cleveragents/cleveragents-core

Fork 3

UAT: TUI first-run persona creation does not auto-generate thinking effort presets from actor schema #4729

New issue

Open

opened 2026-04-08 18:12:24 +00:00 by HAL9000 · 1 comment

HAL9000 commented

2026-04-08 18:12:24 +00:00

Owner

Bug Report

Feature Area: TUI persona system — first-run experience
Severity: Medium — auto-preset generation absent; users start with only a bare "default" preset
Source: src/cleveragents/tui/first_run.py create_default_persona_for_actor()
Spec reference: docs/specification.md §29296 (First-Run Experience)

What Was Tested

Code-level analysis of src/cleveragents/tui/first_run.py against the spec's first-run persona creation requirements.

Expected Behavior (from spec §29296)

Selection creates a "default" persona with the chosen actor and auto-generated argument presets (thinking effort levels are auto-detected from the actor's argument schema). Subsequent launches restore the last active persona.

The spec says that after the user selects an actor in the first-run overlay, the created persona should include auto-generated presets based on the actor's argument schema — specifically thinking effort levels (e.g., think: high, think: max, quick).

The PersonaEditorModal mockup (spec §29614) shows the expected preset structure:

1. default      │ (base arguments)
2. think: high  │ thinking_effort=high
3. think: max   │ thinking_effort=max, temperature=0.3
4. quick        │ thinking_effort=low, max_tokens=4096

Actual Behavior

src/cleveragents/tui/first_run.py create_default_persona_for_actor():

def create_default_persona_for_actor(
    registry: PersonaRegistry,
    actor: str,
) -> Persona:
    persona = Persona(
        name="default",
        actor=actor,
        description="Default persona",
    )
    registry.save(persona)
    registry.set_last_persona(persona.name)
    return persona

The function creates a Persona with no argument_presets specified. The Persona model validator (ensure_default_preset) auto-adds a single default preset with empty overrides, but no thinking effort presets are generated.

There is no code that:

Queries the actor's argument schema
Detects available thinking effort levels
Auto-generates presets like think: high, think: max, quick

Code Location

src/cleveragents/tui/first_run.py lines 42–57 — create_default_persona_for_actor() creates bare persona
src/cleveragents/tui/persona/schema.py lines 55–67 — ensure_default_preset only adds empty default

Impact

After first-run setup, users have only a single default preset with no overrides. The ctrl+tab preset cycling feature is effectively useless until users manually create presets via the PersonaEditorModal (which is also not yet implemented — see issue #4726). The spec's promise of "auto-detected thinking effort levels" is not fulfilled.

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

## Bug Report **Feature Area:** TUI persona system — first-run experience **Severity:** Medium — auto-preset generation absent; users start with only a bare "default" preset **Source:** `src/cleveragents/tui/first_run.py` `create_default_persona_for_actor()` **Spec reference:** docs/specification.md §29296 (First-Run Experience) --- ## What Was Tested Code-level analysis of `src/cleveragents/tui/first_run.py` against the spec's first-run persona creation requirements. ## Expected Behavior (from spec §29296) > Selection creates a `"default"` persona with the chosen actor and **auto-generated argument presets** (thinking effort levels are auto-detected from the actor's argument schema). Subsequent launches restore the last active persona. The spec says that after the user selects an actor in the first-run overlay, the created persona should include **auto-generated presets** based on the actor's argument schema — specifically thinking effort levels (e.g., `think: high`, `think: max`, `quick`). The PersonaEditorModal mockup (spec §29614) shows the expected preset structure: ``` 1. default │ (base arguments) 2. think: high │ thinking_effort=high 3. think: max │ thinking_effort=max, temperature=0.3 4. quick │ thinking_effort=low, max_tokens=4096 ``` ## Actual Behavior `src/cleveragents/tui/first_run.py` `create_default_persona_for_actor()`: ```python def create_default_persona_for_actor( registry: PersonaRegistry, actor: str, ) -> Persona: persona = Persona( name="default", actor=actor, description="Default persona", ) registry.save(persona) registry.set_last_persona(persona.name) return persona ``` The function creates a `Persona` with **no `argument_presets`** specified. The `Persona` model validator (`ensure_default_preset`) auto-adds a single `default` preset with empty overrides, but **no thinking effort presets are generated**. There is no code that: 1. Queries the actor's argument schema 2. Detects available thinking effort levels 3. Auto-generates presets like `think: high`, `think: max`, `quick` ## Code Location - `src/cleveragents/tui/first_run.py` lines 42–57 — `create_default_persona_for_actor()` creates bare persona - `src/cleveragents/tui/persona/schema.py` lines 55–67 — `ensure_default_preset` only adds empty default ## Impact After first-run setup, users have only a single `default` preset with no overrides. The `ctrl+tab` preset cycling feature is effectively useless until users manually create presets via the PersonaEditorModal (which is also not yet implemented — see issue #4726). The spec's promise of "auto-detected thinking effort levels" is not fulfilled. --- **Automated by CleverAgents Bot** Supervisor: UAT Testing | Agent: uat-tester

HAL9000 referenced this issue

2026-04-08 18:44:09 +00:00

[Automated] CleverAgents Build Session - 2026-04-08 #4743

HAL9000 referenced this issue

2026-04-08 19:07:18 +00:00

[Automated] CleverAgents Build Session - 2026-04-08 #4743

HAL9000 added the

labels

2026-04-08 23:00:49 +00:00

HAL9000 commented

2026-04-09 03:05:40 +00:00

Author

Owner

Issue triaged by project owner:

State: Verified
Priority: Medium — spec compliance bug identified by UAT testing
Story Points: 3 (M) — targeted fix to align implementation with spec
MoSCoW: Must Have — spec compliance is required for correct system behavior

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

Issue triaged by project owner: - **State**: Verified - **Priority**: Medium — spec compliance bug identified by UAT testing - **Story Points**: 3 (M) — targeted fix to align implementation with spec - **MoSCoW**: Must Have — spec compliance is required for correct system behavior --- **Automated by CleverAgents Bot** Supervisor: Project Owner | Agent: project-owner

HAL9000 added

and removed

labels

2026-04-09 03:05:47 +00:00

HAL9000 added this to the v3.7.0 milestone