Commit Graph

5070 Commits

Author SHA1 Message Date
Peter Steinberger be46d0ddc6 test: update character eval public panel 2026-04-09 01:25:59 +01:00
Vignesh Natarajan 2484064c48 chore(lint): clear extension lint regressions and add #63416 changelog 2026-04-08 17:17:29 -07:00
Peter Steinberger 39cc6b7dc7 fix: stabilize character eval and Qwen model routing 2026-04-09 01:04:09 +01:00
Peter Steinberger ac12b0701b style: format memory and gateway touchups 2026-04-09 00:44:09 +01:00
Peter Steinberger f2c0482d3c fix: surface delayed browser navigation blocks 2026-04-09 00:42:52 +01:00
Peter Steinberger fbbd644d7a plugins: load lightweight provider discovery entries 2026-04-09 00:33:33 +01:00
Peter Steinberger c62a39c7a1 fix: restore main ci 2026-04-08 23:30:18 +01:00
Mariano d514f4de83 Dreaming: surface grounded scene lane (#63395)
Merged via squash.

Prepared head SHA: 0c7f586f32459dca89894202559377ee946a55ff
Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com>
Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com>
Reviewed-by: @mbelinky
2026-04-09 00:24:47 +02:00
Gustavo Madeira Santana bd7801eefa Slack: key turn-local dedupe by dispatch kind
Scope Slack turn-local delivery dedupe by reply dispatch kind so identical tool and final payloads on the same thread do not collapse into one send.

Expose the existing dispatcher kind on the public reply-runtime seam and cover the Slack tracker and preview-fallback paths with regression tests.
2026-04-08 18:19:34 -04:00
Altay 554bc0a9fd fix(plugins): keep test helpers out of contract barrels (#63311)
Merged via squash.

Prepared head SHA: 769e90c6af377e13a3dcc56f70131e4caa48e0ca
Co-authored-by: altaywtf <9790196+altaywtf@users.noreply.github.com>
Co-authored-by: altaywtf <9790196+altaywtf@users.noreply.github.com>
Reviewed-by: @altaywtf
2026-04-08 22:59:05 +01:00
Gustavo Madeira Santana 10c87527d5 Slack: dedupe partial streaming replies (#62859)
Merged via squash.

Prepared head SHA: cbecb50c06f7657dc259cf9fdc71419b9b390559
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
2026-04-08 17:55:30 -04:00
Mariano Belinky a71ad12044 Memory/dreaming: harden grounded backfill follow-ups 2026-04-08 23:43:39 +02:00
Peter Steinberger 868d03d6d0 fix(memory): align dreaming status payloads 2026-04-08 22:38:29 +01:00
Mariano e8209e4cf9 Memory/dreaming: feed grounded backfill into short-term promotion (#63370)
Merged via squash.

Prepared head SHA: 5dfe246ef94a756dc776dbb34d4ccafa960dbfb7
Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com>
Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com>
Reviewed-by: @mbelinky
2026-04-08 23:31:37 +02:00
lukeboyett f6e1da3ab3 fix(matrix/doctor): migrate legacy channels.matrix.dm.policy 'trusted' (fixes #62931) (#62942)
Merged via squash.

Prepared head SHA: d9f553bccf65eb6f27d465a64fc95eb741d589cc
Co-authored-by: lukeboyett <46942646+lukeboyett@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
2026-04-08 17:00:19 -04:00
Shakker d66e2d5b33 test: cover curated qa missing-key reply classification 2026-04-08 21:55:39 +01:00
Shakker c63d25bd9b fix: classify curated qa missing-key replies 2026-04-08 21:55:39 +01:00
Shakker 9cfa152962 test: cover mixed-traffic qa wait cursors 2026-04-08 21:55:39 +01:00
Shakker 204d766b27 fix: align qa wait cursor semantics 2026-04-08 21:55:39 +01:00
Shakker a6d76df4f0 test: cover qa scenario wait failure replies 2026-04-08 21:55:39 +01:00
Shakker b3f3cfd598 fix: fail fast across qa scenario wait paths 2026-04-08 21:55:39 +01:00
Shakker 491e216c45 fix: fail fast on qa live auth errors 2026-04-08 21:55:39 +01:00
Gustavo Madeira Santana 30211be1cb Slack: treat ACP block text as visible output (#62858)
Merged via squash.

Prepared head SHA: 14f202e1cce5fdd3cec9733efbbe270843716512
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
2026-04-08 16:33:43 -04:00
Eva H d7bf97adb3 fix: enable thinking support for the ollama api (#62712)
Merged via squash.

