* feat(tencent): add bundled Tencent Cloud provider plugin (Tokenhub + Token Plan)
* fix(tencent): use provider-specific default model aliases
Both Tencent providers previously defaulted to the same alias "HY3 Preview",
which collides in buildModelAliasIndex (single alias map, keyed by normalized
alias). When both providers are onboarded, alias-based selection routed to
whichever provider was configured last.
Disambiguate the fallback aliases so resolution is deterministic regardless
of onboarding order:
- tencent-tokenhub -> "HY3 Preview (TokenHub)"
- tencent-token-plan -> "HY3 Preview (Token Plan)"
* docs(tencent): rename model to "Hy3 preview" and drop "HY3" family name
Align with the external-facing product name:
- model display name: "HY3 Preview" -> "Hy3 preview"
- family/umbrella references in docs and auth hints: "HY3" -> "Hy3 preview"
- internal cost constant: HY3_COST -> HY_COST
Model call id (hy3-preview) is unchanged.
* docs(tencent): use "Hy" as the family name in generic references
Keep specific model references as "Hy3 preview" (model catalog names,
onboarding aliases, Available-models docs entries), but switch
family/umbrella references to the plain "Hy" family name so future Hy
versions fit without doc churn:
- auth hints: "Hy via Tencent TokenHub Gateway" / "Hy via Token Plan"
- docs intro + Use-case table: "Tencent Hy models" / "call Hy via ..."
- models.ts pricing comment: "Hy pricing"
* feat(tencent): add tiered pricing for Hy3 preview model
---------
Co-authored-by: albertxyu <albertxyu@tencent.com>
Adds tiered model pricing support for cost tracking, keeps configured pricing ahead of cached catalog values, and includes latest Moonshot Kimi K2.6/K2.5 cost estimates.\n\nThanks @sliverp.
* 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>
Peter Steinberger