Commit Graph

639 Commits

Author SHA1 Message Date
Peter Steinberger
e4adb0b0e3 fix: hide adaptive think option for GPT models 2026-04-21 06:19:29 +01:00
Tak Hoffman
1303b03241 fix: add silent reply policy by conversation type (#68644)
Thanks @Takhoffman.
2026-04-21 05:17:55 +01:00
Peter Steinberger
22bff819ab fix: strengthen agent completion bias 2026-04-21 04:19:26 +01:00
aniaan
c8e5150fd4 feat(moonshot): default to Kimi K2.6 with K2.6-only thinking.keep support (#68816)
Merged via squash.

Prepared head SHA: ed54e02842
Co-authored-by: aniaan <40813941+aniaan@users.noreply.github.com>
Co-authored-by: odysseus0 <8635094+odysseus0@users.noreply.github.com>
Reviewed-by: @odysseus0
2026-04-20 18:04:49 -07:00
Sebastian B Otaegui
f48d040bf5 feat: send compaction start and completion notices (#67830)
Merged via squash.

Prepared head SHA: abedf6cf11
Co-authored-by: feniix <91633+feniix@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman
2026-04-20 11:55:17 -07:00
Josh Avant
d5b326523f qa-lab: make live lanes CI-ready for v1 E2E automation (#69122)
* qa-lab: harden CI defaults and failure semantics for live lanes

* qa-lab: add unit tests for suite progress logging defaults

* qa-lab: cover malformed multipass summary edge cases

* qa-lab: share suite summary failure counting helper

* qa-lab: test allow-failures parse wiring and sanitize progress ids

* fix: note qa CI live-lane defaults in changelog (#69122) (thanks @joshavant)
2026-04-19 21:13:27 -05:00
Peter Steinberger
afebeb5e9a fix: align active-memory timeout schema (#68480) (thanks @Bartok9) 2026-04-18 20:31:41 +01:00
Rubén Cuevas
a0dd5f7e8e Align documented bootstrap context defaults with runtime values (#67968)
* Fix bootstrap default limit docs to match runtime

* docs(context): fix stale bootstrap max/file example
2026-04-18 09:00:21 +05:30
Gustavo Madeira Santana
82fe6f50ef QA: organize scenarios by theme 2026-04-17 11:03:47 -04:00
Gustavo Madeira Santana
bb7e9823a8 QA Lab: add provider registry
Move mock and live provider behavior behind provider-owned definitions so suite, manual, Matrix, and transport lanes share defaults, auth staging, model config, and standalone server startup.

Add AIMock as a first-class local provider mode while keeping mock-openai as the scenario-aware deterministic lane.
2026-04-16 21:24:59 -04:00
Gustavo Madeira Santana
56a9fd4b34 QA Matrix: capture full runner output 2026-04-16 16:18:54 -04:00
Tak Hoffman
b10ae0bf13 fix(docs): add active memory speed recommendations 2026-04-16 01:11:08 -05:00
Tak Hoffman
4f00b76925 fix(context-window): Tighten context limits and bound memory excerpts (#67277)
* Tighten context limits and bound memory excerpts

* Align startup context defaults in config docs

* Align qmd memory_get bounds with shared limits

* Preserve qmd partial memory reads

* Fix shared memory read type import

* Add changelog entry for context bounds
2026-04-15 13:06:02 -05:00
Vincent Koc
a780151fd1 docs: add experimental-features page and de-experimentalize dreaming 2026-04-15 11:46:25 +01:00
Pengfei Ni
88d3620a85 feat(github-copilot): add embedding provider for memory search (#61718)
Merged via squash.

Prepared head SHA: 05a78ce7f2
Co-authored-by: feiskyer <676637+feiskyer@users.noreply.github.com>
Co-authored-by: vincentkoc <25068+vincentkoc@users.noreply.github.com>
Reviewed-by: @vincentkoc
2026-04-15 10:39:28 +01:00
Gustavo Madeira Santana
0c4e0d7030 memory: block dreaming self-ingestion (#66852)
Merged via squash.

