[luv-22] Stream tool calls in -nit mode via stream-json (#22)

* [luv-22] Stream tool calls in -nit mode via stream-json

claude -p only prints the final result by default, so -nit hid every tool
call and intermediate turn. Switch the non-interactive invocation to
--output-format stream-json --verbose --include-partial-messages so each
event surfaces on stdout as it happens.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* Bump to 0.0.16 and document -nit stream-json output

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>

Author: NiveditJain

README.md

@@ -72,7 +72,7 @@ All workspaces live under `~/prs/`. The number comes from the repo's GitHub issu
 | `-n` | Navigate: open a shell instead of Claude |
 | `-r` | Resume: resume the last Claude session |
 | `-p` | Launch Claude in plan permission mode (default: `bypassPermissions`) |
-| `-nit` | Non-interactive: run `claude -p <prompt>` and exit (no REPL) |
+| `-nit` | Non-interactive: run `claude -p <prompt>` and exit (no REPL); streams `stream-json` events to stdout |
 | `-e` | Env: pass `LUV_*` environment variables (with prefix stripped) into the session |
 | `-f`, `--force` | Skip safety checks (with `--clean`) |
 

luv/__init__.py

@@ -363,7 +363,8 @@ def launch(clone_dir: Path, prompt: str | None, plan_mode: bool = False,
     if non_interactive:
         if not prompt:
             die("-nit requires a prompt")
-        mode_flags = []
+        mode_flags = ["--output-format", "stream-json",
+                      "--verbose", "--include-partial-messages"]
         initial_args = ["-p", prompt]
     elif plan_mode:
         mode_flags = ["--permission-mode", "plan"]

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "luv-cli"
-version = "0.0.15"
+version = "0.0.16"
 description = "Launch Claude Code agents on GitHub repos with isolated workspaces and optional Docker dev environments"
 requires-python = ">=3.10"
 license = "MIT"