@herbertgao/pi-extensions 2026.9.17 → 2026.9.19

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

@@ -109,7 +109,7 @@ To route automatic searches through the active Pi model, configure an ordered ro
 
 With `useCurrentModel: true`, the automatic `openai` step uses Hosted `web_search` (or standalone search when `openaiUseAlphaSearch` is enabled) when the active model is a GPT model backed by an official OpenAI Responses endpoint: `openai`/`openai-responses` on HTTPS `api.openai.com`, or `openai-codex`/`openai-codex-responses` on the official ChatGPT Codex endpoint. Third-party gateways, Azure, and other models continue to the next route entry. A tool-level `provider` or top-level `provider` remains an explicit override; `provider: "openai"` keeps the existing independent OpenAI/Codex search-model behavior.
 
-For sandboxed networks that provide outbound proxy transport through environment variables, set `ssrf.trustEnvProxy` to `true` to skip local DNS preflight for proxied hostnames:
+For sandboxed or corporate networks where only the proxy can resolve hostnames, set `ssrf.trustEnvProxy` to `true` to skip local DNS preflight for proxied hostnames:
 
 ```json
 {
@@ -119,7 +119,7 @@ For sandboxed networks that provide outbound proxy transport through environment
 }
 ```
 
-This is an opt-in DNS-preflight adjustment, not proxy transport configuration. `HTTP_PROXY`, `HTTPS_PROXY`, and `ALL_PROXY` are recognized; `NO_PROXY` hosts still undergo DNS validation, and localhost or literal private IP targets remain blocked.
+This is an opt-in DNS-preflight adjustment, not proxy transport configuration. It applies to requests sent through the `proxy` set in `web-search.json` (HTTP(S), `socks5h`, or `socks4a`, including a per-call `proxy` with the same value). When no `proxy` is configured, it applies to hostnames covered by `HTTP_PROXY`, `HTTPS_PROXY`, or `ALL_PROXY`, for sandboxes that route outbound traffic through those variables themselves; the extension does not route requests through environment proxies. A per-call `proxy` that differs from the configured one still gets local DNS validation. `NO_PROXY` hosts still undergo DNS validation, and localhost or literal private IP targets remain blocked.
 
 Optional dependencies for video frame extraction:
 
@@ -163,7 +163,7 @@ 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, Mistral, Bright Data SERP, SerpBase, SerpApi, Serper, Serply, self-hosted SearXNG, keyless DuckDuckGo, Exa, Perplexity AI, Gemini, or Kimi. The default `none` workflow makes no summary-generation model call and opens no curator/browser: it returns bounded raw results, identifies the provider used for each query, and stores the full results for retrieval by responseId. The selected search provider may itself be model-backed.
+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, SerpApi, Serper, Serply, You.com, self-hosted SearXNG, keyless DuckDuckGo, Exa, Perplexity AI, Gemini, or Kimi. The default `none` workflow makes no summary-generation model call and opens no curator/browser: it returns bounded raw results, identifies the provider used for each query, and stores the full results for retrieval by responseId. The selected search provider may itself be model-backed.
 
 ```typescript
 web_search({ query: "rust async programming" })
@@ -186,7 +186,7 @@ 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 Parallel MCP, DuckDuckGo, Kimi, AnySearch, XCrawl, Valyu, xAI, Mistral, Bright Data, SerpBase, SerpApi, Serper, Serply, and Baizhi 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`, `serpapi`, `serper`, `serply`, `baizhi`, `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, SerpApi, Serper, Serply, and Baizhi 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, SerpApi, Serper, Serply, You.com, Baizhi, and Z.ai simultaneously; otherwise `openai`, `brave`, `parallel`, `parallel-mcp`, `tinyfish`, `search1api`, `searchinfinity`, `querit`, `tavily`, `you`, `firecrawl`, `jina`, `serpdive`, `kagi`, `bocha`, `ollama`, `anysearch`, `xcrawl`, `valyu`, `xai`, `mistral`, `brightdata`, `serpbase`, `serpapi`, `serper`, `serply`, `baizhi`, `zai`, `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, SerpApi, Serper, Serply, You.com, Baizhi, and Z.ai are explicit-only) |
 | `includeContent` | Fetch full page content from sources in background |
 | `workflow` | `none` (skip curator; fresh-install default), `summary-review` (open curator and auto-generate a summary draft), or `auto-summary` (generate a summary without opening the curator) |
 
@@ -226,7 +226,7 @@ Thanks to [@linuxtextadventurer](https://github.com/linuxtextadventurer) for PR
 
 ### get_search_content
 
-Retrieve stored content from previous searches or fetches. Search provider answers and every result remain available in full and can be paged with `offset` and `limit` or searched with `findText`. Fetched URL content is stored in full in a private `web-search-cache` directory under the Pi config directory, not in the session JSONL. This includes `fetch_content` answer mode, which stores the original page content. The cache has a one-hour lifetime and fixed limits of 128 entries and 128 MiB; when either limit is reached, the oldest entries are removed first. On macOS and Linux the cache directory and files are kept at permissions `0700` and `0600`, respectively. Use `findText` to locate bounded matching passages without paging through a large page, or use `offset` and `limit` to retrieve slices intentionally.
+Retrieve stored content from previous searches or fetches. Search provider answers and every result remain available in full and can be paged with `offset` and `limit` or searched with `findText`. Fetched URL content is stored in full in a private `web-search-cache` directory under the Pi config directory, not in the session JSONL. This includes `fetch_content` answer mode, which stores the original page content. The cache has a one-hour lifetime and fixed limits of 128 entries and 128 MiB; when either limit is reached, the oldest entries are removed first. Concurrent Pi processes share this cache and its limits. To give a process its own cache without moving `web-search.json`, set `PI_WEB_ACCESS_CACHE_ROOT` to a directory; the cache then lives in `web-search-cache` inside it, and a session resumed without the same value cannot read content cached there. On macOS and Linux the cache directory and files are kept at permissions `0700` and `0600`, respectively. Use `findText` to locate bounded matching passages without paging through a large page, or use `offset` and `limit` to retrieve slices intentionally.
 
