mirror of
https://github.com/norandom/OpenUltraSAST.git
synced 2026-10-16 03:49:26 +00:00
search-with-proof: probe harness (3.2) and agent worker (group 5)
Probe runs each oracle toy pair with a real demo and two gaming demos, records image facts, RSS and disk, fails loudly if isolation is unavailable; dispatchable as an AX task. Worker: reason step without tools, explore tool loop whose run tool goes through the sandbox with a scrubbed env (model key absent), spend reserved before each call. Host probe: 5/5 real demos demonstrated, 10/10 gaming demos inconclusive. 89 tests. Co-Authored-By: Claude Opus 5.5 <[email protected]>
This commit is contained in:
co-authored by
Claude Opus 5.5
parent
a17a6afaf8
commit
0f74767db9
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"modules": 166,
|
||||
"modules": 168,
|
||||
"counts": {
|
||||
"load_bearing": 160,
|
||||
"load_bearing": 162,
|
||||
"standalone_capability": 6
|
||||
},
|
||||
"orphaned": [],
|
||||
@@ -638,6 +638,7 @@
|
||||
"push.runner",
|
||||
"push.snapshot",
|
||||
"push.vetoes",
|
||||
"search.worker",
|
||||
"tool_hunter"
|
||||
]
|
||||
},
|
||||
@@ -708,6 +709,7 @@
|
||||
"plane.budget",
|
||||
"plane.generate",
|
||||
"push.assistance",
|
||||
"search.worker",
|
||||
"tool_hunter"
|
||||
]
|
||||
},
|
||||
@@ -900,7 +902,8 @@
|
||||
"plane.tasks.verify",
|
||||
"plane.workspaces",
|
||||
"search.board",
|
||||
"search.coordinator"
|
||||
"search.coordinator",
|
||||
"search.worker"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -917,7 +920,8 @@
|
||||
"plane.generate",
|
||||
"plane.tasks.roles",
|
||||
"plane.tasks.verify",
|
||||
"search.coordinator"
|
||||
"search.coordinator",
|
||||
"search.worker"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -1235,6 +1239,7 @@
|
||||
"learn.compile",
|
||||
"learn.program",
|
||||
"model.endpoint",
|
||||
"search.worker",
|
||||
"tool_hunter"
|
||||
]
|
||||
},
|
||||
@@ -1247,6 +1252,7 @@
|
||||
"learn.compile",
|
||||
"learn.program",
|
||||
"model.endpoint",
|
||||
"search.worker",
|
||||
"tool_hunter"
|
||||
]
|
||||
},
|
||||
@@ -1561,7 +1567,8 @@
|
||||
"regress.safety",
|
||||
"regress.verdict",
|
||||
"search._sandbox",
|
||||
"search.verify"
|
||||
"search.verify",
|
||||
"search.worker"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -1606,7 +1613,9 @@
|
||||
"reason": "reachable from gate, map_gate, pair_gate, cli",
|
||||
"importers": [
|
||||
"search.coordinator",
|
||||
"search.verify"
|
||||
"search.probe",
|
||||
"search.verify",
|
||||
"search.worker"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -1614,7 +1623,9 @@
|
||||
"classification": "load_bearing",
|
||||
"reason": "reachable from gate, map_gate, pair_gate, cli",
|
||||
"importers": [
|
||||
"search.verify"
|
||||
"search.probe",
|
||||
"search.verify",
|
||||
"search.worker"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -1637,20 +1648,37 @@
|
||||
"module": "search.coordinator",
|
||||
"classification": "standalone_capability",
|
||||
"reason": "search-with-proof Req 1/2/4: injected search executor and offline board checkpoint inspector; agent worker pending",
|
||||
"importers": []
|
||||
"importers": [
|
||||
"search.worker"
|
||||
]
|
||||
},
|
||||
{
|
||||
"module": "search.oracles",
|
||||
"classification": "load_bearing",
|
||||
"reason": "python -m openultrasast.search.oracles",
|
||||
"importers": [
|
||||
"search.probe",
|
||||
"search.verify"
|
||||
]
|
||||
},
|
||||
{
|
||||
"module": "search.probe",
|
||||
"classification": "load_bearing",
|
||||
"reason": "python -m openultrasast.search.probe",
|
||||
"importers": []
|
||||
},
|
||||
{
|
||||
"module": "search.verify",
|
||||
"classification": "load_bearing",
|
||||
"reason": "python -m openultrasast.search.verify",
|
||||
"importers": [
|
||||
"search.probe"
|
||||
]
|
||||
},
|
||||
{
|
||||
"module": "search.worker",
|
||||
"classification": "load_bearing",
|
||||
"reason": "python -m openultrasast.search.worker",
|
||||
"importers": []
|
||||
},
|
||||
{
|
||||
|
||||
Reference in New Issue
Block a user