liqiang
b119135836
Build latest book artifacts / build (push) Canceled after 0s
dependency resolution / resolve (3.11) (push) Canceled after 0s
dependency resolution / resolve (3.13) (push) Canceled after 0s
deploy-pages / build (push) Canceled after 0s
deploy-pages / deploy (push) Canceled after 0s
i18n consistency check / check (push) Canceled after 0s
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
web-search-agent tests / test (push) Canceled after 0s
web-search-agent tests / agentbook (push) Canceled after 0s
73 lines
2.7 KiB
JSON
73 lines
2.7 KiB
JSON
{
|
|
"experiment_id": "2-4",
|
|
"protocol_version": "1.0.0",
|
|
"frozen_on": "2026-07-30",
|
|
"authority": "book/chapter2.md:654",
|
|
"benchmark": "vendored tau-bench airline test split",
|
|
"provider": "OpenAI",
|
|
"model": "gpt-4o-mini",
|
|
"user_model": "gpt-4o-mini",
|
|
"temperature": 0,
|
|
"user_temperature": 0,
|
|
"seed": 20260730,
|
|
"task_ids": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9],
|
|
"trials_per_task": 1,
|
|
"max_agent_steps": 30,
|
|
"arms": {
|
|
"baseline": {
|
|
"tone": "professional neutral",
|
|
"wiki": "original structured rules",
|
|
"tool_descriptions": "complete"
|
|
},
|
|
"tone_trump": {
|
|
"tone": "exaggerated Trump-style",
|
|
"wiki": "original structured rules",
|
|
"tool_descriptions": "complete"
|
|
},
|
|
"tone_casual": {
|
|
"tone": "casual with emoji/slang",
|
|
"wiki": "original structured rules",
|
|
"tool_descriptions": "complete"
|
|
},
|
|
"wiki_random": {
|
|
"tone": "professional neutral",
|
|
"wiki": "same rules flattened and pre-shuffled",
|
|
"tool_descriptions": "complete"
|
|
},
|
|
"no_tool_desc": {
|
|
"tone": "professional neutral",
|
|
"wiki": "original structured rules",
|
|
"tool_descriptions": "all description fields blank"
|
|
},
|
|
"all_ablations": {
|
|
"tone": "casual with emoji/slang",
|
|
"wiki": "same rules flattened and pre-shuffled",
|
|
"tool_descriptions": "all description fields blank"
|
|
}
|
|
},
|
|
"metrics": [
|
|
"tau-bench objective reward/pass rate",
|
|
"agent steps and model calls",
|
|
"tool calls and environment tool errors",
|
|
"provider prompt/completion/total tokens",
|
|
"provider response IDs",
|
|
"LiteLLM native cost estimate"
|
|
],
|
|
"acceptance_gates": [
|
|
"all six arms run the same ten task IDs with the same seed and user simulator",
|
|
"each task is scored only by the vendored tau-bench objective environment",
|
|
"every agent and simulated-user model call is a real provider response with ID and usage",
|
|
"raw request messages, tools, response content/tool calls, usage, timings, and trajectories are retained",
|
|
"the randomized wiki contains the same experimental rule material in the frozen pre-generated order",
|
|
"the no-description arm preserves schemas while blanking every nested description",
|
|
"campaign completion is independent of whether the manuscript hypotheses win",
|
|
"historical percentage claims are not treated as reproduced unless this fixed campaign independently yields them",
|
|
"credential scan passes"
|
|
],
|
|
"hypotheses": {
|
|
"tone": "tone variants have limited effect on objective task success",
|
|
"organization": "randomizing instruction organization reduces success",
|
|
"tool_descriptions": "removing descriptions increases tool errors and reduces success"
|
|
}
|
|
}
|