Commit a1a95f4
ci(065): D1 readiness waits for full tool catalog before scoring
The retrieval scorer was running against a partially-indexed instance: the
readiness probe passed at the first indexed tool (>=1 search result), so scoring
started before all 7 reference servers connected -> Recall@5 measured 0.387 vs
baseline threshold 0.631 (false regression).
Fix: poll /api/v1/tools until the catalog reaches the near-full count (~45 tools
across the 7 servers) and add a short settle for the index build, then score.
Verified locally end-to-end on a fully-indexed instance: Recall@1/3/5/10 =
0.418/0.560/0.681/0.791, Gate(recall_at_5) PASS (0.681 vs 0.631) — the baseline
is exactly reproducible. actionlint clean.
Related #555 datasets; MCP-742.
Co-Authored-By: Paperclip <noreply@paperclip.ing>1 parent 27b07cd commit a1a95f4
1 file changed
Lines changed: 13 additions & 9 deletions
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
151 | 151 | | |
152 | 152 | | |
153 | 153 | | |
| 154 | + | |
| 155 | + | |
| 156 | + | |
| 157 | + | |
| 158 | + | |
| 159 | + | |
154 | 160 | | |
| 161 | + | |
155 | 162 | | |
156 | 163 | | |
157 | 164 | | |
158 | 165 | | |
159 | 166 | | |
160 | | - | |
161 | | - | |
162 | | - | |
163 | | - | |
164 | | - | |
165 | | - | |
166 | | - | |
167 | | - | |
| 167 | + | |
| 168 | + | |
| 169 | + | |
| 170 | + | |
| 171 | + | |
168 | 172 | | |
169 | 173 | | |
170 | 174 | | |
171 | 175 | | |
172 | | - | |
| 176 | + | |
173 | 177 | | |
174 | 178 | | |
175 | 179 | | |
| |||
0 commit comments