alex/g3
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

clean up filter_json a bit (more to come)

Browse Source
This commit is contained in:
Dhanji R. Prasanna
2025-12-22 12:03:09 +11:00
parent 87d9b39ae4
commit 3bc254962c
6 changed files with 85 additions and 88 deletions
Download Patch File Download Diff File Expand all files Collapse all files

86
crates/g3-cli/tests/fixed_filter_tests.rs → crates/g3-cli/tests/filter_json_test.rs
View File

@@ -4,28 +4,28 @@
//! from LLM output streams while preserving all other content.
#[cfg(test)]
mod fixed_filter_tests {
use g3_cli::fixed_filter_json::{fixed_filter_json_tool_calls, reset_fixed_json_tool_state};
mod filter_json_tests {
use g3_cli::filter_json::{filter_json_tool_calls, reset_json_tool_state};
use regex::Regex;
/// Test that regular text without tool calls passes through unchanged.
#[test]
fn test_no_tool_call_passthrough() {
reset_fixed_json_tool_state();
reset_json_tool_state();
let input = "This is regular text without any tool calls.";
let result = fixed_filter_json_tool_calls(input);
let result = filter_json_tool_calls(input);
assert_eq!(result, input);
}
/// Test detection and removal of a complete tool call in a single chunk.
#[test]
fn test_simple_tool_call_detection() {
reset_fixed_json_tool_state();
reset_json_tool_state();
let input = r#"Some text before
{"tool": "shell", "args": {"command": "ls"}}
Some text after"#;
let result = fixed_filter_json_tool_calls(input);
let result = filter_json_tool_calls(input);
let expected = "Some text before\n\nSome text after";
assert_eq!(result, expected);
}
@@ -33,7 +33,7 @@ Some text after"#;
/// Test handling of tool calls that arrive across multiple streaming chunks.
#[test]
fn test_streaming_chunks() {
reset_fixed_json_tool_state();
reset_json_tool_state();
// Simulate streaming where the tool call comes in multiple chunks
let chunks = vec![
@@ -46,7 +46,7 @@ Some text after"#;
let mut results = Vec::new();
for chunk in chunks {
let result = fixed_filter_json_tool_calls(chunk);
let result = filter_json_tool_calls(chunk);
results.push(result);
}
@@ -59,13 +59,13 @@ Some text after"#;
/// Test correct handling of nested braces within JSON strings.
#[test]
fn test_nested_braces_in_tool_call() {
reset_fixed_json_tool_state();
reset_json_tool_state();
let input = r#"Text before
{"tool": "write_file", "args": {"file_path": "test.json", "content": "{\"nested\": \"value\"}"}}
Text after"#;
let result = fixed_filter_json_tool_calls(input);
let result = filter_json_tool_calls(input);
let expected = "Text before\n\nText after";
assert_eq!(result, expected);
}
@@ -117,16 +117,16 @@ Text after"#;
/// Test that tool calls must appear at the start of a line (after newline).
#[test]
fn test_newline_requirement() {
reset_fixed_json_tool_state();
reset_json_tool_state();
// According to spec, tool call should be detected "on the very next newline"
// Our current regex matches any line that contains the pattern, not just after newlines
let input_with_newline = "Text\n{\"tool\": \"shell\", \"args\": {\"command\": \"ls\"}}";
let input_without_newline = "Text {\"tool\": \"shell\", \"args\": {\"command\": \"ls\"}}";
let result1 = fixed_filter_json_tool_calls(input_with_newline);
reset_fixed_json_tool_state();
let result2 = fixed_filter_json_tool_calls(input_without_newline);
let result1 = filter_json_tool_calls(input_with_newline);
reset_json_tool_state();
let result2 = filter_json_tool_calls(input_without_newline);
// With the new aggressive filtering, only the newline case should trigger suppression
// The pattern requires { to be at the start of a line (after ^)
@@ -138,13 +138,13 @@ Text after"#;
/// Test handling of escaped quotes within JSON strings.
