@mate-academy/llm-gateway 7.2.1 → 7.2.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +17 -0
- package/dist/LLMService.constants.d.ts +6073 -2623
- package/dist/providers/LLMAPI/LLMAPI.constants.d.ts +9470 -4295
- package/dist/providers/LLMAPI/LLMAPI.constants.js +2156 -1123
- package/dist/providers/LLMAPI/LLMAPI.constants.js.map +1 -1
- package/dist/providers/LLMAPI/LLMAPI.typedefs.d.ts +125 -56
- package/dist/providers/LLMAPI/LLMAPI.typedefs.js +138 -55
- package/dist/providers/LLMAPI/LLMAPI.typedefs.js.map +1 -1
- package/package.json +5 -1
package/README.md
CHANGED
|
@@ -1605,6 +1605,23 @@ describe('Custom LLM Integration Test', () => {
|
|
|
1605
1605
|
|
|
1606
1606
|
## Developer Guide
|
|
1607
1607
|
|
|
1608
|
+
### Syncing the LLMAPI model list
|
|
1609
|
+
|
|
1610
|
+
The `LLMAPIModelNames` enum and `LLMAPI_AVAILABLE_MODELS` map drift as
|
|
1611
|
+
LLMAPI adds/renames models. The pipeline in
|
|
1612
|
+
[`scripts/sync-llmapi-models/`](scripts/sync-llmapi-models/README.md)
|
|
1613
|
+
reconciles them against `GET https://api.llmapi.ai/v1/models` under these
|
|
1614
|
+
rules:
|
|
1615
|
+
|
|
1616
|
+
- Unscoped aliases are always present; scoped aliases (`openai/…`, `azure/…`,
|
|
1617
|
+
`nebius/…`) only when LLMAPI advertises 2+ providers for that model.
|
|
1618
|
+
- Existing entries are never modified — the pipeline only appends new
|
|
1619
|
+
entries and removes stale ones.
|
|
1620
|
+
- `maxOutputTokens` (the one field absent from the LLMAPI payload) is
|
|
1621
|
+
researched from provider docs via web-search sub-agents.
|
|
1622
|
+
|
|
1623
|
+
See the linked README for the full classify → research → apply workflow.
|
|
1624
|
+
|
|
1608
1625
|
### Pricing Model Architecture
|
|
1609
1626
|
|
|
1610
1627
|
The LLM Gateway uses a flexible function-based pricing model that supports different token types and caching:
|