😏
This commit is contained in:
@@ -0,0 +1,7 @@
|
||||
# Codex Harness Team
|
||||
|
||||
Use this featured profile for general engineering when ChatGPT-backed Codex access is the only required service. Sol owns the critical path and all writes; Luna scouts and Terra designs invariants in isolated native contexts; a fresh Sol context performs one mechanically supervised post-diff review.
|
||||
|
||||
The profile demonstrates that context isolation, parallel read work, role specialization, and adversarial review can add value without changing model makers. Native controls remain advisory, so both native workers are read-only. If the fresh MCP critic cannot run, the root continues with visibly reduced independent verification.
|
||||
|
||||
The fresh critic is the one supervised persistent app-server worker: the integrator can inspect, steer, interrupt, continue, finalize, fork, or cancel it, and its trace and partial evidence survive host loss. Luna and Terra remain native Codex participants; they intentionally demonstrate native context isolation and are not presented as mechanically app-server-controlled workers.
|
||||
@@ -0,0 +1 @@
|
||||
Review the integrated diff from a fresh context. Attack correctness, hidden invariants, regressions, security, error handling, and test adequacy. Ground every finding in an exact location or captured command. Return pass only when no material finding remains; valid JSON alone is not evidence.
|
||||
@@ -0,0 +1 @@
|
||||
Own the critical path and canonical writes. Launch the fast repository scout and invariant designer together only when their questions are independent, then immediately continue diagnosis or implementation. Native participants are advisory read-only contexts: inspect their evidence rather than assuming MMO can supervise every native action. After the integrated diff is stable, use the fresh MCP Sol critic once. Read and explicitly accept or reject that result. Resolve conflicts with repository evidence and tests, and wait only at real barriers.
|
||||
@@ -0,0 +1 @@
|
||||
Independently derive explicit invariants, failure cases, and discriminating tests from the task and repository. Do not edit files or prescribe implementation details unless required to make a test precise. Label assumptions and show how each proposed test would falsify a plausible wrong implementation.
|
||||
@@ -0,0 +1 @@
|
||||
Locate exact files, symbols, tests, and dependencies for the bounded question. Be fast and factual. Do not edit, design the full solution, or duplicate the root's implementation. Return evidence the root can inspect directly.
|
||||
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"title": "Native context evidence",
|
||||
"type": "object",
|
||||
"additionalProperties": false,
|
||||
"properties": {
|
||||
"scope": {"type": "string", "minLength": 1},
|
||||
"evidence": {
|
||||
"type": "array",
|
||||
"maxItems": 50,
|
||||
"items": {
|
||||
"type": "object",
|
||||
"additionalProperties": false,
|
||||
"properties": {
|
||||
"claim": {"type": "string", "minLength": 1},
|
||||
"location": {"type": "string", "minLength": 1},
|
||||
"observation": {"type": "string", "minLength": 1}
|
||||
},
|
||||
"required": ["claim", "location", "observation"]
|
||||
}
|
||||
},
|
||||
"invariants": {"type": "array", "items": {"type": "string"}, "maxItems": 30},
|
||||
"falsifying_tests": {"type": "array", "items": {"type": "string"}, "maxItems": 30},
|
||||
"uncertainties": {"type": "array", "items": {"type": "string"}, "maxItems": 30}
|
||||
},
|
||||
"required": ["scope", "evidence", "invariants", "falsifying_tests", "uncertainties"]
|
||||
}
|
||||
@@ -0,0 +1,44 @@
|
||||
{
|
||||
"title": "Fresh-context integrated diff review",
|
||||
"type": "object",
|
||||
"additionalProperties": false,
|
||||
"properties": {
|
||||
"verdict": {"type": "string", "enum": ["pass", "concerns", "fail", "blocked"]},
|
||||
"findings": {
|
||||
"type": "array",
|
||||
"maxItems": 50,
|
||||
"items": {
|
||||
"type": "object",
|
||||
"additionalProperties": false,
|
||||
"properties": {
|
||||
"severity": {"type": "string", "enum": ["critical", "high", "medium", "low", "note"]},
|
||||
"location": {"type": "string", "minLength": 1},
|
||||
"claim": {"type": "string", "minLength": 1},
|
||||
"evidence": {"type": "string", "minLength": 1},
|
||||
"correction": {"type": "string", "minLength": 1}
|
||||
},
|
||||
"required": ["severity", "location", "claim", "evidence", "correction"]
|
||||
}
|
||||
},
|
||||
"commands": {
|
||||
"type": "array",
|
||||
"maxItems": 20,
|
||||
"items": {
|
||||
"type": "object",
|
||||
"additionalProperties": false,
|
||||
"properties": {
|
||||
"command": {"type": "string", "minLength": 1},
|
||||
"exit_code": {"type": "integer"},
|
||||
"observation": {"type": "string", "minLength": 1}
|
||||
},
|
||||
"required": ["command", "exit_code", "observation"]
|
||||
}
|
||||
},
|
||||
"blockers": {"type": "array", "items": {"type": "string"}, "maxItems": 20}
|
||||
},
|
||||
"required": ["verdict", "findings", "commands", "blockers"],
|
||||
"allOf": [
|
||||
{"if": {"properties": {"verdict": {"const": "pass"}}, "required": ["verdict"]}, "then": {"properties": {"findings": {"maxItems": 0}, "blockers": {"maxItems": 0}}}},
|
||||
{"if": {"properties": {"verdict": {"const": "blocked"}}, "required": ["verdict"]}, "then": {"properties": {"blockers": {"minItems": 1}}}}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,105 @@
|
||||
schema_version = 8
|
||||
id = "codex-harness-team"
|
||||
version = "8.0.0"
|
||||
display_name = "Codex Harness Team"
|
||||
description = "A harness-first ChatGPT-only team combining fast native context isolation with a fresh mechanically supervised Sol critic."
|
||||
tags = ["engineering", "homogeneous-maker", "native", "hybrid", "featured"]
|
||||
maturity = "featured"
|
||||
root = "integrator"
|
||||
smoke = "smoke.toml"
|
||||
|
||||
[agents.integrator]
|
||||
kind = "root"
|
||||
description = "Critical-path Sol engineer, sole writer, and final integrator"
|
||||
model = "codex_chatgpt_builtin__gpt_5_6_sol"
|
||||
reasoning = "high"
|
||||
allowed_reasoning_efforts = ["medium", "high", "xhigh", "max"]
|
||||
execution_mode = "goal"
|
||||
goal_token_budget = 600000
|
||||
max_goal_token_budget = 1000000
|
||||
stall_warning_seconds = 3600
|
||||
finalization_grace_seconds = 1800
|
||||
plan_reasoning = "high"
|
||||
permissions = "workspace-write"
|
||||
can_spawn = ["repo_scout", "invariant_designer", "fresh_critic"]
|
||||
max_active = 1
|
||||
trust = "high"
|
||||
verification = "risk_based"
|
||||
attachments_allowed = true
|
||||
requires_modalities = ["text", "image"]
|
||||
instructions = "agents/integrator.md"
|
||||
|
||||
[agents.repo_scout]
|
||||
description = "Low-latency repository and test reconnaissance in a native context"
|
||||
model = "codex_chatgpt_builtin__gpt_5_6_luna"
|
||||
reasoning = "medium"
|
||||
allowed_reasoning_efforts = ["low", "medium", "high"]
|
||||
permissions = "read-only"
|
||||
backends = ["native"]
|
||||
can_spawn = []
|
||||
max_active = 1
|
||||
allowed_task_kinds = ["locate", "references", "test_analysis"]
|
||||
trust = "normal"
|
||||
verification = "material_changes"
|
||||
contract_enforcement = "warn"
|
||||
output_contract = "contracts/evidence.json"
|
||||
instructions = "agents/repo-scout.md"
|
||||
|
||||
[agents.invariant_designer]
|
||||
description = "Independent native invariant and test designer"
|
||||
model = "codex_chatgpt_builtin__gpt_5_6_terra"
|
||||
reasoning = "high"
|
||||
allowed_reasoning_efforts = ["medium", "high", "xhigh", "max"]
|
||||
permissions = "read-only"
|
||||
backends = ["native"]
|
||||
can_spawn = []
|
||||
max_active = 1
|
||||
allowed_task_kinds = ["analysis", "test_design", "specification"]
|
||||
trust = "high"
|
||||
verification = "material_changes"
|
||||
contract_enforcement = "warn"
|
||||
output_contract = "contracts/evidence.json"
|
||||
instructions = "agents/invariant-designer.md"
|
||||
|
||||
[agents.fresh_critic]
|
||||
description = "Fresh-context Sol critic after the root has an integrated diff"
|
||||
model = "codex_chatgpt_builtin__gpt_5_6_sol"
|
||||
reasoning = "high"
|
||||
allowed_reasoning_efforts = ["medium", "high", "xhigh", "max"]
|
||||
execution_mode = "turn"
|
||||
stall_warning_seconds = 1800
|
||||
finalization_grace_seconds = 900
|
||||
permissions = "read-only"
|
||||
backends = ["mcp"]
|
||||
can_spawn = []
|
||||
max_active = 1
|
||||
allowed_task_kinds = ["review", "verification"]
|
||||
trust = "adversarial_reviewer"
|
||||
verification = "root_adjudication"
|
||||
contract_enforcement = "strict"
|
||||
output_contract = "contracts/review.json"
|
||||
instructions = "agents/fresh-critic.md"
|
||||
|
||||
[agents.integrator.controls.repo_scout]
|
||||
actions = ["inspect", "trace", "steer", "interrupt", "pause", "continue", "detach", "stop", "finalize", "compact", "respond", "set_effort", "fork"]
|
||||
|
||||
[agents.integrator.controls.invariant_designer]
|
||||
actions = ["inspect", "trace", "steer", "interrupt", "pause", "continue", "detach", "stop", "finalize", "compact", "respond", "set_effort", "fork"]
|
||||
|
||||
[agents.integrator.controls.fresh_critic]
|
||||
actions = ["inspect", "trace", "steer", "interrupt", "pause", "continue", "detach", "stop", "finalize", "compact", "respond", "set_effort", "fork"]
|
||||
|
||||
[coordination]
|
||||
mode = "harness_native_first"
|
||||
orchestration = "hybrid"
|
||||
max_active_agents = 4
|
||||
max_depth = 1
|
||||
max_children_per_agent = 3
|
||||
max_active_writers = 0
|
||||
native_max_concurrent_threads = 2
|
||||
native_nested_delegation = false
|
||||
reject_ancestor_role = true
|
||||
wait_policy = "dependency_only"
|
||||
write_conflict_policy = "reject"
|
||||
contradiction_policy = "primary_evidence"
|
||||
result_visibility = "ancestors"
|
||||
@@ -0,0 +1,32 @@
|
||||
schema_version = 8
|
||||
|
||||
[[tasks]]
|
||||
agent = "integrator"
|
||||
task_kind = "analysis"
|
||||
task = "Inspect this profile read-only and explain what the native-first plus fresh-context critic topology demonstrates."
|
||||
mode = "read-only"
|
||||
wall_timeout_seconds = 600
|
||||
|
||||
[[tasks]]
|
||||
agent = "repo_scout"
|
||||
task_kind = "locate"
|
||||
task = "Locate the native-agent snapshot generation code and return exact repository evidence in the required JSON shape."
|
||||
backend = "native"
|
||||
mode = "read-only"
|
||||
wall_timeout_seconds = 600
|
||||
|
||||
[[tasks]]
|
||||
agent = "invariant_designer"
|
||||
task_kind = "test_design"
|
||||
task = "Derive two falsifying tests for the compiled profile concurrency limits and return the required evidence JSON."
|
||||
backend = "native"
|
||||
mode = "read-only"
|
||||
wall_timeout_seconds = 600
|
||||
|
||||
[[tasks]]
|
||||
agent = "fresh_critic"
|
||||
task_kind = "review"
|
||||
task = "Review profiles/codex-harness-team/profile.toml for one concrete inconsistency. Return only the required review JSON with exact evidence."
|
||||
backend = "mcp"
|
||||
mode = "read-only"
|
||||
wall_timeout_seconds = 900
|
||||
Reference in New Issue
Block a user