| | 65 | |
| | 66 | == AI usage == |
| | 67 | |
| | 68 | AI was used in this phase and is logged in full, per the course rule for P1 onward. |
| | 69 | |
| | 70 | * '''Phase log:''' |
| | 71 | [https://github.com/StefanTrsunov/bp/blob/main/docs/P4-Prototype/PrototypeImplementationAIUsage.md PrototypeImplementationAIUsage.md] |
| | 72 | – service used, the bugs found and fixed, the test evidence, and what I decided myself. |
| | 73 | * '''Full conversation transcript:''' |
| | 74 | [https://github.com/StefanTrsunov/bp/blob/main/docs/P1-ConceptualModel/ERModelAIUsage.md ERModelAIUsage.md] |
| | 75 | – the same conversation produced the P1–P4 artefacts, so the complete prompt/response log is |
| | 76 | kept in one place. Direct links: |
| | 77 | [https://github.com/StefanTrsunov/bp/blob/main/docs/P1-ConceptualModel/ERModelAIUsage.md#session-1--2026-04-21 Session 1 – 2026-04-21], |
| | 78 | [https://github.com/StefanTrsunov/bp/blob/main/docs/P1-ConceptualModel/ERModelAIUsage.md#session-2--2026-08-06--2026-08-07 Session 2 – 2026-08-06/07]. |
| | 79 | |
| | 80 | '''Service:''' Claude Code (Anthropic), https://claude.com/claude-code – Claude subscription, |
| | 81 | model Claude Opus 4.7 (1M context). |
| | 82 | |
| | 83 | '''In short:''' session 1 rewrote the existing Chi/HTTP backend as the CLI prototype covering |
| | 84 | UC0001–UC0007 and added the market bot. Session 2 was a review pass I asked for, which found and |
| | 85 | fixed three bugs – a path-resolution bug that made the documented build instructions fail, an |
| | 86 | infinite loop at end of input, and an error check in the wrong order that misreported database |
| | 87 | failures as "Insufficient holding" – and replaced the read-modify-write holding update with a |
| | 88 | single `INSERT … ON CONFLICT DO UPDATE`. |