Prepared head SHA: c0b995035ef734ea4af335c3d2a7611965123122
Co-authored-by: hoyyeva <63033505+hoyyeva@users.noreply.github.com>
Co-authored-by: BruceMacD <5853428+BruceMacD@users.noreply.github.com>
Reviewed-by: @BruceMacD
2026-04-08 13:26:18 -07:00
Agustin Rivera 5f5b3d733b fix(browser): re-check interaction-driven navigations (#63226)
* fix(browser): guard interaction-driven navigations

* fix(browser): avoid rechecking unchanged interaction urls

* fix(browser): guard delayed interaction navigations

* fix(browser): guard interaction-driven navigations for full action duration

* fix(browser): avoid waiting on interaction grace timer

* fix(browser): ignore same-document hash-only URL changes in navigation guard

* fix(browser): dedupe interaction nav guards

* fix(browser): guard same-URL reloads in interaction navigation listeners

* docs(changelog): add interaction navigation guard entry

* fix(browser): drop duplicate ssrfPolicy props

* fix(browser): tighten interaction navigation guards

---------

Co-authored-by: Devin Robison <drobison@nvidia.com>
2026-04-08 13:39:07 -06:00
Agustin Rivera dafcaf9d69 fix(browser): harden browser control override loading (#62663)
* fix(browser): harden browser control overrides

* fix(lint): prepare boundary artifacts for extension oxlint

* docs(changelog): add browser override hardening entry

* fix(lint): avoid duplicate boundary prep

---------

Co-authored-by: Devin Robison <drobison@nvidia.com>
Co-authored-by: Devin Robison <drobison00@users.noreply.github.com>
2026-04-08 13:24:47 -06:00
Gustavo Madeira Santana 9b19c0b87f Matrix: report startup failures as errors 2026-04-08 15:19:43 -04:00
Peter Steinberger 21ef1bf8de feat: parallelize character eval runs 2026-04-08 20:05:55 +01:00
Peter Steinberger f1e75d3259 fix: load QA live provider overrides 2026-04-08 20:05:55 +01:00
Peter Steinberger b3e7858051 build: stage nostr runtime dependencies 2026-04-08 20:05:55 +01:00
Peter Steinberger 79f440c903 fix(memory): accept embedded dreaming heartbeat tokens 2026-04-08 19:59:36 +01:00
Gustavo Madeira Santana 0c00c3c230 fix(matrix): contain sync outage failures (#62779)
Merged via squash.

Prepared head SHA: 901bb767b56250915de2b866db91e4e2d8b098b0
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
2026-04-08 14:41:28 -04:00
Peter Steinberger a3d21539ef test: stabilize full-suite execution 2026-04-08 19:40:57 +01:00
Mariano 078e7a6586 feat(memory): harden grounded REM extraction (#63297)
Merged via squash.

Prepared head SHA: e188b7e26dc5c4d1f449d6889605824fce0a8a81
Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com>
Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com>
Reviewed-by: @mbelinky
2026-04-08 20:28:03 +02:00
Mariano dbf5960bd9 feat(memory): add grounded REM backfill lane (#63273)
Merged via squash.

Prepared head SHA: 4450f25485b5738233098d5dd7450ccd853097a2
Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com>
Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com>
Reviewed-by: @mbelinky
2026-04-08 20:23:28 +02:00
Peter Steinberger 9e4f478f86 feat(plugins): support provider auth aliases 2026-04-08 19:03:04 +01:00
Peter Steinberger 2d0e25c23a fix: pass system prompt to codex cli 2026-04-08 18:15:10 +01:00
Peter Steinberger 4a51a1031d feat: add character eval model options 2026-04-08 17:05:30 +01:00
Peter Steinberger 4bbf78e566 test: make character eval scenario natural 2026-04-08 17:05:30 +01:00
Peter Steinberger 1e274f8695 test: keep chutes implicit provider tests on provider catalog 2026-04-08 16:33:39 +01:00
Peter Steinberger e4c7ee5856 test: keep kimi implicit provider tests on provider catalog 2026-04-08 16:30:56 +01:00
Peter Steinberger e8d5837eea fix: keep minimax provider mocks package-local 2026-04-08 16:13:37 +01:00
Peter Steinberger 17bd5f1dd2 refactor: share html entity tool call decoding 2026-04-08 15:58:47 +01:00
Peter Steinberger 54e5741357 refactor: dedupe telegram exec approval tests 2026-04-08 15:58:47 +01:00
Peter Steinberger 4da74a4d9a refactor: dedupe matrix exec approval tests 2026-04-08 15:58:47 +01:00
Peter Steinberger 82a958dc79 refactor: dedupe firecrawl and directive helpers 2026-04-08 15:58:46 +01:00
Peter Steinberger 34f73abfd3 refactor: dedupe plugin metadata test helpers 2026-04-08 15:58:46 +01:00
Peter Steinberger a5737f83af refactor: dedupe browser navigation guard tests 2026-04-08 15:58:45 +01:00
Peter Steinberger 3101d81053 feat: add QA character eval reports 2026-04-08 15:52:49 +01:00
Peter Steinberger aa3b1357cb fix: support Codex CLI QA auth 2026-04-08 15:52:01 +01:00