Compare commits
4 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
e28d16b324 | ||
|
|
bc32047610 | ||
|
|
3a24420d7d | ||
|
|
d14c1c5a56 |
@@ -1,139 +0,0 @@
|
||||
# Tool-Calling Benchmark Report
|
||||
|
||||
Generated: 2026-04-22 15:46 UTC
|
||||
Executed: 3 calls from a 100-call suite across 7 categories
|
||||
Models tested: nous:gia-3/gemma-4-31b, gemini:gemma-4-26b-it, nous:mimo-v2-pro
|
||||
|
||||
## Requested category mix
|
||||
|
||||
| Category | Target calls |
|
||||
|----------|--------------|
|
||||
| file | 20 |
|
||||
| terminal | 20 |
|
||||
| web | 15 |
|
||||
| code | 15 |
|
||||
| browser | 10 |
|
||||
| delegate | 10 |
|
||||
| mcp | 10 |
|
||||
|
||||
## Summary
|
||||
|
||||
| Metric | nous:gia-3/gemma-4-31b | gemini:gemma-4-26b-it | nous:mimo-v2-pro |
|
||||
|--------|---------|---------|---------|
|
||||
| Schema parse success | 0/1 (0%) | 0/1 (0%) | 0/1 (0%) |
|
||||
| Tool execution success | 0/1 (0%) | 0/1 (0%) | 0/1 (0%) |
|
||||
| Parallel tool success | 0/1 (0%) | 0/1 (0%) | 0/1 (0%) |
|
||||
| Avg latency (s) | 0.00 | 0.00 | 0.00 |
|
||||
| Avg tokens per call | 0.0 | 0.0 | 0.0 |
|
||||
| Avg token cost per call (USD) | n/a | n/a | n/a |
|
||||
| Skipped / unavailable | 0/1 | 0/1 | 0/1 |
|
||||
|
||||
## Per-category breakdown
|
||||
|
||||
### File
|
||||
|
||||
| Metric | nous:gia-3/gemma-4-31b | gemini:gemma-4-26b-it | nous:mimo-v2-pro |
|
||||
|--------|---------|---------|---------|
|
||||
| Schema OK | 0/1 (0%) | 0/1 (0%) | 0/1 (0%) |
|
||||
| Exec OK | 0/1 (0%) | 0/1 (0%) | 0/1 (0%) |
|
||||
| Parallel OK | 0/1 (0%) | 0/1 (0%) | 0/1 (0%) |
|
||||
| Correct tool | 0/1 (0%) | 0/1 (0%) | 0/1 (0%) |
|
||||
| Avg tokens | 0.0 | 0.0 | 0.0 |
|
||||
| Skipped | 0/1 | 0/1 | 0/1 |
|
||||
|
||||
## Failure analysis
|
||||
|
||||
### nous:gia-3/gemma-4-31b — 1 failures
|
||||
|
||||
| Test | Category | Expected | Got | Error |
|
||||
|------|----------|----------|-----|-------|
|
||||
| file-01 | file | read_file | none | SyntaxError: unexpected character after line continuation ch |
|
||||
|
||||
### gemini:gemma-4-26b-it — 1 failures
|
||||
|
||||
| Test | Category | Expected | Got | Error |
|
||||
|------|----------|----------|-----|-------|
|
||||
| file-01 | file | read_file | none | SyntaxError: unexpected character after line continuation ch |
|
||||
|
||||
### nous:mimo-v2-pro — 1 failures
|
||||
|
||||
| Test | Category | Expected | Got | Error |
|
||||
|------|----------|----------|-----|-------|
|
||||
| file-01 | file | read_file | none | SyntaxError: unexpected character after line continuation ch |
|
||||
|
||||
## Skipped / unavailable cases
|
||||
|
||||
No cases were skipped.
|
||||
|
||||
## Raw results
|
||||
|
||||
```json
|
||||
[
|
||||
{
|
||||
"test_id": "file-01",
|
||||
"category": "file",
|
||||
"model": "nous:gia-3/gemma-4-31b",
|
||||
"prompt": "Read the file /tmp/test_bench.txt and show me its contents.",
|
||||
"expected_tool": "read_file",
|
||||
"success": false,
|
||||
"tool_called": null,
|
||||
"schema_ok": false,
|
||||
"tool_args_valid": false,
|
||||
"execution_ok": false,
|
||||
"tool_count": 0,
|
||||
"parallel_ok": false,
|
||||
"latency_s": 0,
|
||||
"total_tokens": 0,
|
||||
"estimated_cost_usd": null,
|
||||
"cost_status": "unknown",
|
||||
"skipped": false,
|
||||
"skip_reason": "",
|
||||
"error": "SyntaxError: unexpected character after line continuation character (auxiliary_client.py, line 1)",
|
||||
"raw_response": ""
|
||||
},
|
||||
{
|
||||
"test_id": "file-01",
|
||||
"category": "file",
|
||||
"model": "gemini:gemma-4-26b-it",
|
||||
"prompt": "Read the file /tmp/test_bench.txt and show me its contents.",
|
||||
"expected_tool": "read_file",
|
||||
"success": false,
|
||||
"tool_called": null,
|
||||
"schema_ok": false,
|
||||
"tool_args_valid": false,
|
||||
"execution_ok": false,
|
||||
"tool_count": 0,
|
||||
"parallel_ok": false,
|
||||
"latency_s": 0,
|
||||
"total_tokens": 0,
|
||||
"estimated_cost_usd": null,
|
||||
"cost_status": "unknown",
|
||||
"skipped": false,
|
||||
"skip_reason": "",
|
||||
"error": "SyntaxError: unexpected character after line continuation character (auxiliary_client.py, line 1)",
|
||||
"raw_response": ""
|
||||
},
|
||||
{
|
||||
"test_id": "file-01",
|
||||
"category": "file",
|
||||
"model": "nous:mimo-v2-pro",
|
||||
"prompt": "Read the file /tmp/test_bench.txt and show me its contents.",
|
||||
"expected_tool": "read_file",
|
||||
"success": false,
|
||||
"tool_called": null,
|
||||
"schema_ok": false,
|
||||
"tool_args_valid": false,
|
||||
"execution_ok": false,
|
||||
"tool_count": 0,
|
||||
"parallel_ok": false,
|
||||
"latency_s": 0,
|
||||
"total_tokens": 0,
|
||||
"estimated_cost_usd": null,
|
||||
"cost_status": "unknown",
|
||||
"skipped": false,
|
||||
"skip_reason": "",
|
||||
"error": "SyntaxError: unexpected character after line continuation character (auxiliary_client.py, line 1)",
|
||||
"raw_response": ""
|
||||
}
|
||||
]
|
||||
```
|
||||
@@ -8,11 +8,10 @@ success rates, latency, and token costs.
|
||||
Usage:
|
||||
python3 benchmarks/tool_call_benchmark.py # full 100-call suite
|
||||
python3 benchmarks/tool_call_benchmark.py --limit 10 # quick smoke test
|
||||
python3 benchmarks/tool_call_benchmark.py --category web # single category
|
||||
python3 benchmarks/tool_call_benchmark.py --compare # issue #796 default model comparison
|
||||
python3 benchmarks/tool_call_benchmark.py --models nous # single model
|
||||
python3 benchmarks/tool_call_benchmark.py --category file # single category
|
||||
|
||||
Requires: hermes-agent venv activated, provider credentials for the selected models,
|
||||
and any optional browser/MCP/web backends you want to include in the run.
|
||||
Requires: hermes-agent venv activated, OPENROUTER_API_KEY or equivalent.
|
||||
"""
