fix(coderd): send assigned chat model IDs verbatim - #28144
Merged
Conversation
Provider hints are now authoritative in model resolution, so no layer strips vendor prefixes from slash-namespaced model IDs. The save-time and request-time rejection of such models on OpenRouter-like openai-type providers guarded against the old stripping behavior and would now block working configurations.
Collaborator
Author
|
@codex review |
|
Codex Review: Didn't find any major issues. Bravo. 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". |
ibetitsmike
marked this pull request as ready for review
August 13, 2026 18:36
ThomasK33
approved these changes
Aug 13, 2026
Collaborator
Author
|
@codex review |
|
Codex Review: Didn't find any major issues. Bravo. 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". |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Fixes #27361 (CODAGT-832).
Problem
When an Agents model was configured under a non-gateway provider type (e.g. Anthropic or OpenAI) with a model ID whose first
/- or:-segment matched a built-in provider name (anthropic,azure,bedrock,google,openai,openai-compat,openrouter,vercel),chatprovider.ResolveModelWithProviderHintparsed it as a canonicalprovider/modelreference: the prefix was stripped and the request rerouted to the embedded provider type, overriding the provider the admin explicitly assigned. LLM gateways (e.g. LiteLLM) that namespace their catalogs asbedrock/...oranthropic/...behind an Anthropic- or OpenAI-type provider failed with an opaque upstream "Model not found", and escaping was impossible (bedrock/bedrock/...still rerouted).Fix
A valid provider hint is now authoritative:
ResolveModelWithProviderHintreturns the assigned provider and the verbatim model ID whenever a hint is present. Canonicalprovider/modelandprovider:modelparsing applies only to hint-less resolution paths. Every production call site derives the hint from the model config's explicitly assigned AI provider, so the assignment always wins.The save-time guard rejecting slash-namespaced models on OpenRouter-like providers typed as
openai(provider namedopenrouteror hosted atopenrouter.ai) is kept: that combination remains a misconfiguration whose correct fix is theopenrouterprovider type, and rejecting it early beats a confusing upstream error. Its wording no longer claims prefix stripping happens.Back-compat note
A pre-existing config that relied on stripping (e.g. model
anthropic/claude-xassigned to an Anthropic-type provider pointing at the real Anthropic API) now sends the prefixed ID verbatim and will get a clear upstream model-not-found error; the admin fixes it by editing the model ID. Nothing in the product ever suggested the canonical form for assigned models.Validation
TestResolveModelWithProviderHintupdated (hints preservebedrock/...,anthropic/...,provider:...verbatim; hint-less canonical parsing unchanged), red-green verified against the old ordering. Gateway and openai-type provider routing tests assert verbatim pass-through end to end../coderd/x/chatd/...suites plusTestCreateChatModelConfig,TestUpdateChatModelConfig, andTestValidateChatModelConfigProviderModelpass.anthropic/claude-haiku-4.5, with trace logs confirmingprovider=openai model=anthropic/claude-haiku-4.5(verbatim, not rerouted); gateway-type (openai-compat) routing withdeepseek/deepseek-v4-pro-0813and the model catalog/picker regressions pass.