Back to corpus
architecturetechnical paper candidatescore 44
METAMORPHOSIS: Context-Aware Code Suggestions from Orbit Logs
METAMORPHOSIS mines historical Orbit data (prompt logs, session histories, noosphere connections, plans) to build a pattern model of developer behavior. It predicts what code actions, files, and tools the developer will need next based on:
Full HTML reader
Read the full artifact
Extracted abstract or opening context
METAMORPHOSIS mines historical Orbit data (prompt logs, session histories, noosphere connections, plans) to build a pattern model of developer behavior. It predicts what code actions, files, and tools the developer will need next based on:
- **Current project context** (which project, which files, git state) - **Session phase** (early exploration vs deep implementation) - **Historical co-occurrence patterns** (what actions typically follow what) - **Cross-project knowledge transfer** (patterns learned in one project apply to similar ones)
| Source | Path | Records | Content | |--------|------|---------|---------| | **Prompt Logs** | `prompt-logs/prompts-all.jsonl` | 2,355 | Every prompt with cwd, git context, session ID, timestamps | | **Session History** | `history.jsonl` | 884 | Display text, project, session grouping | | **Noosphere** | `noosphere/connections.json` | 145 nodes | Dreams, orbit contexts, plans with semantic connections | | **Plans** | `plans/` | 43+ | Architectural plans with status tracking | | **Project Map** | `orbit-project-map.json` | 8 projects | Project ID mappings | | **Per-Project Prompts** | `prompt-logs/projects/*/prompts.jsonl` | Varies | Project-scoped prompt sequences |
| Derived | Description | |---------|-------------| | **Action Sequences** | Ordered prompt chains within sessions | | **Project Fingerprints** | Characteristic action patterns per project | | **Transition Matrices** | Probability of action B following action A | | **Temporal Patterns** | Time-of-day and session-duration correlations | | **Keyword Clusters** | Groups of semantically related prompts |
### Stage 1: Data Ingestion - Parse all JSONL files into structured records - Normalize project paths to canonical names - Group prompts into sessions with temporal ordering - Extract git context (repo, branch, dirty state)
Promotion decision
What has to happen next
Promote into a technical note or architecture paper with implementation anchors.
Why this is not always a full paper yet
Corpus pages are public-safe readers for discovered workspace artifacts. They are not automatically final papers. A corpus item becomes a polished paper only after the editable source, evidence checkpoints, references, figures, render path, and release status are attached through the paper schema.