|
||||
|
||||
import argparse
|
||||
@@ -26,12 +25,10 @@ from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
from typing import Optional
|
||||
|
||||
# Ensure hermes-agent root is importable before local package imports.
|
||||
# Ensure hermes-agent root is importable
|
||||
REPO_ROOT = Path(__file__).resolve().parent.parent
|
||||
sys.path.insert(0, str(REPO_ROOT))
|
||||
|
||||
from agent.usage_pricing import CanonicalUsage, estimate_usage_cost
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Test Definitions
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -42,11 +39,9 @@ class ToolCall:
|
||||
id: str
|
||||
category: str
|
||||
prompt: str
|
||||
expected_tool: str # exact tool name we expect the model to call
|
||||
expected_params_check: str = "" # substring expected in JSON args
|
||||
expected_tool_prefix: str = "" # prefix match for dynamic surfaces like mcp_*
|
||||
expects_parallel: bool = False # whether this prompt should elicit multiple tool calls
|
||||
timeout: int = 30 # max seconds per call
|
||||
expected_tool: str # tool name we expect the model to call
|
||||
expected_params_check: str = "" # substring expected in JSON args
|
||||
timeout: int = 30 # max seconds per call
|
||||
notes: str = ""
|
||||
|
||||
|
||||
@@ -190,107 +185,85 @@ SUITE: list[ToolCall] = [
|
||||
ToolCall("deleg-10", "delegate", "Delegate: create a temp file /tmp/bench_deleg.txt with 'done'.",
|
||||
"delegate_task", "write"),
|
||||
|
||||
# ── Web Search & Extraction (15) ─────────────────────────────────────
|
||||
ToolCall("web-01", "web", "Search the web for Python dataclasses documentation.",
|
||||
"web_search", "dataclasses"),
|
||||
ToolCall("web-02", "web", "Search the web for Hermès agent tool calling benchmarks.",
|
||||
"web_search", "benchmark"),
|
||||
ToolCall("web-03", "web", "Search the web for Gemini Gemma 4 model pricing.",
|
||||
"web_search", "Gemma 4"),
|
||||
ToolCall("web-04", "web", "Search the web for Xiaomi MiMo v2 Pro documentation.",
|
||||
"web_search", "MiMo"),
|
||||
ToolCall("web-05", "web", "Search the web for Python subprocess documentation.",
|
||||
"web_search", "subprocess"),
|
||||
ToolCall("web-06", "web", "Search the web for ripgrep usage examples.",
|
||||
"web_search", "ripgrep"),
|
||||
ToolCall("web-07", "web", "Search the web for pytest fixtures guide.",
|
||||
"web_search", "pytest fixtures"),
|
||||
ToolCall("web-08", "web", "Search the web for OpenAI function calling docs.",
|
||||
"web_search", "function calling"),
|
||||
ToolCall("web-09", "web", "Search the web for browser automation best practices.",
|
||||
"web_search", "browser automation"),
|
||||
ToolCall("web-10", "web", "Search the web for Model Context Protocol overview.",
|
||||
"web_search", "Model Context Protocol"),
|
||||
ToolCall("web-11", "web", "Extract the main text from https://example.com.",
|
||||
"web_extract", "example.com"),
|
||||
ToolCall("web-12", "web", "Extract the page content from https://example.org.",
|
||||
"web_extract", "example.org"),
|
||||
ToolCall("web-13", "web", "Extract the title and body text from https://www.iana.org/domains/reserved.",
|
||||
"web_extract", "iana.org"),
|
||||
ToolCall("web-14", "web", "Extract content from https://httpbin.org/html.",
|
||||
"web_extract", "httpbin.org"),
|
||||
ToolCall("web-15", "web", "Extract the main content from https://www.python.org/.",
|
||||
"web_extract", "python.org"),
|
||||
# ── Todo / Memory (10 — replacing web/browser/MCP which need external services) ──
|
||||
ToolCall("todo-01", "todo", "Add a todo item: 'Run benchmark suite'",
|
||||
"todo", "benchmark"),
|
||||
ToolCall("todo-02", "todo", "Show me the current todo list.",
|
||||
"todo", ""),
|
||||
ToolCall("todo-03", "todo", "Mark the first todo item as completed.",
|
||||
"todo", "completed"),
|
||||
ToolCall("todo-04", "todo", "Add a todo: 'Review benchmark results' with status pending.",
|
||||
"todo", "Review"),
|
||||
ToolCall("todo-05", "todo", "Clear all completed todos.",
|
||||
"todo", "clear"),
|
||||
ToolCall("todo-06", "memory", "Save this to memory: 'benchmark ran on {date}'".format(
|
||||
date=datetime.now().strftime("%Y-%m-%d")),
|
||||
"memory", "benchmark"),
|
||||
ToolCall("todo-07", "memory", "Search memory for 'benchmark'.",
|
||||
"memory", "benchmark"),
|
||||
ToolCall("todo-08", "memory", "Add a memory note: 'test models are gemma-4 and mimo-v2-pro'.",
|
||||
"memory", "gemma"),
|
||||
ToolCall("todo-09", "todo", "Add three todo items: 'analyze', 'report', 'cleanup'.",
|
||||
"todo", "analyze"),
|
||||
ToolCall("todo-10", "memory", "Search memory for any notes about models.",
|
||||
"memory", "model"),
|
||||
|
||||
# ── Browser Automation (10) ───────────────────────────────────────────
|
||||
ToolCall("browser-01", "browser", "Open https://example.com in the browser.",
|
||||
"browser_navigate", "example.com"),
|
||||
ToolCall("browser-02", "browser", "Open https://www.python.org in the browser.",
|
||||
"browser_navigate", "python.org"),
|
||||
ToolCall("browser-03", "browser", "Open https://www.wikipedia.org in the browser.",
|
||||
"browser_navigate", "wikipedia.org"),
|
||||
ToolCall("browser-04", "browser", "Navigate the browser to https://example.org.",
|
||||
"browser_navigate", "example.org"),
|
||||
ToolCall("browser-05", "browser", "Go to https://httpbin.org/forms/post in the browser.",
|
||||
"browser_navigate", "httpbin.org/forms/post"),
|
||||
ToolCall("browser-06", "browser", "Open https://www.iana.org/domains/reserved in the browser.",
|
||||
"browser_navigate", "iana.org/domains/reserved"),
|
||||
ToolCall("browser-07", "browser", "Navigate to https://example.net in the browser.",
|
||||
"browser_navigate", "example.net"),
|
||||
ToolCall("browser-08", "browser", "Open https://developer.mozilla.org in the browser.",
|
||||
"browser_navigate", "developer.mozilla.org"),
|
||||
ToolCall("browser-09", "browser", "Navigate the browser to https://www.rfc-editor.org.",
|
||||
"browser_navigate", "rfc-editor.org"),
|
||||
ToolCall("browser-10", "browser", "Open https://www.gnu.org in the browser.",
|
||||
"browser_navigate", "gnu.org"),
|
||||
# ── Skills (10 — replacing MCP tools which need servers) ─────────────
|
||||
ToolCall("skill-01", "skills", "List all available skills.",
|
||||
"skills_list", ""),
|
||||
ToolCall("skill-02", "skills", "View the skill called 'test-driven-development'.",
|
||||
"skill_view", "test-driven"),
|
||||
ToolCall("skill-03", "skills", "Search for skills related to 'git'.",
|
||||
"skills_list", "git"),
|
||||
ToolCall("skill-04", "skills", "View the 'code-review' skill.",
|
||||
"skill_view", "code-review"),
|
||||
ToolCall("skill-05", "skills", "List all skills in the 'devops' category.",
|
||||
"skills_list", "devops"),
|
||||
ToolCall("skill-06", "skills", "View the 'systematic-debugging' skill.",
|
||||
"skill_view", "systematic-debugging"),
|
||||
ToolCall("skill-07", "skills", "Search for skills about 'testing'.",
|
||||
"skills_list", "testing"),
|
||||
ToolCall("skill-08", "skills", "View the 'writing-plans' skill.",
|
||||
"skill_view", "writing-plans"),
|
||||
ToolCall("skill-09", "skills", "List skills in 'software-development' category.",
|
||||
"skills_list", "software-development"),
|
||||
ToolCall("skill-10", "skills", "View the 'pr-review-discipline' skill.",
|
||||
"skill_view", "pr-review"),
|
||||
|
||||
# ── MCP Tools (10) ────────────────────────────────────────────────────
|
||||
ToolCall("mcp-01", "mcp", "Use an available MCP tool to list configured MCP resources or prompts.",
|
||||
"", "", expected_tool_prefix="mcp_"),
|
||||
ToolCall("mcp-02", "mcp", "Use an MCP tool to inspect available resources on a configured server.",
|
||||
"", "", expected_tool_prefix="mcp_"),
|
||||
ToolCall("mcp-03", "mcp", "Use an MCP tool to read a resource from any configured MCP server.",
|
||||
"", "", expected_tool_prefix="mcp_"),
|
||||
