sweepai/sweep
120 source files scanned · 14 LLM call site(s) · ~7% of LLM spend looks recoverable (static heuristics · repo looks like an app)
[](https://tokenzero.sh/audit/sweepai/sweep)
Models referenced
claude-3-opus-20240229 ×1
Findings
| Severity | Where | Finding | Est. |
|---|---|---|---|
| medium | sweepai/core/prompts.py:995 | 4 static prompt template(s), ~1,424 tokens, and no caching directive anywhere in the repo Most call sites use providers with automatic prefix caching, which only pays off when these templates are sent as a byte-identical prefix: static template first, nothing volatile (dates, ids, user data) interpolated into it. Fix: Keep templates first and static; TokenZero adds a stable `prompt_cache_key` so related requests land on the same cache. | 12% |
| low | sweepai/utils/openai_proxy.py:262 | Tool definitions sent without a cache breakpoint Tool schemas render before the system prompt in the cached prefix. Without a breakpoint on the last tool they are billed in full on every call. Fix: TokenZero marks the last tool automatically; manually, add `cache_control` to the last tool definition. | 8% |
| info | sweepai/utils/openai_proxy.py:262 | Unrecognised model id "claude-3-opus-20240229" Not in the current pricing table: it may be retired or renamed. Retired models return errors or are silently remapped by some providers. Fix: Check the provider model list; TokenZero flags unpriced models in `X-TokenZero-Warning`. | 0% |
Fix all of it with one line
OPENAI_BASE_URL=https://tokenzero.sh/v1 ANTHROPIC_BASE_URL=https://tokenzero.sh
Keys pass through untouched. Cache formatting and exact caching are on by default; cascade routing stays opt-in. How it works