Rodin 67d835909f feat: add context budget system for LLM overflow (#19) ...

Adds a budget package that estimates token usage and progressively
trims context to fit within model-specific limits.

Trim order (least important first):
1. Language patterns
2. Repository conventions
3. Full file context
4. Diff (truncated as last resort)

When content is trimmed, a note is appended to the user prompt so
the LLM knows context was reduced.

- New budget package with Fit(), EstimateTokens(), LimitForModel()
- Model limit table (GPT-4.1: 128K, GPT-5: 200K, Claude: 200K)
- Refactored review/prompt.go: BuildSystemBase() and BuildUserMeta()
  extract non-trimmable content; old functions delegate to new ones
- main.go uses budget.Fit() instead of direct prompt assembly
- 7 unit tests covering all trim paths

Closes #19

2026-05-01 18:46:53 -07:00

..

formatter_test.go

Add unit tests, integration test, CI workflow, and conventions

2026-05-01 10:03:44 -07:00

formatter.go

Initial implementation: AI code review bot for Gitea

2026-05-01 09:42:45 -07:00

parser_test.go

Add unit tests, integration test, CI workflow, and conventions

2026-05-01 10:03:44 -07:00

parser.go

Initial implementation: AI code review bot for Gitea

2026-05-01 09:42:45 -07:00

prompt_test.go

feat: full file context + patterns-repo support

2026-05-01 12:11:49 -07:00

prompt.go

feat: add context budget system for LLM overflow (#19)

2026-05-01 18:46:53 -07:00