Skip to content

feat(codex): support reasoning effort targets config#1294

Merged
christso merged 1 commit into
mainfrom
feature/codex-reasoning-effort-docs_agents-bv-instructions
Jun 3, 2026
Merged

feat(codex): support reasoning effort targets config#1294
christso merged 1 commit into
mainfrom
feature/codex-reasoning-effort-docs_agents-bv-instructions

Conversation

@christso
Copy link
Copy Markdown
Collaborator

@christso christso commented Jun 3, 2026

Summary

Codex targets can now configure SDK reasoning effort from targets.yaml, so eval runs can use env-backed settings like CODEX_MODEL=gpt-5.5 with CODEX_REASONING_EFFORT=low. The wire field remains snake_case-only as model_reasoning_effort, resolves to internal modelReasoningEffort, and is forwarded into startThread with the SDK-supported enum values.

The Codex SDK dependency was stale in the lockfile at 0.104.0, even though the shell codex binary was 0.136.0. This PR bumps @openai/codex-sdk/bundled @openai/codex to 0.136.0 and makes the SDK provider honor the existing Codex executable target setting via codexPathOverride, so targets can use profile shims such as codex-eng.

The root Codex target now includes executable, model, and model_reasoning_effort env bindings, and the Codex target docs list all three fields.

Verification

  • bun test packages/core/test/evaluation/providers/targets.test.ts
  • bun test packages/core/test/evaluation/providers/codex-sdk.test.ts
  • bun test packages/core/test/evaluation/validation/targets-validator.test.ts
  • bunx biome check .agentv/targets.yaml apps/web/src/content/docs/docs/targets/coding-agents.mdx apps/cli/package.json packages/core/package.json packages/core/src/evaluation/providers/codex.ts packages/core/src/evaluation/providers/targets.ts packages/core/src/evaluation/providers/types.ts packages/core/src/evaluation/validation/targets-validator.ts packages/core/test/evaluation/providers/codex-sdk.test.ts packages/core/test/evaluation/providers/targets.test.ts packages/core/test/evaluation/validation/targets-validator.test.ts
  • bun run build

Smoke passed with:

AGENT_TARGET=codex LLM_TARGET=azure GRADER_TARGET=azure CODEX_EXECUTABLE=codex-eng CODEX_MODEL=gpt-5.5 CODEX_REASONING_EFFORT=low CODEX_LOG_DIR=.agentv/logs/codex bun apps/cli/src/cli.ts eval evals/self/azure-smoke.eval.yaml --target codex --workers 3

Result: PASS (2/2, mean 100%). Artifacts were written to:

  • .agentv/results/runs/default/2026-06-03T11-24-27-757Z
  • .agentv/results/runs/default/2026-06-03T11-24-27-757Z/index.jsonl
  • .agentv/results/otel-2026-06-03T11-24-27-757Z.json
  • .agentv/logs/codex/2026-06-03T11-24-28-160Z_codex_simple-math_attempt-1_985a8833.log
  • .agentv/logs/codex/2026-06-03T11-24-28-182Z_codex_capital-of-france_attempt-1_2faff0e9.log

Compound Engineering
GPT-5

@cloudflare-workers-and-pages
Copy link
Copy Markdown

cloudflare-workers-and-pages Bot commented Jun 3, 2026

Deploying agentv with  Cloudflare Pages  Cloudflare Pages

Latest commit: be81c07
Status: ✅  Deploy successful!
Preview URL: https://893e38a9.agentv.pages.dev
Branch Preview URL: https://feature-codex-reasoning-effo.agentv.pages.dev

View logs

@christso christso force-pushed the feature/codex-reasoning-effort-docs_agents-bv-instructions branch from ce93619 to be81c07 Compare June 3, 2026 11:31
@christso christso merged commit c2fdc4c into main Jun 3, 2026
4 checks passed
@christso christso deleted the feature/codex-reasoning-effort-docs_agents-bv-instructions branch June 3, 2026 13:20
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant