Kasper PeulenandClaude Fable 5.1 2f39040b45 chore(agent-eval): run the experiments on Opus 5.5 medium and GPT-6-Sol medium ...

Rename the four experiments after the models they pin, drop the Sonnet
tier with its EVAL_EXTRA_MODELS opt-in, and add the new models to the
pricing table with a per-model cache-read price for Opus 5.5.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

2026-09-28 14:12:42 +02:00

..

agentic-reference

Eval: Port reworked stats-stage skip handling and report rendering

2026-09-07 14:27:10 +00:00

mcp

Eval: Move agent-eval back to the repository root

2026-09-07 12:47:57 +02:00

post-analysis

Eval: Address usage commands to a shell inside agent-eval

2026-09-07 12:48:23 +02:00

utils

Eval: Style console output with node:util styleText, dropping colors.ts

2026-09-07 12:47:58 +02:00

experiment.ts

chore(agent-eval): run the experiments on Opus 5.5 medium and GPT-6-Sol medium

2026-09-28 14:12:42 +02:00

shell-parse.test.ts

agent-eval: Keep quoting context when parsing storybook tools arguments

2026-09-25 17:03:32 +02:00

shell-parse.ts

agent-eval: Keep quoting context when parsing storybook tools arguments

2026-09-25 17:03:32 +02:00

templates.test.ts

agent-eval: Name the plugin CLI channel after storybook tools in comments and README

2026-09-25 15:09:27 +02:00

templates.ts

agent-eval: Name the plugin CLI channel after storybook tools in comments and README

2026-09-25 15:09:27 +02:00

test-utils.test.ts

agent-eval: Parse storybook tools arguments exactly like the CLI

2026-09-25 16:39:53 +02:00

test-utils.ts

agent-eval: Render --json test-run output with only what the checks read

2026-09-25 15:09:27 +02:00

usage.test.ts

chore(agent-eval): run the experiments on Opus 5.5 medium and GPT-6-Sol medium

2026-09-28 14:12:42 +02:00

usage.ts

chore(agent-eval): run the experiments on Opus 5.5 medium and GPT-6-Sol medium

2026-09-28 14:12:42 +02:00