darthrubik
41b49aeeae
Replace hardcoded /tmp/drharness_output.txt with $TEST_TEMP_DIR/drharness_output.txt in all test files. Tests should only write to subfiles/directories of the working directory (which is already a temp directory created by run_test.sh).
115 lines
2.9 KiB
Bash
Executable File
115 lines
2.9 KiB
Bash
Executable File
#!/bin/bash
|
|
# test_edit_history_then_continue.sh - Edit then continue conversation normally
|
|
|
|
# Helper function to run drharness and capture output to a temp file
|
|
run_drharness() {
|
|
"$DRHARNESS" "$@" > "$TEST_TEMP_DIR/drharness_output.txt" 2>&1
|
|
return $?
|
|
}
|
|
|
|
# Helper to get the output
|
|
get_output() {
|
|
cat "$TEST_TEMP_DIR/drharness_output.txt"
|
|
}
|
|
|
|
# Helper to reset editor state for each test
|
|
reset_editor_state() {
|
|
rm -f .editor_input_* .editor_invocation_count hist.md
|
|
}
|
|
|
|
reset_editor_state
|
|
|
|
# Create a chat file with two messages
|
|
create_chat_file chat.json user "hello" assistant "hi there"
|
|
|
|
# Stage the rebase editor output (edit message 0)
|
|
cat > .editor_input_0 << 'EDITEOF'
|
|
# History Rebase Editor
|
|
#
|
|
# Commands:
|
|
# pick - keep the message unchanged
|
|
# edit - modify the message content and/or role
|
|
# drop - remove the message from history
|
|
#
|
|
# Each line format: <command> <index> [<role>] <display_content>
|
|
# - index: 0-based message index
|
|
# - role: [user], [assistant], or [tool] (editable)
|
|
# - display_content: first line of message (display only, not editable here)
|
|
#
|
|
# Lines starting with # are comments and will be ignored.
|
|
# Empty lines are treated as drops.
|
|
#
|
|
-- >8 --
|
|
edit 0 [user] hello
|
|
pick 1 [assistant] hi there
|
|
EDITEOF
|
|
|
|
# Stage the edit prompt response
|
|
cat > .editor_input_1 << 'EDITEOF'
|
|
# (no previous message)
|
|
|
|
Edit message 0 (role: user) below:
|
|
|
|
-- >8 --
|
|
hello world
|
|
EDITEOF
|
|
|
|
# Run drharness with -b flag to edit history
|
|
set +e
|
|
VISUAL="$MOCK_EDITOR" run_drharness -b -F chat.json
|
|
EXIT_CODE=$?
|
|
OUTPUT=$(get_output)
|
|
set -e
|
|
|
|
if [ ${EXIT_CODE} -ne 0 ]; then
|
|
echo "FAIL: edit_then_continue - edit phase: expected exit code 0, got $EXIT_CODE"
|
|
echo "Output: $OUTPUT"
|
|
exit 1
|
|
fi
|
|
|
|
# Verify the edit was saved
|
|
msg0_content=$(dr_result chat.json 0)
|
|
if [ "$msg0_content" != "hello world" ]; then
|
|
echo "FAIL: edit_then_continue - edit not saved correctly"
|
|
exit 1
|
|
fi
|
|
|
|
# Now run drharness normally (without -b) to continue the conversation
|
|
# We need a new editor input for the normal flow
|
|
# Reset staged inputs for the second run
|
|
cat > .editor_input_0 << 'EDITEOF'
|
|
[assistant] hi there
|
|
|
|
-- >8 --
|
|
|
|
how are you?
|
|
EDITEOF
|
|
|
|
# Reset the invocation counter for the new run
|
|
echo "0" > .editor_invocation_count
|
|
|
|
# Create mock LLM response for the debug client
|
|
be_done "I'm doing well, thanks for asking!" > mock_responses.txt
|
|
|
|
# Run drharness normally (uses DebugClient to read from stdin)
|
|
set +e
|
|
VISUAL="$MOCK_EDITOR" run_drharness -d -F chat.json < mock_responses.txt
|
|
EXIT_CODE=$?
|
|
OUTPUT=$(get_output)
|
|
set -e
|
|
|
|
if [ ${EXIT_CODE} -ne 0 ]; then
|
|
echo "FAIL: edit_then_continue - continue phase: expected exit code 0, got $EXIT_CODE"
|
|
echo "Output: $OUTPUT"
|
|
exit 1
|
|
fi
|
|
|
|
# Verify the history now has 4 messages (original 2 + new user message + new assistant response)
|
|
len=$(history_length chat.json)
|
|
if [ "$len" != "4" ]; then
|
|
echo "FAIL: edit_then_continue - expected 4 messages after continue, got $len"
|
|
exit 1
|
|
fi
|
|
|
|
echo "PASS: edit_then_continue"
|