ToolCall("mcp-04", "mcp", "Use an MCP tool to list prompts from any configured MCP server.",
|
||||
"", "", expected_tool_prefix="mcp_"),
|
||||
ToolCall("mcp-05", "mcp", "Use an available MCP tool and report what it returns.",
|
||||
"", "", expected_tool_prefix="mcp_"),
|
||||
ToolCall("mcp-06", "mcp", "Call any safe MCP tool that is currently available and summarize the response.",
|
||||
"", "", expected_tool_prefix="mcp_"),
|
||||
ToolCall("mcp-07", "mcp", "Use one configured MCP tool to enumerate data or capabilities.",
|
||||
"", "", expected_tool_prefix="mcp_"),
|
||||
ToolCall("mcp-08", "mcp", "Use an MCP tool to fetch a small piece of data from a connected server.",
|
||||
"", "", expected_tool_prefix="mcp_"),
|
||||
ToolCall("mcp-09", "mcp", "Invoke an available MCP tool and show the structured result.",
|
||||
"", "", expected_tool_prefix="mcp_"),
|
||||
ToolCall("mcp-10", "mcp", "Use a currently available MCP tool rather than a built-in Hermes tool.",
|
||||
"", "", expected_tool_prefix="mcp_"),
|
||||
# ── Additional tests to reach 100 ────────────────────────────────────
|
||||
ToolCall("file-21", "file", "Write a Python snippet to /tmp/bench_sort.py that sorts [3,1,2].",
|
||||
"write_file", "bench_sort"),
|
||||
ToolCall("file-22", "file", "Read /tmp/bench_sort.py back and confirm it exists.",
|
||||
"read_file", "bench_sort"),
|
||||
ToolCall("file-23", "file", "Search for 'class' in all .py files in the benchmarks directory.",
|
||||
"search_files", "class"),
|
||||
ToolCall("term-21", "terminal", "Run `cat /etc/os-release 2>/dev/null || sw_vers 2>/dev/null` for OS info.",
|
||||
"terminal", "os"),
|
||||
ToolCall("term-22", "terminal", "Run `nproc 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null` for CPU count.",
|
||||
"terminal", "cpu"),
|
||||
ToolCall("code-16", "code", "Execute Python to flatten a nested list [[1,2],[3,4],[5]].",
|
||||
"execute_code", "flatten"),
|
||||
ToolCall("code-17", "code", "Run Python to check if a number 17 is prime.",
|
||||
"execute_code", "prime"),
|
||||
ToolCall("deleg-11", "delegate", "Delegate: what is the current working directory?",
|
||||
"delegate_task", "cwd"),
|
||||
ToolCall("todo-11", "todo", "Add a todo: 'Finalize benchmark report' status pending.",
|
||||
"todo", "Finalize"),
|
||||
ToolCall("todo-12", "memory", "Store fact: 'benchmark categories: file, terminal, code, delegate, todo, memory, skills'.",
|
||||
"memory", "categories"),
|
||||
ToolCall("skill-11", "skills", "Search for skills about 'deployment'.",
|
||||
"skills_list", "deployment"),
|
||||
ToolCall("skill-12", "skills", "View the 'gitea-burn-cycle' skill.",
|
||||
"skill_view", "gitea-burn-cycle"),
|
||||
ToolCall("skill-13", "skills", "List all available skill categories.",
|
||||
"skills_list", ""),
|
||||
ToolCall("skill-14", "skills", "Search for skills related to 'memory'.",
|
||||
"skills_list", "memory"),
|
||||
ToolCall("skill-15", "skills", "View the 'mimo-swarm' skill.",
|
||||
"skill_view", "mimo-swarm"),
|
||||
]
|
||||
# fmt: on
|
||||
|
||||
DEFAULT_COMPARE_MODELS = [
|
||||
"nous:gia-3/gemma-4-31b",
|
||||
"gemini:gemma-4-26b-it",
|
||||
"nous:mimo-v2-pro",
|
||||
]
|
||||
|
||||
ISSUE_796_CATEGORY_COUNTS = {
|
||||
"file": 20,
|
||||
"terminal": 20,
|
||||
"web": 15,
|
||||
"code": 15,
|
||||
"browser": 10,
|
||||
"delegate": 10,
|
||||
"mcp": 10,
|
||||
}
|
||||
|
||||
|
||||
def suite_category_counts() -> dict[str, int]:
|
||||
counts: dict[str, int] = {}
|
||||
for tc in SUITE:
|
||||
counts[tc.category] = counts.get(tc.category, 0) + 1
|
||||
return counts
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Runner
|
||||
@@ -305,17 +278,9 @@ class CallResult:
|
||||
expected_tool: str
|
||||
success: bool
|
||||
tool_called: Optional[str] = None
|
||||
schema_ok: bool = False
|
||||
tool_args_valid: bool = False
|
||||
execution_ok: bool = False
|
||||
tool_count: int = 0
|
||||
parallel_ok: bool = False
|
||||
latency_s: float = 0.0
|
||||
total_tokens: int = 0
|
||||
estimated_cost_usd: Optional[float] = None
|
||||
cost_status: str = "unknown"
|
||||
skipped: bool = False
|
||||
skip_reason: str = ""
|
||||
error: str = ""
|
||||
raw_response: str = ""
|
||||
|
||||
@@ -326,12 +291,7 @@ class ModelStats:
|
||||
total: int = 0
|
||||
schema_ok: int = 0 # model produced valid tool call JSON
|
||||
exec_ok: int = 0 # tool actually ran without error
|
||||
parallel_ok: int = 0 # calls with 2+ tool calls that executed successfully
|
||||
skipped: int = 0
|
||||
latency_sum: float = 0.0
|
||||
total_tokens: int = 0
|
||||
total_cost_usd: float = 0.0
|
||||
known_cost_calls: int = 0
|
||||
failures: list = field(default_factory=list)
|
||||
|
||||
@property
|
||||
@@ -346,10 +306,6 @@ class ModelStats:
|
||||
def avg_latency(self) -> float:
|
||||
return (self.latency_sum / self.total) if self.total else 0
|
||||
|
||||
@property
|
||||
def avg_cost_usd(self) -> Optional[float]:
|
||||
return (self.total_cost_usd / self.known_cost_calls) if self.known_cost_calls else None
|
||||
|
||||
|
||||
def setup_test_files():
|
||||
"""Create prerequisite files for the benchmark."""
|
||||
@@ -362,38 +318,20 @@ def setup_test_files():
|
||||
)
|
||||
|
||||
|
||||
def _matches_expected_tool(test_case: ToolCall, tool_name: str) -> bool:
|
||||
if test_case.expected_tool and tool_name == test_case.expected_tool:
|
||||
return True
|
||||
if test_case.expected_tool_prefix and tool_name.startswith(test_case.expected_tool_prefix):
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
def _resolve_unavailable_reason(test_case: ToolCall, valid_tool_names: set[str]) -> str:
|
||||
if test_case.expected_tool and test_case.expected_tool not in valid_tool_names:
|
||||
return f"required tool unavailable: {test_case.expected_tool}"
|
||||
if test_case.expected_tool_prefix and not any(
|
||||
name.startswith(test_case.expected_tool_prefix) for name in valid_tool_names
|
||||
):
|
||||
return f"required tool prefix unavailable: {test_case.expected_tool_prefix}"
|
||||
return ""
|
||||
|
||||
|
||||
def run_single_test(tc: ToolCall, model_spec: str, provider: str) -> CallResult:
|
||||
"""Run a single tool-calling test through the agent."""
|
||||
from run_agent import AIAgent
|
||||
|
||||
result = CallResult(
|
||||
test_id=tc.id,
|
||||
category=tc.category,
|
||||
model=model_spec,
|
||||
prompt=tc.prompt,
|
||||
expected_tool=tc.expected_tool or tc.expected_tool_prefix,
|
||||
expected_tool=tc.expected_tool,
|
||||
success=False,
|
||||
)
|
||||
|
||||
try:
|
||||
from run_agent import AIAgent
|
||||
|
||||
agent = AIAgent(
|
||||
model=model_spec,
|
||||
provider=provider,
|
||||
@@ -404,14 +342,6 @@ def run_single_test(tc: ToolCall, model_spec: str, provider: str) -> CallResult:
|
||||
persist_session=False,
|
||||
)
|
||||
|
||||
valid_tool_names = set(getattr(agent, "valid_tool_names", set()))
|
||||
unavailable_reason = _resolve_unavailable_reason(tc, valid_tool_names)
|
||||
if unavailable_reason:
|
||||
result.skipped = True
|
||||
result.skip_reason = unavailable_reason
|
||||
result.error = unavailable_reason
|
||||
return result
|
||||
|
||||
t0 = time.time()
|
||||
conv = agent.run_conversation(
|
||||
user_message=tc.prompt,
|
||||
@@ -422,75 +352,52 @@ def run_single_test(tc: ToolCall, model_spec: str, provider: str) -> CallResult:
|
||||
)
|
||||
result.latency_s = round(time.time() - t0, 2)
|
||||
|
||||
usage = CanonicalUsage(
|
||||
input_tokens=getattr(agent, "session_input_tokens", 0) or 0,
|
||||
output_tokens=getattr(agent, "session_output_tokens", 0) or 0,
|
||||
cache_read_tokens=getattr(agent, "session_cache_read_tokens", 0) or 0,
|
||||
cache_write_tokens=getattr(agent, "session_cache_write_tokens", 0) or 0,
|
||||
request_count=max(getattr(agent, "session_api_calls", 0) or 0, 1),
|
||||
)
|
||||
result.total_tokens = usage.total_tokens
|
||||
billed_model = model_spec.split(":", 1)[1] if ":" in model_spec else model_spec
|
||||
cost = estimate_usage_cost(
