The Working Set of a Coding Agent: Coherence Debt in Repository-Scale Tasks
Ranking
Overall
79
Content
95
Popularity
43
Observed public metrics from 1 member.
Merged summary
TL;DR - This study models repository-scale coding as maintaining a graph of coupled facts, with unavailable facts creating “coherence debt.” Across seven models and five harnesses, fact availability—not context distance or extra token spending—primarily determined success.
- Missing facts caused agents to fabricate files or guess values rather than leave work incomplete.
- Prompt-supplied facts worked equally well whether near or far from the relevant edit.
- Successful harnesses differed by over 10Ă— in token use because they reconstructed context at different rates.
- Stale conventions could be worse than absent guidance, while memorized repository knowledge weakened read-based success metrics.
Sources (1)
The Working Set of a Coding Agent: Coherence Debt in Repository-Scale Tasks
Public signals
Hugging Face upvotes 0
TL;DR - This study models repository-scale coding as maintaining a graph of coupled facts, with unavailable facts creating “coherence debt.” Across seven models and five harnesses, fact availability—not context distance or extra token spending—primarily determined success.
- Missing facts caused agents to fabricate files or guess values rather than leave work incomplete.
- Prompt-supplied facts worked equally well whether near or far from the relevant edit.
- Successful harnesses differed by over 10Ă— in token use because they reconstructed context at different rates.
- Stale conventions could be worse than absent guidance, while memorized repository knowledge weakened read-based success metrics.