refactor(coderd/x/chatd): read the OpenAI transport from the model - #27704
Conversation
|
@codex review |
|
Codex Review: Didn't find any major issues. 🎉 Reviewed commit: ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. Codex can also answer questions or update the PR. Try commenting "@codex address that feedback". |
41114c9 to
52526f5
Compare
|
@codex review |
|
Codex Review: Didn't find any major issues. What shall we delve into next? Reviewed commit: ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. Codex can also answer questions or update the PR. Try commenting "@codex address that feedback". |
52526f5 to
ab47d63
Compare
|
@codex review |
|
Codex Review: Didn't find any major issues. Swish! Reviewed commit: ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. Codex can also answer questions or update the PR. Try commenting "@codex address that feedback". |
ab47d63 to
b94cf5c
Compare
|
@codex review |
|
Codex Review: Didn't find any major issues. Breezy! Reviewed commit: ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. Codex can also answer questions or update the PR. Try commenting "@codex address that feedback". |
b94cf5c to
b30188d
Compare
|
@codex review |
|
Codex Review: Didn't find any major issues. Swish! Reviewed commit: ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. Codex can also answer questions or update the PR. Try commenting "@codex address that feedback". |
b30188d to
928159c
Compare
|
@codex review |
|
Codex Review: Didn't find any major issues. Can't wait for the next one! Reviewed commit: ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. Codex can also answer questions or update the PR. Try commenting "@codex address that feedback". |
928159c to
78bbb7f
Compare
|
@codex review |
|
Codex Review: Didn't find any major issues. You're on a roll. Reviewed commit: ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. Codex can also answer questions or update the PR. Try commenting "@codex address that feedback". |
78bbb7f to
366afbe
Compare
|
@codex review |
|
Codex Review: Didn't find any major issues. What shall we delve into next? Reviewed commit: ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. Codex can also answer questions or update the PR. Try commenting "@codex address that feedback". |
366afbe to
87ae792
Compare
…del wrapper (#27703) Stacked on #27683. The OpenAI wire format is decided when the client is built, then thrown away, so downstream sites recompute it from `(provider, modelID, override)`. Any disagreement fails silently: the SDK type-asserts the concrete provider options struct and discards every OpenAI option, and text attachments are dropped because Responses natively accepts only images and PDFs. This adds `chatprovider.Model`, which pairs a fantasy client with the transport resolved from that client's own identity. Its fields are unexported and only the constructor sets the transport, deriving it from the client, so no caller can pick a transport that disagrees with the client it wraps. `chatopenai.Transport`'s zero value is invalid and panics when read rather than defaulting to a wire format, following the existing precedent for construction invariants. `Model` is threaded through construction, the resolve paths, and the four struct fields that store a model for later request preparation. Terminal call sites keep taking `fantasy.LanguageModel` and receive `LanguageModel()`, which avoids a new package edge from `chatloop` and `chatadvisor` into `chatprovider`. No decisions move yet. The consumers still recompute the transport, and `UsesResponsesAPI` now delegates to `TransportFor` so the two agree by construction. #27704 makes the consumers read it from the model. > Mux prepared this PR on Mike's behalf.
Provider option conversion, reasoning effort injection, and file part acceptance each recomputed the OpenAI wire format from (provider, modelID, override). Read it from chatprovider.Model instead, so a decision cannot drift from the client it was built for. ProviderOptionsFromChatConfig now takes a Transport, ApplyReasoningEffort takes a Model, and AcceptsFilePartMediaType becomes a Model method. UsesResponsesAPI and UsesResponsesOptions are deleted, and the override extraction is unexported and reachable only from ModelFromConfig, which now takes the model's ChatModelOpenAIConfig directly. The six scattered extractions at call sites are gone. That also resolves the computer-use mismatch. The computer-use model is a hardcoded default with no config of its own, and its client was built without an override while preparation applied the chat model's. Preparation now reads the computer-use model's own transport, so the two agree without the chat model's client settings following a different model.
87ae792 to
b62d8ea
Compare
Stacked on #27703.
Provider option conversion, reasoning effort injection, and file part acceptance each recomputed the OpenAI wire format from
(provider, modelID, override). They now read it fromchatprovider.Model, so a decision cannot drift from the client it was built for.ProviderOptionsFromChatConfigtakes aTransport,ApplyReasoningEfforttakes aModel, andAcceptsFilePartMediaTypebecomes aModelmethod.UsesResponsesAPIandUsesResponsesOptionsare deleted. The override extraction is unexported and reachable only fromModelFromConfig, which now takes the model'sChatModelOpenAIConfigdirectly, removing the six scattered extractions at call sites.That also resolves the computer-use mismatch. The computer-use model is a hardcoded default with no config row of its own: its client was built without an override while request preparation applied the chat model's. Preparation now reads the computer-use model's own transport, so the two agree without one model's client settings following a different model. Passing the chat model's
openai_configinto the computer-use client would have made them agree on the wrong value.TestModelTransportConsumersAgreepins the invariant in one test: the HTTP path the client actually hits, the concrete provider option struct type, the type created by reasoning effort, and text/image file acceptance.