 ```typescript
 get_search_content({ responseId: "abc123", urlIndex: 0 })
@@ -433,6 +433,7 @@ Config defaults to `~/.pi/agent/web-search.json` when neither `PI_CODING_AGENT_D
   "search1apiApiKey": "...",
   "tavilyApiKey": "tvly-...",
   "tavilyBaseUrl": "https://gateway.example.com/tavily",
+  "youApiKey": "your-ydc-api-key",
   "jinaApiKey": "$JINA_API_KEY",
   "serpdiveApiKey": "sd_live_...",
   "serpdiveModel": "krill",
@@ -444,6 +445,7 @@ Config defaults to `~/.pi/agent/web-search.json` when neither `PI_CODING_AGENT_D
   "serperApiKey": "$SERPER_API_KEY",
   "serplyApiKey": "$SERPLY_API_KEY",
   "baizhiApiKey": "$BAIZHI_API_KEY",
+  "zaiApiKey": "$ZAI_API_KEY",
   "brightdataApiKey": "$BRIGHTDATA_API_KEY",
   "brightdataSerpZone": "pi_serp",
   "xaiApiKey": "xai-...",
@@ -497,6 +499,7 @@ Config defaults to `~/.pi/agent/web-search.json` when neither `PI_CODING_AGENT_D
     "fetchContent": { "enabled": true },
     "getSearchContent": { "enabled": true }
   },
+  "toolActivation": "auto",
   "commands": {
     "websearch": { "enabled": true },
     "curator": { "enabled": true },
@@ -568,7 +571,7 @@ Config defaults to `~/.pi/agent/web-search.json` when neither `PI_CODING_AGENT_D
 
 `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`, `valyuApiKey`, `serpbaseApiKey`, `serpapiApiKey`, `serperApiKey`, `serplyApiKey`, `baizhiApiKey`, `anysearchApiKey`, `xcrawlApiKey`, `xaiApiKey`, `mistralApiKey`, `brightdataApiKey`, `firecrawlApiKey`, `crawl4aiApiToken`, `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 `$$` as a literal leading `$` and `$!` as a literal leading `!`:
+All provider API-key fields (`openaiApiKey`, `braveApiKey`, `parallelApiKey`, `tinyfishApiKey`, `search1apiApiKey`, `searchinfinityApiKey`, `queritApiKey`, `tavilyApiKey`, `youApiKey`, `jinaApiKey`, `serpdiveApiKey`, `kagiApiKey`, `bochaApiKey`, `ollamaApiKey`, `valyuApiKey`, `serpbaseApiKey`, `serpapiApiKey`, `serperApiKey`, `serplyApiKey`, `baizhiApiKey`, `zaiApiKey`, `anysearchApiKey`, `xcrawlApiKey`, `xaiApiKey`, `mistralApiKey`, `brightdataApiKey`, `firecrawlApiKey`, `crawl4aiApiToken`, `exaApiKey`, `perplexityApiKey`, `geminiApiKey`, `datalabApiKey`, and `cloudflareApiKey`) accept explicit credential sources. Use `$NAME` or `${NAME}` to read one named environment variable, or prefix a trusted local shell command with `!` to resolve one value at provider request time. Escape `$$` as a literal leading `$` and `$!` as a literal leading `!`:
 
 ```json
 {
@@ -579,13 +582,13 @@ All provider API-key fields (`openaiApiKey`, `braveApiKey`, `parallelApiKey`, `t
 }
 ```
 