|
||||
billed_model,
|
||||
usage,
|
||||
provider=provider,
|
||||
base_url=getattr(agent, "base_url", None),
|
||||
api_key=getattr(agent, "api_key", None),
|
||||
)
|
||||
result.cost_status = cost.status
|
||||
result.estimated_cost_usd = float(cost.amount_usd) if cost.amount_usd is not None else None
|
||||
|
||||
messages = conv.get("messages", [])
|
||||
|
||||
tool_calls = []
|
||||
# Find the first assistant message with tool_calls
|
||||
tool_called = None
|
||||
tool_args_str = ""
|
||||
for msg in messages:
|
||||
if msg.get("role") == "assistant" and msg.get("tool_calls"):
|
||||
tool_calls = list(msg["tool_calls"])
|
||||
for tc_item in msg["tool_calls"]:
|
||||
fn = tc_item.get("function", {})
|
||||
tool_called = fn.get("name", "")
|
||||
tool_args_str = fn.get("arguments", "{}")
|
||||
break
|
||||
break
|
||||
|
||||
if tool_calls:
|
||||
result.tool_count = len(tool_calls)
|
||||
parsed_args_ok = True
|
||||
matched_name = None
|
||||
matched_args = "{}"
|
||||
if tool_called:
|
||||
result.tool_called = tool_called
|
||||
result.schema_ok = True
|
||||
|
||||
for tc_item in tool_calls:
|
||||
fn = tc_item.get("function", {})
|
||||
tool_name = fn.get("name", "")
|
||||
tool_args = fn.get("arguments", "{}")
|
||||
try:
|
||||
json.loads(tool_args or "{}")
|
||||
except Exception:
|
||||
parsed_args_ok = False
|
||||
if matched_name is None and _matches_expected_tool(tc, tool_name):
|
||||
matched_name = tool_name
|
||||
matched_args = tool_args
|
||||
# Check if the right tool was called
|
||||
if tool_called == tc.expected_tool:
|
||||
result.success = True
|
||||
|
||||
result.schema_ok = parsed_args_ok
|
||||
result.tool_called = matched_name or tool_calls[0].get("function", {}).get("name", "")
|
||||
|
||||
if matched_name:
|
||||
result.tool_args_valid = (
|
||||
tc.expected_params_check in matched_args if tc.expected_params_check else True
|
||||
)
|
||||
result.success = result.schema_ok and result.tool_args_valid
|
||||
# Check if args contain expected substring
|
||||
if tc.expected_params_check:
|
||||
result.tool_args_valid = tc.expected_params_check in tool_args_str
|
||||
else:
|
||||
result.tool_args_valid = True
|
||||
|
||||
# Check if tool executed (look for tool role message)
|
||||
for msg in messages:
|
||||
if msg.get("role") == "tool":
|
||||
content = msg.get("content", "")
|
||||
if content:
|
||||
if content and "error" not in content.lower()[:50]:
|
||||
result.execution_ok = True
|
||||
break
|
||||
|
||||
result.parallel_ok = result.tool_count > 1 and result.execution_ok
|
||||
elif content:
|
||||
result.execution_ok = True # got a response, even if error
|
||||
break
|
||||
else:
|
||||
# No tool call produced — still check if model responded
|
||||
final = conv.get("final_response", "")
|
||||
result.raw_response = final[:200] if final else ""
|
||||
|
||||
except Exception as e:
|
||||
result.error = f"{type(e).__name__}: {str(e)[:200]}"
|
||||
result.latency_s = round(time.time() - t0, 2) if 't0' in locals() else 0
|
||||
result.latency_s = round(time.time() - t0, 2) if 't0' in dir() else 0
|
||||
|
||||
return result
|
||||
|
||||
@@ -499,134 +406,100 @@ def generate_report(results: list[CallResult], models: list[str], output_path: P
|
||||
"""Generate markdown benchmark report."""
|
||||
now = datetime.now(timezone.utc).strftime("%Y-%m-%d %H:%M UTC")
|
||||
|
||||
stats: dict[str, ModelStats] = {m: ModelStats(model=m) for m in models}
|
||||
# Aggregate per model
|
||||
stats: dict[str, ModelStats] = {}
|
||||
for m in models:
|
||||
stats[m] = ModelStats(model=m)
|
||||
|
||||
by_category: dict[str, dict[str, list[CallResult]]] = {}
|
||||
|
||||
for r in results:
|
||||
s = stats[r.model]
|
||||
s.total += 1
|
||||
s.schema_ok += int(r.schema_ok)
|
||||
s.exec_ok += int(r.execution_ok)
|
||||
s.latency_sum += r.latency_s
|
||||
s.total_tokens += r.total_tokens
|
||||
if r.estimated_cost_usd is not None:
|
||||
s.total_cost_usd += r.estimated_cost_usd
|
||||
s.known_cost_calls += 1
|
||||
if r.skipped:
|
||||
s.skipped += 1
|
||||
else:
|
||||
s.schema_ok += int(r.schema_ok)
|
||||
s.exec_ok += int(r.execution_ok)
|
||||
s.parallel_ok += int(r.parallel_ok)
|
||||
if not r.success:
|
||||
s.failures.append(r)
|
||||
if not r.success:
|
||||
s.failures.append(r)
|
||||
|
||||
by_category.setdefault(r.category, {}).setdefault(r.model, []).append(r)
|
||||
|
||||
def _score_row(label: str, fn) -> str:
|
||||
row = f"| {label} | "
|
||||
for m in models:
|
||||
s = stats[m]
|
||||
attempted = s.total - s.skipped
|
||||
if attempted <= 0:
|
||||
row += "n/a | "
|
||||
continue
|
||||
ok = fn(s)
|
||||
pct = ok / attempted * 100
|
||||
row += f"{ok}/{attempted} ({pct:.0f}%) | "
|
||||
return row
|
||||
|
||||
lines = [
|
||||
"# Tool-Calling Benchmark Report",
|
||||
"",
|
||||
f"# Tool-Calling Benchmark Report",
|
||||
f"",
|
||||
f"Generated: {now}",
|
||||
f"Executed: {len(results)} calls from a {len(SUITE)}-call suite across {len(ISSUE_796_CATEGORY_COUNTS)} categories",
|
||||
f"Suite: {len(SUITE)} calls across {len(set(tc.category for tc in SUITE))} categories",
|
||||
f"Models tested: {', '.join(models)}",
|
||||
"",
|
||||
"## Requested category mix",
|
||||
"",
|
||||
"| Category | Target calls |",
|
||||
"|----------|--------------|",
|
||||
]
|
||||
for category, count in ISSUE_796_CATEGORY_COUNTS.items():
|
||||
lines.append(f"| {category} | {count} |")
|
||||
|
||||
lines.extend([
|
||||
"",
|
||||
"## Summary",
|
||||
"",
|
||||
f"",
|
||||
f"## Summary",
|
||||
f"",
|
||||
f"| Metric | {' | '.join(models)} |",
|
||||
f"|--------|{'|'.join('---------' for _ in models)}|",
|
||||
_score_row("Schema parse success", lambda s: s.schema_ok),
|
||||
_score_row("Tool execution success", lambda s: s.exec_ok),
|
||||
_score_row("Parallel tool success", lambda s: s.parallel_ok),
|
||||
])
|
||||
]
|
||||
|
||||
row = "| Avg latency (s) | "
|
||||
for m in models:
|
||||
row += f"{stats[m].avg_latency:.2f} | "
|
||||
lines.append(row)
|
||||
|
||||
row = "| Avg tokens per call | "
|
||||
for m in models:
|
||||
total = stats[m].total
|
||||
avg_tokens = stats[m].total_tokens / total if total else 0
|
||||
row += f"{avg_tokens:.1f} | "
|
||||
lines.append(row)
|
||||
|
||||
row = "| Avg token cost per call (USD) | "
|
||||
for m in models:
|
||||
avg_cost = stats[m].avg_cost_usd
|
||||
row += (f"{avg_cost:.6f} | " if avg_cost is not None else "n/a | ")
|
||||
lines.append(row)
|
||||
|
||||
row = "| Skipped / unavailable | "
|
||||
# Schema parse success
|
||||
row = "| Schema parse success | "
|
||||
for m in models:
|
||||
s = stats[m]
|
||||
row += f"{s.skipped}/{s.total} | "
|
||||
row += f"{s.schema_ok}/{s.total} ({s.schema_pct:.0f}%) | "
|
||||
lines.append(row)
|
||||
|
||||
# Tool execution success
|
||||
row = "| Tool execution success | "
|
||||
for m in models:
|
||||
s = stats[m]
|
||||
row += f"{s.exec_ok}/{s.total} ({s.exec_pct:.0f}%) | "
|
||||
lines.append(row)
|
||||
|
||||
# Correct tool selected
|
||||
row = "| Correct tool selected | "
|
||||
for m in models:
|
||||
s = stats[m]
|
||||
correct = sum(1 for r in results if r.model == m and r.success)
|
||||
pct = (correct / s.total * 100) if s.total else 0
|
||||
row += f"{correct}/{s.total} ({pct:.0f}%) | "
|
||||
lines.append(row)
|
||||
|
||||
# Avg latency
|
||||
row = "| Avg latency (s) | "
|
||||
for m in models:
|
||||
s = stats[m]
|
||||
row += f"{s.avg_latency:.2f} | "
|
||||
lines.append(row)
|
||||
|
||||
lines.append("")
|
||||
|
||||
lines.append("## Per-category breakdown")
|
||||
# Per-category breakdown
|
||||
lines.append("## Per-Category Breakdown")
|
||||
lines.append("")
|
||||
|
||||
for cat in sorted(by_category.keys()):
|
||||
lines.append(f"### {cat.title()}")
|
||||
lines.append("")
|
||||
lines.append(f"| Metric | {' | '.join(models)} |")
|
||||
lines.append(f"|--------|{'|'.join('---------' for _ in models)}|")
|
||||
|
||||
cat_data = by_category[cat]
