Conversation
ThomasK33
added this pull request to stack #4326
September 22, 2026 14:50
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
ThomasK33
force-pushed
the
thomask33/eval-l5-typesafe-provider
branch
from
September 22, 2026 14:55
dd0603b to
5e7da80
Compare
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: dd0603bcc7
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
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".
ThomasK33
added a commit
that referenced
this pull request
Sep 22, 2026
Codex round 1 on #4332: the TypeSafe construction branch passed the raw configured base URL to the SDK, so a hand-edited entry with surrounding whitespace produced `https://proxy/v1 /systemone`. The credential resolver already reads the (policy-forced or configured) URL trimmed — the same value auto model routing's evaluator uses — so the branch now uses that. Test: the whitespace-padded entry sends to the trimmed URL. _Generated with `xum` • Model: `coder:anthropic/claude-fable-5-1` • Thinking: `xhigh` • Cost: `$523.02`_ <!-- mux-attribution: model=coder:anthropic/claude-fable-5-1 thinking=xhigh costs=523.02 -->
Teach the workflow evaluate() resolver the reserved evaluation-only `typesafe` key that main already ships for auto model routing (no new PROVIDER_DEFINITIONS entry): shared resolveTypeSafeCredentials, a createTypeSafeAi construction branch, and the CLI's run-scoped providers copy keeps evaluation-only entries so a TypeSafe-only configuration reaches evaluate(). Offering `typesafe:jev-latest` in the Settings evaluation card moves with the card to its own PR (#4330 was reduced to timeline rendering). _Generated with `xum` • Model: `coder:anthropic/claude-fable-5-1` • Thinking: `xhigh` • Cost: `$511.72`_ <!-- mux-attribution: model=coder:anthropic/claude-fable-5-1 thinking=xhigh costs=511.72 -->
Codex round 1 on #4332: the TypeSafe construction branch passed the raw configured base URL to the SDK, so a hand-edited entry with surrounding whitespace produced `https://proxy/v1 /systemone`. The credential resolver already reads the (policy-forced or configured) URL trimmed — the same value auto model routing's evaluator uses — so the branch now uses that. Test: the whitespace-padded entry sends to the trimmed URL. _Generated with `xum` • Model: `coder:anthropic/claude-fable-5-1` • Thinking: `xhigh` • Cost: `$523.02`_ <!-- mux-attribution: model=coder:anthropic/claude-fable-5-1 thinking=xhigh costs=523.02 -->
ThomasK33
force-pushed
the
thomask33/eval-l5-typesafe-provider
branch
from
September 22, 2026 20:02
4864078 to
d92d312
Compare
This branch has not been deployed
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 join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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.
Summary
Fifth layer of the workflow
evaluate()primitive (stacked on #4330): the evaluation resolver, CLI and wire path learn the reserved evaluation-onlytypesafecredential key that main already ships for auto model routing, so anevaluate()step can run on TypeSafe AI with a TypeSafe-only configuration. No newPROVIDER_DEFINITIONSentry and no chat-picker exposure.Background
Plan layers: L2a #4321 → L2b #4322 → L3a #4324 → L3b #4329 (runner + CLI) → L4 #4330 (timeline rendering) → L5 (this PR) → L6 example + docs.
typesafeis not aProviderName: it is the credential key auto model routing uses for its evaluation model (DEFAULT_AUTO_MODEL_ROUTING_EVALUATION_MODEL), which is exactly whatevaluate()needs.Implementation
EVALUATION_PROVIDERSgainstypesafe(typed asProviderName | typeof TYPESAFE_PROVIDER_KEY);isEvaluationEligibleModelStringacceptstypesafe:<id>.resolveTypeSafeCredentials(shared with auto model routing,providerRequirements.ts) reads thetypesafeproviders entry orTYPESAFE_API_KEY_ENV_VARS;createEvaluationModelgets acreateTypeSafeAibranch. The pinned selection'srouteKindisdirect, and the route comparison is done as strings becauseresolveRoutereturns the key through an unchecked cast.ProviderNames were copied), soxum workflow run --evaluation-model typesafe:jev-latestworks with only a TypeSafe key configured.typesafe:jev-latestin the Settings evaluation card moves with the card to its own PR (see 🤖 feat(workflows): evaluate() step rendering in the workflow timeline and tool card #4330's scope note).Validation
providerModelFactory.test.ts(+3):typesafe:resolves on the direct route from the providers entry and from the env var; missing key →unauthorized; a chat model string is unaffected.evaluationModels.test.ts: eligibility oftypesafe:<id>and rejection of other non-ProviderNameprefixes.src/cli/workflow.test.ts(+1): a TypeSafe-only run config reachesevaluate()(red → green: before the copy fix the run failedunsupported-provider).tests/ipc/workflows/evaluateWire.test.ts(TEST_INTEGRATION=1, +2 lanes): real@ai-sdk/typesafe-aiadapter against the loopback fixture through ORPC — booleans travel asnoul, rounded distributions validate, confidence never reaches the result; a 401 is a provider failure and an interrupted hang aborts the request.make static-checkgreen.Risks
typesafe:-prefixed model strings take the new branch; chat providers and routing are untouched. Secrets: the key is read through the same credential resolver auto model routing already uses; nothing new is persisted.Generated with
xum• Model:coder:anthropic/claude-fable-5-1• Thinking:xhigh• Cost:$511.72