-This syntax applies to provider credentials only; other configuration fields are not interpolated. `firecrawlApiKey`, `crawl4aiApiToken`, `kagiApiKey`, `ollamaApiKey`, `valyuApiKey`, `serpbaseApiKey`, `serpapiApiKey`, `serperApiKey`, `serplyApiKey`, `baizhiApiKey`, `mistralApiKey`, and `brightdataApiKey` use the same credential-source rules, while `braveBaseUrl`, `exaBaseUrl`, `tavilyBaseUrl`, `firecrawlBaseUrl`, `firecrawlApiVersion`, `firecrawlFreshScrape`, `crawl4aiBaseUrl`, `brightdataSerpZone`, and `brightdataUnlockerZone` are literal config values.
+This syntax applies to provider credentials only; other configuration fields are not interpolated. `firecrawlApiKey`, `crawl4aiApiToken`, `kagiApiKey`, `ollamaApiKey`, `valyuApiKey`, `serpbaseApiKey`, `serpapiApiKey`, `serperApiKey`, `serplyApiKey`, `baizhiApiKey`, `zaiApiKey`, `mistralApiKey`, and `brightdataApiKey` use the same credential-source rules, while `braveBaseUrl`, `exaBaseUrl`, `tavilyBaseUrl`, `firecrawlBaseUrl`, `firecrawlApiVersion`, `firecrawlFreshScrape`, `crawl4aiBaseUrl`, `brightdataSerpZone`, `brightdataUnlockerZone`, and `zaiEndpoint` 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_*` and `OP_SERVICE_ACCOUNT_TOKEN`, when present in Pi's environment, are forwarded to trusted resolver commands so 1Password CLI sessions and service accounts can be reused without storing their credentials in config. For example, `"braveApiKey": "!/absolute/path/to/op read 'op://Automation/Brave/credential'"` resolves that item after you replace the executable placeholder with your trusted installation's absolute path, but the `op://` argument is not an authorization boundary: every configured resolver command that receives the token can exercise all vault and item permissions granted to its service account. Prefer a narrowly scoped service account. 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.
+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 and Tavily append `/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"`.
 
@@ -625,17 +628,23 @@ Bright Data Web Unlocker is a paid `fetch_content` fallback after Parallel and b
 
 **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`.
 
+**Tavily key pool.** Set `TAVILY_API_KEY_1` through `TAVILY_API_KEY_20` to try another key when Tavily returns HTTP 401, 402, 403, 429, or 432. `TAVILY_API_KEY_INDEX` picks the first slot to try (default `1`). Search tries each distinct numbered key once, wrapping around, then tries `tavilyApiKey` / `TAVILY_API_KEY`. Explicit `$VAR` and `!command` sources still fail closed. All attempts share the 60-second search deadline.
+
 **Baizhi.** Set `BAIZHI_API_KEY` (or `baizhiApiKey: "$BAIZHI_API_KEY"` in `web-search.json`) and explicitly select `provider: "baizhi"` to call [Baizhi Cloud Agent Toolkit](https://baizhi.cloud/landing/agent-toolkit)'s `websearch_search` over Streamable HTTP MCP. It is excluded from automatic selection and `all`; you may explicitly configure it as the default or in `searchRouting`. The client initializes an MCP session, sends your own key only in the Bearer header, and closes the session after each search. Requests and response bodies share a 60-second deadline and respect cancellation. Redirects are rejected. Queries and filters are sent to the hosted commercial service, and calls may consume credits; review your account permissions and balance. Domain include/exclude filters map to the tool's `filter` object; recency maps to `time_range`, which defaults to `month`. Generated summaries are disabled.
 
