Grok's own inference rather than here. Auth resolves through Pi's model registry first, which means a **SuperGrok or X Premium subscription pays for its own searches** and no `xaiApiKey` has to be configured at all; `xaiApiKey` / `XAI_API_KEY` are the fallback for pay-as-you-go API keys.
+
+Explicit-only is deliberate. A single question typically fans out to roughly a dozen `web_search` tool calls, billed at xAI's per-call tool rate on top of tokens and drawn from the same allowance the account uses for chatting. Letting `auto` or `all` reach for it would spend a subscription the user only meant to talk to. X Search is an additional opt-in because it sends the query to xAI's X search surface and may incur its own tool-call charges.
+
+The model is chosen for you: the registry path walks a best-first candidate list and uses the first id Pi actually knows, so a retired model is skipped rather than sent. The API-key path has no registry to consult and starts at `grok-4.5` for the default web-only request. When `x_search` is enabled, the current xAI docs' `grok-4.6` example is preferred instead. `xaiSearchModel` pins the id explicitly on either path, which is the escape hatch if xAI retires a model before a release ships.
 
-Explicit-only is deliberate. A single question typically fans out to roughly a dozen `web_search` tool calls, billed at xAI's per-call tool rate on top of tokens and drawn from the same allowance the account uses for chatting. Letting `auto` or `all` reach for it would spend a subscription the user only meant to talk to.
+Requests send only `{ model, input, tools }`, the shape verified against a live subscription account. The default `xaiSearchTools` value is `["web_search"]`, preserving the existing behavior. To opt into X Search, set it to `["x_search"]` for X-only searches or `["web_search", "x_search"]` to expose both tools:
 
-The model is chosen for you: the registry path walks a best-first candidate list and uses the first id Pi actually knows, so a retired model is skipped rather than sent. The API-key path has no registry to consult and starts at `grok-4.5`. `xaiSearchModel` pins the id explicitly on either path, which is the escape hatch if xAI retires a model before a release ships.
+```json
+{
+  "xaiSearchTools": ["web_search", "x_search"]
+}
+```
 
-Requests send only `{ model, input, tools }`, the shape verified against a live subscription account. `recencyFilter`, `domainFilter`, and `numResults` are folded into the prompt text rather than sent as tool parameters, so an unrecognized field can never turn a search into a 400. Sources are read from `url_citation` annotations on the answer and from each `web_search_call`'s own sources; there is no top-level `citations` array on this API.
+The value must be a non-empty array containing each of `web_search` and `x_search` at most once. This intentionally does not expose per-call X handle, date, or media-understanding parameters until their request contract is stable. `recencyFilter`, `domainFilter`, and `numResults` remain prompt guidance rather than tool parameters, so an unrecognized field cannot turn a search into a 400. Sources are read in annotation-first order from `url_citation` annotations, raw `web_search_call`/`x_search_call` source lists when present, and xAI's response-level `citations` URL list.
 
 xAI's older Live Search (`search_parameters` on `/v1/chat/completions`) is deprecated and now answers HTTP 410.
 
+### Mistral Conversations
+
+Mistral is an explicit-only provider. Set `mistralApiKey` or `MISTRAL_API_KEY`, then select `provider: "mistral"` or place `"mistral"` in `searchRouting.providers`; it is never chosen by `auto` and never participates in `provider: "all"`. Requests use direct HTTP `POST https://api.mistral.ai/v1/conversations` with bearer authentication and do not require the Mistral SDK.
+
+The default model is `mistral-small-latest`; override it with `mistralSearchModel`. The default built-in tool is `web_search`. Set `mistralSearchTool` to `"web_search_premium"` only when your account is entitled to that potentially cost-sensitive premium search tool:
+
+```json
+{
+  "mistralApiKey": "$MISTRAL_API_KEY",
+  "mistralSearchModel": "mistral-small-latest",
+  "mistralSearchTool": "web_search_premium",
+  "provider": "mistral"
+}
+```
+
+Mistral's Conversations response text becomes the synthesized answer, and `tool_reference` chunks become source results. References without a usable HTTP(S) URL are ignored, duplicate URLs are removed, and shared `numResults` and `domainFilter` limits are enforced locally. Recency, domain, and result-count guidance is included in the user prompt because Mistral's built-in tool does not expose those extension filter fields.
+
 ### Bright Data
 
