fix(cli,gen): redirect tracing to stderr and add LocalGPT label on responses

[Copilot]

Tracing output was written to stdout, causing log lines to interleave with streamed model output mid-line. Additionally, model responses were missing the LocalGPT: label and leading newline in both the chat CLI and gen CLI.

Changes

• crates/cli/src/main.rs — Added .with_writer(std::io::stderr) to both tracing subscriber initializations (gen-mode and async_main), routing all log output to stderr and away from the streamed stdout output.

• crates/cli/src/cli/chat.rs — Changed follow-up response print from print!("{}", follow_up) to print!("\nLocalGPT: {}", follow_up), matching the label applied to the initial response and ensuring clean line separation after tool call output.

• crates/gen/src/main.rs — Applied the same fixes as the CLI: added .with_writer(std::io::stderr) to the tracing subscriber, and updated both response println! calls to use the LocalGPT: label (println!("\nLocalGPT: {}\n", response)) for both the initial-prompt path and the interactive loop — consistent with the chat CLI.

// Before
print!("{}", follow_up);
println!("\n{}\n", response); // gen CLI

// After
print!("\nLocalGPT: {}", follow_up);
println!("\nLocalGPT: {}\n", response); // gen CLI

Original prompt

Problem

When using the localgpt CLI (localgpt chat), the output has formatting inconsistencies:

1. Log lines interleave with streamed model output: Tracing/log output can appear mid-line during streaming, mixing with the model's response text.
2. Missing line breaks before follow-up responses: After tool execution, the follow-up model response concatenates directly with previous content without a proper line break or "LocalGPT:" label.

Root Cause

In crates/cli/src/cli/chat.rs:

Issue 1: Tool follow-up output (line 500)

print!("{}", follow_up);

After tool calls are executed and the follow-up response is printed, there is no leading newline or "LocalGPT:" label. This causes the follow-up text to concatenate directly onto the end of the previous tool call output.

Issue 2: Streaming delta output (line 422)

print!("{}", chunk.delta);

Log lines from tracing/other threads can interleave with the streamed chunks mid-line since stdout and stderr are not synchronized. The tracing subscriber should be configured to write to stderr or a log file, not stdout, to avoid interleaving.

Issue 3: Post-stream newlines (line 520)

println!("\n");

This adds trailing spacing after the full stream, but if tool calls intervene, the newline before the follow-up "LocalGPT:" response is absent.

Required Changes in crates/cli/src/cli/chat.rs

1. Line 500: Change print!("{}", follow_up) to print!("\nLocalGPT: {}", follow_up) so the follow-up response after tool execution starts on a fresh line with the proper label, consistent with the initial response label on line 410.

2. Ensure newlines before tool call notifications (lines 447-450 and 482-485): The tool call markers like [tool_name: detail] should always start on a clean new line. Currently they use println!("\n[...]") which should be sufficient, but verify they produce clean output after streamed content that may not end with a newline.

3. Verify tracing/logging is directed to stderr or a file, not stdout: Check that the tracing subscriber setup in the CLI entry point does not write to stdout. If it does, it should be changed to write to stderr (std::io::stderr()) to prevent log lines from interleaving with the streamed model output. Look at the CLI's main entry point and tracing initialization code (likely in crates/cli/src/main.rs or similar) to ensure the tracing layer uses stderr or a file writer, not stdout.

Expected Behavior

• The "LocalGPT:" label should appear on its own line before every model response, including follow-up responses after tool execution.
• Log/tracing output should not interleave with streamed model output on the same line.
• Each distinct section of output (user prompt, model response, tool calls, follow-up) should be clearly separated by line breaks.

This pull request was created from Copilot chat.

---

💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.

[yiwang]

@copilot make sure gen mode cli also have the same fix, refactor to use same code between those 2 cli as much as possible

[Copilot]

@copilot make sure gen mode cli also have the same fix, refactor to use same code between those 2 cli as much as possible

Done in commit 2135713. Applied the same two fixes to crates/gen/src/main.rs:

1. Added .with_writer(std::io::stderr) to the tracing subscriber (same as the CLI fix).
2. Updated both response println! calls (println!("\n{}\n", response) → println!("\nLocalGPT: {}\n", response)) for the initial-prompt path and the interactive loop — consistent with the \nLocalGPT: label used in the chat CLI.