90 lines
3.1 KiB
TOML
90 lines
3.1 KiB
TOML
|
schema_version = 8
|
||
|
|
id = "competing-implementations-lab"
|
||
|
|
version = "8.0.0"
|
||
|
|
display_name = "Competing Implementations Lab"
|
||
|
|
description = "An experimental Terra root defines one objective contract while DeepSeek and Sonnet independently build competing isolated patches for evidence-based selection."
|
||
|
|
tags = ["implementation", "competition", "isolated-worktrees", "lab"]
|
||
|
|
maturity = "lab"
|
||
|
|
root = "experiment_judge"
|
||
|
|
smoke = "smoke.toml"
|
||
|
|
|
||
|
|
[agents.experiment_judge]
|
||
|
|
kind = "root"
|
||
|
|
description = "Objective-contract author, benchmark owner, canonical writer, and selection authority"
|
||
|
|
model = "codex_chatgpt_builtin__gpt_5_6_terra"
|
||
|
|
reasoning = "high"
|
||
|
|
allowed_reasoning_efforts = ["medium", "high", "xhigh", "max"]
|
||
|
|
execution_mode = "goal"
|
||
|
|
goal_token_budget = 400000
|
||
|
|
max_goal_token_budget = 600000
|
||
|
|
stall_warning_seconds = 3600
|
||
|
|
finalization_grace_seconds = 1800
|
||
|
|
plan_reasoning = "high"
|
||
|
|
permissions = "workspace-write"
|
||
|
|
can_spawn = ["deepseek_candidate", "sonnet_candidate"]
|
||
|
|
max_active = 1
|
||
|
|
trust = "high"
|
||
|
|
verification = "always"
|
||
|
|
instructions = "agents/experiment-judge.md"
|
||
|
|
|
||
|
|
[agents.deepseek_candidate]
|
||
|
|
description = "Independent DeepSeek implementation in an isolated worktree"
|
||
|
|
model = "opencode_go_openai_chat__deepseek_v4_pro"
|
||
|
|
reasoning = "high"
|
||
|
|
allowed_reasoning_efforts = ["high", "max"]
|
||
|
|
execution_mode = "goal"
|
||
|
|
goal_token_budget = 300000
|
||
|
|
max_goal_token_budget = 500000
|
||
|
|
stall_warning_seconds = 1800
|
||
|
|
finalization_grace_seconds = 1800
|
||
|
|
permissions = "workspace-write"
|
||
|
|
backends = ["mcp"]
|
||
|
|
can_spawn = []
|
||
|
|
max_active = 1
|
||
|
|
allowed_task_kinds = ["implement", "benchmark"]
|
||
|
|
trust = "high"
|
||
|
|
verification = "always"
|
||
|
|
contract_enforcement = "strict"
|
||
|
|
output_contract = "contracts/candidate.json"
|
||
|
|
instructions = "agents/candidate.md"
|
||
|
|
|
||
|
|
[agents.sonnet_candidate]
|
||
|
|
description = "Independent Sonnet implementation in a separate isolated worktree"
|
||
|
|
model = "opencode_zen_anthropic_messages__claude_sonnet_5"
|
||
|
|
reasoning = "high"
|
||
|
|
allowed_reasoning_efforts = ["medium", "high", "xhigh", "max"]
|
||
|
|
execution_mode = "goal"
|
||
|
|
goal_token_budget = 300000
|
||
|
|
max_goal_token_budget = 500000
|
||
|
|
stall_warning_seconds = 1800
|
||
|
|
finalization_grace_seconds = 1800
|
||
|
|
permissions = "workspace-write"
|
||
|
|
backends = ["mcp"]
|
||
|
|
can_spawn = []
|
||
|
|
max_active = 1
|
||
|
|
allowed_task_kinds = ["implement", "benchmark"]
|
||
|
|
trust = "high"
|
||
|
|
verification = "always"
|
||
|
|
contract_enforcement = "strict"
|
||
|
|
output_contract = "contracts/candidate.json"
|
||
|
|
instructions = "agents/candidate.md"
|
||
|
|
|
||
|
|
[agents.experiment_judge.controls.deepseek_candidate]
|
||
|
|
actions = ["inspect", "trace", "steer", "interrupt", "pause", "continue", "detach", "stop", "finalize", "compact", "respond", "set_effort", "fork"]
|
||
|
|
|
||
|
|
[agents.experiment_judge.controls.sonnet_candidate]
|
||
|
|
actions = ["inspect", "trace", "steer", "interrupt", "pause", "continue", "detach", "stop", "finalize", "compact", "respond", "set_effort", "fork"]
|
||
|
|
|
||
|
|
[coordination]
|
||
|
|
mode = "matched_competing_implementations_experiment"
|
||
|
|
orchestration = "mcp"
|
||
|
|
max_active_agents = 3
|
||
|
|
max_depth = 1
|
||
|
|
max_children_per_agent = 2
|
||
|
|
max_active_writers = 2
|
||
|
|
reject_ancestor_role = true
|
||
|
|
wait_policy = "dependency_only"
|
||
|
|
write_conflict_policy = "reject"
|
||
|
|
contradiction_policy = "primary_evidence"
|
||
|
|
result_visibility = "session"
|