UAT: agents plan execute rich output missing spec-required execution detail sections — single basic panel shown instead of structured progress panels #3510

Open
opened 2026-04-05 18:44:39 +00:00 by freemo · 0 comments
Owner

Metadata

  • Branch: fix/plan-execute-rich-output-structured-progress-panels
  • Commit Message: fix(cli): render spec-required structured execution progress panels in agents plan execute rich output
  • Milestone: (backlog — see note below)
  • Parent Epic: #397

Backlog note: This issue was discovered during autonomous operation
on milestone v3.5.0. It does not block milestone completion and has been
placed in the backlog for human review and future milestone assignment.

Background

Code-level analysis of src/cleveragents/cli/commands/plan.py against docs/specification.md §"agents plan execute" revealed that the rich terminal output for agents plan execute <PLAN_ID> does not match the spec-required structured execution progress display.

The execute_plan() function (lines 1899–1917 of plan.py) calls _print_lifecycle_plan(plan, title="Plan Executed"), which renders the same basic single panel used by agents plan status. The spec requires structured execution progress panels showing sandbox info, tool calls, phase progression, and more.

Note: Issue #3435 covers the JSON output format for agents plan execute. This issue is specifically about the rich (terminal) output format.

Problem Description

Expected Behavior (from spec §"agents plan execute")

agents plan execute should display execution progress with the following structured panels:

  1. Execution progress panel — Real-time progress through Strategize and Execute phases
  2. Sandbox panel — Sandbox reference, environment type
  3. Tool Calls panel — Count of tool invocations, success/failure breakdown
  4. Files Modified panel — Count and list of files changed in sandbox
  5. Child Plans panel — Count and status of spawned subplans
  6. Checkpoints panel — Checkpoint IDs created during execution
  7. Strategy Summary — Brief summary of the strategy produced during Strategize phase

Actual Behavior (from implementation)

execute_plan() (lines 1899–1917) calls _print_lifecycle_plan(plan, title="Plan Executed"), which renders a single basic panel containing only: ID, Name, Action, Phase, Processing State, Projects, Description, Actors, Timestamps, Error.

Missing from Implementation

  • Execution progress display (Strategize → Execute phase progression)
  • Sandbox reference and environment type
  • Tool Calls count and success/failure breakdown
  • Files Modified count and list
  • Child Plans count and status
  • Checkpoints created during execution
  • Strategy summary from Strategize phase

Code Locations

  • src/cleveragents/cli/commands/plan.pyexecute_plan() function (lines 1732–1939), specifically lines 1899–1917 where rich output is rendered
  • src/cleveragents/cli/commands/plan.py_print_lifecycle_plan() function (lines 1192–1389)

Steps to Reproduce

  1. Create a plan: agents plan use <action> <project>
  2. Execute the plan: agents plan execute <PLAN_ID>
  3. Observe: Basic single panel shown instead of structured execution progress panels

Subtasks

  • Audit docs/specification.md §"agents plan execute" to capture all required rich output panel specifications
  • Design a dedicated _print_execute_result() (or equivalent) rich rendering function for execution output
  • Implement Execution Progress panel showing Strategize → Execute phase progression
  • Implement Sandbox panel showing sandbox reference and environment type
  • Implement Tool Calls panel showing invocation count and success/failure breakdown
  • Implement Files Modified panel showing count and list of files changed in sandbox
  • Implement Child Plans panel showing count and status of spawned subplans
  • Implement Checkpoints panel showing checkpoint IDs created during execution
  • Implement Strategy Summary section showing the strategy produced during Strategize phase
  • Replace the _print_lifecycle_plan(plan, title="Plan Executed") call in execute_plan() with the new rich rendering function
  • Write Behave unit tests covering all new rich output panel rendering paths
  • Write Robot Framework integration tests verifying end-to-end rich output for agents plan execute

Definition of Done

  • agents plan execute <PLAN_ID> rich terminal output displays all spec-required structured panels (Execution Progress, Sandbox, Tool Calls, Files Modified, Child Plans, Checkpoints, Strategy Summary)
  • The basic single-panel fallback (_print_lifecycle_plan) is no longer used for execution output
  • All new rendering logic is statically typed and passes nox -e typecheck
  • Behave unit tests cover all new panel rendering branches
  • Robot Framework integration tests verify the full rich output end-to-end
  • All nox stages pass
  • Coverage >= 97%