Prepared head SHA: 4742656a0d
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
2026-04-14 20:29:12 -04:00
Tak Hoffman
f94d6778b1 fix(active-memory): Move active memory recall into the hidden prompt prefix (#66144)
* move active memory into prompt prefix

* document active memory prompt prefix

* strip active memory prefixes from recall history

* harden active memory prompt prefix handling

* hide active memory prefix in leading history views

* strip hidden memory blocks after prompt merges

* preserve user turns in memory recall cleanup
2026-04-13 16:05:43 -05:00
Rugved Somwanshi
0cfb83edfa feat: LM Studio Integration (#53248)
* Feat: LM Studio Integration

* Format

* Support usage in streaming true

Fix token count

* Add custom window check

* Drop max tokens fallback

* tweak docs

Update generated

* Avoid error if stale header does not resolve

* Fix test

* Fix test

* Fix rebase issues

Trim code

* Fix tests

Drop keyless

Fixes

* Fix linter issues in tests

* Update generated artifacts

* Do not have fatal header resoltuion for discovery

* Do the same for API key as well

* fix: honor lmstudio preload runtime auth

* fix: clear stale lmstudio header auth

* fix: lazy-load lmstudio runtime facade

* fix: preserve lmstudio shared synthetic auth

* fix: clear stale lmstudio header auth in discovery

* fix: prefer lmstudio header auth for discovery

* fix: honor lmstudio header auth in warmup paths

* fix: clear stale lmstudio profile auth

* fix: ignore lmstudio env auth on header migration

* fix: use local lmstudio setup seam

* fix: resolve lmstudio rebase fallout

---------

Co-authored-by: Frank Yang <frank.ekn@gmail.com>
2026-04-13 15:22:44 +08:00
Peter Steinberger
20266c14cb feat(qa-lab): add control ui qa-channel roundtrip scenario 2026-04-12 19:41:06 -07:00
Tak Hoffman
fdd6b9b525 Clarify Active Memory lexical fallback behavior 2026-04-12 14:27:38 -05:00
Tak Hoffman
598ee39527 Clarify Active Memory embedding provider setup 2026-04-12 14:23:02 -05:00
Peter Steinberger
ca2d297c50 docs(qa): clarify markdown scenario contract 2026-04-12 11:59:50 -07:00
Tak Hoffman
c37e49f275 Add /trace toggle and fix Active Memory diagnostics 2026-04-12 13:20:22 -05:00
Marcus Castro
000fc7f233 refactor(qa): add shared QA channel contract and harden worker startup (#64562)
* refactor(qa): add shared transport contract and suite migration

* refactor(qa): harden worker gateway startup

* fix(qa): scope waits and sanitize shutdown artifacts

* fix(qa): confine artifacts and redact preserved logs

* fix(qa): block symlink escapes in artifact paths

* fix(gateway): clear shutdown race timers

* fix(qa): harden shutdown cleanup paths

* fix(qa): sanitize gateway logs in thrown errors

* fix(qa): harden suite startup and artifact paths

* fix(qa): stage bundled plugins from mutated config

* fix(qa): broaden gateway log bearer redaction

* fix(qa-channel): restore runtime export

* fix(qa): stop failed gateway startups as a process tree

* fix(qa-channel): load runtime hook from api surface
2026-04-12 15:02:57 -03:00
Peter Steinberger
15b86ac6d0 fix: narrow qmd defaults and clawblocker memory 2026-04-12 18:52:06 +01:00
Anonymous Amit
42590106ab improve memory fallback lexical ranking (#65395)
* improve memory fallback lexical ranking

* use neutral lexical fallback fixtures

* fix(memory-core): keep lexical boosts out of hybrid search

---------

Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
2026-04-12 18:36:28 +01:00
Tak Hoffman
3d1135fa19 docs: update active-memory fallback guidance 2026-04-11 23:21:57 -05:00
Tak Hoffman
94340b9598 fix(agent-init): move session startup context into the runtime (#65055)
* fix: preload startup memory for bare session resets

* docs: align AGENTS template with startup context runtime

* fix(agent-init): harden startup context prompt handling

* fix(agent-init): tighten startup context parsing and limits

* fix(agent-init): honor calendar-day startup memory windows

* docs: clarify startup daily memory injection
2026-04-11 21:52:16 -05:00
Tak Hoffman
52bf19c45e fix(active-memory): remove built-in fallback model (#65047)
* fix(active-memory): remove built-in fallback model

* fix(active-memory): tighten fallback cleanup
2026-04-11 20:24:07 -05:00
Tak Hoffman
bf544bc9e9 docs: fix active memory gateway command 2026-04-10 23:02:13 -05:00
Gustavo Madeira Santana
25445a9f2e qa-lab: add Matrix live transport QA lane (#64489)
Merged via squash.

