Files
FarmHouse-Holdings/benchmarks/results/capability_qwen3.5_9b.json
T
fez5587andClaude Fable 5 fdf7a67db0 Add PRD, addendum, pre-implementation docs, ADRs, and capability-gate benchmarks
- PRD v1.0 plus addendum with environment reality checks (qwen3.5:9b pool, runaway protection, MVP trim)
- Pre-implementation checklist and GitHub integration plan
- ADR-001: build on Hermes Agent 0.19.0 as agent runtime; engine stays source of truth
- ADR-002: engine stack (FastAPI, Postgres, Redis, React)
- Benchmark suites + results: all five capability gates PASS, pool scaling 1.92x at 4 concurrent

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-03 22:58:52 -05:00

398 lines
8.4 KiB
JSON

{
"host": "http://172.19.96.1:11434",
"model": "qwen3.5:9b",
"json": {
"cases": [
{
"expected": "task.accepted",
"valid_json": true,
"schema_ok": true,
"type_ok": true,
"got": "task.accepted"
},
{
"expected": "task.progressed",
"valid_json": true,
"schema_ok": true,
"type_ok": true,
"got": "task.progressed"
},
{
"expected": "clarification.requested",
"valid_json": true,
"schema_ok": true,
"type_ok": false,
"got": "task.blocked"
},
{
"expected": "approval.requested",
"valid_json": true,
"schema_ok": true,
"type_ok": true,
"got": "approval.requested"
},
{
"expected": "task.completed",
"valid_json": true,
"schema_ok": true,
"type_ok": true,
"got": "task.completed"
},
{
"expected": "artifact.created",
"valid_json": true,
"schema_ok": true,
"type_ok": true,
"got": "artifact.created"
},
{
"expected": "task.blocked",
"valid_json": true,
"schema_ok": true,
"type_ok": true,
"got": "task.blocked"
},
{
"expected": "task.accepted",
"valid_json": true,
"schema_ok": true,
"type_ok": true,
"got": "task.accepted"
},
{
"expected": "task.progressed",
"valid_json": true,
"schema_ok": true,
"type_ok": true,
"got": "task.progressed"
},
{
"expected": "clarification.requested",
"valid_json": true,
"schema_ok": true,
"type_ok": true,
"got": "clarification.requested"
},
{
"expected": "task.accepted",
"valid_json": true,
"schema_ok": true,
"type_ok": true,
"got": "task.accepted"
},
{
"expected": "task.progressed",
"valid_json": true,
"schema_ok": true,
"type_ok": true,
"got": "task.progressed"
},
{
"expected": "clarification.requested",
"valid_json": true,
"schema_ok": true,
"type_ok": true,
"got": "clarification.requested"
},
{
"expected": "approval.requested",
"valid_json": true,
"schema_ok": true,
"type_ok": false,
"got": "task.completed"
},
{
"expected": "task.completed",
"valid_json": true,
"schema_ok": true,
"type_ok": true,
"got": "task.completed"
},
{
"expected": "artifact.created",
"valid_json": true,
"schema_ok": true,
"type_ok": true,
"got": "artifact.created"
},
{
"expected": "task.blocked",
"valid_json": true,
"schema_ok": true,
"type_ok": true,
"got": "task.blocked"
},
{
"expected": "task.accepted",
"valid_json": true,
"schema_ok": true,
"type_ok": true,
"got": "task.accepted"
},
{
"expected": "task.progressed",
"valid_json": true,
"schema_ok": true,
"type_ok": false,
"got": "task.blocked"
},
{
"expected": "clarification.requested",
"valid_json": true,
"schema_ok": true,
"type_ok": true,
"got": "clarification.requested"
}
],
"valid_pct": 100.0,
"correct_type_pct": 85.0
},
"tools": {
"cases": [
{
"expected": "search_code",