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

## Metadata - **Branch**: `fix/plan-execute-rich-output-structured-progress-panels` - **Commit Message**: `fix(cli): render spec-required structured execution progress panels in agents plan execute rich output` - **Milestone**: *(backlog — see note below)* - **Parent Epic**: #397 > **Backlog note:** This issue was discovered during autonomous operation > on milestone v3.5.0. It does not block milestone completion and has been > placed in the backlog for human review and future milestone assignment. ## Background Code-level analysis of `src/cleveragents/cli/commands/plan.py` against `docs/specification.md` §"agents plan execute" revealed that the rich terminal output for `agents plan execute <PLAN_ID>` does not match the spec-required structured execution progress display. The `execute_plan()` function (lines 1899–1917 of `plan.py`) calls `_print_lifecycle_plan(plan, title="Plan Executed")`, which renders the same basic single panel used by `agents plan status`. The spec requires structured execution progress panels showing sandbox info, tool calls, phase progression, and more. **Note**: Issue #3435 covers the JSON output format for `agents plan execute`. This issue is specifically about the rich (terminal) output format. ## Problem Description ### Expected Behavior (from spec §"agents plan execute") `agents plan execute` should display execution progress with the following structured panels: 1. **Execution progress panel** — Real-time progress through Strategize and Execute phases 2. **Sandbox panel** — Sandbox reference, environment type 3. **Tool Calls panel** — Count of tool invocations, success/failure breakdown 4. **Files Modified panel** — Count and list of files changed in sandbox 5. **Child Plans panel** — Count and status of spawned subplans 6. **Checkpoints panel** — Checkpoint IDs created during execution 7. **Strategy Summary** — Brief summary of the strategy produced during Strategize phase ### Actual Behavior (from implementation) `execute_plan()` (lines 1899–1917) calls `_print_lifecycle_plan(plan, title="Plan Executed")`, which renders a single basic panel containing only: ID, Name, Action, Phase, Processing State, Projects, Description, Actors, Timestamps, Error. ### Missing from Implementation - Execution progress display (Strategize → Execute phase progression) - Sandbox reference and environment type - Tool Calls count and success/failure breakdown - Files Modified count and list - Child Plans count and status - Checkpoints created during execution - Strategy summary from Strategize phase ## Code Locations - `src/cleveragents/cli/commands/plan.py` — `execute_plan()` function (lines 1732–1939), specifically lines 1899–1917 where rich output is rendered - `src/cleveragents/cli/commands/plan.py` — `_print_lifecycle_plan()` function (lines 1192–1389) ## Steps to Reproduce 1. Create a plan: `agents plan use <action> <project>` 2. Execute the plan: `agents plan execute <PLAN_ID>` 3. Observe: Basic single panel shown instead of structured execution progress panels ## Subtasks - [ ] Audit `docs/specification.md` §"agents plan execute" to capture all required rich output panel specifications - [ ] Design a dedicated `_print_execute_result()` (or equivalent) rich rendering function for execution output - [ ] Implement **Execution Progress panel** showing Strategize → Execute phase progression - [ ] Implement **Sandbox panel** showing sandbox reference and environment type - [ ] Implement **Tool Calls panel** showing invocation count and success/failure breakdown - [ ] Implement **Files Modified panel** showing count and list of files changed in sandbox - [ ] Implement **Child Plans panel** showing count and status of spawned subplans - [ ] Implement **Checkpoints panel** showing checkpoint IDs created during execution - [ ] Implement **Strategy Summary** section showing the strategy produced during Strategize phase - [ ] Replace the `_print_lifecycle_plan(plan, title="Plan Executed")` call in `execute_plan()` with the new rich rendering function - [ ] Write Behave unit tests covering all new rich output panel rendering paths - [ ] Write Robot Framework integration tests verifying end-to-end rich output for `agents plan execute` ## Definition of Done - [ ] `agents plan execute <PLAN_ID>` rich terminal output displays all spec-required structured panels (Execution Progress, Sandbox, Tool Calls, Files Modified, Child Plans, Checkpoints, Strategy Summary) - [ ] The basic single-panel fallback (`_print_lifecycle_plan`) is no longer used for execution output - [ ] All new rendering logic is statically typed and passes `nox -e typecheck` - [ ] Behave unit tests cover all new panel rendering branches - [ ] Robot Framework integration tests verify the full rich output end-to-end - [ ] All nox stages pass - [ ] Coverage >= 97% --- **Automated by CleverAgents Bot** Supervisor: UAT Testing | Agent: ca-new-issue-creator
freemo added this to the v3.7.0 milestone 2026-04-05 20:36:06 +00:00
Sign in to join this conversation.
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Blocks
#397 Epic: Server & Autonomy Infrastructure
cleveragents/cleveragents-core
Reference
cleveragents/cleveragents-core#3510
No description provided.