Commit Graph

9859 Commits

Author SHA1 Message Date
Magnus Müller 911b036a8b Remove internal Rust eval artifacts 2026-06-05 00:23:24 +00:00
Magnus Müller 8242a18e3e Record eval-visible Rust history proof 2026-06-04 23:26:44 +00:00
Magnus Müller e22b6fe5fc Fix Rust Agent wrapper initialization parity 2026-06-04 23:11:10 +00:00
Magnus Müller c33fcc9ace Ledger browser_fetch resilience proof 2026-06-04 20:05:10 +00:00
Magnus Müller 8b7d2231dc Ledger eval judge timeout parity 2026-06-04 19:53:10 +00:00
Magnus Müller 43b16ec658 Ledger long-run finalization nudge 2026-06-04 19:36:37 +00:00
Magnus Müller 32f50007a1 Ledger durable prompt replay proof 2026-06-04 19:21:56 +00:00
Magnus Müller f65d953c39 Flatten Rust Laminar LLM inputs 2026-06-04 19:06:07 +00:00
Magnus Müller 35e49b5926 Record eval timeout and cache parity proofs 2026-06-04 18:44:01 +00:00
Magnus Müller fcf9817606 Record oversized eval history persistence proof 2026-06-04 18:25:24 +00:00
Magnus Müller ecb2c55c6a Harden Rust Agent timeout reconstruction 2026-06-04 18:14:37 +00:00
Magnus Müller bcf147a2e2 Trace Rust Agent tool definitions in Laminar 2026-06-04 17:57:20 +00:00
Magnus Müller ee8a86a091 Trace Rust Agent tools and cache usage 2026-06-04 17:43:59 +00:00
Magnus Müller ba7df96250 Fix Rust Agent Laminar usage telemetry 2026-06-04 16:54:54 +00:00
Magnus Müller 79691dd9d6 Align Rust Agent constructor with upstream API 2026-06-04 16:20:37 +00:00
Magnus Müller 1474c60da1 Merge remote-tracking branch 'upstream/main' into magnus/browser-use-rust-core-integration
# Conflicts:
#	browser_use/__init__.py
#	browser_use/agent/service.py
#	browser_use/browser/watchdogs/downloads_watchdog.py
#	browser_use/code_use/utils.py
#	browser_use/llm/models.py
#	browser_use/tokens/service.py
#	browser_use/utils.py
2026-06-04 16:14:57 +00:00
Magnus Müller d34bee8801 Fix Rust Anthropic cache cost accounting 2026-06-04 16:11:11 +00:00
Magnus Müller b118bcf6fa Record Rust current-state cache parity 2026-06-04 15:56:08 +00:00
Magnus Müller 46bffc1516 Record Rust prompt cache proof 2026-06-04 15:49:06 +00:00
Magnus Müller 920af58bfa Populate Rust Laminar spans with messages 2026-06-04 15:36:46 +00:00
Magnus Müller 15ac190cc1 Replay Rust LLM turns in Laminar 2026-06-04 15:18:47 +00:00
Magnus Müller c2b5a2682b Price Rust terminal usage summaries 2026-06-04 15:12:57 +00:00
Magnus Müller b6d694de91 Record latest eval timeout hardening 2026-06-04 14:25:40 +00:00
Magnus Müller bc2e3d6e6a Bound Rust terminal event reloads 2026-06-04 13:49:20 +00:00
Magnus Müller 19bfb125a9 Reserve bounded Rust follow-up timeouts 2026-06-04 13:26:23 +00:00
Magnus Müller bb33f4cb91 Record latest real_v8 eval gates 2026-06-04 12:49:36 +00:00
Magnus Müller 1e484c4c77 Record dataset timebox finalization contract 2026-06-04 12:34:57 +00:00
Magnus Müller 76eff55b35 Record text-heavy extraction screenshot restraint 2026-06-04 12:21:56 +00:00
Magnus Müller f75ca82011 Record trajectory judge eval gate 2026-06-04 12:13:28 +00:00
Magnus Müller b3f0aa044e Record non-vision screenshot eval gate 2026-06-04 11:58:27 +00:00
Magnus Müller 50cad881a3 Record batch fetch recipe proof 2026-06-04 11:31:45 +00:00
Magnus Müller 2fda56661e Record batch fetch eval gate 2026-06-04 11:26:08 +00:00
Magnus Müller 6f473d5cd9 Record batch fetch helper proof 2026-06-04 11:14:43 +00:00
Magnus Müller 245e99ae82 Record summary cap eval gate 2026-06-04 11:05:32 +00:00
Magnus Müller ee87e06729 Record browser script summary cap proof 2026-06-04 10:53:49 +00:00
Magnus Müller 728e469709 Record browser script 4k cap eval proof 2026-06-04 10:45:54 +00:00
Magnus Müller 406b0a25eb Record judge retry eval gate 2026-06-04 10:29:53 +00:00
Magnus Müller 5651ee5704 Record stdout cap and judge retry eval proof 2026-06-04 10:18:35 +00:00
Magnus Müller 0445876d2d Record safe Agent SDK fallback proof 2026-06-04 10:00:46 +00:00
Magnus Müller 71a4ddbca1 Compact large Rust terminal history outputs 2026-06-04 09:39:19 +00:00
Magnus Müller 350ee39ae5 Record download filter eval proof 2026-06-04 09:22:38 +00:00
Magnus Müller 20e70519cf Filter generic network auto-downloads 2026-06-04 09:10:02 +00:00
Magnus Müller 0130c5a570 Record judge timeout eval proof 2026-06-04 09:06:40 +00:00
Magnus Müller 068622baf4 Record direct URL sanitizer proof 2026-06-04 08:52:38 +00:00
Magnus Müller 91705e22b7 Sanitize direct-start URL candidates 2026-06-04 08:51:39 +00:00
Magnus Müller 95e63d2868 Record bounded judge eval gate 2026-06-04 08:35:03 +00:00
Magnus Müller 1ba30e73b0 Record bounded Agent SDK judge proof 2026-06-04 08:22:28 +00:00
Magnus Müller 982b7f59f8 Record done result schema proof 2026-06-04 08:05:14 +00:00
Magnus Müller 5d716ea439 Record post fallback eval gate 2026-06-04 07:57:00 +00:00
Magnus Müller ad1e9fe928 Record Agent SDK judge fallback proof 2026-06-04 07:44:43 +00:00