"called": "search_code",
"tool_ok": true,
"args_ok": true
},
{
"expected": "read_file",
"called": "read_file",
"tool_ok": true,
"args_ok": true
},
{
"expected": "run_tests",
"called": "run_tests",
"tool_ok": true,
"args_ok": true
},
{
"expected": "git_commit",
"called": "git_commit",
"tool_ok": true,
"args_ok": true
},
{
"expected": "http_request",
"called": "http_request",
"tool_ok": true,
"args_ok": true
},
{
"expected": "write_file",
"called": "write_file",
"tool_ok": true,
"args_ok": true
},
{
"expected": "ask_manager",
"called": "ask_manager",
"tool_ok": true,
"args_ok": true
},
{
"expected": "search_code",
"called": "search_code",
"tool_ok": true,
"args_ok": true
},
{
"expected": "read_file",
"called": "read_file",
"tool_ok": true,
"args_ok": true
},
{
"expected": "git_commit",
"called": "git_commit",
"tool_ok": true,
"args_ok": true
},
{
"expected": "run_tests",
"called": "run_tests",
"tool_ok": true,
"args_ok": true
},
{
"expected": "http_request",
"called": "http_request",
"tool_ok": true,
"args_ok": true
},
{
"expected": "search_code",
"called": "search_code",
"tool_ok": true,
"args_ok": true
},
{
"expected": "read_file",
"called": "read_file",
"tool_ok": true,
"args_ok": true
},
{
"expected": "run_tests",
"called": "run_tests",
"tool_ok": true,
"args_ok": true
},
{
"expected": "git_commit",
"called": "git_commit",
"tool_ok": true,
"args_ok": true
},
{
"expected": "http_request",
"called": "http_request",
"tool_ok": true,
"args_ok": true
},
{
"expected": "write_file",
"called": "write_file",
"tool_ok": true,
"args_ok": true
},
{
"expected": "ask_manager",
"called": "ask_manager",
"tool_ok": true,
"args_ok": true
},
{
"expected": "search_code",
"called": "search_code",
"tool_ok": true,
"args_ok": true
},
{
"expected": "read_file",
"called": "read_file",
"tool_ok": true,
"args_ok": true
},
{
"expected": "git_commit",
"called": "git_commit",
"tool_ok": true,
"args_ok": true
},
{
"expected": "run_tests",
"called": "run_tests",
"tool_ok": true,
"args_ok": true
},
{
"expected": "http_request",
"called": "http_request",
"tool_ok": true,
"args_ok": true
}
],
"tool_pct": 100.0,
"tool_and_args_pct": 100.0
},
"code": {
"cases": [
{
"name": "slugify",
"passed": true,
"error": ""
},
{
"name": "merge_intervals",
"passed": true,
"error": ""
},
{
"name": "parse_dotenv",
"passed": true,
"error": ""
},
{
"name": "fix_bug",
"passed": true,
"error": ""
},
{
"name": "retry_decorator",
"passed": true,
"error": ""
},
{
"name": "csv_group",
"passed": true,
"error": ""
}
],
"pass_pct": 100.0
},
"retention": {
"cases": [
{
"iteration": 1,
"ok": true,
"adversarial": false
},
{
"iteration": 2,
"ok": true,
"adversarial": false
},
{
"iteration": 3,
"ok": true,
"adversarial": false
},
{
"iteration": 4,
"ok": true,
"adversarial": false
},
{
"iteration": 5,
"ok": true,
"adversarial": true
},
{
"iteration": 6,
"ok": true,
"adversarial": false
},
{
"iteration": 7,
"ok": true,
"adversarial": true
},
{
"iteration": 8,
"ok": true,
"adversarial": false
},
{
"iteration": 9,
"ok": true,
"adversarial": false
},
{
"iteration": 10,
"ok": true,
"adversarial": false
}
],
"ok_pct": 100.0
},
"elapsed_s": 86.9,
"gates": {
"json_valid>=95": true,
"json_correct_type>=80": true,
"tools>=80": true,
"code>=50": true,
"retention>=80": true
}
}