mirror of
https://github.com/openclaw/openclaw.git
synced 2026-05-06 16:50:43 +00:00
feat(tencent): add bundled Tencent Cloud provider plugin (Tokenhub + Token Plan) (#68460)
* 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>
This commit is contained in:
@@ -1292,6 +1292,7 @@
|
||||
"providers/sglang",
|
||||
"providers/stepfun",
|
||||
"providers/synthetic",
|
||||
"providers/tencent",
|
||||
"providers/together",
|
||||
"providers/venice",
|
||||
"providers/vercel-ai-gateway",
|
||||
|
||||
90
docs/providers/tencent.md
Normal file
90
docs/providers/tencent.md
Normal file
@@ -0,0 +1,90 @@
|
||||
---
|
||||
title: "Tencent Cloud (TokenHub + Token Plan)"
|
||||
summary: "Tencent Cloud TokenHub and Token Plan setup (separate keys)"
|
||||
read_when:
|
||||
- You want to use Tencent Hy models with OpenClaw
|
||||
- You need the TokenHub API key or Token Plan (LKEAP) setup
|
||||
---
|
||||
|
||||
# Tencent Cloud (TokenHub + Token Plan)
|
||||
|
||||
The Tencent Cloud provider gives access to Tencent Hy models via two endpoints
|
||||
with separate API keys:
|
||||
|
||||
- **TokenHub** (`tencent-tokenhub`) — call Hy via Tencent TokenHub Gateway
|
||||
- **Token Plan** (`tencent-token-plan`) — call Hy via the LKEAP
|
||||
Token Plan endpoint
|
||||
|
||||
Both providers use OpenAI-compatible APIs.
|
||||
|
||||
## Quick start
|
||||
|
||||
TokenHub:
|
||||
|
||||
```bash
|
||||
openclaw onboard --auth-choice tokenhub-api-key
|
||||
```
|
||||
|
||||
Token Plan:
|
||||
|
||||
```bash
|
||||
openclaw onboard --auth-choice tencent-token-plan-api-key
|
||||
```
|
||||
|
||||
## Non-interactive example
|
||||
|
||||
```bash
|
||||
# TokenHub
|
||||
openclaw onboard --non-interactive \
|
||||
--mode local \
|
||||
--auth-choice tokenhub-api-key \
|
||||
--tokenhub-api-key "$TOKENHUB_API_KEY" \
|
||||
--skip-health \
|
||||
--accept-risk
|
||||
|
||||
# Token Plan
|
||||
openclaw onboard --non-interactive \
|
||||
--mode local \
|
||||
--auth-choice tencent-token-plan-api-key \
|
||||
--tencent-token-plan-api-key "$LKEAP_API_KEY" \
|
||||
--skip-health \
|
||||
--accept-risk
|
||||
```
|
||||
|
||||
## Providers and endpoints
|
||||
|
||||
| Provider | Endpoint | Use case |
|
||||
| -------------------- | ------------------------------------- | ----------------------- |
|
||||
| `tencent-tokenhub` | `tokenhub.tencentmaas.com/v1` | Hy via Tencent TokenHub |
|
||||
| `tencent-token-plan` | `api.lkeap.cloud.tencent.com/plan/v3` | Hy via LKEAP Token Plan |
|
||||
|
||||
Each provider uses its own API key. Setup registers only the selected provider.
|
||||
|
||||
## Available models
|
||||
|
||||
### tencent-tokenhub
|
||||
|
||||
- **hy3-preview** — Hy3 preview (256K context, reasoning, default)
|
||||
|
||||
### tencent-token-plan
|
||||
|
||||
- **hy3-preview** — Hy3 preview (256K context, reasoning, default)
|
||||
|
||||
## Notes
|
||||
|
||||
- TokenHub model refs use `tencent-tokenhub/<modelId>`. Token Plan model refs
|
||||
use `tencent-token-plan/<modelId>`.
|
||||
- Override pricing and context metadata in `models.providers` if needed.
|
||||
|
||||
## Environment note
|
||||
|
||||
If the Gateway runs as a daemon (launchd/systemd), make sure `TOKENHUB_API_KEY`
|
||||
or `LKEAP_API_KEY` is available to that process (for example, in
|
||||
`~/.openclaw/.env` or via `env.shellEnv`).
|
||||
|
||||
## Related documentation
|
||||
|
||||
- [OpenClaw Configuration](/configuration)
|
||||
- [Model Providers](/concepts/model-providers)
|
||||
- [Tencent TokenHub](https://cloud.tencent.com/document/product/1823/130050)
|
||||
- [Tencent Token Plan API](https://cloud.tencent.com/document/product/1823/130060)
|
||||
Reference in New Issue
Block a user