 Bright Data SERP is a **paid, third-party search proxy**: your query, its filters, and the result URLs
@@ -922,7 +968,8 @@ Rate limits: Perplexity is capped at 10 requests/minute (client-side). Jina Sear
 | `anysearch.ts` | Explicit-only AnySearch search provider |
 | `xcrawl.ts` | Explicit-only XCrawl search provider |
 | `valyu.ts` | Explicit-only Valyu research search provider |
-| `xai-search.ts` | Explicit-only xAI (Grok) hosted web_search provider |
+| `xai-search.ts` | Explicit-only xAI (Grok) hosted web/X search provider |
+| `mistral-search.ts` | Explicit-only Mistral Conversations web search provider |
 | `kimi-search.ts` | Explicit-only Kimi Code Plan search provider |
 | `searxng.ts` | Self-hosted SearXNG JSON API search provider |
 | `duckduckgo.ts` | Explicit-only keyless DuckDuckGo HTML search provider |

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

@@ -40,6 +40,7 @@ function buildProviderButtons(
 		{ value: "anysearch", label: "AnySearch", available: available.anysearch },
 		{ value: "xcrawl", label: "XCrawl", available: available.xcrawl },
 		{ value: "xai", label: "xAI", available: available.xai },
+		{ value: "mistral", label: "Mistral", available: available.mistral },
 		{ value: "brightdata", label: "Bright Data", available: available.brightdata },
 		{ value: "serpbase", label: "SerpBase", available: available.serpbase },
 		{ value: "serper", label: "Serper", available: available.serper },
@@ -1468,7 +1469,7 @@ 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", "parallel-mcp", "tinyfish", "search1api", "searchinfinity", "querit", "tavily", "firecrawl", "jina", "serpdive", "kagi", "bocha", "ollama", "searxng", "duckduckgo", "perplexity", "gemini", "kimi", "anysearch", "xcrawl", "xai", "brightdata", "serpbase", "serper", "valyu"];
+  var providers = ["all", "openai", "exa", "brave", "parallel", "parallel-mcp", "tinyfish", "search1api", "searchinfinity", "querit", "tavily", "firecrawl", "jina", "serpdive", "kagi", "bocha", "ollama", "searxng", "duckduckgo", "perplexity", "gemini", "kimi", "anysearch", "xcrawl", "xai", "mistral", "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";
@@ -1695,6 +1696,7 @@ const SCRIPT = `(function() {
     if (provider === "anysearch") return "AnySearch";
     if (provider === "xcrawl") return "XCrawl";
     if (provider === "xai") return "xAI";
+    if (provider === "mistral") return "Mistral";
     if (provider === "brightdata") return "Bright Data";
     if (provider === "serpbase") return "SerpBase";
     return "Unknown";

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

@@ -17,6 +17,8 @@ type CuratorStoredEvent =
 
 export interface CuratorServerOptions {
 	queries: string[];
+	/** First index available to searches added while initial results are still streaming. */
+	initialResultIndexCapacity?: number;
 	sessionToken: string;
 	timeout: number;
 	availableProviders: ProviderAvailability;
@@ -194,6 +196,7 @@ export function startCuratorServer(
 ): Promise<CuratorServerHandle> {
 	const {
 		queries,
+		initialResultIndexCapacity,
 		sessionToken,
 		timeout,
 		availableProviders,
@@ -213,7 +216,7 @@ export function startCuratorServer(
 	let sseResponse: ServerResponse | null = null;
 	const streamedEventsByResultIndex = new Map<number, CuratorStoredEvent>();
 	let searchStreamDone = queries.length === 0;
-	let nextQueryIndex = queries.length;
+	let nextQueryIndex = Math.max(queries.length, initialResultIndexCapacity ?? queries.length);
 	let summarizeAbortController: AbortController | null = null;
 	let summarizeRequestSeq = 0;
 
