eric/scriptorium
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 6 Wiki Activity

Added support for the service_tier key in profiles

Browse Source
This commit is contained in:
Eric Rakestraw
2026-05-26 07:44:49 -05:00
parent 3f4fd230b9
commit c6c5e3cb69
16 changed files with 65 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/config.md
View File

@@ -157,6 +157,7 @@ max_tokens: 500
top_p: 1.0
timeout_seconds: 90
api_key_env: SCRIPTORIUM_API_KEY
service_tier: priority
```
Field reference:
@@ -168,6 +169,7 @@ Field reference:
- `max_tokens` (optional): `>= 0`
- `top_p` (optional): range `0..1`
- `timeout_seconds` (optional): `>= 0`
- `service_tier` (optional): provider-specific request tier such as OpenRouter `flex` or `priority`
- `reasoning_effort` (optional)
- `api_key_env` (optional)
- `extra_params` (optional map of strings)
@@ -181,7 +183,7 @@ Profile rules:
Current outbound request behavior:
- The OpenAI-compatible client currently serializes: `model`, `messages`, `temperature`, `max_tokens`, `top_p`, and optional `response_format` for `json_schema` prompts.
- The OpenAI-compatible client currently serializes: `model`, `messages`, `temperature`, `max_tokens`, `top_p`, `service_tier`, and optional `response_format` for `json_schema` prompts.
- `reasoning_effort` and `extra_params` are parsed and carried in effective settings, but are not currently serialized into outbound chat-completions requests.
## Schema Behavior