UAT: `agents project context inspect` output missing spec-required `uko_graph`, `active_strategies`, and detailed `budget` fields — returns tier metrics instead #2502

New issue

Open

opened 2026-04-03 18:40:24 +00:00 by freemo · 1 comment

freemo commented

2026-04-03 18:40:24 +00:00

Owner

Summary

agents project context inspect returns tier-based metrics (tier_metrics, tier_budget, project_fragments, actor_visibility, phase_analysis) instead of the spec-required ACMS inspection data (uko_graph, active_strategies, detailed budget with model window breakdown). The command's output structure is fundamentally different from what the spec defines.

What Was Tested

Code-level analysis of src/cleveragents/cli/commands/project_context.py (the context_inspect command, lines 918-1161) against docs/specification.md §4108-4256.

Expected Behavior (from spec §4210-4256)

The JSON output must contain:

{
  "command": "project context inspect",
  "status": "ok",
  "data": {
    "inspection": {
      "project": "local/api-service",
      "view": "execute",
      "focus": ["uko-py:module/src.auth"],
      "breadth": 2,
      "depth": 3,
      "depth_name": "MEMBER_SUMMARY"
    },
    "uko_graph": {
      "root": "uko-py:module/src.auth",
      "root_depth": 9,
      "root_depth_name": "FULL_SOURCE",
      "root_tokens": 1240,
      "edges": [
        { "relation": "contains", "target": "uko-py:class/AuthHandler", "depth": 3, "tokens": 320 },
        ...
      ]
    },
    "active_strategies": [
      { "name": "breadth-depth-navigator", "quality": 0.85, "budget_pct": 0.45, "fragments": 4 },
      { "name": "semantic-embedding", "quality": 0.60, "budget_pct": 0.35, "fragments": 6 },
      { "name": "simple-keyword", "quality": 0.30, "budget_pct": 0.20, "fragments": 3 }
    ],
    "budget": {
      "model_window": 128000,
      "response_reserve": 4096,
      "tool_definitions": 2400,
      "system_prompt": 1200,
      "skeleton_reserve": 18046,
      "skeleton_ratio": 0.15,
      "available_budget": 102258,
      "used": 1990,
      "utilization": 0.019
    }
  }
}

The Rich output must show:

UKO Graph (N-hop neighborhood) with node hierarchy and edge relations
Active Strategies panel with quality scores and budget percentages
Budget panel with model window, response reserve, tool definitions, system prompt, skeleton reserve, available budget, and utilization

Actual Behavior

The command returns:

{
  "project": "...",
  "view": "all",
  "tier_metrics": { "hot_count": ..., "warm_count": ..., "cold_count": ... },
  "tier_budget": { "max_tokens_hot": ..., "max_decisions_warm": ..., "max_decisions_cold": ... },
  "project_fragments": { "total": ..., "by_tier": { "hot": ..., "warm": ..., "cold": ... } },
  "actor_visibility": { "strategize": ..., "execute": ..., "apply": ... },
  "acms_config": { ... },
  "phase_analysis": { ... },
  "fragments": [ ... ]
}

The Rich output shows tier metrics, tier budget, project fragments, actor visibility, and phase analysis — none of which are in the spec.

Missing from output:

inspection object with focus, breadth, depth, depth_name
uko_graph with root node, depth, tokens, and edges with relations
active_strategies with quality scores and budget percentages
budget with model window breakdown (model_window, response_reserve, tool_definitions, system_prompt, skeleton_reserve, skeleton_ratio, available_budget, used, utilization)

Code Location

src/cleveragents/cli/commands/project_context.py lines 918-1161 (context_inspect function)

Steps to Reproduce

Create a project: agents project add local/test-project
Run: agents project context inspect --format json local/test-project
Observe the output lacks uko_graph, active_strategies, and detailed budget fields

Severity

High — The command's output structure is completely different from the spec. Users and tooling expecting the spec-documented output will receive incompatible data. The UKO graph visualization (the primary debugging tool for context quality) is entirely absent.

Metadata

Branch: fix/context-inspect-output-structure
Commit Message: fix(cli): align context inspect output with spec — add uko_graph, active_strategies, budget fields
Parent Epic: #396

Subtasks

Add inspection object to output with focus, breadth, depth, depth_name
Add uko_graph to output: query UKO graph for focus nodes and return root + edges with relations
Add active_strategies to output: query strategy registry for enabled strategies with quality scores and budget percentages
Add detailed budget to output: include model_window, response_reserve, tool_definitions, system_prompt, skeleton_reserve, skeleton_ratio, available_budget, used, utilization
Update Rich output to show UKO Graph panel, Active Strategies panel, and detailed Budget panel
Add unit tests for the corrected output structure

Definition of Done

agents project context inspect --format json returns inspection, uko_graph, active_strategies, and budget fields matching the spec
Rich output shows UKO Graph, Active Strategies, and Budget panels
All tests pass with ≥97% coverage

