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
Vincent Koc
10ee46c373
fix(plugins): extract provider config policy contexts
2026-04-12 03:45:35 +01:00
Vincent Koc
61da711b1a
fix(cycles): split provider runtime model types
2026-04-11 22:50:45 +01:00
Vincent Koc
a88fbf0f64
fix(cycles): split reply payload and option contracts
2026-04-11 22:24:55 +01:00
Vincent Koc
7f5a5a34db
fix(plugins): split hook contract types
2026-04-11 18:06:18 +01:00
Vincent Koc
796d4dfc49
fix(reply): split dispatcher shared types
2026-04-11 16:52:18 +01:00
Vincent Koc
97d1b88e3f
fix(cycles): split plugin runtime contract leaf types
2026-04-11 15:39:32 +01:00
Vincent Koc
74e7b8d47b
fix(cycles): bulk extract leaf type surfaces
2026-04-11 13:26:50 +01:00
Vincent Koc
7308e72fac
fix(cycles): continue seam extraction
2026-04-11 10:43:22 +01:00
Vincent Koc
7198a9f0ee
fix(cycles): reduce remaining static import seams
2026-04-11 02:46:41 +01:00
Vincent Koc
81235fd923
fix(cycles): split shared contract seams
2026-04-11 02:46:40 +01:00
Vincent Koc
95bc417944
fix(cycles): split residual shared type seams
2026-04-11 02:46:40 +01:00
Peter Steinberger
202f80792e
feat: add plugin text transforms
2026-04-11 02:17:39 +01:00
Peter Steinberger
31a0b7bd42
feat: add Codex app-server controls
2026-04-10 22:19:00 +01:00
Peter Steinberger
44ec4d05de
feat: add pluggable agent harness registry
2026-04-10 21:22:16 +01:00
Peter Steinberger
9fd08f9d0f
refactor: remove type-only import cycles
2026-04-10 15:14:27 +01:00
Pavan Kumar Gondhi
6517c700de
fix(nostr): require operator.admin scope for profile mutation routes [AI] ( #63553 )
...
* fix: address issue
* fix: address review feedback
* fix: address review feedback
* fix: finalize issue changes
* fix: address PR review feedback
* fix: address review-pr skill feedback
* fix: address PR review feedback
* fix: address review-pr skill feedback
* fix: address PR review feedback
* fix: address PR review feedback
* fix: address PR review feedback
* fix: address PR review feedback
* docs: add changelog entry for PR merge
2026-04-10 16:38:41 +05:30
Qasim Soomro
71617ef2f0
fix: allow private network provider request opt-in ( #63671 )
...
* feat(models): allow private network via models.providers.*.request
Add optional request.allowPrivateNetwork for operator-controlled self-hosted
OpenAI-compatible bases (LAN/overlay/split DNS). Plumbs the flag into
resolveProviderRequestPolicyConfig for streaming provider HTTP and OpenAI
responses WebSocket so SSRF policy can allow private-resolved model URLs
when explicitly enabled.
Updates zod schema, config help/labels, and unit tests for sanitize/merge.
* agents thread provider request into websocket stream
* fix(config): scope allowPrivateNetwork to model requests
* fix(agents): refresh websocket manager on request changes
* fix(agents): scope runtime private-network overrides to models
* fix: allow private network provider request opt-in (#63671 ) (thanks @qas)
---------
Co-authored-by: Ayaan Zaidi <hi@obviy.us >
2026-04-10 11:11:03 +05:30
Peter Steinberger
39cc6b7dc7
fix: stabilize character eval and Qwen model routing
2026-04-09 01:04:09 +01:00
ruclaw7
81969c7a91
fix: prefer codex gpt-5.4 runtime metadata ( #62694 ) (thanks @ruclaw7)
...
* Agents: prefer runtime codex gpt-5.4 metadata
* Agents: move codex gpt-5.4 override into provider hook
* fix: repair codex runtime preference hooks
* fix: use workspace dir for codex runtime preference
* test: cover codex workspace dir hook
* fix: prefer codex gpt-5.4 runtime metadata (#62694 ) (thanks @ruclaw7)
---------
Co-authored-by: Rudi Cilibrasi <cilibrar@gmail.com >
Co-authored-by: Rudi Cilibrasi <rudi@metagood.com >
Co-authored-by: Ayaan Zaidi <hi@obviy.us >
2026-04-08 08:16:23 +05:30
DhruvBhatia0
12331f0463
feat: add pluggable compaction provider registry ( #56224 )
...
Merged via squash.
