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

Validate and compose provider endpoints

Browse Source
This commit is contained in:
Eric Rakestraw
2026-08-11 23:38:45 +00:00
parent c281f721bc
commit 3a43550f70
18 changed files with 448 additions and 84 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
docs/internal/llm.md
View File

@@ -25,16 +25,19 @@ and request precedence. The client uses its endpoint, credential metadata,
generation fields, and extra parameters. `BackendID` remains routing metadata
for the generation boundary and is not mapped into the provider payload.
Construction validates the configured base URL and clones any supplied
`http.Client` so Promptkit can apply its timeout default without mutating the
caller's client. Generation then:
Construction trims and validates a nonempty configured base URL and clones any
supplied `http.Client` so Promptkit can apply its timeout default without
mutating the caller's client. An empty configured base remains valid because a
resolved request target may supply the endpoint. Generation then:
1. validates shared execution-setting invariants and endpoint requirements;
1. validates shared execution-setting invariants and the final selected base
endpoint;
2. maps the internal request into the OpenAI-compatible chat payload;
3. validates and merges extra parameters;
4. resolves authentication;
5. performs the outbound request under the applicable deadlines; and
6. decodes the first response choice and token usage.
4. composes `/chat/completions` through parsed URL path operations;
5. resolves authentication;
6. performs the outbound request under the applicable deadlines; and
7. decodes the first response choice and token usage.
`internal/llm` owns the set of reserved OpenAI-compatible request fields used
when validating extra parameters. Backend registration consumes the same rule
@@ -65,6 +68,10 @@ configuration, invalid generation requests, request execution failures,
non-success provider statuses, and malformed successful responses. Provider
response bodies are not included in non-success errors.
Invalid nonempty configured endpoints are configuration failures. A missing or
invalid final selected endpoint is an invalid generation request and is
rejected before transport.
An `http.Client.Do` failure is represented by a redacting multi-cause error:
the package request-failure sentinel and the exact returned transport error are
both available through `errors.Is` and `errors.As`, while the rendered text
@@ -80,7 +87,8 @@ The
[OpenAI-compatible client tests](../../internal/llm/openai_compatible_client_test.go)
own configuration, client cloning, deterministic deadline precedence,
authentication, request and response mapping, malformed data, error identity,
cancellation, endpoint selection, and response-body suppression. The root
cancellation, endpoint selection and composition, pre-transport rejection, and
response-body suppression. The root
transport contract tests also verify that resolved backend settings reach this
client without serializing backend identity and that ordinary-run cancellation
retains its public generation and context identities. All use local test