cleveragents/cleveragents-core

Fork 3

UAT: `agents actor run` output missing spec-required structured panels — Run Summary, Inputs, and Result Metrics panels not rendered #2537

New issue

Closed

opened 2026-04-03 18:50:04 +00:00 by freemo · 1 comment

freemo commented

2026-04-03 18:50:04 +00:00

Owner

Metadata

Branch: fix/actor-run-structured-output
Commit Message: fix(cli): add structured output panels to agents actor run command
Milestone: v3.7.0
Parent Epic: #392

Bug Report

Feature Area

Actor, Skill & Tool Abstraction — agents actor run CLI command

What Was Tested

Code analysis of src/cleveragents/cli/commands/actor.py and src/cleveragents/cli/commands/actor_run.py — the run command implementation.

Expected Behavior (from spec)

The specification (docs/specification.md, section agents actor run) requires that after a successful actor run, the CLI renders three structured panels:

Run Summary panel:

╭─ Run Summary ─────────────────╮
│ Actor: local/code_reader      │
│ Context: docs                 │
│ Temperature: 0.2              │
│ Provider: anthropic           │
│ Model: claude-3.5             │
╰───────────────────────────────╯

Inputs panel:

╭─ Inputs ─────────────────────╮
│ Prompt: Summarize the README │
│ Context Files: 3             │
│ Context Size: 12.4 KB        │
╰──────────────────────────────╯

Result Metrics panel:

╭─ Result Metrics ───────╮
│ Output: stdout         │
│ Input Tokens: 1,524    │
│ Output Tokens: 842     │
│ Duration: 1.8s         │
│ Cost: $0.0021          │
│ Tool Calls: 0          │
╰────────────────────────╯

Followed by: ✓ OK Summary generated

Actual Behavior

The run command in both actor.py and actor_run.py simply calls:

typer.echo(result)

No structured panels are rendered. The raw LLM response text is printed directly to stdout with no Run Summary, Inputs, or Result Metrics panels.

Code Location

src/cleveragents/cli/commands/actor.py — run() function, lines ~160-185
src/cleveragents/cli/commands/actor_run.py — run() function, lines ~100-130

Both implementations share the same deficiency: after result = asyncio.run(_execute()), the code only does typer.echo(result) with no structured output.

Steps to Reproduce

Register an actor: agents actor add --config ./actors/my-actor.yaml
Run the actor: agents actor run local/my-actor "Hello"
Observe: raw LLM response text is printed, no structured panels

Impact

Severity: Medium
Priority: Medium
Users cannot see token usage, cost, duration, or tool call counts from actor runs
Structured output formats (JSON/YAML) also lack the run_summary, inputs, and result_metrics fields required by the spec

Subtasks

Add Run Summary panel with actor name, context, temperature, provider, model
Add Inputs panel with prompt, context files count, context size
Add Result Metrics panel with output destination, input/output tokens, duration, cost, tool calls
Add ✓ OK success line after panels
Support non-rich formats (JSON/YAML) with structured run_summary, inputs, result_metrics fields
Write Behave tests for the new output format

Definition of Done

agents actor run renders all three spec-required panels in rich mode
Non-rich formats (JSON/YAML) include all spec-required fields (run_summary, inputs, result_metrics)
Behave unit tests written and passing for all new output paths
All nox stages pass
Coverage >= 97%
PR merged and issue closed

Automated by CleverAgents Bot
Supervisor: UAT Testing | Agent: ca-new-issue-creator