#[test]
fn test_json_with_escaped_quotes() {
reset_fixed_json_tool_state();
reset_json_tool_state();
let input = r#"Text
{"tool": "write_file", "args": {"content": "He said \"hello\" to me"}}
More text"#;
let result = fixed_filter_json_tool_calls(input);
let result = filter_json_tool_calls(input);
let expected = "Text\n\nMore text";
assert_eq!(result, expected);
}
@@ -152,14 +152,14 @@ More text"#;
/// Test graceful handling of incomplete/malformed JSON.
#[test]
fn test_edge_case_malformed_json() {
reset_fixed_json_tool_state();
reset_json_tool_state();
// Test what happens with malformed JSON that starts like a tool call
let input = r#"Text
{"tool": "shell", "args": {"command": "ls"
More text"#;
let result = fixed_filter_json_tool_calls(input);
let result = filter_json_tool_calls(input);
// Should handle gracefully - since JSON is incomplete, it should return content before JSON
let expected = "Text\n";
assert_eq!(result, expected);
@@ -168,22 +168,22 @@ More text"#;
/// Test processing multiple independent tool calls sequentially.
#[test]
fn test_multiple_tool_calls_sequential() {
reset_fixed_json_tool_state();
reset_json_tool_state();
// Test processing multiple tool calls one at a time
let input1 = r#"First text
{"tool": "shell", "args": {"command": "ls"}}
Middle text"#;
let result1 = fixed_filter_json_tool_calls(input1);
let result1 = filter_json_tool_calls(input1);
let expected1 = "First text\n\nMiddle text";
assert_eq!(result1, expected1);
// Reset and process second tool call
reset_fixed_json_tool_state();
reset_json_tool_state();
let input2 = r#"More text
{"tool": "read_file", "args": {"file_path": "test.txt"}}
Final text"#;
let result2 = fixed_filter_json_tool_calls(input2);
let result2 = filter_json_tool_calls(input2);
let expected2 = "More text\n\nFinal text";
assert_eq!(result2, expected2);
}
@@ -191,13 +191,13 @@ Final text"#;
/// Test tool calls with complex multi-line arguments.
#[test]
fn test_tool_call_with_complex_args() {
reset_fixed_json_tool_state();
reset_json_tool_state();
let input = r#"Before
{"tool": "str_replace", "args": {"file_path": "test.rs", "diff": "--- old\n-old line\n+++ new\n+new line", "start": 0, "end": 100}}
After"#;
let result = fixed_filter_json_tool_calls(input);
let result = filter_json_tool_calls(input);
let expected = "Before\n\nAfter";
assert_eq!(result, expected);
}
@@ -205,12 +205,12 @@ After"#;
/// Test input containing only a tool call with no surrounding text.
#[test]
fn test_tool_call_only() {
reset_fixed_json_tool_state();
reset_json_tool_state();
let input = r#"
{"tool": "final_output", "args": {"summary": "Task completed successfully"}}"#;
let result = fixed_filter_json_tool_calls(input);
let result = filter_json_tool_calls(input);
let expected = "\n";
assert_eq!(result, expected);
}
@@ -218,14 +218,14 @@ After"#;
/// Test accurate brace counting with deeply nested structures.
#[test]
fn test_brace_counting_accuracy() {
reset_fixed_json_tool_state();
reset_json_tool_state();
// Test complex nested structure
let input = r#"Start
{"tool": "write_file", "args": {"content": "function() { return {a: 1, b: {c: 2}}; }", "file_path": "test.js"}}
End"#;
let result = fixed_filter_json_tool_calls(input);
let result = filter_json_tool_calls(input);
let expected = "Start\n\nEnd";
assert_eq!(result, expected);
}
@@ -233,14 +233,14 @@ End"#;
/// Test that braces within strings don't affect brace counting.