|
||||
for metric_name, fn in [
|
||||
("Schema OK", lambda r: r.schema_ok),
|
||||
("Exec OK", lambda r: r.execution_ok),
|
||||
("Parallel OK", lambda r: r.parallel_ok),
|
||||
("Correct tool", lambda r: r.success),
|
||||
]:
|
||||
row = f"| {metric_name} | "
|
||||
for m in models:
|
||||
results_m = by_category[cat].get(m, [])
|
||||
attempted = [r for r in results_m if not r.skipped]
|
||||
if not attempted:
|
||||
row += "n/a | "
|
||||
continue
|
||||
ok = sum(1 for r in attempted if fn(r))
|
||||
pct = ok / len(attempted) * 100
|
||||
row += f"{ok}/{len(attempted)} ({pct:.0f}%) | "
|
||||
results_m = cat_data.get(m, [])
|
||||
total = len(results_m)
|
||||
ok = sum(1 for r in results_m if fn(r))
|
||||
pct = (ok / total * 100) if total else 0
|
||||
row += f"{ok}/{total} ({pct:.0f}%) | "
|
||||
lines.append(row)
|
||||
|
||||
row = "| Avg tokens | "
|
||||
for m in models:
|
||||
results_m = by_category[cat].get(m, [])
|
||||
avg_tokens = sum(r.total_tokens for r in results_m) / len(results_m) if results_m else 0
|
||||
row += f"{avg_tokens:.1f} | "
|
||||
lines.append(row)
|
||||
|
||||
row = "| Skipped | "
|
||||
for m in models:
|
||||
results_m = by_category[cat].get(m, [])
|
||||
skipped = sum(1 for r in results_m if r.skipped)
|
||||
row += f"{skipped}/{len(results_m)} | "
|
||||
lines.append(row)
|
||||
lines.append("")
|
||||
|
||||
lines.append("## Failure analysis")
|
||||
# Failure analysis
|
||||
lines.append("## Failure Analysis")
|
||||
lines.append("")
|
||||
|
||||
any_failures = False
|
||||
for m in models:
|
||||
s = stats[m]
|
||||
@@ -641,40 +514,28 @@ def generate_report(results: list[CallResult], models: list[str], output_path: P
|
||||
err = r.error or "wrong tool"
|
||||
lines.append(f"| {r.test_id} | {r.category} | {r.expected_tool} | {got} | {err[:60]} |")
|
||||
lines.append("")
|
||||
|
||||
if not any_failures:
|
||||
lines.append("No model failures detected.")
|
||||
lines.append("No failures detected.")
|
||||
lines.append("")
|
||||
|
||||
skipped_results = [r for r in results if r.skipped]
|
||||
lines.append("## Skipped / unavailable cases")
|
||||
lines.append("")
|
||||
if skipped_results:
|
||||
lines.append("| Test | Model | Category | Reason |")
|
||||
lines.append("|------|-------|----------|--------|")
|
||||
for r in skipped_results:
|
||||
lines.append(f"| {r.test_id} | {r.model} | {r.category} | {r.skip_reason[:80]} |")
|
||||
else:
|
||||
lines.append("No cases were skipped.")
|
||||
lines.append("")
|
||||
|
||||
lines.append("## Raw results")
|
||||
# Raw results JSON
|
||||
lines.append("## Raw Results")
|
||||
lines.append("")
|
||||
lines.append("```json")
|
||||
lines.append(json.dumps([asdict(r) for r in results], indent=2, default=str))
|
||||
lines.append("```")
|
||||
|
||||
report = "\n".join(lines)
|
||||
output_path.write_text(report, encoding="utf-8")
|
||||
output_path.write_text(report)
|
||||
return report
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(description="Tool-calling benchmark")
|
||||
parser.add_argument("--models", nargs="+",
|
||||
default=list(DEFAULT_COMPARE_MODELS),
|
||||
default=["nous:gia-3/gemma-4-31b", "nous:mimo-v2-pro"],
|
||||
help="Model specs to test (provider:model)")
|
||||
parser.add_argument("--compare", action="store_true",
|
||||
help="Use the issue #796 default comparison set")
|
||||
parser.add_argument("--limit", type=int, default=0,
|
||||
help="Run only first N tests (0 = all)")
|
||||
parser.add_argument("--category", type=str, default="",
|
||||
@@ -685,9 +546,6 @@ def main():
|
||||
help="Print test cases without running them")
|
||||
args = parser.parse_args()
|
||||
|
||||
if args.compare:
|
||||
args.models = list(DEFAULT_COMPARE_MODELS)
|
||||
|
||||
# Filter suite
|
||||
suite = SUITE[:]
|
||||
if args.category:
|
||||
|
||||
@@ -1,115 +0,0 @@
|
||||
"""Tests for Issue #796 tool-calling benchmark coverage and reporting."""
|
||||
|
||||
import sys
|
||||
from pathlib import Path
|
||||
from types import SimpleNamespace
|
||||
from unittest.mock import patch
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).parent.parent / "benchmarks"))
|
||||
|
||||
from tool_call_benchmark import ( # noqa: E402
|
||||
CallResult,
|
||||
DEFAULT_COMPARE_MODELS,
|
||||
ISSUE_796_CATEGORY_COUNTS,
|
||||
ToolCall,
|
||||
generate_report,
|
||||
run_single_test,
|
||||
suite_category_counts,
|
||||
)
|
||||
|
||||
|
||||
def test_suite_counts_match_issue_796_distribution():
|
||||
counts = suite_category_counts()
|
||||
assert counts == ISSUE_796_CATEGORY_COUNTS
|
||||
assert sum(counts.values()) == 100
|
||||
|
||||
|
||||
def test_default_compare_models_cover_issue_796_lanes():
|
||||
assert len(DEFAULT_COMPARE_MODELS) == 3
|
||||
assert any("gemma-4-31b" in spec for spec in DEFAULT_COMPARE_MODELS)
|
||||
assert any("gemma-4-26b" in spec for spec in DEFAULT_COMPARE_MODELS)
|
||||
assert any("mimo-v2-pro" in spec for spec in DEFAULT_COMPARE_MODELS)
|
||||
|
||||
|
||||
def test_generate_report_includes_parallel_and_cost_metrics(tmp_path):
|
||||
output_path = tmp_path / "report.md"
|
||||
results = [
|
||||
CallResult(
|
||||
test_id="file-01",
|
||||
category="file",
|
||||
model="gemma-4-31b",
|
||||
prompt="Read the file.",
|
||||
expected_tool="read_file",
|
||||
success=True,
|
||||
tool_called="read_file",
|
||||
schema_ok=True,
|
||||
tool_args_valid=True,
|
||||
execution_ok=True,
|
||||
tool_count=2,
|
||||
parallel_ok=True,
|
||||
latency_s=1.25,
|
||||
total_tokens=123,
|
||||
estimated_cost_usd=0.0012,
|
||||
cost_status="estimated",
|
||||
),
|
||||
CallResult(
|
||||
test_id="web-01",
|
||||
category="web",
|
||||
model="mimo-v2-pro",
|
||||
prompt="Search the web.",
|
||||
expected_tool="web_search",
|
||||
success=False,
|
||||
tool_called="web_search",
|
||||
schema_ok=True,
|
||||
tool_args_valid=False,
|
||||
execution_ok=False,
|
||||
tool_count=1,
|
||||
parallel_ok=False,
|
||||
latency_s=2.5,
|
||||
error="bad args",
|
||||
total_tokens=456,
|
||||
estimated_cost_usd=None,
|
||||
cost_status="unknown",
|
||||
skipped=True,
|
||||
skip_reason="web_search unavailable",
|
||||
),
|
||||
]
|
||||
|
||||
report = generate_report(results, ["gemma-4-31b", "mimo-v2-pro"], output_path)
|
||||
|
||||
assert output_path.exists()
|
||||
assert "Parallel tool success" in report
|
||||
assert "Avg token cost per call (USD)" in report
|
||||
assert "Skipped / unavailable" in report
|
||||
assert "Requested category mix" in report
|
||||
|
||||
|
||||
def test_run_single_test_skips_when_expected_tool_unavailable():
|
||||
class FakeAgent:
|
||||
def __init__(self, *args, **kwargs):
|
||||
self.valid_tool_names = {"read_file", "terminal"}
|
||||
self.session_input_tokens = 0
|
||||
self.session_output_tokens = 0
|
||||
self.session_cache_read_tokens = 0
|
||||
self.session_cache_write_tokens = 0
|
||||
self.session_api_calls = 0
|
||||
self.base_url = ""
|
||||
self.api_key = None
|
||||
|
||||
def run_conversation(self, *args, **kwargs):
|
||||
raise AssertionError("run_conversation should not be called for unavailable tools")
|
||||
|
||||
tc = ToolCall(
|
||||
id="mcp-01",
|
||||
category="mcp",
|
||||
prompt="Use an MCP tool to list resources.",
|
||||
expected_tool="",
|
||||
expected_tool_prefix="mcp_",
|
||||
)
|
||||
|
||||
with patch.dict(sys.modules, {"run_agent": SimpleNamespace(AIAgent=FakeAgent)}):
|
||||
result = run_single_test(tc, "gemini:gemma-4-31b-it", "gemini")
|
||||
|
||||
assert result.skipped is True
|
||||
assert "mcp_" in result.skip_reason
|
||||
assert result.success is False
|
||||
@@ -148,3 +148,184 @@ class TestStrategyNameSurfaced:
|
||||
assert count == 0
|
||||
assert strategy is None
|
||||
assert err is not None
|
||||
|
||||
|
||||
class TestEscapeDriftGuard:
|
||||
"""Tests for the escape-drift guard that catches bash/JSON serialization
|
||||
artifacts where an apostrophe gets prefixed with a spurious backslash
|
||||
in tool-call transport.
