Commit Graph
1414 Commits
Author SHA1 Message Date
ciregenz 68017465ce [eric] browser: add a deterministic completion-honesty gate to catch ghost successes 2026-06-02 18:14:57 -07:00
ciregenz 2b2d5909a8 [eric] browser: instrument skill lifecycle, measure replay speedup, flag silent non-help 2026-06-02 18:03:43 -07:00
ciregenz 294e96d782 [eric] browser: version skills behind a trust gate, compose on proven sub-skills 2026-06-02 18:03:36 -07:00
ciregenz 5bb0b46890 [eric] browser: give the agent tools to list and deprecate its own learned skills 2026-06-02 16:33:21 -07:00
ciregenz e2a77b5eae [eric] browser: parameterize skills so one skill serves a task with different inputs 2026-06-02 16:27:11 -07:00
ciregenz e30d70ce97 [eric] browser: persist skills across sessions with secret-redaction gate 2026-06-02 16:17:23 -07:00
ciregenz 3aa9cf6ba0 [eric] browser: front-load page perception into turn 1 to cut orientation round-trips 2026-06-02 14:02:47 -07:00
ciregenz a015036383 [eric] browser: prompt-cache the fixed prefix and push batching to cut first-run turns 2026-06-02 14:01:00 -07:00
ciregenz 014414440b [eric] browser: decompose BrowserBatch into discrete replayable skill steps 2026-06-02 13:32:54 -07:00
ciregenz d1c1b44ee7 [eric] browser: replay learned skills with zero LLM calls, fall back on any miss 2026-06-02 12:49:55 -07:00
ciregenz d6682190cc [eric] browser: in-memory skill cache that distills tasks into replayable steps 2026-06-02 12:45:42 -07:00
ciregenz e911898387 [eric] browser: add robust click_by_name and share enumerate/click helpers 2026-06-02 12:43:21 -07:00
ciregenz 69c4546735 [eric] browser: refine ghost detector so read tasks need returned content, not state change 2026-06-02 12:35:12 -07:00
ciregenz 8a0cb4a6a0 [eric] browser: human-performance benchmark harness for rudimentary tasks 2026-06-02 12:29:59 -07:00
ciregenz 54249bc015 [eric] browser: retry cold screenshot capture to dodge the turn-0 viz race 2026-06-02 12:27:28 -07:00
ciregenz e2102afeab [eric] browser: metrics analyzer with ghost-success detection 2026-06-02 12:13:59 -07:00
ciregenz a8964830ac [eric] browser: record per-tool latency, tokens, and per-task completion metrics 2026-06-02 12:12:41 -07:00
ciregenz ea823951c6 [eric] browser: loop test for WebMCP-detect and route list/replay tools 2026-06-02 04:15:08 -07:00
ciregenz 15781d2a3b [eric] browser: list captured routes and replay safe GETs to skip the UI (tier 2) 2026-06-02 04:11:50 -07:00
ciregenz e0359e0752 [eric] browser: passively capture redacted shadow-API routes while browsing (tier 2) 2026-06-02 04:08:10 -07:00
ciregenz 6e006dd472 [eric] browser: detect a page's declared WebMCP tools (tier 1) 2026-06-02 04:03:10 -07:00
ciregenz f574696eb2 [eric] browser: one-shot crash-safe trial switch for webview on Windows electron 42 2026-06-02 03:56:07 -07:00
ciregenz 43ba7d2f1c [eric] browser: unit and end-to-end loop tests for the new browser behaviors 2026-06-02 03:56:07 -07:00
ciregenz 82dcb6bb4e [eric] browser: per-domain hints, deterministic stagnation, and aux-LLM fallback 2026-06-02 03:56:07 -07:00
ciregenz 21360cd2ea [eric] browser: rank/cap/goal-boost the element list and click into cross-origin iframes 2026-06-02 03:55:58 -07:00
ciregenz 74fbef0bc4 [eric] browser: auto-attach OOPIF child frames and route CDP by sessionId 2026-06-02 03:55:52 -07:00
ciregenz d798b61121 [eric] release: bump version to 1.1.72 v1.1.72 2026-06-01 15:59:13 -07:00
