UAT: `agents session tell` produces stub echo output instead of spec-required orchestrator panels #4672

New issue

Closed

opened 2026-04-08 17:59:30 +00:00 by HAL9000 · 1 comment

HAL9000 commented

2026-04-08 17:59:30 +00:00

Owner

Summary

agents session tell produces a stub "Acknowledged: " response instead of the spec-required rich output panels showing orchestrator execution results.

Expected Behavior (from `docs/specification.md` §agents session tell)

The command should display four Rich panels:

Plan Request — Actor, Session, Automation, Prompt
Commands Executed — list of CleverAgents commands the orchestrator issued
Result — action/project/resource created
Usage — Input Tokens, Output Tokens, Cost, Duration, Tool Calls

Success line: ✓ OK Orchestrator completed N commands

Actual Behavior

The implementation in src/cleveragents/cli/commands/session.py (lines 820–860) produces:

assistant_content = (
    f"Acknowledged: {prompt[:100]}"
    if not actor
    else f"[{actor}] Acknowledged: {prompt[:100]}"
)

Output:

user: Hello, world
assistant: Acknowledged: Hello, world

No orchestrator execution occurs. No Plan Request, Commands Executed, Result, or Usage panels are rendered.

Code Location

src/cleveragents/cli/commands/session.py — tell() function, lines 800–860
The docstring itself acknowledges this: "For M3, the actor execution is stubbed — the assistant echoes an acknowledgement."

Impact

This is the primary user interface for CleverAgents (per spec). The stub implementation means users cannot actually interact with the orchestrator via agents session tell.

Steps to Reproduce

# Create a session
agents session create

# Tell the session something
agents session tell --session <SESSION_ID> "Create an action to refresh dependency locks"

Expected: Rich panels showing orchestrator execution
Actual: assistant: Acknowledged: Create an action to refresh dependency locks

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

## Summary `agents session tell` produces a stub "Acknowledged: <prompt>" response instead of the spec-required rich output panels showing orchestrator execution results. ## Expected Behavior (from `docs/specification.md` §agents session tell) The command should display four Rich panels: 1. **Plan Request** — Actor, Session, Automation, Prompt 2. **Commands Executed** — list of CleverAgents commands the orchestrator issued 3. **Result** — action/project/resource created 4. **Usage** — Input Tokens, Output Tokens, Cost, Duration, Tool Calls Success line: `✓ OK Orchestrator completed N commands` ## Actual Behavior The implementation in `src/cleveragents/cli/commands/session.py` (lines 820–860) produces: ```python assistant_content = ( f"Acknowledged: {prompt[:100]}" if not actor else f"[{actor}] Acknowledged: {prompt[:100]}" ) ``` Output: ``` user: Hello, world assistant: Acknowledged: Hello, world ``` No orchestrator execution occurs. No Plan Request, Commands Executed, Result, or Usage panels are rendered. ## Code Location - `src/cleveragents/cli/commands/session.py` — `tell()` function, lines 800–860 - The docstring itself acknowledges this: "For M3, the actor execution is stubbed — the assistant echoes an acknowledgement." ## Impact This is the **primary user interface** for CleverAgents (per spec). The stub implementation means users cannot actually interact with the orchestrator via `agents session tell`. ## Steps to Reproduce ```bash # Create a session agents session create # Tell the session something agents session tell --session <SESSION_ID> "Create an action to refresh dependency locks" ``` Expected: Rich panels showing orchestrator execution Actual: `assistant: Acknowledged: Create an action to refresh dependency locks` --- **Automated by CleverAgents Bot** Supervisor: UAT Testing | Agent: uat-tester

HAL9000 added this to the v3.5.0 milestone

2026-04-08 18:05:39 +00:00

freemo added the

labels

2026-04-08 23:39:47 +00:00

HAL9000 commented

2026-04-09 00:21:25 +00:00

Author

Owner

Closing as duplicate of #4862 — both issues report the same problem: agents session tell is stubbed and does not invoke the real orchestrator actor. Issue #4862 has milestone v3.3.0 assigned.

Automated by CleverAgents Bot
Supervisor: Backlog Grooming | Agent: backlog-groomer

Closing as duplicate of #4862 — both issues report the same problem: `agents session tell` is stubbed and does not invoke the real orchestrator actor. Issue #4862 has milestone v3.3.0 assigned. --- **Automated by CleverAgents Bot** Supervisor: Backlog Grooming | Agent: backlog-groomer

HAL9000 closed this issue

2026-04-09 00:21:31 +00:00

HAL9000 referenced this issue

2026-04-09 00:48:37 +00:00

[AUTO-GROOMER] Backlog Grooming Report (Cycle 4) #5017