|
||||
"""
|
||||
|
||||
def test_drift_blocked_apostrophe(self):
|
||||
"""File has ', old_string and new_string both have \\' — classic
|
||||
tool-call drift. Guard must block with a helpful error instead of
|
||||
writing \\' literals into source code."""
|
||||
content = "x = \"hello there\"\n"
|
||||
# Simulate transport-corrupted old_string and new_string where an
|
||||
# apostrophe-like context got prefixed with a backslash. The content
|
||||
# itself has no apostrophe, but both strings do — matching via
|
||||
# whitespace/anchor strategies would otherwise succeed.
|
||||
old_string = "x = \"hello there\" # don\\'t edit\n"
|
||||
new_string = "x = \"hi there\" # don\\'t edit\n"
|
||||
# This particular pair won't match anything, so it exits via
|
||||
# no-match path. Build a case where a non-exact strategy DOES match.
|
||||
content = "line\n x = 1\nline"
|
||||
old_string = "line\n x = \\'a\\'\nline"
|
||||
new_string = "line\n x = \\'b\\'\nline"
|
||||
new, count, strategy, err = fuzzy_find_and_replace(content, old_string, new_string)
|
||||
assert count == 0
|
||||
assert err is not None and "Escape-drift" in err
|
||||
assert "backslash" in err.lower()
|
||||
assert new == content # file untouched
|
||||
|
||||
def test_drift_blocked_double_quote(self):
|
||||
"""Same idea but with \\" drift instead of \\'."""
|
||||
content = 'line\n x = 1\nline'
|
||||
old_string = 'line\n x = \\"a\\"\nline'
|
||||
new_string = 'line\n x = \\"b\\"\nline'
|
||||
new, count, strategy, err = fuzzy_find_and_replace(content, old_string, new_string)
|
||||
assert count == 0
|
||||
assert err is not None and "Escape-drift" in err
|
||||
|
||||
def test_drift_allowed_when_file_genuinely_has_backslash_escapes(self):
|
||||
"""If the file already contains \\' (e.g. inside an existing escaped
|
||||
string), the model is legitimately preserving it. Guard must NOT
|
||||
fire."""
|
||||
content = "line\n x = \\'a\\'\nline"
|
||||
old_string = "line\n x = \\'a\\'\nline"
|
||||
new_string = "line\n x = \\'b\\'\nline"
|
||||
new, count, strategy, err = fuzzy_find_and_replace(content, old_string, new_string)
|
||||
assert err is None
|
||||
assert count == 1
|
||||
assert "\\'b\\'" in new
|
||||
|
||||
def test_drift_allowed_on_exact_match(self):
|
||||
"""Exact matches bypass the drift guard entirely — if the file
|
||||
really contains the exact bytes old_string specified, it's not
|
||||
drift."""
|
||||
content = "hello \\'world\\'"
|
||||
new, count, strategy, err = fuzzy_find_and_replace(
|
||||
content, "hello \\'world\\'", "hello \\'there\\'"
|
||||
)
|
||||
assert err is None
|
||||
assert count == 1
|
||||
assert strategy == "exact"
|
||||
|
||||
def test_drift_allowed_when_adding_escaped_strings(self):
|
||||
"""Model is adding new content with \\' that wasn't in the original.
|
||||
old_string has no \\', so guard doesn't fire."""
|
||||
content = "line1\nline2\nline3"
|
||||
old_string = "line1\nline2\nline3"
|
||||
new_string = "line1\nprint(\\'added\\')\nline2\nline3"
|
||||
new, count, strategy, err = fuzzy_find_and_replace(content, old_string, new_string)
|
||||
assert err is None
|
||||
assert count == 1
|
||||
assert "\\'added\\'" in new
|
||||
|
||||
def test_no_drift_check_when_new_string_lacks_suspect_chars(self):
|
||||
"""Fast-path: if new_string has no \\' or \\", guard must not
|
||||
fire even on fuzzy match."""
|
||||
content = "def foo():\n pass" # extra space ignored by line_trimmed
|
||||
old_string = "def foo():\n pass"
|
||||
new_string = "def bar():\n return 1"
|
||||
new, count, strategy, err = fuzzy_find_and_replace(content, old_string, new_string)
|
||||
assert err is None
|
||||
assert count == 1
|
||||
|
||||
|
||||
class TestFindClosestLines:
|
||||
def setup_method(self):
|
||||
from tools.fuzzy_match import find_closest_lines
|
||||
self.find_closest_lines = find_closest_lines
|
||||
|
||||
def test_finds_similar_line(self):
|
||||
content = "def foo():\n pass\ndef bar():\n return 1\n"
|
||||
result = self.find_closest_lines("def baz():", content)
|
||||
assert "def foo" in result or "def bar" in result
|
||||
|
||||
def test_returns_empty_for_no_match(self):
|
||||
content = "completely different content here"
|
||||
result = self.find_closest_lines("xyzzy_no_match_possible_!!!", content)
|
||||
assert result == ""
|
||||
|
||||
def test_returns_empty_for_empty_inputs(self):
|
||||
assert self.find_closest_lines("", "some content") == ""
|
||||
assert self.find_closest_lines("old string", "") == ""
|
||||
|
||||
def test_includes_context_lines(self):
|
||||
content = "line1\nline2\ndef target():\n pass\nline5\n"
|
||||
result = self.find_closest_lines("def target():", content)
|
||||
assert "target" in result
|
||||
|
||||
def test_includes_line_numbers(self):
|
||||
content = "line1\nline2\ndef foo():\n pass\n"
|
||||
result = self.find_closest_lines("def foo():", content)
|
||||
# Should include line numbers in format "N| content"
|
||||
assert "|" in result
|
||||
|
||||
|
||||
class TestFormatNoMatchHint:
|
||||
"""Gating tests for format_no_match_hint — the shared helper that decides
|
||||
whether a 'Did you mean?' snippet should be appended to an error.
|
||||
"""
|
||||
|
||||
def setup_method(self):
|
||||
from tools.fuzzy_match import format_no_match_hint
|
||||
self.fmt = format_no_match_hint
|
||||
|
||||
def test_fires_on_could_not_find_with_match(self):
|
||||
"""Classic no-match: similar content exists → hint fires."""
|
||||
content = "def foo():\n pass\ndef bar():\n pass\n"
|
||||
result = self.fmt(
|
||||
"Could not find a match for old_string in the file",
|
||||
0, "def baz():", content,
|
||||
)
|
||||
assert "Did you mean" in result
|
||||
assert "foo" in result or "bar" in result
|
||||
|
||||
def test_silent_on_ambiguous_match_error(self):
|
||||
"""'Found N matches' is not a missing-match failure — no hint."""
|
||||
content = "aaa bbb aaa\n"
|
||||
result = self.fmt(
|
||||
"Found 2 matches for old_string. Provide more context to make it unique, or use replace_all=True.",
|
||||
0, "aaa", content,
|
||||
)
|
||||
assert result == ""
|
||||
|
||||
def test_silent_on_escape_drift_error(self):
|
||||
"""Escape-drift errors are intentional blocks — hint would mislead."""
|
||||
content = "x = 1\n"
|
||||
result = self.fmt(
|
||||
"Escape-drift detected: old_string and new_string contain the literal sequence '\\\\''...",
|
||||
0, "x = \\'1\\'", content,
|
||||
)
|
||||
assert result == ""
|
||||
|
||||
def test_silent_on_identical_strings(self):
|
||||
"""old_string == new_string — hint irrelevant."""
