evandro/ForgeLM
1
0 Fork 0
Code Issues 1 Pull Requests Actions Packages Projects Releases Wiki Activity

chore: expand template benchmark coverage

Browse Source
This commit is contained in:
Evandro Fonseca Junior committed 2026-03-26 18:20:35 -03:00
1 parent bad2bb33a5
commit f96b42c356
5 files changed
+52 -2
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

autoresearch.md
+2
View File
@@ -42,3 +42,5 @@ and Kimi, while preserving a safe generic fallback for unknown models.
- `prepare_prompt()` is the cleanest insertion point for dynamic templates because both blocking and streaming paths already consume its rendered string.
- `ModelCatalog` currently resolves aliases only; it has no model-family metadata or template registry yet.
- The benchmark for this segment is a targeted ignored test suite that scores family detection/template rendering coverage for Qwen, Gemma, Llama, Kimi, and the generic fallback.
- Baseline run 7 scored only `20.0%` because just the generic fallback path passed; Qwen, Gemma, Llama, and Kimi were still rendered through the old generic formatter.
- Run 8 (`ceb83f2`) added family detection plus built-in template selection inside `compat.rs` and immediately raised coverage to `100.0%` (5/5 passing), making it the current best for segment 1.