 The Baizhi input contract is based on the [published September 16 discovery snapshot](https://github.com/ct-jaryn/baizhi-agent-toolkit/blob/b774c117369b8da2a1e42c7d01bf9535bb9a41c6/tests/fixtures/tools-history-2026-09-16.json); it has no output schema. This first version preserves MCP text and structured content as the provider answer rather than guessing result item fields. Consequently it does not populate source cards or fetch pages with `includeContent`. Tests use a synthetic MCP backend; live service results and billing have not been validated. This integration does not imply the hosted backend is open source.
 
+**Z.ai.** Set `ZAI_API_KEY` (or `zaiApiKey: "$ZAI_API_KEY"` in `web-search.json`) to a GLM Coding Plan key and explicitly select `provider: "zai"` to call the plan's [Web Search MCP server](https://docs.z.ai/devpack/mcp/search-mcp-server) (`webSearchPrime`). Searches count against your Coding Plan quota rather than per-call API billing. Keys are issued per site: the default `zaiEndpoint: "global"` uses `api.z.ai`, and `zaiEndpoint: "china"` uses `open.bigmodel.cn` for keys from bigmodel.cn. No other endpoint can be configured, redirects are rejected, and the key is sent only in the Bearer header. Z.ai is excluded from automatic selection and `all`; you may configure it as the default or in `searchRouting`. Recency maps to `search_recency_filter`; `domainFilter` accepts one included domain, because the tool takes a single `search_domain_filter` and has no exclusions. The tool has no result count, so results are trimmed to `numResults`. Z.ai does not publish the tool's input or output schema; the mapping follows established MCP clients, and tests use a synthetic MCP backend.
+
 **Serply.** Set `serplyApiKey` or `SERPLY_API_KEY` and select `provider: "serply"` to query [Serply](https://serply.io)'s Google Search API. Serply 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`. The key is sent in the `X-Api-Key` request header. Domain filters are sent as Google `site:` clauses and reapplied locally; recency maps to Google's `tbs` time filter. Each request consumes Serply search credits; see the [API documentation](https://serply.io/docs).
 
+**You.com.** Set `youApiKey` or `YDC_API_KEY` and select `provider: "you"` to query the [You.com Web Search API](https://you.com/docs/guides/search). You.com 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`. The key is sent in the `X-API-Key` request header. Domain filters map to `include_domains` and `exclude_domains`, and recency maps to `freshness`. Each request consumes You.com API credits.
+
 **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`, `SERPAPI_KEY`, `SERPER_API_KEY`, `SERPLY_API_KEY`, `BAIZHI_API_KEY`, `ANYSEARCH_API_KEY`, `XCRAWL_API_KEY`, `VALYU_API_KEY`, `XAI_API_KEY`, `MISTRAL_API_KEY`, `BRIGHTDATA_API_KEY`, `FIRECRAWL_API_KEY`, `CRAWL4AI_API_TOKEN`, `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"`, `"serpapi"`, `"serper"`, `"serply"`, `"baizhi"`, `"searxng"`, `"exa"`, `"perplexity"`, or `"gemini"`. Parallel MCP, AnySearch, XCrawl, Valyu, xAI, Mistral, Bright Data, SerpBase, SerpApi, Serper, Serply, and Baizhi 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: `"none"` (default; raw results, no curator), `"summary-review"` (opens curator with an auto-generated summary draft), or `"auto-summary"` (returns a model-generated summary without opening the browser 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
+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`, `YDC_API_KEY`, `JINA_API_KEY`, `SERPDIVE_API_KEY`, `KAGI_API_KEY`, `BOCHA_API_KEY`, `OLLAMA_API_KEY`, `SERPBASE_API_KEY`, `SERPAPI_KEY`, `SERPER_API_KEY`, `SERPLY_API_KEY`, `BAIZHI_API_KEY`, `ZAI_API_KEY`, `ANYSEARCH_API_KEY`, `XCRAWL_API_KEY`, `VALYU_API_KEY`, `XAI_API_KEY`, `MISTRAL_API_KEY`, `BRIGHTDATA_API_KEY`, `FIRECRAWL_API_KEY`, `CRAWL4AI_API_TOKEN`, `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, then newest bare `gpt-N` or `gpt-N.N` id, then newest other `gpt-<version>` id); 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"`, `"serpapi"`, `"serper"`, `"serply"`, `"you"`, `"baizhi"`, `"zai"`, `"searxng"`, `"exa"`, `"perplexity"`, or `"gemini"`. Parallel MCP, AnySearch, XCrawl, Valyu, xAI, Mistral, Bright Data, SerpBase, SerpApi, Serper, Serply, You.com, Baizhi, and Z.ai 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: `"none"` (default; raw results, no curator), `"summary-review"` (opens curator with an auto-generated summary draft), or `"auto-summary"` (returns a model-generated summary without opening the browser 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 networks where only the proxy can resolve hostnames; it skips local DNS preflight only for hostnames sent through the configured `proxy` or, when none is configured, hostnames covered by valid HTTP(S) proxy env vars in sandboxes that route through them, 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.
 
