110 lines
3.6 KiB
JSON
110 lines
3.6 KiB
JSON
[
|
|
{
|
|
"name": "streaming_text",
|
|
"category": "baseline",
|
|
"description": "Validates streamed assistant text with no tool calls.",
|
|
"parity_refs": [
|
|
"Mock parity harness \u2014 milestone 1",
|
|
"Streaming response support validated by the mock parity harness"
|
|
]
|
|
},
|
|
{
|
|
"name": "read_file_roundtrip",
|
|
"category": "file-tools",
|
|
"description": "Exercises read_file tool execution and final assistant synthesis.",
|
|
"parity_refs": [
|
|
"Mock parity harness \u2014 milestone 1",
|
|
"File tools \u2014 harness-validated flows"
|
|
]
|
|
},
|
|
{
|
|
"name": "grep_chunk_assembly",
|
|
"category": "file-tools",
|
|
"description": "Validates grep_search partial JSON chunk assembly and follow-up synthesis.",
|
|
"parity_refs": [
|
|
"Mock parity harness \u2014 milestone 1",
|
|
"File tools \u2014 harness-validated flows"
|
|
]
|
|
},
|
|
{
|
|
"name": "write_file_allowed",
|
|
"category": "file-tools",
|
|
"description": "Confirms workspace-write write_file success and filesystem side effects.",
|
|
"parity_refs": [
|
|
"Mock parity harness \u2014 milestone 1",
|
|
"File tools \u2014 harness-validated flows"
|
|
]
|
|
},
|
|
{
|
|
"name": "write_file_denied",
|
|
"category": "permissions",
|
|
"description": "Confirms read-only mode blocks write_file with an error result.",
|
|
"parity_refs": [
|
|
"Mock parity harness \u2014 milestone 1",
|
|
"Permission enforcement across tool paths"
|
|
]
|
|
},
|
|
{
|
|
"name": "multi_tool_turn_roundtrip",
|
|
"category": "multi-tool-turns",
|
|
"description": "Executes read_file and grep_search in the same assistant turn before the final reply.",
|
|
"parity_refs": [
|
|
"Mock parity harness \u2014 milestone 2 (behavioral expansion)",
|
|
"Multi-tool assistant turns"
|
|
]
|
|
},
|
|
{
|
|
"name": "bash_stdout_roundtrip",
|
|
"category": "bash",
|
|
"description": "Validates bash execution and stdout roundtrip in danger-full-access mode.",
|
|
"parity_refs": [
|
|
"Mock parity harness \u2014 milestone 2 (behavioral expansion)",
|
|
"Bash tool \u2014 upstream has 18 submodules, Rust has 1:"
|
|
]
|
|
},
|
|
{
|
|
"name": "bash_permission_prompt_approved",
|
|
"category": "permissions",
|
|
"description": "Exercises workspace-write to bash escalation with a positive approval response.",
|
|
"parity_refs": [
|
|
"Mock parity harness \u2014 milestone 2 (behavioral expansion)",
|
|
"Permission enforcement across tool paths"
|
|
]
|
|
},
|
|
{
|
|
"name": "bash_permission_prompt_denied",
|
|
"category": "permissions",
|
|
"description": "Exercises workspace-write to bash escalation with a denied approval response.",
|
|
"parity_refs": [
|
|
"Mock parity harness \u2014 milestone 2 (behavioral expansion)",
|
|
"Permission enforcement across tool paths"
|
|
]
|
|
},
|
|
{
|
|
"name": "plugin_tool_roundtrip",
|
|
"category": "plugin-paths",
|
|
"description": "Loads an external plugin tool and executes it through the runtime tool registry.",
|
|
"parity_refs": [
|
|
"Mock parity harness \u2014 milestone 2 (behavioral expansion)",
|
|
"Plugin tool execution path"
|
|
]
|
|
},
|
|
{
|
|
"name": "auto_compact_triggered",
|
|
"category": "session-compaction",
|
|
"description": "Verifies auto-compact fires when cumulative input tokens exceed the configured threshold.",
|
|
"parity_refs": [
|
|
"Session compaction behavior matching",
|
|
"auto_compaction threshold from env"
|
|
]
|
|
},
|
|
{
|
|
"name": "token_cost_reporting",
|
|
"category": "token-usage",
|
|
"description": "Confirms usage token counts and estimated_cost appear in JSON output.",
|
|
"parity_refs": [
|
|
"Token counting / cost tracking accuracy"
|
|
]
|
|
}
|
|
]
|