You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
cargo run --example export_graph # Generate reduction_graph.json for docs/paper builds
174
174
cargo run --example export_schemas # Generate problem schemas for docs/paper builds
175
+
make regenerate-fixtures # Regenerate example_db/fixtures/examples.json (slow, needs ILP)
175
176
make test clippy # Must pass
176
177
```
177
178
179
+
`make regenerate-fixtures` is required so the paper can load the new rule's example data from `src/example_db/fixtures/examples.json`. Without it, the `reduction-rule` entry in Step 5 will reference missing fixture data.
180
+
178
181
Structural and quality review is handled by the `review-pipeline` stage, not here. The run stage just needs to produce working code.
The review-implementation report should already include:
115
118
- Review Range: base SHA, head SHA
116
119
- Scope: review type (model/rule/generic), subject metadata
117
120
- Deterministic Checks: whitelist + completeness status
118
121
- Changed Files and Diff Stat
119
-
- Linked Issue Context
120
122
121
-
Both reports are reused for the rest of the skill — do not regenerate either.
123
+
The two expensive context calls are allowed exactly once each per top-level `review-pipeline` invocation. Both reports are reused for the rest of the skill — do not regenerate either.
122
124
123
125
Branch from the review-pipeline report:
124
126
-`Bundle status: empty` => the selected PR is no longer eligible; run `cd "$REPO_ROOT" && python3 scripts/pipeline_worktree.py cleanup --worktree "$WORKTREE_DIR"`, then for untargeted runs return to Step 0a, for explicit `PR` runs STOP
0 commit comments