59657913fd
perf(test): prune duplicate memory host tests
2026-04-20 20:05:37 +01:00
88de927a0c
perf(test): dedupe memory host mirror tests
2026-04-20 20:02:19 +01:00
f006678f3c
refactor: share balanced json extraction
2026-04-20 14:40:21 +01:00
faae8e08b3
test: share qmd multi-agent config fixture
2026-04-19 02:43:52 +01:00
805481c176
perf: narrow bonjour and sqlite runtime type surfaces
2026-04-19 02:03:19 +01:00
a0919685be
perf: narrow local llama type surface
2026-04-18 23:38:04 +01:00
0195da6b0e
refactor: cache optional runtime imports
2026-04-18 20:45:26 +01:00
2b7b5774b6
chore: remove dead code
2026-04-18 20:27:42 +01:00
5f075d3d49
test: reuse session file fixture root
2026-04-17 19:57:19 +01:00
dadcfb574f
test: trim surrogate chunk fixtures
2026-04-17 19:38:53 +01:00
77e6e4cf87
refactor: move memory embeddings into provider plugins
2026-04-17 02:57:18 +01:00
3a59eddd07
test: reduce hotspot fixture overhead
2026-04-17 02:37:00 +01:00
dbc8179f31
test: narrow hotspot mocks
2026-04-17 01:53:16 +01:00
cd330f5f98
test: isolate gemini embedding request helpers
2026-04-17 01:46:47 +01:00
fd48dfa68f
test: trim memory and mcp hotspots
2026-04-17 01:39:39 +01:00
2e08c77582
test: slim provider registry mocks
2026-04-17 01:29:12 +01:00
59b98334f6
test: narrow hotspot boundaries
2026-04-17 01:10:48 +01:00
ce1be0f43d
test: speed gemini embedding tests
2026-04-17 00:00:41 +01:00
b2cae7f12a
test: trim duplicate memory hotspot coverage
2026-04-16 23:15:38 +01:00
d59604b15e
test: speed up hotspot boundaries
2026-04-16 22:55:30 +01:00
63e53fbf2e
test: trim duplicate hotspot coverage
2026-04-16 22:19:32 +01:00
372c0051ba
test: speed up slow import-boundary tests
2026-04-16 21:14:17 +01:00
82e349a48a
memory: strip inbound metadata envelopes from user messages in session corpus ( #66548 )
...
Merged via squash.
Prepared head SHA: 98562b2a844436110+zqchris@users.noreply.github.com >
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com >
Reviewed-by: @jalehman
2026-04-16 11:15:44 -07:00
8c392f0019
fix(dreaming): default storage.mode to "separate" so phase blocks stop polluting daily memory files ( #66412 )
...
Merged via squash.
Prepared head SHA: 4b1c8ac4ec142179942+mjamiv@users.noreply.github.com >
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com >
Reviewed-by: @jalehman
2026-04-15 13:49:18 -07:00
a1b01f0281
fix(memory-core): skip dreaming transcript ingestion via session store ( #67315 )
...
Merged via squash.
Prepared head SHA: 87c09b2a75550978+jalehman@users.noreply.github.com >
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com >
Reviewed-by: @jalehman
2026-04-15 13:09:07 -07:00
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
88d3620a85
feat(github-copilot): add embedding provider for memory search ( #61718 )
...
Merged via squash.
Prepared head SHA: 05a78ce7f2676637+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
0c4e0d7030
memory: block dreaming self-ingestion ( #66852 )
...
Merged via squash.
Prepared head SHA: 4742656a0d5599352+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
8820a43818
fix(memory): preserve embedding proxy provider prefixes ( #66452 )
...
* fix(memory): preserve embedding proxy provider prefixes
* docs(changelog): fix embeddings entry
* Update CHANGELOG.md
2026-04-14 11:05:07 +01:00
2e1b5407dd
fix: preserve qmd command paths
2026-04-13 10:51:32 +01:00
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
067f27f6a2
fix: normalize stale qmd binary paths
2026-04-12 19:08:59 +01:00
15b86ac6d0
fix: narrow qmd defaults and clawblocker memory
2026-04-12 18:52:06 +01:00
847739d82c
Fix dreaming replay, repair polluted artifacts, and gate wiki tabs ( #65138 )
...
* fix(active-memory): preserve parent channel context for recall runs
* fix(active-memory): keep recall runs on the resolved channel
* fix(active-memory): prefer resolved recall channel over wrapper hints
* fix(active-memory): trust explicit recall channel hints
* fix(active-memory): rank recall channel fallbacks by trust
* Fix dreaming replay and recovery flows
* fix: prevent dreaming event loss and diary write races
* chore: add changelog entry for memory fixes
* fix: harden dreaming repair and diary writes
* fix: harden dreaming artifact archive naming
2026-04-12 00:25:11 -05:00
a45c4bebc5
test(memory): share backend config collection helpers
2026-04-12 05:16:46 +01:00
885209ed03
feat: default active memory QMD recall to search ( #65068 )
...
* feat(active-memory): default QMD recall to search
* feat(active-memory): surface search debug telemetry
* fix(active-memory): avoid forking qmd managers
2026-04-11 20:56:21 -05:00
74e7b8d47b
fix(cycles): bulk extract leaf type surfaces
2026-04-11 13:26:50 +01:00
d85b2a0e81
refactor: simplify core conversions
2026-04-11 01:17:51 +01:00
d236cb4680
chore: enable redundant type constituent checks
2026-04-10 21:23:40 +01:00
56fc20fb7c
test: align Vitest config path assertions
2026-04-10 15:49:37 +01:00
383ea34efe
fix(reply): keep resolved secret config stable ( #64249 )
...
Merged via squash.
Prepared head SHA: 973f863d8c132747814+mbelinky@users.noreply.github.com >
Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com >
Reviewed-by: @mbelinky
2026-04-10 14:56:30 +02:00
4bd720527b
fix(memory-lancedb): accept dreaming config for slot-owned memory ( #63874 )
...
Merged via squash.
Prepared head SHA: 9aaf29bd36132747814+mbelinky@users.noreply.github.com >
Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com >
Reviewed-by: @mbelinky
2026-04-09 23:03:53 +02:00
77e0e3bac5
fix(memory): split embedding provider types
2026-04-09 08:32:32 +01:00
b358db1775
refactor: dedupe embedding provider test fixtures
2026-04-08 15:58:47 +01:00
3174c6919d
refactor: dedupe gateway memory trimmed readers
2026-04-08 01:36:39 +01:00
88ac6f1194
refactor: dedupe remaining lowercase helpers
2026-04-07 22:57:52 +01:00
b6970865b6
refactor: dedupe path lowercase helpers
2026-04-07 22:57:52 +01:00
bfff74fb11
refactor: dedupe core lowercase helpers
2026-04-07 20:58:01 +01:00
9314bb7180
refactor: dedupe extension lowercase helpers
2026-04-07 15:12:32 +01:00
948d139399
refactor: dedupe lowercase helper readers
2026-04-07 15:12:32 +01:00
Peter Steinberger