docs(examples): add provider-owned batching example#1739
Merged
Conversation
Deploying agentv with
|
| Latest commit: |
c422af4
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://b186b33a.agentv.pages.dev |
| Branch Preview URL: | https://av-kfik56-provider-batch-exa.agentv.pages.dev |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
This adds a runnable replacement example for throughput-oriented CLI tools after runner-level Batch CLI deprecation: AgentV still invokes the provider once per eval case, while the CLI adapter queues those requests and flushes them as one provider-owned batch.
The example keeps batching out of eval runner config. The eval selects a normal provider label, the provider catalog uses a normal CLI provider without
batch_requestsorprovider_batching, and the adapter maps each queued request back to its own output/error identity using the AgentV{EVAL_ID}.Related: av-kfik.56
Validation
bun installbun run buildpassed after installing worktree dependencies; build emitted existing Rollup/Zod declaration warnings.bun apps/cli/src/cli.ts validate examples/features/provider-owned-batching/evals/suite.yamlbun examples/features/provider-owned-batching/scripts/smoke-provider-owned-batching.tsPROVIDER_OWNED_BATCH_STATE_DIR=/tmp/agentv-provider-owned-batching-eval-state bun apps/cli/src/cli.ts eval examples/features/provider-owned-batching/evals/suite.yaml --providers examples/features/provider-owned-batching/providers.yamltimeoutflush withrequest_idsticket-block,ticket-clear, andticket-review.bunx biome check examples/README.md examples/features/provider-owned-batchinggit diff --checkbun run validate:examplesstill fails on unrelated existingexamples/showcase/multi-model-benchmark/evals/benchmark.eval.yamlbecauseevaluate_options.repeatstill uses the removed object shape.This is example-only: no eval/provider execution behavior changed, so live provider/grader dogfood for core behavior is not applicable.
Post-Deploy Monitoring & Validation
No additional operational monitoring required. This PR adds a local deterministic example and does not change runtime service behavior.