Prepared head SHA: ae9bb37751
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras
2026-04-10 19:35:08 -04:00
Peter Steinberger
c66afe472a docs: add codex harness setup guide 2026-04-10 21:45:32 +01:00
Peter Steinberger
c16b1b7433 docs: document harness fallback policy 2026-04-10 21:27:26 +01:00
Peter Steinberger
bfc0889776 docs: document Codex harness plugin workflow 2026-04-10 21:22:16 +01:00
Peter Steinberger
3027efaf21 test: raise QA suite default concurrency 2026-04-10 13:45:57 +01:00
Peter Steinberger
4c14f55c62 test: parallelize QA suite scenarios 2026-04-10 13:45:57 +01:00
Peter Steinberger
7e2a1db53b fix: recover silent LLM idle timeouts 2026-04-10 08:09:17 +01:00
Shakker
655cfb477a docs: clarify multipass live auth support 2026-04-09 23:53:13 +01:00
Shakker
a04c331cc1 docs: document qa multipass runner 2026-04-09 23:53:13 +01:00
Tak Hoffman
b83726d13e Feat: Add Active Memory recall plugin (#63286)
* Refine plugin debug plumbing

* Tighten plugin debug handling

* Reduce active memory overhead

* Abort active memory sidecar on timeout

* Rename active memory blocking subagent wording

* Fix active memory cache and recall selection

* Preserve active memory session scope

* Sanitize recalled context before retrieval

* Add active memory changelog entry

* Harden active memory debug and transcript handling

* Add active memory policy config

* Raise active memory timeout default

* Keep usage footer on primary reply

* Clear stale active memory status lines

* Match legacy active memory status prefixes

* Preserve numeric active memory bullets

* Reuse canonical session keys for active memory

* Let active memory subagent decide relevance

* Refine active memory plugin summary flow

* Fix active memory main-session DM detection

* Trim active memory summaries at word boundaries

* Add active memory prompt styles

* Fix active memory stale status cleanup

* Rename active memory subagent wording

* Add active memory prompt and thinking overrides

* Remove active memory legacy status compat

* Resolve active memory session id status

* Add active memory session toggle

* Add active memory global toggle

* Fix active memory toggle state handling

* Harden active memory transcript persistence

* Fix active memory chat type gating

* Scope active memory transcripts by agent

* Show plugin debug before replies
2026-04-09 11:27:37 -05:00
Peter Steinberger
be46d0ddc6 test: update character eval public panel 2026-04-09 01:25:59 +01:00
Peter Steinberger
39cc6b7dc7 fix: stabilize character eval and Qwen model routing 2026-04-09 01:04:09 +01:00
Mariano
d514f4de83 Dreaming: surface grounded scene lane (#63395)
Merged via squash.

Prepared head SHA: 0c7f586f32
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
Mariano Belinky
85427441a2 Docs/memory: explain grounded backfill flows 2026-04-08 23:48:09 +02:00
Mariano Belinky
a71ad12044 Memory/dreaming: harden grounded backfill follow-ups 2026-04-08 23:43:39 +02:00
Peter Steinberger
21ef1bf8de feat: parallelize character eval runs 2026-04-08 20:05:55 +01:00
Peter Steinberger
9e4f478f86 feat(plugins): support provider auth aliases 2026-04-08 19:03:04 +01:00
Peter Steinberger
4a51a1031d feat: add character eval model options 2026-04-08 17:05:30 +01:00
Peter Steinberger
3101d81053 feat: add QA character eval reports 2026-04-08 15:52:49 +01:00
Peter Steinberger
d9dc75774b fix: align LLM idle timeout policy 2026-04-08 14:31:41 +01:00