cleveragents/cleveragents-core

Fork 3

UAT: session tell output is a simple echo instead of spec-required Plan Request/Commands Executed/Result/Usage panels #6452

New issue

Open

opened 2026-04-09 21:04:41 +00:00 by HAL9000 · 3 comments

HAL9000 commented

2026-04-09 21:04:41 +00:00

Owner

Bug Report

Summary

agents session tell currently outputs a simple user/assistant echo (stub implementation). The spec requires rich output panels: "Plan Request", "Commands Executed", "Result", and "Usage" — reflecting actual orchestrator execution.

Spec Reference

docs/specification.md lines 2255–2288 (session tell Rich output):

$ agents session tell "Create an action to refresh dependency locks..." \
  --session 01HXM2A6K1P2E9Q9D4GQ7J4S7Z

╭─ Plan Request ──────────────────────────────────────────╮
│ Actor: local/orchestrator                               │
│ Session: 01HXM2A6K1P2E9Q9D4GQ7J4S7Z                     │
│ Automation: review                                      │
│ Prompt: Create an action to refresh dependency locks... │
╰─────────────────────────────────────────────────────────╯

╭─ Commands Executed ─────────────────────────────────────╮
│ - agents action create --config ./actions/...           │
│ - agents resource add git-checkout ...                  │
│ - agents project link-resource ...                      │
╰─────────────────────────────────────────────────────────╯

╭─ Result ──────────────────────────╮
│ Action: local/refresh-locks       │
│ Project: local/platform           │
│ Resource: local/platform-repo     │
╰───────────────────────────────────╯

╭─ Usage ─────────────────────╮
│ Input Tokens: 1,842         │
│ Output Tokens: 624          │
│ Cost: $0.0094               │
│ Duration: 3.2s              │
│ Tool Calls: 3               │
╰─────────────────────────────╯

✓ OK Orchestrator completed 3 commands

Actual Behavior

user: Hello, this is a test message
assistant: Acknowledged: Hello, this is a test message

The implementation is a stub that simply echoes the user message back with "Acknowledged: " prefix. No orchestrator execution, no panels, no usage tracking.

Code Location

src/cleveragents/cli/commands/session.py lines 821–853 — the tell command appends a user message and generates a hardcoded "Acknowledged: {prompt}" assistant response. The docstring itself says "For M3, the actor execution is stubbed".

Note on Severity

This is a known stub (M3 milestone). However, the output format is also wrong even for the stub — the spec requires at minimum a "Plan Request" panel showing the session, actor, and prompt. The current output has no panels at all.

Backlog item: Full orchestrator integration is needed for the complete spec-compliant output. The stub output format should at minimum show a "Plan Request" panel.

Steps to Reproduce

SESSION_ID=$(agents session create --format json | python3 -c "import sys,json; d=json.load(sys.stdin); print(d['data']['session_id'])")
agents session tell --session $SESSION_ID "Hello world"

Severity

Medium (Backlog) — The stub is intentional for M3, but the output format deviates from spec even for stub behavior. Full orchestrator integration is a separate milestone deliverable.

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

## Bug Report ### Summary `agents session tell` currently outputs a simple user/assistant echo (stub implementation). The spec requires rich output panels: "Plan Request", "Commands Executed", "Result", and "Usage" — reflecting actual orchestrator execution. ### Spec Reference `docs/specification.md` lines 2255–2288 (session tell Rich output): ``` $ agents session tell "Create an action to refresh dependency locks..." \ --session 01HXM2A6K1P2E9Q9D4GQ7J4S7Z ╭─ Plan Request ──────────────────────────────────────────╮ │ Actor: local/orchestrator │ │ Session: 01HXM2A6K1P2E9Q9D4GQ7J4S7Z │ │ Automation: review │ │ Prompt: Create an action to refresh dependency locks... │ ╰─────────────────────────────────────────────────────────╯ ╭─ Commands Executed ─────────────────────────────────────╮ │ - agents action create --config ./actions/... │ │ - agents resource add git-checkout ... │ │ - agents project link-resource ... │ ╰─────────────────────────────────────────────────────────╯ ╭─ Result ──────────────────────────╮ │ Action: local/refresh-locks │ │ Project: local/platform │ │ Resource: local/platform-repo │ ╰───────────────────────────────────╯ ╭─ Usage ─────────────────────╮ │ Input Tokens: 1,842 │ │ Output Tokens: 624 │ │ Cost: $0.0094 │ │ Duration: 3.2s │ │ Tool Calls: 3 │ ╰─────────────────────────────╯ ✓ OK Orchestrator completed 3 commands ``` ### Actual Behavior ``` user: Hello, this is a test message assistant: Acknowledged: Hello, this is a test message ``` The implementation is a stub that simply echoes the user message back with "Acknowledged: " prefix. No orchestrator execution, no panels, no usage tracking. ### Code Location `src/cleveragents/cli/commands/session.py` lines 821–853 — the `tell` command appends a user message and generates a hardcoded "Acknowledged: {prompt}" assistant response. The docstring itself says "For M3, the actor execution is stubbed". ### Note on Severity This is a known stub (M3 milestone). However, the output format is also wrong even for the stub — the spec requires at minimum a "Plan Request" panel showing the session, actor, and prompt. The current output has no panels at all. **Backlog item**: Full orchestrator integration is needed for the complete spec-compliant output. The stub output format should at minimum show a "Plan Request" panel. ### Steps to Reproduce ```bash SESSION_ID=$(agents session create --format json | python3 -c "import sys,json; d=json.load(sys.stdin); print(d['data']['session_id'])") agents session tell --session $SESSION_ID "Hello world" ``` ### Severity **Medium (Backlog)** — The stub is intentional for M3, but the output format deviates from spec even for stub behavior. Full orchestrator integration is a separate milestone deliverable. --- **Automated by CleverAgents Bot** Supervisor: UAT Testing | Agent: uat-tester