#[test]
fn test_string_escaping_in_json() {
reset_fixed_json_tool_state();
reset_json_tool_state();
// Test JSON with escaped quotes and braces in strings
let input = r#"Text
{"tool": "shell", "args": {"command": "echo \"Hello {world}\" > file.txt"}}
More"#;
let result = fixed_filter_json_tool_calls(input);
let result = filter_json_tool_calls(input);
let expected = "Text\n\nMore";
assert_eq!(result, expected);
}
@@ -248,7 +248,7 @@ More"#;
/// Verify compliance with the exact specification requirements.
#[test]
fn test_specification_compliance() {
reset_fixed_json_tool_state();
reset_json_tool_state();
// Test the exact specification requirements:
// 1. Detect start with regex '\w*{\w*"tool"\w*:\w*"' on newline
@@ -257,7 +257,7 @@ More"#;
// 4. Return everything else
let input = "Before text\nSome more text\n{\"tool\": \"test\", \"args\": {}}\nAfter text\nMore after";
let result = fixed_filter_json_tool_calls(input);
let result = filter_json_tool_calls(input);
let expected = "Before text\nSome more text\n\nAfter text\nMore after";
assert_eq!(result, expected);
}
@@ -265,13 +265,13 @@ More"#;
/// Test that non-tool JSON objects are not filtered.
#[test]
fn test_no_false_positives() {
reset_fixed_json_tool_state();
reset_json_tool_state();
// Test that we don't incorrectly identify non-tool JSON as tool calls
let input = r#"Some text
{"not_tool": "value", "other": "data"}
More text"#;
let result = fixed_filter_json_tool_calls(input);
let result = filter_json_tool_calls(input);
// Should pass through unchanged since it doesn't match the tool pattern
assert_eq!(result, input);
}
@@ -279,7 +279,7 @@ More text"#;
/// Test patterns that look similar to tool calls but aren't exact matches.
#[test]
fn test_partial_tool_patterns() {
reset_fixed_json_tool_state();
reset_json_tool_state();
// Test patterns that look like tool calls but aren't complete
let test_cases = vec![
@@ -289,8 +289,8 @@ More text"#;
];
for input in test_cases {
reset_fixed_json_tool_state();
let result = fixed_filter_json_tool_calls(input);
reset_json_tool_state();
let result = filter_json_tool_calls(input);
// These should all pass through unchanged
assert_eq!(result, input, "Input should pass through: {}", input);
}
@@ -299,7 +299,7 @@ More text"#;
/// Test streaming with very small chunks (character-by-character).
#[test]
fn test_streaming_edge_cases() {
reset_fixed_json_tool_state();
reset_json_tool_state();
// Test streaming with very small chunks
let chunks = vec![
@@ -308,7 +308,7 @@ More text"#;
let mut results = Vec::new();
for chunk in chunks {
let result = fixed_filter_json_tool_calls(chunk);
let result = filter_json_tool_calls(chunk);
results.push(result);
}
@@ -322,7 +322,7 @@ More text"#;
/// Debug test with detailed logging for streaming behavior.
#[test]
fn test_streaming_debug() {
reset_fixed_json_tool_state();
reset_json_tool_state();
// Debug the exact failing case
let chunks = vec![
@@ -335,7 +335,7 @@ More text"#;
let mut results = Vec::new();
for (i, chunk) in chunks.iter().enumerate() {
let result = fixed_filter_json_tool_calls(chunk);
let result = filter_json_tool_calls(chunk);
println!("Chunk {}: {:?} -> {:?}", i, chunk, result);
results.push(result);
}
@@ -351,7 +351,7 @@ More text"#;
/// Test handling of truncated JSON followed by complete JSON (the json_err pattern)
#[test]
fn test_truncated_then_complete_json() {
reset_fixed_json_tool_state();
reset_json_tool_state();
// Simulate the pattern from json_err trace:
// 1. Incomplete/truncated JSON appears
@@ -365,7 +365,7 @@ More text"#;
let mut results = Vec::new();
for (i, chunk) in chunks.iter().enumerate() {
let result = fixed_filter_json_tool_calls(chunk);
let result = filter_json_tool_calls(chunk);
println!("Chunk {}: {:?} -> {:?}", i, chunk, result);
results.push(result);
}