 Kimi search calls `POST https://api.kimi.com/coding/v1/search` with the query as `text_query`. This is the Kimi Code Plan search service, not Moonshot Open Platform `$web_search`. The endpoint exposes no native recency parameter, so `recencyFilter` is unsupported and is not sent. Shared `domainFilter` and `numResults` behavior is enforced locally on the returned `search_results`.
@@ -644,7 +653,7 @@ 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, Mistral, Bright Data, SerpBase, SerpApi, Serper, Serply, and Baizhi are always excluded because they are explicit-only; Bright Data, SerpBase, SerpApi, Serper, and Serply are paid Google SERP providers, while Baizhi, 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.
+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, SerpApi, Serper, Serply, You.com, Baizhi, and Z.ai are always excluded because they are explicit-only; Bright Data, SerpBase, SerpApi, Serper, Serply, and You.com are paid search APIs, while Baizhi, Z.ai, 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.
 
@@ -985,7 +994,17 @@ When `false`, a requested Curator session never tries to open a Glimpse window o
 
 ### Tool activation
 
-Pi starts normal sessions with the compact `web_enable` tool. Its guidance lists only the web capabilities enabled in `web-search.json`. The model can call it without a human toggle; the configured search, source-check, fetch, and stored-content tools then appear on the immediately following model request. Disabled tools stay unregistered, and alternate `toolNames` are preserved. Warm and resumed sessions retain their recorded tool selection.
+With dynamic activation, Pi starts a session with only the compact `web_enable` tool. Its guidance lists only the web capabilities enabled in `web-search.json`. The model can call it without a human toggle; the configured search, source-check, fetch, and stored-content tools then appear on the immediately following model request. Disabled tools stay unregistered, and alternate `toolNames` are preserved. Warm and resumed sessions retain their recorded tool selection, so a session recorded without `web_enable` does not gain it after an install or upgrade; start a new session to use web tools there.
+
+Enabling the tools mid-conversation can cost a prompt-cache miss. Some models accept tools added partway through a conversation. For the others, Pi resends the whole conversation on the request after `web_enable`, which can invalidate the cached prefix for that request. Later requests can cache the updated conversation again.
+
+`"toolActivation"` in `web-search.json` picks the behavior:
+
+- `"auto"` (the default) uses dynamic activation when the session's model accepts added tools, according to Pi's model catalog. Otherwise every enabled web tool is available from the first request, so `web_enable` never causes that cache miss. The choice is made once, from the model selected when a new session starts; switching models later doesn't change it, and warm or resumed sessions keep their recorded tools.
+- `"dynamic"` starts every new session with `web_enable`, even on models where enabling the tools can cause a cache miss.
+- `"eager"` never uses `web_enable` and keeps every enabled web tool available from the first request. It also suits models that rarely call `web_enable` on their own.
+
+Restart Pi after changing it. Dynamic activation needs Pi 0.86.0 or newer; older Pi logs a warning and keeps every enabled web tool available.
 
