Resolve profiles through built-in backends
This commit is contained in:
@@ -136,7 +136,7 @@ A profile supplies model execution settings:
|
||||
|
||||
```yaml
|
||||
id: local-summary
|
||||
endpoint: http://localhost:8000/v1
|
||||
backend: openrouter
|
||||
model: example-model
|
||||
temperature: 0.2
|
||||
max_tokens: 500
|
||||
@@ -144,7 +144,6 @@ top_p: 0.95
|
||||
timeout_seconds: 90
|
||||
service_tier: flex
|
||||
reasoning_effort: medium
|
||||
api_key_env: EXAMPLE_API_KEY
|
||||
extra_params:
|
||||
provider_option: enabled
|
||||
```
|
||||
@@ -152,7 +151,8 @@ extra_params:
|
||||
| Field | Required | Meaning |
|
||||
| --- | --- | --- |
|
||||
| `id` | yes | Non-empty profile identifier. IDs must be unique within one source. |
|
||||
| `endpoint` | yes | Non-empty OpenAI-compatible base URL, including an API version path when required. |
|
||||
| `backend` | unless `endpoint` is present | Backend registry ID. It is trimmed and registry membership is checked when the profile is prepared. |
|
||||
| `endpoint` | unless `backend` is present | Non-empty OpenAI-compatible base URL, including an API version path when required. When both connection fields are present, this overrides the backend endpoint without changing backend identity. |
|
||||
| `model` | yes | Non-empty provider model name. |
|
||||
| `temperature` | no | Number from 0 through 2. |
|
||||
| `max_tokens` | no | Integer zero or greater. |
|
||||
@@ -166,6 +166,9 @@ extra_params:
|
||||
Raw `api_key` is prohibited in profile YAML. Store only an environment
|
||||
variable name in `api_key_env`.
|
||||
|
||||
Promptkit does not infer a backend from a model or endpoint. Endpoint-only
|
||||
profiles remain supported and have no effective backend ID.
|
||||
|
||||
`extra_params` accepts null, booleans, finite numbers, strings, arrays, and
|
||||
objects with string keys. Keys must be non-empty. With the built-in client,
|
||||
they also cannot collide with the standard fields listed in the
|
||||
@@ -176,8 +179,9 @@ they also cannot collide with the standard fields listed in the
|
||||
Execution settings resolve in this order:
|
||||
|
||||
1. framework defaults;
|
||||
2. the selected profile; and
|
||||
3. request `ExecutionTargetOverride` values.
|
||||
2. the selected backend, when the profile names one;
|
||||
3. the selected profile; and
|
||||
4. request `ExecutionTargetOverride` values.
|
||||
|
||||
The framework defaults are:
|
||||
|
||||
@@ -194,8 +198,10 @@ explicit zero is preserved. In particular, an explicit request
|
||||
`timeout_seconds` of zero disables the per-generation deadline while leaving
|
||||
the caller context and transport timeout intact.
|
||||
|
||||
Non-empty request strings replace profile strings. A non-empty request
|
||||
`ExtraParams` map replaces the profile map rather than merging keys.
|
||||
Non-empty profile strings replace backend defaults, and non-empty request
|
||||
strings replace both. Backend identity is retained when either layer overrides
|
||||
the endpoint. A non-empty `extra_params` map at each layer replaces the entire
|
||||
lower-precedence map rather than merging keys.
|
||||
The [outbound integration contract](integrations/openai-compatible-chat.md)
|
||||
defines how the effective settings are serialized.
|
||||
|
||||
@@ -217,9 +223,11 @@ invalid matching profile is an error and does not fall back. In-memory
|
||||
|
||||
## Built-In Profile Catalog
|
||||
|
||||
Built-ins use the OpenRouter-compatible endpoint and
|
||||
`OPENROUTER_API_KEY`. A custom or in-memory profile with the same ID takes
|
||||
precedence.
|
||||
Every built-in selects the `openrouter` backend. The engine's built-in backend
|
||||
registry supplies `https://openrouter.ai/api/v1` and the environment-variable
|
||||
name `OPENROUTER_API_KEY`, so individual profiles contain only model and
|
||||
generation settings. A custom or in-memory profile with the same profile ID
|
||||
takes precedence.
|
||||
|
||||
| Provider | ID | Model |
|
||||
| --- | --- | --- |
|
||||
@@ -270,6 +278,10 @@ prompt, profile, schema, or example files:
|
||||
- a request can provide a direct `APIKey` or override `APIKeyEnv`; and
|
||||
- a direct request key takes precedence over environment lookup.
|
||||
|
||||
After a direct request key, the credential-source precedence is request
|
||||
`APIKeyEnv`, profile `api_key_env`, then the backend default. An in-memory
|
||||
profile with `APIKeyRequired` clears an inherited backend environment name and
|
||||
requires a direct key unless the request explicitly supplies `APIKeyEnv`.
|
||||
Promptkit validates required credential availability during preparation.
|
||||
Direct keys are excluded from JSON results and redacted by public string
|
||||
formatters. Environment-variable names may appear in prepared metadata, but
|
||||
|
||||
Reference in New Issue
Block a user