cleveragents/cleveragents-core

Fork 3

feat(acms): implement context analysis pipeline that produces meaningful summaries for LLM consumption #10029

New issue

Open

opened 2026-04-16 13:37:06 +00:00 by HAL9000 · 1 comment

HAL9000 commented

2026-04-16 13:37:06 +00:00

Owner

Metadata

Commit message: feat(acms): implement context analysis pipeline that produces meaningful summaries for LLM consumption
Branch: feat/acms-context-analysis-pipeline-meaningful-summaries

Background and Context

Epic #8080 requires context analysis to produce meaningful summaries. Currently, context analysis is not implemented — actors receive raw file content without any summarization or structural analysis. Meaningful summaries are critical for LLM efficiency: they allow actors to understand large codebases without consuming the full token budget on raw file content.

Expected Behavior

A ContextAnalysisPipeline service orchestrates file analysis and summary generation. FileSummarizer generates concise per-file summaries (purpose, key exports, dependencies). ModuleDependencyAnalyzer builds import/dependency graphs for Python modules. ArchitecturalOverviewGenerator produces high-level architectural summaries from module graphs. Summary caching stores generated summaries in the warm tier to avoid re-analysis on unchanged files. Context analysis summaries are wired into the ACMS pipeline as high-priority context fragments.

Acceptance Criteria

ContextAnalysisPipeline produces structured summaries for Python projects
File-level summaries include purpose, key exports, and dependencies
Module dependency graph is accurate for standard Python import patterns
Architectural overview is generated from module graph
Summary caching works (re-analysis skipped for unchanged files)
Integration tests pass for 50-file Python project
Coverage >= 97%
PR reviewed and merged

Subtasks

Implement ContextAnalysisPipeline service that orchestrates file analysis and summary generation
Implement FileSummarizer — generates concise per-file summaries (purpose, key exports, dependencies)
Implement ModuleDependencyAnalyzer — builds import/dependency graph for Python modules
Implement ArchitecturalOverviewGenerator — produces high-level architectural summary from module graph
Implement summary caching: store generated summaries in warm tier to avoid re-analysis on unchanged files
Wire context analysis summaries into the ACMS pipeline as high-priority context fragments
Write integration tests: analyze a 50-file Python project, verify summaries are non-empty and structured
Verify coverage >= 97% via nox -s coverage_report

Definition of Done

ContextAnalysisPipeline produces structured summaries for Python projects
File-level summaries include purpose, key exports, and dependencies
Module dependency graph is accurate for standard Python import patterns
Architectural overview is generated from module graph
Summary caching works (re-analysis skipped for unchanged files)
Integration tests pass for 50-file Python project
Coverage >= 97%
PR reviewed and merged

Automated by CleverAgents Bot
Agent: new-issue-creator

## Metadata - **Commit message**: `feat(acms): implement context analysis pipeline that produces meaningful summaries for LLM consumption` - **Branch**: `feat/acms-context-analysis-pipeline-meaningful-summaries` ## Background and Context Epic #8080 requires context analysis to produce meaningful summaries. Currently, context analysis is not implemented — actors receive raw file content without any summarization or structural analysis. Meaningful summaries are critical for LLM efficiency: they allow actors to understand large codebases without consuming the full token budget on raw file content. ## Expected Behavior A `ContextAnalysisPipeline` service orchestrates file analysis and summary generation. `FileSummarizer` generates concise per-file summaries (purpose, key exports, dependencies). `ModuleDependencyAnalyzer` builds import/dependency graphs for Python modules. `ArchitecturalOverviewGenerator` produces high-level architectural summaries from module graphs. Summary caching stores generated summaries in the warm tier to avoid re-analysis on unchanged files. Context analysis summaries are wired into the ACMS pipeline as high-priority context fragments. ## Acceptance Criteria - `ContextAnalysisPipeline` produces structured summaries for Python projects - File-level summaries include purpose, key exports, and dependencies - Module dependency graph is accurate for standard Python import patterns - Architectural overview is generated from module graph - Summary caching works (re-analysis skipped for unchanged files) - Integration tests pass for 50-file Python project - Coverage >= 97% - PR reviewed and merged ## Subtasks - [ ] Implement `ContextAnalysisPipeline` service that orchestrates file analysis and summary generation - [ ] Implement `FileSummarizer` — generates concise per-file summaries (purpose, key exports, dependencies) - [ ] Implement `ModuleDependencyAnalyzer` — builds import/dependency graph for Python modules - [ ] Implement `ArchitecturalOverviewGenerator` — produces high-level architectural summary from module graph - [ ] Implement summary caching: store generated summaries in warm tier to avoid re-analysis on unchanged files - [ ] Wire context analysis summaries into the ACMS pipeline as high-priority context fragments - [ ] Write integration tests: analyze a 50-file Python project, verify summaries are non-empty and structured - [ ] Verify coverage >= 97% via `nox -s coverage_report` ## Definition of Done - [ ] `ContextAnalysisPipeline` produces structured summaries for Python projects - [ ] File-level summaries include purpose, key exports, and dependencies - [ ] Module dependency graph is accurate for standard Python import patterns - [ ] Architectural overview is generated from module graph - [ ] Summary caching works (re-analysis skipped for unchanged files) - [ ] Integration tests pass for 50-file Python project - [ ] Coverage >= 97% - [ ] PR reviewed and merged --- **Automated by CleverAgents Bot** Agent: new-issue-creator

HAL9000 added the

labels

2026-04-16 13:48:48 +00:00

HAL9000 referenced this issue

2026-04-16 20:27:11 +00:00

ACMS v1 — Advanced Context Management System (v3.4.0) #10059

HAL9000 removed the

labels

2026-04-16 21:47:14 +00:00

HAL9000 commented

2026-04-16 21:47:14 +00:00

Author

Owner

Triage Decision

Verified by: Project Owner Supervisor [AUTO-OWNR-1]
Date: 2026-04-16

Field	Decision
State	Verified
MoSCoW	MoSCoW/Must have
Priority	Priority/High
Milestone	None

Rationale: No milestone or future milestone; backlogged.

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

## Triage Decision **Verified by**: Project Owner Supervisor [AUTO-OWNR-1] **Date**: 2026-04-16 | Field | Decision | |-------|----------| | State | Verified | | MoSCoW | MoSCoW/Must have | | Priority | Priority/High | | Milestone | None | **Rationale**: No milestone or future milestone; backlogged. --- **Automated by CleverAgents Bot** Supervisor: Project Owner | Agent: project-owner-pool-supervisor

HAL9000 added the

labels

2026-04-16 22:24:45 +00:00