 ### Shortcuts
 
@@ -1009,7 +1028,7 @@ Rate limits: Perplexity is capped at 10 requests/minute (client-side). Jina Sear
 ## 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. 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 sanitized browser/profile attempts and classifies SQLite, profile, missing-cookie, password-store, and decryption failures.
+- 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 Linux, Chrome and Chromium check Secret Service first, then use `kwallet-query` for the standard KWallet safe-storage entry during a KDE session. 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 sanitized browser/profile attempts and classifies SQLite, profile, missing-cookie, password-store, and decryption failures.
 - 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).
@@ -1034,6 +1053,7 @@ Rate limits: Perplexity is capped at 10 requests/minute (client-side). Jina Sear
 | `searchinfinity.ts` | Byteplus Searchinfinity search provider |
 | `querit.ts` | Querit Search and Contents API provider |
 | `tavily.ts` | Tavily Search API provider |
+| `you.ts` | You.com Search API provider |
 | `firecrawl.ts` | Firecrawl search provider and extraction fallback |
 | `crawl4ai.ts` | Self-hosted Crawl4AI extraction fallback |
 | `jina-search.ts` | Jina Search API provider |
@@ -1046,6 +1066,7 @@ Rate limits: Perplexity is capped at 10 requests/minute (client-side). Jina Sear
 | `serper.ts` | Explicit-only Serper Google SERP provider |
 | `serply.ts` | Explicit-only Serply Google SERP provider |
 | `baizhi.ts` | Explicit-only Baizhi Streamable HTTP MCP search provider |
+| `zai.ts` | Explicit-only Z.ai GLM Coding Plan MCP search provider |
 | `anysearch.ts` | Explicit-only AnySearch search provider |
 | `xcrawl.ts` | Explicit-only XCrawl search provider |
 | `valyu.ts` | Explicit-only Valyu research search provider |

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

@@ -15,8 +15,16 @@ interface BrowserConfig {
 	keychainService?: string;
 	keychainAccount?: string;
 	secretToolApp?: string;
+	kwalletFolder?: string;
+	kwalletEntry?: string;
 }
 
+type BrowserPassword = {
+	value: string | null;
+	source?: "secret-service" | "kwallet";
+	warning?: string;
+};
+
 type SqliteRow = Record<string, unknown>;
 type SqliteFailure = "unavailable" | "query";
 
@@ -67,8 +75,8 @@ const MACOS_BROWSER_CONFIGS: BrowserConfig[] = [
 ];
 
 const LINUX_BROWSER_CONFIGS: BrowserConfig[] = [
-	{ id: "chromium", name: "Chromium", baseDir: ".config/chromium", secretToolApp: "chromium" },
-	{ id: "chrome", name: "Chrome", baseDir: ".config/google-chrome", secretToolApp: "chrome" },
+	{ id: "chromium", name: "Chromium", baseDir: ".config/chromium", secretToolApp: "chromium", kwalletFolder: "Chromium Keys", kwalletEntry: "Chromium Safe Storage" },
+	{ id: "chrome", name: "Chrome", baseDir: ".config/google-chrome", secretToolApp: "chrome", kwalletFolder: "Chrome Keys", kwalletEntry: "Chrome Safe Storage" },
 ];
 
 const WINDOWS_BROWSER_CONFIGS: BrowserConfig[] = [
@@ -76,7 +84,7 @@ const WINDOWS_BROWSER_CONFIGS: BrowserConfig[] = [
 	{ id: "edge", name: "Edge", baseDir: "Microsoft/Edge/User Data", usesLocalAppData: true },
 ];
 
-const browserPasswordCache = new Map<string, Promise<string | null>>();
+const browserPasswordCache = new Map<string, Promise<BrowserPassword[]>>();
 let lastCookieDiagnostic: string | null = null;
 let lastCookieDiagnosticDetails: BrowserCookieDiagnosticDetails | null = null;
 let sqliteModule: typeof import("node:sqlite") | null = null;
@@ -194,10 +202,13 @@ export async function getBrowserCookiesForHosts(
 					sawRequiredCookies = true;
 				}
 