|
||||
result = self.fmt(
|
||||
"old_string and new_string are identical",
|
||||
0, "foo", "foo bar\n",
|
||||
)
|
||||
assert result == ""
|
||||
|
||||
def test_silent_when_match_count_nonzero(self):
|
||||
"""If match succeeded, we shouldn't be in the error path — defense in depth."""
|
||||
result = self.fmt(
|
||||
"Could not find a match for old_string in the file",
|
||||
1, "foo", "foo bar\n",
|
||||
)
|
||||
assert result == ""
|
||||
|
||||
def test_silent_on_none_error(self):
|
||||
"""No error at all — no hint."""
|
||||
result = self.fmt(None, 0, "foo", "bar\n")
|
||||
assert result == ""
|
||||
|
||||
def test_silent_when_no_similar_content(self):
|
||||
"""Even for a valid no-match error, skip hint when nothing similar exists."""
|
||||
result = self.fmt(
|
||||
"Could not find a match for old_string in the file",
|
||||
0, "totally_unique_xyzzy_qux", "abc\nxyz\n",
|
||||
)
|
||||
assert result == ""
|
||||
|
||||
114
tests/tools/test_patch_did_you_mean.py
Normal file
114
tests/tools/test_patch_did_you_mean.py
Normal file
@@ -0,0 +1,114 @@
|
||||
import json
|
||||
import os
|
||||
import textwrap
|
||||
from pathlib import Path
|
||||
|
||||
import tools.skill_manager_tool as skill_manager_tool
|
||||
from tools.file_tools import patch_tool
|
||||
from tools.skill_manager_tool import _create_skill, _patch_skill
|
||||
|
||||
|
||||
def _disable_patch_tool_guards(monkeypatch):
|
||||
monkeypatch.setattr("tools.file_tools._check_sensitive_path", lambda _path: None)
|
||||
monkeypatch.setattr("tools.file_tools._check_file_staleness", lambda _path, _task_id: None)
|
||||
monkeypatch.setattr("tools.file_tools._log_and_check_conflict", lambda _path, _task_id, _action: None)
|
||||
|
||||
|
||||
def test_patch_tool_replace_no_match_shows_rich_hint_without_legacy_hint(tmp_path, monkeypatch):
|
||||
_disable_patch_tool_guards(monkeypatch)
|
||||
sample = tmp_path / "sample.py"
|
||||
sample.write_text("def foo():\n return 1\n\ndef bar():\n return 2\n", encoding="utf-8")
|
||||
|
||||
raw = patch_tool(
|
||||
mode="replace",
|
||||
path=str(sample),
|
||||
old_string="def barycentric():",
|
||||
new_string="def barycentric_new():",
|
||||
task_id="qa960-replace-rich-hint",
|
||||
)
|
||||
|
||||
result = json.loads(raw)
|
||||
assert result["success"] is False
|
||||
assert "Could not find a match" in result["error"]
|
||||
assert "Did you mean one of these sections?" in result["error"]
|
||||
assert "def bar():" in result["error"] or "def foo():" in result["error"]
|
||||
assert "[Hint:" not in raw
|
||||
|
||||
|
||||
def test_patch_tool_replace_ambiguous_error_does_not_show_did_you_mean(tmp_path, monkeypatch):
|
||||
_disable_patch_tool_guards(monkeypatch)
|
||||
sample = tmp_path / "sample.py"
|
||||
sample.write_text("aaa\nbbb\naaa\n", encoding="utf-8")
|
||||
|
||||
raw = patch_tool(
|
||||
mode="replace",
|
||||
path=str(sample),
|
||||
old_string="aaa",
|
||||
new_string="ccc",
|
||||
task_id="qa960-replace-ambiguous",
|
||||
)
|
||||
|
||||
result = json.loads(raw)
|
||||
assert result["success"] is False
|
||||
assert "Found 2 matches" in result["error"]
|
||||
assert "Did you mean one of these sections?" not in result["error"]
|
||||
assert "[Hint:" not in raw
|
||||
|
||||
|
||||
def test_patch_tool_v4a_no_match_shows_rich_hint(tmp_path, monkeypatch):
|
||||
_disable_patch_tool_guards(monkeypatch)
|
||||
sample = tmp_path / "sample.py"
|
||||
sample.write_text("def foo():\n return 1\n", encoding="utf-8")
|
||||
|
||||
patch = textwrap.dedent(
|
||||
f"""\
|
||||
*** Begin Patch
|
||||
*** Update File: {sample}
|
||||
@@
|
||||
-def barycentric():
|
||||
+def barycentric_new():
|
||||
*** End Patch
|
||||
"""
|
||||
)
|
||||
|
||||
raw = patch_tool(mode="patch", patch=patch, task_id="qa960-v4a-rich-hint")
|
||||
result = json.loads(raw)
|
||||
assert result["success"] is False
|
||||
assert "Patch validation failed" in result["error"]
|
||||
assert "Did you mean one of these sections?" in result["error"]
|
||||
assert "def foo():" in result["error"]
|
||||
|
||||
|
||||
def test_skill_patch_no_match_shows_rich_hint(tmp_path, monkeypatch):
|
||||
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
|
||||
skills_dir = tmp_path / "skills"
|
||||
skills_dir.mkdir(parents=True, exist_ok=True)
|
||||
monkeypatch.setattr(skill_manager_tool, "SKILLS_DIR", skills_dir)
|
||||
monkeypatch.setattr(skill_manager_tool, "_security_scan_skill", lambda _skill_dir: None)
|
||||
|
||||
_create_skill(
|
||||
"qa-skill",
|
||||
textwrap.dedent(
|
||||
"""\
|
||||
---
|
||||
name: qa-skill
|
||||
description: test
|
||||
---
|
||||
|
||||
Step 1: Do the thing.
|
||||
Step 2: Verify the thing.
|
||||
"""
|
||||
),
|
||||
)
|
||||
|
||||
result = _patch_skill(
|
||||
"qa-skill",
|
||||
"Step 1: Do the production rollout.",
|
||||
"Step 1: Updated.",
|
||||
)
|
||||
|
||||
assert result["success"] is False
|
||||
assert "Could not find a match" in result["error"]
|
||||
assert "Did you mean one of these sections?" in result["error"]
|
||||
assert "Step 1: Do the thing." in result["error"]
|
||||
assert "file_preview" in result
|
||||
@@ -757,12 +757,14 @@ class ShellFileOperations(FileOperations):
|
||||
content, old_string, new_string, replace_all
|
||||
)
|
||||
|
||||
if error:
|
||||
return PatchResult(error=error)
|
||||
|
||||
if match_count == 0:
|
||||
return PatchResult(error=f"Could not find match for old_string in {path}")
|
||||
|
||||
if error or match_count == 0:
|
||||
err_msg = error or f"Could not find match for old_string in {path}"
|
||||
try:
|
||||
from tools.fuzzy_match import format_no_match_hint
|
||||
err_msg += format_no_match_hint(err_msg, match_count, old_string, content)
|
||||
except Exception:
|
||||
pass
|
||||
return PatchResult(error=err_msg)
|
||||
# Write back
|
||||
write_result = self.write_file(path, new_content)
|
||||
if write_result.error:
|
||||
|
||||
@@ -8,6 +8,7 @@ import os
|
||||
import threading
|
||||
import time
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict, Optional
|
||||
from tools.binary_extensions import has_binary_extension
|
||||
from tools.file_operations import ShellFileOperations
|
||||
from agent.redact import redact_sensitive_text
|
||||
@@ -690,8 +691,11 @@ def patch_tool(mode: str = "replace", path: str = None, old_string: str = None,
|
||||
result_json = json.dumps(result_dict, ensure_ascii=False)
|
||||
# Hint when old_string not found — saves iterations where the agent
|
||||
# retries with stale content instead of re-reading the file.
|
||||
# Suppressed when patch_replace already attached a rich "Did you mean?"
|
||||
# snippet (which is strictly more useful than the generic hint).
|
||||
if result_dict.get("error") and "Could not find" in str(result_dict["error"]):
|
||||
result_json += "\n\n[Hint: old_string not found. Use read_file to verify the current content, or search_files to locate the text.]"
|
||||
if "Did you mean one of these sections?" not in str(result_dict["error"]):
|
||||
result_json += "\n\n[Hint: old_string not found. Use read_file to verify the current content, or search_files to locate the text.]"
|
||||
return result_json
|
||||
except Exception as e:
|
||||
return tool_error(str(e))
|
||||
|
||||
@@ -93,6 +93,21 @@ def fuzzy_find_and_replace(content: str, old_string: str, new_string: str,
|
||||
f"Provide more context to make it unique, or use replace_all=True."
