a19d924797
fix(lmstudio): expose read-only reachability probe for guided setup ( #119134 )
...
* fix(lmstudio): expose read-only reachability probe for guided setup
* fix(lmstudio): route guided availability through public setup API
2026-08-20 00:32:05 -07:00
61eb7b932b
fix(agents): keep guided auth atomic through creation ( #126096 )
...
* fix(agents): make guided auth creation atomic
* fix(auth): keep staged agent workspace explicit
* test(auth): use managed temp directory
* fix(gateway): finish detached lifecycle dispatch migration
* fix(auth): carry staged workspace through providers
* test(auth): align mocks with batch persistence
2026-08-18 18:18:53 -07:00
568b920b21
feat(lint): enforce import ordering and deduplication ( #124730 )
...
* refactor(imports): dedupe and hoist imports
* feat(lint): enforce import/no-duplicates and import/first
2026-08-16 11:44:52 -07:00
6aa27d6ecd
refactor: retire August compat windows (embedding API, pi aliases, target parser, spawning hook, setup exports, WhatsApp inbound aliases) ( #124416 )
...
* refactor(plugin-sdk): retire embedded Pi aliases
* refactor(channels): retire explicit target compatibility
* refactor(plugins): retire subagent spawning hook
* refactor(plugin-sdk): retire shipped channel setup exports
* refactor(whatsapp): retire inbound callback aliases
Proof: focused build and WhatsApp E2E green; broad WhatsApp suite 188/189 files green. extensions/whatsapp/src/monitor-inbox.policy.test.ts flakes only in the parallel batch and passes isolated (10/10).
* refactor(plugin-sdk): retire memory embedding registrar
Migrate every bundled provider and manifest to registerEmbeddingProvider and contracts.embeddingProviders. Preserve memory-specific batching, local-service acquisition, index identity, and auto-selection through the canonical generic registry adapter, then remove the parallel registrar, registry, diagnostics, contracts, tests, and docs.
* chore(plugin-sdk): tighten retired surface budgets
Pin the post-retirement public SDK surface to 144 entrypoints, 4,312 exports, 2,564 callable exports, and 1,133 deprecated exports; agent-harness-runtime now permits exactly nine deprecated exports.
2026-08-15 22:43:47 -07:00
4fa7c243c6
fix(lmstudio): use only loaded models during setup
2026-08-02 22:45:09 +08:00
94b85cba5f
feat(setup): improve local model onboarding
2026-07-31 08:53:13 +08:00
98a066c90e
fix(agents): project llama.cpp-safe tool schemas ( #115598 )
...
Co-authored-by: Jithin Mohandas <mohandasjithin@gmail.com >
2026-07-29 01:33:32 -04:00
b6c3ff1aa1
fix(providers): make Ollama and LM Studio onboarding reliable ( #114405 )
...
* fix(ollama): persist local auth only after model selection
* fix(ollama): preserve native max thinking effort
* fix(lmstudio): preserve model tool capabilities
* fix(lmstudio): preserve configured model compatibility
* test(ollama): prove isolated onboarding and persisted gateway turns
* fix(ollama): fail closed on unresolved secret references
* fix(ollama): keep local onboarding model catalogs installed-only
* fix(onboard): preflight local models before reset
* fix(lmstudio): normalize unsupported tool schema patterns
* Revert "test(ollama): prove isolated onboarding and persisted gateway turns"
This reverts commit 1d333d4c67b6cf43c4def40f93075ac6bda34847.
* Revert "fix(ollama): preserve native max thinking effort"
This reverts commit 5d2600b0982e5bca73b1b5f8b42f660fa5f2473d.
* fix(lmstudio): preserve typed model compatibility
* test(lmstudio): await provider catalog augmentation
* test(ollama): narrow optional discovery auth fixture
* test(lmstudio): narrow reset validator registration
* fix(onboard): preserve verified local model lean defaults
* test(ollama): split non-interactive onboarding auth regressions
* fix(onboard): exclude hosted Ollama models from lean defaults
* test(onboard): prove local reset preflight order
2026-07-27 05:07:29 -04:00
da59d6ade9
feat(onboarding): detect local inference providers ( #108605 )
...
* feat(onboarding): detect local inference providers
* fix(onboarding): satisfy inference choice lint
* chore(i18n): refresh onboarding locales
* chore: leave changelog to release automation
* chore(plugin-sdk): refresh API baseline
* fix(onboarding): preserve source config during local activation
2026-07-15 22:46:16 -07:00
4fa5092cdc
docs: document small extension sources
2026-06-04 21:02:07 -04:00
bbc1772f4d
build: enable modern TypeScript module syntax
...
* build: enable modern TypeScript flags
* build: drop erasable TypeScript syntax flag
* build: keep legacy class field semantics
2026-05-25 10:10:12 +01:00
311e4608d1
feat: unify model catalog registration
2026-05-09 02:34:56 -04:00
252c63429e
fix(providers): map native reasoning efforts
2026-04-27 13:27:58 +01:00
45778a840d
fix(lmstudio): allow keyless local onboarding
2026-04-27 08:15:17 +01:00
77e6e4cf87
refactor: move memory embeddings into provider plugins
2026-04-17 02:57:18 +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
sunlit-deng