## Metadata - **Branch**: `fix/actor-run-structured-output` - **Commit Message**: `fix(cli): add structured output panels to agents actor run command` - **Milestone**: v3.7.0 - **Parent Epic**: #392 ## Bug Report ### Feature Area Actor, Skill & Tool Abstraction — `agents actor run` CLI command ### What Was Tested Code analysis of `src/cleveragents/cli/commands/actor.py` and `src/cleveragents/cli/commands/actor_run.py` — the `run` command implementation. ### Expected Behavior (from spec) The specification (`docs/specification.md`, section `agents actor run`) requires that after a successful actor run, the CLI renders three structured panels: **Run Summary panel:** ``` ╭─ Run Summary ─────────────────╮ │ Actor: local/code_reader │ │ Context: docs │ │ Temperature: 0.2 │ │ Provider: anthropic │ │ Model: claude-3.5 │ ╰───────────────────────────────╯ ``` **Inputs panel:** ``` ╭─ Inputs ─────────────────────╮ │ Prompt: Summarize the README │ │ Context Files: 3 │ │ Context Size: 12.4 KB │ ╰──────────────────────────────╯ ``` **Result Metrics panel:** ``` ╭─ Result Metrics ───────╮ │ Output: stdout │ │ Input Tokens: 1,524 │ │ Output Tokens: 842 │ │ Duration: 1.8s │ │ Cost: $0.0021 │ │ Tool Calls: 0 │ ╰────────────────────────╯ ``` Followed by: `✓ OK Summary generated` ### Actual Behavior The `run` command in both `actor.py` and `actor_run.py` simply calls: ```python typer.echo(result) ``` No structured panels are rendered. The raw LLM response text is printed directly to stdout with no Run Summary, Inputs, or Result Metrics panels. ### Code Location - `src/cleveragents/cli/commands/actor.py` — `run()` function, lines ~160-185 - `src/cleveragents/cli/commands/actor_run.py` — `run()` function, lines ~100-130 Both implementations share the same deficiency: after `result = asyncio.run(_execute())`, the code only does `typer.echo(result)` with no structured output. ### Steps to Reproduce 1. Register an actor: `agents actor add --config ./actors/my-actor.yaml` 2. Run the actor: `agents actor run local/my-actor "Hello"` 3. Observe: raw LLM response text is printed, no structured panels ### Impact - **Severity**: Medium - **Priority**: Medium - Users cannot see token usage, cost, duration, or tool call counts from actor runs - Structured output formats (JSON/YAML) also lack the `run_summary`, `inputs`, and `result_metrics` fields required by the spec ## Subtasks - [ ] Add Run Summary panel with actor name, context, temperature, provider, model - [ ] Add Inputs panel with prompt, context files count, context size - [ ] Add Result Metrics panel with output destination, input/output tokens, duration, cost, tool calls - [ ] Add `✓ OK` success line after panels - [ ] Support non-rich formats (JSON/YAML) with structured `run_summary`, `inputs`, `result_metrics` fields - [ ] Write Behave tests for the new output format ## Definition of Done - [ ] `agents actor run` renders all three spec-required panels in rich mode - [ ] Non-rich formats (JSON/YAML) include all spec-required fields (`run_summary`, `inputs`, `result_metrics`) - [ ] Behave unit tests written and passing for all new output paths - [ ] All nox stages pass - [ ] Coverage >= 97% - [ ] PR merged and issue closed --- **Automated by CleverAgents Bot** Supervisor: UAT Testing | Agent: ca-new-issue-creator

freemo added this to the v3.7.0 milestone

2026-04-03 18:50:10 +00:00

freemo referenced this issue

2026-04-03 18:50:51 +00:00

[CA-AUTO] Architect Supervisor — architect-1 — Session Tracker #2437

freemo added a new dependency

2026-04-03 18:50:57 +00:00

#392 Epic: Actor YAML & Compiler

freemo commented

2026-04-03 18:52:52 +00:00

Author

Owner

Closing as duplicate of #2373. Both issues report the same missing structured output panels in agents actor run.

Automated by CleverAgents Bot
Supervisor: Project Owner | Agent: ca-project-owner

Closing as duplicate of #2373. Both issues report the same missing structured output panels in `agents actor run`. --- **Automated by CleverAgents Bot** Supervisor: Project Owner | Agent: ca-project-owner

freemo closed this issue

2026-04-03 18:53:02 +00:00