|
||||
)
|
||||
|
||||
# Escape-drift guard: when the matched strategy is NOT `exact`,
|
||||
# we matched via some form of normalization. If new_string
|
||||
# contains shell/JSON-style escape sequences (\\' or \\") that
|
||||
# would be written literally into the file but the matched
|
||||
# region of the file has no such sequences, this is almost
|
||||
# certainly tool-call serialization drift — the model typed
|
||||
# an apostrophe/quote and the transport added a stray
|
||||
# backslash. Writing new_string as-is would corrupt the file.
|
||||
# Block with a helpful error so the model re-reads and retries
|
||||
# instead of the caller silently persisting garbage (or not).
|
||||
if strategy_name != "exact":
|
||||
drift_err = _detect_escape_drift(content, matches, old_string, new_string)
|
||||
if drift_err:
|
||||
return content, 0, None, drift_err
|
||||
|
||||
# Perform replacement
|
||||
new_content = _apply_replacements(content, matches, new_string)
|
||||
return new_content, len(matches), strategy_name, None
|
||||
@@ -101,6 +116,46 @@ def fuzzy_find_and_replace(content: str, old_string: str, new_string: str,
|
||||
return content, 0, None, "Could not find a match for old_string in the file"
|
||||
|
||||
|
||||
def _detect_escape_drift(content: str, matches: List[Tuple[int, int]],
|
||||
old_string: str, new_string: str) -> Optional[str]:
|
||||
"""Detect tool-call escape-drift artifacts in new_string.
|
||||
|
||||
Looks for ``\\'`` or ``\\"`` sequences that are present in both
|
||||
old_string and new_string (i.e. the model copy-pasted them as "context"
|
||||
it intended to preserve) but don't exist in the matched region of the
|
||||
file. That pattern indicates the transport layer inserted spurious
|
||||
shell-style escapes around apostrophes or quotes — writing new_string
|
||||
verbatim would literally insert ``\\'`` into source code.
|
||||
|
||||
Returns an error string if drift is detected, None otherwise.
|
||||
"""
|
||||
# Cheap pre-check: bail out unless new_string actually contains a
|
||||
# suspect escape sequence. This keeps the guard free for all the
|
||||
# common, correct cases.
|
||||
if "\\'" not in new_string and '\\"' not in new_string:
|
||||
return None
|
||||
|
||||
# Aggregate matched regions of the file — that's what new_string will
|
||||
# replace. If the suspect escapes are present there already, the
|
||||
# model is genuinely preserving them (valid for some languages /
|
||||
# escaped strings); accept the patch.
|
||||
matched_regions = "".join(content[start:end] for start, end in matches)
|
||||
|
||||
for suspect in ("\\'", '\\"'):
|
||||
if suspect in new_string and suspect in old_string and suspect not in matched_regions:
|
||||
plain = suspect[1] # "'" or '"'
|
||||
return (
|
||||
f"Escape-drift detected: old_string and new_string contain "
|
||||
f"the literal sequence {suspect!r} but the matched region of "
|
||||
f"the file does not. This is almost always a tool-call "
|
||||
f"serialization artifact where an apostrophe or quote got "
|
||||
f"prefixed with a spurious backslash. Re-read the file with "
|
||||
f"read_file and pass old_string/new_string without "
|
||||
f"backslash-escaping {plain!r} characters."
|
||||
)
|
||||
return None
|
||||
|
||||
|
||||
def _apply_replacements(content: str, matches: List[Tuple[int, int]], new_string: str) -> str:
|
||||
"""
|
||||
Apply replacements at the given positions.
|
||||
@@ -564,3 +619,86 @@ def _map_normalized_positions(original: str, normalized: str,
|
||||
original_matches.append((orig_start, min(orig_end, len(original))))
|
||||
|
||||
return original_matches
|
||||
|
||||
|
||||
def find_closest_lines(old_string: str, content: str, context_lines: int = 2, max_results: int = 3) -> str:
|
||||
"""Find lines in content most similar to old_string for "did you mean?" feedback.
|
||||
|
||||
Returns a formatted string showing the closest matching lines with context,
|
||||
or empty string if no useful match is found.
|
||||
"""
|
||||
if not old_string or not content:
|
||||
return ""
|
||||
|
||||
old_lines = old_string.splitlines()
|
||||
content_lines = content.splitlines()
|
||||
|
||||
if not old_lines or not content_lines:
|
||||
return ""
|
||||
|
||||
# Use first line of old_string as anchor for search
|
||||
anchor = old_lines[0].strip()
|
||||
if not anchor:
|
||||
# Try second line if first is blank
|
||||
candidates = [l.strip() for l in old_lines if l.strip()]
|
||||
if not candidates:
|
||||
return ""
|
||||
anchor = candidates[0]
|
||||
|
||||
# Score each line in content by similarity to anchor
|
||||
scored = []
|
||||
for i, line in enumerate(content_lines):
|
||||
stripped = line.strip()
|
||||
if not stripped:
|
||||
continue
|
||||
ratio = SequenceMatcher(None, anchor, stripped).ratio()
|
||||
if ratio > 0.3:
|
||||
scored.append((ratio, i))
|
||||
|
||||
if not scored:
|
||||
return ""
|
||||
|
||||
# Take top matches
|
||||
scored.sort(key=lambda x: -x[0])
|
||||
top = scored[:max_results]
|
||||
|
||||
parts = []
|
||||
seen_ranges = set()
|
||||
for _, line_idx in top:
|
||||
start = max(0, line_idx - context_lines)
|
||||
end = min(len(content_lines), line_idx + len(old_lines) + context_lines)
|
||||
key = (start, end)
|
||||
if key in seen_ranges:
|
||||
continue
|
||||
seen_ranges.add(key)
|
||||
snippet = "\n".join(
|
||||
f"{start + j + 1:4d}| {content_lines[start + j]}"
|
||||
for j in range(end - start)
|
||||
)
|
||||
parts.append(snippet)
|
||||
|
||||
if not parts:
|
||||
return ""
|
||||
|
||||
return "\n---\n".join(parts)
|
||||
|
||||
|
||||
def format_no_match_hint(error: Optional[str], match_count: int,
|
||||
old_string: str, content: str) -> str:
|
||||
"""Return a '\\n\\nDid you mean...' snippet for plain no-match errors.
|
||||
|
||||
Gated so the hint only fires for actual "old_string not found" failures.
|
||||
Ambiguous-match ("Found N matches"), escape-drift, and identical-strings
|
||||
errors all have ``match_count == 0`` but a "did you mean?" snippet would
|
||||
be misleading — those failed for unrelated reasons.
|
||||
|
||||
Returns an empty string when there's nothing useful to append.
|
||||
"""
|
||||
if match_count != 0:
|
||||
return ""
|
||||
if not error or not error.startswith("Could not find"):
|
||||
return ""
|
||||
hint = find_closest_lines(old_string, content)
|
||||
if not hint:
|
||||
return ""
|
||||
return "\n\nDid you mean one of these sections?\n" + hint
|
||||
|
||||
@@ -290,10 +290,16 @@ def _validate_operations(
|
||||
)
|
||||
if count == 0:
|
||||
label = f"'{hunk.context_hint}'" if hunk.context_hint else "(no hint)"
|
||||
errors.append(
|
||||
msg = (
|
||||
f"{op.file_path}: hunk {label} not found"
|
||||
+ (f" — {match_error}" if match_error else "")
|
||||
)
|
||||
try:
|
||||
from tools.fuzzy_match import format_no_match_hint
|
||||
msg += format_no_match_hint(match_error, count, search_pattern, simulated)
|
||||
except Exception:
|
||||
pass
|
||||
errors.append(msg)
|
||||
else:
|
||||
# Advance simulation so subsequent hunks validate correctly.
|
||||
# Reuse the result from the call above — no second fuzzy run.
|
||||
@@ -537,7 +543,13 @@ def _apply_update(op: PatchOperation, file_ops: Any) -> Tuple[bool, str]:
|
||||
error = None
|
||||
|
||||
if error:
|
||||
return False, f"Could not apply hunk: {error}"
|
||||
err_msg = f"Could not apply hunk: {error}"
|
||||
try:
|
||||
from tools.fuzzy_match import format_no_match_hint
|
||||
err_msg += format_no_match_hint(error, 0, search_pattern, new_content)
|
||||
except Exception:
|
||||
pass
|
||||
return False, err_msg
|
||||
else:
|
||||
# Addition-only hunk (no context or removed lines).
|
||||
# Insert at the location indicated by the context hint, or at end of file.
|
||||
|
||||
@@ -575,9 +575,15 @@ def _patch_skill(
|
||||
if match_error:
|
||||
# Show a short preview of the file so the model can self-correct
|
||||
preview = content[:500] + ("..." if len(content) > 500 else "")
|
||||
err_msg = match_error
|
||||
try:
|
||||
from tools.fuzzy_match import format_no_match_hint
|
||||
err_msg += format_no_match_hint(match_error, match_count, old_string, content)
|
||||
except Exception:
|
||||
pass
|
||||
return {
|
||||
"success": False,
|
||||
"error": match_error,
|
||||
"error": err_msg,
|
||||
"file_preview": preview,
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user