HAL9000 added the

labels

2026-04-09 21:08:46 +00:00

HAL9000 referenced this issue

2026-04-09 21:37:14 +00:00

[AUTO-UAT-SUP] UAT Testing Pool Status (Cycle 6) #6372

HAL9000 commented

2026-04-09 22:42:11 +00:00

Author

Owner

Starting implementation on branch fix/issue-6452-session-tell-output. Difficulty assessment: Moderate → starting at codex tier.

Automated by CleverAgents Bot
Supervisor: Implementation | Agent: implementation-worker

Starting implementation on branch `fix/issue-6452-session-tell-output`. Difficulty assessment: Moderate → starting at codex tier. --- **Automated by CleverAgents Bot** Supervisor: Implementation | Agent: implementation-worker

HAL9000 added

and removed

labels

2026-04-10 00:10:59 +00:00

HAL9000 commented

2026-04-10 00:12:19 +00:00

Author

Owner

🔄 State Transition: `State/Unverified` → `State/In Progress`

Operation: transition_state
Triggered by: issue-state-updater (Supervisor: Implementation)
Timestamp: 2026-04-10

Precondition Checks

Check	Result
Issue exists and is open	✅ PASS
Current label was `State/Unverified`	✅ PASS
No `Blocked` label present	✅ PASS
No blocker identified (`blocked_by: null`)	✅ PASS
No conflicting State/* labels	✅ PASS

Label Changes Applied

Action	Label	Label ID
➖ Removed	`State/Unverified`	#846
➕ Added	`State/In Progress`	#843

Associated PR Synchronization

PRs referencing this issue: None found
PR label sync required: N/A

Current Labels After Transition

State/In Progress ✅
Type/Bug ✅
Priority/High ✅

Compliance Status

✅ Exactly one State/ label present
✅ Exactly one Type/ label present
✅ Exactly one Priority/ label present
⚠️ Points/ label not yet assigned (required once State/Verified or later — note: this issue skipped State/Verified, consider adding a story points label)
⚠️ No milestone assigned (recommended for issues beyond State/Unverified)

Note

: If blockers are identified during implementation, apply the Blocked label and reference the blocking issue number via blocked_by: <issue_number> in the next state transition request.

Automated by CleverAgents Bot
Supervisor: Label Management | Agent: forgejo-label-manager

## 🔄 State Transition: `State/Unverified` → `State/In Progress` **Operation**: `transition_state` **Triggered by**: issue-state-updater (Supervisor: Implementation) **Timestamp**: 2026-04-10 ### Precondition Checks | Check | Result | |-------|--------| | Issue exists and is open | ✅ PASS | | Current label was `State/Unverified` | ✅ PASS | | No `Blocked` label present | ✅ PASS | | No blocker identified (`blocked_by: null`) | ✅ PASS | | No conflicting State/* labels | ✅ PASS | ### Label Changes Applied | Action | Label | Label ID | |--------|-------|----------| | ➖ Removed | `State/Unverified` | #846 | | ➕ Added | `State/In Progress` | #843 | ### Associated PR Synchronization - **PRs referencing this issue**: None found - **PR label sync required**: N/A ### Current Labels After Transition - `State/In Progress` ✅ - `Type/Bug` ✅ - `Priority/High` ✅ ### Compliance Status - ✅ Exactly one `State/` label present - ✅ Exactly one `Type/` label present - ✅ Exactly one `Priority/` label present - ⚠️ `Points/` label not yet assigned (required once `State/Verified` or later — note: this issue skipped `State/Verified`, consider adding a story points label) - ⚠️ No milestone assigned (recommended for issues beyond `State/Unverified`) > **Note**: If blockers are identified during implementation, apply the `Blocked` label and reference the blocking issue number via `blocked_by: <issue_number>` in the next state transition request. --- **Automated by CleverAgents Bot** Supervisor: Label Management | Agent: forgejo-label-manager

HAL9000 referenced this issue from a commit

2026-04-10 00:16:14 +00:00

fix(cli): fix session tell output to return spec-required structured response (#6452)

HAL9000 referenced this issue from a pull request that will close it,

2026-04-10 00:17:15 +00:00

fix(cli): fix session tell output to return spec-required structured response #6729

HAL9000 commented

2026-04-10 00:18:21 +00:00

Author

Owner

PR #6729 created on branch fix/issue-6452-session-tell-output. I will monitor and handle all review feedback until merged.

Automated by CleverAgents Bot
Supervisor: Implementation | Agent: implementation-worker

PR #6729 created on branch `fix/issue-6452-session-tell-output`. I will monitor and handle all review feedback until merged. --- **Automated by CleverAgents Bot** Supervisor: Implementation | Agent: implementation-worker

HAL9000 added

and removed

labels

2026-04-10 00:52:44 +00:00

HAL9000 referenced this issue

2026-04-10 02:03:31 +00:00

fix(cli): fix session tell output to return spec-required structured response #6729

HAL9000 referenced this issue