-				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) {
+				const browserPasswords = currentPlatform === "win32" ? [] : await readBrowserPasswords(config, currentPlatform);
+				for (const password of browserPasswords) if (password.warning) warningSet.add(password.warning);
+				const windowsKey = currentPlatform === "win32" ? await readWindowsEncryptionKey(config, home) : null;
+				const browserKeys = browserPasswords.flatMap((password) => password.value
+					? [pbkdf2Sync(password.value, "saltysalt", currentPlatform === "darwin" ? 1003 : 1, 16, "sha1")]
+					: []);
+				if (currentPlatform === "win32" ? !windowsKey : browserKeys.length === 0) {
 					warningSet.add(currentPlatform === "win32"
 						? `Could not read ${config.name} Windows cookie encryption key`
 						: `Could not read ${config.name} cookie encryption password`);
@@ -220,6 +231,7 @@ export async function getBrowserCookiesForHosts(
 				const entries: BrowserCookieEntry[] = [];
 				const cookies: CookieMap = {};
 				const requiredDecryptFailures = new Set<string>();
+				let kwalletAttempted = browserPasswords.some((password) => password.source === "kwallet");
 				for (const row of rowsResult.rows) {
 					const name = typeof row.name === "string" ? row.name : "";
 					if (!name) continue;
@@ -227,9 +239,28 @@ export async function getBrowserCookiesForHosts(
 					if (!value && typeof row.encrypted_value_hex === "string" && /^[0-9a-f]*$/i.test(row.encrypted_value_hex)) {
 						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 (currentPlatform === "win32") {
+							value = decryptWindowsCookieValue(encrypted, windowsKey!, metaVersion.value >= 24);
+						} else {
+							for (const key of browserKeys) {
+								value = decryptCookieValue(encrypted, key, metaVersion.value >= 24);
+								if (value) break;
+							}
+						}
+						if (!value && currentPlatform === "linux" && !kwalletAttempted && browserPasswords.some((password) => password.source === "secret-service") && requiredCookies?.includes(name)) {
+							kwalletAttempted = true;
+							const fallback = await readKWalletPassword(config);
+							if (fallback.warning) warningSet.add(fallback.warning);
+							if (fallback.value) {
+								const key = pbkdf2Sync(fallback.value, "saltysalt", 1, 16, "sha1");
+								browserKeys.push(key);
+								value = decryptCookieValue(encrypted, key, metaVersion.value >= 24);
+								if (value) {
+									browserPasswords.push(fallback);
+									browserPasswordCache.set(passwordCacheKey(config, currentPlatform), Promise.resolve([...browserPasswords]));
+								}
+							}
+						}
 						if (!value && requiredCookies?.includes(name)) requiredDecryptFailures.add(name);
 					}
 					if (!value) continue;
@@ -417,20 +448,24 @@ function removePkcs7Padding(buf: Buffer): Buffer {
 	return !padding || padding > 16 ? buf : buf.subarray(0, buf.length - padding);
 }
 
-function readBrowserPassword(config: BrowserConfig, currentPlatform: typeof process.platform): Promise<string | null> {
-	const cacheKey = `${currentPlatform}:${config.name}`;
+function passwordCacheKey(config: BrowserConfig, currentPlatform: typeof process.platform): string {
+	return `${currentPlatform}:${config.name}`;
+}
+
+function readBrowserPasswords(config: BrowserConfig, currentPlatform: typeof process.platform): Promise<BrowserPassword[]> {
+	const cacheKey = passwordCacheKey(config, currentPlatform);
 	const cached = browserPasswordCache.get(cacheKey);
 	if (cached) return cached;
 	const passwordResult = currentPlatform === "darwin"
 		? config.keychainAccount && config.keychainService
-			? readKeychainPassword(config.keychainAccount, config.keychainService).then(password => ({ password, cacheable: Boolean(password) }))
-			: Promise.resolve({ password: null, cacheable: false })
+			? readKeychainPassword(config.keychainAccount, config.keychainService).then(value => ({ value, cacheable: Boolean(value) }))
+			: Promise.resolve({ value: null, cacheable: false })
 		: currentPlatform === "linux"
-			? readLinuxPassword(config.secretToolApp)
-			: Promise.resolve({ password: null, cacheable: false });
-	const passwordPromise = passwordResult.then(({ password, cacheable }) => {
+			? readLinuxPassword(config)
+			: Promise.resolve({ value: null, cacheable: false });
+	const passwordPromise = passwordResult.then(({ cacheable, ...password }) => {
 		if (!cacheable) browserPasswordCache.delete(cacheKey);
-		return password;
+		return [password];
 	}, (error) => {
 		browserPasswordCache.delete(cacheKey);
 		throw error;
@@ -477,17 +512,36 @@ function readKeychainPassword(account: string, service: string): Promise<string
 	});
 }
 
-function readLinuxPassword(secretToolApp: string | undefined): Promise<{ password: string; cacheable: boolean }> {
-	if (!secretToolApp) return Promise.resolve({ password: "peanuts", cacheable: true });
+function readLinuxCommandPassword(command: string, args: string[]): Promise<{ value: string | null; failed: boolean }> {
 	return new Promise((resolve) => {
-		execFile("secret-tool", ["lookup", "application", secretToolApp], { timeout: 5000 }, (err, stdout) => {
-			if (err) { resolve({ password: "peanuts", cacheable: false }); return; }
-			const password = stdout.trim();
-			resolve(password ? { password, cacheable: true } : { password: "peanuts", cacheable: false });
-		});
+		execFile(command, args, { timeout: 5000 }, (err, stdout) => resolve({ value: err ? null : stdout.trim() || null, failed: Boolean(err) }));
 	});
 }
 
