Search castle's Chrome tabs and history over CDP https://git.soarez.net/sz/pi-castle-cdp-search.git/atom/src/index.ts?h=master 2026-08-03T20:45:52Z 2026-08-03T20:45:52Z Igor Soarez igor@soarez.org 2026-08-03T20:45:52Z urn:sha1:97b7804d02d0a8ffc9afdc64069069baf93ef392 ctx.ui.notify is a no-op when hasUI is false, so `pi -p /search-engine` changed the stored engine and printed nothing — the command looked broken. Print mode now falls back to stdout. JSON mode deliberately does not: its stdout is a structured event stream and a stray line would corrupt it. 2026-08-03T20:43:56Z Igor Soarez igor@soarez.org 2026-08-03T20:43:56Z urn:sha1:db69207c06e8d5233bff4996e3ef5b43332d533f Engine resolution mirrors the browser target: CCS_SEARCH_ENGINE, then a /search-engine choice persisted machine-wide, then Google. A per-call `engine` parameter sits above both so the agent can fall back when one engine starts serving captchas — the one case where the model, not the operator, has to make the call. Unlike the CDP target there is no safety argument for the environment winning: driving the wrong browser means automating someone's signed-in Chrome, choosing a different index does not. An unsupported recency window is refused, naming the engines that support it, rather than dropped. Silently returning unfiltered results is indistinguishable from success, which is the failure this whole design is trying to avoid. Extraction grows a second mode. DuckDuckGo, Bing and Brave have clean per-result containers; Google does not, so its heading-walk stays as its own path rather than being bent into the item shape. DuckDuckGo and Bing route links through redirectors, unwrapped in the page. Third silent-failure trap found, alongside Google's two: on Bing, `count` cancels `filters`. With ex1:"ez1" alone every result is hours old; add count in either order and months-old results return, looking perfectly ordinary. Bing now drops count whenever a date filter is present. Challenge detection widened to Brave's "Verifying you're not a bot" and "Quick check before you continue searching", which the previous Google- shaped matcher missed entirely — found by tripping it. 2026-08-03T20:18:02Z Igor Soarez igor@soarez.org 2026-08-03T20:18:02Z urn:sha1:495de0d5283dd3e4a6ef715b596c4a2892e95915 Attaches to a browser that is already running — never launches one — using the same endpoint configuration as pi-browser-harness, so a single /browser-target choice governs both packages. One tool, castle_cdp_search, deliberately not named web_search so it coexists with pi-web-access rather than shadowing it. Notes from validating against castle's Chrome: - tbs=qdr:*, the parameter Google's own Tools menu writes, renders an empty page on this profile; the older as_qdr=* works. Any date filter combined with udm=14 is also empty, so recency drops udm. - Target.createTarget must not be raced against the abort signal: raceAbort abandons the promise but cannot cancel the command, and the command's side effect is a tab nothing is left holding. - A search cancelled while queued has to be removed from the semaphore queue, or the slot handed to it later is never counted back. - A decaying rate-limit block stops serving /sorry/ and returns an empty results page instead, indistinguishable from a genuine zero-hit search.