@@ -297,6 +300,7 @@ export function startCuratorServer(
 		if (provider === "anysearch") return availableProviders.anysearch;
 		if (provider === "xcrawl") return availableProviders.xcrawl;
 		if (provider === "xai") return availableProviders.xai;
+		if (provider === "mistral") return availableProviders.mistral;
 		if (provider === "brightdata") return availableProviders.brightdata;
 		if (provider === "serpbase") return availableProviders.serpbase;
 		if (provider === "serper") return availableProviders.serper;

package/node_modules/pi-web-access/gemini-search.ts

@@ -37,9 +37,10 @@ import { isSerpBaseAvailable, searchWithSerpBase } from "./serpbase.ts";
 import { isSerperAvailable, searchWithSerper } from "./serper.ts";
 import { isValyuAvailable, searchWithValyu } from "./valyu.ts";
 import { isKimiSearchAvailable, searchWithKimi } from "./kimi-search.ts";
+import { isMistralAvailable, searchWithMistral } from "./mistral-search.ts";
 import { getWebSearchConfigPath } from "./utils.ts";
 
-export const RESOLVED_SEARCH_PROVIDERS = ["openai", "brave", "parallel", "parallel-mcp", "tinyfish", "search1api", "searchinfinity", "querit", "tavily", "firecrawl", "jina", "searxng", "duckduckgo", "perplexity", "gemini", "kimi", "exa", "serpdive", "kagi", "ollama", "anysearch", "xai", "brightdata", "serpbase", "serper", "valyu", "bocha", "xcrawl"] as const;
+export const RESOLVED_SEARCH_PROVIDERS = ["openai", "brave", "parallel", "parallel-mcp", "tinyfish", "search1api", "searchinfinity", "querit", "tavily", "firecrawl", "jina", "searxng", "duckduckgo", "perplexity", "gemini", "kimi", "exa", "serpdive", "kagi", "ollama", "anysearch", "xai", "mistral", "brightdata", "serpbase", "serper", "valyu", "bocha", "xcrawl"] as const;
 export const SEARCH_PROVIDERS = ["auto", "all", ...RESOLVED_SEARCH_PROVIDERS] as const;
 
 export type ResolvedSearchProvider = typeof RESOLVED_SEARCH_PROVIDERS[number];
@@ -104,7 +105,7 @@ export interface AttributedSearchResponse extends SearchResponse {
 
