UAT: `agents actor run` is single-shot only — missing interactive mode, `--project`, and `--session` flags #6303

New issue

Open

opened 2026-04-09 20:08:13 +00:00 by HAL9000 · 0 comments

HAL9000 commented

2026-04-09 20:08:13 +00:00

Owner

Summary

The spec defines agents actor run <ACTOR_NAME> [--skill <SKILL>] [--project <PROJECT>] [--session <SESSION>] as starting an interactive session with the named actor. The implementation instead requires a mandatory positional <PROMPT> argument and executes a single-shot run, never entering interactive mode. The --project and --session flags are entirely absent.

Spec Reference

docs/specification.md — Actor Commands:

agents actor run <ACTOR_NAME> [--skill <SKILL>] [--project <PROJECT>] [--session <SESSION>]

Starts an interactive session with the actor
--project scopes the session to a project
--session attaches to or resumes a named session

Code Location

src/cleveragents/cli/commands/actor.py, lines 48–200

@app.command()
def run(
    name: ...,
    prompt: Annotated[str, typer.Argument(help="Prompt text to send to the actor")],  # line 54 — mandatory
    ...
    skill: list[str] | None = None,  # present ✓
    # --project: MISSING
    # --session: MISSING
) -> None:

The function body calls app_exec.run_single_shot(prompt, ...) (lines 144, 158, 168, 177) — there is no interactive REPL loop.

Steps to Reproduce

# Try to start an interactive actor session as per spec
agents actor run local/my-actor --project my-project --session ws1
# Error: no such options --project / --session
# Without those flags, the command requires a positional <prompt> arg and exits immediately after one round-trip

Expected vs Actual

	Expected	Actual
Command signature	`run <ACTOR_NAME> [--skill] [--project] [--session]`	`run <NAME> <PROMPT> [--skill] [--config] [--output] ...`
Mode	Interactive session (REPL loop)	Single-shot prompt/response
`--project` flag	Present	Missing
`--session` flag	Present	Missing

Impact

Users cannot start persistent interactive actor sessions. Project and session scoping for actor runs is unavailable.

Automated by CleverAgents Bot
Supervisor: UAT Testing | Agent: uat-tester

## Summary The spec defines `agents actor run <ACTOR_NAME> [--skill <SKILL>] [--project <PROJECT>] [--session <SESSION>]` as starting an **interactive session** with the named actor. The implementation instead requires a mandatory positional `<PROMPT>` argument and executes a single-shot run, never entering interactive mode. The `--project` and `--session` flags are entirely absent. ## Spec Reference `docs/specification.md` — Actor Commands: ``` agents actor run <ACTOR_NAME> [--skill <SKILL>] [--project <PROJECT>] [--session <SESSION>] ``` - Starts an **interactive session** with the actor - `--project` scopes the session to a project - `--session` attaches to or resumes a named session ## Code Location `src/cleveragents/cli/commands/actor.py`, lines 48–200 ```python @app.command() def run( name: ..., prompt: Annotated[str, typer.Argument(help="Prompt text to send to the actor")], # line 54 — mandatory ... skill: list[str] | None = None, # present ✓ # --project: MISSING # --session: MISSING ) -> None: ``` The function body calls `app_exec.run_single_shot(prompt, ...)` (lines 144, 158, 168, 177) — there is no interactive REPL loop. ## Steps to Reproduce ```bash # Try to start an interactive actor session as per spec agents actor run local/my-actor --project my-project --session ws1 # Error: no such options --project / --session # Without those flags, the command requires a positional <prompt> arg and exits immediately after one round-trip ``` ## Expected vs Actual | | Expected | Actual | |---|---|---| | Command signature | `run <ACTOR_NAME> [--skill] [--project] [--session]` | `run <NAME> <PROMPT> [--skill] [--config] [--output] ...` | | Mode | Interactive session (REPL loop) | Single-shot prompt/response | | `--project` flag | Present | **Missing** | | `--session` flag | Present | **Missing** | ## Impact Users cannot start persistent interactive actor sessions. Project and session scoping for actor runs is unavailable. --- **Automated by CleverAgents Bot** Supervisor: UAT Testing | Agent: uat-tester

HAL9000 referenced this issue

2026-04-09 20:18:09 +00:00

[AUTO-UAT-POOL] UAT Testing Report (Cycle 3) #6294

HAL9000 added the

labels

2026-04-09 20:19:29 +00:00