Prepared head SHA: 0cc9cf3f30
Co-authored-by: DhruvBhatia0 <69252327+DhruvBhatia0@users.noreply.github.com >
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com >
Reviewed-by: @jalehman
2026-04-07 10:55:34 -07:00
pgondhi987
f0c9978030
fix(feishu): enforce workspace-only localRoots in docx upload actions [AI-assisted] ( #62369 )
...
* fix: address issue
* docs(changelog): add feishu workspace-only docx entry
---------
Co-authored-by: Devin Robison <drobison@nvidia.com >
2026-04-07 10:35:03 -06:00
Peter Steinberger
c2f9de3935
feat: unify live cli backend probes
2026-04-07 10:35:24 +01:00
Peter Steinberger
0af808b457
test: add cli backend live matrix metadata
2026-04-07 09:06:09 +01:00
Vincent Koc
947a43dae3
feat(memory-wiki): add belief-layer digests and compat migration
2026-04-07 08:56:24 +01:00
Peter Steinberger
1c41987876
refactor(auth): split auth state from auth store
2026-04-06 13:42:44 +01:00
Peter Steinberger
ef923805f5
Revert "refactor(cli): remove custom cli backends"
...
This reverts commit 6243806f7b .
2026-04-06 13:40:42 +01:00
Peter Steinberger
c39f061003
Revert "refactor(cli): remove bundled cli text providers"
...
This reverts commit 05d351c430 .
2026-04-06 13:40:41 +01:00
Peter Steinberger
7e0e2f81e5
refactor(auth): isolate external oauth overlays
2026-04-06 13:30:25 +01:00
Vincent Koc
5716d83336
feat(memory-wiki): restore llm wiki stack
2026-04-06 04:56:52 +01:00
Peter Steinberger
dc0ee2e178
feat: add music generation tooling
2026-04-06 01:47:14 +01:00
Peter Steinberger
471d056e2f
refactor: move browser runtime seams behind plugin metadata
2026-04-05 23:13:14 +01:00
Vincent Koc
94256ea1a0
revert(memory-wiki): back out llm wiki stack
2026-04-05 22:44:20 +01:00
Vincent Koc
2f72363984
feat(memory-core): bridge wiki corpus into memory tools
2026-04-05 22:34:02 +01:00
Vincent Koc
c11e7a7420
feat(memory-wiki): add prompt supplement integration
2026-04-05 22:34:01 +01:00
Peter Steinberger
05d351c430
refactor(cli): remove bundled cli text providers
2026-04-05 18:46:36 +01:00
Peter Steinberger
6243806f7b
refactor(cli): remove custom cli backends
2026-04-05 18:04:48 +01:00
Peter Steinberger
82ce30b789
feat(plugins): add reply dispatch hook
2026-04-05 16:11:31 +01:00
Peter Steinberger
40ffada812
refactor: keep plugin legacy repair in doctor
2026-04-05 15:44:53 +01:00
Peter Steinberger
629baf5fa7
refactor: move plugin setup and memory capabilities to registries
2026-04-05 14:53:53 +01:00
Peter Steinberger
760c4be438
feat(agents): add provider-owned system prompt contributions
2026-04-05 14:05:41 +01:00
Vincent Koc
4613f121ad
fix(agents): preserve native Anthropic replay tool ids ( #61254 )
...
* fix(agents): preserve native Anthropic replay tool ids
* docs(changelog): note native Anthropic replay ids
* fix(agents): preserve native Anthropic replay ids selectively
2026-04-05 09:53:52 +01:00
Peter Steinberger
e3ac0f43df
feat(qwen): add qwen provider and video generation
2026-04-04 19:34:56 +01:00
Peter Steinberger
fb0d60d7f3
fix: resolve MiniMax portal usage auth
2026-04-04 12:42:30 +01:00
Peter Steinberger
bbb0b574c4
refactor: centralize gateway method policy helpers
2026-04-04 20:07:18 +09:00
Peter Steinberger
b167ad052c
refactor(providers): move defaults and error policy into plugins
2026-04-04 07:43:14 +01:00
Peter Steinberger
ae7942bf5e
fix: prefer Claude CLI in Anthropic onboarding
2026-04-04 14:49:55 +09:00
Peter Steinberger
eb9051cc7c
refactor(openai): move native transport policy into extension
2026-04-04 04:27:14 +01:00
Peter Steinberger
a23ab9b906
refactor: move voice-call realtime providers into extensions
2026-04-04 12:07:23 +09:00
Peter Steinberger
58d2b9dd46
fix: add runtime model contextTokens caps
2026-04-04 09:36:53 +09:00