ciregenz 63e321b9fa [eric] agent: call out the literal "-" in the no-dashes voice rule 2026-06-01 15:48:23 -07:00
ciregenz ee894a5029 [eric] dashboard: calm the glowing agent card, drop the four infinite glow anims 2026-06-01 15:42:34 -07:00
ciregenz b153425a9a [eric] dashboard: calm the branch tether, drop marching-ants + pulse + blur filter 2026-06-01 15:01:13 -07:00
ciregenz 0b4d41ad92 [eric] chat: glide the streaming tool pill in and keep the commit hand-off seamless 2026-06-01 15:01:13 -07:00
ciregenz 06006cd54a [eric] chat: add thumbs up/down feedback with a why-modal routed to cloud analytics 2026-06-01 15:01:13 -07:00
ciregenz c89ba4dc30 [eric] agent: give the assistant a tight, quirky, no-dashes texting voice 2026-06-01 15:01:13 -07:00
ciregenz 3d65cacddf [eric] tools: drop personal gmail from the connected-account comment example 2026-06-01 15:01:13 -07:00
ciregenz 04faff315a [eric] ci: fix mcp-bundles node path and whitelist wheel sboms in host-leakage 2026-06-01 15:01:13 -07:00
eric e1101d4c2c [eric] chat: drive tool bubble entrance with a js mount-transition instead of a fragile mount keyframe that silently no-op'd (why tools appeared out of nowhere while streamed text slid in) 2026-06-01 13:51:43 -07:00
eric 8176338b2c [eric] chat: soften tool bubble enter to a 260ms glide so tools landing after a long pending gap slide in like the text instead of popping 2026-06-01 13:17:49 -07:00
eric d5cc1d222a [eric] chat: pin to bottom across the markdown-commit settle window so overflow-anchor cant yank the view up to the user message on stream end 2026-06-01 12:44:55 -07:00
eric 2718bddaf7 [eric] chat: keep the user message on remount for any live session, not just still-pending ones (ws echo clears pending instantly) 2026-06-01 12:44:55 -07:00
eric b30ccb061e [eric] chat: revert reveal rate to the faster constant-velocity version (40cps cruise felt sluggish) 2026-06-01 12:16:42 -07:00
eric 6138fe2495 [eric] chat: re-stick to bottom after a stream ends so the live-markdown height swap cant strand the view (unless you scrolled up) 2026-06-01 12:11:14 -07:00
eric 03f9636f00 [eric] chat: keep the optimistic user message on remount mid-stream so it stops vanishing when you leave and come back 2026-06-01 12:11:14 -07:00
eric c874122e0b [eric] chat: reveal at a readable ~40cps cruise with bounded catch-up instead of the 1000cps firehose 2026-06-01 12:11:14 -07:00
eric a3114367d9 [eric] merge: streaming cadence + live markdown + auth/devtools/browser fixes from dev 2026-06-01 11:55:38 -07:00
eric 4e2077a6b7 [eric] chat: keep tool body collapsed mid-stream, ease bubbles in, stop scroll-anchor fighting autoscroll 2026-06-01 11:55:27 -07:00
eric d2d0589501 [eric] chat: render markdown live while streaming so formatting doesnt snap in only at the end 2026-06-01 11:55:27 -07:00
eric 894a4b7e23 [eric] chat: rewrite stream reveal as a buffered constant-velocity controller to kill the pump-pump stutter 2026-06-01 11:55:27 -07:00
eric 6a2b55f23b [eric] browser: wait briefly for webview re-register before card-not-found to absorb the remount race 2026-06-01 11:55:17 -07:00
eric f6c1f73931 [eric] win: toggle devtools on f12 + ctrl/cmd+shift+i since the windows menu bar is hidden 2026-06-01 11:55:17 -07:00
eric bcb88ebefb [eric] auth: dev-only /api/dev/token so the split-port frontend can authenticate (404s when packaged) 2026-06-01 11:55:17 -07:00