 const CONFIG_PATH = getWebSearchConfigPath();
 const DEFAULT_SEARCH_MODEL = "gemini-3.6-flash";
-// Explicit-only providers (Parallel MCP, DuckDuckGo, Kimi, AnySearch, XCrawl, xAI, Bright Data, SerpBase, Serper, Valyu) are deliberately absent:
+// Explicit-only providers (Parallel MCP, DuckDuckGo, Kimi, AnySearch, XCrawl, xAI, Mistral, Bright Data, SerpBase, Serper, Valyu) are deliberately absent:
 // `all` must never fan out to an opt-in or paid provider without the user asking for it.
 export const ALL_SEARCH_PROVIDERS: ResolvedSearchProvider[] = ["searxng", "openai", "exa", "brave", "parallel", "tinyfish", "search1api", "searchinfinity", "querit", "tavily", "firecrawl", "jina", "serpdive", "kagi", "ollama", "perplexity", "gemini", "bocha"];
 const VALID_ROUTING_KINDS = ["transient", "quota", "network", "invalid-response", "unsupported"] as const;
@@ -360,6 +361,7 @@ async function searchWithResolvedProvider(
 	if (provider === "ollama") return { ...(await searchWithOllama(query, options)), provider };
 	if (provider === "anysearch") return { ...(await searchWithAnySearch(query, options)), provider };
 	if (provider === "xai") return { ...(await searchWithXai(query, options, options.extensionContext)), provider };
+	if (provider === "mistral") return { ...(await searchWithMistral(query, options)), provider };
 	if (provider === "brightdata") return { ...(await searchWithBrightData(query, options)), provider };
 	if (provider === "serpbase") return { ...(await searchWithSerpBase(query, options)), provider };
 	if (provider === "serper") return { ...(await searchWithSerper(query, options)), provider };
@@ -407,6 +409,7 @@ async function isResolvedProviderAvailable(provider: ResolvedSearchProvider, opt
 	if (provider === "ollama") return isOllamaAvailable();
 	if (provider === "anysearch") return isAnySearchAvailable();
 	if (provider === "xai") return isXaiSearchAvailable(options.extensionContext);
+	if (provider === "mistral") return isMistralAvailable();
 	if (provider === "brightdata") return isBrightDataAvailable();
 	if (provider === "serpbase") return isSerpBaseAvailable();
 	if (provider === "serper") return isSerperAvailable();
@@ -445,6 +448,7 @@ function providerLabel(provider: ResolvedSearchProvider): string {
 	if (provider === "kimi") return "Kimi";
 	if (provider === "ollama") return "Ollama";
 	if (provider === "xai") return "xAI";
+	if (provider === "mistral") return "Mistral";
 	if (provider === "brightdata") return "Bright Data";
 	if (provider === "serpbase") return "SerpBase";
 	if (provider === "serper") return "Serper";
@@ -475,7 +479,7 @@ async function searchWithProviders(
 			: await isResolvedProviderAvailable(provider, options),
 	})))).filter((entry) => entry.available).map((entry) => entry.provider);
 	if (providers.length === 0) {
-		throw new Error("No configured search provider available for provider \"all\". Parallel MCP, DuckDuckGo, Kimi, AnySearch, xAI, Bright Data, SerpBase, Serper, Valyu, and XCrawl are excluded.");
+		throw new Error("No configured search provider available for provider \"all\". Parallel MCP, DuckDuckGo, Kimi, AnySearch, xAI, Mistral, Bright Data, SerpBase, Serper, Valyu, and XCrawl are excluded.");
 	}
 
 	const settled = await Promise.allSettled(
@@ -768,7 +772,7 @@ export async function search(query: string, options: FullSearchOptions = {}): Pr
 		"  3. Set OPENAI_API_KEY, BRAVE_API_KEY, PARALLEL_API_KEY, TINYFISH_API_KEY, SEARCH1API_KEY, SEARCHINFINITY_API_KEY, QUERIT_API_KEY, TAVILY_API_KEY, FIRECRAWL_BASE_URL, JINA_API_KEY, SERPDIVE_API_KEY, KAGI_API_KEY, BOCHA_API_KEY, OLLAMA_API_KEY, SEARXNG_BASE_URL, EXA_API_KEY, PERPLEXITY_API_KEY, GEMINI_API_KEY, or CLOUDFLARE_API_KEY env vars\n" +
 		"  4. Set GOOGLE_GEMINI_BASE_URL with CLOUDFLARE_API_KEY for Cloudflare AI Gateway routing\n" +
 		"  5. Sign into gemini.google.com in a supported Chromium-based browser\n" +
-		"  6. Explicitly select provider: \"anysearch\" for anonymous AnySearch, \"xcrawl\" for XCrawl, \"xai\" for Grok, \"brightdata\" with brightdataSerpZone for paid Bright Data SERP, \"serpbase\" or \"serper\" for Google SERP, or \"valyu\" for research search"
+		"  6. Explicitly select provider: \"anysearch\" for anonymous AnySearch, \"xcrawl\" for XCrawl, \"xai\" for Grok, \"mistral\" for Mistral Conversations web search, \"brightdata\" with brightdataSerpZone for paid Bright Data SERP, \"serpbase\" or \"serper\" for Google SERP, or \"valyu\" for research search"
 	);
 }