+function isKdeSession(): boolean {
+	const desktop = process.env.XDG_CURRENT_DESKTOP?.toLowerCase().split(":") ?? [];
+	return process.env.KDE_FULL_SESSION?.toLowerCase() === "true" || desktop.includes("kde");
+}
+
+async function readKWalletPassword(config: BrowserConfig): Promise<BrowserPassword> {
+	if (!isKdeSession() || !config.kwalletFolder || !config.kwalletEntry) return { value: null };
+	const result = await readLinuxCommandPassword("kwallet-query", ["-f", config.kwalletFolder, "-r", config.kwalletEntry, "kdewallet"]);
+	return {
+		value: result.value,
+		source: result.value ? "kwallet" : undefined,
+		...(result.failed ? { warning: `Could not read ${config.name} KWallet cookie encryption password` } : {}),
+	};
+}
+
+async function readLinuxPassword(config: BrowserConfig): Promise<BrowserPassword & { cacheable: boolean }> {
+	if (!config.secretToolApp) return { value: "peanuts", cacheable: false };
+	const secretService = await readLinuxCommandPassword("secret-tool", ["lookup", "application", config.secretToolApp]);
+	if (secretService.value) return { value: secretService.value, source: "secret-service", cacheable: true };
+	const kwallet = await readKWalletPassword(config);
+	if (kwallet.value) return { ...kwallet, cacheable: true };
+	return { value: "peanuts", warning: kwallet.warning, cacheable: false };
+}
+
 async function importSqlite(): Promise<typeof import("node:sqlite") | null> {
 	if (process.env.PI_WEB_ACCESS_DISABLE_NODE_SQLITE === "1") return null;
 	if (sqliteImportAttempted) return sqliteModule;

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

@@ -46,7 +46,9 @@ function buildProviderButtons(
 		{ value: "serpapi", label: "SerpApi", available: available.serpapi },
 		{ value: "serper", label: "Serper", available: available.serper },
 		{ value: "serply", label: "Serply", available: available.serply },
+		{ value: "you", label: "You.com", available: available.you },
 		{ value: "baizhi", label: "Baizhi", available: available.baizhi },
+		{ value: "zai", label: "Z.ai", available: available.zai },
 		{ value: "valyu", label: "Valyu", available: available.valyu },
 	];
 
@@ -1474,7 +1476,7 @@ const SCRIPT = `(function() {
   var token = DATA.sessionToken;
   var timeoutSec = DATA.timeout;
   var queries = Array.isArray(DATA.queries) ? DATA.queries : [];
-  var providers = ["auto", "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", "serpapi", "serper", "serply", "valyu", "baizhi"];
+  var providers = ["auto", "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", "serpapi", "serper", "serply", "valyu", "baizhi", "you", "zai"];
   var availProviders = DATA.availableProviders && typeof DATA.availableProviders === "object" ? DATA.availableProviders : {};
   var workflow = "summary-review";
   var initialDefaultProvider = typeof DATA.defaultProvider === "string" ? DATA.defaultProvider : "exa";
@@ -1709,7 +1711,9 @@ const SCRIPT = `(function() {
     if (provider === "serpapi") return "SerpApi";
     if (provider === "serper") return "Serper";
     if (provider === "serply") return "Serply";
+    if (provider === "you") return "You.com";
     if (provider === "baizhi") return "Baizhi";
+    if (provider === "zai") return "Z.ai";
     if (provider === "valyu") return "Valyu";
     return "Unknown";
   }

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

@@ -305,7 +305,9 @@ export function startCuratorServer(
 		if (provider === "serpbase") return availableProviders.serpbase;
 		if (provider === "serper") return availableProviders.serper;
 		if (provider === "serply") return availableProviders.serply;
+		if (provider === "you") return availableProviders.you;
 		if (provider === "baizhi") return availableProviders.baizhi;
+		if (provider === "zai") return availableProviders.zai;
 		if (provider === "valyu") return availableProviders.valyu;
 		return false;
 	}