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

## Summary `agents project context inspect` returns tier-based metrics (`tier_metrics`, `tier_budget`, `project_fragments`, `actor_visibility`, `phase_analysis`) instead of the spec-required ACMS inspection data (`uko_graph`, `active_strategies`, detailed `budget` with model window breakdown). The command's output structure is fundamentally different from what the spec defines. ## What Was Tested Code-level analysis of `src/cleveragents/cli/commands/project_context.py` (the `context_inspect` command, lines 918-1161) against `docs/specification.md` §4108-4256. ## Expected Behavior (from spec §4210-4256) The JSON output must contain: ```json { "command": "project context inspect", "status": "ok", "data": { "inspection": { "project": "local/api-service", "view": "execute", "focus": ["uko-py:module/src.auth"], "breadth": 2, "depth": 3, "depth_name": "MEMBER_SUMMARY" }, "uko_graph": { "root": "uko-py:module/src.auth", "root_depth": 9, "root_depth_name": "FULL_SOURCE", "root_tokens": 1240, "edges": [ { "relation": "contains", "target": "uko-py:class/AuthHandler", "depth": 3, "tokens": 320 }, ... ] }, "active_strategies": [ { "name": "breadth-depth-navigator", "quality": 0.85, "budget_pct": 0.45, "fragments": 4 }, { "name": "semantic-embedding", "quality": 0.60, "budget_pct": 0.35, "fragments": 6 }, { "name": "simple-keyword", "quality": 0.30, "budget_pct": 0.20, "fragments": 3 } ], "budget": { "model_window": 128000, "response_reserve": 4096, "tool_definitions": 2400, "system_prompt": 1200, "skeleton_reserve": 18046, "skeleton_ratio": 0.15, "available_budget": 102258, "used": 1990, "utilization": 0.019 } } } ``` The Rich output must show: - UKO Graph (N-hop neighborhood) with node hierarchy and edge relations - Active Strategies panel with quality scores and budget percentages - Budget panel with model window, response reserve, tool definitions, system prompt, skeleton reserve, available budget, and utilization ## Actual Behavior The command returns: ```json { "project": "...", "view": "all", "tier_metrics": { "hot_count": ..., "warm_count": ..., "cold_count": ... }, "tier_budget": { "max_tokens_hot": ..., "max_decisions_warm": ..., "max_decisions_cold": ... }, "project_fragments": { "total": ..., "by_tier": { "hot": ..., "warm": ..., "cold": ... } }, "actor_visibility": { "strategize": ..., "execute": ..., "apply": ... }, "acms_config": { ... }, "phase_analysis": { ... }, "fragments": [ ... ] } ``` The Rich output shows tier metrics, tier budget, project fragments, actor visibility, and phase analysis — none of which are in the spec. **Missing from output:** - `inspection` object with `focus`, `breadth`, `depth`, `depth_name` - `uko_graph` with root node, depth, tokens, and edges with relations - `active_strategies` with quality scores and budget percentages - `budget` with model window breakdown (model_window, response_reserve, tool_definitions, system_prompt, skeleton_reserve, skeleton_ratio, available_budget, used, utilization) ## Code Location `src/cleveragents/cli/commands/project_context.py` lines 918-1161 (`context_inspect` function) ## Steps to Reproduce 1. Create a project: `agents project add local/test-project` 2. Run: `agents project context inspect --format json local/test-project` 3. Observe the output lacks `uko_graph`, `active_strategies`, and detailed `budget` fields ## Severity **High** — The command's output structure is completely different from the spec. Users and tooling expecting the spec-documented output will receive incompatible data. The UKO graph visualization (the primary debugging tool for context quality) is entirely absent. ## Metadata - **Branch**: `fix/context-inspect-output-structure` - **Commit Message**: `fix(cli): align context inspect output with spec — add uko_graph, active_strategies, budget fields` - **Parent Epic**: #396 ## Subtasks - [ ] Add `inspection` object to output with `focus`, `breadth`, `depth`, `depth_name` - [ ] Add `uko_graph` to output: query UKO graph for focus nodes and return root + edges with relations - [ ] Add `active_strategies` to output: query strategy registry for enabled strategies with quality scores and budget percentages - [ ] Add detailed `budget` to output: include model_window, response_reserve, tool_definitions, system_prompt, skeleton_reserve, skeleton_ratio, available_budget, used, utilization - [ ] Update Rich output to show UKO Graph panel, Active Strategies panel, and detailed Budget panel - [ ] Add unit tests for the corrected output structure ## Definition of Done - `agents project context inspect --format json` returns `inspection`, `uko_graph`, `active_strategies`, and `budget` fields matching the spec - Rich output shows UKO Graph, Active Strategies, and Budget panels - All tests pass with ≥97% coverage --- **Automated by CleverAgents Bot** Supervisor: UAT Testing | Agent: ca-uat-tester

freemo commented

2026-04-03 18:40:59 +00:00

Author

Owner

Issue triaged by project owner:

State: Verified
MoSCoW: Should Have — Spec compliance or quality improvement that should be included in the milestone.

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

Issue triaged by project owner: - **State**: Verified - **MoSCoW**: Should Have — Spec compliance or quality improvement that should be included in the milestone. --- **Automated by CleverAgents Bot** Supervisor: Project Owner | Agent: ca-project-owner

freemo referenced this issue

2026-04-03 18:43:28 +00:00

[UAT-SUPERVISOR] Progress Report — Cycle 1571 — v3.7.0 #2516

freemo referenced this issue

2026-04-04 20:50:23 +00:00

[CA-AUTO] Project Owner — project-owner-1 — Session Tracker #2793

freemo added this to the v3.7.0 milestone

2026-04-05 05:07:07 +00:00